DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence Paper • 2606.19348 • Published Apr 26 • 9
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Paper • 2606.13473 • Published 22 days ago • 92
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published 22 days ago • 109
Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization Paper • 2606.12373 • Published 23 days ago • 7
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling Paper • 2606.12370 • Published 23 days ago • 21
google/diffusiongemma-26B-A4B-it Image-Text-to-Text • 26B • Updated about 13 hours ago • 1.42M • 1.09k
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding Paper • 2605.29707 • Published May 28 • 152
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Paper • 2605.22791 • Published May 21 • 33