English
Related papers

Related papers: AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoi…

200 papers

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Robotics · Computer Science 2025-09-29 Asher J. Hancock , Xindi Wu , Lihan Zha , Olga Russakovsky , Anirudha Majumdar

Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronounced in real-world settings, where viewpoint variability is…

Robotics · Computer Science 2026-01-07 Youngjoon Jeong , Junha Chun , Taesup Kim

Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments,…

Robotics · Computer Science 2025-10-21 Ruihan Zhao , Tyler Ingebrand , Sandeep Chinchali , Ufuk Topcu

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in robotic manipulation,enabling robots to execute natural language commands through end-to-end learning from visual observations.However, deploying large-scale…

Robotics · Computer Science 2025-12-16 Abdullah Yahya Abdullah Omaisan , Ibrahim Sheikh Mohamed

Amid growing efforts to leverage advances in large language models (LLMs) and vision-language models (VLMs) for robotics, Vision-Language-Action (VLA) models have recently gained significant attention. By unifying vision, language, and…

Robotics · Computer Science 2025-10-09 Kento Kawaharazuka , Jihoon Oh , Jun Yamada , Ingmar Posner , Yuke Zhu

Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera…

Robotics · Computer Science 2025-08-19 Tianyi Zhang , Haonan Duan , Haoran Hao , Yu Qiao , Jifeng Dai , Zhi Hou

Vision-language-action (VLA) models trained on large-scale internet data and robot demonstrations have the potential to serve as generalist robot policies. However, despite their large-scale training, VLAs are often brittle to…

Robotics · Computer Science 2024-10-04 Asher J. Hancock , Allen Z. Ren , Anirudha Majumdar

Vision-Language Models (VLMs) have demonstrated impressive capabilities in zero-shot action recognition by learning to associate video embeddings with class embeddings. However, a significant challenge arises when relying solely on action…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Yehna Kim , Young-Eun Kim , Seong-Whan Lee

Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Dezhao Luo , Jiabo Huang , Shaogang Gong , Hailin Jin , Yang Liu

Vision-Language-Action (VLA) models have shown remarkable achievements, driven by the rich implicit knowledge of their vision-language components. However, achieving generalist robotic agents demands precise grounding into physical…

Robotics · Computer Science 2025-07-15 Jialei Huang , Shuo Wang , Fanqi Lin , Yihang Hu , Chuan Wen , Yang Gao

Vision-language models (VLMs) are gaining attention in medical image analysis. These are pre-trained on large, heterogeneous data sources, yielding rich and transferable representations. Notably, the combination of modality-specialized VLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Julio Silva-Rodríguez , Fereshteh Shakeri , Houda Bahig , Jose Dolz , Ismail Ben Ayed

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to…

Robotics · Computer Science 2026-03-31 Vineet Bhat , Yu-Hsiang Lan , Prashanth Krishnamurthy , Ramesh Karri , Farshad Khorrami

Robotic manipulation requires sophisticated commonsense reasoning, a capability naturally possessed by large-scale Vision-Language Models (VLMs). While VLMs show promise as zero-shot planners, their lack of grounded physical understanding…

Robotics · Computer Science 2026-03-18 Emily Yue-Ting Jia , Weiduo Yuan , Tianheng Shi , Vitor Guizilini , Jiageng Mao , Yue Wang

Efficiently predicting motion plans directly from vision remains a fundamental challenge in robotics, where planning typically requires explicit goal specification and task-specific design. Recent vision-language-action (VLA) models infer…

Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing…

Vision-Language-Action (VLA) models often fail to generalize to unseen camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach…

Robotics · Computer Science 2026-03-10 Ali Abouzeid , Malak Mansour , Qinbo Sun , Zezhou Sun , Dezhen Song

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Manjunath Prasad Holenarasipura Rajiv , B. M. Vidyavathi

Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) a fine-grained disentanglement of complex visual scene and textual context, and (ii) a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-10 Zeyu Han , Fangrui Zhu , Qianru Lao , Huaizu Jiang

Vision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying…