When Can LLMs Learn to Reason with Weak Supervision?
Paper • 2604.18574 • Published • 25
Pavel Izmailov
pavelizmailov
AI & ML interests
LLMs, Reasoning, Reinforcement Learning, AI for Science, AI for Math, Alignment, World Models
Recent Activity
authored a paper about 1 month ago
FlexiViT: One Model for All Patch Sizes authored a paper about 1 month ago
Does Knowledge Distillation Really Work? authored a paper about 1 month ago
OpenAI o1 System CardOrganizations
upvoted a paper about 1 month ago