Showing 1–50 of 221 results for author: Ni, Z

USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes

Authors: Li-Heng Chen, Haokai Pang, Chengye Su, Jiarun Liu, Qifeng Chen, Ziqian Ni, Jianxin Huang, Shi-Sheng Huang, Hongbo Fu, Sheng Yang

Abstract: Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-oriented 3D primitives (\eg, 3D Gaussians) serve as two distinct yet highly complementary levels for scene understanding. Existing methods typically treat dynamic reconstruction and instance-level perception as separate ta… ▽ More Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-oriented 3D primitives (\eg, 3D Gaussians) serve as two distinct yet highly complementary levels for scene understanding. Existing methods typically treat dynamic reconstruction and instance-level perception as separate tasks, despite their shared goal of estimating the underlying 3D world state. As a result, dynamic reconstruction is under-constrained while 3D detection lacks geometric grounding. To address this gap, we propose USR-Drive, a unified conditional generative framework that, given only posed multi-view driving videos, jointly recovers dense dynamic geometry and instance-level object layouts within a shared scene representation. Specifically, USR-Drive represents dense Gaussian primitives and sparse 3D bounding boxes as two aligned latent token streams and jointly denoises them with a unified multi-modal diffusion Transformer. Unlike prior paradigms that use boxes as external conditions or predict them with detached modules, USR-Drive treats them as mutually constrained state variables with a Unified Positional Encoding (UPE) that aligns heterogeneous tokens within a shared metric spatiotemporal coordinate. Via such unified representation and generative framework, the two modalities reinforce each other: geometry supplies dense metric evidence for box prediction, while boxes provide instance-level structural priors that help preserve spatial consistency and reduce ambiguity in sequential 3D geometric representation. Our approach successfully delivers state-of-the-art results for both dynamic reconstruction and 3D detection on the nuScenes and VKitti datasets. △ Less

Submitted 19 August, 2026; originally announced August 2026.

MANIGUARD: A Benchmark and Data Suite for Specification-Grounded Safety Evaluation and Improvement of Robotic Manipulation

Authors: Yiyan Peng, Philip Wang, Simon Sinong Zhan, Yiqi Lyu, Zhenyang Ni, Jixin Yan, Fiorelli Wong, Ruochen Jiao, Hang Yin, Xinyu Cao, Huajie Shao, Manling Li, Ruohan Zhang, Qi Zhu

Abstract: Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard-Bench task suite and a paired safety-annotated trajectory-generation pipeline.… ▽ More Foundation-model policies for robotic manipulation are advancing rapidly on task success, but rigorous evaluation of whether they succeed safely is still lacking. We introduce ManiGuard, a specification-grounded framework for evaluating and improving the safety of foundation-model manipulation, comprising the ManiGuard-Bench task suite and a paired safety-annotated trajectory-generation pipeline. ManiGuard-Bench organizes six contact-rich household task families into 200 locked base tasks along a skill $\times$ constraint taxonomy, with safety specified independently of task success. Each task is evaluated under one in-distribution and four single-axis out-of-distribution perturbations that hold the safety specification fixed, giving 1,000 locked scenarios. Every rollout is runtime-checked by LTL$_f$-grounded automaton monitors over physics-grounded predicates rather than learned classifiers or LLM judges, in simulation and on a physical Franka platform. The pipeline pairs an automated motion-planning generator with human teleoperation, annotated by the same per-step monitor, and directly supports safety-aware fine-tuning; we release 8,000 safety-annotated demonstrations, 40 per base task. Benchmarking zero-shot and fine-tuned VLAs across more than 23,000 rollouts, we find: (i) safety must be evaluated independently of task success, as 6-21% of successful rollouts violate the specification; (ii) fine-tuning on our suite raises safe task completion from near zero to 7.5-29.8% and engaged-and-safe behavior from 16-40% to 51-72%; but (iii) a gap remains that scaling demonstrations does not close, with 21-42% of engaged rollouts still violating, two of six families below 2% safe success for every policy, and these failures persisting under distribution shift and on hardware. △ Less

Submitted 18 August, 2026; originally announced August 2026.

OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction

Authors: Hongbo Gao, Wei Zhang, Zeyu Ni, Dihao Zhu, Ruifeng Li, Yunke Wang, Chang Xu

Abstract: Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene cov… ▽ More Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene coverage while leaving partially observed objects incompletely reconstructed. To address this limitation, we propose OccamView, an object-conditioned view-selection framework for frame-budgeted active 3D Gaussian reconstruction. Rather than predicting unseen object geometry or performing shape completion, OccamView maintains an online object memory from open-vocabulary detections grounded in measured RGB-D observations and represents unresolved local occupancy around detected objects as conservative hidden-region proxies. Candidate viewpoints are then evaluated using an occlusion-aware proxy-coverage score. Furthermore, we introduce a Geo-Floor mechanism that restricts object-conditioned re-ranking to geometrically competitive candidates, allowing object-conditioned cues to guide complementary observations while preserving the geometry-driven exploration behavior of the underlying planner. Experiments on Replica and Matterport3D under a unified frame-budgeted protocol show that OccamView consistently reduces Completion and improves Completion Ratio across five frame budgets, with particularly pronounced gains under limited frame budgets. These results demonstrate that lightweight object-conditioned cues effectively complement geometry-driven active view planning. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Comments: 7 pages, 5 figures. Preprint

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Authors: Shuo Liang, Yixing Ma, Pengfei Zhou, Zhenglin Wan, Xingyan Chen, Zihan Mei, Manting Li, Feihan Chen, Zhiwen Wang, Bin Xu, Haotian Zhang, Jiajun Song, Shiya Su, Run Liu, Zhenghang Ni, Yifa Yu, Jintao Hong, Bolong Feng, Yifei Liu, Zirui Zhang, Jingxuan Zhang, Songlin Zhao, Yifan Bai, Kang Tan, Yizhe Liu , et al. (11 additional authors not shown)

Abstract: Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial risks of misinformation. Existing benchmarks, however, provide limited evidence on detector and generator behavior in such settings, including how detectability varies with generation conditions, how people perceive generated videos, and whether detec… ▽ More Recent video generators can fabricate realistic depictions of wars, disasters, public emergencies, and other real-world crises, creating substantial risks of misinformation. Existing benchmarks, however, provide limited evidence on detector and generator behavior in such settings, including how detectability varies with generation conditions, how people perceive generated videos, and whether detectors remain reliable during social dissemination. To address this gap, we introduce RA-Bench, a benchmark for AI-generated video detection that uses Real videos as Anchors. RA-Bench contains 17,886 videos, comprising 1,830 real-video anchors across 10 social-risk categories and 16,056 generated clips from four open-source and five closed-source generators. Based on RA-Bench, we organize our evaluation along three dimensions. We first assess detector generalization across seven traditional detectors, ten zero-shot multimodal models under three review settings, and two MLLMs specifically fine-tuned on AI-generated video detection. Across these methods, none of the three detector families generalizes consistently across RA-Bench instances. We then examine how detectability varies with generation quality, conditioning information, and sampling seeds. These analyses show that generation properties affect detector families differently, while source-level detection patterns remain stable across seeds. Finally, we study human authenticity judgments and detector reliability during social dissemination. We find that videos that mislead people are also difficult for current detectors, and that social dissemination makes detection harder. Together, these findings show that current methods struggle to detect realistic AI-generated videos, highlighting the need for detectors robust to evolving video generators. △ Less

Submitted 16 August, 2026; v1 submitted 14 August, 2026; originally announced August 2026.

Comments: 63 pages, 20 figures, 32 tables

The Quartic Hessian Conjecture in Dimension Four

Authors: Zixiang Ni

Abstract: The Hessian conjecture asks whether a polynomial with nonzero constant Hessian determinant has a polynomial gradient inverse. It is known in dimensions at most three, false in dimensions at least five, and open in dimension four. We prove its four-variable quartic case. The top homogeneous part has zero Hessian determinant and, by the four-dimensional homogeneous Hesse theorem, is a cone. We div… ▽ More The Hessian conjecture asks whether a polynomial with nonzero constant Hessian determinant has a polynomial gradient inverse. It is known in dimensions at most three, false in dimensions at least five, and open in dimension four. We prove its four-variable quartic case. The top homogeneous part has zero Hessian determinant and, by the four-dimensional homogeneous Hesse theorem, is a cone. We divide its cone representative into three exhaustive types: a genuinely ternary quartic with nonzero ternary Hessian, a genuinely binary quartic, and a fourth power of a linear form. In the first type, the degree-seven determinant equation forces the cubic part to be affine-linear in the cone direction. In the binary type, the degree-six equation gives a constant null direction in a two-variable Hessian of the cubic part. In the unary type, the degree-five equation and a constant-direction lemma give the same conclusion. Every type therefore reduces to \[ f=P(x_1,x_2,x_3)+x_4Q(x_1,x_2,x_3)+a x_4^2, \qquad °Q\leq2. \] We prove, independently of the degree or top part of \(P\), that every constant-Hessian polynomial of this form has a polynomial gradient inverse. The branch \(a\ne0\) descends from the known three-dimensional Hessian conjecture after a Schur complement. When \(a=0\), an isotropic-cone rank analysis eliminates rank two, solves the rank-one exception by an explicit triangular inverse, and reduces rank zero to the two-dimensional Hessian conjecture. The coupled degree-six identity is retained throughout; no component with respect to a fixed quadratic form is separated. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation

Authors: Yunhao Zhao, Zhenyang Ni, Haoyang Chen, Ruohan Zhang, Qi Zhu

Abstract: Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observation or a short fixed-length history. However, real-world manipulation is often non-Markovian, requiring robots to retain and reason over task-relevant information from long-horizon interaction histories to determine the next action. To address this… ▽ More Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observation or a short fixed-length history. However, real-world manipulation is often non-Markovian, requiring robots to retain and reason over task-relevant information from long-horizon interaction histories to determine the next action. To address this challenge, we propose HyMeS, a hybrid learning framework that leverages the reasoning and memory-management capabilities of coding agents to steer a Markovian VLA for memory-dependent manipulation. Specifically, HyMeS learns low-level motor skills through gradient-based imitation learning, while a coding agent acquires high-level memory-management strategies through heuristic learning by iteratively updating an executable heuristic system from rollout feedback. Furthermore, we close the loop between steering and execution through multimodal stage-completion verification, which updates memory using proprioceptive signals and multi-frame VLM judgments. Compared with end-to-end memory-augmented VLAs, HyMeS requires demonstrations only for reusable motor skills rather than for every history-dependent task configuration, enabling data-efficient compositional generalization. On RoboMemArena, HyMeS improves mean cumulative success from 52.5% to 66.2% and mean task success from 41.3% to 60.1% over pi0.5, while outperforming PrediMem by 4.5 points in cumulative success and 14.5 points in task success. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 9 pages, 4 figures, and 3 tables

Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming

Authors: Menglin Han, Yang Ding, Yulei Lu, Haoran Yu, Xin Ma, Junyi Chen, Zhangkai Ni, Lin Ma, Yaohui Wang

Abstract: Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas. First, autoregressively reusing generated blocks as context creates exposure bias, causing errors and visual drift to accumulate over long rollouts. Second,… ▽ More Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual consistency. Adapting a pretrained bidirectional model to this setting presents two key dilemmas. First, autoregressively reusing generated blocks as context creates exposure bias, causing errors and visual drift to accumulate over long rollouts. Second, a global speech utterance does not indicates a causal generator which portion should be spoken next when only limited local audio-video context is available. We present Vorch-Streamer, a post-training framework that addresses these challenges and enables real-time long-form Text-to-Audio-Video (T2AV) streaming. We construct a synthetic corpus of 80K avatar clips spanning 12-21 seconds and first train a causal generator with mixed Teacher Forcing and Diffusion Forcing. We then apply long-horizon Self Forcing with DMD distillation, exposing the model to its own rollout distribution while preserving the quality of the pretrained bidirectional teacher. To explicitly control speech progression, an external language model predicts discrete 25-Hz speech-planning tokens, whose continuous features condition the audio diffusion branch and align each causal block with the content it should speak. With bounded causal context and four-step denoising, Vorch-Streamer jointly generates audio and video from text at 27.12 FPS, exceeding the 24-FPS real-time playback rate while maintaining competitive audio-lip synchronization and strong identity preservation over long-form generation. △ Less

Submitted 6 August, 2026; v1 submitted 6 August, 2026; originally announced August 2026.

Comments: Project page: https://vorch-project.github.io/Vorch-Streamer-project/

SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models

Authors: Yaozhi Wen, Jialong Guo, Zhenliang Ni, Han Shu, Xinghao Chen

Abstract: While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter sizes lead to significant computational overhead, limiting their deployment on resource-constrained devices. While pruning has been effective for compressing Large Language Models (LLMs), directly applying it to VLMs leads to significant performan… ▽ More While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter sizes lead to significant computational overhead, limiting their deployment on resource-constrained devices. While pruning has been effective for compressing Large Language Models (LLMs), directly applying it to VLMs leads to significant performance drops, largely due to redundant visual tokens interfering with importance estimation. To this end, we propose SlimVLM, a structured pruning framework designed to compress VLMs while preserving their task performance. We introduce an adaptive visual token selection strategy for VLMs that leverages average text-to-visual attention scores to assess the importance of visual tokens, removing redundant ones during pruning based on a set threshold, thereby optimizing the importance calculation. Recognizing the varying tolerance to sparsity across different modules, we also propose a Sensitivity-aware dynamic pruning mechanism that determines the appropriate pruning ratio for each module by calculating the linear reconstruction error between the outputs of the pruned and unpruned modules, ensuring overall performance stability. Experimental results show that SlimVLM outperforms existing methods across multiple multimodal benchmarks, achieving state-of-the-art performance. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Partially-Observable Transmission Control for UAV-Enabled Federated Learning in IoT Networks

Authors: Masoud Ghazikor, Zhou Ni, Morteza Hashemi

Abstract: Uncrewed aerial vehicle (UAV)-enabled federated learning (FL) can provide flexible, on-demand edge intelligence for large-scale IoT deployments, but operating in shared unlicensed bands makes uplink update delivery interference-coupled and unreliable. In this paper, we develop a packet-level transmission framework that captures buffer overflow, delay violations, and transmission errors, and uses t… ▽ More Uncrewed aerial vehicle (UAV)-enabled federated learning (FL) can provide flexible, on-demand edge intelligence for large-scale IoT deployments, but operating in shared unlicensed bands makes uplink update delivery interference-coupled and unreliable. In this paper, we develop a packet-level transmission framework that captures buffer overflow, delay violations, and transmission errors, and uses the resulting packet delivery ratio (PDR) to represent partial-update reception through a packetized, Bernoulli-masked FL aggregation process. We then formulate a fairness-consensus bilevel (FCB) optimization that jointly controls (i) transmission thresholds to maximize the average PDR while reaching consensus under partial observability and (ii) transmission powers to improve the worst PDR and enforce fairness across IoT learners. To solve this problem, we propose an alternating FCB optimizer composed of a consensus-based threshold controller (CTC), which drives the IoT learners toward a PDR-efficient consensus on transmission thresholds, and a fairness-based power controller (FPC), which updates transmission powers to improve the worst PDR and ensure fairness under the resulting consensus thresholds. Numerical results on CNN-based FL tasks show that the FCB optimizer improves FL aggregation and training performance by enhancing packet-level update delivery, consistently outperforming baseline transmission policies. △ Less

Submitted 1 August, 2026; originally announced August 2026.

Comments: GLOBECOM 2026-2026 IEEE Global Communications Conference

Fast Trainable Multilinear Bases for Image Compression

Authors: Shiwen An, Zhongyi Ni, Huanhai Zhou, Jin-Guo Liu

Abstract: The Discrete Fourier Transform, the Discrete Cosine Transform, and their block-wise variants underpin most deployed image and video codecs. Their effectiveness rests on three properties: they run in near-linear time (linear up to a polylogarithmic factor), they are exactly invertible, and they carry few to no parameters. In this work, we generalize these bases to isometric multilinear bases, allow… ▽ More The Discrete Fourier Transform, the Discrete Cosine Transform, and their block-wise variants underpin most deployed image and video codecs. Their effectiveness rests on three properties: they run in near-linear time (linear up to a polylogarithmic factor), they are exactly invertible, and they carry few to no parameters. In this work, we generalize these bases to isometric multilinear bases, allowing a small number of extra parameters, polylogarithmic in the image size, while preserving all three properties. Given an image dataset, we develop a systematic framework that searches this family for the basis compressing the dataset most effectively: the basis is parameterized as an isometric tensor network, inspired by quantum many-body theory, and trained with Riemannian optimization on the manifold of unitary matrices. Across natural photographs and line drawings, the trained bases consistently improve on their fixed, non-parametric counterparts. On Quick Draw line-drawing compression, they store images in roughly $20\%$ fewer bytes than JPEG's $8 \times 8$ block cosine transform at the same reconstruction quality. △ Less

Submitted 17 August, 2026; v1 submitted 26 July, 2026; originally announced August 2026.

LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA

Authors: Zhilin Wu, Zhangkai Ni, Chengmei Yang, Longzhen Yang, Yihang Liu, Ying Wen, Lianghua He

Abstract: In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal information is crucial for reliable assessment of disease progression and treatment response. However, despite the rapid advancement of multimodal large language models (MLLMs), longitudinal medical visual reasoning remains largely underexplored. To… ▽ More In clinical practice, patients often undergo multiple imaging examinations over successive visits, yielding longitudinal data. Modeling such temporal information is crucial for reliable assessment of disease progression and treatment response. However, despite the rapid advancement of multimodal large language models (MLLMs), longitudinal medical visual reasoning remains largely underexplored. To fill this gap, we propose LoMeVQA, a comprehensive benchmark consisting of 206K longitudinal visual question answering (VQA) pairs for temporal medical image analysis. LoMeVQA covers five tasks: progress classification, progress description, progress report generation, differential region grounding, and differential region description. To construct the dataset, we develop an automated pipeline that (1) organizes patient records chronologically, (2) extracts clinically meaningful entities via a medical knowledge graph, and (3) models their temporal evolution to guide large language models in generating high-quality longitudinal VQA pairs. Extensive evaluations demonstrate that both general-purpose and medical-domain MLLMs perform poorly on LoMeVQA, revealing substantial limitations in temporal reasoning. To address these limitations, we introduce MedLong-8B, which achieves state-of-the-art performance across all tasks. Beyond benchmarking, we conduct detailed analyses that uncover key failure modes and shed light on how to improve longitudinal medical visual reasoning. Our data is available at: https://github.com/pepperbubble/LoMeVQA △ Less

Submitted 30 July, 2026; originally announced July 2026.

