The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Paper • 2609.18063 • Published Sep 16 • 34
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published Aug 17 • 112
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents Paper • 2610.22732 • Published 19 days ago • 9
On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models Paper • 2610.32770 • Published 11 days ago • 49
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction Paper • 2610.22543 • Published 8 days ago • 55
Zep: A Temporal Knowledge Graph Architecture for Agent Memory Paper • 2501.13956 • Published Jan 20, 2025 • 18
Towards Looped Models Done Right, Part II: Rethinking at Fixed Points Paper • 2610.06833 • Published 29 days ago • 31
Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design Paper • 2610.23036 • Published 18 days ago • 21
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 21 days ago • 107
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models Paper • 2610.12572 • Published 26 days ago • 105
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 20 days ago • 68
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? Paper • 2610.28763 • Published 14 days ago • 28
RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement Paper • 2609.39045 • Published Sep 30 • 48
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published Oct 1 • 78
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 159
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 94