RELIC: Interactive Video World Model with Long-Horizon Memory
Yicong Hong, Yiqun Mei, Chongjian Ge, Yiran Xu, Yang Zhou, Sai Bi, Yannick Hold-Geoffroy, Mike Roberts, Matthew Fisher, Eli Shechtman, Kalyan Sunkavalli, Feng L… 展开作者
Yicong Hong, Yiqun Mei, Chongjian Ge, Yiran Xu, Yang Zhou, Sai Bi, Yannick Hold-Geoffroy, Mike Roberts, Matthew Fisher, Eli Shechtman, Kalyan Sunkavalli, Feng Liu, Zhengqi Li, Hao Tan
A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approaches address only one of these aspects in isolation, as achieving all three simultaneously is highly challenging-for example, long-term memory mechanisms often degrade real-time performance. In this work, we present RELIC, a unified framework that tackles these three challenges altogether. Given a single image and a text description, RELIC enables memory-aware, long-duration exploration of arbitrary scenes in real time. Built upon recent autoregressive video-diffusion distillation techniques, our model represents long-horizon memory using highly compressed historical latent tokens encoded with both relative actions and absolute camera poses within the KV cache. This compact, camera-aware memory structure supports implicit 3D-consistent content retrieval and enforces long-term coherence with minimal computational overhead. In parallel, we fine-tune a bidirectional teacher video model to generate sequences beyond its original 5-second training horizon, and transform it into a causal student generator using a new memory-efficient self-forcing paradigm that enables full-context distillation over long-duration teacher as well as long student self-rollouts. Implemented as a 14B-parameter model and trained on a curated Unreal Engine-rendered dataset, RELIC achieves real-time generation at 16 FPS while demonstrating more accurate action following, more stable long-horizon streaming, and more robust spatial-memory retrieval compared with prior work. These capabilities establish RELIC as a strong foundation for the next generation of interactive world modeling.
MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；vivo BlueImage Lab, vivo Mobile Communication Co., Ltd.（vivo蓝影实验室，vivo移动通信有限公司）；National University of Singapore（新加坡国立大学）
LIVE: Long-horizon Interactive Video World Modeling
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Loop Area Institute（深圳河套学院）；Microsoft Research（微软研究院）；The University of Hong Kong（香港大学）；Voyager Research, Didi Chuxing Project（Voyager研究，滴滴出行项目）
MRIFE: A Mask-Recovering and Interactive-Feature-Enhancing Semantic Segmentation Network For Relic Landslide Detection
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）；China Aero Geophysical Survey and Remote Sensing Center for Natural Resources（中国自然资源航空物探遥感中心）；La Trobe University（拉筹伯大学）
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding
The Hong Kong University of Science and Technology（香港科技大学）；Xiaohongshu Inc.（小红书公司）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）
LaGen: Towards Autoregressive LiDAR Scene Generation
University of Science and Technology of China（中国科学技术大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Jiao Tong University（上海交通大学）；Fudan University（复旦大学）
From Perception to Action: An Interactive Benchmark for Vision Reasoning
Singapore University of Technology（新加坡科技设计大学）；Singapore Management University (SMU), Singapore（新加坡管理学院）；Nanyang Technological University (NTU), Singapore（南洋理工大学）；University of Science（科学大学）
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
Department of Engineering, University of Cambridge, U.K.（剑桥大学工程系）；Peking University（北京大学）；University of Twente（埃因霍温理工大学）；Mechanical Systems Control Laboratory, University of California, Berkeley, USA（加州大学伯克利分校机械系统控制实验室）；ETH Zurich（苏黎世联邦理工学院）；Microsoft（微软公司）；University of Oxford（牛津大学）
