Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training Paper • 2607.01232 • Published 15 days ago • 6
PoseShield: Neural Collision Fields for Human Self-Collision Resolution Paper • 2606.29686 • Published 18 days ago • 6
electricsheepafrica/africa-owid-expected-years-of-schooling-vs-share-in-extreme-poverty Viewer • Updated Jun 3 • 1.73k • 163 • 1
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published May 28 • 152
SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models Paper • 2605.31597 • Published May 29 • 8
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR Paper • 2605.19282 • Published May 19 • 9
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238