English
Related papers

Related papers: SlotVLA: Towards Modeling of Object-Relation Repre…

200 papers

Vision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically…

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…

The choice of representation plays a key role in self-driving. Bird's eye view (BEV) representations have shown remarkable performance in recent years. In this paper, we propose to learn object-centric representations in BEV to distill a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Shadi Hamdan , Fatma Güney

Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Anupam Pani , Yanchao Yang

Vision-language-action (VLA) models hold promise as generalist robotics solutions by translating visual and linguistic inputs into robot actions, yet they lack reliability due to their black-box nature and sensitivity to environmental…

Robotics · Computer Science 2025-02-10 Hong Lu , Hengxu Li , Prithviraj Singh Shahani , Stephanie Herbers , Matthias Scheutz

Deformable objects manipulation can benefit from representations that seamlessly integrate vision and touch while handling occlusions. In this work, we present a novel approach for, and real-world demonstration of, multimodal visuo-tactile…

Robotics · Computer Science 2022-10-10 Youngsun Wi , Andy Zeng , Pete Florence , Nima Fazeli

The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Ayush Chakravarthy , Trang Nguyen , Anirudh Goyal , Yoshua Bengio , Michael C. Mozer

Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency and poor generalization. We argue that these bottlenecks stem from the prevailing Direct…

Robotics · Computer Science 2026-05-28 Yutai Li , Shaohui Peng , Jiaming Guo , Di Huang , Zihao Zhang , Yuxuan Guo , Yunkai Gao , Siming Lan , Ling Li , Xing Hu , Yunji Chen

Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a novel VLA approach that leverages the competitive…

Robotics · Computer Science 2025-12-23 Max Argus , Jelena Bratulic , Houman Masnavi , Maxim Velikanov , Nick Heppert , Abhinav Valada , Thomas Brox

General-purpose robots must master long-horizon manipulation, defined as tasks involving multiple kinematic structure changes (e.g., attaching or detaching objects) in unstructured environments. While Vision-Language-Action (VLA) models…

Robotics · Computer Science 2026-02-26 Yue Yang , Shuo Cheng , Yu Fang , Homanga Bharadhwaj , Mingyu Ding , Gedas Bertasius , Daniel Szafir

Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in…

Robotics · Computer Science 2024-10-16 Shiyu Jin , Jinxuan Xu , Yutian Lei , Liangjun Zhang

Current Vision-Language-Action (VLA) models typically treat the deepest representation of a vision-language backbone as universally optimal for action prediction. However, robotic manipulation is composed of many frequent closed-loop…

Artificial Intelligence · Computer Science 2026-05-12 Boyang Shen , Kaixiang Yang , Hao Wang , Qiuyu Yu , Qiang Xie , Qiang Li , Zhiwei Wang

Deformable object manipulation requires computationally efficient representations that are compatible with robotic sensing modalities. In this paper, we present VIRDO:an implicit, multi-modal, and continuous representation for…

Robotics · Computer Science 2022-09-28 Youngsun Wi , Pete Florence , Andy Zeng , Nima Fazeli

Visual-textual understanding is essential for language-guided robot manipulation. Recent works leverage pre-trained vision-language models to measure the similarity between encoded visual observations and textual instructions, and then…

Robotics · Computer Science 2025-09-30 Chaoran Zhu , Hengyi Wang , Yik Lung Pang , Changjae Oh

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs…

While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Tri Cao , Khoi Le , Thong Nguyen , Cong-Duy Nguyen , Quynh Vo , Anh Tuan Luu , Chunyan Miao , See-Kiong Ng , Shuicheng Yan , Bryan Hooi

Learning multi-object dynamics from visual data using unsupervised techniques is challenging due to the need for robust, object representations that can be learned through robot interactions. This paper presents a novel framework with two…

Robotics · Computer Science 2023-10-10 Alireza Rezazadeh , Athreyi Badithela , Karthik Desingh , Changhyun Choi

Humans act with context and intention, with reasoning playing a central role. While internet-scale data has enabled broad reasoning capabilities in AI systems, grounding these abilities in physical action remains a major challenge. We…

Robotics · Computer Science 2025-12-11 Peijun Tang , Shangjin Xie , Binyan Sun , Baifu Huang , Kuncheng Luo , Haotian Yang , Weiqi Jin , Jianan Wang

Vision-language-action (VLA) models have shown strong generalization for robotic action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their perception and,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Heyu Guo , Shanmu Wang , Ruichun Ma , Shiqi Jiang , Yasaman Ghasempour , Omid Abari , Baining Guo , Lili Qiu

Recent Large Vision Language Models (LVLMs) present remarkable zero-shot conversational and reasoning capabilities given multimodal queries. Nevertheless, they suffer from object hallucination, a phenomenon where LVLMs are prone to generate…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yun Xing , Yiheng Li , Ivan Laptev , Shijian Lu