具身智能 · 全部实体（第 89 / 100 页）

本页收录第 8801–8900 条，共 10000 条 · 返回 具身智能 首页

• VLA-MP: A Vision-Language-Action Framework for Multimodal Perception and Physics-Constrained Action Generation in Autonomous Driving.
  Autonomous driving in complex real-world environments requires robust perception, reasoning, and physically feasible planning, which remain challenging for current end-to-end approaches. This paper introduces VLA-MP, a unified vision-language-action framework …
  europepmc Maoning Ge, Kento Ohtani, Yingjie Niu, Yuxiao Zhang 等 2025 置信度 0.80
• An Open Pharma Vision for company-sponsored biomedical research publications.
  europepmc 2026 置信度 0.80
• Transitioning to a Flexible, Tiered, Developmentally Informed Same-Day Screening Model for Preschoolers in Low-Resource Settings.
  europepmc 2026 置信度 0.80
• The impact of linguistic features on CTR in Instagram ads: A study of supplement and cosmetic products.
  europepmc 2026 置信度 0.80
• How can reasoning capability empower the AI copilot robot in endoscopic surgery.
  europepmc 2026 置信度 0.80
• Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation.
  Considering how to make the model accurately understand and follow natural language instructions and perform actions consistent with world knowledge is a key challenge in robot manipulation. This mainly includes human fuzzy instruction reasoning and the follow…
  pubmed Ren P, Zhang K, Zheng H, Li Z 等 2025 置信度 0.82
• Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views.
  europepmc 2026 置信度 0.80
• The Informational Cost of Agency: A Bounded Measurement Layer for Deployed Reinforcement Learning
  europepmc 2026 置信度 0.80
• Both ends of artificial intelligence impacting privacy: a review of violation and protection.
  europepmc 2026 置信度 0.80
• Tensor language model enables generative scheduling for efficient tensor compilation.
  europepmc 2026 置信度 0.80
• Precision oncology: from large language models to multi-agent systems.
  With the rapid growth of electronic health records, medical imaging, and high-throughput omics data, precision oncology faces increasing demands for cross-modal information integration and complex clinical decision support. In recent years, large language mode…
  europepmc 2026 置信度 0.80
• Generative Artificial Intelligence and Large Language Models in Clinical Oncology.
  europepmc 2026 置信度 0.80
• Real-Time Target-Oriented Grasping Framework for Resource-Constrained Robots.
  europepmc 2026 置信度 0.80
• Large Language Models Estimate Fine-Grained Human Color-Concept Associations.
  europepmc 2026 置信度 0.80
• When intelligence begins to act: a thoughtful appraisal of agentic AI in biomedicine.
  The expanding role of intelligent systems in biomedical science marks a shift from passive analysis towards active participation in discovery and care. Recent scholarship has begun to frame these systems not merely as models, but as agents capable of planning,…
  europepmc 2026 置信度 0.80
• The role of vocabulary concreteness in modulating embodied semantic representations in learners of Chinese as a foreign language.
  europepmc 2026 置信度 0.80
• InfoMSD: an information-maximization self-distillation framework for parameter-efficient fine-tuning on artwork images.
  europepmc 2026 置信度 0.80
• Exploring vision transformers for deep feature extraction and classification in video genre recognition for digital media.
  europepmc 2026 置信度 0.80
• Predicting Momentary Suicidal Ideation From Smartphone Screenshots Using Vision-Language Models: Prospective Machine Learning Study.
  europepmc 2026 置信度 0.80
• Will multimodal large language models ever achieve deep understanding of the world?
  europepmc 2025 置信度 0.80
• Shared leadership team: the creation, journey, lessons learned.
  europepmc 2026 置信度 0.80
• Toward Accurate Procedure Planning in Instructional Videos: Visual State Generation Helps Task-Selective Diffusion.
  europepmc 2026 置信度 0.80
• CA-VLN: Collaborative Agents in MLLM-Powered Visual-Language Navigation.
  europepmc 2026 置信度 0.80
• Vision-Language Models for Transmission Line Fault Detection: A New Approach for Grid Reliability and Optimization.
  europepmc 2026 置信度 0.80
• MoE-based multimodal alignment for vocal metaverse classrooms.
  europepmc 2026 置信度 0.80
• Active Vision in Driving: Joint Modeling of Scanpaths and Risk Perception.
  europepmc 2026 置信度 0.80
• Contrastive language image pretraining for a cardiac magnetic resonance image embedding with zero-shot capabilities.
  europepmc 2026 置信度 0.80
• Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy.
