具身智能 · 全部实体（第 90 / 100 页）

本页收录第 8901–9000 条，共 10000 条 · 返回 具身智能 首页

• A survey on large language model based autonomous agents
  Abstract Autonomous agents have long been a research focus in academic and industry communities. Previous research often focuses on training agents with limited knowledge within isolated environments, which diverges significantly from human learning processes,…
  openalex Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang 等 2024-03-22 置信度 0.72 Computer scienceArtificial intelligence
• Multimodal fusion with vision-language-action models for robotic manipulation: A systematic review
  Vision Language Action (VLA) models represent a new frontier in robotics by unifying perception, reasoning, and control within a single multimodal learning framework. By integrating visual, linguistic, and action modalities, they enable multimodal fusion syste…
  openalex Muhayy Ud Din, Waseem Akram, Lyes Saad Saoud, Jan Rosell 等 2025-12-16 置信度 0.72 Computer scienceArtificial intelligenceMachine learningBenchmarkingRobustness (evolution)
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
  The recent GPT-4 has demonstrated extraordinary multi-modal abilities, such as directly generating websites from handwritten text and identifying humorous elements within images. These features are rarely observed in previous vision-language models. However, t…
  openalex Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li 等 2023-04-20 置信度 0.72 Computer scienceUsabilityRepetition (rhetorical device)ModalCode (set theory)
• Coordination Models and Languages
  openalex George Α. Papadopoulos, Farhad Arbab 1998-01-01 置信度 0.72 Computer scienceRotation formalisms in three dimensionsInterfacingComponent (thermodynamics)Set (abstract data type)
• RoboNurse-VLA: Robotic Scrub Nurse System based on Vision-Language-Action Model
  In modern healthcare, the demand for autonomous robotic assistants has grown significantly, particularly in the operating room, where surgical tasks require precision and reliability. Robotic scrub nurses have emerged as a promising solution to improve efficie…
  openalex Shunlei Li, Jin Wang, Rui Dai, Wanyu Ma 等 2025-10-19 置信度 0.72 Task (project management)Computer scienceHuman–computer interactionHandoverArtificial intelligence
• CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Mo…
  openalex Qixiu Li, Yaobo Liang, Zeyu Wang, Lin Luo 等 2024-11-29 置信度 0.72 Action (physics)Cognitive scienceCognitionCognitive roboticsPsychology
• Large Language Models are Zero-Shot Reasoners
  Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a recent technique for e…
  openalex Takeshi Kojima, Shixiang Gu, Machel Reid, Yutaka Matsuo 等 2022-05-24 置信度 0.72 Shot (pellet)Task (project management)Benchmark (surveying)Computer scienceZero (linguistics)
• Teacher cognition in language teaching: A review of research on what language teachers think, know, believe, and do
  This paper reviews a selection of research from the field of foreign and second language teaching into what is referred to here as teacher cognition – what teachers think, know, and believe and the relationships of these mental constructs to what teachers do i…
  openalex Simon Borg 2003-04-01 置信度 0.72 CognitionPsychologyMainstreamLanguage educationPerspective (graphical)
• Force Dynamics in Language and Cognition
  “Force dynamics” refers to a previously neglected semantic category—how entities interact with respect to force. This category includes such concepts as: the exertion of force, resistance to such exertion and the overcoming of such resistance, blockage of a fo…
  openalex Léonard Talmy 1988-01-01 置信度 0.72 Notional amountDynamics (music)CognitionCognitive scienceCognitive psychology
• Active vision: the psychology of looking and seeing
  PASSIVE VISION AND ACTIVE VISION 1.1 Introduction 1.2 Passive vision 1.3 Visual attention 1.4 Active vision 1.5 Active vision and vision for action 1.6 Outline of the book BACKGROUND TO ACTIVE VISION 2.1 Introduction 2.2 The inhomogeneity of the visual project…
  openalex 2004-04-01 置信度 0.72 AestheticsPsychologyHistoryEpistemologyPhilosophy
• Health literacy and public health: A systematic review and integration of definitions and models
  BACKGROUND: Health literacy concerns the knowledge and competences of persons to meet the complex demands of health in modern society. Although its importance is increasingly recognised, there is no consensus about the definition of health literacy or about it…
  openalex Kristine Sørensen, Stephan Van den Broucke, James Fullam, Gerardine Doyle 等 2012-01-25 置信度 0.72 Health literacyPublic healthHealth promotionConceptual modelHealth care
• Florence: A New Foundation Model for Computer Vision
  Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on diverse, large-scale …
  openalex Lu Yuan, Dongdong Chen, Yi‐Ling Chen, Noel Codella 等 2021-11-22 置信度 0.72 Computer scienceArtificial intelligenceObject (grammar)Computer visionRepresentation (politics)
• OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
  We present OpenDriveVLA, a Vision-Language Action (VLA) model designed for end-to-end autonomous driving, built upon open-source large language models. OpenDriveVLA generates spatially-grounded driving actions by leveraging multimodal inputs, including both 2D…
  openalex Xingcheng Zhou, Xuyuan Han, Feng Yang, Yunpu Ma 等 2026-03-14 置信度 0.72 Computer scienceArtificial intelligenceAction (physics)TrajectoryBridge (graph theory)
• MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models
  Developing versatile quadruped robots that can smoothly perform various actions and tasks in real-world environments remains a significant challenge. This paper introduces a novel vision-language-action (VLA) model, mixture of robotic experts (MoRE), for quadr…
  openalex Han Zhao, Wenxuan Song, Donglin Wang, Xinyang Tong 等 2025-05-19 置信度 0.72 Reinforcement learningScalabilityComputer scienceAction (physics)Artificial intelligence
• A survey of methods for explaining black box models
  In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many…
  openalex Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini 等 2019-01-01 置信度 0.72 InterpretabilityBlack boxComputer sciencePerspective (graphical)Data science
• Autonomous chemical research with large language models
  Abstract Transformer-based large language models are making significant strides in various fields, such as natural language processing 1–5 , biology 6,7 , chemistry 8–10 and computer programming 11,12 . Here, we show the development and capabilities of Coscien…
  openalex Daniil A. Boiko, Robert MacKnight, Ben Kline, Gabriel dos Passos Gomes 2023-12-20 置信度 0.72 Computer scienceDocumentationAutomationTransformerArtificial intelligence
• Identity and Language Learning
  This second edition of Norton’s classic text on language learning and identity will bring her ground-breaking ideas to a new generation of students, teachers and researchers. Featuring a comprehensive Introduction and an Afterword by Claire Kramsch, this new e…
  openalex Bonny Norton 2013-12-31 置信度 0.72 Identity (music)LinguisticsLanguage acquisitionMathematics educationComputer science
• InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
  Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input distributions and task diversi…
  openalex Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong 等 2023-05-11 置信度 0.72 Computer scienceLanguage modelArtificial intelligenceTransformerNatural language processing
• The pandemic of physical inactivity: global action for public health
  Physical inactivity is the fourth leading cause of death worldwide. We summarise present global efforts to counteract this problem and point the way forward to address the pandemic of physical inactivity. Although evidence for the benefits of physical activity…
  openalex Harold W. Kohl, Cora L. Craig, Estelle V. Lambert, Shigeru Inoue 等 2012-07-01 置信度 0.72 PandemicPublic healthHealth promotionAction (physics)Workforce
• TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require e…
  openalex Junjie Wen, Yichen Zhu, Jinming Li, Minjie Zhu 等 2024-09-19 置信度 0.72 Computer scienceAction (physics)Artificial intelligenceData manipulation languageComputer vision
• Features and development of <i>Coot</i>
  Coot is a molecular-graphics application for model building and validation of biological macromolecules. The program displays electron-density maps and atomic models and allows model manipulations such as idealization, real-space refinement, manual rotation/tr…
  openalex Paul Emsley, Bernhard Lohkamp, W. G. Scott, Kevin Cowtan 2010-03-23 置信度 0.72 Computer scienceScripting languageSoftwareInterface (matter)Human–computer interaction
• The imperative for regulatory oversight of large language models (or generative AI) in healthcare
  The rapid advancements in artificial intelligence (AI) have led to the development of sophisticated large language models (LLMs) such as GPT-4 and Bard. The potential implementation of LLMs in healthcare settings has already garnered considerable attention bec…
  openalex Bertalan Meskó, Eric J. Topol 2023-07-06 置信度 0.72 Transformative learningContext (archaeology)Health careHarmEngineering ethics
• VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
  Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While this approach greatly enhances performance, it also incurs significant training c…
  openalex Yihao Wang, Pengxiang Ding, Lingxiao Li, Can Cui 等 2026-03-14 置信度 0.72 Bridging (networking)Computer scienceBridge (graph theory)Artificial intelligenceInference
• What matters in building vision–language–action models for generalist robots
  openalex Xinghang Li, Peiyan Li, Long Qian, Minghuan Liu 等 2026-02-11 置信度 0.72 Computer scienceRobotKey (lock)Foundation (evidence)Focus (optics)
• Transforming vision into action
  openalex Melvyn A. Goodale 2010-08-05 置信度 0.72 Vision for perception and vision for actionAction (physics)PerceptionPsychologyControl (management)
• NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
  Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, …
  openalex Gengze Zhou, Yicong Hong, Qi Wu 2024-03-24 置信度 0.72 Computer scienceLinguisticsCognitive scienceArtificial intelligencePsychology
• A Survey on Vision-Language-Action Models for Autonomous Driving
  The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving…
  openalex Shan Jiang, Zilin Huang, Kangan Qian, Ziang Luo 等 2025-06-30 置信度 0.72 Computer scienceTRACE (psycholinguistics)Control (management)Measure (data warehouse)Human–computer interaction
• REBUS and the Anarchic Brain: Toward a Unified Model of the Brain Action of Psychedelics
  This paper formulates the action of psychedelics by integrating the free-energy principle and entropic brain hypothesis. We call this formulation relaxed beliefs under psychedelics (REBUS) and the anarchic brain, founded on the principle that—via their entropi…
  openalex Robin Carhart‐Harris, Karl Friston 2019-06-20 置信度 0.72 Prior probabilityAction (physics)PsychologyConsciousnessPsilocybin
• Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training
  Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper, we present the firs…
  openalex Weituo Hao, Chunyuan Li, Xiujun Li, Lawrence Carin 等 2020-06-01 置信度 0.72 Computer scienceTask (project management)Artificial intelligenceNatural languageBenchmark (surveying)
• Taxonomy of Risks posed by Language Models
  Responsible innovation on large-scale Language Models (LMs) requires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxonomy of ethical and social risks associated with LMs. We identify twenty-…
  openalex Laura Weidinger, Jonathan Uesato, Maribeth Rauh, Conor Griffin 等 2022-06-20 置信度 0.72 MisinformationTaxonomy (biology)HarmRisk analysis (engineering)Futures studies
• Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation
  In robotic, task goals can be conveyed through various modalities, such as language, goal images, and goal videos. However, natural language can be ambiguous, while images or videos may offer overly detailed specifications. To tackle these challenges, we intro…
  openalex Xiaoqi Li, Jingyun Xu, Mingxu Zhang, Jiaming Liu 等 2025-06-10 置信度 0.72 Computer scienceAction (physics)Artificial intelligenceObject (grammar)Computer vision
• A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation
  Recently, some studies have integrated Multimodal Large Language Models into robotic manipulation, constructing vision-language-action models (VLAs) to interpret multimodal information and predict SE(3) poses. While VLAs have shown promising progress, they may…
  openalex Chenxuan Li, Jiaming Liu, Guanqun Wang, Li, Xiaoqi 等 2024-05-27 置信度 0.72 End-to-end principleComputer scienceRobotArtificial intelligence
• $π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
  In order for robots to be useful, they must perform practically relevant tasks in the real world, outside of the lab. While vision-language-action (VLA) models have demonstrated impressive results for end-to-end robot control, it remains an open question how f…
  openalex Physical Intelligence, Kevin Black, Noah Brown, James Darpinian 等 2025-04-22 置信度 0.72 Computer scienceGeneralizationRobotArtificial intelligenceObject (grammar)
• VLA-Grasp: a vision-language-action modeling with cross-modality fusion for task-oriented grasping
  Task-oriented grasping (TOG) aims to predict the appropriate pose for grasping based on a specific task. While recent approaches have incorporated semantic knowledge into TOG models to enable robots to understand linguistic commands, they lack the ability to l…
  openalex Jianwei Zhu, Xueying Sun, Qiang Zhang, Mingmin Liu 2025-05-06 置信度 0.72 GRASPComputational intelligenceModality (human–computer interaction)Action (physics)Task (project management)
• The Esterel synchronous programming language: design, semantics, implementation
  openalex Gérard Berry, Georges Gonthier 1992-11-01 置信度 0.72 Computer scienceProgramming languageSemantics (computer science)Asynchronous communicationOperational semantics
• Deep learning-enabled medical computer vision
  A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields-including medicine-to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of mod…
  openalex Andre Esteva, Katherine Chou, Serena Yeung, Nikhil Naik 等 2021-01-08 置信度 0.72 Software deploymentWorkflowDeep learningConvolutional neural networkComputer science
• PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding
  Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control. However, action chunking…
  openalex Wenxuan Song, Jiayi Chen, Pengxiang Ding, Han Zhao 等 2025-10-19 置信度 0.72 Decoding methodsChunking (psychology)Computer scienceAction (physics)Inference
• A review and synthesis of the first 20years of PET and fMRI studies of heard speech, spoken language and reading
