Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 142
Yunxiao Shi
Yunxiao
·
AI & ML interests
Recommender System, Information Retrieval, LLM Agent
Recent Activity
authored a paper 3 days ago
PersonaX: A Recommendation Agent Oriented User Modeling Framework for Long Behavior Sequence authored a paper 3 days ago
MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models authored a paper 4 days ago
iAgent: LLM Agent as a Shield between User and Recommender SystemsOrganizations
upvoted 2
papers about 1 year ago