Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation Paper • 2508.20470 • Published 9 days ago • 64
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation Paper • 2503.06053 • Published Mar 8 • 138
From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation up to 100K Tokens Paper • 2502.18890 • Published Feb 26 • 30
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding Paper • 2503.12797 • Published Mar 17 • 32
UniF^2ace: Fine-grained Face Understanding and Generation with Unified Multimodal Models Paper • 2503.08120 • Published Mar 11 • 32
CoRe^2: Collect, Reflect and Refine to Generate Better and Faster Paper • 2503.09662 • Published Mar 12 • 34
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs Paper • 2503.01307 • Published Mar 3 • 39