Showing 1–50 of 359 results for author: Liang, K

Infinite Subtraction Games with Periodic Outcomes and Aperiodic SG Values

Authors: Kai Liang

Abstract: We find some significant special cases of subtraction games with infinite subtraction sets, whose outcome sequences are periodic, but whose SG value sequences are bounded and aperiodic. We find some significant special cases of subtraction games with infinite subtraction sets, whose outcome sequences are periodic, but whose SG value sequences are bounded and aperiodic. △ Less

Submitted 18 August, 2026; originally announced August 2026.

MSC Class: 91A46

Perspective-Invariant Attack with Enhanced Transferability of Adversarial Examples

Authors: Kaisheng Liang, Yiming Cao, Bin Xiao

Abstract: Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely… ▽ More Adversarial examples generated on a surrogate deep neural network (DNN) can often successfully fool other black-box DNN models. This cross-model transferability poses serious security threats to DNNs in practical applications. Input transformation techniques are widely used to enhance adversarial transferability by increasing the diversity of input images. However, existing methods primarily rely on local operations with limited degrees of freedom (DOF), such as block-wise shuffling and resizing, overlooking global perspective transformations that naturally arise from viewpoint changes. In this work, we propose a Perspective-Invariant Attack (PIA), which introduces a multi-DOF vertex sampling strategy that systematically covers the perspective transformation hierarchy from 2-DOF translation to 8-DOF projective mapping. By generating geometrically diverse input variations, PIA effectively reduces overfitting of adversarial perturbations to the surrogate model, thereby improving adversarial transferability. We further propose PIA-Mix, a generic extension that maintains a complementary transformation pool and efficiently combines our perspective transformation with auxiliary methods for improved transferability. Extensive experiments involving various DNN architectures, advanced defense mechanisms, and multimodal large language models (LLMs) demonstrate that PIA and PIA-Mix outperform state-of-the-art transfer-based attacks. △ Less

Submitted 15 August, 2026; originally announced August 2026.

Journal ref: IEEE Transactions on Information Forensics and Security, vol. 21, pp. 6818-6831, 2026

A Finite Automaton Approach to Combinatorial Games

Authors: Kai Liang

Abstract: This study applies finite automata to the automatic solving of a variety of combinatorial games. For games whose positions and moves can be represented as regular languages and their operations, we design a two-stage automatic solving algorithm: first, construct a candidate finite automaton to determine the $\mathcal{P}$- and $\mathcal{N}$-positions, and then perform rigorous formal verificati… ▽ More This study applies finite automata to the automatic solving of a variety of combinatorial games. For games whose positions and moves can be represented as regular languages and their operations, we design a two-stage automatic solving algorithm: first, construct a candidate finite automaton to determine the $\mathcal{P}$- and $\mathcal{N}$-positions, and then perform rigorous formal verification on this automaton; once verified, a complete solution of the game is obtained. For partizan octal games, we introduce a generalized misère quotient, overcoming the limitation that traditional theory applies only to impartial games. Using the above algorithm, we successfully solve the majority of two-digit partizan octal games, and based on these results, we propose a partizan version of Guy's conjecture. We also successfully solve a considerable number of partizan octal games under misère play, and give a conjecture on the structure of those games exhibiting ``algebraic periodicity'' among them. For Kotzig's nim, we resolve the most important related conjecture: we prove that the outcomes and SG values are periodic under both normal and misère play (including their partizan versions). Our algorithm successfully solves several small-scale cases, including misère play and partizan versions. This study pioneers a new theoretical tool and algorithmic paradigm for the automatic solving of combinatorial games, and has broad prospects for further extension and application in the field of combinatorial game theory. △ Less

Submitted 13 August, 2026; originally announced August 2026.

MSC Class: 91A46

MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents

Authors: Kaichao Liang, Yuqi Cui, Hao Kong, Xinyuan Huang, Guohaotian Hou, Qingcan Kang, Liang Chen, Yiyang Yin, Ke Ye, Jiaquan Guo, Da Chen, Lingan Zeng, Yixing Peng, Rong Yao, Shixiong Kai, Mingxuan Yuan

Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory… ▽ More Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory systems often remain fixed after development, limiting their ability to adapt their memory models, organization strategies, and procedural knowledge through continued use. We present MindMemOS, a portable and self-evolving memory operating layer that organizes open-world information using a unified entity property timestructure. MindMemOS supports scenario-adaptive memory modeling, higher-order pattern discovery, autonomous memory refinement, and continuous skill evolution. Its MindMemEvolve algorithm employs validation-driven evolutionary search to optimize memory schemas for target scenarios, whiledreaming consolidates accumulated memories by merging redundant records and resolving conflicts. In addition, implicit corrective feedback serves as a human-in-the-loop signal for identifying and revising potentially inaccurate or misaligned memories. Its MindSkillEvolve algorithm further transforms agent execution trajectories into reusable and progressively refined skills. MindMemOS achieves 94.03% accuracy on LOCOMO and 70.63% on PersonaMem. MindSkillEvolve improves SpreadsheetBench success by 9.2 percentage points over the initial-skill baseline. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Comments: 35 pages,14 figures

EMAS: Stabilizing Multi-Agent System Evolution through Evidence-Guided Revision

Authors: Chao Fei, Qingyi Si, Kaihua Liang, Yanghua Xiao, Panos Kalnis, Hongcheng Guo

Abstract: Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experi… ▽ More Many methods for automated multi-agent system design optimize prompts and topologies during an initial design stage and then deploy the resulting system unchanged on subsequent samples. Experience from these samples is rarely consolidated into reusable system updates, while accuracy-oriented designs may incur high token costs. We introduce EMAS (Evolving Multi-Agent System), which uses this experience to revise MAS topology and prompts without updating LLM parameters, either to improve accuracy or to reduce cost. EMAS converts traces into structured diagnoses that specify a revision operation and target. It generates a candidate revision only when the same diagnosis recurs across samples and applies it only if paired validation against the current MAS meets the corresponding acceptance criterion. Across four benchmarks and two LLMs, EMAS attains the highest task-weighted overall accuracy for both backbones and is best or tied in six of eight model--benchmark settings. Within two evolution epochs, EMAS achieves relative gains of 6.30% and 20.10% in task-weighted accuracy on Kimi-K2-6 and Qwen3.6-27B, respectively. On MBPP with Qwen3.6-27B, EMAS raises accuracy from 55.09% to 89.12% while reducing token use per task by 62.2%. These results show that EMAS can turn experience from new samples into reusable updates to MAS topology and prompts. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Learning Latent Reasoning Traces for Scalar Reward Models End-to-End

Authors: Sanwoo Lee, Clive Bai, Hsiu-Yuan Huang, Kun Liang, Weijie Liu, Yunfang Wu

Abstract: Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilistic reward modeling, they rely on superficial cues that fail to generalize to complex or out-of-distribution (OOD) tasks. Conversely, generative RMs leverage extensive reasoning to improve robustness on challenging tasks… ▽ More Reward models (RMs) are central to aligning large language models with human preferences via reinforcement learning. Although traditional scalar RMs enable efficient and probabilistic reward modeling, they rely on superficial cues that fail to generalize to complex or out-of-distribution (OOD) tasks. Conversely, generative RMs leverage extensive reasoning to improve robustness on challenging tasks, but their natural language-based scores lack the numerical flexibility and probabilistic interpretability that scalar RMs offer. While recent approaches combine both paradigms through off-policy multi-task learning, such parallel optimization does not guarantee that generated reasoning traces actively align with or benefit downstream scalar reward prediction. To address this mismatch, we propose LatentRM, a reward modeling framework that learns intermediate reasoning traces as discrete latent variables to explicitly maximize the likelihood of downstream scalar rewards. Through on-policy optimization of the latent reasoning space end-to-end, LatentRM tightly couples deep reasoning-based evaluation with precise scoring. Extensive validations on in-distribution and OOD datasets and RLHF show that LatentRM outperforms scalar, generative, and hybrid RMs on preference modeling and policy alignment across tasks ranging from open-ended conversation to complex reasoning. △ Less

Submitted 31 July, 2026; originally announced July 2026.

From Inline Notes to Collected Commentaries: Toward Context-Preserving Organization of Exegetical Knowledge in Classical Chinese Texts

Authors: Ke Liang, Qi Su, Churen Huang

Abstract: Inline notes and collected commentaries are important forms of scholarly communication that evolved within the Confucian exegetical tradition, yet have received little computational attention. Drawing on traditional Chinese exegetics and philology, this paper formulates collected commentary compilation as an NLP task and proposes a computational framework that preserves the contextual dependency o… ▽ More Inline notes and collected commentaries are important forms of scholarly communication that evolved within the Confucian exegetical tradition, yet have received little computational attention. Drawing on traditional Chinese exegetics and philology, this paper formulates collected commentary compilation as an NLP task and proposes a computational framework that preserves the contextual dependency of inline notes while enabling their automatic compilation and exegetical knowledge organization. It combines two-step prompt chaining for identifying the associated main-text segments and exegetical functions of annotations with cross-source mention clustering for integrating commentary across editions, achieving a CoNLL F1 score above 97% in a case study on the Classic of Mountains. Our framework lays the foundation for the large-scale organization of historical exegetical knowledge, thereby supporting a broad range of downstream philological and NLP tasks. △ Less

Submitted 31 July, 2026; originally announced July 2026.

