RELIC: Interactive Video World Model with Long-Horizon Memory Paper • 2512.04040 • Published 13 days ago • 23
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance Paper • 2512.08765 • Published 7 days ago • 123
StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation Paper • 2512.09363 • Published 7 days ago • 67
Composing Concepts from Images and Videos via Concept-prompt Binding Paper • 2512.09824 • Published 6 days ago • 27
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs Paper • 2510.11696 • Published Oct 13 • 176
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models Paper • 2510.12784 • Published Oct 14 • 19
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing Paper • 2506.17450 • Published Jun 20 • 64