Comments: 23 pages, 17 figures, 7 tables. Code and data: https://github.com/pepperbubble/LoMeVQA

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Authors: Haolei Xu, Xiaowen Xu, Haiwen Hong, Zixuan Ni, Hongxing Li, Yiwen Qiu, Weiming Lu, Yongliang Shen

Abstract: On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, w… ▽ More On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute. We identify a teacher-student continuation asymmetry on failed prefixes, where the teacher tends to redirect while the student continues along the original direction, and convert it into a label-free handoff trigger in Relay On-Policy Distillation (Relay-OPD). During training, Relay-OPD constructs relay trajectories by letting the teacher briefly take over at detected trigger points to produce a teacher leg, after which the student resumes and is optimized on the resulting trajectory. A limited relay budget concentrates intervention on critical early positions while limiting departure from the student policy. With a Qwen3-4B-Instruct-2507 teacher and Qwen3-0.6B/1.7B-Non-Thinking students on eight mathematical reasoning benchmarks, Relay-OPD achieves the best or second-best results on every benchmark, outperforming standard OPD by +5.73% and the strongest baseline FastOPD by +1.49% on average for 1.7B, with consistent gains at 0.6B. Training trajectory length is reduced by over 50%. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: Project Page: https://zju-real.github.io/Relay-OPD Code: https://github.com/zju-real/Relay-OPD

FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents

Authors: Xianfu Cheng, Shiwei Zhang, Jiyu Zhao, Jian Yang, Xinyuan Wang, Ming Zhou, Weixiao Zhou, Xiangyuan Guan, Xiang Li, Zhenhe Wu, Ziyi Ni, Zhoujun Li, Bingjing Xu

Abstract: Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale information and generate reliable and accurate content. However, when handling complex real-world problems, different agents still show significant performance variation. In this work, we design Finance-LaTeX SKILL, a skill for synthesizing financial documents with complex layouts… ▽ More Agentic Reasoning has become a transformative force in financial analysis due to its ability to integrate large-scale information and generate reliable and accurate content. However, when handling complex real-world problems, different agents still show significant performance variation. In this work, we design Finance-LaTeX SKILL, a skill for synthesizing financial documents with complex layouts based on expert knowledge. Using an agent workflow built on this skill, we generate 2,000 professional financial documents along with 6,000 high-quality question-answer pairs. To evaluate the overall capability of agents, we introduce FinanceComplexQA, a comprehensive open-ended generation benchmark for financial documents that closely resembles real-world scenarios. It contains 2,026 deep research tasks targeting 1009 financial documents. FinanceComplexQA has 8 key features: bilingual support; coverage of six mainstream scenarios and seven tasks; expert-level document reasoning questions; deep research of complex layouts; relatively stable and permanent reference answers; and precise evaluation through an Agent-as-a-Judge with multiple evaluation metrics. Using FinanceComplexQA, we conduct a comprehensive evaluation of leading RAG systems and agentic reasoning tools for financial document QA. Through identifying and analyzing failure cases, we provide an in-depth study of their capabilities in numerical computation, multi-hop reasoning, content summarization, and industry analysis. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: 27 pages, 9 tables, 2 figures

Variable-Length Generative Protein Design via Generalized Poisson Flow

Authors: Chaoran Cheng, Zhanghan Ni, Yanru Qu, Yuxin Chen, Ruihan Guo, Jiajun Fan, Ge Liu

Abstract: The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- and flow-based generative models typically require the protein length to be specified before sampling, limiting their flexibility in exploring the feasible design space. To address this limitation, we introduce Generalized… ▽ More The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- and flow-based generative models typically require the protein length to be specified before sampling, limiting their flexibility in exploring the feasible design space. To address this limitation, we introduce Generalized Poisson Flow (GPFlow), a variable-length generative framework that learns the rate function of an inhomogeneous generalized Poisson process by minimizing its negative log-likelihood. We establish population-level guarantees for recovering the joint multimodal distribution and derive an upper bound on the KL divergence between the data and generated distributions. We comprehensively evaluate GPFlow across structure and sequence design, motif scaffolding, and peptide co-design, spanning Euclidean, categorical, and Riemannian modalities to fully validate its variable-length generation quality. In unconditional design, GPFlow improves structural designability and achieves the best distributional fitness for sequence design compared to their corresponding fixed-length baselines, while perfectly recovering the length distribution. In conditional motif scaffolding, GPFlow ranks first on 10 of 16 structure-based design tasks with significantly more unique successes and also achieves more passed tasks in sequence-based design. In peptide co-design, GPFlow remains competitive even without access to a native-length oracle. △ Less

Submitted 9 July, 2026; originally announced July 2026.

RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement

Authors: Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai

Abstract: Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object pairings, often resulting in concept omission or semantic drift where a dominant entity overwhelms the generation. Tracing these failures to a lack of compositional balance during the denoising trajectory, we propose RADIANCE, a training-free framew… ▽ More Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object pairings, often resulting in concept omission or semantic drift where a dominant entity overwhelms the generation. Tracing these failures to a lack of compositional balance during the denoising trajectory, we propose RADIANCE, a training-free framework that treats inference as a closed-loop feedback process. RADIANCE augments pretrained backbones with three modular components: (1) a Compositional Similarity Monitor (CSM) that tracks the emergence of objects and attributes in intermediate latents via CLIP-based feedback; (2) a Bidirectional Scale Controller (BSC) that applies a reactive "restoring force" using positive and negative IP-Adapter scales to rebalance biased trajectories; and (3) a Feedback Guidance Scheduler (FGS) that coordinates these updates across timesteps without additional training. We further extend the framework to multi-object prompts via Delayed Adapter Activation (DAA) and Layer-wise Alternating Guidance (LAG) to prevent premature concept fusion. By overlapping monitoring and denoising through pipelined execution, RADIANCE maintains competitive latency while significantly enhancing the per-sample success rate and effective throughput. Experiments on RareBench and T2I-CompBench demonstrate that RADIANCE consistently enhances compositional alignment and perceptual quality over state-of-the-art baselines. △ Less

Submitted 6 July, 2026; originally announced July 2026.

Comments: Accepted to ECCV 2026. Camera-ready version

Asymmetric physics enables efficient learning in quadrupedal robot swarms

Authors: Yuang Zhang, Yunlong Song, Zhihao He, Zelin Ni, Kangyu Wang, Tianchi Liu, Yu Hu, Feng Yu, Danping Zou, Weiyao Lin

Abstract: Animal collectives navigate cluttered environments through local coordination, yet robot swarms still struggle to reproduce this capability in the physical world. End-to-end learning offers a route to such coordination, but scaling it to embodied swarms remains difficult: standard sampling-based reinforcement learning becomes inefficient when visual perception, dense robot-robot interaction, and c… ▽ More Animal collectives navigate cluttered environments through local coordination, yet robot swarms still struggle to reproduce this capability in the physical world. End-to-end learning offers a route to such coordination, but scaling it to embodied swarms remains difficult: standard sampling-based reinforcement learning becomes inefficient when visual perception, dense robot-robot interaction, and contact-rich locomotion must be learned together. Here we show that asymmetric physics enables efficient end-to-end learning of vision-based, decentralized control in large swarms of quadrupedal robots. During training, quadrupeds interact in shared environments, where a high-fidelity, non-differentiable simulator generates realistic motion and contact dynamics, and differentiable surrogate models provide gradients for navigation and locomotion policies. This separation enables up to 512 quadrupeds to learn coordinated navigation policies in obstacle-rich environments. At deployment, each robot acts from a single forward-facing depth camera, without explicit communication, centralized planning, or global maps. The policies generalize across forests, bridges, enclosures, narrow passages, and mazes, and zero-shot transfer to six physical quadrupeds across five real-world scenarios. The resulting swarms exhibit predictive avoidance, right-side yielding, pausing before bottlenecks, and wall following, showing that asymmetric physics enables efficient training of scalable decentralized control policies for quadrupedal robot swarms. △ Less

Submitted 22 June, 2026; originally announced June 2026.

SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation

Authors: Songlin Wei, Zhenhao Ni, Jie Liu, Zhenyu Zhao, Junjie Ye, Hongyi Jing, Junkai Xia, Xiawei Liu, Michael Leong, Liang Heng, Di Huang, Yue Wang

Abstract: Humanoid foundation models are advancing faster than we can evaluate them. While real-world testing is expensive and difficult to reproduce, existing simulation benchmarks focus primarily on table-top or wheeled robots. A scalable and reproducible benchmark for whole-body humanoid loco-manipulation remains an open problem. To this end, we present SIMPLE, a unified simulation testbed for humanoid p… ▽ More Humanoid foundation models are advancing faster than we can evaluate them. While real-world testing is expensive and difficult to reproduce, existing simulation benchmarks focus primarily on table-top or wheeled robots. A scalable and reproducible benchmark for whole-body humanoid loco-manipulation remains an open problem. To this end, we present SIMPLE, a unified simulation testbed for humanoid policy learning and evaluation. SIMPLE couples the accurate contact-rich dynamics of MuJoCo with the photorealistic rendering of IsaacSim. It provides a large-scale environment comprising 60 diverse whole-body tasks, 50 indoor scenes, and over 1,000 object assets. To facilitate scalable data collection, the framework integrates two data generation pipelines: automated trajectory generation via motion planning and a low-latency VR teleoperation interface. We further integrate and benchmark mainstream humanoid policies at scale in SIMPLE, including lightweight imitation networks, large vision-language-action (VLA) models, and recent world action models (WAMs). Our experiments reveal a strong correlation between policy performance in simulation and the real world. Furthermore, we demonstrate that policies trained on data collected in SIMPLE can be transferred zero-shot to physical humanoid robots under similar settings, providing a robust and reproducible foundation for humanoid robotics research. △ Less

Submitted 6 June, 2026; originally announced June 2026.

