Efficient Video Generation

Latest papers

25 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Speculative Forcing for Efficient Autoregressive Video Generation
Oct 15, 2026Hyunwook Choi, Seungryong Kim, Dongyoon Han +1Efficient Video Generation Autoregressive Video Generation
KAIST AI · NAVER AI Lab
PreCoG: Preview-Edit for Efficient Video Correction in Generation-Time
Oct 9, 2026Yilai Liu, Wenqi Pei, Zhifeng Lu +3Efficient Video Generation T2V Generation
NICE Lab, The University of Hong Kong · Beijing University of Posts and Telecommunications
Real-Time Joint Audio-Video Generation by Parallel Adapter Composition
Oct 7, 2026Jingyu Li, Xiaoxiao Xiang, Yiwen GuoAudio-Video Generation Real-Time Interactive Video Generation
LIGHTSPEED · Independent Researcher
SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video
Sep 29, 2026Haozhe Liu, Tian Ye, Shuchen Xue +9Diffusion Model Acceleration Video Super-Resolution
NVIDIA
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
Jul 23, 2026Junsong Chen, Jincheng Yu, Yitong Li +11Video Diffusion Models Attention Residual Connections
NVIDIA
MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation
Jul 16, 2026Yinhan Zhang, Dinwei Tan, Xianghao Kong +3Video Diffusion Models Diffusion Model Fine-Tuning
HKUST · Tencent · HKUST(GZ)
ACID: Adaptive Caching for vIDeo generation
Jul 14, 2026Om Agrawal, Saurabh Agarwal, Aditya AkellaVideo Diffusion Models Diffusion Model Caching
UT Austin
Vidu S1: A Real-Time Interactive Video Generation Model
Jul 3, 2026Jintao Zhang, Kai Jiang, Jintao Chen +24Streaming Video Generation Real-Time Interactive Video Generation
Tsinghua University, Shengshu Technology · Shengshu Technology
EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
Jun 29, 2026Jiayu Chen, Hengyi Zhang, Maoliang Li +5Video Diffusion Models Edge Computing
School of Computer Science, Peking University, China · International School, Beijing University of Posts and Telecommunications, China · School of Information Science and Technology, Beijing Forestry University, China +1
Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation
Jun 21, 2026Yitong Li, Junsong Chen, Haopeng Li +6Quantization Diffusion Model Inference Acceleration
NVIDIA Research, Efficient AI Team & Singapore Lab.
Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation
Jun 3, 2026Yuxuan Bian, Zeyue Xue, Songchun Zhang +9Long Video Generation Memory-Augmented Video Generation
1The Chinese University of Hong Kong · 2Joy Future Academy, JD · 3The Hong Kong University of Science and Technology +4
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
May 29, 2026Jiazheng Xing, Hangjie Yuan, Lingling Cai +9Video Generation Efficient Video Generation
Zhejiang University · National University of Singapore · DAMO Academy, Alibaba Group +4
PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution
May 25, 2026Wenxue Li, Jingjing Ren, Peng Zhang +6Video Generation High-Resolution Video Generation
The Hong Kong University of Science and Technology (Guangzhou) · MiLM Plus, Xiaomi Inc · The Hong Kong University of Science and Technology
Dynamic Video Generation: Shaping Video Generation Across Time and Space
May 20, 2026Shikang Zheng, Jingkai Huang, Jiacheng Liu +5Video Diffusion Models Diffusion Model Inference Acceleration
Shanghai Jiao Tong University · South China University of Technology · Tsinghua University
SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation
May 7, 2026YaoYang Liu, Yuechen Zhang, Wenbo Li +3Image-to-Video Generation Video Generation
HKUST · CUHK · Joy Future Academy +2
Motion-Aware Caching for Efficient Autoregressive Video Generation
May 3, 2026Jing Xu, Yuexiao Ma, Xuzhe Zheng +7Video Diffusion Models KV-Cache Management
1Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China · 2ByteDance · 3Max Planck Institute for Intelligent Systems, 4ELLIS Institute Tbingen, 5Tbingen AI Center
Alice v1: Distillation-Enhanced Video Generation Surpassing Closed-Source Models
Apr 27, 2026Wang Xiaoyu, Phong Nguyen, Chen ZhaoVideo Diffusion Models Diffusion Model Distillation
Mirage Team Open Source Research
Motif-Video 2B: Technical Report
Apr 14, 2026Junghwan Lim, Wai Ting Cheung, Minsu Ha +25T2V Generation Video Foundation Models
Motif Technologies
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
Mar 30, 2026Muyang He, Hanzhong Guo, Junxiong Lin +1Video Generation Efficient Video Generation
School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China · Hong Kong Generative AI Research and Development Center, Hong Kong SAR, China
FlashSign: Pose-Free Guidance for Efficient Sign Language Video Generation
Mar 30, 2026Liuzhou Zhang, Zeyu Zhang, Biao Wu +10Efficient Video Generation Sign Language Generation
HUST · GigaAI · UTS +7
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Mar 19, 2026Jiayi Luo, Jiayu Chen, Jiankun Wang +6Efficient Video Generation Video Generation
SKLCCSE, School of Computer Science and Engineering, Beihang University · Zhongguancun Academy · School of Computer Science, Peking University +4
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
Mar 10, 2026Minh Khoa Le, Kien Do, Duc Thanh Nguyen +1Efficient Video Generation Video Diffusion Models
Applied Artificial Intelligence Initiative, Deakin University, Australia · FPT Smart Cloud, Vietnam · Deakin University, Australia
Helios: Real Real-Time Long Video Generation Model
Mar 4, 2026Shenghai Yuan, Yuanyang Yin, Zongjian Li +3Efficient Video Generation Long-Horizon Video Generation
Peking University · ByteDance China · Chengdu Anu Intelligence +1
PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
Mar 1, 2026Jiangshan Wang, Kang Zhao, Jiayi Guo +5Efficient Video Generation Diffusion Model Inference Acceleration
MMLab, CUHK · Tsinghua University · Tongyi Lab, Alibaba
CHAI: CacHe Attention Inference for text2video
Feb 18, 2026Joel Mathew Cherian, Ashutosh Muralidhara Bharadwaj, Vima Gupta +1T2V Generation Efficient Video Generation
Georgia Institute of Technology.