Comments: 15 pages, 4 figures

Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

Authors: Tianyi Gao, Han Fang, Tianyi Ding, Hao Li, Xin Wei, Hongbo Sun, Xiaodong Dong, Ye Yuan, Jinglin Xu, Kongming Liang, Hao Sun, Jingmin Xin

Abstract: Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing, text-based methods rely on coordinates or index prediction, severely limiting the perceptual capabilities of the model for dense visual objects. Meanwhile, latent token-based methods employ special tokens without inher… ▽ More Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing, text-based methods rely on coordinates or index prediction, severely limiting the perceptual capabilities of the model for dense visual objects. Meanwhile, latent token-based methods employ special tokens without inherent spatial references and use a decoding mechanism that lacks thinking steps, weakening high-level reasoning capabilities. Consequently, developing a unified framework that excels in both perception and reasoning remains challenging. To address this, we propose Mixture-of-Thought-Tokens (Motto), a new free-form multimodal grounding method that bridges the perception-reasoning gap, enabling MLLMs to empower diverse, arbitrary grounding queries. Specifically, we introduce Spatially-Grounded Thought Tokenization to explicitly align special tokens with spatial locations for clear spatial correspondence and visual interpretability. We further design a Context-Adaptive Chain-of-Tokens that dynamically switch grounding modes within an interleaved reasoning chain, achieving robust grounding across tasks of varying complexity. In addition, we construct PR-Bench, a new referring expression comprehension benchmark to evaluate the perception-reasoning gap. Extensive experiments demonstrate that Motto achieves state-of-the-art performance across diverse free-form grounding tasks. △ Less

Submitted 27 July, 2026; originally announced July 2026.

Comments: Accepted by ACM MM 2026

PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption

Authors: Liangqin Ren, Zeyan Liu, Fengjun Li, Kaitai Liang, Zhu Li, Bo Luo

Abstract: In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (MLaaS) frameworks assume fully trusted models, the need for privacy-preserving DNN evaluation arises. In a secure multi-party computation scenario, both the model and the data are considered proprietary, i.e., the model… ▽ More In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (MLaaS) frameworks assume fully trusted models, the need for privacy-preserving DNN evaluation arises. In a secure multi-party computation scenario, both the model and the data are considered proprietary, i.e., the model owner does not want to reveal the highly valuable DL model to the user, while the user does not wish to disclose their private data samples either. Conventional privacy-preserving deep learning solutions ask the users to send encrypted samples to the model owners, who must handle the heavy lifting of ciphertext-domain computation with homomorphic encryption. In this paper, we present a novel solution, namely, PrivDNN, which (1) offloads the computation to the user side by sharing an encrypted deep learning model with them, (2) significantly improves the efficiency of DNN evaluation using partial DNN encryption, (3) ensures model accuracy and model privacy using a core neuron selection and encryption scheme. Experimental results show that PrivDNN reduces privacy-preserving DNN inference time and memory requirement by up to 97% while maintaining model performance and privacy. Codes can be found at https://github.com/LiangqinRen/PrivDNN △ Less

Submitted 23 July, 2026; originally announced July 2026.

Comments: Published in Proceedings on Privacy Enhancing Technologies (PoPETs 2024)

Journal ref: Proceedings on Privacy Enhancing Technologies, 2024(3), 477-494

LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications

Authors: Daniela Rojas, Abdulwahab Albassam, Aidan G. Leung, Jett Ngo, Ryan Luo, Peter R. Quawas, Junpyung Kim, Kangkai Liang, Mansi Nanavati, Jonathan Mai, Meng-Chi Tsai, Yun-Tong Tsai, Yize Chen, Yuanyuan Shi

Abstract: Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to desi… ▽ More Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to designing and evaluating such systems. LLMs can produce numerically plausible yet physically infeasible outputs, evaluation protocols vary across tasks, and the boundary between what the model should and should not compute is implicit. This paper presents a solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification. We review the building blocks of LLM and agentic AI systems for power systems: prompting strategies and agentic architectures. We instantiate the principle in four case studies: wind power forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis, each comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics. EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%. We propose a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency. A consistent division of labor emerges: the agentic system reliably orchestrates, retrieves, and explains, while trusted tools compute and a verification gate decides what is reported. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Comments: 28 pages, 11 figures, 6 tables; plus supplementary material. Review/tutorial article

Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory

Authors: Qingcan Kang, Mingyang Liu, Shixiong Kai, Kaichao Liang, Zhentao Tang, Yuqi Cui, Tao Zhong, Mingxuan Yuan

Abstract: Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can be used at once. Existing systems mainly follow two strategies: memory retention and memory consolidation. Retention keeps raw records and preserves exact details, but relevant evidence may not fit under a tight budget; c… ▽ More Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can be used at once. Existing systems mainly follow two strategies: memory retention and memory consolidation. Retention keeps raw records and preserves exact details, but relevant evidence may not fit under a tight budget; consolidation compresses and combines records, improving coverage per token but risking the loss of query-critical details. Neither strategy is universally preferable. This raises two central questions: when should consolidation replace retention, and which operator -- Merge, Abstract, or Rewrite -- should be selected? We formalize this decision by decomposing each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits. Their balance explains why the preferred action changes with relative budget pressure. We implement this mechanism with Offline Abstraction-Safety (OAS), a lightweight learner that estimates action utilities from pre-generation features with held-out harm calibration. The public LongMemEval and LoCoMo benchmarks show the same budget-dependent pattern. On LongMemEval, consolidation improves absolute accuracy by up to 48% under tight budgets, whereas retention is preferable under loose budgets; LoCoMo replicates this crossover at a smaller budget, consistent with its shorter evidence. On both datasets, cross-note abstraction and merging generally outperform local rewriting when compression is necessary. △ Less

Submitted 20 July, 2026; v1 submitted 20 July, 2026; originally announced July 2026.

SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training

Authors: Keyu Liang, Haoye Wang, Yanfu Yan, Zhiyuan Wan, Zhongxin Liu

Abstract: Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeling semantic relevance between queries and code. However, these rerankers overlook critical non-functional qualities like execution speed, memory usage, and maintainability, which are essential for practical software deve… ▽ More Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeling semantic relevance between queries and code. However, these rerankers overlook critical non-functional qualities like execution speed, memory usage, and maintainability, which are essential for practical software development. Studies reveal developers expect results to maintain high coding standards and satisfy specific needs, such as resource optimization, highlighting the importance of quality-aware code search. Achieving quality-aware code search faces two major challenges: the scarcity of quality-annotated datasets for effective training and the limitations of standard contrastive learning objectives, which fail to capture the ordinal relationships among high-quality, low-quality, and irrelevant code. Although contrastive learning excels in distinguishing relevant from irrelevant code, its binary objective does not support nuanced quality distinctions.To address these challenges, we propose SynH-Rank, a quality-aware code reranking framework that combines LLM-driven diverse data synthesis with hierarchical ranking training. SynH-Rank employs a three-level labeling scheme to explicitly model the hierarchy: high-quality relevant > low-quality relevant > irrelevant. Additionally, we introduce a new benchmark with 4,209 pairs and two novel metrics: Quality Preference Accuracy (QPA) for assessing prioritization of high-quality code and Multi-Condition Accuracy (MCA) for evaluating performance under complex constraints.Experimental results show SynH-Rank improves QPA by 20.15\% over backbone models and outperforms standard relevance-only contrastive training by 15.80\%, while simultaneously enhancing traditional relevance metrics and multi-condition generalizability. △ Less

Submitted 19 July, 2026; originally announced July 2026.

VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation

Authors: Songyu Xu, Xin Wang, Qiang Chen, Xinran Wang, Muxi Diao, Yuxuan Zhang, Kongming Liang, Rui Lin, Zhanyu Ma

Abstract: Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluated. Existing evaluation protocols often rely on prompts that are short and semantically shallow, with limited atomic constraints and weak spatio-temporal dependencies. They also frequently depend on costly human evaluati… ▽ More Recent video generation models (VGMs) have made substantial progress in visual fidelity, yet their ability to follow long, compositional instructions remains insufficiently evaluated. Existing evaluation protocols often rely on prompts that are short and semantically shallow, with limited atomic constraints and weak spatio-temporal dependencies. They also frequently depend on costly human evaluation or handcrafted vision pipelines, while providing little diagnostic insight into which instruction constraints succeed or fail. To address this gap, we propose VGIF-Score, a highly automated and interpretable framework for evaluating instruction following in video generation. VGIF-Score consists of two complementary components: an objective completion branch that parses prompts into a Spatio-Temporal Directed Acyclic Graph (ST-DAG) and performs dependency-aware QA with short-circuit diagnostics, and a subjective satisfaction branch that uses instruction-conditioned AutoRubric to assess cinematography, visual purity, motion smoothness, and physics adherence. Together, these components produce a unified score that captures both objective completion and perceptual satisfaction. We instantiate this framework on VGIF-Bench, a benchmark of 223 long, structurally entangled prompts paired with approximately 4.3K fine-grained evaluation items. Experiments on 14 proprietary and open-source VGMs across more than 3K generated videos show that VGIF-Score provides reliable, interpretable, and diagnostically useful evaluation of video generation instruction following. The code will be available at https://github.com/PRIS-CV/VGIF-SCORE. △ Less

Submitted 15 July, 2026; originally announced July 2026.