A unified multi-task framework enables interpretable chest radiograph analysis

Authors: Lijian Xu, Ziyu Ni, Xinglong Liu, Xiaosong Wang, Hongsheng Li, Shaoting Zhang

Abstract: While multimodal deep learning has advanced medical imaging analysis, existing black-box systems \textcolor{black}{may remain confined to isolated tasks, often overlooking} the trust-sensitive nature of clinical diagnosis as a multi-task process. We propose IMT-CXR (Interpretable Multi-task Transformer for Chest X-ray Analysis), a framework that emulates radiologists' diagnostic workflow through t… ▽ More While multimodal deep learning has advanced medical imaging analysis, existing black-box systems \textcolor{black}{may remain confined to isolated tasks, often overlooking} the trust-sensitive nature of clinical diagnosis as a multi-task process. We propose IMT-CXR (Interpretable Multi-task Transformer for Chest X-ray Analysis), a framework that emulates radiologists' diagnostic workflow through three evidence-driven stages: 1) Disease recognition; 2) Attribute characterization (e.g., size, location, severity quantification); 3) Evidence-integrated report generation with traceable decision pathways. The framework employs a unified transformer architecture optimized via medical-domain instruction tuning, sequentially executing four clinical tasks: multi-label disease classification, lesion localization, anatomical segmentation, and radiology report generation. Experimental validation demonstrates competitive performance on ten CXR benchmarks under direct inference and fine-tuning settings. In a blinded evaluation of 160 historical reports from four medical centers, three radiologists rated 66\% of AI-generated reports as comparable to or surpassing original clinical reports in diagnostic clarity, highlighting the framework's translational potential. By establishing traceable diagnostic pathways from anatomical findings to conclusions, this work bridges the gap between AI technical metrics and clinical utility, advancing trustworthy AI systems in medical imaging. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Skillful high-resolution weather forecasting independent of physical models

Authors: Pengcheng Zhao, Siqi Xiang, Weixin Jin, Zekun Ni, Jiang Bian, Zuliang Fang, Hongyu Sun, Bin Zhang, Richard E. Turner, Jonathan Weyn, Haiyu Dong, Kit Thambiratnam, Qi Zhang

Abstract: Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end mod… ▽ More Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end models typically rely on NWP-generated reanalyses for supervision, thereby inheriting the biases and resolution limitations of those NWPs, and limiting adaptation to settings where suitable reanalysis products are unavailable, infrequently updated, or expensive to produce. Here we introduce ObsCast, a regional system that generates both analysis and predictions, without using any NWP-derived data in either training or inference, while still achieving state-of-the-art performance in short-term high-resolution regional modeling. Over the contiguous United States and Europe, ObsCast outperforms operational NWP for near-surface variables through 18 h and produces skillful precipitation forecasts. It provides a simpler and more adaptable route to build and refine regional forecasting services directly from local observations, without the need to develop complex and costly traditional forecasting pipelines. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Comments: 26 pages, 10 figures

Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity

Authors: Yiran Pang, Zhen Ni, Xiangnan Zhong

Abstract: Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous environments where differing state-transition dynamics lead to non-identical input distributions and imbalanced parameter updates during aggregation. Therefore, this p… ▽ More Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous environments where differing state-transition dynamics lead to non-identical input distributions and imbalanced parameter updates during aggregation. Therefore, this paper develops a personalized observation normalization (PON) method, allowing each agent to locally normalize raw state inputs using a continuously updated running mean and variance. This design ensures consistent scaling of local feature without overshadowing across agents during aggregation. Furthermore, we demonstrate that sharing normalization parameters across agents is ineffective due to the diverse local input distributions, which highlights the necessity of personalized statistics. Experiments on heterogeneous MuJoCo tasks show that our developed PON accelerates training and achieves superior performance compared to baseline methods. △ Less

Submitted 10 April, 2026; originally announced May 2026.

Comments: Accepted at the International Joint Conference on Neural Networks (IJCNN) 2025

BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization

Authors: Zhengyang Ni, Feng Yan, Yu Guo, Fei Wang

Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability. Existing brick generation methods either rely on heuristic optimization, which can break down when the target 3D shape does not admit a feasible structure under predefined constraints, or generate brick sequenc… ▽ More Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability. Existing brick generation methods either rely on heuristic optimization, which can break down when the target 3D shape does not admit a feasible structure under predefined constraints, or generate brick sequences without explicitly modeling the underlying 3D geometry and assembly relations. In this work, we present BrickAnything, a geometry-conditioned autoregressive framework for generating buildable brick structures from diverse 3D representations. BrickAnything uses point clouds as a unified geometric interface and predicts brick sequences that reconstruct the target shape under assembly constraints. To model structural dependencies among bricks, we introduce a structure-aware tree tokenization, which represents brick structures through local attachment relations. This formulation makes sequence generation more consistent with the physical construction process, and reduces invalid intermediate states. We further introduce preference-based alignment post-training, validity-constrained decoding and adaptive rollback to improve buildability objectives such as stability and geometric fidelity. Extensive experiments demonstrate that BrickAnything produces geometrically faithful and physically realizable brick structures, and that the proposed tokenization effectively reduces rollback and regeneration compared with conventional ordering strategies. △ Less

Submitted 15 August, 2026; v1 submitted 25 May, 2026; originally announced May 2026.

Comments: Revised version with updated Code: https://github.com/xjtunzy/BrickAnything

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Authors: Yang Yue, Fangyun Wei, Tianyu He, Jinjing Zhao, Zanlin Ni, Zeyu Liu, Jiayi Guo, Lei Shi, Yue Dong, Li Chen, Ji Li, Gao Huang, Dong Chen

Abstract: Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attri… ▽ More Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features. We attribute this gap to standard discrete-tokenizer objectives being weakly aligned with text legibility and facial fidelity, as these objectives typically optimize generic reconstruction while compressing diverse content uniformly. To address this, we propose InsightTok, a simple yet effective discrete visual tokenization framework that enhances text and face fidelity through localized, content-aware perceptual losses. With a compact 16k codebook and a 16x downsampling rate, InsightTok significantly outperforms prior tokenizers in text and face reconstruction without compromising general reconstruction quality. These gains consistently transfer to autoregressive image generation in InsightAR, producing images with clearer text and more faithful facial details. Overall, our results highlight the potential of specialized supervision in tokenizer training for advancing discrete image generation. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: Code and checkpoints are available at https://github.com/LeapLabTHU/InsightTok

CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL

Authors: Zhenyang Ni, Yijiang Li, Ruochen Jiao, Simon Sinong Zhan, Sipeng Chen, Zhenfei Yin, Minshuo Chen, Philip Torr, Zhaoran Wang, Qi Zhu

Abstract: Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training offers a natural route to adapting VGMs, existing video-RL rewards often reduce each rollout to a low-level visual metric, whereas manipulation video evaluation re… ▽ More Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training offers a natural route to adapting VGMs, existing video-RL rewards often reduce each rollout to a low-level visual metric, whereas manipulation video evaluation requires logic-based verification of whether the rollout satisfies a compositional task specification. To fill this gap, we introduce a compositional constraint-based reward model for post-training embodied video generation models, which automatically formulates task requirements as a composition of Linear Temporal Logic constraints, providing faithful rewards and localized error information in generated videos. To achieve effective improvement in high-dimensional video generation using these reward signals, we further propose CreFlow, a novel online RL framework with two key designs: i) a credit-aware NFT loss that confines the RL update to reward-relevant regions, preventing perturbations to unrelated regions during post-training; and ii) a corrective reflow loss that leverages within-group positive samples as an explicit estimate of the correction direction, stabilizing and accelerating training. Experiments show that CreFlow yields reward judgments better aligned with human and simulator success labels than existing methods and improves downstream execution success by 23.8 percentage points across eight bimanual manipulation tasks. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

Authors: Zeyu Liu, Zanlin Ni, Yang Yue, Cheng Da, Huan Yang, Di Zhang, Kun Gai, Gao Huang

Abstract: Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to… ▽ More Unified multimodal models are envisioned to bridge the gap between understanding and generation. Yet, to achieve competitive performance, state-of-the-art models adopt largely decoupled understanding and generation components. This design, while effective for individual tasks, weakens the connection required for mutual enhancement, leaving the potential synergy empirically uncertain. We propose to explicitly restore this synergy by introducing Understanding-Oriented Post-Training (UNO), a lightweight framework that treats understanding not only as a distinct task, but also a direct supervisory signal to steer generative representations. By incorporating objectives that encode semantic abstraction (captioning) and structural details (visual regression), we enable effective gradient flow from understanding to generation. Extensive experiments on image generation and editing demonstrate that understanding can serve as an effective catalyst for generation. △ Less

Submitted 7 May, 2026; originally announced May 2026.

Enhancing AI and Dynamical Subseasonal Forecasts with Probabilistic Bias Correction

Authors: Hannah Guan, Soukayna Mouatadid, Paulo Orenstein, Judah Cohen, Haiyu Dong, Zekun Ni, Jeremy Berman, Genevieve Flaspohler, Alex Lu, Jakob Schloer, Joshua Talib, Jonathan A. Weyn, Lester Mackey

Abstract: Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ah… ▽ More Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ahead), due to compounding errors, systemic model biases, and the chaotic nature of the atmosphere. To counter this degradation, we introduce probabilistic bias correction (PBC), a machine learning framework that substantially reduces systematic error by learning to correct historical probabilistic forecasts. When applied to the leading dynamical and AI models from the European Centre for Medium-Range Weather Forecasts (ECMWF), PBC doubles the modest subseasonal skill of the AI Forecasting System and improves the skill of the operationally-debiased dynamical model for 91% of pressure, 92% of temperature, and 98% of precipitation targets. We designed PBC for operational deployment, and, in ECMWF's 2025 real-time forecasting competition, its global forecasts placed first for all weather variables and lead times, outperforming the dynamical models from six operational forecasting centers, an international dynamical multi-model ensemble, ECMWF's AI Forecasting System, and the forecasting systems of 34 teams worldwide. These probabilistic skill gains translate into more accurate prediction of extreme events and have the potential to improve agricultural planning, energy management, and disaster preparedness in vulnerable communities. △ Less

Submitted 10 July, 2026; v1 submitted 17 April, 2026; originally announced April 2026.

Draft-and-Prune: Improving the Reliability of Auto-formalization for Logical Reasoning

Authors: Zhiyu Ni, Zheng Liang, Liangcheng Song, Chenrui Cao, Xian Zhang, Alberto Sangiovanni-Vincentelli, Pierluigi Nuzzo

Abstract: Auto-formalization (AF) translates natural-language reasoning problems into solver-executable programs, enabling symbolic solvers to perform sound logical deduction. In practice, however, AF pipelines are currently brittle: programs may fail to execute, or execute but encode incorrect semantics. While prior work largely mitigates syntactic failures via repairs based on solver feedback, reducing se… ▽ More Auto-formalization (AF) translates natural-language reasoning problems into solver-executable programs, enabling symbolic solvers to perform sound logical deduction. In practice, however, AF pipelines are currently brittle: programs may fail to execute, or execute but encode incorrect semantics. While prior work largely mitigates syntactic failures via repairs based on solver feedback, reducing semantics failures remains a major bottleneck. We propose Draft-and-Prune (D&P), an inference-time framework that improves AF-based logical reasoning via diversity and verification. D&P first drafts multiple natural-language plans and conditions program generation on them. It further prunes executable but contradictory or ambiguous formalizations, and aggregates predictions from surviving paths via majority voting. Across four representative benchmarks (AR-LSAT, ProofWriter, PrOntoQA, LogicalDeduction), D&P substantially strengthens AF-based reasoning without extra supervision. On AR-LSAT, in the AF-only setting, D&P achieves 78.43% accuracy with GPT-4 and 78.00% accuracy with GPT-4o, significantly outperforming the strongest AF baselines MAD-LOGIC and CLOVER. D&P then attains near-ceiling performance on the other benchmarks, including 100% on PrOntoQA and LogicalDeduction. △ Less

Submitted 26 March, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes

Authors: Xinxin Jin, Zhengwei Ni, Zhengguo Sheng, Victor C. M. Leung

Abstract: As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face significant challenges regarding reliability and interaction efficiency. Direct execution of LLM-generated commands often leads to entity hallucinations (e.g., trying to control non-existent devices). Meanwhile, existing iterative frameworks (e.g., SAGE) suffer from t… ▽ More As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face significant challenges regarding reliability and interaction efficiency. Direct execution of LLM-generated commands often leads to entity hallucinations (e.g., trying to control non-existent devices). Meanwhile, existing iterative frameworks (e.g., SAGE) suffer from the Interaction Frequency Dilemma, oscillating between reckless execution and excessive user questioning. To address these issues, we propose a Dual-Stage Intent-Aware (DS-IA) Framework. This framework separates high-level user intent understanding from low-level physical execution. Specifically, Stage 1 serves as a semantic firewall to filter out invalid instructions and resolve vague commands by checking the current state of the home. Stage 2 then employs a deterministic cascade verifier-a strict, step-by-step rule checker that verifies the room, device, and capability in sequence-to ensure the action is actually physically possible before execution. Extensive experiments on the HomeBench and SAGE benchmarks demonstrate that DS-IA achieves an Exact Match (EM) rate of 58.56% (outperforming baselines by over 28%) and improves the rejection rate of invalid instructions to 87.04%. Evaluations on the SAGE benchmark further reveal that DS-IA resolves the Interaction Frequency Dilemma by balancing proactive querying with state-based inference. Specifically, it boosts the Autonomous Success Rate (resolving tasks without unnecessary user intervention) from 42.86% to 71.43%, while maintaining high precision in identifying irreducible ambiguities that truly necessitate human clarification. These results underscore the framework's ability to minimize user disturbance through accurate environmental grounding. △ Less

Submitted 17 March, 2026; originally announced March 2026.

$Ψ_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation

Authors: Songlin Wei, Hongyi Jing, Boqian Li, Zhenyu Zhao, Jiageng Mao, Zhenhao Ni, Sicheng He, Jie Liu, Xiawei Liu, Kaidi Kang, Sheng Zang, Weiduo Yuan, Marco Pavone, Di Huang, Yue Wang

Abstract: We introduce $Ψ_0$ (Psi-Zero), an open foundation model to address challenging humanoid loco-manipulation tasks. While existing approaches often attempt to address this fundamental problem by co-training on large and diverse human and humanoid data, we argue that this strategy is suboptimal due to the fundamental kinematic and motion disparities between humans and humanoid robots. Therefore, data… ▽ More We introduce $Ψ_0$ (Psi-Zero), an open foundation model to address challenging humanoid loco-manipulation tasks. While existing approaches often attempt to address this fundamental problem by co-training on large and diverse human and humanoid data, we argue that this strategy is suboptimal due to the fundamental kinematic and motion disparities between humans and humanoid robots. Therefore, data efficiency and model performance remain unsatisfactory despite the considerable data volume. To address this challenge, \ours\;decouples the learning process to maximize the utility of heterogeneous data sources. Specifically, we propose a staged training paradigm with different learning objectives: First, we autoregressively pre-train a VLM backbone on large-scale egocentric human videos to acquire generalizable visual-action representations. Then, we post-train a flow-based action expert on high-quality humanoid robot data to learn precise robot joint control. Our research further identifies a critical yet often overlooked data recipe: in contrast to approaches that scale with noisy Internet clips or heterogeneous cross-embodiment robot datasets, we demonstrate that pre-training on high-quality egocentric human manipulation data followed by post-training on domain-specific real-world humanoid trajectories yields superior performance. Extensive real-world experiments demonstrate that \ours\ achieves the best performance using only about 800 hours of human video data and 30 hours of real-world robot data, outperforming baselines pre-trained on more than 10$\times$ as much data by over 40\% in overall success rate across multiple tasks. We will open-source the entire ecosystem to the community, including a data processing and training pipeline, a humanoid foundation model, and a real-time action inference engine. △ Less

Submitted 12 March, 2026; originally announced March 2026.

AdaGen: Learning Adaptive Policy for Image Synthesis

Authors: Zanlin Ni, Yulin Wang, Yeguo Hua, Renping Zhou, Jiayi Guo, Jun Song, Bo Zheng, Gao Huang

Abstract: Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their success is the decomposition of synthesis into multiple steps. However, this introduces a proliferation of step-specific parameters (e.g., noise level or temperatur… ▽ More Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their success is the decomposition of synthesis into multiple steps. However, this introduces a proliferation of step-specific parameters (e.g., noise level or temperature at each step). Existing approaches typically rely on manually-designed rules to manage this complexity, demanding expert knowledge and trial-and-error. Furthermore, these static schedules lack the flexibility to adapt to the unique characteristics of each sample, yielding sub-optimal performance. To address this issue, we present AdaGen, a general, learnable, and sample-adaptive framework for scheduling the iterative generation process. Specifically, we formulate the scheduling problem as a Markov Decision Process, where a lightweight policy network determines suitable parameters given the current generation state, and can be trained through reinforcement learning. Importantly, we demonstrate that simple reward designs, such as FID or pre-trained reward models, can be easily hacked and may not reliably guarantee the desired quality or diversity of generated samples. Therefore, we propose an adversarial reward design to guide the training of the policy networks. Finally, we introduce an inference-time refinement strategy and a controllable fidelity-diversity trade-off mechanism to further enhance the performance and flexibility of AdaGen. Comprehensive experiments on four generative paradigms validate the superiority of AdaGen. For example, AdaGen achieves better performance on DiT-XL with 3 times lower inference cost and improves the FID of VAR from 1.92 to 1.59 with negligible computational overhead. △ Less

Submitted 6 March, 2026; originally announced March 2026.

Comments: Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Journal version of arXiv:2409.00342 (ECCV 2024). Code is available at: https://github.com/LeapLabTHU/AdaGen

EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation

Authors: Gehao Zhang, Zhenyang Ni, Payal Mohapatra, Han Liu, Ruohan Zhang, Qi Zhu

Abstract: Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynamics, offering a compelling foundation for zero-shot robotic manipulation. However, VGMs often produce physically implausible rollouts, and converting their pixel-space motion into robot actions through geometric retargeting further introduces cumulativ… ▽ More Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynamics, offering a compelling foundation for zero-shot robotic manipulation. However, VGMs often produce physically implausible rollouts, and converting their pixel-space motion into robot actions through geometric retargeting further introduces cumulative errors from imperfect depth estimation and keypoint tracking. To address these challenges, we present \method{}, a data-free framework that aligns VGM outputs with compositional constraints generated by vision-language models (VLMs) at inference time. The key insight is that VLMs offer a capability complementary to VGMs: structured spatial reasoning that can identify the physical constraints critical to the success and safety of manipulation execution. Given a language instruction, \method{} uses a VLM to automatically extract a set of compositional constraints capturing task-specific requirements, which are then applied at two stages: (1) constraint-guided rollout selection, which scores and filters a batch of VGM rollouts to retain the most physically plausible candidate, and (2) constraint-based trajectory optimization, which uses the selected rollout as initialization and refines the robot trajectory under the same constraint set to correct retargeting errors. We evaluate \method{} on six real-robot manipulation tasks requiring precise, constraint-sensitive execution, improving the overall success rate by 43.3\% points over the strongest baseline without any task-specific training data. △ Less

Submitted 5 March, 2026; originally announced March 2026.

LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving

Authors: Qihao Sun, Jiarun Liu, Ziqian Ni, Jianyun Xu, Tao Xie, Lijun Zhao, Ruifeng Li, Sheng Yang

Abstract: Accurate metric depth is critical for autonomous driving perception and simulation, yet current approaches struggle to achieve high metric accuracy, multi-view and temporal consistency, and cross-domain generalization. To address these challenges, we present DriveMVS, a novel multi-view stereo framework that reconciles these competing objectives through two key insights: (1) Sparse but metricall… ▽ More Accurate metric depth is critical for autonomous driving perception and simulation, yet current approaches struggle to achieve high metric accuracy, multi-view and temporal consistency, and cross-domain generalization. To address these challenges, we present DriveMVS, a novel multi-view stereo framework that reconciles these competing objectives through two key insights: (1) Sparse but metrically accurate LiDAR observations can serve as geometric prompts to anchor depth estimation in absolute scale, and (2) deep fusion of diverse cues is essential for resolving ambiguities and enhancing robustness, while a spatio-temporal decoder ensures consistency across frames. Built upon these principles, DriveMVS embeds the LiDAR prompt in two ways: as a hard geometric prior that anchors the cost volume, and as soft feature-wise guidance fused by a triple-cue combiner. Regarding temporal consistency, DriveMVS employs a spatio-temporal decoder that jointly leverages geometric cues from the MVS cost volume and temporal context from neighboring frames. Experiments show that DriveMVS achieves state-of-the-art performance on multiple benchmarks, excelling in metric accuracy, temporal stability, and zero-shot cross-domain transfer, demonstrating its practical value for scalable, reliable autonomous driving systems. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Agentified Assessment of Logical Reasoning Agents

Authors: Zhiyu Ni, Yifeng Xiao, Zheng Liang

Abstract: We present a framework for evaluating and benchmarking logical reasoning agents when assessment itself must be reproducible, auditable, and robust to execution failures. Building on agentified assessment, we use an assessor agent to issue tasks, enforce execution budgets, parse outputs, and record structured failure types, while the agent under test only needs to expose a standardized agent-to-age… ▽ More We present a framework for evaluating and benchmarking logical reasoning agents when assessment itself must be reproducible, auditable, and robust to execution failures. Building on agentified assessment, we use an assessor agent to issue tasks, enforce execution budgets, parse outputs, and record structured failure types, while the agent under test only needs to expose a standardized agent-to-agent interface. As a case study, we benchmark an auto-formalization agent for first-order logic (FOL) reasoning on a solver-verified and repaired split of FOLIO. The agent translates natural language premises and conclusions into executable Z3Py programs and employs satisfiability modulo theories (SMT) solving to determine logical entailment. On the cleaned FOLIO validation set, the auto-formalization agent achieves 86.70% accuracy under the assessor protocol, outperforming a chain-of-thought baseline (73.89%). △ Less

Submitted 2 April, 2026; v1 submitted 3 March, 2026; originally announced March 2026.

Comments: Accepted at ICLR 2026 Agents in the Wild (AIWILD) Workshop. 5 pages, 2 figures, 1 table

Rigidity-Aware Geometric Pretraining for Protein Design and Conformational Ensembles

Authors: Zhanghan Ni, Yanjing Li, Zeju Qiu, Bernhard Schölkopf, Hongyu Guo, Weiyang Liu, Shengchao Liu

Abstract: Generative models have recently advanced $\textit{de novo}$ protein design by learning the statistical regularities of natural structures. However, current approaches face three key limitations: (1) Existing methods cannot jointly learn protein geometry and design tasks, where pretraining can be a solution; (2) Current pretraining methods mostly rely on local, non-rigid atomic representations for… ▽ More Generative models have recently advanced $\textit{de novo}$ protein design by learning the statistical regularities of natural structures. However, current approaches face three key limitations: (1) Existing methods cannot jointly learn protein geometry and design tasks, where pretraining can be a solution; (2) Current pretraining methods mostly rely on local, non-rigid atomic representations for property prediction downstream tasks, limiting global geometric understanding for protein generation tasks; and (3) Existing approaches have yet to effectively model the rich dynamic and conformational information of protein structures. To overcome these issues, we introduce $\textbf{RigidSSL}$ ($\textit{Rigidity-Aware Self-Supervised Learning}$), a geometric pretraining framework that front-loads geometry learning prior to generative finetuning. Phase I (RigidSSL-Perturb) learns geometric priors from 432K structures from the AlphaFold Protein Structure Database with simulated perturbations. Phase II (RigidSSL-MD) refines these representations on 1.3K molecular dynamics trajectories to capture physically realistic transitions. Underpinning both phases is a bi-directional, rigidity-aware flow matching objective that jointly optimizes translational and rotational dynamics to maximize mutual information between conformations. Empirically, RigidSSL variants improve designability by up to 43% while enhancing novelty and diversity in unconditional generation. Furthermore, RigidSSL-Perturb improves the success rate by 5.8% in zero-shot motif scaffolding and RigidSSL-MD captures more biophysically realistic conformational ensembles in G protein-coupled receptor modeling. △ Less

Submitted 6 March, 2026; v1 submitted 2 March, 2026; originally announced March 2026.

Comments: The Fourteenth International Conference on Learning Representations; Code available at: https://github.com/ZhanghanNi/RigidSSL.git

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Authors: Yahong Wang, Juncheng Wu, Zhangkai Ni, Chengmei Yang, Yihang Liu, Longzhen Yang, Yuyin Zhou, Ying Wen, Lianghua He

Abstract: Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability acros… ▽ More Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune. △ Less

Submitted 19 February, 2026; originally announced February 2026.

TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation

Authors: Yuanzhi Liang, Xuan'er Wu, Yirui Liu, Yijie Fang, Yizhen Fan, Ke Hao, Rui Li, Ruiying Liu, Ziqi Ni, Peng Yu, Yanbo Wang, Haibin Huang, Qizhen Weng, Chi Zhang, Xuelong Li

Abstract: Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long temporal horizons. This report presents a systematical post-training framework that organizes supervised policy shaping, reward-driven reinforcement learning, and preference-based refinement into a single stability-constra… ▽ More Post-training is the decisive step for converting a pretrained video generator into a production-oriented model that is instruction-following, controllable, and robust over long temporal horizons. This report presents a systematical post-training framework that organizes supervised policy shaping, reward-driven reinforcement learning, and preference-based refinement into a single stability-constrained optimization stack. The framework is designed around practical video-generation constraints, including high rollout cost, temporally compounding failure modes, and feedback that is heterogeneous, uncertain, and often weakly discriminative. By treating optimization as a staged, diagnostic-driven process rather than a collection of isolated tricks, the report summarizes a cohesive recipe for improving perceptual fidelity, temporal coherence, and prompt adherence while preserving the controllability established at initialization. The resulting framework provides a clear blueprint for building scalable post-training pipelines that remain stable, extensible, and effective in real-world deployment settings. △ Less

Submitted 7 February, 2026; originally announced February 2026.

Wavelet-Domain Masked Image Modeling for Color-Consistent HDR Video Reconstruction

Authors: Yang Zhang, Zhangkai Ni, Wenhan Yang, Hanli Wang

Abstract: High Dynamic Range (HDR) video reconstruction aims to recover fine brightness, color, and details from Low Dynamic Range (LDR) videos. However, existing methods often suffer from color inaccuracies and temporal inconsistencies. To address these challenges, we propose WMNet, a novel HDR video reconstruction network that leverages Wavelet domain Masked Image Modeling (W-MIM). WMNet adopts a two-phas… ▽ More High Dynamic Range (HDR) video reconstruction aims to recover fine brightness, color, and details from Low Dynamic Range (LDR) videos. However, existing methods often suffer from color inaccuracies and temporal inconsistencies. To address these challenges, we propose WMNet, a novel HDR video reconstruction network that leverages Wavelet domain Masked Image Modeling (W-MIM). WMNet adopts a two-phase training strategy: In Phase I, W-MIM performs self-reconstruction pre-training by selectively masking color and detail information in the wavelet domain, enabling the network to develop robust color restoration capabilities. A curriculum learning scheme further refines the reconstruction process. Phase II fine-tunes the model using the pre-trained weights to improve the final reconstruction quality. To improve temporal consistency, we introduce the Temporal Mixture of Experts (T-MoE) module and the Dynamic Memory Module (DMM). T-MoE adaptively fuses adjacent frames to reduce flickering artifacts, while DMM captures long-range dependencies, ensuring smooth motion and preservation of fine details. Additionally, since existing HDR video datasets lack scene-based segmentation, we reorganize HDRTV4K into HDRTV4K-Scene, establishing a new benchmark for HDR video reconstruction. Extensive experiments demonstrate that WMNet achieves state-of-the-art performance across multiple evaluation metrics, significantly improving color fidelity, temporal coherence, and perceptual quality. The code is available at: https://github.com/eezkni/WMNet △ Less

Submitted 7 February, 2026; originally announced February 2026.

