activity
20242026
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.CV2026

EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation

Songlin Yang, Haobin Zhong, Ruilin Zhang +23

The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community tr…

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.CL2025

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…

cs.CL2024

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…