Showing 1–50 of 88 results for author: Yao, G

VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding

Authors: Fan Zhang, Guangming Yao, Jinyang Wu, Hao Wu, Zheng Lian, Xinyu Geng, Jingdong Chen, Yi Yuan, Pheng-Ann Heng

Abstract: Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs). However, existing leading models have already achieved approximately 90% accuracy on the Video-MME leaderboard, suggesting that conventional single-turn video understanding tasks are becoming increasingly saturated and insufficient for assessing the intelligence of advanced MLLMs.… ▽ More Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs). However, existing leading models have already achieved approximately 90% accuracy on the Video-MME leaderboard, suggesting that conventional single-turn video understanding tasks are becoming increasingly saturated and insufficient for assessing the intelligence of advanced MLLMs. Towards this end, we introduce VideoGAIA, an agentic video understanding benchmark for general artificial intelligence (AI) assistants. Moving beyond one-shot video question answering, VideoGAIA formulates video understanding as a multi-turn, tool-augmented interaction process, where models must iteratively perceive videos, invoke external tools, gather complementary information, and integrate multimodal evidence across turns. VideoGAIA contains 271 model-human co-designed tasks covering diverse and complex real-world scenarios. Each video-question-answer instance is independently verified by three human experts to ensure both correctness and appropriate difficulty. All evaluated MLLMs, including frontier models such as GPT-5.5 and Kimi-K3, achieve less than 60% accuracy on VideoGAIA, highlighting its value as a high-quality and timely benchmark for evaluating next-generation MLLMs. We hope that VideoGAIA will facilitate the transition from conventional video understanding toward agentic video understanding. △ Less

Submitted 11 August, 2026; originally announced August 2026.

verdi: retrieval is not transfer for continual world model optimization

Authors: Junyu Wu, Shiqin Nie, Youyi Kou, Baohua Yin, Guocai Yao, Qingyu Chen, Jingheng Ma, Shiji Zhou, Hongyong Song, Mingchen Zhuge, Sen Cui, Changshui Zhang

Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research agents automate the optimization loop bu… ▽ More Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence. However, optimizing a pretrained world model toward a user-specified objective remains difficult: each campaign typically rediscovers optimization strategies from scratch, and the resulting knowledge rarely transfers to the next model. Existing research agents automate the optimization loop but treat successful strategies as directly reusable recipes, without principled safeguards for when transfer is appropriate. We argue instead that retrieval is not transfer: a strategy validated on one model is at best an optimization hypothesis for another, and becomes transferable knowledge only after target-side experimental valida- tion. Guided by this principle, we propose VERDI , a continual framework for evidence-licensed world model optimization. VERDI characterizes each world model through shared inference-time probes to construct an Optimization Fin- gerprint, retrieves relevant prior experience as ranked hypotheses, and validates every candidate under a frozen target-side verifier before admitting it as reusable evidence; contradictions among nearby fingerprints further trigger probe evolution, continually refining the diagnostic representation itself. Experiments on Ctrl-World, the Cosmos family, and RoboCoin show that VERDI reduces search cost by 68%, GPU cost by 69%, and negative transfer from 0.34 to 0.06, while predicting transfer outcomes with 83% sign accuracy. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 28pages, 13figures,conference

FeelWorld: Visuo-Tactile World Model for Hierarchical Contact Prediction and Planning

Authors: Wenxuan Ma, Chaofan Zhang, Chao Xue, Yinghao Cai, Guocai Yao, Shaowei Cui, Shuo Wang

Abstract: Humans plan physical interactions by imagining the possible outcomes of candidate actions. However, existing visual world models primarily capture appearance dynamics while overlooking the tactile states that govern contact-rich interactions, potentially producing imagined futures that appear visually plausible but violate physical dynamics. We introduce FeelWorld, a hierarchical visuo-tactile wor… ▽ More Humans plan physical interactions by imagining the possible outcomes of candidate actions. However, existing visual world models primarily capture appearance dynamics while overlooking the tactile states that govern contact-rich interactions, potentially producing imagined futures that appear visually plausible but violate physical dynamics. We introduce FeelWorld, a hierarchical visuo-tactile world model that jointly predicts future visual latents and three tactile states. FeelWorld organizes these states hierarchically as contact state, a 3D tactile latent that encodes force-related information, and slip state. These states are jointly predicted by a shared latent dynamics model with explicit supervision. To prevent irrelevant tactile signals during free-space motion from degrading visual prediction, we introduce a contact-gated asymmetric attention mechanism that maintains a visual-only prediction pathway before contact and enables joint visuo-tactile dynamics prediction during contact. The model is further trained with autoregressive rollouts and context noise injection to improve robustness to compounding errors. The predicted contact and slip states also support contact-aware CEM planning. Experiments on chip grasping, fruit grasping, and USB insertion show that FeelWorld reduces 10-step LPIPS from 0.084 to 0.058 and maintains an LPIPS that is 61% lower than that of the visual baseline after an 80-step autoregressive rollout. FeelWorld also achieves an average zero-shot planning success rate of 81.7%, providing an effective approach for incorporating tactile sensing into world models. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: 9 pages, 7 figures

LATTICE: Constraint-Directed Scheduling, Memory Planning, and Pipeline Refinement for NPUs

Authors: Runhao Liu, Minnan Pei, Fei Ding, Guangzhen Yao, You Li, Peng Xiao, Gang Li, Peng Zhang

Abstract: General-purpose NPUs execute fine-grained command DAGs across heterogeneous compute and memory-transfer engines backed by finite, explicitly managed on-chip memories. This execution model creates a directed dependency between scheduling and memory planning: different legal topological orders induce different lifetime overlap, placement opportunities, and spill behavior, while a materialized layout… ▽ More General-purpose NPUs execute fine-grained command DAGs across heterogeneous compute and memory-transfer engines backed by finite, explicitly managed on-chip memories. This execution model creates a directed dependency between scheduling and memory planning: different legal topological orders induce different lifetime overlap, placement opportunities, and spill behavior, while a materialized layout introduces physical-address reuse constraints absent from the input precedence DAG. Command order therefore shapes the feasible memory plan, and the realized plan in turn defines the legal space for subsequent timing refinement. We present LATTICE, a deterministic constraint-directed compiler pipeline. Memory-Pressure-Aware Topological Scheduling reshapes lifetime geometry before address binding; Deterministic Linear Repackaging materializes tiered placement, spill/reload events, and plan-induced reuse constraints; and Critical Path Enhancement recovers pipeline parallelism while preserving the selected memory plan. Every accepted schedule passes independent memory and timing verification. Across six artifact-provided command traces labeled as derived from a Da Vinci NPU flow, LATTICE achieves the best or tied-best result in all 24 evaluated workload-metric comparisons. Relative to the best evaluated baseline for each workload and metric, it reduces peak memory, extra DDR traffic, spill count, and modeled makespan by 18.3% lower, 20.4% lower, 14.1% lower, and 16.3% lower, respectively. Plan-preserving CPE further reduces makespan by 12.1% over Freeze while leaving placement and memory traffic unchanged, establishing the static memory plan as a verifiable scheduling contract between memory planning and pipeline optimization. △ Less

Submitted 4 August, 2026; v1 submitted 19 July, 2026; originally announced July 2026.

Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning

Authors: Zishuo Li, Bowen Yang, Changtao Miao, Kai Zhu, Hao Chen, Qingze Guan, Zhengxing Wu, Wanke Zhan, Yang Sun, Zhiyi Huang, Zitong Shan, Zhenchao Jin, Jiadong Hong, Taowen Wang, Yushi Feng, You Liu, Yibo Wang, Yifan Yang, Zhaowen Zhou, Man Luo, Hao Cheng, Bo Zhang, Jianshu Li, Jiansheng Cai, Guocai Yao , et al. (7 additional authors not shown)

Abstract: Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, community-oriented egocentric manipulation dataset and toolchain spanning the full pipeline from smartphone capture to model… ▽ More Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-level structured annotations, and reusable tools for robot learning. We present Open-AoE, an open, community-oriented egocentric manipulation dataset and toolchain spanning the full pipeline from smartphone capture to model training. Its first release contains approximately 2,000 hours of manipulation video collected in natural environments by 500+ contributors using 400+ smartphones. The dataset provides text annotations, MANO-based hand poses, camera trajectories, and temporally localized atomic actions. Open-AoE further includes a data processing pipeline that transforms raw recordings into structured samples through temporal action segmentation, semantic annotation, hand reconstruction, and camera trajectory reconstruction. Meanwhile, we provide a separate downstream toolchain supports visualization, cross-embodiment retargeting, model-specific data conversion, and training recipes for VLA policies, WAMs, and World Models. By integrating scalable capture, structured processing, and downstream adaptation, Open-AoE reduces the barriers to both data contribution and reuse, providing practical open infrastructure for embodied model training, human-to-robot transfer, and world modeling. △ Less

Submitted 18 July, 2026; v1 submitted 15 July, 2026; originally announced July 2026.

Orca: The World is in Your Mind

Authors: Yihao Wang, Yuheng Ji, Mingyu Cao, Yanqing Shen, Runze Xiao, Huaihai Lyu, Senwei Xie, Euan Liu, Klara Tian, Tianfeng Long, Yichi Zhang, Zhengliang Cai, Ruike Chen, Jifan Zhao, Ruochuan Shi, Zihan Tang, Jing Lyu, Wenxing Tan, Ningbo Zhang, Yangtao Hu, Yuming Gao, Xiansheng Chen, Junkai Zhao, Congsheng Xu, Boan Zhu , et al. (32 additional authors not shown)

Abstract: We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward un… ▽ More We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than optimizing isolated next-token, next-frame, or next-action prediction, we are centered on Next-State-Prediction modeling, offering a unified state-transition modeling route toward understanding, predicting, and acting upon the world. Orca learns through two complementary paradigms: unconscious learning captures dense natural state transitions from continuous videos, and conscious learning models sparse meaningful state transitions by language-described events and VQA supervision. For pre-training, we construct a large-scale world-learning inventory data, including 125K hours of video data and 160M event annotations. After pre-training, Orca learns a unified world latent space. To examine whether the learned latent supports downstream, we evaluate it by three representative downstream readouts: text generation, image prediction, and embodied action generation. Orca's backbone is frozen, and only the lightweight modality-specific decoders are trainable. Experiments show the scalability of the proposed paradigm and verify that stronger world latent enables stronger downstream readouts. Orca outperforms similar-sized specialized baselines. These results show that Orca, as a general world foundation model, presents a promising approach to understanding, predicting, and acting upon the world. Finally, we discuss the current limitations, aiming to provide useful insights and inspiration for the community. △ Less

Submitted 17 July, 2026; v1 submitted 29 June, 2026; originally announced June 2026.

Comments: Project page: https://orca-wm.github.io/

LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models

Authors: Rongxu Cui, Zongzheng Zhang, Jingrui Pang, Haohan Chi, Jinbang Guo, Saining Zhang, Shaoxuan Xie, Xin Jin, Yao Mu, Jiaolong Yang, Guocai Yao, Xianyuan Zhan, Ya-Qin Zhang, Hao Zhao

Abstract: Despite the impressive manipulation capabilities of Vision-Language-Action (VLA) models, their operational safety under strict constraints remains largely unverified. To address this, we introduce a parametric safety benchmark to procedurally generate safety-critical scenarios with comprehensive stochasticity. To overcome the scalability bottlenecks of human teleoperation, we develop a novel keypo… ▽ More Despite the impressive manipulation capabilities of Vision-Language-Action (VLA) models, their operational safety under strict constraints remains largely unverified. To address this, we introduce a parametric safety benchmark to procedurally generate safety-critical scenarios with comprehensive stochasticity. To overcome the scalability bottlenecks of human teleoperation, we develop a novel keypose-driven data generation pipeline. Leveraging this infrastructure, we curate a large-scale dataset of 19,664 strictly collision-free demonstrations with extensive domain randomization. We then conduct a systematic cross-paradigm evaluation of eight VLA and two embodied foundation models. Our analysis reveals a critical generalization-safety tension: although high-diversity training fosters safer trajectories, task success remains fundamentally bottlenecked by sub-optimal trajectory synthesis and semantic misalignment. By providing a scalable pipeline, a robust dataset, and profound failure-mode insights, LIBERO-Safety establishes a crucial foundation for developing safe and reliable VLA models. △ Less

Submitted 26 June, 2026; v1 submitted 22 June, 2026; originally announced June 2026.

Comments: Accepted by ECCV 2026, Project Page: https://libero-safety.github.io/

ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies

Authors: Zenan Wu, Bingqing Wei, Lu Liu, Zheqi He, Xi Wang, Jiakang Liu, Zehui Li, Guocai Yao, Jing-Shu Zheng, Xi Yang, Yongtao Wang

Abstract: Generalist manipulation policies are increasingly presented as foundation models for robotic control, but their real-world generalization remains difficult to diagnose. A policy may succeed on demonstrated tasks while still failing to execute fine-grained atomic skills or recombine learned skills in new task structures. We introduce \textbf{ATOM-Bench}, a real-world benchmark for evaluating both a… ▽ More Generalist manipulation policies are increasingly presented as foundation models for robotic control, but their real-world generalization remains difficult to diagnose. A policy may succeed on demonstrated tasks while still failing to execute fine-grained atomic skills or recombine learned skills in new task structures. We introduce \textbf{ATOM-Bench}, a real-world benchmark for evaluating both atomic skills and compositional generalization in manipulation policies. ATOM-Bench factorizes tabletop manipulation into motor atoms and instruction atoms, and contains 30 atomic tasks and 24 held-out compositional tasks across paired single-arm and dual-arm robot tracks. We collect 3,000 human demonstrations for atomic fine-tuning and release both the demonstration data and evaluation rollout data to support reproducible real-world evaluation. Policies are fine-tuned on atomic tasks and evaluated on both atomic skill acquisition and held-out compositional tasks. We further introduce Atomic Score (AS) and Compositional Failure Share (CFS) to distinguish failures caused by weak atomic skills from failures caused by limited compositional reuse. Through 2,700 physical rollouts on five representative manipulation policies, we find that current policies can acquire simple instruction-grounding skills, but still struggle with fine-grained motor atoms, counting, and logical filtering. More importantly, strong atomic performance does not reliably transfer to held-out compositional tasks. ATOM-Bench provides a diagnostic testbed for studying whether failures arise from weak motor execution, poor instruction grounding, or limited compositional reuse. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Comments: Homepage: https://flageval-baai.github.io/AtomBenchPage

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

Authors: Cong Chen, Guo Gan, Kaixiang Ji, ZhaoYang Zhang, Zhen Yang, Guangming Yao, Hao Chen, Jingdong Chen, Yi Yuan, Chunhua Shen

Abstract: Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a H… ▽ More Current Vision-Language Models struggle with hours-long videos because processing full-length visual sequences induces prohibitive token explosion and attention dilution. To overcome this, we introduce MemDreamer to decouple perception and reasoning, shifting long-video understanding into an agentic exploration process. As a plug-and-play framework, it incrementally streams videos to construct a Hierarchical Graph Memory, a top-down three-tier architecture for semantic abstraction, anchored by a foundational graph capturing spatiotemporal and causal relations. During inference, the reasoning model employs agentic tool-augmented retrieval, navigating hierarchies, searching nodes, and traversing logical edges via an Observation-Reason-Action loop. Experiments show MemDreamer achieves SOTA results across four mainstream benchmarks, narrowing the gap with human experts to only 3.7 points. It constrains the reasoning context window to merely 2% of full-context ingestion while delivering a 12.5 point absolute accuracy gain. Furthermore, statistical analysis uncovers a strong positive linear correlation between an VLM's performance on logic reasoning and long-video understanding benchmarks, establishing agentic capability scaling as a new paradigm for multimodal comprehension. △ Less

Submitted 24 June, 2026; v1 submitted 5 June, 2026; originally announced June 2026.

FederatedSkill: Federated Learning for Agentic Skill Evolution

Authors: Jingbo Yang, Guanyu Yao, Yang Zhang, Ramana Rao Kompella, Gaowen Liu, Shiyu Chang

Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement. However, isolated single-user task streams lack the diversity required to build comprehensive skills. While cross-user collaboration can overcome this data bottleneck, current trajectory-sharing approaches compromise user privacy and impose a uniform global l… ▽ More Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement. However, isolated single-user task streams lack the diversity required to build comprehensive skills. While cross-user collaboration can overcome this data bottleneck, current trajectory-sharing approaches compromise user privacy and impose a uniform global library that fails to accommodate client heterogeneity. We introduce FederatedSkill, a privacy-preserving framework for collaborative agent evolution. Moving beyond raw trajectory sharing, FederatedSkill utilizes semantic skill diffs, structured patches over local libraries, as the fundamental unit of communication. On the server side, an evolution agent aggregates these patches to dynamically model client-specific capability boundaries, facilitating strictly personalized skill evolution rather than a suboptimal global average. Evaluated across 20 distinct agent task families, FederatedSkill demonstrates substantial gains over self-evolving baselines, achieving up to a 44.4% increase in success rate and a 37.5% reduction in computational cost. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

Authors: Zhenyu Yu, Yangchen Zeng, Chunlei Meng, Guangzhen Yao, Shuigeng Zhou

Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these works by introducing Mirage, a representation-level auditing framework that comprises four complementary diagnostics: Linear probe recovery (LPR), centered kernel alignment (CKA), feature separability scoring, and laye… ▽ More Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these works by introducing Mirage, a representation-level auditing framework that comprises four complementary diagnostics: Linear probe recovery (LPR), centered kernel alignment (CKA), feature separability scoring, and layer-wise recovery analysis. Extensive experiments across seven datasets and seven baseline methods following recent VFL unlearning protocols reveal three key findings: (1) Forgetting gap: methods that pass output-level certification still retain substantial class structure in their representations, with LPR exceeding the retrained baseline by up to 15.4 points; CKA shows that these models remain structurally closer to the original than to the retrained reference, while separability scores indicate persistent geometric discrimination. (2) Unlearning trilemma: no existing method simultaneously achieves high utility, output-level forgetting, and representation-level forgetting. (3) Class-sample asymmetry: class-level forgetting leaves strong representational traces (LPR exceeding 96 percent on several datasets), whereas sample-level forgetting is indistinguishable from chance (LPR is approximately 50 percent); layer-wise analysis further shows that residual class information persists across network depths. These findings call for representation-aware evaluation standards in federated unlearning research. Code is publicly available at https://github.com/YuZhenyuLindy/Mirage. △ Less

Submitted 26 June, 2026; v1 submitted 19 May, 2026; originally announced May 2026.

Dexora: Open-source VLA for High-DoF Bimanual Dexterity

Authors: Zongzheng Zhang, Jingrui Pang, Zhuo Yang, Kun Li, Minwen Liao, Saining Zhang, Guoxuan Chi, Jinbang Guo, Huan-ang Gao, Modi Shi, Dongyun Ge, Yao Mu, Jiayuan Gu, Rui Chen, Hao Dong, Huazhe Xu, Li Yi, Yixin Zhu, Hang Zhao, Pengwei Wang, Shanghang Zhang, Guocai Yao, Jianyu Chen, Hongyang Li, Hao Zhao

Abstract: Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduc… ▽ More Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper control or single-arm dexterous hand manipulation. While low-dimensional gripper control can often be handled with simpler methods, high-dimensional dexterous hand control benefits greatly from full end-to-end VLA learning. In this work, we introduce Dexora, the first open-source VLA system that natively targets dual-arm, dual-hand high-DoF manipulation. We design a hybrid teleoperation pipeline that decouples gross arm kinematics (captured with a custom exoskeleton backpack) from fine finger motion (markerless hand tracking via Apple Vision Pro), and that drives both a physical dual-arm dual-hand platform and an identical MuJoCo digital twin. Using that interface, we assemble a large training corpus: an embodiment-matched synthetic corpus (100K simulated trajectories, 6.5M frames) and a real-world dataset of 10K teleoperated episodes (2.92M frames). To mitigate noisy teleoperation demonstrations, we propose a data-quality-aware training recipe: an offline discriminator provides clip-level weights for diffusion-transformer policy training, down-weighting low-quality demonstrations. Empirically, Dexora outperforms competitive VLA baselines on both basic and dexterous benchmarks (e.g., average dexterous success 66.7% vs. 51.7%), attains 90% success on basic tasks, and shows robust out-of-distribution and cross-embodiment generalization. Ablations confirm the importance of real data and the discriminator for dexterity. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: Accpeted by ICRA 2026

EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning

Authors: Zeyu Wang, Chang Liu, Eduardus Tjitrahardja, Yuntao Wang, Borislav Pavlov, Fangfei Gou, Jose Manuel Davila, Dai Shi, Ran Xu, Yue Pan, Jiayi Tan, Shuting Chang, Qi Wang, Jinzhao Li, Jiacheng Hua, Yifei Huang, Jingwei Sun, Yu Zhang, Liuxin Zhang, Guocai Yao, Jia Jia, Yin Li, Qianying Wang, Yuanchun Shi, Miao Liu

Abstract: Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI assistant experiences, remains largely overlooked. In this work, we introduce EgoIntrospect, the first egocentric dataset captured in user-driven scenarios with self-annotations that explicitly reveal users' interactive intentions with AI assistants… ▽ More Despite extensive efforts on egocentric video datasets and benchmarks, understanding users' internal states, which is crucial for enabling seamless AI assistant experiences, remains largely overlooked. In this work, we introduce EgoIntrospect, the first egocentric dataset captured in user-driven scenarios with self-annotations that explicitly reveal users' interactive intentions with AI assistants. EgoIntrospect was collected using a cross-device setup, providing synchronized video, audio, gaze, motion, and physiological signals. It consists of 180 hours of recordings from 60 subjects, with an average recording duration of 3 hours per subject. Leveraging EgoIntrospect, we formalize a suite of tasks centered on user internal states, including affective experience, interactive intent, and cognitive memory. We further process the annotations to construct benchmarks that evaluate the ability of modern multimodal large language models to reason about users' internal states from egocentric observations. Experiments on our benchmark suggest that existing multimodal large language models struggle to effectively leverage multimodal signals to infer users' subjective internal states. The dataset and annotations will be made publicly available to advance research in egocentric vision and wearable AI assistants. Project page: https://ego-introspect.github.io/ △ Less

Submitted 17 May, 2026; originally announced May 2026.

CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems

Authors: Jingbo Yang, Guanyu Yao, Bairu Hou, Xinghan Yang, Nikolai Glushnev, Iwona Bialynicka-Birula, Duo Ding, Shiyu Chang

Abstract: As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge is a promising solution for scalable evaluation, the reliability of these judges in detecting specific policy violations remains largely unexplored. This gap is… ▽ More As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge is a promising solution for scalable evaluation, the reliability of these judges in detecting specific policy violations remains largely unexplored. This gap is primarily due to the lack of a systematic data generation method, which has been hindered by the extensive cost of fine-grained human annotation and the difficulty of synthesizing realistic agent violations. In this paper, we introduce CompliBench, a novel benchmark designed to evaluate the ability of LLM judges to detect and localize guideline violations in multi-turn dialogues. To overcome data scarcity, we develop a scalable, automated data generation pipeline that simulates user-agent interactions. Our controllable flaw injection process automatically yields precise ground-truth labels for the violated guideline and the exact conversation turn, while an adversarial search method ensures these introduced perturbations are highly challenging. Our comprehensive evaluation reveals that current state-of-the-art proprietary LLMs struggle significantly with this task. In addition, we demonstrate that a small-scale judge model fine-tuned on our synthesized data outperforms leading LLMs and generalizes well to unseen business domains, highlighting our pipeline as an effective foundation for training robust generative reward models. △ Less

Submitted 14 April, 2026; originally announced April 2026.

OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction

Authors: Shaqi Luo, Yuanyuan Li, Youhao Hu, Chenhao Yu, Chaoran Xu, Jiachen Zhang, Guocai Yao, Tiejun Huang, Ran He, Zhongyuan Wang

Abstract: UMI-style interfaces enable scalable robot learning, but existing systems remain largely visuomotor, relying primarily on RGB observations and trajectory while providing only limited access to physical interaction signals. This becomes a fundamental limitation in contact-rich manipulation, where success depends on contact dynamics such as tactile interaction, internal grasping force, and external… ▽ More UMI-style interfaces enable scalable robot learning, but existing systems remain largely visuomotor, relying primarily on RGB observations and trajectory while providing only limited access to physical interaction signals. This becomes a fundamental limitation in contact-rich manipulation, where success depends on contact dynamics such as tactile interaction, internal grasping force, and external interaction wrench that are difficult to infer from vision alone. We present OmniUMI, a unified framework for physically grounded robot learning via human-aligned multimodal interaction. OmniUMI synchronously captures RGB, depth, trajectory, tactile sensing, internal grasping force, and external interaction wrench within a compact handheld system, while maintaining collection--deployment consistency through a shared embodiment design. To support human-aligned demonstration, OmniUMI enables natural perception and modulation of internal grasping force, external interaction wrench, and tactile interaction through bilateral gripper feedback and the handheld embodiment. Built on this interface, we extend diffusion policy with visual, tactile, and force-related observations, and deploy the learned policy through impedance-based execution for unified regulation of motion and contact behavior. Experiments demonstrate reliable sensing and strong downstream performance on force-sensitive pick-and-place, interactive surface erasing, and tactile-informed selective release. Overall, OmniUMI combines physically grounded multimodal data acquisition with human-aligned interaction, providing a scalable foundation for learning contact-rich manipulation. △ Less

Submitted 5 May, 2026; v1 submitted 12 April, 2026; originally announced April 2026.

FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation

Authors: Liuzhou Zhang, Zeyu Zhang, Biao Wu, Luyao Tang, Zirui Song, Hongyang He, Renda Han, Guangzhen Yao, Huacan Wang, Ronghao Chen, Xiuying Chen, Guan Huang, Zheng Zhu

Abstract: Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need… ▽ More Sign language plays a crucial role in bridging communication gaps between the deaf and hard-of-hearing communities. However, existing sign language video generation models often rely on complex intermediate representations, which limits their flexibility and efficiency. In this work, we propose a novel pose-free framework for real-time sign language video generation. Our method eliminates the need for intermediate pose representations by directly mapping natural language text to sign language videos using a diffusion-based approach. We introduce two key innovations: (1) a pose-free generative model based on the a state-of-the-art diffusion backbone, which learns implicit text-to-gesture alignments without pose estimation, and (2) a Trainable Sliding Tile Attention (T-STA) mechanism that accelerates inference by exploiting spatio-temporal locality patterns. Unlike previous training-free sparsity approaches, T-STA integrates trainable sparsity into both training and inference, ensuring consistency and eliminating the train-test gap. This approach significantly reduces computational overhead while maintaining high generation quality, making real-time deployment feasible. Our method increases video generation speed by 3.07x without compromising video quality. Our contributions open new avenues for real-time, high-quality, pose-free sign language synthesis, with potential applications in inclusive communication tools for diverse communities. Code: https://github.com/AIGeeksGroup/FlashSign. △ Less

Submitted 29 March, 2026; originally announced March 2026.

FG-CLTP: Fine-Grained Contrastive Language Tactile Pretraining for Robotic Manipulation

Authors: Wenxuan Ma, Chaofan Zhang, Yinghao Cai, Guocai Yao, Shaowei Cui, Shuo Wang

Abstract: Recent advancements in integrating tactile sensing into vision-language-action (VLA) models have demonstrated transformative potential for robotic perception. However, existing tactile representations predominantly rely on qualitative descriptors (e.g., texture), neglecting quantitative contact states such as force magnitude, contact geometry, and principal axis orientation, which are indispensabl… ▽ More Recent advancements in integrating tactile sensing into vision-language-action (VLA) models have demonstrated transformative potential for robotic perception. However, existing tactile representations predominantly rely on qualitative descriptors (e.g., texture), neglecting quantitative contact states such as force magnitude, contact geometry, and principal axis orientation, which are indispensable for fine-grained manipulation. To bridge this gap, we propose FG-CLTP, a fine-grained contrastive language tactile pretraining framework. We first introduce a novel dataset comprising over 100k tactile 3D point cloud-language pairs that explicitly capture multidimensional contact states from the sensor's perspective. We then implement a discretized numerical tokenization mechanism to achieve quantitative-semantic alignment, effectively injecting explicit physical metrics into the multimodal feature space. The proposed FG-CLTP model yields a 95.9% classification accuracy and reduces the regression error (MAE) by 52.6% compared to state-of-the-art methods. Furthermore, the integration of 3D point cloud representations establishes a sensor-agnostic foundation with a minimal sim-to-real gap of 3.5%. Building upon this fine-grained representation, we develop a 3D tactile-language-action (3D-TLA) architecture driven by a flow matching policy to enable multimodal reasoning and control. Extensive experiments demonstrate that our framework significantly outperforms strong baselines in contact-rich manipulation tasks, providing a robust and generalizable foundation for tactile-language-action models. △ Less

Submitted 11 March, 2026; originally announced March 2026.

Comments: 9 pages, 6 figures

\$OneMillion-Bench: How Far are Language Agents from Human Experts?

Authors: Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen, Kaiyuan Chen, Tiliang Duan, Jiayun Dong, Xiaobo Hu, Zixia Jia, Yang Liu, Tao Peng, Yixin Ren, Ran Tian, Zaiyuan Wang, Yanglihong Xiao, Gang Yao, Lingyue Yin, Ge Zhang, Chun Zhang, Jianpeng Jiao, Zilong Zheng, Yuan Gong

Abstract: As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands. To this end, we introduce \$OneMillion-Bench \$OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare… ▽ More As language models (LMs) evolve from chat assistants to long-horizon agents capable of multi-step reasoning and tool use, existing benchmarks remain largely confined to structured or exam-style tasks that fall short of real-world professional demands. To this end, we introduce \$OneMillion-Bench \$OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios. Unlike prior work, the benchmark requires retrieving authoritative sources, resolving conflicting evidence, applying domain-specific rules, and making constraint decisions, where correctness depends as much on the reasoning process as the final answer. We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents. Together, \$OneMillion-Bench provides a unified testbed for assessing agentic reliability, professional depth, and practical readiness in domain-intensive scenarios. △ Less

Submitted 9 March, 2026; originally announced March 2026.

Comments: 39 pages, 9 figures, 8 tables

AoE: Always-on Egocentric Human Video Collection for Embodied AI

Authors: Bowen Yang, Zishuo Li, Yang Sun, Changtao Miao, Yifan Yang, Man Luo, Xiaotong Yan, Feng Jiang, Jinchuan Shi, Yankai Fu, Ning Chen, Junkai Zhao, Pengwei Wang, Guocai Yao, Shanghang Zhang, Hao Chen, Zhe Li, Kai Zhu

Abstract: Embodied foundation models require large-scale, high-quality real-world interaction data for pre-training and scaling. However, existing data collection methods suffer from high infrastructure costs, complex hardware dependencies, and limited interaction scope, making scalable expansion challenging. In fact, humans themselves are ideal physically embodied agents. Therefore, obtaining egocentric re… ▽ More Embodied foundation models require large-scale, high-quality real-world interaction data for pre-training and scaling. However, existing data collection methods suffer from high infrastructure costs, complex hardware dependencies, and limited interaction scope, making scalable expansion challenging. In fact, humans themselves are ideal physically embodied agents. Therefore, obtaining egocentric real-world interaction data from globally distributed "human agents" offers advantages of low cost and sustainability. To this end, we propose the Always-on Egocentric (AoE) data collection system, which aims to simplify hardware dependencies by leveraging humans themselves and their smartphones, enabling low-cost, highly efficient, and scene-agnostic real-world interaction data collection to address the challenge of data scarcity. Specifically, we first employ an ergonomic neck-mounted smartphone holder to enable low-barrier, large-scale egocentric data collection through a cloud-edge collaborative architecture. Second, we develop a cross-platform mobile APP that leverages on-device compute for real-time processing, while the cloud hosts automated labeling and filtering pipelines that transform raw videos into high-quality training data. Finally, the AoE system supports distributed Ego video data collection by anyone, anytime, and anywhere. We evaluate AoE on data preprocessing quality and downstream tasks, demonstrating that high-quality egocentric data significantly boosts real-world generalization. △ Less

Submitted 1 March, 2026; v1 submitted 27 February, 2026; originally announced February 2026.

Affordance-Graphed Task Worlds: Self-Evolving Task Generation for Scalable Embodied Learning

Authors: Xiang Liu, Sen Cui, Guocai Yao, Zhong Cao, Jingheng Ma, Min Zhang, Changshui Zhang

Abstract: Training robotic policies directly in the real world is expensive and unscalable. Although generative simulation enables large-scale data synthesis, current approaches often fail to generate logically coherent long-horizon tasks and struggle with dynamic physical uncertainties due to open-loop execution. To address these challenges, we propose Affordance-Graphed Task Worlds (AGT-World), a unified… ▽ More Training robotic policies directly in the real world is expensive and unscalable. Although generative simulation enables large-scale data synthesis, current approaches often fail to generate logically coherent long-horizon tasks and struggle with dynamic physical uncertainties due to open-loop execution. To address these challenges, we propose Affordance-Graphed Task Worlds (AGT-World), a unified framework that autonomously constructs interactive simulated environments and corresponding robot task policies based on real-world observations. Unlike methods relying on random proposals or static replication, AGT-World formalizes the task space as a structured graph, enabling the precise, hierarchical decomposition of complex goals into theoretically grounded atomic primitives. Furthermore, we introduce a Self-Evolution mechanism with hybrid feedback to autonomously refine policies, combining Vision-Language Model reasoning and geometric verification. Extensive experiments demonstrate that our method significantly outperforms in success rates and generalization, achieving a self-improving cycle of proposal, execution, and correction for scalable robot learning. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Scaling World Model for Hierarchical Manipulation Policies

Authors: Qian Long, Yueze Wang, Jiaxi Song, Junbo Zhang, Peiyan Li, Wenxuan Wang, Yuqi Wang, Haoyang Li, Shaoxuan Xie, Guocai Yao, Hanbo Zhang, Xinlong Wang, Zhongyuan Wang, Xuguang Lan, Huaping Liu, Xinghang Li

Abstract: Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework \our{} that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsua… ▽ More Vision-Language-Action (VLA) models are promising for generalist robot manipulation but remain brittle in out-of-distribution (OOD) settings, especially with limited real-robot data. To resolve the generalization bottleneck, we introduce a hierarchical Vision-Language-Action framework \our{} that leverages the generalization of large-scale pre-trained world model for robust and generalizable VIsual Subgoal TAsk decomposition VISTA. Our hierarchical framework \our{} consists of a world model as the high-level planner and a VLA as the low-level executor. The high-level world model first divides manipulation tasks into subtask sequences with goal images, and the low-level policy follows the textual and visual guidance to generate action sequences. Compared to raw textual goal specification, these synthesized goal images provide visually and physically grounded details for low-level policies, making it feasible to generalize across unseen objects and novel scenarios. We validate both visual goal synthesis and our hierarchical VLA policies in massive out-of-distribution scenarios, and the performance of the same-structured VLA in novel scenarios could boost from 14% to 69% with the guidance generated by the world model. Results demonstrate that our method outperforms previous baselines with a clear margin, particularly in out-of-distribution scenarios. Project page: \href{https://vista-wm.github.io/}{https://vista-wm.github.io} △ Less

Submitted 12 February, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception

Authors: Ruoxuan Feng, Yuxuan Zhou, Siyu Mei, Dongzhan Zhou, Pengwei Wang, Shaowei Cui, Bin Fang, Guocai Yao, Di Hu

Abstract: Real-world contact-rich manipulation demands robots to perceive temporal tactile feedback, capture subtle surface deformations, and reason about object properties as well as force dynamics. Although optical tactile sensors are uniquely capable of providing such rich information, existing tactile datasets and models remain limited. These resources primarily focus on object-level attributes (e.g., m… ▽ More Real-world contact-rich manipulation demands robots to perceive temporal tactile feedback, capture subtle surface deformations, and reason about object properties as well as force dynamics. Although optical tactile sensors are uniquely capable of providing such rich information, existing tactile datasets and models remain limited. These resources primarily focus on object-level attributes (e.g., material) while largely overlooking fine-grained tactile temporal dynamics during physical interactions. We consider that advancing dynamic tactile perception requires a systematic hierarchy of dynamic perception capabilities to guide both data collection and model design. To address the lack of tactile data with rich dynamic information, we present ToucHD, a large-scale hierarchical tactile dataset spanning tactile atomic actions, real-world manipulations, and touch-force paired data. Beyond scale, ToucHD establishes a comprehensive tactile dynamic data ecosystem that explicitly supports hierarchical perception capabilities from the data perspective. Building on it, we propose AnyTouch 2, a general tactile representation learning framework for diverse optical tactile sensors that unifies object-level understanding with fine-grained, force-aware dynamic perception. The framework captures both pixel-level and action-specific deformations across frames, while explicitly modeling physical force dynamics, thereby learning multi-level dynamic perception capabilities from the model perspective. We evaluate our model on benchmarks that covers static object properties and dynamic physical attributes, as well as real-world manipulation tasks spanning multiple tiers of dynamic perception capabilities-from basic object-level understanding to force-aware dexterous manipulation. Experimental results demonstrate consistent and strong performance across sensors and tasks. △ Less

Submitted 10 February, 2026; originally announced February 2026.

Comments: Accepted by ICLR 2026

DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter

Authors: Xukun Li, Yu Sun, Lei Zhang, Bosheng Huang, Yibo Peng, Yuan Meng, Haojun Jiang, Shaoxuan Xie, Guocai Yao, Alois Knoll, Zhenshan Bing, Xinlong Wang, Zhenguo Sun

Abstract: Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of mul… ▽ More Bimanual dexterous manipulation relies on integrating multimodal inputs to perform complex real-world tasks. To address the challenges of effectively combining these modalities, we propose DECO, a decoupled multimodal diffusion transformer that disentangles vision, proprioception, and tactile signals through specialized conditioning pathways, enabling structured and controllable integration of multimodal inputs, with a lightweight adapter for parameter-efficient injection of additional signals. Alongside DECO, we release DECO-50 dataset for bimanual dexterous manipulation with tactile sensing, consisting of 50 hours of data and over 5M frames, collected via teleoperation on real dual-arm robots. We train DECO on DECO-50 and conduct extensive real-world evaluation with over 2,000 robot rollouts. Experimental results show that DECO achieves the best performance across all tasks, with a 72.25% average success rate and a 21% improvement over the baseline. Moreover, the tactile adapter brings an additional 10.25% average success rate across all tasks and a 20% gain on complex contact-rich tasks while tuning less than 10% of the model parameters. △ Less

Submitted 17 August, 2026; v1 submitted 5 February, 2026; originally announced February 2026.

Comments: 25 pages, 8 figures. Project Page: https://baai-humanoid.github.io/DECO-webpage/

RoboBrain 2.5: Depth in Sight, Time in Mind

Authors: Huajie Tan, Enshen Zhou, Zhiyu Li, Yijie Xu, Yuheng Ji, Xiansheng Chen, Cheng Chi, Pengwei Wang, Huizhu Jia, Yulong Ao, Mingyu Cao, Sixiang Chen, Zhe Li, Mengzhen Liu, Zixiao Wang, Shanyu Rong, Yaoxu Lyu, Zhongxia Zhao, Peterson Co, Yibo Li, Yi Han, Shaoxuan Xie, Guocai Yao, Songjing Wang, Leiduo Zhang , et al. (10 additional authors not shown)

Abstract: We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative gro… ▽ More We introduce RoboBrain 2.5, a next-generation embodied AI foundation model that advances general perception, spatial reasoning, and temporal modeling through extensive training on high-quality spatiotemporal supervision. Building upon its predecessor, RoboBrain 2.5 introduces two major capability upgrades. Specifically, it unlocks Precise 3D Spatial Reasoning by shifting from 2D pixel-relative grounding to depth-aware coordinate prediction and absolute metric constraint comprehension, generating complete 3D manipulation traces as ordered keypoint sequences under physical constraints. Complementing this spatial precision, the model establishes Dense Temporal Value Estimation that provides dense, step-aware progress prediction and execution state understanding across varying viewpoints, producing stable feedback signals for downstream learning. Together, these upgrades extend the framework toward more physically grounded and execution-aware embodied intelligence for complex, fine-grained manipulation. The code and checkpoints are available at project website: https://superrobobrain.github.io △ Less

Submitted 20 January, 2026; originally announced January 2026.

Comments: 37 pages, 13 figures, Technical Report

VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots

Authors: Yongsheng Zhao, Lei Zhao, Baoping Cheng, Gongxin Yao, Xuanzhang Wen, Han Gao

Abstract: Vision-Language-Action (VLA) models have achieved remarkable breakthroughs in robotics, with the action chunk playing a dominant role in these advances. Given the real-time and continuous nature of robotic motion control, the strategies for fusing a queue of successive action chunks have a profound impact on the overall performance of VLA models. Existing methods suffer from jitter, stalling, or e… ▽ More Vision-Language-Action (VLA) models have achieved remarkable breakthroughs in robotics, with the action chunk playing a dominant role in these advances. Given the real-time and continuous nature of robotic motion control, the strategies for fusing a queue of successive action chunks have a profound impact on the overall performance of VLA models. Existing methods suffer from jitter, stalling, or even pauses in robotic action execution, which not only limits the achievable execution speed but also reduces the overall success rate of task completion. This paper introduces VLA-RAIL (A Real-Time Asynchronous Inference Linker), a novel framework designed to address these issues by conducting model inference and robot motion control asynchronously and guaranteeing smooth, continuous, and high-speed action execution. The core contributions of the paper are two fold: a Trajectory Smoother that effectively filters out the noise and jitter in the trajectory of one action chunk using polynomial fitting and a Chunk Fuser that seamlessly align the current executing trajectory and the newly arrived chunk, ensuring position, velocity, and acceleration continuity between two successive action chunks. We validate the effectiveness of VLA-RAIL on a benchmark of dynamic simulation tasks and several real-world manipulation tasks. Experimental results demonstrate that VLA-RAIL significantly reduces motion jitter, enhances execution speed, and improves task success rates, which will become a key infrastructure for the large-scale deployment of VLA models. △ Less

Submitted 31 December, 2025; originally announced December 2025.

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

Authors: Huajie Tan, Sixiang Chen, Yijie Xu, Zixiao Wang, Yuheng Ji, Cheng Chi, Yaoxu Lyu, Zhongxia Zhao, Xiansheng Chen, Peterson Co, Shaoxuan Xie, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

Abstract: The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered by two fundamental limitations: their reward models lack step-aware understanding and rely on single-view perception, leading to unreliable assessments of fine-… ▽ More The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered by two fundamental limitations: their reward models lack step-aware understanding and rely on single-view perception, leading to unreliable assessments of fine-grained manipulation progress; and their reward shaping procedures are theoretically unsound, often inducing a semantic trap that misguides policy optimization. To address these, we introduce Dopamine-Reward, a novel reward modeling method for learning a general-purpose, step-aware process reward model from multi-view inputs. At its core is our General Reward Model (GRM), trained on a vast 3,400+ hour dataset, which leverages Step-wise Reward Discretization for structural understanding and Multi-Perspective Reward Fusion to overcome perceptual limitations. Building upon Dopamine-Reward, we propose Dopamine-RL, a robust policy learning framework that employs a theoretically-sound Policy-Invariant Reward Shaping method, which enables the agent to leverage dense rewards for efficient self-improvement without altering the optimal policy, thereby fundamentally avoiding the semantic trap. Extensive experiments across diverse simulated and real-world tasks validate our approach. GRM achieves state-of-the-art accuracy in reward assessment, and Dopamine-RL built on GRM significantly improves policy learning efficiency. For instance, after GRM is adapted to a new task in a one-shot manner from a single expert trajectory, the resulting reward model enables Dopamine-RL to improve the policy from near-zero to 95% success with only 150 online rollouts (approximately 1 hour of real robot interaction), while retaining strong generalization across tasks. Project website: https://robo-dopamine.github.io △ Less

Submitted 29 December, 2025; originally announced December 2025.

Comments: 27 pages, 11 figures

MOVE: A Simple Motion-Based Data Collection Paradigm for Spatial Generalization in Robotic Manipulation

Authors: Huanqian Wang, Chi Bene Chen, Yang Yue, Danhua Tao, Tong Guo, Shaoxuan Xie, Denghang Huang, Shiji Song, Guocai Yao, Gao Huang

Abstract: Imitation learning method has shown immense promise for robotic manipulation, yet its practical deployment is fundamentally constrained by the data scarcity. Despite prior work on collecting large-scale datasets, there still remains a significant gap to robust spatial generalization. We identify a key limitation: individual trajectories, regardless of their length, are typically collected from a \… ▽ More Imitation learning method has shown immense promise for robotic manipulation, yet its practical deployment is fundamentally constrained by the data scarcity. Despite prior work on collecting large-scale datasets, there still remains a significant gap to robust spatial generalization. We identify a key limitation: individual trajectories, regardless of their length, are typically collected from a \emph{single, static spatial configuration} of the environment. This includes fixed object and target spatial positions as well as unchanging camera viewpoints, which significantly restricts the diversity of spatial information available for learning. To address this critical bottleneck in data efficiency, we propose \textbf{MOtion-Based Variability Enhancement} (\emph{MOVE}), a simple yet effective data collection paradigm that enables the acquisition of richer spatial information from dynamic demonstrations. Our core contribution is an augmentation strategy that injects motion into any movable objects within the environment for each demonstration. This process implicitly generates a dense and diverse set of spatial configurations within a single trajectory. We conduct extensive experiments in both simulation and real-world environments to validate our approach. For example, in simulation tasks requiring strong spatial generalization, \emph{MOVE} achieves an average success rate of 39.1\%, a 76.1\% relative improvement over the static data collection paradigm (22.2\%), and yields up to 2--5$\times$ gains in data efficiency on certain tasks. Our code is available at https://github.com/lucywang720/MOVE. △ Less

Submitted 4 December, 2025; originally announced December 2025.

Comments: 9 pages, 9 figures

HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction

Authors: Pengcheng Fang, Hongli Chen, Guangzhen Yao, Jian Shi, Fangfang Tang, Xiaohao Cai, Shanshan Shan, Feng Liu

Abstract: Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a hierarchical shared-routed Mixture-of-Experts (MoE) Mamba architecture that couples frequency decomposition with content-adaptive computation. The model comprises two core components: (i) a separable frequency-consistent… ▽ More Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a hierarchical shared-routed Mixture-of-Experts (MoE) Mamba architecture that couples frequency decomposition with content-adaptive computation. The model comprises two core components: (i) a separable frequency-consistent Laplacian pyramid (SF-Lap) that delivers alias-resistant, stable low- and high-frequency streams; and (ii) a hierarchical shared-routed MoE that performs per-pixel top-1 sparse dispatch to shared experts and local routers, enabling effective specialization with stable cross-depth behavior. A lightweight global context path is fused into an unrolled, data-consistency-regularized backbone to reinforce long-range reasoning and preserve anatomical coherence. Evaluated on fastMRI, CC359, ACDC, M4Raw, and Prostate158, HiFi-MambaV2 consistently outperforms CNN-, Transformer-, and prior Mamba-based baselines in PSNR, SSIM, and NMSE across single- and multi-coil settings and multiple acceleration factors, consistently surpassing consistent improvements in high-frequency detail and overall structural fidelity. These results demonstrate that HiFi-MambaV2 enables reliable and robust MRI reconstruction. △ Less

Submitted 23 November, 2025; originally announced November 2025.

SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios

Authors: Juntao Cheng, Wanyue Zhang, Zhiwei Yu, Shuo Ren, Zheqi He, Shaoxuan Xie, Guocai Yao, Jieru Lin, Börje F. Karlsson, Jiajun Zhang

Abstract: Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting with these interfaces requires agents not only to ground language in visual observations,but also to execute actions, track temporally evolving state changes, and verify whether intended outcomes have been achieved. Howev… ▽ More Tangible control interfaces (TCIs), such as appliance panels, remotes, elevators, and embedded GUIs, are a fundamental component of everyday human-built environments. Interacting with these interfaces requires agents not only to ground language in visual observations,but also to execute actions, track temporally evolving state changes, and verify whether intended outcomes have been achieved. However, existing benchmarks predominantly evaluate open-loop perception or single-step action execution, failing to capture this continuous cycle of interaction, feedback, and correction. We introduce SWITCH, a benchmark for closed-loop interactive reasoning with TCIs in realistic egocentric environments1. SWITCH comprises 1,170 temporally interactive videos across diverse functional categories, providing structured annotations of instructions, actions, state transitions, outcomes, and recovery behaviors over time. To probe generative world modeling, SWITCH also evaluates video generation models on interaction-centered tasks using both LLM-as-judge and human evaluation2.Experiments with frontier proprietary and opensource multimodal models reveal persistent weaknesses in fine-grained visual-temporal perception, outcome verification, and error recovery, highlighting SWITCH as a testbed for closed-loop embodied intelligence. △ Less

Submitted 7 July, 2026; v1 submitted 20 November, 2025; originally announced November 2025.

Comments: The dataset is available at https://huggingface.co/datasets/BAAI-Agents/SWITCH

RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation

Authors: Shihan Wu, Xuecheng Liu, Shaoxuan Xie, Pengwei Wang, Xinghang Li, Bowen Yang, Zhe Li, Kai Zhu, Hongyu Wu, Yiheng Liu, Zhaoye Long, Runtian Xu, Yue Wang, Chong Liu, Dihan Wang, Ziqiang Ni, Xiang Yang, You Liu, Ruoxuan Feng, Lei Zhang, Denghang Huang, Chenghao Jin, Anlan Yin, Xinlong Wang, Zhenguo Sun , et al. (59 additional authors not shown)

Abstract: Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robot… ▽ More Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation. △ Less

Submitted 13 April, 2026; v1 submitted 21 November, 2025; originally announced November 2025.

Comments: Add experiments

METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model

Authors: Yankai Fu, Ning Chen, Junkai Zhao, Shaozhe Shan, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

Abstract: Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipulation. A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills, as teleoperation is difficult and costly. Human data, with its vast scale and diverse manipulation behaviors, provides rich priors for learning roboti… ▽ More Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipulation. A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills, as teleoperation is difficult and costly. Human data, with its vast scale and diverse manipulation behaviors, provides rich priors for learning robotic actions. While prior works have explored leveraging human demonstrations, they are often constrained by limited scenarios and a large visual gap between human and robots. To eliminate these limitations, we propose METIS, a vision-language-action (VLA) model for dexterous manipulation pretrained on multi-source egocentric datasets. We first construct EgoAtlas, which integrates large-scale human and robotic data from multiple sources, all unified under a consistent action space. We further extract motion-aware dynamics, a compact and discretized motion representation, which provides efficient and expressive supervision for VLA training. Built upon them, METIS integrates reasoning and acting into a unified framework, enabling effective deployment to downstream dexterous manipulation tasks. Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks. Experimental results also highlight the superior generalization and robustness to out-of-distribution scenarios. These findings emphasize METIS as a promising step toward a generalist model for dexterous manipulation. △ Less

Submitted 21 November, 2025; originally announced November 2025.

High-Performance N-Queens Solver on GPU: Iterative DFS with Zero Bank Conflicts

Authors: Guangchao Yao, Yali Li

Abstract: The counting of solutions to the N-Queens problem is a classic NP-complete problem with extremely high computational complexity. As of now, the academic community has rigorously verified the number of solutions only up to N <= 26. In 2016, the research team led by PreuBer solved the 27-Queens problem using FPGA hardware, which took approximately one year, though the result remains unverified indep… ▽ More The counting of solutions to the N-Queens problem is a classic NP-complete problem with extremely high computational complexity. As of now, the academic community has rigorously verified the number of solutions only up to N <= 26. In 2016, the research team led by PreuBer solved the 27-Queens problem using FPGA hardware, which took approximately one year, though the result remains unverified independently. Recent studies on GPU parallel computing suggest that verifying the 27-Queens solution would still require about 17 months, indicating excessively high time and computational resource costs. To address this challenge, we propose an innovative parallel computing method on NVIDIA GPU platform, with the following core contributions: (1) An iterative depth-first search (DFS) algorithm for solving the N-Queens problem; (2) Complete mapping of the required stack structure to GPU shared memory; (3) Effective avoidance of bank conflicts through meticulously designed memory access patterns; (4) Various optimization techniques are employed to achieve optimal performance. Under the proposed optimization framework, we successfully verified the 27-Queens problem in just 28.4 days using eight RTX 5090 GPUs, thereby confirming the correctness of PreuBer's computational results. Moreover, we have reduced the projected solving time for the next open case-the 28-Queens problem-to approximately 11 months, making its resolution computationally feasible. Compared to the state-of-the-art GPU methods, our method achieves over 10x speedup on identical hardware configurations (8 A100), while delivering over 26x acceleration when utilizing 8 RTX 5090 GPUs, and brings fresh perspectives to this long-stagnant problem. △ Less

Submitted 14 November, 2025; originally announced November 2025.

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

Authors: Inclusion AI, :, Bowen Ma, Cheng Zou, ChengKun Du, Canxiang Yan, Chunxiang Jin, Chunjie Shen, Chenyu Lian, Chengxiang Fan, Dandan Zheng, Fudong Wang, Furong Xu, Guangming Yao, Haohao Liu, Han Peng, Jun Zhou, Junluan Xia, Jingdong Chen, Jianing Li, Jianxin Sun, Jianjiang Zhu, Jianping Jiang, Jinpeng Ou, Jun Peng , et al. (51 additional authors not shown)

Abstract: We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimo… ▽ More We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimodal intelligence across vision, speech, and language, representing a key step toward Artificial General Intelligence (AGI). Compared to its predecessor, the upgraded version exhibits substantial improvements across multimodal understanding and generation. Notably, it achieves strong performance on vision-language understanding benchmarks, with overall scores on par with Gemini 2.5 Pro, and enables seamless switching among multimodal tasks in multi-turn interactions. In speech, it achieves strong performance in contextual and dialect-aware ASR while enabling joint, continuous-generation of speech, sound, and music. In vision, it introduces generative semantic segmentation that achieves competitive standalone performance and enhances spatial control and editing consistency, alongside marked improvements in identity preservation, and high-fidelity in-image text rendering. Together, these capabilities demonstrate that a single unified model can serve as a practical foundation for general-purpose multimodal intelligence. △ Less

Submitted 26 March, 2026; v1 submitted 28 October, 2025; originally announced October 2025.

Comments: 18 pages, 5 figures

Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes

Authors: Guanyu Yao, Qiucheng Wu, Yang Zhang, Zhaowen Wang, Handong Zhao, Shiyu Chang

Abstract: Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically, current MLLMs often over-rely on textual cues while under-attending to visual content, resulting in suboptimal performance on tasks that require genuine visual re… ▽ More Multimodal large language models (MLLMs) have demonstrated strong capabilities on vision-and-language tasks. However, recent findings reveal an imbalance in their reasoning capabilities across visual and textual modalities. Specifically, current MLLMs often over-rely on textual cues while under-attending to visual content, resulting in suboptimal performance on tasks that require genuine visual reasoning. We refer to this phenomenon as the \textit{modality gap}, defined as the performance disparity between text-centric and vision-centric inputs. In this paper, we analyze the modality gap through the lens of training recipes. We first show that existing training recipes tend to amplify this gap. Then, we systematically explore strategies to bridge it from two complementary perspectives: data and loss design. Our findings provide insights into developing training recipes that mitigate the modality gap and promote more balanced multimodal reasoning. Our code is publicly available at https://github.com/UCSB-NLP-Chang/Bridging-Modality-Gap. △ Less

Submitted 7 January, 2026; v1 submitted 26 October, 2025; originally announced October 2025.

VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series

Authors: Pengyu Xu, Shijia Li, Ao Sun, Feng Zhang, Yahan Li, Bo Wu, Zhanyu Ma, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Rui Wang, Yang Liu, Xiaobo Hu, Fan Yang, Jia Zheng, Guanghua Yao

Abstract: We propose OutboundEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound calling scenarios. Unlike existing methods that suffer from three key limitations - insufficient dataset diversity and category coverage, unrealistic user simulation, and inaccurate evaluation metrics - OutboundEval addresses these issues through a structured framewor… ▽ More We propose OutboundEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound calling scenarios. Unlike existing methods that suffer from three key limitations - insufficient dataset diversity and category coverage, unrealistic user simulation, and inaccurate evaluation metrics - OutboundEval addresses these issues through a structured framework. First, we design a benchmark spanning six major business domains and 30 representative sub-scenarios, each with scenario-specific process decomposition, weighted scoring, and domain-adaptive metrics. Second, we develop a large-model-driven User Simulator that generates diverse, persona-rich virtual users with realistic behaviors, emotional variability, and communication styles, providing a controlled yet authentic testing environment. Third, we introduce a dynamic evaluation method that adapts to task variations, integrating automated and human-in-the-loop assessment to measure task execution accuracy, professional knowledge application, adaptability, and user experience quality. Experiments on 12 state-of-the-art LLMs reveal distinct trade-offs between expert-level task completion and interaction fluency, offering practical insights for building reliable, human-like outbound AI systems. OutboundEval establishes a practical, extensible, and domain-oriented standard for benchmarking LLMs in professional applications. △ Less

Submitted 14 November, 2025; v1 submitted 24 October, 2025; originally announced October 2025.

Robobench: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models as Embodied Brain

Authors: Yulin Luo, Chun-Kai Fan, Menghang Dong, Jiayu Shi, Xiangju Mi, Mengdi Zhao, Bo-Wen Zhang, Cheng Chi, Jiaming Liu, Gaole Dai, Rongyu Zhang, Ruichuan An, Kun Wu, Zhengping Che, Shaoxuan Xie, Guocai Yao, Zhongxia Zhao, Pengwei Wang, Guang Liu, Zhongyuan Wang, Tiejun Huang, Shanghang Zhang

Abstract: Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems often follow a dual-system paradigm, where System 2 performs high-level reasoning and System 1 handles low-level control. We refer to System 2 as the embodied brain, the cognitive core for decision-making in manipulation. Although evaluating this embodied br… ▽ More Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a central challenge. Recent embodied systems often follow a dual-system paradigm, where System 2 performs high-level reasoning and System 1 handles low-level control. We refer to System 2 as the embodied brain, the cognitive core for decision-making in manipulation. Although evaluating this embodied brain is crucial, existing benchmarks mainly measure execution success or cover only limited aspects of high-level cognition and task realism. We introduce RoboBench, a benchmark for evaluating multimodal large language models (MLLMs) as embodied brains. RoboBench covers five dimensions: Instruction Comprehension, Perception Reasoning, Generalized Planning, Affordance Prediction, and Failure Analysis. It spans 14 capabilities, 25 tasks, and 6,092 QA pairs. To improve realism, it draws from large-scale real robotic data and in-house collection across diverse embodiments, attribute-rich objects, multi-view scenes, and memory-driven navigation. For planning, RoboBench introduces an MLLM-as-world-simulator framework that assesses whether predicted plans can achieve critical object-state changes under physical and visual constraints, enabling more faithful evaluation of long-horizon reasoning than symbolic matching. Experiments on 18 state-of-the-art MLLMs reveal persistent limitations in implicit instruction understanding, spatiotemporal reasoning, cross-scenario planning, fine-grained affordance understanding, and failure diagnosis. We further analyze how embodied cognitive abilities relate to downstream robotic control. RoboBench offers a comprehensive scaffold for quantifying high-level cognition and guiding next-generation MLLMs toward more robust robotic intelligence. △ Less

Submitted 5 July, 2026; v1 submitted 20 October, 2025; originally announced October 2025.

Comments: ECCV 2026 Camera Ready

Skin Lesion Classification Based on ResNet-50 Enhanced With Adaptive Spatial Feature Fusion

Authors: Runhao Liu, Fengyi Zha, Fei Ding, Guangzhen Yao, Peng Zhang

Abstract: Skin cancer classification is challenging due to high inter-class similarity, intra-class variability, and artifacts in dermoscopic images. To address these issues, we propose an improved ResNet-50 with Adaptive Spatial Feature Fusion (ASFF), which adaptively integrates multi-scale semantic and surface features to refine representations and reduce overfitting. The ResNet-50 model is enhanced with… ▽ More Skin cancer classification is challenging due to high inter-class similarity, intra-class variability, and artifacts in dermoscopic images. To address these issues, we propose an improved ResNet-50 with Adaptive Spatial Feature Fusion (ASFF), which adaptively integrates multi-scale semantic and surface features to refine representations and reduce overfitting. The ResNet-50 model is enhanced with an adaptive feature fusion mechanism to achieve more effective multi-scale feature extraction and improve overall performance. Specifically, a dual-branch design fuses high-level semantic and mid-level detail features which use global average pooling and fully connected layers to produce spatial weights, and emphasizes lesion-relevant regions. Evaluated on a balanced subset of ISIC 2020 (3,297 images, randomly selected from the original dataset), the ASFF-based ResNet-50 outperforms multiple CNN baselines, achieving 93.182% accuracy with superior precision, recall, specificity, and F1. It also reaches 0.9670 AUC (P-R) and 0.9717 AUC (ROC). Grad-CAM visualizations show more accurate focus on lesion areas.The proposed model also generalizes well to ISIC 2019 external validation, outperforming the ResNet-50 baseline. These findings demonstrate that the proposed approach provides a more effective and efficient solution for computer-aided skin cancer diagnosis. The generation codes, weights and confusion matrices are open sourced in https://github.com/Grapesea/ASFF-ResNet50-enhanced. △ Less

Submitted 29 May, 2026; v1 submitted 4 October, 2025; originally announced October 2025.

Exploring the Challenge and Value of Deep Learning in Automated Skin Disease Diagnosis

Authors: Runhao Liu, Ziming Chen, Guangzhen Yao, Peng Zhang

Abstract: Skin cancer is one of the most prevalent and deadly forms of cancer worldwide, highlighting the critical importance of early detection and diagnosis in improving patient outcomes. Deep learning (DL) has shown significant promise in enhancing the accuracy and efficiency of automated skin disease diagnosis, particularly in detecting and classifying skin lesions. However, several challenges remain fo… ▽ More Skin cancer is one of the most prevalent and deadly forms of cancer worldwide, highlighting the critical importance of early detection and diagnosis in improving patient outcomes. Deep learning (DL) has shown significant promise in enhancing the accuracy and efficiency of automated skin disease diagnosis, particularly in detecting and classifying skin lesions. However, several challenges remain for DL-based skin cancer diagnosis, including complex features, image noise, intra-class variation, inter-class similarity, and data imbalance. This review synthesizes recent research and discusses innovative approaches to address these challenges, such as data augmentation, hybrid models, and feature fusion. Furthermore, the review highlights the integration of DL models into clinical workflows, offering insights into the potential of deep learning to revolutionize skin disease diagnosis and improve clinical decision-making. This review uniquely integrates a PRISMA-based methodology with a challenge-oriented taxonomy, providing a systematic and transparent synthesis of recent deep learning advances for skin disease diagnosis. It further highlights emerging directions such as hybrid CNN-Transformer architectures and uncertainty-aware models, emphasizing its contribution to future dermatological AI research. △ Less

Submitted 16 January, 2026; v1 submitted 4 October, 2025; originally announced October 2025.

Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMs

Authors: Xin Hu, Yue Kang, Guanzi Yao, Tianze Kang, Mengjie Wang, Heyao Liu

Abstract: This study addresses the generalization limitations commonly observed in large language models under multi-task and cross-domain settings. Unlike prior methods such as SPoT, which depends on fixed prompt templates, our study introduces a unified multi-task learning framework with dynamic prompt scheduling mechanism. By introducing a prompt pool and a task-aware scheduling strategy, the method dyna… ▽ More This study addresses the generalization limitations commonly observed in large language models under multi-task and cross-domain settings. Unlike prior methods such as SPoT, which depends on fixed prompt templates, our study introduces a unified multi-task learning framework with dynamic prompt scheduling mechanism. By introducing a prompt pool and a task-aware scheduling strategy, the method dynamically combines and aligns prompts for different tasks. This enhances the model's ability to capture semantic differences across tasks. During prompt fusion, the model uses task embeddings and a gating mechanism to finely control the prompt signals. This ensures alignment between prompt content and task-specific demands. At the same time, it builds flexible sharing pathways across tasks. In addition, the proposed optimization objective centers on joint multi-task learning. It incorporates an automatic learning strategy for scheduling weights, which effectively mitigates task interference and negative transfer. To evaluate the effectiveness of the method, a series of sensitivity experiments were conducted. These experiments examined the impact of prompt temperature parameters and task number variation. The results confirm the advantages of the proposed mechanism in maintaining model stability and enhancing transferability. Experimental findings show that the prompt scheduling method significantly improves performance on a range of language understanding and knowledge reasoning tasks. These results fully demonstrate its applicability and effectiveness in unified multi-task modeling and cross-domain adaptation. △ Less

Submitted 9 September, 2025; originally announced September 2025.

Topology-Aware Graph Reinforcement Learning for Dynamic Routing in Cloud Networks

Authors: Yuxi Wang, Heyao Liu, Guanzi Yao, Nyutian Long, Yue Kang

Abstract: This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decis… ▽ More This paper proposes a topology-aware graph reinforcement learning approach to address the routing policy optimization problem in cloud server environments. The method builds a unified framework for state representation and structural evolution by integrating a Structure-Aware State Encoding (SASE) module and a Policy-Adaptive Graph Update (PAGU) mechanism. It aims to tackle the challenges of decision instability and insufficient structural awareness under dynamic topologies. The SASE module models node states through multi-layer graph convolution and structural positional embeddings, capturing high-order dependencies in the communication topology and enhancing the expressiveness of state representations. The PAGU module adjusts the graph structure based on policy behavior shifts and reward feedback, enabling adaptive structural updates in dynamic environments. Experiments are conducted on the real-world GEANT topology dataset, where the model is systematically evaluated against several representative baselines in terms of throughput, latency control, and link balance. Additional experiments, including hyperparameter sensitivity, graph sparsity perturbation, and node feature dimensionality variation, further explore the impact of structure modeling and graph updates on model stability and decision quality. Results show that the proposed method outperforms existing graph reinforcement learning models across multiple performance metrics, achieving efficient and robust routing in dynamic and complex cloud networks. △ Less

Submitted 5 September, 2025; originally announced September 2025.

Adaptive generative moment matching networks for improved learning of dependence structures

Authors: Marius Hofert, Gan Yao

Abstract: An adaptive bandwidth selection procedure for the mixture kernel in the maximum mean discrepancy (MMD) for fitting generative moment matching networks (GMMNs) is introduced, and improved learning of copula random number generators is demonstrated. Based on the relative error of the training loss, the number of kernels is increased during training; additionally, the relative error of the validation… ▽ More An adaptive bandwidth selection procedure for the mixture kernel in the maximum mean discrepancy (MMD) for fitting generative moment matching networks (GMMNs) is introduced, and improved learning of copula random number generators is demonstrated. Based on the relative error of the training loss, the number of kernels is increased during training; additionally, the relative error of the validation loss is used as an early stopping criterion. While training time remains similar, adaptively training GMMNs (AGMMNs) significantly increases training performance, which is shown based on validation MMD trajectories, samples and validation MMD values. Superiority of AGMMNs over GMMNs and parametric copula models is also demonstrated in terms of three applications. First, convergence rates of estimators based on quasi-random versus pseudo-random samples from copulas are investigated in dimensions as large as 100 for the first time. Second, replicated validation MMDs, as well as Monte Carlo and quasi-Monte Carlo applications demonstrate the improved training of AGMMNs for a copula model implied by the 50 constituents of the S&P 500 index after deGARCHing. Last, both the latter dataset and 50 constituents of the FTSE 100 are used to demonstrate that the improved training of AGMMNs indeed translates to an improved model prediction. △ Less

Submitted 11 June, 2026; v1 submitted 29 August, 2025; originally announced August 2025.

MSC Class: 62H99; 65C60; 60E05; 00A72; 65C10

D$^2$-LIO: Enhanced Optimization for LiDAR-IMU Odometry Considering Directional Degeneracy

Authors: Guodong Yao, Hao Wang, Qing Chang

Abstract: LiDAR-inertial odometry (LIO) plays a vital role in achieving accurate localization and mapping, especially in complex environments. However, the presence of LiDAR feature degeneracy poses a major challenge to reliable state estimation. To overcome this issue, we propose an enhanced LIO framework that integrates adaptive outlier-tolerant correspondence with a scan-to-submap registration strategy.… ▽ More LiDAR-inertial odometry (LIO) plays a vital role in achieving accurate localization and mapping, especially in complex environments. However, the presence of LiDAR feature degeneracy poses a major challenge to reliable state estimation. To overcome this issue, we propose an enhanced LIO framework that integrates adaptive outlier-tolerant correspondence with a scan-to-submap registration strategy. The core contribution lies in an adaptive outlier removal threshold, which dynamically adjusts based on point-to-sensor distance and the motion amplitude of platform. This mechanism improves the robustness of feature matching in varying conditions. Moreover, we introduce a flexible scan-to-submap registration method that leverages IMU data to refine pose estimation, particularly in degenerate geometric configurations. To further enhance localization accuracy, we design a novel weighting matrix that fuses IMU preintegration covariance with a degeneration metric derived from the scan-to-submap process. Extensive experiments conducted in both indoor and outdoor environments-characterized by sparse or degenerate features-demonstrate that our method consistently outperforms state-of-the-art approaches in terms of both robustness and accuracy. △ Less

Submitted 19 August, 2025; originally announced August 2025.

Comments: 7 page, 2 figures

Federated Anomaly Detection for Multi-Tenant Cloud Platforms with Personalized Modeling

Authors: Yuxi Wang, Heyao Liu, Nyutian Long, Guanzi Yao

Abstract: This paper proposes an anomaly detection method based on federated learning to address key challenges in multi-tenant cloud environments, including data privacy leakage, heterogeneous resource behavior, and the limitations of centralized modeling. The method establishes a federated training framework involving multiple tenants. Each tenant trains the model locally using private resource usage data… ▽ More This paper proposes an anomaly detection method based on federated learning to address key challenges in multi-tenant cloud environments, including data privacy leakage, heterogeneous resource behavior, and the limitations of centralized modeling. The method establishes a federated training framework involving multiple tenants. Each tenant trains the model locally using private resource usage data. Through parameter aggregation, a global model is optimized, enabling cross-tenant collaborative anomaly detection while preserving data privacy. To improve adaptability to diverse resource usage patterns, a personalized parameter adjustment mechanism is introduced. This allows the model to retain tenant-specific feature representations while sharing global knowledge. In the model output stage, the Mahalanobis distance is used to compute anomaly scores. This enhances both the accuracy and stability of anomaly detection. The experiments use real telemetry data from a cloud platform to construct a simulated multi-tenant environment. The study evaluates the model's performance under varying participation rates and noise injection levels. These comparisons demonstrate the proposed method's robustness and detection accuracy. Experimental results show that the proposed method outperforms existing mainstream models across key metrics such as Precision, Recall, and F1-Score. It also maintains stable performance in various complex scenarios. These findings highlight the method's practical potential for intelligent resource monitoring and anomaly diagnosis in cloud computing environments. △ Less

Submitted 13 August, 2025; originally announced August 2025.

Multi-Agent Reinforcement Learning for Adaptive Resource Orchestration in Cloud-Native Clusters

Authors: Guanzi Yao, Heyao Liu, Linyan Dai

Abstract: This paper addresses the challenges of high resource dynamism and scheduling complexity in cloud-native database systems. It proposes an adaptive resource orchestration method based on multi-agent reinforcement learning. The method introduces a heterogeneous role-based agent modeling mechanism. This allows different resource entities, such as compute nodes, storage nodes, and schedulers, to adopt… ▽ More This paper addresses the challenges of high resource dynamism and scheduling complexity in cloud-native database systems. It proposes an adaptive resource orchestration method based on multi-agent reinforcement learning. The method introduces a heterogeneous role-based agent modeling mechanism. This allows different resource entities, such as compute nodes, storage nodes, and schedulers, to adopt distinct policy representations. These agents are better able to reflect diverse functional responsibilities and local environmental characteristics within the system. A reward-shaping mechanism is designed to integrate local observations with global feedback. This helps mitigate policy learning bias caused by incomplete state observations. By combining real-time local performance signals with global system value estimation, the mechanism improves coordination among agents and enhances policy convergence stability. A unified multi-agent training framework is developed and evaluated on a representative production scheduling dataset. Experimental results show that the proposed method outperforms traditional approaches across multiple key metrics. These include resource utilization, scheduling latency, policy convergence speed, system stability, and fairness. The results demonstrate strong generalization and practical utility. Across various experimental scenarios, the method proves effective in handling orchestration tasks with high concurrency, high-dimensional state spaces, and complex dependency relationships. This confirms its advantages in real-world, large-scale scheduling environments. △ Less

Submitted 13 August, 2025; originally announced August 2025.

