Datasets and trained checkpoints of Composition-RL
xuxin
xx18
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Progressive Residual Warmup for Language Model Pretraining authored
a paper
3 days ago
Progressive Residual Warmup for Language Model Pretraining authored
a paper
27 days ago
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models Organizations
models 23
xx18/Baseline-4B-MATH12K
Updated
• 6
xx18/Composition-RL-30B-A3B
Updated
• 2
xx18/Composition-RL-4B-Physics_Math
Updated
• 5
xx18/Composition-RL-4B-Depth1_2_3
Updated
• 4
xx18/Composition-RL-4B-Depth1_2
Updated
• 3
xx18/Composition-RL-4B
Updated
• 5
xx18/Composition-RL-14B
Updated
• 7
xx18/Composition-RL-8B
Updated
• 4
xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3
Text Generation • 4B • Updated
• 11
xx18/DirectRL_Qwen3-4B_baseline2
Text Generation • 4B • Updated
• 7
datasets 6
xx18/MATH-Composition-Depth3
Viewer
• Updated
• 132k • 10
xx18/Physics-MATH-Composition-141K
Viewer
• Updated
• 141k • 9
xx18/MATH-Composition-199K
Viewer
• Updated
• 199k • 18
xx18/Composition-RL-EVA
Viewer
• Updated
• 12.8k • 11
xx18/TFPI-EVA
Preview
• Updated
• 50
xx18/R2PE
Viewer
• Updated
• 38.7k • 16 • 2