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 18 days ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories upvoted a paper 22 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 • 2
TianHongZXY/Qwen2.5-Math-7B-GRPO
8B • Updated • 12
TianHongZXY/OpenR1-Math-46k-8192-Qwen2.5-7B-Instruct-GRPO-clip_0.28
Updated
TianHongZXY/Qwen2.5-Math-7B-W-REINFORCE
8B • Updated • 18 • 1
TianHongZXY/Qwen3-4B-GRPO
4B • Updated • 1
TianHongZXY/Qwen3-4B-PPO
4B • Updated • 2
TianHongZXY/Qwen3-4B-PSR
4B • Updated • 2 • 1
TianHongZXY/Qwen2.5-Math-7B-PPO
8B • Updated • 2
datasets 6
TianHongZXY/CHIMERA
Viewer • Updated • 9.23k • 424 • 21
TianHongZXY/aime-1983-2025
Viewer • Updated • 963 • 414
TianHongZXY/AIME2025
Viewer • Updated • 30 • 174 • 1
TianHongZXY/AIME2024
Viewer • Updated • 30 • 136
TianHongZXY/amc23
Viewer • Updated • 40 • 175
TianHongZXY/MATH
Viewer • Updated • 12.5k • 746 • 3