32 citations · 48 across the 47 of their papers we have counts for
52 papers
Self-Evolving Embodied Agents via Skill-Harness Evolution
Peidong Wang, Zhiming Ma, Ying Chang +7
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces,…
HarmTrace: Anchor-Calibrated Decoupled Optimization for Fine-Grained Target Identification in Harmful Memes
Yujia Li, Yiqun Zhang, Zihan Cheng +7
Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while misidentifying the attacked tar…
Can MLLMs Decode the Creative Leap? Introducing C4 for Cross-Concept Understanding
Ming Wang, Yuqing Zhang, Tingna Xie +5
Creative capabilities of MLLMs matter in design, communication, education, and human--AI collaboration, yet remain difficult to evaluate because explicit targets and reward signals…
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
Ming Wang, Peidong Wang, Xiaocui Yang +4
Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the development of lifelong agents that r…
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
Zihan Wang, Hao Wang, Boyuan Jiang +8
Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time. We observe that, even afte…
TRAM: Enhancing Multimodal Reasoning with Trajectory-Derived Auxiliary Memory
Kang Liu, Zijing Wang, Yongkang Liu +5
Multimodal Large Reasoning Models (MLRMs) have achieved strong performance on tasks requiring visual understanding and multi-step inference. However, as reasoning trajectories grow…
CrossLex: A Source-Grounded Benchmark for Cross-Jurisdictional Legal Reasoning in Large Language Models
Xiaocui Yang, Xican Tan, Shoujie Chen +3
Legal reasoning is inherently jurisdiction-dependent: the same facts can call for different legal rules and yield different conclusions across legal systems. Yet existing benchmark…
What are Key Factors for Updates in RL for LLM Reasoning?
Peidong Wang, Demi Wang, Xufang Luo +5
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning ability of large language models. However, much of the existi…
PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
Wen Zhang, Xiaocui Yang, Zhuoyue Gao +3
Empathetic spoken dialogue systems require not only semantically appropriate responses but also emotionally aligned prosodic expression. However, cascade pipelines often discard ac…
Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models
Yichen Gao, Yiqun Zhang, Zijing Wang +7
Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This raises a basic question: is the audio-supported answer unavail…
SAILRec: Steering LLM Attention to Dual-Side Semantically Aligned Collaborative Embeddings for Recommendation
Xi Wu, Jiale Wang, Zihan Wang +5
Recent LLM-based recommenders enhance language models with collaborative embeddings from user-item interactions, but making such embeddings available does not ensure their proper u…
CR-Seg: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation
Yifan Cao, Xiaocui Yang, Faxian Wan +3
Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically rely on either learned semant…
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
Ming Wang, Shuang Wu, Bixuan Wang +7
Self-report questionnaires remain the prevailing tool for probing the psychological states of persona-conditioned agents (PC-Agents). However, classical instruments inherit two wel…
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
Zijing Wang, Mingyang Wang, Ercong Nie +6
Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; however, extending an existing mu…
How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
YiJie Huang, Yiqun Zhang, Zhuoyue Jia +7
Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling quest…
From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
Xiao Wang, Yifei Zhang, YongKang Liu +4
Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors learned from millions of prefer…
MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
Yiqun Zhang, Hao Li, Zihan Wang +6
Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model invocations, accumulating substan…
GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
Faxian Wan, Xiaocui Yang, Yifan Cao +3
Moving beyond the traditional binary classification paradigm of Multimodal Sarcasm Detection, Multimodal Sarcasm Target Identification (MSTI) presents a more formidable challenge,…
WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing
Fanheng Kong, Jingyuan Zhang, Yang Yue +10
The emergence of Large Language Models (LLMs) has catalyzed a paradigm shift in programming, giving rise to "vibe coding", where users can build complete projects and even control…
DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference
Zihan Wang, Hao Wang, Shi Feng +6
Medical reasoning models remain constrained by parametric knowledge and are thus susceptible to forgetting and hallucinations. DeepResearch (DR) models ground outputs in verifiable…
NEAT: Neuron-Based Early Exit for Large Reasoning Models
Kang Liu, Yongkang Liu, Xiaocui Yang +5
Large Reasoning Models (LRMs) often suffer from \emph{overthinking}, a phenomenon in which redundant reasoning steps are generated after a correct solution has already been reached…
Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
Yinzhi Zhao, Ming Wang, Shi Feng +3
Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety a…
ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation
Zhuoyue Gao, Xiaohui Wang, Xiaocui Yang +4
Empathetic speech dialogue requires not only understanding linguistic content but also perceiving rich paralinguistic information such as prosody, tone, and emotional intensity for…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically de…