English
Related papers

Related papers: STARRY: Spatial-Temporal Action-Centric World Mode…

200 papers

The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction. Since collecting policy rollouts in the real world is expensive, we investigate whether a…

Robotics · Computer Science 2026-02-17 Yanjiang Guo , Tony Lee , Lucy Xiaoyang Shi , Jianyu Chen , Percy Liang , Chelsea Finn

Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned…

Robotics · Computer Science 2026-04-08 Hao Li , Qi Lv , Rui Shao , Xiang Deng , Yinchuan Li , Jianye Hao , Liqiang Nie

World models aim to simulate environments and enable effective agent behavior. However, modeling real-world environments presents unique challenges as they dynamically change across both space and, crucially, time. To capture these composed…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Héctor Carrión , Yutong Bai , Víctor A. Hernández Castro , Kishan Panaganti , Ayush Zenith , Matthew Trang , Tony Zhang , Pietro Perona , Jitendra Malik

Existing robot policies predominantly adopt the task-centric approach, requiring end-to-end task data collection. This results in limited generalization to new tasks and difficulties in pinpointing errors within long-horizon, multi-stage…

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Robotics · Computer Science 2021-12-08 Michael James McDonald , Dylan Hadfield-Menell

Recent advances in diffusion transformers have empowered video generation models to generate high-quality video clips from texts or images. However, world models with the ability to predict long-horizon futures from past observations and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Yixuan Zhu , Jiaqi Feng , Wenzhao Zheng , Yuan Gao , Xin Tao , Pengfei Wan , Jie Zhou , Jiwen Lu

As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interactions with visually…

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder performance and…

Service robots must retrieve objects in dynamic, open-world settings where requests may reference attributes ("the red mug"), spatial context ("the mug on the table"), or past states ("the mug that was here yesterday"). Existing approaches…

Generalizing beyond the training domain in image-based behavior cloning remains challenging. Existing methods address individual axes of generalization, workspace shifts, viewpoint changes, and cross-embodiment transfer, yet they are…

Robotics · Computer Science 2026-01-28 Ruiyu Wang , Zheyu Zhuang , Danica Kragic , Florian T. Pokorny

We introduce Forecast-aware Gaussian Splatting (Forecast-GS), a predictive 3D representation framework for language-conditioned robotic manipulation. While recent manipulation systems have made progress by grounding language instructions…

Robotics · Computer Science 2026-05-13 Kaixin Jia , Jiacheng Xu

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Wenyao Zhang , Hongsi Liu , Zekun Qi , Yunnan Wang , Xinqiang Yu , Jiazhao Zhang , Runpei Dong , Jiawei He , Fan Lu , He Wang , Zhizheng Zhang , Li Yi , Wenjun Zeng , Xin Jin

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical…

World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of these imagined futures remains under-examined: is a generated future merely visually…

Robotics · Computer Science 2026-05-11 Bo-Kai Ruan , Teng-Fang Hsiao , Ling Lo , Hong-Han Shuai

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…

Robotics · Computer Science 2026-03-25 Ruisen Tu , Arth Shukla , Sohyun Yoo , Xuanlin Li , Junxi Li , Jianwen Xie , Hao Su , Zhuowen Tu

Diffusion Language Models (DLMs) enable parallel decoding via iterative denoising, where remasking strategies play a critical role in balancing inference speed and output quality. Existing methods predominantly rely on static confidence…

Computation and Language · Computer Science 2026-02-24 Xinhao Sun , Huaijin Zhao , Maoliang Li , Zihao Zheng , Jiayu Chen , Yun Liang , Xiang Chen

Enabling reliable long-horizon robotic manipulation is a crucial step toward open-world embodied intelligence. However, VLM-based planners treat each step as an isolated observation-to-action mapping, forcing them to reinfer scene geometry…

Recent advancements in vision-language-action (VLA) models have shown promise in robotic manipulation, yet they continue to struggle with long-horizon, multi-step tasks. Existing methods lack internal reasoning mechanisms that can identify…

Visual navigation requires the robot to reach a specified goal such as an image, based on a sequence of first-person visual observations. While recent learning-based approaches have made significant progress, they often focus on improving…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Hao Ren , Zetong Bi , Yiming Zeng , Zhaoliang Wan , Lu Qi , Hui Cheng

In recent years, the Robotics field has initiated several efforts toward building generalist robot policies through large-scale multi-task Behavior Cloning. However, direct deployments of these policies have led to unsatisfactory…