Softpick: No Attention Sink, No Massive Activations with Rectified Softmax Paper • 2504.20966 • Published 8 days ago • 25
100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models Paper • 2505.00551 • Published 7 days ago • 29
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce Paper • 2504.11343 • Published 22 days ago • 16
DataDecide: How to Predict Best Pretraining Data with Small Experiments Paper • 2504.11393 • Published 22 days ago • 17
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations Paper • 2504.10481 • Published 23 days ago • 84
VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks Paper • 2504.05118 • Published about 1 month ago • 25
GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning Paper • 2504.00891 • Published Apr 1 • 13