SpecBlock: Block-Iterative Speculative Decoding with Dynamic Tree Drafting Paper • 2605.07243 • Published 5 days ago • 3
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts Paper • 2602.03473 • Published 5 days ago • 11
MDN: Parallelizing Stepwise Momentum for Delta Linear Attention Paper • 2605.05838 • Published 6 days ago • 4
MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference Paper • 2605.07363 • Published 5 days ago • 12
LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Paper • 2605.08083 • Published 5 days ago • 59
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Paper • 2604.27393 • Published 13 days ago • 64
AI Co-Mathematician: Accelerating Mathematicians with Agentic AI Paper • 2605.06651 • Published 6 days ago • 13
SkillOS: Learning Skill Curation for Self-Evolving Agents Paper • 2605.06614 • Published 6 days ago • 38
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Paper • 2605.06130 • Published 6 days ago • 92
MiA-Signature: Approximating Global Activation for Long-Context Understanding Paper • 2605.06416 • Published 6 days ago • 53
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation Paper • 2605.04128 • Published 8 days ago • 16
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published 13 days ago • 71
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents Paper • 2605.05185 • Published 7 days ago • 96
Stream-T1: Test-Time Scaling for Streaming Video Generation Paper • 2605.04461 • Published 7 days ago • 102
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces Paper • 2605.02801 • Published 9 days ago • 7