arXiv 2610.29989 · cs.CV · 2026-10-21
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Ruopeng Gao, Yukun Huang, Jiarui Hu, Shuai Wang, Wenbo Hu, Ying Shan, Limin Wang
ARC Lab, Tencent
在最新榜 #33 本站收录于 2026-10-23
一句话要点
腾讯 ARC 实验室提出“未来片段预测”（FCP）辅助目标：自回归视频扩散训练时额外预测隔开若干片段的未来画面，迫使模型学习场景如何演变；物理合理性更好、训练总算力更低，推理流程不变。
Tencent ARC Lab adds Future Chunk Prediction (FCP), an auxiliary objective that predicts temporally separated chunks during teacher-forced autoregressive video diffusion training, improving physical plausibility at lower training compute with inference unchanged.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉生成
- StreamEval: Evaluating Interactive Streaming Video Generation Models ▲649
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models ▲325
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation ▲200
同主题：高效训练与推理
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching 2026-10-15 · ▲556
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation 2026-09-29 · ▲511
- VideoJev: System One Model for Video Understanding and Interaction 2026-10-13 · ▲375
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- LEV: Thinking Fast and Deep with Looped Decision Models 2026-10-14 · ▲337
同机构：ARC Lab
- Player-1: Learning to Play from Synthetic Experience 2026-10-14
- Multics: Generative Multi-Player World Model with Hierarchical Communication 2026-10-12
- WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory 2026-09-21
- GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation 2026-09-21
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。