8 papers
Context Is Not Authority: Structured Runtime Governance for Financial Market Agents
Rui Tang, Qiangqiang Liu, Yichi Zhang +3
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…
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…
Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
Dazhao Du, Jian Liu, Jialong Qin +7
Video large language models (Video LLMs) can achieve strong video-QA accuracy without reliably tracking spatiotemporal dynamics. A model may answer a motion question from static cu…
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)…
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…
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…
Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization
Jian Li, Shenglin Yin, Yujia Zhang +4
Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has increasingly focused on t…
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness
Jian Li, Haojing Huang, Yujia Zhang +6
Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as D…