English
Related papers

Related papers: Video2Act: A Dual-System Video Diffusion Policy wi…

200 papers

Vision-Language-Action (VLA) models have recently shown strong potential for robot learning by following language instructions. However, in practice, language alone is often insufficient to precisely convey human intent. It is difficult to…

Recent developments in Video Diffusion Models (VDMs) have demonstrated remarkable capability to generate high-quality video content. Nonetheless, the potential of VDMs for creating transparent videos remains largely uncharted. In this…

Graphics · Computer Science 2025-03-04 Menghao Li , Zhenghao Zhang , Junchao Liao , Long Qin , Weizhi Wang

Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment, and has become essential in mission-critical domains such as supply chains and industrial systems. However,…

Machine Learning · Computer Science 2026-03-11 Hongyu Cao , Jinghan Zhang , Kunpeng Liu , Dongjie Wang , Feng Xia , Haifeng Chen , Xiaohua Hu , Yanjie Fu

Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image-conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Yanqin Jiang , Chaohui Yu , Chenjie Cao , Fan Wang , Weiming Hu , Jin Gao

Due to storage and bandwidth limitations, videos transmitted over the Internet often exhibit low quality, characterized by low-resolution and compression artifacts. Although video super-resolution (VSR) is an efficient video enhancing…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Hongyu An , Xinfeng Zhang , Shijie Zhao , Li Zhang , Ruiqin Xiong

Collaborative driving systems leverage vehicle-to-everything (V2X) communication for multi-agent collaborative perception to enhance driving safety, yet they remain constrained by scarce annotated real-world V2X driving datasets and limited…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yihang Tao , Yu Guo , Senkang Hu , Yanan Ma , Zihan Fang , Sam Kwong , Yuguang Fang

Diffusion models have marked a significant milestone in the enhancement of image and video generation technologies. However, generating videos that precisely retain the shape and location of moving objects such as robots remains a…

Robotics · Computer Science 2024-07-04 Peng Wang , Zhihao Guo , Abdul Latheef Sait , Minh Huy Pham

In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to manipulate a variety of objects in diverse poses. Though prior work has shown benefits of using human videos for policy learning, performance…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Zerui Chen , Shizhe Chen , Etienne Arlaud , Ivan Laptev , Cordelia Schmid

We present a diffusion-based video editing framework, namely DiffusionAtlas, which can achieve both frame consistency and high fidelity in editing video object appearance. Despite the success in image editing, diffusion models still…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Shao-Yu Chang , Hwann-Tzong Chen , Tyng-Luh Liu

In this paper, we build upon two major recent developments in the field, Diffusion Policies for visuomotor manipulation and large pre-trained multimodal foundational models to obtain a robotic skill learning system. The system can obtain…

Vision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. However, existing VLA systems still struggle to generalize across…

Pre-trained perception models excel in generic image domains but degrade significantly in novel environments like indoor scenes. The conventional remedy is fine-tuning on downstream data which incurs catastrophic forgetting of prior…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Tianci Tang , Tielong Cai , Hongwei Wang , Gaoang Wang

Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific…

Robotics · Computer Science 2026-05-26 Boyu Li , Chaoyi Xu , Haoqi Yuan , Xinrun Xu , Börje F. Karlsson , Dongbin Zhao , Haoran Li , Zongqing Lu

In dynamic environments such as warehouses, hospitals, and homes, robots must seamlessly transition between gross motion and precise manipulations to complete complex tasks. However, current Vision-Language-Action (VLA) frameworks, largely…

While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we explore leveraging pre-trained text-to-image diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Heeseong Shin , Byeongho Heo , Dongyoon Han , Seungryong Kim , Taekyung Kim

Imitation Learning presents a promising approach for learning generalizable and complex robotic skills. The recently proposed Diffusion Policy generates robot action sequences through a conditional denoising diffusion process, achieving…

Machine Learning · Computer Science 2024-12-03 Xiu Yuan

Incorporating camera intrinsics into video generation models offers a principled way to control not only scene dynamics but also the imaging process that governs visual appearance. Prior work has primarily focused on extrinsic control, such…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Debabrata Mandal , Zhihan Peng , Yujie Wang , Praneeth Chakravarthula

Many robotic systems, such as mobile manipulators or quadrotors, cannot be equipped with high-end GPUs due to space, weight, and power constraints. These constraints prevent these systems from leveraging recent developments in visuomotor…

Robotics · Computer Science 2024-07-02 Aaditya Prasad , Kevin Lin , Jimmy Wu , Linqi Zhou , Jeannette Bohg

Vision-Language-Action (VLA) models adapt large vision-language backbones to map images and instructions into robot actions. However, prevailing VLAs either generate actions auto-regressively in a fixed left-to-right order or attach…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Zhixuan Liang , Yizhuo Li , Tianshuo Yang , Chengyue Wu , Sitong Mao , Tian Nian , Liuao Pei , Shunbo Zhou , Xiaokang Yang , Jiangmiao Pang , Yao Mu , Ping Luo

Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation…