Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 30 days ago • 247
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 11 days ago • 205
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 10 days ago • 136
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Paper • 2606.08063 • Published 21 days ago • 79
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Paper • 2606.12087 • Published 17 days ago • 75
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks Paper • 2606.12344 • Published 17 days ago • 68
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 24 days ago • 125
AlphaTransit: Learning to Design City-scale Transit Routes Paper • 2605.28730 • Published about 1 month ago • 7
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs Paper • 2605.25188 • Published May 24 • 16
PANDO: Efficient Multimodal AI Agents via Online Skill Distillation Paper • 2605.24785 • Published May 26 • 11
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published about 1 month ago • 431