The collection for the Paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"
Xinyu Zhu
TianHongZXY
AI & ML interests
Large Language Models; Reasoning; Reinforcement Learning
Recent Activity
liked
a dataset
1 day ago
nvidia/OpenScienceReasoning-2
liked
a model
8 days ago
Qwen/Qwen3-235B-A22B-Thinking-2507
liked
a dataset
12 days ago
nvidia/Nemotron-Post-Training-Dataset-v1
Organizations
models
12
TianHongZXY/Qwen2.5-Math-7B-GRPO
8B
•
Updated
•
8
TianHongZXY/OpenR1-Math-46k-8192-Qwen2.5-Math-7B-RoPE-40K-GRPO-use_guide-clip_ratio_upper_0.28
Updated
TianHongZXY/OpenR1-Math-46k-8192-Qwen2.5-7B-Instruct-GRPO-clip_0.28
Updated
TianHongZXY/OpenR1-Math-46k-8192-Qwen2.5-7B-Instruct-GRPO-gpt-4o-summary_wo_think-clip_0.28
Updated
TianHongZXY/Qwen2.5-Math-7B-W-REINFORCE
8B
•
Updated
•
6
TianHongZXY/Qwen3-4B-NSR
Updated
•
4
TianHongZXY/Qwen3-4B-GRPO
4B
•
Updated
•
4
TianHongZXY/Qwen3-4B-PPO
4B
•
Updated
•
4
TianHongZXY/Qwen3-4B-PSR
4B
•
Updated
•
6
TianHongZXY/Qwen2.5-Math-7B-PPO
8B
•
Updated
•
10
datasets
57
TianHongZXY/synthesize_problems
Viewer
•
Updated
•
6.47k
•
17
TianHongZXY/aime-1983-2025
Viewer
•
Updated
•
963
•
4
TianHongZXY/AIME2025
Viewer
•
Updated
•
30
•
103
•
1
TianHongZXY/AIME2024
Viewer
•
Updated
•
30
•
7
TianHongZXY/amc23
Updated
•
82
TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_1500_to_1600
Viewer
•
Updated
•
100
•
3
TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4900_to_5000
Viewer
•
Updated
•
100
•
2
TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4800_to_4900
Viewer
•
Updated
•
100
•
2
TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4700_to_4800
Viewer
•
Updated
•
100
•
4
TianHongZXY/MATH-test-Tulu-3-8B-SFT-beam_search-completions-temp_0.8-range_4600_to_4700
Viewer
•
Updated
•
100
•
3