  The anatomy of language has been investigated with PET or fMRI for more than 20 years. Here I attempt to provide an overview of the brain areas associated with heard speech, speech production and reading. The conclusions of many hundreds of studies were consid…
  openalex Cathy J. Price 2012-05-12 置信度 0.72 Reading (process)Articulation (sociology)Speech productionComputer scienceSpoken language
• Whatever next? Predictive brains, situated agents, and the future of cognitive science
  Brains, it has recently been argued, are essentially prediction machines. They are bundles of cells that support perception and action by constantly attempting to match incoming sensory inputs with top-down expectations or predictions. This is achieved using a…
  openalex Andy Clark 2013-05-10 置信度 0.72 SituatedCognitive scienceCognitionPsychologyComputer science
• Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks
  Vision-Language Navigation (VLN) is a task where an agent learns to navigate following a natural language instruction. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches fully exploit vision and…
  openalex Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang 2020-06-01 置信度 0.72 Computer scienceTask (project management)Benchmark (surveying)Natural languageArtificial intelligence
• Retrieval-Augmented Generation for Large Language Models: A Survey
  Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by inc…
  openalex Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia 等 2023-12-18 置信度 0.72 CredibilityComputer scienceModular designBenchmark (surveying)Data science
• Motivation in second and foreign language learning
  All this work could be conceivable
  openalex Zoltán Dörnyei 1998-07-01 置信度 0.72 Content (measure theory)PsychologyForeign languageMathematics educationCognitive psychology
• Joint action: bodies and minds moving together
  openalex Natalie Sebanz, H. Bekkering, Günther Knoblich 2006-01-11 置信度 0.72 Action (physics)CognitionPsychologyContext (archaeology)Perception
• Shake-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Manipulations and Liquid Mixing
  This paper introduces Shake-VLA, a Vision-Language-Action (VLA) model-based system designed to enable bimanual robotic manipulation for automated cocktail preparation. The system integrates a vision module for detecting ingredient bottles and reading labels, a…
  openalex Mohammad Salman Khan, Selamawit Asfaw, Dmitrii Iarchuk, Miguel Altamirano Cabrera 等 2025-03-04 置信度 0.72 ShakeMixing (physics)Action (physics)Computer scienceArtificial intelligence
• Coh-Metrix: Analysis of text on cohesion and language
  openalex Arthur C. Graesser, Danielle S. McNamara, Max M. Louwerse, Zhiqiang Cai 2004-05-01 置信度 0.72 Cohesion (chemistry)Computer scienceReadabilityNatural language processingArtificial intelligence
• Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models
  Abstract Foundation Vision Language Models (VLMs) exhibit strong capabilities in multi-modal representation learning, comprehension, and reasoning. By injecting action components into the VLMs, Vision-Language-Action models (VLAs) can be naturally formed and a…
  openalex Huaping Liu, Xinghang Li, Peiyan Li, Minghuan Liu 等 2025-02-25 置信度 0.72 Generalist and specialist speciesAction (physics)RobotComputer scienceArtificial intelligence
• EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy
  In endoscopic procedures, autonomous tracking of abnormal regions and following circumferential cutting markers can significantly reduce the cognitive burden on endoscopists. However, conventional model-based pipelines are fragile for each component (e.g., det…
  openalex Chi Kit Ng, Long Bai, Guankun Wang, Yupeng Wang 等 2025-05-21 置信度 0.72 Artificial intelligenceComputer visionComputer scienceGeneralizationComponent (thermodynamics)
• Probing a Vision-Language-Action Model for Symbolic States and Integration into a Cognitive Architecture
  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 changes. In contrast, cog…
  openalex Hong Lu, Hengxu Li, Prithviraj Singh Shahani, Stephanie Herbers 等 2025-06-24 置信度 0.72 Computer scienceArchitectureAction (physics)Cognitive architectureCognition
• Language Reasoning in Vision-Language-Action Model for Robotic Grasping
  Grasping tasks are crucial for the interaction between the robot and environment, requiring the robot to make autonomous decisions based on environmental conditions and instructions. Recently, multimodal Vision Language Models (VLMs) have demonstrated signific…
  openalex Lingling Fan, Kang Chen, Zhezhuang Xu, Meng Yuan 等 2024-11-01 置信度 0.72 Computer scienceAction (physics)Artificial intelligenceLanguage modelHuman–computer interaction
• LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation
  Building on the advancements of Large Language Models (LLMs) and Vision Language Models (VLMs), recent research has introduced Vision-Language-Action (VLA) models as an integrated solution for robotic manipulation tasks. These models take camera images and nat…
