AI.info

Limin Wang

Explore Limin Wang on AI.info.

• Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline
• LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
• TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
• Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
• VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
• UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
• VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations
• MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
• ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
• UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation