Temporal Consistency in Video Generation

Follow this topic Ask about this topic

Momentum

30 papers in the last four weeks, up 275% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 224

All topics

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
Mar 18, 2026Xi Ye, Wenjia Yang, Yangyang Xu +4Diffusion Model Alignment Video Diffusion Models
Tsinghua University · Ant Group · University of Chinese Academy of Sciences
UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
Feb 26, 2026Tianxing Xu, Zixuan Wang, Guangyuan Wang +5Camera-Controlled Video Generation Video Diffusion Models
Tsinghua University China · Tongyi Lab, Alibaba China · University of Science and Technology of China China
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Feb 8, 2026Haodong Li, Shaoteng Liu, Zhe Lin +1Autoregressive Diffusion Long-Horizon Video Generation
UC San Diego · Adobe Research
Motion Attribution for Video Generation
Jan 13, 2026Xindi Wu, Despoina Paschalidou, Jun Gao +5Gradient-Based Attribution Feature Attribution
NVIDIA · Princeton University · University of Michigan +3
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
Dec 17, 2025Yuwei Guo, Ceyuan Yang, Hao He +5Video Diffusion Models Autoregressive Diffusion
The Chinese University of Hong Kong, Hong Kong, China · ByteDance Seed, China · ByteDance, China
Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation
Dec 4, 2025Yanran Zhang, Ziyi Wang, Wenzhao Zheng +3Video Diffusion Models 3D Scene Generation
Department of Automation, Tsinghua University, China · GigaAI
BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation
Nov 28, 2025Zeyu Zhang, Jinyuan Mao, Shuning Chang +5Long-Horizon Video Generation Autoregressive Video Generation
DAMO Academy, Alibaba Group · Zhejiang University · Hupan Lab
Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising
Nov 5, 2025Shuangquan Lyu, Jian Mao, Yue MaVideo Diffusion Models Long Video Generation
Carnegie Mellon University · Jilin University · Tsinghua University
VRWKV-Editor: Reducing quadratic complexity in transformer-based video editing
Sep 30, 2025Abdelilah Aitrouga, Youssef Hmamouche, Amal El Fallah SeghrouchniVideo Diffusion Models Video Editing
International Artificial Intelligence Center of Morocco University Mohammed VI Polytechnic Rabat, Morocco · Sorbonne University, LIP6 - UMR 7606 CNRS, France
Vivid-VR: Distilling Concepts from Text-to-Video Diffusion Transformer for Photorealistic Video Restoration
Aug 20, 2025Haoran Bai, Xiaoxu Chen, Canqian Yang +3Video Diffusion Models Diffusion Transformer
Alibaba Group - Taobao & Tmall Group
S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
Aug 11, 2025Peng Dai, Feitong Tan, Qiangeng Xu +6Multi-View Video Generation Image Inpainting
Department of Electrical and Electronic Engineering at The University of Hong Kong, Hong Kong.
MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
Jun 1, 2025Tong Zhang, Victor Escorcia, Juan C Leon Alcazar +1Diffusion Model Guidance Video Editing
Department of Computer Science King Abdullah University of Science and Technology Thuwal, Saudi Arabia · Independent Researcher
Auto-Regressive Models Need Structural Registers: Semantic Foresight Improves Coherent Driving Video Continuation
Dec 4, 2024Ruibo Ming, Jingwei Wu, Zhewei Huang +4Video Prediction Autoregressive Video Generation
Tsinghua University · Megvii Technology · University of the Chinese Academy of Sciences +2
AnyView: Synthesizing Any Novel View in Dynamic Scenes
Date pendingBasile Van Hoorick, Dian Chen, Shun Iwase +7Multi-View Consistency Camera-Conditioned Video Generation
Toyota Research Institute, CA, USA · Amazon Web Services, CA, USA

Mar 18, 2026, cs.CVJ/K move · Enter open · S save

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning

Xi Ye, Wenjia Yang, Yangyang Xu, Xiaoyang Liu+3

Tsinghua University · Ant Group · University of Chinese Academy of Sciences

Diffusion Model Alignment Video Diffusion Models Diffusion Model Fine-Tuning RL for Diffusion Models Diffusion Models for Motion Generation Temporal Consistency in Video Generation

Open paper AskPDF arXiv

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 temporal coherence, especially after fine-tuning. We study motion alignment in video diffusion models post-training. To address this, we introduce pixel-motion rewards based on pixel flux dynamics, capturing both instantaneous and long-term motion consistency. We further propose \underline{S}mooth \underline{H}ybr\underline{i}d \underline{F}ine-\underline{t}uning (SHIFT), a scalable reward-driven framework that unifies supervised fine-tuning and advantage-weighted fine-tuning. Benefiting from novel adversarial advantages, SHIFT improves convergence speed and mitigates reward hacking. Experiments show that our approach efficiently resolves dynamic-degree collapse in modern video diffusion models supervised fine-tuning. Project page: https://xiye20.github.io/projects/SHIFT/.

Momentum

Related topics

Latest papers 224