  openalex Zhijie Wang, Zhehua Zhou, Jiayang Song, Yuheng Huang 等 2024-10-07 置信度 0.72 Action (physics)Computer scienceHuman–computer interactionArtificial intelligenceQuantum mechanics
• Compositional Context Fine-Tuning Vision-Language Model for Complex Assembly Action Understanding from Videos
  Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand-object interactions. We adapt vision-language models (VLMs) to this challenging domain with …
  arxiv Hao Zheng, Jinyi Huang, Tiantian Zheng, Xun Xu 等 2026-07-12T15:09:33Z 置信度 0.78 cs.CV
• Hierarchical Pre-Training of Vision Encoders with Large Language Model
  The field of computer vision has experienced significant advancements through scalable vision encoders and multimodal pre-training frameworks. However, existing approaches often treat vision encoders and large language models (LLMs) as independent modules, lim…
  arxiv Eugene Lee, Ting-Yu Chang, Jui-Huang Tsai, Jiajie Diao 等 2026-03-31T18:00:39Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• VLP: A Survey on Vision-Language Pre-training
  In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid …
  arxiv Feilong Chen, Duzhen Zhang, Minglun Han, Xiuyi Chen 等 2022-02-18T07:54:02Z 置信度 0.78 cs.CVcs.CL
• Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
  Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In…
  arxiv Yongchao Feng, Yajie Liu, Shuai Yang, Wenrui Cai 等 2025-04-13T08:28:13Z 置信度 0.78 cs.CVcs.AI
• Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
  The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This in-depth review present…
  arxiv Ranjan Sapkota, Manoj Karkee 2025-08-25T17:21:00Z 置信度 0.78 cs.CVcs.AIcs.CL
• Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
  Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the Vision-Language-Vision (VLV) au…
  arxiv Tiezheng Zhang, Yitong Li, Yu-cheng Chou, Jieneng Chen 等 2025-07-09T17:59:04Z 置信度 0.78 cs.CV
• Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection
  Vision-Language-Action (VLA) models have demonstrated strong potential for predicting semantic actions in navigation tasks, demonstrating the ability to reason over complex linguistic instructions and visual contexts. However, they are fundamentally hindered b…
  arxiv Jaehwan Jeong, Evelyn Zhu, Jinying Lin, Emmanuel Jaimes 等 2026-03-14T06:26:11Z 置信度 0.78 cs.ROcs.CV
• Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
  This paper surveys vision-language pre-training (VLP) methods for multimodal intelligence that have been developed in the last few years. We group these approaches into three categories: ($i$) VLP for image-text tasks, such as image captioning, image-text retr…
  arxiv Zhe Gan, Linjie Li, Chunyuan Li, Lijuan Wang 等 2022-10-17T17:11:36Z 置信度 0.78 cs.CVcs.CL
• BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
  Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight inference wrapper that can …
  arxiv Xiaoyu Ma, Zhengqing Yuan, Zheyuan Zhang, Kaiwen Shi 等 2025-12-12T18:30:45Z 置信度 0.78 cs.RO
• Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP
  Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy spans of text, capture…
  arxiv Vedant Palit, Rohan Pandey, Aryaman Arora, Paul Pu Liang 2023-08-27T18:46:47Z 置信度 0.78 cs.CLcs.AIcs.CV
• Explaining Vision and Language through Graphs of Events in Space and Time
  Artificial Intelligence makes great advances today and starts to bridge the gap between vision and language. However, we are still far from understanding, explaining and controlling explicitly the visual content from a linguistic perspective, because we still …
  arxiv Mihai Masala, Nicolae Cudlenco, Traian Rebedea, Marius Leordeanu 2023-08-29T07:25:06Z 置信度 0.78 cs.AIcs.CLcs.CV
• Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition
  Existing vision-based action recognition is susceptible to occlusion and appearance variations, while wearable sensors can alleviate these challenges by capturing human motion with one-dimensional time-series signal. For the same action, the knowledge learned …
  arxiv Yang Liu, Keze Wang, Guanbin Li, Liang Lin 2020-09-01T03:38:31Z 置信度 0.78 cs.CV
• VARCO-VISION: Expanding Frontiers in Korean Vision-Language Models
  In this paper, we introduce an open-source Korean-English vision-language model (VLM), VARCO-VISION. We incorporate a step-by-step training strategy that allows a model learn both linguistic and visual information while preserving the backbone model's knowledg…
  arxiv Jeongho Ju, Daeyoung Kim, SunYoung Park, Youngjune Kim 2024-11-28T12:38:42Z 置信度 0.78 cs.CVcs.CL
• How do language models learn facts? Dynamics, curricula and hallucinations
  Large language models accumulate vast knowledge during pre-training, yet the dynamics governing this acquisition remain poorly understood. This work investigates the learning dynamics of language models on a synthetic factual recall task, uncovering three key …
  arxiv Nicolas Zucchet, Jörg Bornschein, Stephanie Chan, Andrew Lampinen 等 2025-03-27T16:43:45Z 置信度 0.78 cs.CLcs.LG
• Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision?
  Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising observation that re…
  arxiv Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou 2026-05-21T17:35:04Z 置信度 0.78 cs.CVcs.AIcs.CL
• VLS: Steering Pretrained Robot Policies via Vision-Language Models
  Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a limitation of imitation l…
  arxiv Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu, Jiafei Duan 等 2026-02-03T19:50:16Z 置信度 0.78 cs.ROcs.CV
• Benchmarking Vision Language Models on German Factual Data
  Similar to LLMs, the development of vision language models is mainly driven by English datasets and models trained in English and Chinese language, whereas support for other languages, even those considered high-resource languages such as German, remains signi…
  arxiv René Peinl, Vincent Tischler 2025-04-15T11:55:24Z 置信度 0.78 cs.CL
• MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models
  Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging…
  arxiv Han Jang, Junhyeok Lee, Songsoo Kim, Chae Young Lim 等 2026-06-19T08:06:09Z 置信度 0.78 cs.CVcs.AIcs.CL
• The Evolution of First Person Vision Methods: A Survey
  The emergence of new wearable technologies such as action cameras and smart-glasses has increased the interest of computer vision scientists in the First Person perspective. Nowadays, this field is attracting attention and investments of companies aiming to de…
  arxiv Alejandro Betancourt, Pietro Morerio, Carlo S. Regazzoni, Matthias Rauterberg 2014-09-04T16:38:43Z 置信度 0.78 cs.CV
• Multi-Frame, Lightweight &amp; Efficient Vision-Language Models for Question Answering in Autonomous Driving
  Vision-Language Models (VLMs) and Multi-Modal Language models (MMLMs) have become prominent in autonomous driving research, as these models can provide interpretable textual reasoning and responses for end-to-end autonomous driving safety tasks using traffic s…
  arxiv Akshay Gopalkrishnan, Ross Greer, Mohan Trivedi 2024-03-28T21:18:33Z 置信度 0.78 cs.CVcs.AI
• Coordinated Robustness Evaluation Framework for Vision-Language Models
  Vision-language models, which integrate computer vision and natural language processing capabilities, have demonstrated significant advancements in tasks such as image captioning and visual question and answering. However, similar to traditional models, they a…
  arxiv Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour 等 2025-06-05T08:09:05Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
  Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of creating smaller, f…
  arxiv Xuanlin Li, Yunhao Fang, Minghua Liu, Zhan Ling 等 2023-07-06T17:05:26Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• Evaluating Vision-Language Models as Evaluators in Path Planning
  Despite their promise to perform complex reasoning, large language models (LLMs) have been shown to have limited effectiveness in end-to-end planning. This has inspired an intriguing question: if these models cannot plan well, can they still contribute to the …
  arxiv Mohamed Aghzal, Xiang Yue, Erion Plaku, Ziyu Yao 2024-11-27T19:32:03Z 置信度 0.78 cs.CVcs.CL
• Geometric Action Model for Robot Policy Learning
  Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent vision-language-action models (VLAs) and video world-action models (WAMs) inherit strong semantic or…
  arxiv Jisang Han, Seonghu Jeon, Jaewoo Jung, René Zurbrügg 等 2026-06-15T17:58:03Z 置信度 0.78 cs.ROcs.CVcs.LG
• VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
  Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where visual inputs are treated as static context. This limits the ability of the model …
  arxiv Chaoyang Wang, Wenrui Bao, Sicheng Gao, Bingxin Xu 等 2026-03-15T17:59:51Z 置信度 0.78 cs.CVcs.AIcs.RO
• ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
  Vision-Language-Action models have emerged as essential generalist robot policies for diverse manipulation tasks, conventionally relying on directly translating multimodal inputs into actions via Vision-Language Model embeddings. Recent advancements have intro…
  arxiv Linqing Zhong, Yi Liu, Yifei Wei, Ziyu Xiong 等 2026-01-16T16:17:06Z 置信度 0.78 cs.RO
• ECA-LP / ECA-RuleML: A Homogeneous Event-Condition-Action Logic Programming Language
  Event-driven reactive functionalities are an urgent need in nowadays distributed service-oriented applications and (Semantic) Web-based environments. An important problem to be addressed is how to correctly and efficiently capture and process the event-based b…
  arxiv Adrian Paschke 2006-09-26T14:36:47Z 置信度 0.78 cs.AIcs.LOcs.SE
• Tactile Modality Fusion for Vision-Language-Action Models
  We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. While advances in VLAs have introduced robot policies that are both generalizable and semantically grounded, these model…
  arxiv Charlotte Morissette, Amin Abyaneh, Wei-Di Chang, Anas Houssaini 等 2026-03-15T20:57:51Z 置信度 0.78 cs.ROcs.CVcs.LG
• WiCV 2019: The Sixth Women In Computer Vision Workshop
  In this paper we present the Women in Computer Vision Workshop - WiCV 2019, organized in conjunction with CVPR 2019. This event is meant for increasing the visibility and inclusion of women researchers in the computer vision field. Computer vision and machine …
  arxiv Irene Amerini, Elena Balashova, Sayna Ebrahimi, Kathryn Leonard 等 2019-09-23T08:52:33Z 置信度 0.78 cs.CV
• CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks
  Contrastive language-image pretraining (CLIP) links vision and language modalities into a unified embedding space, yielding the tremendous potential for vision-language (VL) tasks. While early concurrent works have begun to study this potential on a subset of …
  arxiv Zhecan Wang, Noel Codella, Yen-Chun Chen, Luowei Zhou 等 2022-01-15T01:54:01Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LGcs.MM
• Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge
  Medical vision-and-language pre-training (Med-VLP) has received considerable attention owing to its applicability to extracting generic vision-and-language representations from medical images and texts. Most existing methods mainly contain three elements: uni-…
  arxiv Zhihong Chen, Guanbin Li, Xiang Wan 2022-09-15T08:00:01Z 置信度 0.78 cs.CLcs.CV
• ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding
  Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare ev…
  arxiv Liang Shi, Boyu Jiang, Tong Zeng, Feng Guo 2024-10-01T18:10:23Z 置信度 0.78 cs.CV
• The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
  Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas. Most existing methods take the words in the instructions and the discrete views of …
  arxiv Yuankai Qi, Zizheng Pan, Yicong Hong, Ming-Hsuan Yang 等 2021-04-09T02:44:39Z 置信度 0.78 cs.CLcs.CV
• Minimalist Vision with Freeform Pixels
  A minimalist vision system uses the smallest number of pixels needed to solve a vision task. While traditional cameras use a large grid of square pixels, a minimalist camera uses freeform pixels that can take on arbitrary shapes to increase their information c…
  arxiv Jeremy Klotz, Shree K. Nayar 2024-12-30T21:27:07Z 置信度 0.78 cs.CVeess.IV
• Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
  The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this constraint, researc…
  arxiv Akash Ghosh, Arkadeep Acharya, Sriparna Saha, Vinija Jain 等 2024-02-20T18:57:34Z 置信度 0.78 cs.CVcs.AIcs.CL
• Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
  We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document understanding. Our model is trained on a comprehensive instruction-following datas…
  arxiv Granite Vision Team, Leonid Karlinsky, Assaf Arbelle, Abraham Daniels 等 2025-02-14T05:36:32Z 置信度 0.78 cs.CVcs.AI
• Discriminating Similar Languages: Evaluations and Explorations
  We present an analysis of the performance of machine learning classifiers on discriminating between similar languages and language varieties. We carried out a number of experiments using the results of the two editions of the Discriminating between Similar Lan…
  arxiv Cyril Goutte, Serge Léger, Shervin Malmasi, Marcos Zampieri 2016-09-30T20:57:52Z 置信度 0.78 cs.CL
• OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue
  Large multimodal language models (LMMs) have achieved significant success in general domains. However, due to the significant differences between medical images and text and general web content, the performance of LMMs in medical scenarios is limited. In ophth…
  arxiv Weihao Gao, Zhuo Deng, Zhiyuan Niu, Fuju Rong 等 2023-06-21T11:09:48Z 置信度 0.78 cs.CV
• Are Compressed Language Models Less Subgroup Robust?