Oct 15, 2026J/K move · Enter open · S save

Speculative Forcing for Efficient Autoregressive Video Generation

Hyunwook Choi, Seungryong Kim, Dongyoon Han, Sangdoo Yun

KAIST AI · NAVER AI Lab

Efficient Video Generation Autoregressive Video Generation Streaming Video Generation Speculative Decoding Few-Step Diffusion Sampling Long Video Generation

Open paper AskPDF arXiv

Few-step autoregressive video generators enable streaming generation, yet they run every token through the final denoising step, regardless of how much refinement it needs. We find this uniform computation is often unnecessary: many tokens already closely match their eventual full-step outputs in the initial steps, while others require refinement until the end. We introduce Speculative Forcing, a framework that treats intermediate clean estimates as drafts and predicts when individual tokens can be safely accepted early. Once accepted, a token is frozen as its final output and undergoes no further denoising, while its cached keys and values remain available as context for the remaining tokens. We explore two alternative verifier designs: a training-free one based on similarity to clean content and stability across steps, and a learned one that reads the frozen generator's intermediate features to estimate each token's remaining gap to its full-step output. Across short-video, long-video, and world generation, Speculative Forcing preserves the quality of full-step sampling while substantially reducing computation. On LongLive, it matches the four-step generator with ~1.7 denoising steps per token, running over 1.5x faster at 41.7 and 37.8 fps. On Lingbot-World 2.0, where camera motion continually changes the visible content, it maintains quality with ~2.5 denoising steps per token and runs 1.35x faster at 24.5 fps.