Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Paper • 2609.08798 • Published • 84
Xinze Liu
Xinze919
·
AI & ML interests
Reinforcement learning; Streaming video understanding; Omni-modal representation across video, audio, image, and text
Recent Activity
upvoted a paper about 16 hours ago
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation authored a paper 9 days ago
AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval upvoted a paper 9 days ago
AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal RetrievalOrganizations
None yet