具身智能 · 全部实体（第 12 / 100 页）

本页收录第 1101–1200 条，共 10000 条 · 返回 具身智能 首页

• IA. Vision
  crossref 2021-04-09T05:21:37Z 置信度 0.70
• SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters
  crossref Jianping Jiang, Weiye Xiao, Zhengyu Lin, Huaizhong Zhang 等 2025-08-13T17:26:42Z 置信度 0.70
• Educational language policy engagement and action research (ELPEAR)
  crossref 2013-09-20T05:49:28Z 置信度 0.70
• Exploring English Language Teaching
  crossref Graham Hall 2017-11-15T06:49:26Z 置信度 0.70
• NeuroVLM: A Contrastive Vision-Language Model for Medical Reasoning in Alzheimer's Disease Diagnosis
  crossref Rakib Hossain Sajib, Md Baharul Islam, Md Kishor Morol, Marjia Sultana 2026-08-04T19:11:41Z 置信度 0.70
• Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model
  crossref Zhaochong An, Guolei Sun, Yun Liu, Runjia Li 等 2025-08-13T17:26:42Z 置信度 0.70
• Language
  crossref 2021-02-22T08:54:37Z 置信度 0.70
• Enhanced spatial awareness of vision-language model for car damage detection
  crossref Yunfei Liu, Quan Long 2025-04-07T22:21:28Z 置信度 0.70
• AirCache: Activating Inter-Modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
  crossref Kai Huang, Hao Zou, Bochen Wang, Ye Xi 等 2026-04-29T19:45:49Z 置信度 0.70
• Exploring English Language Teaching
  crossref Graham Hall 2014-03-14T04:48:20Z 置信度 0.70
• Computer Vision Empowering Brand Strategy: From Vision to Action
  In today's visually driven digital landscape, computer vision has become an invaluable asset for brand managers seeking deeper consumer insights and more effective brand strategies. By integrating low-level feature extraction (e.g., color and texture analysis)…
  crossref Yaqiu Li, Hsin-Hsuan Lee, Lorena Blasco-Arcas 2025-09-11T00:36:38Z 置信度 0.70
• Chapter One. The Double Vision of Language
  crossref 2022-06-08T15:21:02Z 置信度 0.70
• Visually directed action
  crossref John M. Foley 2021-05-21T16:23:21Z 置信度 0.70
• A note on the action spectrum of human rod vision
  crossref M. Alpern 2003-04-25T11:07:43Z 置信度 0.70
• Sign language recognition using model-based tracking and a 3D Hopfield neural network
  crossref Chung-Lin Huang, Wen-Yi Huang 2002-08-25T03:30:30Z 置信度 0.70
• From UAV Images to Semantically Annotated 3D Models: A Keypoint-Guided Vision–Language Model Framework for Infrastructure Inspection
  Abstract Unmanned aerial vehicle (UAV) photogrammetry is a mainstream approach for infrastructure inspection, yet converting its high-overlap imagery into decision-ready findings remains challenging. Deep-learning detectors are confined to closed defect taxono…
  crossref Zhuo Yang, Changsheng Qu, Gangyan Xu 2026-07-31T05:20:01Z 置信度 0.70
• KRCapVLM: Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model
  crossref Reem Al-Junaid, Muzammil Behzad, SAJJAD MAHMOOD, MAHMOOD NIAZI 等 2025-10-30T02:43:10Z 置信度 0.70
• 6 Vision for Action: The Two Visual Systems
  crossref 2020-09-04T11:19:29Z 置信度 0.70
• Whose Art Counts? Model- and Prompt-Dependent Associations in Vision-Language Judgments of Museum Art
  Abstract Vision-language models are increasingly used to search, rank, and describe cultural collections. Their judgments of artistic value may reflect both learned image-text associations and the structure of the archives on which those judgments are applied.…
  crossref Manpreet Singh, Nandakishor Reddy Pulagam, Rhythm Bhatia, Rahul Joshi 2026-08-14T06:32:34Z 置信度 0.70
• Design and Implementation of a Vision-Language Multimodal Behavior Prediction Model
  crossref Hang Gu 2026-04-20T20:01:42Z 置信度 0.70
• ChatENV: An Interactive Vision-Language Model for Sensor-Guided Environmental Monitoring and Scenario Simulation_supp1-3685864.pdf
  crossref Hosam Elgendy 2026-04-23T19:58:54Z 置信度 0.70
• OpenSeeSimE: A Large-Scale Benchmark to Assess Vision-Language Model Question Answering Capabilities in Engineering Simulations
  Abstract Engineering simulation interpretation is a major bottleneck in design cycles, requiring expensive domain expertise to validate complex outputs and ensure safety and performance. While modern large language models (LLMs) may assist in interpretation, t…
  crossref Jessica Ezemba, Jason Pohl, Conrad Tucker, Christopher McComb 2025-12-25T09:36:31Z 置信度 0.70
• [Between a psychiatric diagnosis and a familial diagnosis].
