The collection for the Paper "CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning"
Xinyu Zhu
TianHongZXY
AI & ML interests
Large Language Models; Reasoning; Reinforcement Learning
Recent Activity
authored a paper 15 days ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories upvoted a paper 20 days ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 TrajectoriesOrganizations
models 12
TianHongZXY/CHIMERA-4B-SFT
4B • Updated • 3 • 2
TianHongZXY/CHIMERA-4B-RL
4B • Updated • 4 • 4
TianHongZXY/Qwen3-4B-NSR
4B • Updated • 1
TianHongZXY/Qwen2.5-Math-7B-GRPO
8B • Updated • 11
TianHongZXY/OpenR1-Math-46k-8192-Qwen2.5-7B-Instruct-GRPO-clip_0.28
Updated
TianHongZXY/Qwen2.5-Math-7B-W-REINFORCE
8B • Updated • 17 • 1
TianHongZXY/Qwen3-4B-GRPO
4B • Updated
TianHongZXY/Qwen3-4B-PPO
4B • Updated • 1
TianHongZXY/Qwen3-4B-PSR
4B • Updated • 1 • 1
TianHongZXY/Qwen2.5-Math-7B-PPO
8B • Updated • 1
datasets 6
TianHongZXY/CHIMERA
Viewer • Updated • 9.23k • 432 • 21
TianHongZXY/aime-1983-2025
Viewer • Updated • 963 • 395
TianHongZXY/AIME2025
Viewer • Updated • 30 • 175 • 1
TianHongZXY/AIME2024
Viewer • Updated • 30 • 133
TianHongZXY/amc23
Viewer • Updated • 40 • 176
TianHongZXY/MATH
Viewer • Updated • 12.5k • 1.06k • 3