Yu Meng's Lab

meng-lab's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

weizhepei 

submitted a paper to Daily Papers 3 days ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

Paper • 2605.21468 • Published 4 days ago • 44

weizhepei 

updated a model 12 days ago

meng-lab/MATH-Qwen3-8B-Base-GRPO-Serval

Updated 12 days ago

weizhepei 

published a model 12 days ago

meng-lab/MATH-OLMo-3-1025-7B-GRPO-Serval-15K

Updated 12 days ago

weizhepei 

published a model 16 days ago

meng-lab/MATH-OLMo-3-1025-7B-GRPO-Serval

Updated 16 days ago

TianHongZXY 

updated a model 17 days ago

meng-lab/MATH-Qwen3-8B-Base-GRPO-Serval

Updated 12 days ago

TianHongZXY 

published a model 27 days ago

meng-lab/MATH-Qwen3-8B-Base-GRPO-Serval

Updated 12 days ago

TianHongZXY 

authored a paper 3 months ago

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

Paper • 2603.00889 • Published Mar 1 • 55

TianHongZXY 

submitted a paper to Daily Papers 3 months ago

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

Paper • 2603.00889 • Published Mar 1 • 55

TianHongZXY 

authored a paper 8 months ago

RAST: Reasoning Activation in LLMs via Small-model Transfer

Paper • 2506.15710 • Published May 30, 2025

wlchen 

authored a paper 12 months ago

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Paper • 2506.01347 • Published Jun 2, 2025 • 3

TianHongZXY 

authored a paper 12 months ago

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Paper • 2506.01347 • Published Jun 2, 2025 • 3

weizhepei 

updated a collection 12 months ago

AdaDecode

Collection

[ICML 2025] AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism. • 18 items • Updated Jun 4, 2025 • 3