Comments: Accepted by PRCV2026

CCFM: Collision-Constrained Flow Matching for Safety-Critical Scenario Generation

Authors: Ke Li, Kaidi Liang, Yuxin Ding, Debojyoti Biswas, Xianbiao Hu, Ruwen Qin

Abstract: Evaluation of autonomous vehicle (AV) planners in safety-critical closed-loop simulation is essential for real-world deployment. However, generating controllable safety-critical scenarios remains challenging. Existing approaches use soft guidance that provides only probabilistic preferences and cannot guarantee the satisfaction of geometric and severity constraints associated with specific collisi… ▽ More Evaluation of autonomous vehicle (AV) planners in safety-critical closed-loop simulation is essential for real-world deployment. However, generating controllable safety-critical scenarios remains challenging. Existing approaches use soft guidance that provides only probabilistic preferences and cannot guarantee the satisfaction of geometric and severity constraints associated with specific collision types. We introduce Collision-Constrained Flow Matching (CCFM), a novel framework that guarantees precise collision control through hard physical constraints. CCFM consists of three key components: (i) a heuristic collision selector that optimally identifies an adversarial agent and collision type via composite scoring; (ii) structured hard constraints that explicitly define four collision types (rear-end, side, cut-in, head-on) through contact point, heading, and severity requirements; and (iii) a collision-constrained flow matching sampler that enforces the constraints via Gauss-Newton manifold projection. CCFM achieves collision rate up to 46.4% on nuScenes and 83.1% on nuPlan, significantly outperforming baselines while preserving realistic driving behavior. By enabling controllable collision characteristics in safety-critical scenario generation, CCFM provides a reliable foundation for AV safety evaluation and sim-to-real crash data generation. The code and implementation details are available at https://github.com/KELISBU/CCFM. △ Less

Submitted 5 July, 2026; originally announced July 2026.

Comments: Accepted by ECCV 2026

MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models

Authors: Yuanzhi Liu, Shousheng Zhao, Bo Zhou, Kongming Liang, Zhanyu Ma

Abstract: Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to temporal staleness, data contamination, and costly maintenance. We present MMBench-Live, a continuously evolving multimodal benchmark built by a multi-agent-driven automated pipeline. Our framework treats benchmark evolution as task-guided dataset co… ▽ More Evaluation benchmarks are essential for assessing vision-language models (VLMs), but most multimodal benchmarks are static, making them vulnerable to temporal staleness, data contamination, and costly maintenance. We present MMBench-Live, a continuously evolving multimodal benchmark built by a multi-agent-driven automated pipeline. Our framework treats benchmark evolution as task-guided dataset construction, integrating structured benchmark specification, feedback-controlled real-time data acquisition, and verifiable QA generation with executable reasoning. To maintain cross-version comparability, we introduce a distribution-consistent update strategy that extracts task-related visual patterns from the original benchmark to guide data collection and filtering. Instantiated from MMBench, MMBench-Live contains 5.9K newly generated evaluation instances with a high answer correctness rate, while each update costs about USD 30 and takes 1-2 hours. Extensive evaluations show that MMBench-Live preserves stable model rankings, maintains semantic alignment with the original benchmark, and exhibits weaker contamination-related memorization signals, suggesting a practical and scalable paradigm for sustainable multimodal benchmark evolution. The project is available at https://github.com/PRIS-CV/MMBench-Live. △ Less

Submitted 2 July, 2026; originally announced July 2026.

ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language Models

Authors: Kaier Liang, Hengde Dai, Cristian-Ioan Vasile

Abstract: Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging. It requires extracting implicit temporal and logical constraints from natural language commands and executing multiple sub-tasks accordingly. Recent zero-shot object navigation methods use vision-language models (VLMs) to guide frontier-based exploration in unknown environments, but th… ▽ More Enabling robots to follow natural language commands to complete zero-shot long-horizon tasks remains challenging. It requires extracting implicit temporal and logical constraints from natural language commands and executing multiple sub-tasks accordingly. Recent zero-shot object navigation methods use vision-language models (VLMs) to guide frontier-based exploration in unknown environments, but they are limited to single-target tasks. Real-world commands such as "Clean either the chair or the couch, then turn on the tv." require navigating to multiple targets in a temporally constrained order, which no existing zero-shot system can handle. We present ViTL, a framework that addresses this gap at two levels. At the task level, we use a large language model (LLM) to compile natural language commands into Linear Temporal Logic (LTL) formulas, which are then converted into Deterministic Finite Automata~(DFA) that coordinate multi-channel value maps and trigger dynamic replanning when new objects are detected. At the navigation level, we introduce directional score: rather than producing a direction-agnostic value across the entire field of view, we label frontier directions on the observation image and extract per-direction scores from the VLM. Experiments on Habitat-Matterport 3D (HM3D) show that the full framework enables zero-shot long-horizon completion of natural language navigation tasks with temporal constraints, and that directional score improves single-target navigation accuracy and efficiency over the baseline. △ Less

Submitted 28 June, 2026; originally announced June 2026.

Invisible Impact of Empathy on Behavioral Change: Isolating the Effect of Empathy in Long-term Physical Activity Coaching Chatbot Interactions

Authors: Li Siyan, Kai-Hui Liang, Shopnil Shahriar, Yilin Ye, Shiyoh Goetsu, Wei-Wei Du, Masahiro Yoshida, Tsunayuki Ohwa, Xuhai Xu, Zhou Yu

Abstract: Current dialogue systems, powered by large language models, often treat empathy as essential without assessing its true impact, especially in behavior change, where motivation and adherence often depend on subtle user-chatbot dynamics. We examine this assumption by building three WhatsApp physical-activity (PA) coaching chatbots that differ only in empathy level and evaluating them in a six-week w… ▽ More Current dialogue systems, powered by large language models, often treat empathy as essential without assessing its true impact, especially in behavior change, where motivation and adherence often depend on subtle user-chatbot dynamics. We examine this assumption by building three WhatsApp physical-activity (PA) coaching chatbots that differ only in empathy level and evaluating them in a six-week within-subject study (N = 13). Participants struggled to distinguish between the empathy conditions, and the non-empathetic version was often rated as more engaging and useful. However, higher-empathy variants were still associated with a larger overall average increase in step counts and faster improvement in intention to follow advice. These results suggest empathy's role is nuanced: it may be hard for lay users to identify explicitly, but it can still shape motivation and trust that support sustained change. We interpret this pattern through the Elaboration Likelihood Model's peripheral route. We highlight design implications for building next-generation PA coaching chatbots that balance effectiveness with human-like connection. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Comments: Shortened version of paper accepted into CUI Short paper and WIP

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Authors: Qingcan Kang, Liu Mingyang, Shixiong Kai, Kaichao Liang, Tao Zhong, Mingxuan Yuan

Abstract: Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budge… ▽ More Long-horizon language agents accumulate observations, reasoning traces, and retrieved facts exceeding context windows, making memory retention a fundamental resource-allocation problem. Existing systems treat retention as local and do not model long-term consequences under observability constraints. To fill this gap, we formulate memory retention as a constrained stochastic optimization with budget feasibility, evidence utility, and delayed costs including miss, reacquisition, and stale penalties. We show this multi-step problem is NP-hard, making exact solution intractable. Moreover, deployment decisions must be made under partial observability. To address these challenges, we propose OSL-MR (Observability-Safe Learning for Memory Retention), a learning-augmented framework that enforces a strict separation between online-observable features and offline-available supervision. OSL-MR combines an evidence learner trained from realized evidence with a Mixed-Score heuristic that serves as a deployable online-safe baseline and an inductive prior. The policy learns query-conditioned evidence from interaction data and remains deployable under the same constraints. Experiments on LoCoMo and LongMemEval show OSL-MR outperforms recency-based, Generative Agents-style, and other heuristic baselines, especially under tight budgets. The Mixed-Score prior improves precision and recall, and sensitivity analysis shows robustness across cost settings. On small solvable instances, single-step optimization is insufficient to anticipate future demand shifts, while OSL-MR stays significantly closer to the dynamic-programming optimum, confirming the necessity of the sequential formulation and reinforcing our learning-guided approximation. These results establish constrained stochastic optimization and optimization-guided learning as a principled foundation for memory management in long-horizon agents. △ Less

Submitted 29 June, 2026; v1 submitted 9 June, 2026; originally announced June 2026.

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Authors: PSBC LLM Team, Huawei LLM Team, Ruihan Long, Junjie Wu, Tianan Zhang, Duo Zhang, Yaozong Wu, Jinbin Fu, Chang Liu, Zhentao Tang, Wenshuang Yang, Xin Wang, Zhihao Song, Ning Huang, Wenjing Xu, Shuai Zong, Shupei Sun, Sen Wang, Jing Hu, Bin Wang, Xinyu Wang, Junkui Ju, Zequn Ding, Jie Ran, Man Luo , et al. (34 additional authors not shown)

Abstract: Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei… ▽ More Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference. △ Less

Submitted 4 June, 2026; originally announced June 2026.