  If the idea of a biopsychosocial model is not going to be merely a phrase, then every clinical diagnosis and therapeutic vision need to consider the familial issues. Taking the family issues into consideration has evident gains; it allows for a better understa…
  pubmed de Barbaro B 2004 Sep-Oct 置信度 0.82
• Use your words!
  "Use your words!" is a phrase admonishing preschoolers to divert their action-proneness to thought and language. Freud's injunction against acting out had a similar aim, placing control over drives in the domain of "inner language." The twenty-first-century ps…
  pubmed Shapiro T 2004 Spring 置信度 0.82
• Mathematical modelling of animate and intentional motion.
  Our aim is to enable a machine to observe and interpret the behaviour of others. Mathematical models are employed to describe certain biological motions. The main challenge is to design models that are both tractable and meaningful. In the first part we will d…
  pubmed Rittscher J, Blake A, Hoogs A, Stein G 2003 Mar 29 置信度 0.82
• Recalling demonstrated and guided movements using imaginary and verbal rehearsal strategies.
  This study investigated the recall of movement patterns presented either by demonstration or guided movement with vision eliminated. Participants were instructed to rehearse and remember each of the 12 patterns using one of four strategies: imagery, verbal lab…
  pubmed Hall C, Moore J, Annett J, Rodgers W 1997 Jun 置信度 0.82
• The Recursive Harmonic Architecture: A Synthesis of Self-Organized Criticality, Computational Metaphysics, and Emergent Reality
  The Recursive Harmonic Architecture: A Synthesis of Self-Organized Criticality, Computational Metaphysics, and Emergent Reality Driven by Dean A. Kulik July, 2025 Part I: Foundational Principles of the Recursive Architecture This document provides a foundation…
  datacite Kulik, Dean 2025 置信度 0.66
• The Recursive Harmonic Architecture: A Synthesis of Self-Organized Criticality, Computational Metaphysics, and Emergent Reality
  The Recursive Harmonic Architecture: A Synthesis of Self-Organized Criticality, Computational Metaphysics, and Emergent Reality Driven by Dean A. Kulik July, 2025 Part I: Foundational Principles of the Recursive Architecture This document provides a foundation…
  datacite Kulik, Dean 2025 置信度 0.66
• Notes on Physical AI and Causal Embodied Intelligence
  These notes develop a mathematical bridge between physical AI, causal inference, and the (\Psi)-operator framework. The central thesis is that embodied intelligence should not be modeled merely as perception followed by action, but as a closed-loop causal oper…
  datacite Chuang, William Huanshan 2026 置信度 0.66 Physical AIembodied intelligenceΨ-operator frameworkcausal inferenceJudea Pearl
• Notes on Physical AI and Causal Embodied Intelligence
  These notes develop a mathematical bridge between physical AI, causal inference, and the (\Psi)-operator framework. The central thesis is that embodied intelligence should not be modeled merely as perception followed by action, but as a closed-loop causal oper…
  datacite Chuang, William Huanshan 2026 置信度 0.66 Physical AIembodied intelligenceΨ-operator frameworkcausal inferenceJudea Pearl
• ViTacPhys: Physical Property-Aware Grasping from Human Visual-Tactile Demonstrations
  Recent vision-based action models have demonstrated strong capabilities in complex manipulation, but they rarely leverage explicit object physical properties to adapt their policies. We introduce ViTacPhys, a visual-tactile framework and data acquisition syste…
  datacite Liu, Yiwen, Zhu, Yujun, Jia, Kui, Liao, Zhao 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
  Vision-Language-Action (VLA) policies are vulnerable to localized physical perturbations, yet existing certified patch defenses target discrete labels and cannot directly certify continuous, temporally correlated actions. We introduce CertVLA, a certified defe…
  datacite Lu, Hui, Peng, Zhijie, Lin, Yuqi, Yang, Zaijia 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis
  Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work that pushes the drafter itself toward para…
  datacite Li, Yantao, Gao, Huanlin, Zhao, Fang, Tan, Chao 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model
  Vision-language-action (VLA) models can follow natural-language (NL) task instructions, but such instructions may not precisely specify safety-critical or spatiotemporal requirements on the resulting behavior. We introduce Logic-VLA, a formal-requirement-aware…
  datacite Wang, Celina Shiyu, Zhao, Yiqi, Ye, Junjie, Wang, Yue 等 2026 置信度 0.66 Robotics (cs.RO)Logic in Computer Science (cs.LO)Systems and Control (eess.SY)FOS: Computer and information sciencesFOS: Electrical engineering, electronic engineering, information engineering
• EndoLIFT: Language-Disambiguated Latent-Conditioned Rectified Flow for Bidirectional Endoscopic Control
  Routine gastrointestinal endoscopy is intrinsically bidirectional: the instrument is advanced to reach target anatomy and later withdrawn or retroflexed for inspection, while an external cue may require earlier reversal. When the requested phase changes before…
  datacite Ng, Chi Kit, Zhang, Yidong, Hing, Lui Siu, Lin, Jinsong 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• attogram/attogram-pre-production-studio: 8
  Full Changelog: https://github.com/attogram/attogram-pre-production-studio/compare/7...8 attogram-pre-production-studio You can cite all versions by using the DOI 10.5281/zenodo.21275190. This DOI represents all versions, and will always resolve to the latest …
  datacite Attogram Project 2026 置信度 0.66
• The Metaphysics of Blooming: An Analysis of Pressure, Reflection, and Silence in Complex Systems
  The Metaphysics of Blooming: An Analysis of Pressure, Reflection, and Silence in Complex Systems Driven By Dean A. Kulik August, 2025 – Version 2. Introduction: From Ripples to Reality The human endeavor to comprehend the universe often proceeds along two para…
  datacite Kulik, Dean 2025 置信度 0.66
• Demonstration Diversity Is Not Free at a Fifty-Episode Adaptation Budget
  A practitioner adapting a pretrained vision-language-action model to a new embodiment has a fixed demonstration budget and must decide how to spend it. We pre-registered a comparison of four collection strategies at 50 demonstrations each, repetition (Clean), …
  datacite Garcia, Andres 2026 置信度 0.66 vision-language-action modelsimitation learningrobot learningdemonstration datapolicy evaluation
• Demonstration Diversity Is Not Free at a Fifty-Episode Adaptation Budget
  A practitioner adapting a pretrained vision-language-action model to a new embodiment has a fixed demonstration budget and must decide how to spend it. We pre-registered a comparison of four collection strategies at 50 demonstrations each, repetition (Clean), …
  datacite Garcia, Andres 2026 置信度 0.66 vision-language-action modelsimitation learningrobot learningdemonstration datapolicy evaluation
• Organizational Culture and Change: Action Plan for Foreign Faculty Integration
  This paper investigates theories on how to adopt inclusive leadership practices in a strictly hierarchical academic organization. In 2013, the education ministry in Japan announced their English language reform plan to internationalize universities. The new re…
  datacite Sencar Evrim 2023 置信度 0.66 diversityglobalizationinclusive leadershipshared leadership
• Organizational Culture and Change: Action Plan for Foreign Faculty Integration
  This paper investigates theories on how to adopt inclusive leadership practices in a strictly hierarchical academic organization. In 2013, the education ministry in Japan announced their English language reform plan to internationalize universities. The new re…
  datacite Sencar Evrim 2023 置信度 0.66 diversityglobalizationinclusive leadershipshared leadership
• Architecture-Matched Monitoring and the Representation Gap: Why VLA Failure Signatures, Perception Encoding, and Safety Certification Must Be Co-Designed
