collaborators

7 papers

cs.CV2026

Deep Thought Alignment: Trajectory-Level Latent Distillation for Video Reasoning

Ao Shen, Yongheng Zhang, Yinghui Li +3

Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information. This dilemma motivates t…

cs.AI2026

From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities

Jiayi Kuang, Yinghui Li, Yunze Song +11

Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks evaluate onl…

cs.AI2026

From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI

Yongheng Zhang, Ziang Liu, Jiaxuan Zhu +17

Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reasoning, action, memory, and self-im…

cs.CV2026

Thinking in Video: Can Video Generators Really Reason About the Real World?

Yongheng Zhang, Guang Yang, Ruihan Hou +12

Recent advances in world models and video generation have given rise to an emerging reasoning paradigm that leverages video generative models to simulate, predict, and reason about…

cs.AI2026

TopoAgent: A Self-Evolving Topological Agent for Multimodal Scientific Reasoning

Mingze Xu, Yinghui Li, Jiayi Kuang +5

While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning. Such…

cs.CV2026

Latent Visual Cache for Video Reasoning

Yongheng Zhang, Zhipeng Xu, Hao Wu +4

Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt "read-once, generate-many" paradigm, in which visua…