collaborators

7 papers

cs.CV2026

Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation

Dazhao Du, Shiyan Du, Jian Liu +8

Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs…

cs.AI2026

Context Is Not Authority: Structured Runtime Governance for Financial Market Agents

Rui Tang, Qiangqiang Liu, Yichi Zhang +4

Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy. We present SAGE-Fin, a finance-specific authority-ha…

cs.CV2026

Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning

Dazhao Du, Jian Liu, Jialong Qin +7

Video large language models (Video LLMs) achieve strong benchmark accuracy, yet often answer video questions through shortcuts such as single-frame cues and language priors rather…

cs.CV2026

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues

Dazhao Du, Liao Duan, Jian Liu +5

Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal large language models (MLLMs)…

cs.AI2026

Recall Isn't Enough: Bounding Commitments in Personalized Language Systems

Rui Tang, Yichi Zhang, Xi Chen +4

Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it turns noisy hints into hard con…

cs.CL2026

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

Yujie Feng, Jian Li, Zhihan Zhou +7

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contex…