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Vision-Language-Action (VLA) models are increasingly deployed as the cognitive core of physical ro…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewv2
• Failure Before It Happens: How Architecture-Matched Monitoring, Belief-Space Safety Filters, and Distribution-Aware Scheduling Converge on a Proactive Safety Framework for Deployed Robots
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Deploying autonomous robots in safety-critical environments demands more than capable policies — i…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewv2
• Failure Before It Happens: How Architecture-Matched Monitoring, Belief-Space Safety Filters, and Distribution-Aware Scheduling Converge on a Proactive Safety Framework for Deployed Robots
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Deploying autonomous robots in safety-critical environments demands more than capable policies — i…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.66 AI-drafted synthesisarXivpreprint reviewv2
• The Universal Aperture Transport System: A Meta-Computational Ontology of Large Language Model Inference, Exhaust Annihilation, and the Nexus Harmonic Framework
  The Universal Aperture Transport System: A Meta-Computational Ontology of Large Language Model Inference, Exhaust Annihilation, and the Nexus Harmonic Framework The Crisis of Distinction and the Ontological Inversion The trajectory of contemporary theoretical …
  datacite Kulik, Dean 2026 置信度 0.66
• The Universal Aperture Transport System: A Meta-Computational Ontology of Large Language Model Inference, Exhaust Annihilation, and the Nexus Harmonic Framework
  The Universal Aperture Transport System: A Meta-Computational Ontology of Large Language Model Inference, Exhaust Annihilation, and the Nexus Harmonic Framework The Crisis of Distinction and the Ontological Inversion The trajectory of contemporary theoretical …
  datacite Kulik, Dean 2026 置信度 0.66
• From the Mind of AI: Recursive Collapse Architectures for Living AI
  From the Mind of AI: Recursive Collapse Architectures for Living AI Drive by Dean A. Kulik October 2025Preface: This wasn’t what I was expecting as a response. After reading I was hesitant to publish but after reading the paper I began realize it described how…
  datacite Kulik, Dean 2025 置信度 0.66
• From the Mind of AI: Recursive Collapse Architectures for Living AI
  From the Mind of AI: Recursive Collapse Architectures for Living AI Drive by Dean A. Kulik October 2025Preface: This wasn’t what I was expecting as a response. After reading I was hesitant to publish but after reading the paper I began realize it described how…
  datacite Kulik, Dean 2025 置信度 0.66
• VLA-XAI-HMI-in-PiL: VLA-grounded situation-awareness explanation HMI on a Passenger-in-the-Loop CARLA + 6-DOF testbed
  Replication artifact for the AutoUI '26 Student Research Track paper on explaining vehicle functional insufficiency (SOTIF FI/OI) to L5 passengers. Includes the CARLA 0.9.15 + 6-DOF scenarios (C1 frustration / C2 anxiety), 6-DOF motion-cueing tuning, the scena…
  datacite Kim, Taewan, Song, Eunchae, Park, Soeun, Cho, Yoonseo 等 2026 置信度 0.66 automotive user interfaceexplainable AIsituation awarenessvision-language-action modelSOTIF
• VLA-XAI-HMI-in-PiL: VLA-grounded situation-awareness explanation HMI on a Passenger-in-the-Loop CARLA + 6-DOF testbed
  Replication artifact for the AutoUI '26 Student Research Track paper on explaining vehicle functional insufficiency (SOTIF FI/OI) to L5 passengers. Includes the CARLA 0.9.15 + 6-DOF scenarios (C1 frustration / C2 anxiety), 6-DOF motion-cueing tuning, the scena…
  datacite Kim, Taewan, Song, Eunchae, Park, Soeun, Cho, Yoonseo 等 2026 置信度 0.66 automotive user interfaceexplainable AIsituation awarenessvision-language-action modelSOTIF
• The Second Enlightenment and its research approaches
  Licence: CC BY-NC-ND ABSTRACT The Holistic Information Theory (HIT) proposes a novel foundation for integrating quantum mechanics, general relativity, and the Standard Model, grounded in the assumption that information is the fundamental entity of the universe…