  With the rapid advancement of artificial intelligence and robotics, the integration of Large Language Models (LLMs) with 3D vision is emerging as a transformative approach to enhancing robotic sensing technologies. This convergence enables machines to perceive…
  pubmed Mehta V, Sharma C, Thiyagarajan K 2025 置信度 0.82
• Artificial Intelligence in Minimally Invasive and Robotic Gastrointestinal Surgery: Major Applications and Recent Advances.
  europepmc 2026 置信度 0.80
• Contextual assembly of lexical functions in large language models.
  europepmc 2025 置信度 0.80
• Hierarchical Compositional Alignment for Zero-Shot Part-Level Segmentation.
  europepmc 2026 置信度 0.80
• A Systematic Literature Review on Integrated Deep Learning and Multiagent Vision-Language Frameworks for Pathology Image Analysis and Report Generation.
  This systematic literature review investigates the integration of deep learning (DL), vision-language models (VLMs), and multiagent systems in the analysis of pathology images and automated report generation. The rapid advancement of whole-slide imaging (WSI) …
  europepmc 2026 置信度 0.80
• Sign2Story: A Multimodal Framework for Near-Real-Time Hand Gestures via Smartphone Sensors to AI-Generated Audio-Comics.
  europepmc 2026 置信度 0.80
• Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
  europepmc 2026 置信度 0.80
• Deep learning-based robotic cloth manipulation applications: systematic review, challenges and opportunities for physical AI.
  europepmc 2026 置信度 0.80
• Establishing AI-driven evaluation standards and human-in-the-loop guidance for digital first aid education: a perspective.
  europepmc 2026 置信度 0.80
• Artificial intelligence in rehabilitation: a review of clinical effectiveness, real-world performance, safety, and equity across modalities and settings.
  europepmc 2026 置信度 0.80
• Persuading large language models to comply with objectionable requests.
  europepmc 2026 置信度 0.80
• The Cross-Linguistic Coordination of Overt Attention and Speech Production as Evidence for a Language of Vision.
  europepmc 2026 置信度 0.80
• LLaVA-Pose: Keypoint-Integrated Instruction Tuning for Human Pose and Action Understanding.
  europepmc 2025 置信度 0.80
• Involving Citizens in Integrated Care. Lessons Learned Through Participatory Action Research in Three Communities in the Netherlands.
  europepmc 2026 置信度 0.80
• Hierarchical Prototype Alignment for Video Temporal Grounding.
  europepmc 2026 置信度 0.80
• The influence of aspect markers and tense on the action-sentence compatibility effect in Mandarin action sentence comprehension.
  europepmc 2026 置信度 0.80
• Transcendental model selection: a computational account of symbolic cognition and general intelligence through morality and culture.
  General intelligence enables flexible problem solving across diverse contexts by minimizing uncertainty. Symbolic systems such as language extend this capacity, allowing humans to build social groups and construct world models beyond typical biological constra…
  europepmc 2026 置信度 0.80
• Artificial Intelligence in Botulinum Toxin Injections: A Mini-Review of Current Applications, Challenges, and Translational Perspectives.
  europepmc 2026 置信度 0.80
• ToggleMimic: A Two-Stage Policy for Text-Driven Humanoid Whole-Body Control.
  europepmc 2025 置信度 0.80
• Identification of Risk Factors for Glaucoma Progression in Free-Text Clinical Notes Using a Local Large Language Model.
  europepmc 2026 置信度 0.80
• Perception, assessment, and coaching: a systematic review and taxonomy of computer vision-based physical rehabilitation techniques.
  The digital transformation of rehabilitation training has become a public health imperative driven by a global demand that outstrips professional medical resources and is compounded by a deficit in public rehabilitation literacy. As traditional hospital-centri…
  pubmed Ye P, Li Y, Qu M, Liu J 等 2026 置信度 0.82
• EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos.
