LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 13 days ago • 203
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models Paper • 2607.08317 • Published 20 days ago • 35
timaeus/rl-lm-pythia70m-formality-neg-beta0-grpo-nostd-gs4-tp1-tk0-pt80000-steerSWL12c8000sm0.0032-seed1 Updated 22 days ago • 1 • 1
ElizabethMwangi/whisper-large-v3-swahili-nss-afrivoice-cv Automatic Speech Recognition • 2B • Updated Jun 20 • 2 • 1
electricsheepasia/asia-owid-dealt-with-anxiety-depression-took-prescribed-medication Viewer • Updated Jun 3 • 27 • 18 • 1
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196