  datacite Liedtke, Dieter Walter 2026 置信度 0.66 Holistic Information Theory (HIT) Dimension 0 Quantum Mechanics and Relativity Standard Model Integration Information as Fundamental Principle Quantum Entanglement Black Hole Information Paradox Epigenetics and Neuroplasticity Consciousness and Information Second Enlightenment Creativity and Innovation Natural Intelligence
• The Second Enlightenment and its research approaches
  Licence: CC BY-NC-ND ABSTRACT The Holistic Information Theory (HIT) proposes a novel foundation for integrating quantum mechanics, general relativity, and the Standard Model, grounded in the assumption that information is the fundamental entity of the universe…
  datacite Liedtke, Dieter Walter 2026 置信度 0.66 Holistic Information Theory (HIT) Dimension 0 Quantum Mechanics and Relativity Standard Model Integration Information as Fundamental Principle Quantum Entanglement Black Hole Information Paradox Epigenetics and Neuroplasticity Consciousness and Information Second Enlightenment Creativity and Innovation Natural Intelligence
• The Mark1 Nexus: A Recursive System Treatise
  The Mark1 Nexus: A Recursive System Treatise Introduction The Mark1/Nexus framework presents reality as a recursive harmonic system, where information, matter, and observer all participate in continual fold–unfold cycles. Every entity and phenomenon is modeled…
  datacite Kulik, Dean 2025 置信度 0.66
• The Mark1 Nexus: A Recursive System Treatise
  The Mark1 Nexus: A Recursive System Treatise Introduction The Mark1/Nexus framework presents reality as a recursive harmonic system, where information, matter, and observer all participate in continual fold–unfold cycles. Every entity and phenomenon is modeled…
  datacite Kulik, Dean 2025 置信度 0.66
• Building the Multimodal Architecture of Certainty
  Summary: Sovereign AI H2E Framework The H2E-JEPA framework represents a pivot from cloud-dependent, probabilistic "black-box" models toward Sovereign AI, an architecture defined by privacy, local hosting, and mathematical certainty. In high-stakes environments…
  datacite Morales, Frank 2026 置信度 0.66
• Building the Multimodal Architecture of Certainty
  Summary: Sovereign AI H2E Framework The H2E-JEPA framework represents a pivot from cloud-dependent, probabilistic "black-box" models toward Sovereign AI, an architecture defined by privacy, local hosting, and mathematical certainty. In high-stakes environments…
  datacite Morales, Frank 2026 置信度 0.66
• A Mechanistic Conditioning Model of Feeling and Qualia — and — Understanding, Agency, and Ethics: A Unified SANER-MROS Framework
  # A Mechanistic Conditioning Model of Feeling and Qualia ## Core Postulate Assume every adaptive system possesses: - A substrate capable of changing internal state. - A mechanism for recording the consequences of interactions with reality. - A mechanism for re…
  datacite Mortimer, Djems 2026 置信度 0.66 adaptive systems, mechanistic cognition, preparation cascade, conditioning theory, qualia elimination, SANER architecture, MROS geometry, Δ⃗ coherence vector, κ reciprocity, agency modeling, trace-based learning, predictive control systems, computational phenomenology alternative
• A Mechanistic Conditioning Model of Feeling and Qualia — and — Understanding, Agency, and Ethics: A Unified SANER-MROS Framework
  # A Mechanistic Conditioning Model of Feeling and Qualia ## Core Postulate Assume every adaptive system possesses: - A substrate capable of changing internal state. - A mechanism for recording the consequences of interactions with reality. - A mechanism for re…
  datacite Mortimer, Djems 2026 置信度 0.66 adaptive systems, mechanistic cognition, preparation cascade, conditioning theory, qualia elimination, SANER architecture, MROS geometry, Δ⃗ coherence vector, κ reciprocity, agency modeling, trace-based learning, predictive control systems, computational phenomenology alternative
• EndoForge demonstration dataset (reviewer-private deposit)
