English
Related papers

Related papers: SAM2Act: Integrating Visual Foundation Model with …

200 papers

Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to generalize beyond the specific environments and conditions they…

This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image…

Artificial Intelligence · Computer Science 2026-04-01 Yuci Han , Alper Yilmaz

Effectively handling the interplay between spatial perception and action generation remains a critical bottleneck in robotic manipulation. Existing methods typically treat spatial perception and action execution as decoupled or strictly…

Robotics · Computer Science 2026-05-13 Kai Xiong , Hongjie Fang , Lixin Yang , Cewu Lu

Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies. While many reinforcement learning (RL) algorithms incorporate memory, the field lacks a universal benchmark to assess an agent's memory…

Machine Learning · Computer Science 2026-03-05 Egor Cherepanov , Nikita Kachaev , Alexey K. Kovalev , Aleksandr I. Panov

Robots often struggle to follow free-form human instructions in real-world settings due to computational and sensing limitations. We address this gap with a lightweight, fully on-device pipeline that converts natural-language commands into…

Robotics · Computer Science 2026-02-11 Archit Sharma , Dharmendra Sharma , John Rebeiro , Peeyush Thakur , Narendra Dhar , Laxmidhar Behera

This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accomplish a given task. Although recent Vision-Language Models (VLMs) have achieved impressive…

Robotics · Computer Science 2026-04-10 Peiran Xu , Jiaqi Zheng , Yadong Mu

Inspired by Segment Anything 2, which generalizes segmentation from images to videos, we propose SAM2MOT--a novel segmentation-driven paradigm for multi-object tracking that breaks away from the conventional detection-association framework.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Junjie Jiang , Zelin Wang , Manqi Zhao , Yin Li , DongSheng Jiang

This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction…

Robotics · Computer Science 2025-08-18 Hanwen Wan , Yifei Chen , Yixuan Deng , Zeyu Wei , Dongrui Li , Zexin Lin , Donghao Wu , Jiu Cheng , Xiaoqiang Ji

We present Im2Flow2Act, a scalable learning framework that enables robots to acquire real-world manipulation skills without the need of real-world robot training data. The key idea behind Im2Flow2Act is to use object flow as the…

Robotics · Computer Science 2024-10-07 Mengda Xu , Zhenjia Xu , Yinghao Xu , Cheng Chi , Gordon Wetzstein , Manuela Veloso , Shuran Song

Reliable simulation evaluation of robot manipulation policies serves as a high-fidelity proxy for real-world performance. Although existing benchmarks cover a wide range of task categories, they lack visual realism, creating a large domain…

Robotics · Computer Science 2026-05-08 Yixin Zhu , Zixiong Wang , Jian Yang , Jin Xie , Jingyi Yu , Jiayuan Gu , Beibei Wang

Current vision-language-action (VLA) models, pre-trained on large-scale robotic data, exhibit strong multi-task capabilities and generalize well to variations in visual and language instructions for manipulation. However, their success rate…

Robotics · Computer Science 2025-10-17 Han Zhao , Jiaxuan Zhang , Wenxuan Song , Pengxiang Ding , Donglin Wang

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-language backbones. However, most existing VLAs rely primarily on 2D visual representations,…

Robotics · Computer Science 2026-05-21 Shizhe Chen , Paul Pacaud , Cordelia Schmid

Current datasets for action recognition tasks face limitations stemming from traditional collection and generation methods, including the constrained range of action classes, absence of multi-viewpoint recordings, limited diversity, poor…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Xingyu Song , Zhan Li , Shi Chen , Kazuyuki Demachi

Manual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process. Recent advancements in foundation models for video object segmentation,…

Image and Video Processing · Electrical Eng. & Systems 2025-11-04 Yuwen Chen , Zafer Yildiz , Qihang Li , Yaqian Chen , Haoyu Dong , Hanxue Gu , Nicholas Konz , Maciej A. Mazurowski

Vision Language Action (VLA) models represent a transformative shift in robotics, with the aim of unifying visual perception, natural language understanding, and embodied control within a single learning framework. This review presents a…

Robotics · Computer Science 2026-01-21 Muhayy Ud Din , Waseem Akram , Lyes Saad Saoud , Jan Rosell , Irfan Hussain

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the…

Robotics · Computer Science 2026-03-30 Zhuoran Li , Zhiyang Li , Kaijun Zhou , Jinyu Gu

Generalist robot manipulators need to learn a wide variety of manipulation skills across diverse environments. Current robot training pipelines rely on humans to provide kinesthetic demonstrations or to program simulation environments and…

Robotics · Computer Science 2023-10-30 Pushkal Katara , Zhou Xian , Katerina Fragkiadaki

Imitation learning is a popular paradigm to teach robots new tasks, but collecting robot demonstrations through teleoperation or kinesthetic teaching is tedious and time-consuming. In contrast, directly demonstrating a task using our human…

Robotics · Computer Science 2026-02-16 Nick Heppert , Minh Quang Nguyen , Abhinav Valada

How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion information from web data through human video generation and…

‹ Prev 1 3 4 5 6 7 10 Next ›