From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

Authors: Mingyang Liu, Qingcan Kang, Yuke Wang, Shixiong Kai, Kaichao Liang, Hui-Ling Zhen, Tao Zhong, Mingxuan Yuan, Linqi Song

Abstract: Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updat… ▽ More Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-based news-forecasting pipelines face two practical limitations: relevant news articles often exceed the model's context window, and iterative retrieval of supplementary news is typically unguided, leading to redundant updates and slow convergence. We address these issues with a novel framework that combines importance-aware news compression and process-level retrieval supervision. First, we train an importance reward model that estimates the forecasting utility of each article and uses this signal to allocate compression budgets during sequential pairwise fusion, preserving informative content within a fixed context limit. Second, we introduce a process reward model (PRM) that ranks multiple supplementary-news candidates conditioned on the current error profile and the history of previously selected articles, replacing one-shot blind retrieval with quality-controlled selection. Both components are trained offline using historical data with ground truth; inference uses the frozen filtering logic and compression modules without any reflection loop. Experiments on finance, energy, traffic, and bitcoin forecasting benchmarks show that our method improves prediction accuracy over strong baselines, significantly reduces the number of refinement iterations compared to the iterative baseline, and remains effective when relevant articles span thousands of tokens. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Hardness of Obligatory-Test Scheduling on Multiple Machines

Authors: Kao-Chuan Liang, Ya-Chun Liang

Abstract: We study online scheduling with obligatory testing on $m$ identical parallel machines, with the objective of minimizing the sum of completion times. Each job comprises a test of known length and a processing operation of initially unknown length. The processing time is revealed only when the test completes. Unlike in optional testing models, the scheduler does not choose whether to acquire informa… ▽ More We study online scheduling with obligatory testing on $m$ identical parallel machines, with the objective of minimizing the sum of completion times. Each job comprises a test of known length and a processing operation of initially unknown length. The processing time is revealed only when the test completes. Unlike in optional testing models, the scheduler does not choose whether to acquire information. Instead, it must decide how to allocate machine capacity between testing unrevealed jobs and processing jobs whose sizes are already known. Previous single-machine lower-bound constructions suggest a natural $\sqrt{2}$ benchmark [ESA 2024: 48:1-14]. However, these constructions cannot be directly transferred to identical parallel machines by a simple replication argument. An online algorithm may interleave jobs from different copies, and the test and processing operation of a job need not be scheduled on the same machine. We address this difficulty by introducing a completion-threshold framework that reasons directly about global progress under total machine capacity. For each $X$, let $T_X$ be the earliest time at which the algorithm has completed at least $X$ jobs. The identity $\sum_{X=1}^{N}T_X$ then converts pointwise progress bounds into lower bounds on the total completion time. Using this framework, we prove a three-type lower bound of $1.4811$ and a dyadic multi-type lower bound tending to $3/2$. The latter also improves the deterministic single-machine lower bound from $\sqrt{2}$ to $3/2$. On the algorithmic side, we give a parallel version of single-machine 1-SORT and prove that, if single-machine 1-SORT is $ρ$-competitive, then its parallel version is $\frac{2(m+ρ-1)}{m+1}$-competitive on $m$ identical machines. △ Less

Submitted 14 July, 2026; v1 submitted 1 June, 2026; originally announced June 2026.

ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation

Authors: Kun Liang, Chenming Tang, Clive Bai, Weijie Liu, Saiyong Yang, Yunfang Wu

Abstract: On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate supervision to late positions with low marginal value for the current student. We revisit this assumption through the useful supervision horizon: student-induced ro… ▽ More On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate supervision to late positions with low marginal value for the current student. We revisit this assumption through the useful supervision horizon: student-induced rollouts can drift from teacher-preferred continuations, while aligned prefixes may already preserve the long-horizon OPD update direction. We propose ADWIN, an adaptive-window framework for OPD that treats rollout length as an online admissibility decision, training on short teacher-anchored prefixes while using delayed full-rollout probes to audit prefix--full alignment and adapt the next horizon with staleness control. Across math and code reasoning benchmarks in single-task, multi-task, and strong-to-weak settings, ADWIN improves the accuracy--compute trade-off over full-rollout OPD and prefix-based baselines, reducing end-to-end training cost by up to 4.1 times while achieving comparable or better accuracy. △ Less

Submitted 27 May, 2026; originally announced May 2026.

MemGym: a Long-Horizon Memory Environment for LLM Agents

Authors: Wujiang Xu, Yu Wang, Kai Mei, Kaiqu Liang, Zhenting Wang, Mingyu Jin, Han Zhang, Shi-Xiong Zhang, Wenyue Hua, Sambit Sahu, Dimitris N. Metaxas

Abstract: Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory formation that occurs during extended agent execution. Consequently, the memory systems they produce transfer poorly to realistic agentic environments, such as coding a… ▽ More Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory formation that occurs during extended agent execution. Consequently, the memory systems they produce transfer poorly to realistic agentic environments, such as coding and web navigation. We present MemGym, a benchmark for agentic memory that unifies existing agent gyms and in-house memory-grounded pipelines behind one memory-reasoning interface. MemGym spans five evaluation tracks grouped into four agentic regimes: tool-use dialogue (tau2-bench), multi-turn deep-research search (MEMGYM-DR), coding (SWE-Gym and MEMGYM-CODEQA), and computer use (WebArena-Infinity). MemGym reports memory-isolated scores that decouple memory performance from reasoning, retrieval, and tool-use ability, so memory strategies can be ranked without those confounders. Our synthetic pipelines for MEMGYM-CODEQA and MEMGYM-DR are length-controllable, ablation-verified at every stage, and tightly aligned with downstream scenarios. To make evaluation on coding environments academically tractable, we train MemRM, a lightweight reward model (Qwen3-1.7B fine-tuned with QLoRA) that scores compression quality as a fast scalar read in place of full Docker rollouts. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Curriculum Group Policy Optimization: Adaptive Sampling for Unleashing the Potential of Text-to-Image Generation

Authors: Baoteng Li, Xianghao Zang, Xinran Wang, Xiangyu Na, Zhixiang He, Hao Sun, Chi Zhang, Zhongjiang He, Tianwei Cao, Kongming Liang, Zhanyu Ma

Abstract: Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been successfully applied to T2I tasks. However, the uniform sampling strategy commonly used during training often ignores the match between sample difficulty and th… ▽ More Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been successfully applied to T2I tasks. However, the uniform sampling strategy commonly used during training often ignores the match between sample difficulty and the model's current learning capability, leading to low training efficiency. We argue that improving training efficiency requires continuously prioritizing prompts that match the model's evolving capability and remain actively learnable. To this end, we propose Curriculum Group Policy Optimization (CGPO), an adaptive curriculum training framework. During training, each prompt produces a group of images scored by a reward model. We use the variance of group rewards as an online proxy for prompt inconsistency. A higher variance suggests that the model has partially captured the prompt requirements but has not yet achieved stable mastery. Such prompts are more likely to provide useful learning signals, so we increase their sampling probabilities accordingly. Additionally, to address data imbalance in multi-category datasets, we design a category calibration method based on proportional fairness optimization, which balances training difficulty across categories. Experiments on GenEval, T2I-CompBench++, and DPG Bench demonstrate that our framework effectively improves generation performance. △ Less

Submitted 17 May, 2026; originally announced May 2026.

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Authors: Haiwen Diao, Penghao Wu, Hanming Deng, Jiahao Wang, Shihao Bai, Silei Wu, Weichen Fan, Wenjie Ye, Wenwen Tong, Xiangyu Fan, Yan Li, Yubo Wang, Zhijie Cao, Zhiqian Lin, Zhitao Yang, Zhongang Cai, Yuwei Niu, Yue Zhu, Bo Liu, Chengguang Lv, Haojia Yu, Haozhe Xie, Hongli Wang, Jianan Fan, Jiaqi Li , et al. (33 additional authors not shown)

Abstract: Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned representation spaces. We argue that this divide is not merely an engineering artifact, but a structural limitation that hinders the emergence of native multimoda… ▽ More Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned representation spaces. We argue that this divide is not merely an engineering artifact, but a structural limitation that hinders the emergence of native multimodal intelligence. Hence, we introduce SenseNova-U1, a native unified multimodal paradigm built upon NEO-unify, in which understanding and generation evolve as synergistic views of a single underlying process. We launch two native unified variants, SenseNova-U1-8B-MoT and SenseNova-U1-A3B-MoT, built on dense (8B) and mixture-of-experts (30B-A3B) understanding baselines, respectively. Designed from first principles, they rival top-tier understanding-only VLMs across text understanding, vision-language perception, knowledge reasoning, agentic decision-making, and spatial intelligence. Meanwhile, they deliver strong semantic consistency and visual fidelity, excelling in conventional or knowledge-intensive any-to-image (X2I) synthesis, complex text-rich infographic generation, and interleaved vision-language generation, with or without think patterns. Beyond performance, we show detailed model design, data preprocessing, pre-/post-training, and inference strategies to support community research. Last but not least, preliminary evidence demonstrates that our models extend beyond perception and generation, performing strongly in vision-language-action (VLA) and world model (WM) scenarios. This points toward a broader roadmap where models do not translate between modalities, but think and act across them in a native manner. Multimodal AI is no longer about connecting separate systems, but about building a unified one and trusting the necessary capabilities to emerge from within. △ Less

Submitted 12 May, 2026; originally announced May 2026.

Comments: Project page: https://github.com/OpenSenseNova/SenseNova-U1

Privacy-preserving Chunk Scheduling in a BitTorrent Implementation of Federated Learning

Authors: Naicheng Li, Javad Dogani, Rui Wang, Kaitai Liang, Nikolaos Laoutaris

Abstract: Traditional federated learning (FL) relies on a central aggregator server, which can create performance bottlenecks and privacy risks. Decentralized mix-and-forward designs remove the server, but repeated local mixing can attenuate global information under heterogeneity and expose peer-to-peer neighborhoods as a privacy attack surface. To preserve FedAvg-style aggregation semantics over updates re… ▽ More Traditional federated learning (FL) relies on a central aggregator server, which can create performance bottlenecks and privacy risks. Decentralized mix-and-forward designs remove the server, but repeated local mixing can attenuate global information under heterogeneity and expose peer-to-peer neighborhoods as a privacy attack surface. To preserve FedAvg-style aggregation semantics over updates reconstructable by the round deadline while scaling dissemination, we present FLTorrent, a BitTorrent-based dissemination layer for serverless FL with a short warm-up. Warm-up hardens within-round source unlinkability, a dissemination-layer goal orthogonal to content protections such as DP or secure aggregation, via pre-round obfuscation, randomized lags, and coordination-only non-owner-first scheduling with the tracker off the data path, before switching to vanilla BitTorrent swarming. We upper-bound the per-transfer attribution posterior by the fraction of owner chunks in a sender's eligible cover set, and derive a tighter high-probability bound that improves with early non-owner mass. A simple heuristic, GreedyFastestFirst, attains about 92% of a bandwidth-optimal max-flow upper bound, while warm-up remains a stable about 12% share of a round across 100-500 peers. Under an observation-only local adversary, FLTorrent drives attribution success close to neighborhood-level random guessing for typical nodes, improves with network size, and remains robust under collusion. In LLM-scale dissemination stress tests over 7-10 Gbps access links, FLTorrent adds only about 6-10% round-time overhead relative to BitTorrent-only. Overall, FLTorrent shows that within-round unlinkability and BitTorrent-level efficiency can co-exist with predictable, low overheads at scale. △ Less

Submitted 14 May, 2026; v1 submitted 11 May, 2026; originally announced May 2026.

