Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 27 days ago • 247
Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models Paper • 2605.28132 • Published 28 days ago • 25
Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective Paper • 2605.27476 • Published 29 days ago • 20
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use Paper • 2605.14038 • Published May 13 • 15
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools Paper • 2605.20682 • Published May 20 • 85
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published May 13 • 274
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion Paper • 2605.01466 • Published May 2 • 6