4 papers
Offline-Online Curriculum RL for Multimodal Reasoning
Wendi Deng, Hang Du, Guoshun Nan +11
Multimodal large language models exhibit capabilities on reasoning tasks, yet often produce flawed intermediate steps while yielding correct final answers. This behavior undermines…
LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs
Jingfeng Chen, Jiawen Qian, Wendi Deng +5
Video understanding in multimodal large language models requires selecting informative frames from long, redundant videos under limited visual-token budgets. Existing methods often…
Atomic Consistency Preference Optimization for Long-Form Question Answering
Jingfeng Chen, Raghuveer Thirukovalluru, Junlin Wang +2
Large Language Models (LLMs) often produce factoid hallucinations - plausible yet incorrect answers. A common mitigation strategy is model alignment, which improves factual accurac…
ArbiViewGen: Controllable Arbitrary Viewpoint Camera Data Generation for Autonomous Driving via Stable Diffusion Models
Yatong Lan, Jingfeng Chen, Yiru Wang +1
Arbitrary viewpoint image generation holds significant potential for autonomous driving, yet remains a challenging task due to the lack of ground-truth data for extrapolated views,…