  To reduce the inference cost of large language models, model compression is increasingly used to create smaller scalable models. However, little is known about their robustness to minority subgroups defined by the labels and attributes of a dataset. In this pa…
  arxiv Leonidas Gee, Andrea Zugarini, Novi Quadrianto 2024-03-26T15:50:37Z 置信度 0.78 cs.LGcs.CL
• VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
  Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present in their internal rep…
  arxiv Haz Sameen Shahgir, Xiaofu Chen, Yu Fu, Erfan Shayegani 等 2026-04-02T19:40:56Z 置信度 0.78 cs.CVcs.CL
• Modeling Language Change in Historical Corpora: The Case of Portuguese
  This paper presents a number of experiments to model changes in a historical Portuguese corpus composed of literary texts for the purpose of temporal text classification. Algorithms were trained to classify texts with respect to their publication date taking i…
  arxiv Marcos Zampieri, Shervin Malmasi, Mark Dras 2016-09-30T20:57:01Z 置信度 0.78 cs.CL
• Unforgettable Generalization in Language Models
  When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs learn to generate nea…
  arxiv Eric Zhang, Leshem Choshen, Jacob Andreas 2024-09-03T18:55:54Z 置信度 0.78 cs.LGcs.CL
• EasyARC: Evaluating Vision Language Models on True Visual Reasoning
  Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking true visual reasoning w…
  arxiv Mert Unsal, Aylin Akkus 2025-06-13T09:03:33Z 置信度 0.78 cs.CVcs.LG
• Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training
  Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical vision-and-language under…
  arxiv Zhihong Chen, Yuhao Du, Jinpeng Hu, Yang Liu 等 2022-09-15T07:26:43Z 置信度 0.78 cs.CVcs.CL
• VoxelPrompt: A Vision Agent for End-to-End Medical Image Analysis
  We present VoxelPrompt, an end-to-end image analysis agent that tackles free-form radiological tasks. Given any number of volumetric medical images and a natural language prompt, VoxelPrompt integrates a language model that generates executable code to invoke …
  arxiv Andrew Hoopes, Neel Dey, Victor Ion Butoi, John V. Guttag 等 2024-10-10T22:11:43Z 置信度 0.78 eess.IVcs.AIcs.CV
• LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries
  Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection …
  arxiv Shijie Lian, Bin Yu, Xiaopeng Lin, Laurence T. Yang 等 2026-01-21T17:15:22Z 置信度 0.78 cs.AIcs.CLcs.CVcs.RO
• Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models
  Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks. However, a challenge hindering their application in real-world scenarios, particularly regarding safety, robustness, and reliability, is their constrained se…
  arxiv Jiaying Lu, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo 等 2023-09-07T22:59:56Z 置信度 0.78 cs.CVcs.CL
• Behavioral Bias of Vision-Language Models: A Behavioral Finance View
  Large Vision-Language Models (LVLMs) evolve rapidly as Large Language Models (LLMs) was equipped with vision modules to create more human-like models. However, we should carefully evaluate their applications in different domains, as they may possess undesired …
  arxiv Yuhang Xiao, Yudi Lin, Ming-Chang Chiu 2024-09-23T17:54:47Z 置信度 0.78 cs.CLcs.AI
• The Stellar Imager (SI) Vision Mission
  The Stellar Imager (SI) is a UV-Optical, Space-Based Interferometer designed to enable 0.1 milli-arcsecond (mas) spectral imaging of stellar surfaces and of the Universe in general and asteroseismic imaging of stellar interiors. SI is identified as a "Flagship…
  arxiv Kenneth G. Carpenter, Carolus J. Schrijver, Margarita Karovska, SI Vision Mission Team 2006-06-16T19:05:51Z 置信度 0.78 astro-ph
• Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation
  Multimodal foundation models have demonstrated strong generalization, yet their ability to transfer knowledge to specialized domains such as garment generation remains underexplored. We introduce VLG, a vision-language-garment model that synthesizes garments f…
  arxiv Jan Ackermann, Kiyohiro Nakayama, Guandao Yang, Tong Wu 等 2025-06-05T16:22:17Z 置信度 0.78 cs.CV