Zhongqi Yue

Benchmarking Open-Set Recognition Beyond Vision-Language Pre-training

Expanding the Action Space of LLMs to Reason Beyond Language

HOW TO TRAIN YOUR DIFFUSION MODELS FOR FEW- SHOT CLASSIFICATION

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example

Towards Debiased Source-Free Domain Adaptation