Comments: This paper has been accepted to the 46th IEEE International Conference on Distributed Computing Systems (ICDCS 2026). Please cite the IEEE proceedings version once it becomes available

DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents

Authors: Qisong Zhang, Wenzhuo Wu, Zhuangzhuang Jia, Yunhao Yang, Huayu Zhang, Xianghao Zang, Zhixiang He, Zhongjiang He, Kongming Liang, Zhanyu Ma

Abstract: Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instead it emerges through iterative generation, inspection, correction, filtering, and export. We present DataEvolver, a closed-loop visual data engine that organizes this process around explicit goals, persistent artifacts,… ▽ More Constructing controllable visual data is a major bottleneck for image editing and multimodal understanding. Useful supervision is rarely produced by a single rendering pass; instead it emerges through iterative generation, inspection, correction, filtering, and export. We present DataEvolver, a closed-loop visual data engine that organizes this process around explicit goals, persistent artifacts, bounded corrective actions, and acceptance decisions. DataEvolver supports multiple artifact types, including RGB images, masks, depth maps, normal maps, meshes, poses, trajectories, and review traces. In the current release, the system operates through two coupled loops: generation-time self-correction within each sample and validation-time self-expansion across dataset rounds. We validate the framework on an image-level object-rotation setting. With a fixed Qwen-Edit LoRA probe, our final Ours+DualGate model outperforms both the unadapted base model and a public multi-angle LoRA on SpatialEdit and a held-out evaluation set. Ablations show a consistent improvement path from scene-aware generation to feedback-driven correction and dual-gated validation. Beyond the released rotation data, our main contribution is a reusable framework for building visual datasets through explicit goal tracking, review, correction, and acceptance loops. △ Less

Submitted 3 May, 2026; originally announced May 2026.

Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion

Authors: Ge Luo, Jun-Jie Huang, Qi Yu, Tianrui Liu, Ke Liang, Yuming Xiang, Wentao Zhao, Xinwang Liu, Meng Wang

Abstract: Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learning. However, most existing deep unfolding image fusion methods are derived from alternating minimization, which updates the features of different modalities separately. This design introduces considerable computational a… ▽ More Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learning. However, most existing deep unfolding image fusion methods are derived from alternating minimization, which updates the features of different modalities separately. This design introduces considerable computational and memory overhead, limiting deployment on resource-constrained edge devices. To address this issue, we propose CDNet, a lightweight Combined Dictionary Unfolding Network for multi-source image fusion. Rather than introducing a new sparse coding prior or empirically compressing an existing fusion network, CDNet translates the unique-common decomposition prior of coupled dictionary learning into a structurally constrained joint unfolding architecture. The resulting CDBlock follows a block-sparse interaction topology and performs a model-derived joint update of common and modality-specific representations, thereby streamlining feature learning and improving efficiency.In addition, we design a compact High- and Low-frequency Image Fidelity loss for unsupervised training without ground-truth images. We evaluate CDNet on four tasks, including multi-exposure image fusion, infrared and visible image fusion, medical image fusion, and infrared and visible image fusion for semantic segmentation. Experimental results show that CDNet achieves competitive or superior fusion performance with high efficiency. For infrared and visible image fusion, CDNet outperforms competing methods on four of six metrics on the TNO dataset and five of six metrics on the RoadScene dataset. In particular, it surpasses the second-best method by 1.23 dB and 1.59 dB in PSNR on TNO and RoadScene, respectively. △ Less

Submitted 1 May, 2026; originally announced May 2026.

DETOUR: A Practical Backdoor Attack against Object Detection

Authors: Dazhuang Liu, Yanqi Qiao, Rui Wang, Kaitai Liang, Georgios Smaragdakis

Abstract: Object detection (OD) is critical to real-world vision systems, yet existing backdoor attacks on detection transformers (DETRs) for OD tasks rely on patch-wise triggers optimized at fixed locations with minimal perturbations. Such attacks overlook that backdoor triggers in the real world may appear at different sizes, fields of view (FoVs), and locations in images, while minimal perturbations are… ▽ More Object detection (OD) is critical to real-world vision systems, yet existing backdoor attacks on detection transformers (DETRs) for OD tasks rely on patch-wise triggers optimized at fixed locations with minimal perturbations. Such attacks overlook that backdoor triggers in the real world may appear at different sizes, fields of view (FoVs), and locations in images, while minimal perturbations are difficult for cameras to capture, limiting attack practicality. We first observe that a patch-wise trigger in DETR delivers high attack effectiveness when activating the backdoor across neighboring locations, a phenomenon we term the trigger radiating effect (TRE). Meanwhile, inserting patch-wise triggers across multiple locations synergistically enhances TRE, resulting in high attack effectiveness across images. We propose DETOUR, a practical backdoor attack by using semantic triggers that are effective in real-world object detection systems. To ensure attack practicality, we rescale trigger patterns to different sizes and insert them at various predefined locations during backdoor training, enabling the model to recognize the trigger regardless of its spatial configurations. To address FoV variations in physical deployments, we extract the trigger pattern from a real-world object (e.g., a mug) captured under multiple FoVs and inject the trigger accordingly, promoting viewpoint-invariant backdoor activation and enhancing TRE across the entire image. As a result, the backdoor can be reliably activated under diverse FoVs and spatial configurations. △ Less

Submitted 27 April, 2026; originally announced April 2026.

Decoupled Travel Planning with Behavior Forest

Authors: Duanyang Yuan, Sihang Zhou, Yanning Hou, Xiaoshu Chen, Haoyuan Chen, Ke Liang, Jiyuan Liu, Chuan Ma, Xinwang Liu, Jian Huang

Abstract: Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning step is not only constrained locally but also influenced by global constraints spanning multiple subtasks, leading to a tightly coupled and complex decision process. Existing travel planning methods typically rely on a si… ▽ More Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In such tasks, each planning step is not only constrained locally but also influenced by global constraints spanning multiple subtasks, leading to a tightly coupled and complex decision process. Existing travel planning methods typically rely on a single decision space that entangles all subtasks and constraints, failing to distinguish between locally acting constraints within a subtask and global constraints that span multiple subtasks. Consequently, the model is forced to jointly reason over local and global constraints at each decision step, increasing the reasoning burden and reducing planning efficiency. To address this problem, we propose the Behavior Forest method. Specifically, our approach structures the decision-making process into a forest of parallel behavior trees, where each behavior tree is responsible for a subtask. A global coordination mechanism is introduced to orchestrate the interactions among these trees, enabling modular and coherent travel planning. Within this framework, large language models are embedded as decision engines within behavior tree nodes, performing localized reasoning conditioned on task-specific constraints to generate candidate subplans and adapt decisions based on coordination feedback. The behavior trees, in turn, provide an explicit control structure that guides LLM generation. This design decouples complex tasks and constraints into manageable subspaces, enabling task-specific reasoning and reducing the cognitive load of LLM. Experimental results show that our method outperforms state-of-the-art methods by 6.67% on the TravelPlanner and by 11.82% on the ChinaTravel benchmarks, demonstrating its effectiveness in increasing LLM performance for complex multi-constraint travel planning. △ Less

Submitted 23 April, 2026; originally announced April 2026.

AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation

Authors: Yanning Hou, Duanyang Yuan, Sihang Zhou, Xiaoshu Chen, Ke Liang, Siwei Wang, Xinwang Liu, Jian Huang

Abstract: Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby improving retrieval coverage and precision. However, we observe that treating text chunks as the basic unit of knowledge representation rigidly groups multiple atomic facts together, limiting the flexibility and adaptability needed to support diverse re… ▽ More Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby improving retrieval coverage and precision. However, we observe that treating text chunks as the basic unit of knowledge representation rigidly groups multiple atomic facts together, limiting the flexibility and adaptability needed to support diverse retrieval scenarios. Additionally, triple-based entity linking is sensitive to relation-extraction errors, which can lead to missing or incorrect reasoning paths and ultimately hurt retrieval accuracy. To address these issues, we propose the Atom-Entity Graph, a more precise and reliable architecture for knowledge representation and indexing. In our approach, knowledge is stored as knowledge atoms, namely individual, self-contained units of factual information, rather than coarse-grained text chunks. This allows knowledge elements to be flexibly reassembled without mutual interference, thereby enabling seamless alignment with diverse query perspectives. Edges between entities simply indicate whether a relationship exists. By combining personalized PageRank with relevance-based filtering, we maintain accurate entity connections and improve the reliability of reasoning. Theoretical analysis and experiments on five public benchmarks show that the proposed AtomicRAG algorithm outperforms strong RAG baselines in retrieval accuracy and reasoning robustness. Code: https://github.com/7HHHHH/AtomicRAG. △ Less

Submitted 10 February, 2026; originally announced April 2026.

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers

Authors: Dazhuang Liu, Yanqi Qiao, Rui Wang, Kaitai Liang, Georgios Smaragdakis

Abstract: Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger location during inference to maximize trigger attention. However, they overlook the self-attention mechanism in ViTs, which captures long-range dependencies across patches. In this wo… ▽ More Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Existing patch-wise attacks typically assume a single fixed trigger location during inference to maximize trigger attention. However, they overlook the self-attention mechanism in ViTs, which captures long-range dependencies across patches. In this work, we observe that a patch-wise trigger can achieve high attack effectiveness when activating backdoors across neighboring patches, a phenomenon we term the Trigger Radiating Effect (TRE). We further find that inter-patch trigger insertion during training can synergistically enhance TRE compared to single-patch insertion. Prior ViT-specific attacks that maximize trigger attention often sacrifice visual and attention stealthiness, making them detectable. Based on these insights, we propose PASTA, a twofold stealthy patch-wise backdoor attack in both pixel and attention domains. PASTA enables backdoor activation when the trigger is placed at arbitrary patches during inference. To achieve this, we introduce a multi-location trigger insertion strategy to enhance TRE. However, preserving stealthiness while maintaining strong TRE is challenging, as TRE is weakened under stealthy constraints. We therefore formulate a bi-level optimization problem and propose an adaptive backdoor learning framework, where the model and trigger iteratively adapt to each other to avoid local optima. Extensive experiments show that PASTA achieves 99.13% attack success rate across arbitrary patches on average, while significantly improving visual and attention stealthiness (144.43x and 18.68x) and robustness (2.79x) against state-of-the-art ViT defenses across four datasets, outperforming CNN- and ViT-based baselines. △ Less

Submitted 21 April, 2026; originally announced April 2026.

A Weak Solution of Inverse Treblecross

Authors: Kai Liang, Muxi Li

Abstract: We give a weak solution for an impartial game we called ``Inverse Treblecross''. We have determined which of its starting positions are $\mathscr{P}$-position and give a reasonable strategy. We give a weak solution for an impartial game we called ``Inverse Treblecross''. We have determined which of its starting positions are $\mathscr{P}$-position and give a reasonable strategy. △ Less

Submitted 17 April, 2026; originally announced April 2026.

MSC Class: 91A46

The Role of Emotional Stimuli and Intensity in Shaping Large Language Model Behavior

Authors: Ameen Patel, Felix Lee, Kyle Liang, Joseph Thomas

Abstract: Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited to single types of positive emotional stimuli and have not considered varying degrees of emotion intensity in their analyses. In this paper, we explore the effe… ▽ More Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited to single types of positive emotional stimuli and have not considered varying degrees of emotion intensity in their analyses. In this paper, we explore the effects of four distinct emotions - joy, encouragement, anger, and insecurity - in emotional prompting and evaluate them on accuracy, sycophancy, and toxicity. We develop a prompt-generation pipeline with GPT-4o mini to create a suite of LLM and human-generated prompts with varying intensities across the four emotions. Then, we compile a "Gold Dataset" of prompts where human and model labels align. Our empirical evaluation on LLM behavior suggests that positive emotional stimuli lead to more accurate and less toxic results, but also increase sycophantic behavior. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Journal ref: Poster Presentation at AACL Student Research Workshop 2025

DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions

Authors: Xinran Wang, Yuxuan Zhang, Xiao Zhang, Haolong Yan, Muxi Diao, Songyu Xu, Zhonghao Yan, Hongbing Li, Kongming Liang, Zhanyu Ma

Abstract: Accurately detecting and localizing hallucinations is a critical task for ensuring high reliability of image captions. In the era of Multimodal Large Language Models (MLLMs), captions have evolved from brief sentences into comprehensive narratives, often spanning hundreds of words. This shift exponentially increases the challenge: models must now pinpoint specific erroneous spans or words within e… ▽ More Accurately detecting and localizing hallucinations is a critical task for ensuring high reliability of image captions. In the era of Multimodal Large Language Models (MLLMs), captions have evolved from brief sentences into comprehensive narratives, often spanning hundreds of words. This shift exponentially increases the challenge: models must now pinpoint specific erroneous spans or words within extensive contexts, rather than merely flag response-level inconsistencies. However, existing benchmarks lack the fine granularity and domain diversity required to evaluate this capability. To bridge this gap, we introduce DetailVerifyBench, a rigorous benchmark comprising 1,000 high-quality images across five distinct domains. With an average caption length of over 200 words and dense, token-level annotations of multiple hallucination types, it stands as the most challenging benchmark for precise hallucination localization in the field of long image captioning to date. Our benchmark is available at https://zyx-hhnkh.github.io/DetailVerifyBench/. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Comments: 8 pages, 5 figures. The dataset and code are available at https://zyx-hhnkh.github.io/DetailVerifyBench/

Differentiable SpaTiaL: Symbolic Learning and Reasoning with Geometric Temporal Logic for Manipulation Tasks

Authors: Licheng Luo, Kaier Liang, Cristian-Ioan Vasile, Mingyu Cai

Abstract: Executing complex manipulation in cluttered environments requires satisfying coupled geometric and temporal constraints. Although Spatio-Temporal Logic (SpaTiaL) offers a principled specification framework, its use in gradient-based optimization is limited by non-differentiable geometric operations. Existing differentiable temporal logics focus on the robot's internal state and neglect interactive… ▽ More Executing complex manipulation in cluttered environments requires satisfying coupled geometric and temporal constraints. Although Spatio-Temporal Logic (SpaTiaL) offers a principled specification framework, its use in gradient-based optimization is limited by non-differentiable geometric operations. Existing differentiable temporal logics focus on the robot's internal state and neglect interactive object-environment relations, while spatial logic approaches that capture such interactions rely on discrete geometry engines that break the computational graph and preclude exact gradient propagation. To overcome this limitation, we propose Differentiable SpaTiaL, a fully tensorized toolbox that constructs smooth, autograd-compatible geometric primitives directly over polygonal sets. To the best of our knowledge, this is the first end-to-end differentiable symbolic spatio-temporal logic toolbox. By analytically deriving differentiable relaxations of key spatial predicates--including signed distance, intersection, containment, and directional relations--we enable an end-to-end differentiable mapping from high-level semantic specifications to low-level geometric configurations, without invoking external discrete solvers. This fully differentiable formulation unlocks two core capabilities: (i) massively parallel trajectory optimization under rigorous spatio-temporal constraints, and (ii) direct learning of spatial logic parameters from demonstrations via backpropagation. Experimental results validate the effectiveness and scalability of the proposed framework. △ Less

Submitted 7 April, 2026; v1 submitted 2 April, 2026; originally announced April 2026.

Comments: Code available at: https://github.com/plen1lune/DiffSpaTiaL

HMPDM: A Diffusion Model for Driving Video Prediction with Historical Motion Priors

Authors: Ke Li, Tianjia Yang, Kaidi Liang, Xianbiao Hu, Ruwen Qin

Abstract: Video prediction is a useful function for autonomous driving, enabling intelligent vehicles to reliably anticipate how driving scenes will evolve and thereby supporting reasoning and safer planning. However, existing models are constrained by multi-stage training pipelines and remain insufficient in modeling the diverse motion patterns in real driving scenes, leading to degraded temporal consisten… ▽ More Video prediction is a useful function for autonomous driving, enabling intelligent vehicles to reliably anticipate how driving scenes will evolve and thereby supporting reasoning and safer planning. However, existing models are constrained by multi-stage training pipelines and remain insufficient in modeling the diverse motion patterns in real driving scenes, leading to degraded temporal consistency and visual quality. To address these challenges, this paper introduces the historical motion priors-informed diffusion model (HMPDM), a video prediction model that leverages historical motion priors to enhance motion understanding and temporal coherence. The proposed deep learning system introduces three key designs: (i) a Temporal-aware Latent Conditioning (TaLC) module for implicit historical motion injection; (ii) a Motion-aware Pyramid Encoder (MaPE) for multi-scale motion representation; (iii) a Self-Conditioning (SC) strategy for stable iterative denoising. Extensive experiments on the Cityscapes and KITTI benchmarks demonstrate that HMPDM outperforms state-of-the-art video prediction methods with efficiency, achieving a 28.2% improvement in FVD on Cityscapes under the same monocular RGB input configuration setting. The implementation codes are publicly available at https://github.com/KELISBU/HMPDM. △ Less

Submitted 28 March, 2026; originally announced March 2026.

ADaFuSE: Adaptive Diffusion-generated Image and Text Fusion for Interactive Text-to-Image Retrieval

Authors: Zhuocheng Zhang, Xingwu Zhang, Kangheng Liang, Guanxuan Li, Richard Mccreadie, Zijun Long

Abstract: Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched, resulting in increased effectiveness. However, existing frameworks fuse multi-modal views of user feedback by simple embedding addition. In this work, we show that this static and undifferentiated fusion indiscriminately… ▽ More Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched, resulting in increased effectiveness. However, existing frameworks fuse multi-modal views of user feedback by simple embedding addition. In this work, we show that this static and undifferentiated fusion indiscriminately incorporates generative noise produced by the diffusion model, leading to performance degradation for up to 55.62% samples. We further propose ADaFuSE (Adaptive Diffusion-Text Fusion with Semantic-aware Experts), a lightweight fusion model designed to align and calibrate multi-modal views for diffusion-augmented I-TIR, which can be plugged into existing frameworks without modifying the backbone encoder. Specifically, we introduce a dual-branch fusion mechanism that employs an adaptive gating branch to dynamically balance modality reliability, alongside a semantic-aware mixture-of-experts branch to capture fine-grained cross-modal nuances. Via thorough evaluation over four standard I-TIR benchmarks, ADaFuSE achieves state-of-the-art performance, surpassing DAR by up to 3.49% in Hits@10 with only a 5.29% parameter increase, while exhibiting stronger robustness to noisy and longer interactive queries. These results show that generative augmentation coupled with principled fusion provides a simple, generalizable alternative to fine-tuning for interactive retrieval. △ Less

Submitted 23 March, 2026; originally announced March 2026.

