From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space
Paper • 2604.14142 • Published • 27
TanYuQiao
Trae1ounG
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
Seedance 2.0: Advancing Video Generation for World Complexity upvoted a paper 5 days ago
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space submitted a paper 5 days ago
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train SpaceOrganizations
None yet
submitted a
paper to Daily Papers 5 days ago
authored 3
papers 4 months ago
Better wit than wealth: Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
Paper • 2503.23895 • Published • 1
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Paper • 2512.19673 • Published • 66
Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
Paper • 2505.14436 • Published