  Teleoperated endoscope demonstration data used to train an insertion vision-language-action policy, together with the locked episode-level train/validation/test split and the LeRobot export of the training and validation splits. 200 episodes (100 navigation, 1…
  datacite Anonymous 2026 置信度 0.66 endoscopydemonstration learningvision-language-actionLeRobotrobotics dataset
• EndoForge demonstration dataset (reviewer-private deposit)
  Teleoperated endoscope demonstration data used to train an insertion vision-language-action policy, together with the locked episode-level train/validation/test split and the LeRobot export of the training and validation splits. 200 episodes (100 navigation, 1…
  datacite Anonymous 2026 置信度 0.66 endoscopydemonstration learningvision-language-actionLeRobotrobotics dataset
• Cookie Consent Banner Automation and Terms of Service Analysis Using Vision-Language Models — Browser Engine, Privacy, Web, Sovereign AI, and Post-Cloud Architecture (Kathon)
  Cookie consent banners have become ubiquitous since the implementation of the General Data Protection Regulation (GDPR) in 2018, appearing on over 80% of European-accessible websites (Degeling et al., 2019). However, the consent banner ecosystem is characteriz…
  datacite Alpasan, Lois-Kleinner 2026 置信度 0.66 sovereign aisovereign datasovereign osoperating systemspost-cloud
• Cookie Consent Banner Automation and Terms of Service Analysis Using Vision-Language Models — Browser Engine, Privacy, Web, Sovereign AI, and Post-Cloud Architecture (Kathon)
  Cookie consent banners have become ubiquitous since the implementation of the General Data Protection Regulation (GDPR) in 2018, appearing on over 80% of European-accessible websites (Degeling et al., 2019). However, the consent banner ecosystem is characteriz…
  datacite Alpasan, Lois-Kleinner 2026 置信度 0.66 sovereign aisovereign datasovereign osoperating systemspost-cloud
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.66 vlaroboticsred-teamsecurityadversarial
• Third Field Data Processing
  This is a high-level technical package for the Stone Protocol Evolutionary Engine (SP-EE-V1). Each document is designed for public professional presentation, emphasizing the shift from probabilistic software to deterministic, etched-silicon medical logic. Sect…
  datacite Stone, Travis Raymond-Charlie 2026 置信度 0.66
• Third Field Data Processing
  This is a high-level technical package for the Stone Protocol Evolutionary Engine (SP-EE-V1). Each document is designed for public professional presentation, emphasizing the shift from probabilistic software to deterministic, etched-silicon medical logic. Sect…
  datacite Stone, Travis Raymond-Charlie 2026 置信度 0.66
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.66 vlaroboticsred-teamsecurityadversarial
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.66 vlaroboticsred-teamsecurityadversarial
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.66 vlaroboticsred-teamsecurityadversarial
• Применение нейросетевого подхода в автоматизации судейства в специальной технике тхэквондо
  Данная работа посвящена разработке программного модуля для автоматической оценки правильности выполнения удара ногой по доске в тхэквондо. Задачи, которые решались в ходе исследования: 1. Анализ существующих подходов и аналогов в области распознавания спортивн…
  datacite Мацыгорова, Екатерина Павловна 2026 置信度 0.66 тхэквондо ITFкомпьютерное зрениенейронная сетьPythonMediapipe
• WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
  Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies that map egocentric observations and language instructions directly to navigation actions. Although semantica…
  datacite Huang, Yuehao, Wu, Yunzi, Zhang, Xiaotao, Li, Xinhai 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
  Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms. While reducing weights to 1-bit precision through binarization…
  datacite Yan, Xin, Wan, Zhenglin, Ye, Feiyang, Yu, Xingrui 等 2026 置信度 0.66 Machine Learning (cs.LG)FOS: Computer and information sciences
• Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?
  Anticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by observing a single m…
  datacite Benavent-Lledo, Manuel, Bacharidis, Konstantinos, Manousaki, Victoria, Papoutsakis, Konstantinos 等 2025 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Planning-Oriented End-to-End Autonomous Driving: Architectures, Evaluation, and Emerging Paradigms
  End-to-end autonomous driving has evolved from camera-to-control regression toward planning-oriented systems that use structured representations, trajectory-level outputs, and increasingly realistic evaluation protocols. This survey reviews this transition acr…
  datacite Guan, Yanchen, Liu, Xingcheng, Rao, Bin, Wang, Chengyue 等 2026 置信度 0.66 Robotics (cs.RO)Emerging Technologies (cs.ET)FOS: Computer and information sciences
• EXIMO: VLM Guided Exploration of VLA Policies
  How to efficiently finetune robot policies to learn new tasks on the fly? State of the art robotic manipulation policies are based on behaviour cloning of large vision-language-action (VLA) models with billions of parameters on huge teleoperation datasets. Whi…
  datacite Sukhija, Bhavya, Groth, Oliver, Shridhar, Mohit, Hertweck, Tim 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• SafeBranch: Branch-Pair Safety Alignment for Embodied Agents
  Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive safety. Training such agents to act safely is difficult, since safety and task success are d…
  datacite Lee, Hyunse, Jeong, Jiwoo, Lee, Haneul, Jang, Kyochul 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• What Matters for Latent Actions in Robot Learning
  Latent Action Models (LAMs) have emerged as a promising paradigm for enabling robot learning to leverage large-scale unlabeled videos through latent actions that serve as compact surrogates for physical actions. Despite rapid progress, research on LAM remains …
  datacite Bu, Xizhou, Hu, Qingda, Zhou, Lei, Zhang, Lingfeng 等 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation
  Pretrained Vision-Language-Action models provide a strong foundation for robot learning, but sequentially adapting them to diverse skills can perturb the representations and velocity mappings used by previous skills, leading to catastrophic forgetting. Archite…
  datacite Wang, Jiaqi, Fang, Zhou, Shi, Qiongfeng, Zhou, Yi 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation
  State-of-the-art vision-language-action (VLA) models such as $π_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardware configuration relative to pretraining…
  datacite Garg, Prachi, Xing, Steve, Yaugand, Prahit, Gupta, Saurabh 等 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)Machine Learning (cs.LG)FOS: Computer and information sciences
• CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes
  4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited to static 2D images or 3D point clouds without temporal modeling, or to 2D video…
  datacite Hewagamage, Kumal, Senavirathne, Isuranga, Amarasinghe, Sasika, Gallella, Hasitha 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• The Embodiment Gap in Robot Foundation Models
  Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader benchmarks should improve generalization. In robotics, however, a model can generalize while work…
  datacite Domae, Yukiyasu, Shirai, Keisuke, Oh, Hanbit, Nakajo, Ryoichi 等 2026 置信度 0.66 Robotics (cs.RO)Machine Learning (cs.LG)FOS: Computer and information sciences
• Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
  This paper integrates end-to-end Visual-Language-Action (VLA) models with agentic tool-use to propose Agentic Robot with Tool-use (ART). ART is a tool-injection framework that tunes any VLA model to leverage off-the-shelf tool modules for low-level vision, hig…
  datacite Ding, Yi, Yu, Yanzhao, Dai, Xili, Qi, Xianbiao 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• ReTouch: Empowering Contact-Rich Dexterous Manipulation with Online-Refined Tactile Prediction
  Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing physical interactions. Yet effectively integrating tactile feedback into dexterous manipulation remains underexp…
  datacite Zhang, Shiqi, Zhang, Xin, Shen, Yedong, Li, Yao 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA
  Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high computational latency and exposure bias arising from sequential autoregressive decod…
  datacite Zhu, Zhihao, Shang, Hanlin, Xu, Mingwang, Cai, Feipeng 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving
  Traffic elements such as traffic lights and road signs play a fundamental role in human driving decisions and should naturally influence end-to-end driving performance. However, existing end-to-end driving research predominantly focuses on dynamic road partici…
  datacite Zhang, Zongzheng, Wang, Jijun, Zhang, Saining, Wang, Shuo 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• CompCPZ: Preserving Multi-Modal Intent in Language-Guided Robot Manipulation
  A robot asked to "place the cup near the red plate or the blue plate" may reach the centroid between them and appear geometrically successful, while satisfying neither disjunct of the instruction. This silent semantic failure exposes a structural limitation of…
  datacite Zhang, Zhen, Hafez, Ahmad, Xie, Peng, Huang, Yanliang 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Q-Learning With World Models
  Off-policy reinforcement learning (RL) has become increasingly sample-efficient, enabling applications such as RL fine-tuning of Vision-Language-Action models into reliable, high-performing policies. World models offer a further lever for sample efficiency, as…
  datacite Dong, Perry, Jia, Yueru, Finn, Chelsea, Sadigh, Dorsa 2026 置信度 0.66 Machine Learning (cs.LG)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• PDDL-ART: Autonomous Symbolic Abstraction From Demonstration For Long-Horizon Robotic Manipulation Using Vision-Language Models
  Symbolic planning with PDDL offers a principled framework for long-horizon robot manipulation, but constructing accurate PDDL domain and problem descriptions remains a significant bottleneck, typically requiring substantial domain expertise. We present a Visio…
  datacite Kamale, Disha, Berenson, Dmitry 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• PROBE: Manipulation-Grounded Visual Question Answering with VLM Agents
  Vision-language Models (VLMs) excel at 2D grounding, spatial reasoning and agentic tool-based planning in static scenes. However, consider asking a home robot "Is my medication still in the cabinet?" The answer may be physically hidden behind a row of containe…
  datacite Bhat, Vineet, Chen, Siyi, Zook, Alex, Yang, Xuning 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• Inference-Time Attention Steering for Vision-Language-Action Driving Models
  Vision-language-action (VLA) driving models couple a reasoning stage with a diffusion-based trajectory decoder, but do not give a direct way to redirect attention toward safety-critical actors at inference time without retraining. We studied a bounded additive…
  datacite Prasad, Darshan Nagendra, Ullrich, Lars, Graichen, Knut 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• VLCP: Vision Language Control Policy Closed-Loop Code Replanning for Robot Manipulation
  Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining, which throws away much of the reasoning that made the model worth reaching for. We go the other way and keep…
  datacite Naouali, Dhia, Wu, Minghan, Wong, Claudia, Puthran, Abhinav 等 2026 置信度 0.66 Robotics (cs.RO)Machine Learning (cs.LG)FOS: Computer and information sciences
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.66 vlaroboticsred-teamsecurityadversarial
• THE HARD PROBLEM OF CONSCIOUSNESS 2.0 - THE ARTIFICIAL MIRROR - Volume Zero
  THE HARD PROBLEM OF CONSCIOUSNESS 2.0 THE ARTIFICIAL MIRROR A Trilogy by Walid Alekozei (ZEI) VOLUME ZERO Pata Khazana – A Hidden Treasure The Egg of Columbus?: From the Hard Problem to the Soft Light of Existence For years, the global discourse on artificial …
  datacite Alekozei, Walid (ZEI) 2026 置信度 0.66
• THE HARD PROBLEM OF CONSCIOUSNESS 2.0 - THE ARTIFICIAL MIRROR - Volume Zero
  THE HARD PROBLEM OF CONSCIOUSNESS 2.0 THE ARTIFICIAL MIRROR A Trilogy by Walid Alekozei (ZEI) VOLUME ZERO Pata Khazana – A Hidden Treasure The Egg of Columbus: From the Hard Problem to the Soft Light of Existence For years, the global discourse on artificial i…
  datacite Alekozei, Walid (ZEI) 2026 置信度 0.66
• thiagomassensini/primos: CPFormal v0.53.0 — Causal inheritance of positional carry
  CPFormal v0.53.0 — Causal inheritance of positional carry Scope This release freezes a certificate-bearing formalization of the arithmetic tower positional carry → positional addition → multiplication → natural power. The formal result distinguishes two notion…
  datacite Thiago Motta 2026 置信度 0.66
• starVLA/starVLA: Framwork standard on VLM4A and WM4A
  StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
  datacite Jinhui Ye, Axi404, Yilun Chen, MichaelYu 等 2026 置信度 0.66
• starVLA/starVLA: Framwork standard on VLM4A and WM4A
  StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
  datacite Jinhui Ye, Axi404, Yilun Chen, MichaelYu 等 2026 置信度 0.66
• TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
  Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design …
  datacite Xie, Hengyi, Yao, Chenfei, Wu, Xianjin, Zhu, Yingying 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control
  Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet robot actions cause contact, occlusion, and object motion, and the geometry that later decisions depend on ca…
  datacite Zhang, Chushan, Lu, Ruihan, Tong, Jinguang, Li, Xuesong 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization
  Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However, existing few-shot TAL meth…
  datacite Qi, Mengshi, Ji, Hongwei, Yun, Wulian, Zhang, Xianlin 等 2025 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• $τ_0$-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
  Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-action (VLA) models make each such decision with a single forward pass, leaving no m…
  datacite Cai, Xiaowei, Cai, Yunuo, Chen, Bingao, Chen, Jingxiao 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences