17 papers · 1 filter
Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction
Yangyang Xu, Haobo Yuan, Yuzhu Wang +4
Vision foundation backbones provide strong representations for dense prediction, yet a single shared feature still needs to support tasks with different, image-dependent adaptation…
Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
Min Zhao, Hongzhou Zhu, Kaiwen Zheng +6
Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong r…
-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
Yuzhu Wang, Xi Ye, Duo Su +2
Training-free camera control for pretrained flow-matching video generators is a partial-observation inverse problem: a depth-warped guidance video supplies noisy evidence on a subs…
L2P: Unlocking Latent Potential for Pixel Generation
Zhennan Chen, Junwei Zhu, Xu Chen +7
Pixel diffusion models have recently regained attention for visual generation. However, training advanced pixel-space models from scratch demands prohibitive computational and data…
SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Xi Ye, Wenjia Yang, Yangyang Xu +4
Image-conditioned video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term tempo…
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Chendong Xiang, Jiajun Liu, Jintao Zhang +7
Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial pers…