WorldKV: Efficient World Memory with World Retrieval and Compression Paper • 2605.22718 • Published 1 day ago • 26
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 9 days ago • 96
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking Paper • 2605.12587 • Published 10 days ago • 37
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models Paper • 2603.23499 • Published Mar 24 • 51
Grounding World Simulation Models in a Real-World Metropolis Paper • 2603.15583 • Published Mar 16 • 154
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation Paper • 2510.23581 • Published Oct 27, 2025 • 42
Visual Representation Alignment for Multimodal Large Language Models Paper • 2509.07979 • Published Sep 9, 2025 • 84
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs Paper • 2506.09522 • Published Jun 11, 2025 • 21