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability

Authors: Xiaoxu Zhu, Junhua Li, Aaron J. Li, Guangchao Yao, Xiaojie Yu

Abstract: Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks through supposedly anonymized representations. We present two contributions to address these challenges. First, we develop InterpTRQE-SptME (Timbre Residual Quant… ▽ More Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks through supposedly anonymized representations. We present two contributions to address these challenges. First, we develop InterpTRQE-SptME (Timbre Residual Quantitative Evaluation Benchmark of Speech pre-training Models Encoding via Interpretability), a benchmark that directly measures residual speaker information in content embeddings using SHAP-based interpretability analysis. Unlike existing indirect metrics, our approach quantifies the exact proportion of speaker information remaining after disentanglement. Second, we propose InterpTF-SptME, which uses these interpretability insights to filter speaker information from embeddings. Testing on VCTK with seven models including HuBERT, WavLM, and ContentVec, we find that SHAP Noise filtering reduces speaker residuals from 18.05% to nearly zero while maintaining recognition accuracy (CTC loss increase under 1%). The method is model-agnostic and requires no retraining. △ Less

Submitted 31 March, 2026; v1 submitted 19 July, 2025; originally announced July 2025.

Comments: 5 pages, 4 figures

MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

Authors: Xinyang Li, Gen Li, Zhihui Lin, Yichen Qian, GongXin Yao, Weinan Jia, Aowen Wang, Weihua Chen, Fan Wang

Abstract: Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong generation capabilities. However, several challenges remain for diffusion-based methods: 1) inefficient inference and visual artifacts caused by the implicit latent s… ▽ More Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong generation capabilities. However, several challenges remain for diffusion-based methods: 1) inefficient inference and visual artifacts caused by the implicit latent space of Variational Auto-Encoders (VAE), which complicates the diffusion process; 2) a lack of authentic facial expressions and head movements due to inadequate multi-modal information fusion. In this paper, MoDA handles these challenges by: 1) defining a joint parameter space that bridges motion generation and neural rendering, and leveraging flow matching to simplify diffusion learning; 2) introducing a multi-modal diffusion architecture to model the interaction among noisy motion, audio, and auxiliary conditions, enhancing overall facial expressiveness. In addition, a coarse-to-fine fusion strategy is employed to progressively integrate different modalities, ensuring effective feature fusion. Experimental results demonstrate that MoDA improves video diversity, realism, and efficiency, making it suitable for real-world applications. Project Page: https://lixinyyang.github.io/MoDA.github.io/ △ Less

Submitted 8 August, 2025; v1 submitted 3 July, 2025; originally announced July 2025.

Comments: 12 pages, 7 figures

MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination

Authors: Ao Jia, Haiming Wu, Guohui Yao, Dawei Song, Songkun Ji, Yazhou Zhang

Abstract: Large language models (LLMs) are prone to three types of hallucination: Input-Conflicting, Context-Conflicting and Fact-Conflicting hallucinations. The purpose of this study is to mitigate the different types of hallucination by exploiting the interdependence between them. For this purpose, we propose a Multi-Information Adapter for Large Language Models (MALM). This framework employs a tailored m… ▽ More Large language models (LLMs) are prone to three types of hallucination: Input-Conflicting, Context-Conflicting and Fact-Conflicting hallucinations. The purpose of this study is to mitigate the different types of hallucination by exploiting the interdependence between them. For this purpose, we propose a Multi-Information Adapter for Large Language Models (MALM). This framework employs a tailored multi-graph learning approach designed to elucidate the interconnections between original inputs, contextual information, and external factual knowledge, thereby alleviating the three categories of hallucination within a cohesive framework. Experiments were carried out on four benchmarking datasets: HaluEval, TruthfulQA, Natural Questions, and TriviaQA. We evaluated the proposed framework in two aspects: (1) adaptability to different base LLMs on HaluEval and TruthfulQA, to confirm if MALM is effective when applied on 7 typical LLMs. MALM showed significant improvements over LLaMA-2; (2) generalizability to retrieval-augmented generation (RAG) by combining MALM with three representative retrievers (BM25, Spider and DPR) separately. Furthermore, automated and human evaluations were conducted to substantiate the correctness of experimental results, where GPT-4 and 3 human volunteers judged which response was better between LLaMA-2 and MALM. The results showed that both GPT-4 and human preferred MALM in 79.4% and 65.6% of cases respectively. The results validate that incorporating the complex interactions between the three types of hallucination through a multilayered graph attention network into the LLM generation process is effective to mitigate the them. The adapter design of the proposed approach is also proven flexible and robust across different base LLMs. △ Less

Submitted 14 June, 2025; originally announced June 2025.

Ming-Omni: A Unified Multimodal Model for Perception and Generation

Authors: Inclusion AI, Biao Gong, Cheng Zou, Chuanyang Zheng, Chunluan Zhou, Canxiang Yan, Chunxiang Jin, Chunjie Shen, Dandan Zheng, Fudong Wang, Furong Xu, GuangMing Yao, Jun Zhou, Jingdong Chen, Jianxin Sun, Jiajia Liu, Jianjiang Zhu, Jun Peng, Kaixiang Ji, Kaiyou Song, Kaimeng Ren, Libin Wang, Lixiang Ru, Lele Xie, Longhua Tan , et al. (33 additional authors not shown)

Abstract: We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single… ▽ More We propose Ming-Omni, a unified multimodal model capable of processing images, text, audio, and video, while demonstrating strong proficiency in both speech and image generation. Ming-Omni employs dedicated encoders to extract tokens from different modalities, which are then processed by Ling, an MoE architecture equipped with newly proposed modality-specific routers. This design enables a single model to efficiently process and fuse multimodal inputs within a unified framework, thereby facilitating diverse tasks without requiring separate models, task-specific fine-tuning, or structural redesign. Importantly, Ming-Omni extends beyond conventional multimodal models by supporting audio and image generation. This is achieved through the integration of an advanced audio decoder for natural-sounding speech and Ming-Lite-Uni for high-quality image generation, which also allow the model to engage in context-aware chatting, perform text-to-speech conversion, and conduct versatile image editing. Our experimental results showcase Ming-Omni offers a powerful solution for unified perception and generation across all modalities. Notably, our proposed Ming-Omni is the first open-source model we are aware of to match GPT-4o in modality support, and we release all code and model weights to encourage further research and development in the community. △ Less

Submitted 10 June, 2025; originally announced June 2025.

Comments: 18 pages,8 figures

Addressing Noise and Stochasticity in Fraud Detection for Service Networks

Authors: Wenxin Zhang, Ding Xu, Xi Xuan, Lei Jiang, Guangzhen Yao, Renda Han, Xiangxiang Lang, Cuicui Luo

Abstract: Fraud detection is crucial in social service networks to maintain user trust and improve service network security. Existing spectral graph-based methods address this challenge by leveraging different graph filters to capture signals with different frequencies in service networks. However, most graph filter-based methods struggle with deriving clean and discriminative graph signals. On the one hand… ▽ More Fraud detection is crucial in social service networks to maintain user trust and improve service network security. Existing spectral graph-based methods address this challenge by leveraging different graph filters to capture signals with different frequencies in service networks. However, most graph filter-based methods struggle with deriving clean and discriminative graph signals. On the one hand, they overlook the noise in the information propagation process, resulting in degradation of filtering ability. On the other hand, they fail to discriminate the frequency-specific characteristics of graph signals, leading to distortion of signals fusion. To address these issues, we develop a novel spectral graph network based on information bottleneck theory (SGNN-IB) for fraud detection in service networks. SGNN-IB splits the original graph into homophilic and heterophilic subgraphs to better capture the signals at different frequencies. For the first limitation, SGNN-IB applies information bottleneck theory to extract key characteristics of encoded representations. For the second limitation, SGNN-IB introduces prototype learning to implement signal fusion, preserving the frequency-specific characteristics of signals. Extensive experiments on three real-world datasets demonstrate that SGNN-IB outperforms state-of-the-art fraud detection methods. △ Less

Submitted 1 May, 2025; originally announced May 2025.

FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detection

Authors: Wenxin Zhang, Ding Xu, Guangzhen Yao, Xiaojian Lin, Renxiang Guan, Chengze Du, Renda Han, Xi Xuan, Cuicui Luo

Abstract: Time series anomaly detection is critical for system monitoring and risk identification, across various domains, such as finance and healthcare. However, for most reconstruction-based approaches, detecting anomalies remains a challenge due to the complexity of sequential patterns in time series data. On the one hand, reconstruction-based techniques are susceptible to computational deviation stemmi… ▽ More Time series anomaly detection is critical for system monitoring and risk identification, across various domains, such as finance and healthcare. However, for most reconstruction-based approaches, detecting anomalies remains a challenge due to the complexity of sequential patterns in time series data. On the one hand, reconstruction-based techniques are susceptible to computational deviation stemming from anomalies, which can lead to impure representations of normal sequence patterns. On the other hand, they often focus on the time-domain dependencies of time series, while ignoring the alignment of frequency information beyond the time domain. To address these challenges, we propose a novel Frequency-augmented Convolutional Transformer (FreCT). FreCT utilizes patch operations to generate contrastive views and employs an improved Transformer architecture integrated with a convolution module to capture long-term dependencies while preserving local topology information. The introduced frequency analysis based on Fourier transformation could enhance the model's ability to capture crucial characteristics beyond the time domain. To protect the training quality from anomalies and improve the robustness, FreCT deploys stop-gradient Kullback-Leibler (KL) divergence and absolute error to optimize consistency information in both time and frequency domains. Extensive experiments on four public datasets demonstrate that FreCT outperforms existing methods in identifying anomalies. △ Less

Submitted 10 May, 2025; v1 submitted 1 May, 2025; originally announced May 2025.