Hehai Lin
2 papers · Latest:
Computer Vision
PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning
PRISM introduces a black-box on-policy distillation stage to align large multimodal models, mitigating distributional drift between SFT and RLVR for improved performance.
2604.28123
Human-Computer InteractionCoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through Comments
CoNewsReader uses comments and AI to enhance critical news reading and understanding on social media.
2604.27905
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.