3 papers
cs.CV2026
LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding
Xiaodong Wang, Langling Huang, Zhirong Wu +4
The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interacti…
cs.CV2025
LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs
Xiaodong Wang, Jinfa Huang, Li Yuan +1
Most Video Large Language Models (Video-LLMs) adopt preference alignment techniques, e.g., DPO~\citep{rafailov2024dpo}, to optimize the reward margin between a winning response ($y…
cs.CV2025
ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos
Xiaodong Wang, Peixi Peng
Real-world driving requires people to observe the current environment, anticipate the future, and make appropriate driving decisions. This requirement is aligned well with the capa…