FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing Paper • 2604.22586 • Published 13 days ago • 16
Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets Paper • 2604.22294 • Published 13 days ago • 16
LLM Safety From Within: Detecting Harmful Content with Internal Representations Paper • 2604.18519 • Published 17 days ago • 24
DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction Paper • 2604.21518 • Published 14 days ago • 28
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond Paper • 2604.22748 • Published 13 days ago • 223
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models Paper • 2603.22003 • Published Mar 23 • 12