  Analyzing hand-object interaction in egocentric vision facilitates VR/AR applications and human-robot policy transfer. Existing research has mostly focused on modeling the behavior paradigm of interactive actions (i.e., "how to interact"). However, the more ch…
  pubmed Ma J, Zhang E, Zheng YD, Xie Y 等 2026 Jul 29 置信度 0.82
• Fine-Grained Self-Paced Relational Preserving Network for Cross-Domain Few-Shot Facial Expression Recognition.
  Cross-domain few-shot facial expression recognition (CF-FER) aims to adapt models trained on basic expressions to recognize novel compound expressions using only a few annotated examples. Although vision-language models (VLMs) have shown promise in few-shot le…
  pubmed Wang K, Ding R, Wang H, Yan Y 2026 置信度 0.82
• A Lightweight Vision-Language-Action Policy with Progress-Aware Hybrid Execution for UAV Waypoint Navigation in AirSim.
  Offline action prediction does not by itself guarantee reliable closed-loop flight for unmanned aerial vehicle (UAV) vision-language-action (VLA) models. We study a controlled AirSim Blocks waypoint task using 100 expert episodes and 3385 RGB-D, instruction, s…
  pubmed Xu Y, Lin H, Yang Y, Xia J 等 2026 Jul 22 置信度 0.82
• Review: Techniques in Egocentric Multi-View Image Analysis: Advances, Challenges, and Future Directions.
  Egocentric multi-view image analysis refers to the processing of utilizing synchronized video streams captured from multiple wearable cameras worn on the head or body, providing complementary first-person perspectives of dynamic, real-world interactions. Unlik…
  pubmed Phan DT, Nguyen HD 2026 Jul 17 置信度 0.82
• The rise of AI companions: From prediction to surgery in the digital twin era.
  Artificial intelligence (AI) is rapidly reshaping orthopaedic surgery, supported by advances in data science, computational power, and perioperative digitalization. Within this evolving landscape, five "AI companions" structure the surgeon's workflow. The "AI …
  pubmed Gauci MO, Duval G, Rony L 2026 Jul 16 置信度 0.82
• Facial Expression Metrics as Digital Biomarkers of Neurologic Disease.
  Facial movements can be key indicators of neurological health and emotional state, offering insights into motor and neuropsychiatric functions that are disrupted in neurologic disorders. Neurological disease can present with characteristic differences in facia…
  pubmed Nylander A, Poole S, Hsu NS, Henderson K 等 2025 Dec 置信度 0.82
• Integrating Agglomerative Perception with One-step Action Generation for Robotic Manipulation.
  Developing generalizable robotic policies that balance inference efficiency, manipulation accuracy, and robustness remains a formidable challenge. Existing Vision-Language-Action models demand prohibitive data scales, while keyframe-based approaches struggle t…
  pubmed Wang S, Wang L, Huo H, Zhou S 等 2026 Jul 13 置信度 0.82
• OmniPathoVQA: Benchmarking pathology vision-language models with Encyclopedia-scale knowledge.
  Pathology vision-language models (VLMs) are promising for building the clinical decision support systems. However, a key barrier to real-world clinical deployment lies in the lack of rigorous and clinically meaningful model evaluation. Existing pathology visua…
  pubmed Chen K, Wei L, Rui S, Yuan Y 等 2026 Sep 置信度 0.82
• Global, regional, and national burden of tuberculosis and multidrug-resistant tuberculosis by HIV status, 1990-2023: a systematic analysis for the Global Burden of Disease Study 2023.
  Tuberculosis (TB) is the leading global cause of death from a single infectious agent. Recent reductions in global health funding have threatened TB control, making comprehensive assessment of TB, HIV-related TB, and drug-resistant TB burdens before these disr…
  pubmed GBD 2023 TB HIV Collaborators 2026 Jul 1 置信度 0.82
• A Survey on Vision--Language--Action Models for Embodied AI
  Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language model…
  pubmed Yueen Ma, Zixing Song, Yuzheng Zhuang, Jianye Hao 等 2026 置信度 0.82 Embodied cognitionAction (physics)Computer scienceCognitive scienceArtificial intelligence
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
  We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control to boost generalization and enable emergent semantic reasoning. Our goal is to enable a single end-to-end trained model to both lear…
  openalex Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar 等 2023-07-28 置信度 0.72 Computer scienceNatural languageArtificial intelligenceRobotGeneralization
• Learning Transferable Visual Models From Natural Language Supervision
  State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concep…
  openalex Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等 2021-02-26 置信度 0.72 Computer scienceArtificial intelligenceGeneralityTransfer of learningTask (project management)
• TinyVLA: Toward 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 2025-02-24 置信度 0.72 Action (physics)Computer scienceArtificial intelligenceHuman–computer interactionComputer vision
• OpenVLA: An Open-Source Vision-Language-Action Model
  Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-langua…
  openalex Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao 等 2024-06-13 置信度 0.72 Open sourceAction (physics)Computer scienceArtificial intelligenceProgramming language
• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
  Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual …
  openalex Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson 等 2017-02-06 置信度 0.72 Artificial intelligenceComputer scienceNatural language processingGenomeImage (mathematics)
• FAST: Efficient Action Tokenization for Vision-Language-Action Models
  Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously effective for capturing complex and generalizable robotic behaviors.However, such models require us to choose a tokenization of our continuous …
  openalex Karl Pertsch, Kyle Stachowicz, Brian Ichter, Danny Driess 等 2025-06-21 置信度 0.72 Computer scienceAction (physics)Artificial intelligenceNatural language processingFeature (linguistics)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
  Vision-language-action models (VLAs) have shown potential in leveraging pretrained vision-language models and diverse robot demonstrations for learning generalizable sensorimotor control. While this paradigm effectively utilizes large-scale data from both robo…
  openalex Qingqing Zhao, Yao Lu, Moo Jin Kim, Zipeng Fu 等 2025-06-10 置信度 0.72 Computer scienceAction (physics)Cognitive scienceChain (unit)Artificial intelligence
• Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  Amid growing efforts to leverage advances in large language models (LLMs) and visionlanguage models (VLMs) for robotics, Vision-Language-Action (VLA) models have recently gained significant attention. By unifying vision, language, and action data at scale, whi…
  openalex Kento Kawaharazuka, Jihoon Oh, Jun Yamada, Ingmar Posner 等 2025-01-01 置信度 0.72 Computer scienceLeverage (statistics)Software deploymentScalabilityRobot
• Internet of Things (IoT): A vision, architectural elements, and future directions
  openalex Jayavardhana Gubbi, Rajkumar Buyya, Slaven Marusic, Marimuthu Palaniswami 2013-02-24 置信度 0.72 Computer scienceInternet of ThingsThe InternetMultimediaWorld Wide Web
• Grounding language in action
  openalex Arthur M. Glenberg, Michael P. Kaschak 2002-09-01 置信度 0.72 SentenceEmbodied cognitionComprehensionPsychologyMeaning (existential)
• π₀: A Vision-Language-Action Flow Model for General Robot Control
  openalex Kevin Black, Noah Brown, Danny Driess, A. Esmail 等 2025-06-21 置信度 0.72 Computer scienceControl theory (sociology)RobotControl engineeringControl (management)
• Training language models to follow instructions with human feedback
  Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these models are not aligned…
  openalex Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida 等 2022-03-04 置信度 0.72 Computer scienceLanguage modelSet (abstract data type)Simple (philosophy)Reinforcement learning
• Very Deep Convolutional Networks for Large-Scale Image Recognition
  In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) c…
  openalex Karen Simonyan, Andrew Zisserman 2014-09-04 置信度 0.72 Computer scienceConvolution (computer science)Convolutional neural networkArtificial intelligenceDeep learning
• QUAR-VLA: Vision-Language-Action Model for Quadruped Robots
  openalex Pengxiang Ding, Han Zhao, Wenjie Zhang, Wenxuan Song 等 2024-10-29 置信度 0.72 Computer scienceRobotAction (physics)Artificial intelligenceComputer vision
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
  NVIDIA https://navila-bot.github.ioMove forward out of the room.Turn right at the end.Proceed to the grass and stop in front of the soccers.Walk forward along the way.Turn a little left and keep going straight.Stop in front of the red door.Turn left immediatel…
  openalex An‐Chieh Cheng, Yandong Ji, Zhaojing Yang, Zaitian Gongye 等 2025-06-21 置信度 0.72 Legged robotComputer scienceRobotArtificial intelligenceComputer vision
• