LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training Paper • 2605.29888 • Published 8 days ago • 32
Running 1 The Physical AI Inference Gap in Batch-1 LLM Decode 🪜 1 Interactive companion to the batch-1 LLM decode paper
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published 24 days ago • 195
🧬 Carbon Collection Carbon 500M, 3B, 8B genomic models and GGUF variants for llama.cpp • 7 items • Updated 2 days ago • 43
Stabilizing Efficient Reasoning with Step-Level Advantage Selection Paper • 2604.24003 • Published Apr 27 • 8