Mapping Gemma3 onto an Edge Dataflow Architecture

Authors: Shouyu Du, Miaoxiang Yu, Zhenyu Xu, Zhiheng Ni, Jillian Cai, Qing Yang, Tao Wei

Abstract: We present the first end-to-end deployment of the Gemma3 family of large language and vision models on a tiled edge dataflow architecture (AMD Ryzen AI NPU). Our work introduces a set of hardware-aware techniques. For prefill, we introduce an efficient dequantization engine, optimize tiled matrix multiplication kernels, and propose FlowQKV, a chunked, pipelined attention mechanism. For decoding, w… ▽ More We present the first end-to-end deployment of the Gemma3 family of large language and vision models on a tiled edge dataflow architecture (AMD Ryzen AI NPU). Our work introduces a set of hardware-aware techniques. For prefill, we introduce an efficient dequantization engine, optimize tiled matrix multiplication kernels, and propose FlowQKV, a chunked, pipelined attention mechanism. For decoding, we introduce FusedDQP, which fuses dequantization and projection into a single kernel, and FlowKV, which re-structures attention to sustain high memory bandwidth utilization. Together with a compact Q4NX 4-bit quantization format, these methods yield up to $5.2\times$ faster prefill and $4.8\times$ faster decoding versus the iGPU, and $33.5\times$ and $2.2\times$ over the CPU, respectively. Power efficiency improves by as much as $67.2\times$ and $222.9\times$ compared to the iGPU and CPU. The proposed approach demonstrates that modern NPUs can deliver practical, low-power LLM and VLM inference at the edge, and provides a generalizable blueprint for mapping transformer-based models onto tiled dataflow accelerators. △ Less

Submitted 24 February, 2026; v1 submitted 27 January, 2026; originally announced February 2026.

Comments: Original Version, data shall be updated

Toward a Sustainable Federated Learning Ecosystem: A Practical Least Core Mechanism for Payoff Allocation

Authors: Zhengwei Ni, Zhidu Li, Wei Chen, Zhaoyang Zhang, Zehua Wang, F. Richard Yu, Victor C. M. Leung

Abstract: Emerging network paradigms and applications increasingly rely on federated learning (FL) to enable collaborative intelligence while preserving privacy. However, the sustainability of such collaborative environments hinges on a fair and stable payoff allocation mechanism. Focusing on coalition stability, this paper introduces a payoff allocation framework based on the least core (LC) concept. Unlik… ▽ More Emerging network paradigms and applications increasingly rely on federated learning (FL) to enable collaborative intelligence while preserving privacy. However, the sustainability of such collaborative environments hinges on a fair and stable payoff allocation mechanism. Focusing on coalition stability, this paper introduces a payoff allocation framework based on the least core (LC) concept. Unlike traditional methods, the LC prioritizes the cohesion of the federation by minimizing the maximum dissatisfaction among all potential subgroups, ensuring that no participant has an incentive to break away. To adapt this game-theoretic concept to practical, large-scale networks, we propose a streamlined implementation with a stack-based pruning algorithm, effectively balancing computational efficiency with allocation precision. Case studies in federated intrusion detection demonstrate that our mechanism correctly identifies pivotal contributors and strategic alliances. The results confirm that the practical LC framework promotes stable collaboration and fosters a sustainable FL ecosystem. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Comments: 7 pages, 3 figures, submitted to IEEE Network

FlowBypass: Rectified Flow Trajectory Bypass for Training-Free Image Editing

Authors: Menglin Han, Zhangkai Ni

Abstract: Training-free image editing has attracted increasing attention for its efficiency and independence from training data. However, existing approaches predominantly rely on inversion-reconstruction trajectories, which impose an inherent trade-off: longer trajectories accumulate errors and compromise fidelity, while shorter ones fail to ensure sufficient alignment with the edit prompt. Previous attemp… ▽ More Training-free image editing has attracted increasing attention for its efficiency and independence from training data. However, existing approaches predominantly rely on inversion-reconstruction trajectories, which impose an inherent trade-off: longer trajectories accumulate errors and compromise fidelity, while shorter ones fail to ensure sufficient alignment with the edit prompt. Previous attempts to address this issue typically employ backbone-specific feature manipulations, limiting general applicability. To address these challenges, we propose FlowBypass, a novel and analytical framework grounded in Rectified Flow that constructs a bypass directly connecting inversion and reconstruction trajectories, thereby mitigating error accumulation without relying on feature manipulations. We provide a formal derivation of two trajectories, from which we obtain an approximate bypass formulation and its numerical solution, enabling seamless trajectory transitions. Extensive experiments demonstrate that FlowBypass consistently outperforms state-of-the-art image editing methods, achieving stronger prompt alignment while preserving high-fidelity details in irrelevant regions. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

Authors: Zhixiong Yue, Feiyang Ye, Zixuan Ni, Sheng Shen, Yu Zhang

Abstract: Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators. However, existing RL-based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address the… ▽ More Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators. However, existing RL-based approaches for flow matching models typically rely on numerous denoising steps, while suffering from sparse and imprecise reward signals that often lead to suboptimal alignment. To address these limitations, we propose Temperature-Annealed Few-step Sampling with Group Relative Policy Optimization (TAFS-GRPO), a novel framework for training flow matching text-to-image models into efficient few-step generators well aligned with human preferences. Our method iteratively injects adaptive time-dependent noise into one-step clean predictions. By repeatedly annealing the model's sampled outputs, it introduces stochasticity into the sampling process while preserving the semantic integrity of each generated image. Moreover, its step-aware advantage integration mechanism combines GRPO with temperature-annealed sampling to eliminate the need for a differentiable reward function and provide dense, step-specific rewards for stable policy optimization. Extensive experiments demonstrate that TAFS-GRPO achieves strong performance in few-step text-to-image generation and significantly improves the alignment of generated images with human preferences. The code and models of this work will be available to facilitate further research. △ Less

Submitted 6 August, 2026; v1 submitted 1 February, 2026; originally announced February 2026.

UrgentMOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality Assessment

Authors: Wei Wang, Wangyou Zhang, Chenda Li, Jiahe Wang, Samuele Cornell, Marvin Sach, Kohei Saijo, Yihui Fu, Zhaoheng Ni, Bing Han, Xun Gong, Mengxiao Bi, Tim Fingscheidt, Shinji Watanabe, Yanmin Qian

Abstract: Automatic speech quality assessment has become increasingly important as modern speech generation systems continue to advance, while human listening tests remain costly, time-consuming, and difficult to scale. Most existing learning-based assessment models rely primarily on scarce human-annotated mean opinion score (MOS) data, which limits robustness and generalization, especially when training ac… ▽ More Automatic speech quality assessment has become increasingly important as modern speech generation systems continue to advance, while human listening tests remain costly, time-consuming, and difficult to scale. Most existing learning-based assessment models rely primarily on scarce human-annotated mean opinion score (MOS) data, which limits robustness and generalization, especially when training across heterogeneous datasets. In this work, we propose UrgentMOS, a unified speech quality assessment framework that jointly learns from diverse objective and perceptual quality metrics, while explicitly tolerating the absence of arbitrary subsets of metrics during training. By leveraging complementary quality facets under heterogeneous supervision, UrgentMOS enables effective utilization of partially annotated data and improves robustness when trained on large-scale, multi-source datasets. Beyond absolute score prediction, UrgentMOS explicitly models pairwise quality preferences by directly predicting comparative MOS (CMOS), making it well suited for preference-based evaluation scenarios commonly adopted in system benchmarking. Extensive experiments across a wide range of speech quality datasets, including simulated distortions, speech enhancement, and speech synthesis, demonstrate that UrgentMOS consistently achieves state-of-the-art performance in both absolute and comparative evaluation settings. △ Less

Submitted 26 January, 2026; originally announced January 2026.

The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models

Authors: Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, Cheng Yu, Bo Zheng, Gao Huang

Abstract: Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. However, in this paper, we find that for general reasoning tasks (e.g., mathemati… ▽ More Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. However, in this paper, we find that for general reasoning tasks (e.g., mathematics and coding), arbitrary order generation may in fact limit the reasoning potential of dLLMs. We observe that dLLMs tend to exploit this order flexibility to bypass high-uncertainty tokens that are crucial for exploration, which can lead to a premature collapse of solution coverage. This observation motivates a rethink of RL approaches for dLLMs, where considerable complexities, such as handling combinatorial trajectories and intractable likelihoods, are often devoted to preserving this flexibility. We show that effective reasoning can be elicited by simply forgoing arbitrary order and applying standard Group Relative Policy Optimization (GRPO) instead. Our approach, JustGRPO, is minimalist yet surprisingly effective (e.g., 89.1% accuracy on GSM8K) while fully retaining the parallel decoding ability of dLLMs. Project page: https://nzl-thu.github.io/the-flexibility-trap △ Less

Submitted 8 June, 2026; v1 submitted 21 January, 2026; originally announced January 2026.

Comments: Code and pre-trained models: https://github.com/LeapLabTHU/JustGRPO

ICASSP 2026 URGENT Speech Enhancement Challenge

Authors: Chenda Li, Wei Wang, Marvin Sach, Wangyou Zhang, Kohei Saijo, Samuele Cornell, Yihui Fu, Zhaoheng Ni, Tim Fingscheidt, Shinji Watanabe, Yanmin Qian

Abstract: The ICASSP 2026 URGENT Challenge advances the series by focusing on universal speech enhancement (SE) systems that handle diverse distortions, domains, and input conditions. This overview paper details the challenge's motivation, task definitions, datasets, baseline systems, evaluation protocols, and results. The challenge is divided into two complementary tracks. Track 1 focuses on universal spee… ▽ More The ICASSP 2026 URGENT Challenge advances the series by focusing on universal speech enhancement (SE) systems that handle diverse distortions, domains, and input conditions. This overview paper details the challenge's motivation, task definitions, datasets, baseline systems, evaluation protocols, and results. The challenge is divided into two complementary tracks. Track 1 focuses on universal speech enhancement, while Track 2 introduces speech quality assessment for enhanced speech. The challenge attracted over 80 team registrations, with 29 submitting valid entries, demonstrating significant community interest in robust SE technologies. △ Less

Submitted 19 January, 2026; originally announced January 2026.

