E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models Paper • 2609.37533 • Published 5 days ago • 57
Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding Paper • 2609.32019 • Published 9 days ago • 41
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 10 days ago • 101
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus Paper • 2609.15504 • Published 20 days ago • 37
The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning Paper • 2608.14229 • Published Aug 14 • 17
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution Paper • 2608.08311 • Published Aug 8 • 95
Running on Zero Agents Featured 46 CADENA Stepwise CAD 📐 46 Turn a 3D mesh into a parametric CadQuery program
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models Paper • 2606.19297 • Published Jun 17 • 78
Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages Paper • 2606.20517 • Published Jun 18 • 61
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering Paper • 2606.00683 • Published May 30 • 102