Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models Paper • 2605.28132 • Published 12 days ago • 25
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published 27 days ago • 195
xummer/llama3-1-8b-gsm8k-dualAdd-setupB-tn2000-lora-zh Text Generation • Updated 20 days ago • 22 • 1
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex Paper • 2605.06139 • Published May 7 • 69
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published May 3 • 166
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 327