Comments: The overview paper of the ICASSP 2026 URGENT Speech Enhancement Challenge

SLAP: Scalable Language-Audio Pretraining with Variable-Duration Audio and Multi-Objective Training

Authors: Xinhao Mei, Gael Le Lan, Haohe Liu, Zhaoheng Ni, Varun Nagaraja, Yang Liu, Yangyang Shi, Vikas Chandra

Abstract: Contrastive language-audio pretraining (CLAP) has achieved notable success in learning semantically rich audio representations and is widely adopted for various audio-related tasks. However, current CLAP models face several key limitations. First, they are typically trained on relatively small datasets, often comprising a few million audio samples. Second, existing CLAP models are restricted to sh… ▽ More Contrastive language-audio pretraining (CLAP) has achieved notable success in learning semantically rich audio representations and is widely adopted for various audio-related tasks. However, current CLAP models face several key limitations. First, they are typically trained on relatively small datasets, often comprising a few million audio samples. Second, existing CLAP models are restricted to short and fixed duration, which constrains their usage in real-world scenarios with variable-duration audio. Third, the standard contrastive training objective operates on global representations, which may hinder the learning of dense, fine-grained audio features. To address these challenges, we introduce Scalable Language-Audio Pretraining (SLAP), which scales language-audio pretraining to 109 million audio-text pairs with variable audio durations and incorporates multiple training objectives. SLAP unifies contrastive loss with additional self-supervised and captioning losses in a single-stage training, facilitating the learning of richer dense audio representations. The proposed SLAP model achieves new state-of-the-art performance on audio-text retrieval and zero-shot audio classification tasks, demonstrating its effectiveness across diverse benchmarks. △ Less

Submitted 18 January, 2026; originally announced January 2026.

Comments: Accepted to ICASSP 2026

TiInsight: A SQL-based Automated Exploratory Data Analysis System through Large Language Models

Authors: Jun-Peng Zhu, Boyan Niu, Peng Cai, Zheming Ni, Kai Xu, Jiajun Huang, Shengbo Ma, Bing Wang, Xuan Zhou, Guanglei Bao, Donghui Zhang, Liu Tang, Qi Liu

Abstract: The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration. However, existing methods generally lack the ability for cross-domain analysis, and the exploration of LLMs capabilities remains insufficient. This paper presents Ti… ▽ More The SQL-based exploratory data analysis has garnered significant attention within the data analysis community. The emergence of large language models (LLMs) has facilitated the paradigm shift from manual to automated data exploration. However, existing methods generally lack the ability for cross-domain analysis, and the exploration of LLMs capabilities remains insufficient. This paper presents TiInsight, an SQL-based automated cross-domain exploratory data analysis system. First, TiInsight offers a user-friendly GUI enabling users to explore data using natural language queries. Second, TiInsight offers a robust cross-domain exploratory data analysis pipeline: hierarchical data context (i.e., HDC) generation, question clarification and decomposition, text-to-SQL (i.e., TiSQL), and data visualization (i.e., TiChart). Third, we have implemented and deployed TiInsight in the production environment of PingCAP and demonstrated its capabilities using representative datasets. The demo video is available at https://youtu.be/JzYFyYd-emI. △ Less

Submitted 14 January, 2026; originally announced January 2026.

Comments: 4 pages, 5 figures

ACM Class: H.4

Journal ref: Companion of the International Conference on Management of Data (SIGMOD Companion '26), May 31-June 05, 2026, Bengaluru, India

REVNET: Rotation-Equivariant Point Cloud Completion via Vector Neuron Anchor Transformer

Authors: Zhifan Ni, Eckehard Steinbach

Abstract: Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses, limiting their applicability in real-world scenarios. While data augmentation with random rotations can partially mitigate this issue, it significantly increase… ▽ More Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses, limiting their applicability in real-world scenarios. While data augmentation with random rotations can partially mitigate this issue, it significantly increases the learning burden and still fails to guarantee robust performance under arbitrary poses. To address this challenge, we propose the Rotation-Equivariant Anchor Transformer (REVNET), a novel framework built upon the Vector Neuron (VN) network for robust point cloud completion under arbitrary rotations. To preserve local details, we represent partial point clouds as sets of equivariant anchors and design a VN Missing Anchor Transformer to predict the positions and features of missing anchors. Furthermore, we extend VN networks with a rotation-equivariant bias formulation and a ZCA-based layer normalization to improve feature expressiveness. Leveraging the flexible conversion between equivariant and invariant VN features, our model can generate point coordinates with greater stability. Experimental results show that our method outperforms state-of-the-art approaches on the synthetic MVP dataset in the equivariant setting. On the real-world KITTI dataset, REVNET delivers competitive results compared to non-equivariant networks, without requiring input pose alignment. The source code will be released on GitHub under URL: https://github.com/nizhf/REVNET. △ Less

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

Comments: ICPR 2026

Defenses Against Prompt Attacks Learn Surface Heuristics

Authors: Shawn Li, Chenxiao Yu, Zhiyu Ni, Hao Li, Charith Peris, Chaowei Xiao, Yue Zhao

Abstract: Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests. When adversarial instructions appear in user queries or externally retrieved content, models may override intended logic. Recent defenses rely on supervised fine-t… ▽ More Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests. When adversarial instructions appear in user queries or externally retrieved content, models may override intended logic. Recent defenses rely on supervised fine-tuning with benign and malicious labels. Although these methods achieve high attack rejection rates, we find that they rely on narrow correlations in defense data rather than harmful intent, leading to systematic rejection of safe inputs. We analyze three recurring shortcut behaviors induced by defense fine-tuning. \emph{Position bias} arises when benign content placed later in a prompt is rejected at much higher rates; across reasoning benchmarks, suffix-task rejection rises from below \textbf{10\%} to as high as \textbf{90\%}. \emph{Token trigger bias} occurs when strings common in attack data raise rejection probability even in benign contexts; inserting a single trigger token increases false refusals by up to \textbf{50\%}. \emph{Topic generalization bias} reflects poor generalization beyond the defense data distribution, with defended models suffering test-time accuracy drops of up to \textbf{40\%}. These findings suggest that current prompt-injection defenses frequently respond to attack-like surface patterns rather than the underlying intent. We introduce controlled diagnostic datasets and a systematic evaluation across two base models and multiple defense pipelines, highlighting limitations of supervised fine-tuning for reliable LLM security. △ Less

Submitted 11 January, 2026; originally announced January 2026.

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents

Authors: Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng, Yao Xu, Zheqing Zhang, Xin Li, Jitao Sang, Xiaogang Duan, Xuelei Wang, Chengbao Liu, Jie Tan

Abstract: Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, often leading to fragmented memories and unstable long-horizon personalization. We present TiMem, a temporal--hierarch… ▽ More Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, often leading to fragmented memories and unstable long-horizon personalization. We present TiMem, a temporal--hierarchical memory framework that organizes conversations through a Temporal Memory Tree (TMT), enabling systematic memory consolidation from raw conversational observations to progressively abstracted persona representations. TiMem is characterized by three core properties: (1) temporal--hierarchical organization through TMT; (2) semantic-guided consolidation that enables memory integration across hierarchical levels without fine-tuning; and (3) complexity-aware memory recall that balances precision and efficiency across queries of varying complexity. Under a consistent evaluation setup, TiMem achieves state-of-the-art accuracy on both benchmarks, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S. It outperforms all evaluated baselines while reducing the recalled memory length by 52.20% on LoCoMo. Manifold analysis indicates clear persona separation on LoCoMo and reduced dispersion on LongMemEval-S. Overall, TiMem treats temporal continuity as a first-class organizing principle for long-horizon memory in conversational agents. The code is available at https://github.com/TiMEM-AI/timem. △ Less

Submitted 30 April, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

Comments: ACL 2026 Findings

GCRank: A Generative Contextual Comprehension Paradigm for Takeout Ranking Model

Authors: Ziheng Ni, Congcong Liu, Cai Shang, Yiming Sun, Junjie Li, Zhiwei Fang, Guangpeng Chen, Jian Li, Zehua Zhang, Changping Peng, Zhangang Lin, Ching Law, Jingping Shao

Abstract: The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further ampl… ▽ More The ranking stage serves as the central optimization and allocation hub in advertising systems, governing economic value distribution through eCPM and orchestrating the user-centric blending of organic and advertising content. Prevailing ranking models often rely on fragmented modules and hand-crafted features, limiting their ability to interpret complex user intent. This challenge is further amplified in location-based services such as food delivery, where user decisions are shaped by dynamic spatial, temporal, and individual contexts. To address these limitations, we propose a novel generative framework that reframes ranking as a context comprehension task, modeling heterogeneous signals in a unified architecture. Our architecture consists of two core components: the Generative Contextual Encoder (GCE) and the Generative Contextual Fusion (GCF). The GCE comprises three specialized modules: a Personalized Context Enhancer (PCE) for user-specific modeling, a Collective Context Enhancer (CCE) for group-level patterns, and a Dynamic Context Enhancer (DCE) for real-time situational adaptation. The GCF module then seamlessly integrates these contextual representations through low-rank adaptation. Extensive experiments confirm that our method achieves significant gains in critical business metrics, including click-through rate and platform revenue. We have successfully deployed our method on a large-scale food delivery advertising platform, demonstrating its substantial practical impact. This work pioneers a new perspective on generative recommendation and highlights its practical potential in industrial advertising systems. △ Less

Submitted 15 October, 2025; originally announced January 2026.

MambaSeg: Harnessing Mamba for Accurate and Efficient Image-Event Semantic Segmentation

Authors: Fuqiang Gu, Yuanke Li, Xianlei Long, Kangping Ji, Chao Chen, Qingyi Gu, Zhenliang Ni

Abstract: Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages suc… ▽ More Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception. △ Less

Submitted 30 December, 2025; originally announced December 2025.

Comments: Accepted by AAAI 2026