SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Paper • 2609.20519 • Published 8 days ago • 130
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models Paper • 2608.16887 • Published Aug 17 • 36
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators Paper • 2607.15273 • Published Jul 16 • 13
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 77
Multiplayer Interactive World Models with Representation Autoencoders Paper • 2607.05352 • Published Jul 6 • 27
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space Paper • 2607.05373 • Published Jul 6 • 42
Representation Distribution Matching for One-Step Visual Generation Paper • 2607.02375 • Published Jul 2 • 11
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Paper • 2607.02517 • Published Jul 2 • 31
OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation Paper • 2606.17628 • Published Jun 16 • 30
Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation Paper • 2606.04527 • Published Jun 3 • 29
minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models Paper • 2605.30263 • Published May 28 • 58
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published May 28 • 145
Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving Paper • 2605.23163 • Published May 25 • 17