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.
Continuous Speculative Decoding for Autoregressive Image Generation
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统实验室）；JD.COM Inc（京东集团股份有限公司）；China Tower Corporation Limited（中国铁塔股份有限公司）
SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation
The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Peking University（北京大学）；xAI；Tsinghua University（清华大学）；Shanghai Jiao Tong University（上海交通大学）
CSD: Content-aware Speculative Decoding for Efficient Image Generation
East China Normal University（东华大学）；Huawei Foundation（华为基金会）；Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE（统计与数据科学高级理论与应用关键实验室-教育部）
Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion
Stanford University（斯坦福大学）；Massachusetts Institute of Technology（麻省理工学院）；Peking University（北京大学）；University of California, Berkeley（加州大学伯克利分校）；ByteDance（字节跳动）
Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models
College of Software Engineering, Southeast University（东南大学软件工程学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Cyber Science and Engineering, Southeast University（东南大学网络空间安全学院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算机与信息系统学院）
Glance Forcing: Making Bidirectional Diffusion Autoregressive at a Glance
Wuhan University（武汉大学）；University of Electronic Science and Technology of China（电子科技大学）；Sun Yat-sen University（中山大学）；University of Washington（华盛顿大学）；National University of Singapore（新加坡国立大学）；Central South University（中南大学）
In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion
School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；Tencent Youtu Lab（腾讯云图实验室）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation
Southeast University, Nanjing, China（东南大学）；Nanyang Technological University, Singapore（南洋理工大学）；A STAR Centre for Frontier AI Research (CFAR), Singapore（A STAR前沿人工智能研究中心）
FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
South China University of Technology（南方科技大学）；Tsinghua University（清华大学）；Zhejiang University（浙江大学）；Tencent VISVISE（腾讯VISVISE）；Peking University（北京大学）；Singapore Management University（新加坡国立大学）
Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（东南大学新一代人工智能技术及交叉应用重点实验室（教育部））；New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA)（模式识别新实验室（NLPR），多模态人工智能系统国家重点实验室（MAIS），中国科学院自动化研究所（CASIA））；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Computing and Information Systems, Singapore Management University（新加坡国立大学计算机与信息学院）
