arXiv:2606. 10135v1 Announce Type: cross Abstract: Transitioning bidirectional video diffusion models into an autoregressive paradigm improves the interactivity of video world models, but existing causal pipelines need many stages (control fine-tuning, autoregressive training, causal initialization, few-step distillation) and still trail bidirectional models in quality due to error accumulation.
By Shaohao Rui, Xiaofeng Mao, Zhanyu Zhang, Peijia Lin, Yansong Zhu, Yibo Zhang, Haibin Wan, Weijie Ma
The paper introduces a large‑scale synthetic data pipeline built on Unreal Engine to generate action‑conditioned, multi‑view video for training world models. The system operates in two stages: real‑time physics simulation records trajectories, then offline rendering produces high‑quality video. It includes a distributed production framework with task partitioning, automated filtering, and a 25‑server cluster, yielding over 2,600 hours of 1080p and 6,000 hours of 720p video from 429 levels and 40 characters.
By Haoyu Wang, Songchun Zhang, Haoran Li, Haoyang Huang, Zeyue Xue, Nan Duan
ForeTime‑VLA is a causal vision‑language‑action policy that distills future‑aware representations from a frozen Fast‑WAM teacher, enabling it to anticipate contact events during conveyor‑belt manipulation. The method compresses current and future video latents into a 64‑dimensional target, uses an eight‑frame history encoder to predict this target along with manipulation phase and time‑to‑transition, and conditions a VLM prefix on future tokens and phase. On a deduplicated conveyor‑belt dataset, ForeTime‑VLA reduces test MAE by 2.63% and L2 by 3.02%, while real‑robot experiments show significantly higher grasp success rates compared to the next‑best reference.
whyItMatters":"The approach demonstrates that distilling future‑token knowledge from a world‑action model can improve dynamic manipulation performance without the computational cost of running the teacher at inference time."
By Siyuan Ma, Yutian Zhang, Boshi Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Xiaojin Huang
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
By Chenxi Song, Yanming Yang, Chi Zhang
arXiv:2608. 14498v1 Announce Type: new Abstract: Vision-language models (VLMs) enable embodied agents to reason and act from visual observations and language instructions.
By Hanfeng Lu, Tianyu Feng, Suyi Li, Yuheng Zhao, Wei Gao, Shaopan Xiong, Ju Huang, Siran Yang, Jiamang Wang, Lin Qu, Wei Wang
arXiv:2605.30263v2 Announce Type: replace
Abstract: Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time intera...
By Min Zhao, Hongzhou Zhu, Bokai Yan, Zihan Zhou, Yimin Chen, Honglie Wang, Wenqiang Sun, Zhengwei Fang, Zizheng Xun, Zihao Li, Kaiwen Zheng, Guande He, Xiao Yang, Chongxuan Li, Fan Bao, Jun Zhu