Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty? Paper • 2605.12684 • Published 3 days ago • 2
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation Paper • 2605.12925 • Published 1 day ago • 2
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning Paper • 2605.13037 • Published 1 day ago • 3
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 1 day ago • 69
VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors Paper • 2605.11424 • Published 3 days ago • 3
From Web to Pixels: Bringing Agentic Search into Visual Perception Paper • 2605.12497 • Published 3 days ago • 10
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation Paper • 2605.12305 • Published 3 days ago • 2
δ-mem: Efficient Online Memory for Large Language Models Paper • 2605.12357 • Published 3 days ago • 97
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models Paper • 2605.08735 • Published 6 days ago • 63
SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning Paper • 2605.09423 • Published 5 days ago • 1
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation Paper • 2605.10813 • Published 4 days ago • 9
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace Paper • 2605.10913 • Published 4 days ago • 1
HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper • 2605.06747 • Published 8 days ago • 49
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search Paper • 2605.07510 • Published 7 days ago • 5
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation Paper • 2605.08029 • Published 7 days ago • 10
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling Paper • 2605.05922 • Published 8 days ago • 4