Yijun Yang

9

Papers

154

Total Citations

Papers (9)

MMA-Diffusion: MultiModal Attack on Diffusion Models

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Detect Any Mirrors: Boosting Learning Reliability on Large-Scale Unlabeled Data with an Iterative Data Engine

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning

Medical World Model

GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing