AI.info

Zhuotao Tian

Explore Zhuotao Tian on AI.info.

• FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
• Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
• SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation
• Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations