Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention Paper • 2510.13940 • Published Oct 15 • 6
PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning Paper • 2510.13809 • Published Oct 15 • 37
Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization Paper • 2508.14811 • Published Aug 20 • 42
FlexPainter: Flexible and Multi-View Consistent Texture Generation Paper • 2506.02620 • Published Jun 3 • 14
RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification Paper • 2503.02537 • Published Mar 4 • 12