Scheduling Parallel Optical Circuit Switches for AI Training

Authors: Kevin Liang, Litao Qiao, Isaac Keslassy, Bill Lin

Abstract: The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed interest in optical circuit switches (OCSes) as a high-bandwidth, energy-efficient alternative for AI fabrics. Deploying multiple parallel OCSes is a leading alternative. However, efficiently scheduling time-varying traffic matrices across parallel optical switch… ▽ More The rapid growth of AI training has dramatically increased datacenter traffic demand and energy consumption, which has motivated renewed interest in optical circuit switches (OCSes) as a high-bandwidth, energy-efficient alternative for AI fabrics. Deploying multiple parallel OCSes is a leading alternative. However, efficiently scheduling time-varying traffic matrices across parallel optical switches with non-negligible reconfiguration delays remains an open challenge. We consider the problem of scheduling a single AI traffic demand matrix $D$ over $s$ parallel OCSes while minimizing the makespan under reconfiguration delay $δ$. Our algorithm Spectra relies on a three-step approach: Decompose $D$ into a minimal set of weighted permutations; Schedule these permutations across parallel switches using load-aware assignment; then Equalize the imbalanced loads on the switches via controlled permutation splitting. Evaluated on realistic AI training workloads (GPT model and Qwen MoE expert routing) as well as standard benchmarks, Spectra vastly outperforms a baseline based on state-of-the-art algorithms, reducing schedule makespan by an average factor of $1.4\times$ on GPT AI workloads, $1.9\times$ on MoE AI workloads, and $2.4\times$ on standard benchmarks. Further, the makespans achieved by Spectra consistently approach newly derived lower bounds. △ Less

Submitted 7 March, 2026; originally announced March 2026.

Retrieval-Augmented Generation with Covariate Time Series

Authors: Kenny Ye Liang, Zhongyi Pei, Huan Zhang, Yuhui Liu, Shaoxu Song, Jianmin Wang

Abstract: While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial scenario characterized by (1) data scarcity, (2) short transient sequences, and (3) covariate coupled dynamics. Unfortunately, existing time-series… ▽ More While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial scenario characterized by (1) data scarcity, (2) short transient sequences, and (3) covariate coupled dynamics. Unfortunately, existing time-series RAG approaches predominantly rely on generated static vector embeddings and learnable context augmenters, which may fail to distinguish similar regimes in such scarce, transient, and covariate coupled scenarios. To address these limitations, we propose RAG4CTS, a regime-aware, training-free RAG framework for Covariate Time-Series. Specifically, we construct a hierarchal time-series native knowledge base to enable lossless storage and physics-informed retrieval of raw historical regimes. We design a two-stage bi-weighted retrieval mechanism that aligns historical trends through point-wise and multivariate similarities. For context augmentation, we introduce an agent-driven strategy to dynamically optimize context in a self-supervised manner. Extensive experiments on PRSOV demonstrate that our framework significantly outperforms state-of-the-art baselines in prediction accuracy. The proposed system is deployed in Apache IoTDB within China Southern Airlines. Since deployment, our method has successfully identified one PRSOV fault in two months with zero false alarm. △ Less

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

Comments: 12 pages. Preprint

Generative Visual Chain-of-Thought for Image Editing

Authors: Zijin Yin, Tiankai Hang, Yiji Cheng, Shiyi Zhang, Runze He, Yu Xu, Chunyu Wang, Bing Li, Zheng Chang, Kongming Liang, Qinglin Lu, Zhanyu Ma

Abstract: Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Visual Chain-of-Thought (GVCoT), a unified framework that performs native visual reasoning by first generating spatial cues to localize the target region and then executing the edit. Unlike prior text-only CoT or tool-depe… ▽ More Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Visual Chain-of-Thought (GVCoT), a unified framework that performs native visual reasoning by first generating spatial cues to localize the target region and then executing the edit. Unlike prior text-only CoT or tool-dependent visual CoT paradigms, GVCoT jointly optimizes visual tokens generated during the reasoning and editing phases in an end-to-end manner. This way fosters the emergence of innate spatial reasoning ability and enables more effective utilization of visual-domain cues. The main challenge of training GCVoT lies in the scarcity of large-scale editing data with precise edit region annotations; to this end, we construct GVCoT-Edit-Instruct, a dataset of 1.8M high-quality samples spanning 19 tasks. We adopt a progressive training strategy: supervised fine-tuning to build foundational localization ability in reasoning trace before final editing, followed by reinforcement learning to further improve reasoning and editing quality. Finally, we introduce SREdit-Bench, a new benchmark designed to comprehensively stress-test models under sophisticated scenes and fine-grained referring expressions. Experiments demonstrate that GVCoT consistently outperforms state-of-the-art models on SREdit-Bench and ImgEdit. We hope our GVCoT will inspire future research toward interpretable and precise image editing. △ Less

Submitted 16 March, 2026; v1 submitted 2 March, 2026; originally announced March 2026.

Comments: Project page: https://pris-cv.github.io/GVCoT/

Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing

Authors: Zijin Yin, Bing Li, Kongming Liang, Hao Sun, Zhongjiang He, Zhanyu Ma, Jun Guo

Abstract: Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in advance. In this paper, we construct an automatic data generation pipeline Gen4Seg to stress-test semantic segmentation models by generating various challenging… ▽ More Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in advance. In this paper, we construct an automatic data generation pipeline Gen4Seg to stress-test semantic segmentation models by generating various challenging samples with different attribute changes. Beyond previous evaluation paradigms focusing solely on global weather and style transfer, we investigate variations in both appearance and geometry attributes at the object and image level. These include object color, material, size, position, as well as image-level variations such as weather and style. To achieve this, we propose to edit visual attributes of existing real images with precise control of structural information, empowered by diffusion models. In this way, the existing segmentation labels can be reused for the edited images, which greatly reduces the labor costs. Using our pipeline, we construct two new benchmarks, Pascal-EA and COCO-EA. We benchmark a wide variety of semantic segmentation models, spanning from closed-set models to open-vocabulary large models. We have several key findings: 1) advanced open-vocabulary models do not exhibit greater robustness compared to closed-set methods under geometric variations; 2) data augmentation techniques, such as CutOut and CutMix, are limited in enhancing robustness against appearance variations; 3) our pipeline can also be employed as a data augmentation tool and improve both in-distribution and out-of-distribution performances. Our work suggests the potential of generative models as effective tools for automatically analyzing segmentation models, and we hope our findings will assist practitioners and researchers in developing more robust and reliable segmentation models. △ Less

Submitted 16 March, 2026; v1 submitted 2 March, 2026; originally announced March 2026.

Comments: Accepted to IEEE TPAMI 2026

SegSEM: Enabling and Enhancing SAM2 for SEM Contour Extraction

Authors: Da Chen, Guangyu Hu, Kaihong Xu, Kaichao Liang, Songjiang Li, Wei Yang, XiangYu Wen, Mingxuan Yuan

Abstract: Extracting high-fidelity 2D contours from Scanning Electron Microscope (SEM) images is critical for calibrating Optical Proximity Correction (OPC) models. While foundation models like Segment Anything 2 (SAM2) are promising, adapting them to specialized domains with scarce annotated data is a major challenge. This paper presents a case study on adapting SAM2 for SEM contour extraction in a few-sho… ▽ More Extracting high-fidelity 2D contours from Scanning Electron Microscope (SEM) images is critical for calibrating Optical Proximity Correction (OPC) models. While foundation models like Segment Anything 2 (SAM2) are promising, adapting them to specialized domains with scarce annotated data is a major challenge. This paper presents a case study on adapting SAM2 for SEM contour extraction in a few-shot setting. We propose SegSEM, a framework built on two principles: a data-efficient fine-tuning strategy that adapts by selectively training only the model's encoders, and a robust hybrid architecture integrating a traditional algorithm as a confidence-aware fallback. Using a small dataset of 60 production images, our experiments demonstrate this methodology's viability. The primary contribution is a methodology for leveraging foundation models in data-constrained industrial applications. △ Less

Submitted 18 April, 2026; v1 submitted 23 February, 2026; originally announced February 2026.

Comments: 4 pages, 6 figures, accpeted by ISCAS 2026

Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images

Authors: Yuxuan Yang, Zhonghao Yan, Yi Zhang, Bo Yun, Muxi Diao, Guowei Zhao, Kongming Liang, Wenbin Li, Zhanyu Ma

Abstract: Hepatocellular Carcinoma diagnosis relies heavily on the interpretation of gigapixel Whole Slide Images. However, current computational approaches are constrained by fixed-resolution processing mechanisms and inefficient feature aggregation, which inevitably lead to either severe information loss or high feature redundancy. To address these challenges, we propose Hepato-LLaVA, a specialized Multi-… ▽ More Hepatocellular Carcinoma diagnosis relies heavily on the interpretation of gigapixel Whole Slide Images. However, current computational approaches are constrained by fixed-resolution processing mechanisms and inefficient feature aggregation, which inevitably lead to either severe information loss or high feature redundancy. To address these challenges, we propose Hepato-LLaVA, a specialized Multi-modal Large Language Model designed for fine-grained hepatocellular pathology analysis. We introduce a novel Sparse Topo-Pack Attention mechanism that explicitly models 2D tissue topology. This mechanism effectively aggregates local diagnostic evidence into semantic summary tokens while preserving global context. Furthermore, to overcome the lack of multi-scale data, we present HepatoPathoVQA, a clinically grounded dataset comprising 33K hierarchically structured question-answer pairs validated by expert pathologists. Our experiments demonstrate that Hepato-LLaVA achieves state-of-the-art performance on HCC diagnosis and captioning tasks, significantly outperforming existing methods. Our code and implementation details are available at https://pris-cv.github.io/Hepto-LLaVA/. △ Less

Submitted 1 March, 2026; v1 submitted 22 February, 2026; originally announced February 2026.

Comments: 10 pages, 3 figures

Learning Personalized Agents from Human Feedback

Authors: Kaiqu Liang, Julia Kruk, Shengyi Qian, Xianjun Yang, Shengjie Bi, Yuanshun Yao, Shaoliang Nie, Mingyang Zhang, Lijuan Liu, Jaime Fernández Fisac, Shuyan Zhou, Saghar Hosseini

Abstract: Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or encoding user profiles in external memory. However, these approaches struggle with new users and with preferences that change over time. We introduce Personali… ▽ More Modern AI agents are powerful but often fail to align with the idiosyncratic, evolving preferences of individual users. Prior approaches typically rely on static datasets, either training implicit preference models on interaction history or encoding user profiles in external memory. However, these approaches struggle with new users and with preferences that change over time. We introduce Personalized Agents from Human Feedback (PAHF), a framework for continual personalization in which agents learn online from live interaction using explicit per-user memory. PAHF operationalizes a three-step loop: (1) seeking pre-action clarification to resolve ambiguity, (2) grounding actions in preferences retrieved from memory, and (3) integrating post-action feedback to update memory when preferences drift. To evaluate this capability, we develop a four-phase protocol and two benchmarks in embodied manipulation and online shopping. These benchmarks quantify an agent's ability to learn initial preferences from scratch and subsequently adapt to persona shifts. Our theoretical analysis and empirical results show that integrating explicit memory with dual feedback channels is critical: PAHF learns substantially faster and consistently outperforms both no-memory and single-channel baselines, reducing initial personalization error and enabling rapid adaptation to preference shifts. △ Less

Submitted 17 February, 2026; originally announced February 2026.

From Snapshot Sensing to Persistent EM World Modeling: A Generative-Space Perspective for ISAC

Authors: Pin-Han Ho, Haoran Mei, Limei Peng, Yiming Miao, Kairan Liang, Yan Jiao

Abstract: Electromagnetic (EM) world modeling is emerging as a foundational capability for environment-aware and embodiment-enabled wireless systems. However, most existing mmWave sensing solutions are designed for snapshot-based parameter estimation and rely on hardware-intensive architectures, making scalable and persistent world modeling difficult to achieve. This article rethinks mmWave sensing from a s… ▽ More Electromagnetic (EM) world modeling is emerging as a foundational capability for environment-aware and embodiment-enabled wireless systems. However, most existing mmWave sensing solutions are designed for snapshot-based parameter estimation and rely on hardware-intensive architectures, making scalable and persistent world modeling difficult to achieve. This article rethinks mmWave sensing from a system-level perspective and introduces a generative-space framework, in which sensing is realized through controlled traversal of a low-dimensional excitation space spanning frequency, waveform, and physical embodiment. This perspective decouples spatial observability from rigid antenna arrays and transmit-time multiplexing, enabling flexible and scalable sensing-by-design radios. To illustrate the practicality of this framework, we present a representative realization called Multi-RF Chain Frequency-as-Aperture Clip-on Aperture Fabric (MRC-FaA-CAF), where multiple FMCW sources coordinate frequency-selective modules distributed along guided-wave backbones. This architecture enables interference-free excitation, preserves beat-frequency separability, and maintains low calibration overhead. Case studies show that generative-space-driven sensing can achieve update rates comparable to phased arrays while avoiding dense RF replication and the latency penalties of TDM-MIMO systems. Overall, this work positions generative-space-driven sensing as a practical architectural foundation for mmWave systems that move beyond snapshot sensing toward persistent EM world modeling. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Comments: 7 pages, 6 figures/tables

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Authors: Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao, Bo Dong, Bojun Wang, Boyu Chen, Brian Li, Buyun Ma, Chang Su, Changxin Miao, Changyi Wan, Chao Lou, Chen Hu, Chen Xu, Chenfeng Yu, Chengting Feng, Chengyuan Yao, Chunrui Han, Dan Ma, Dapeng Shi, Daxin Jiang, Dehua Ma, Deshan Sun , et al. (191 additional authors not shown)

Abstract: We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/f… ▽ More We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments. △ Less

Submitted 23 February, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Comments: Technical report for Step 3.5 Flash

Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers

Authors: Shuo Zhang, Wenzhuo Wu, Huayu Zhang, Jiarong Cheng, Xianghao Zang, Chao Ban, Hao Sun, Zhongjiang He, Tianwei Cao, Kongming Liang, Zhanyu Ma

Abstract: Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particularly in complex scenes. Existing approaches suffer from two main limitations: (1) difficulty in achieving accurate geometric editing of object translation, rotation, and scaling; (2) inadequate modeling… ▽ More Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particularly in complex scenes. Existing approaches suffer from two main limitations: (1) difficulty in achieving accurate geometric editing of object translation, rotation, and scaling; (2) inadequate modeling of intricate lighting and shadow effects, leading to unrealistic results. To address these issues, we propose GeoEdit, a framework that leverages in-context generation through a diffusion transformer module, which integrates geometric transformations for precise object edits. Moreover, we introduce Effects-Sensitive Attention, which enhances the modeling of intricate lighting and shadow effects for improved realism. To further support training, we construct RS-Objects, a large-scale geometric editing dataset containing over 120,000 high-quality image pairs, enabling the model to learn precise geometric editing while generating realistic lighting and shadows. Extensive experiments on public benchmarks demonstrate that GeoEdit consistently outperforms state-of-the-art methods in terms of visual quality, geometric accuracy, and realism. △ Less

Submitted 9 February, 2026; originally announced February 2026.

FaA-CAF: Modular Single-RF-Chain Near-Field mmWave Sensing via Clip-On Antenna Fabric

Authors: Pin-Han Ho, Haoran Mei, Limei Peng, Yiming Miao, Xu Fan, Kairan Liang, Tong Wei, Wei Duan

Abstract: Near field mmWave sensing is poised to play a key role in future wireless systems, enabling environment-aware, embodied, and application adaptive operation under stringent form-factor and hardware constraints. However, achieving high spatial resolution in the near field typically requires large antenna arrays, multiple radio frequency (RF) chains, or mechanical scanning, creating a fundamental ten… ▽ More Near field mmWave sensing is poised to play a key role in future wireless systems, enabling environment-aware, embodied, and application adaptive operation under stringent form-factor and hardware constraints. However, achieving high spatial resolution in the near field typically requires large antenna arrays, multiple radio frequency (RF) chains, or mechanical scanning, creating a fundamental tension between spatial observability and system simplicity. This paper presents frequency as aperture clip on antenna fabric (FaACAF), a hardware efficient sensing by design architecture that synthesizes spatial aperture through the FaA paradigm using a single RF chain. FaACAF realizes a modular clip on aperture fabric, in which frequency selective clip on modules (CMs) are attached to a shared guided-wave substrate and implicitly coordinated by the instantaneous frequency modulated continuous wave (FMCW) excitation frequency. In this fabric, FMCW signaling simultaneously indexes the sensing aperture and orchestrates uplink/downlink signal distribution and echo multiplexing in a switch free, fully passive, and all analog manner, eliminating RF switching and multichannel front ends. An online self calibration mechanism stabilizes the frequency to aperture mapping under practical attachment variability without requiring full matrix calibration. Two case studies illustrate the robustness of the proposed approach and quantify the predictable sensing margin tradeoffs introduced by modular deployment. Overall, FaACAF demonstrates that near field spatial observability can be scaled through architectural coordination in the frequency domain rather than hardware expansion, providing a reconfigurable and hardware efficient pathway toward embodied sensing and integrated sensing and communication (ISAC) in future wireless systems. △ Less

Submitted 6 February, 2026; originally announced February 2026.

FOCUS: DLLMs Know How to Tame Their Compute Bound

Authors: Kaihua Liang, Xin Tan, An Zhong, Hong Xu, Marco Canini

Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. W… ▽ More Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, but their deployment is constrained by high decoding cost. In this work, we identify a key inefficiency in DLLM decoding: while computation is parallelized over token blocks, only a small subset of tokens is decodable at each diffusion step, causing most compute to be wasted on non-decodable tokens. We further observe a strong correlation between attention-derived token importance and token-wise decoding probability. Based on this insight, we propose FOCUS, an inference system designed for DLLMs. By dynamically focusing computation on decodable tokens and evicting non-decodable ones on-the-fly, FOCUS increases the effective batch size, alleviating compute limitations and enabling scalable throughput. Empirical evaluations demonstrate that FOCUS achieves up to 3.52$\times$ throughput improvement over the production-grade engine LMDeploy in large-batch settings, while preserving or improving generation quality across multiple benchmarks. △ Less

Submitted 10 June, 2026; v1 submitted 30 January, 2026; originally announced January 2026.

Comments: ICML 2026 camera-ready version

ACM Class: I.2.7; C.4