Changpeng Yang's picture

12

Changpeng Yang

thkelper

·

https://gpt.dance

thkelper

AI & ML interests

Computer Vision, Large Language Model, Multi-omics

Recent Activity

upvoted a paper about 2 hours ago

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

upvoted a paper 7 days ago

Self-Distilled Agentic Reinforcement Learning

upvoted a paper 3 months ago

OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions

View all activity

Organizations

Papers 1

arxiv:2601.22491

models 2

thkelper/Qwen2.5-1.5B-Open-R1-Distill

Updated Feb 25, 2025

thkelper/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Updated Feb 25, 2025

datasets 0

None public yet