Jiahang Cao

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

Recursive Cleaning for Large-scale Protein Data via Multimodal Learning

The Meta-Representation Hypothesis

A Dual-Agent Adversarial Framework for Generalizable Reinforcement Learning

Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream

Enhancing Discontinuous Radiance Fields with Continuous representation