Internalizing Discovery Capability into LLM
Young-Jun Lee PRO
passing2961
AI & ML interests
Scientific Discovery, Autoresearch
Recent Activity
upvoted a paper 4 days ago
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics upvoted a paper 6 days ago
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation upvoted a paper 7 days ago
τ^τ-Bench: An Environment for End-To-End, Realistic Agent ConstructionOrganizations
Internalizing Discovery Capability into LLM
A collection of benchmarks for evaluating LMs or VLMs under multi-turn interaction
Skill-of-Mind-Infused LLM
Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge
Multi-modal conversation model & Multi-modal dialogue summarization model
General multi-modal conversation datasets