AI.info

Yansong Tang

Explore Yansong Tang on AI.info.

• CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
• AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
• Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
• Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
• VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning