English
Related papers

Related papers: OFlow: Injecting Object-Aware Temporal Flow Matchi…

200 papers

Vision-Language-Action (VLA) models have achieved remarkable progress in robotic manipulation by mapping multimodal observations and instructions directly to actions. However, they typically mimic expert trajectories without predictive…

Feature matching across video streams remains a cornerstone challenge in computer vision. Increasingly, robust multimodal matching has garnered interest in robotics, surveillance, remote sensing, and medical imaging. While traditional rely…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Jie Wang , Chen Ye Gan , Caoqi Wei , Jiangtao Wen , Yuxing Han

Task and motion planning are long-standing challenges in robotics, especially when robots have to deal with dynamic environments exhibiting long-term dynamics, such as households or warehouses. In these environments, long-term dynamics…

Robotics · Computer Science 2025-09-23 Francesco Argenziano , Miguel Saavedra-Ruiz , Sacha Morin , Daniele Nardi , Liam Paull

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component…

In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the…

For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others. This can be done using different sensors and modalities. In this…

Computer Vision and Pattern Recognition · Computer Science 2023-09-07 Andrea Ciamarra , Federico Becattini , Lorenzo Seidenari , Alberto Del Bimbo

Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. However, standard training optimizes a pointwise velocity objective while inference…

Robotics · Computer Science 2026-05-12 Riad Ahmed , Sujosh Nag , Moniruzzaman Akash , Mostafa Hussein , Momotaz Begum

Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…

Computer Vision and Pattern Recognition · Computer Science 2020-11-05 René Schuster , Christian Unger , Didier Stricker

Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors and inefficiency. While Vision-Language Models (VLMs)…

Robotics · Computer Science 2026-02-12 Songen Gu , Yunuo Cai , Tianyu Wang , Simo Wu , Yanwei Fu

Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challenge, we introduce FLoWN, a flow matching model that learns to…

Machine Learning · Computer Science 2025-04-22 Daniel Saragih , Deyu Cao , Tejas Balaji , Ashwin Santhosh

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion…

The Visual-Language-Action (VLA) models can follow text instructions according to visual observations of the surrounding environment. This ability to map multimodal inputs to actions is derived from the training of the VLA model on…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Jinyue Bian , Zhaoxing Zhang , Zhengyu Liang , Shiwei Zheng , Shengtao Zhang , Rong Shen , Chen Yang , Anzhou Hou

Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to operate reliably in dynamic environments and often fail…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Shijie Zhou , Bin Zhu , Jiarui Yang , Xiangyu Zhao , Jingjing Chen , Yu-Gang Jiang

Event cameras capture brightness changes asynchronously with microsecond resolution, yet existing optical flow methods fail to fully exploit this temporal continuity. Frame-based approaches impose artificial accumulation latency and suffer…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Gunwoo Jeon , Chaesong Park , Jongwoo Lim

Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while the model computes the next one. This creates a prediction-execution misalignment: the…

Robotics · Computer Science 2026-05-20 Yixiang Zhu , Yonghao Chen , Rui Meng , Jingyu Guo , Jiaxiang Zou , Zijie Yang , Taowen Wang , Xinyu Chen

Flow-matching-based policies have recently emerged as a promising approach for learning-based robot manipulation, offering significant acceleration in action sampling compared to diffusion-based policies. However, conventional flow-matching…

Robotics · Computer Science 2025-10-03 Xuanran Zhai , Qianyou Zhao , Qiaojun Yu , Ce Hao

Inspired by how humans reason over discrete objects and their relationships, we explore whether compact object-centric and object-relation representations can form a foundation for multitask robotic manipulation. Most existing robotic…

Integrating visual-language instructions into visuomotor policies is gaining momentum in robot learning for enhancing open-world generalization. Despite promising advances, existing approaches face two challenges: limited language…

Robotics · Computer Science 2025-10-24 Wenhui Huang , Changhe Chen , Han Qi , Chen Lv , Yilun Du , Heng Yang

One of the central challenges preventing robots from acquiring complex manipulation skills is the prohibitive cost of collecting large-scale robot demonstrations. In contrast, humans are able to learn efficiently by watching others interact…

Robotics · Computer Science 2025-11-13 Changhe Chen , Quantao Yang , Xiaohao Xu , Nima Fazeli , Olov Andersson

Learning latent actions from large-scale videos is crucial for the pre-training of scalable embodied foundation models, yet existing methods often struggle with action-irrelevant distractors. Although incorporating action supervision can…

Robotics · Computer Science 2026-03-24 Xizhou Bu , Jiexi Lyu , Fulei Sun , Ruichen Yang , Zhiqiang Ma , Wei Li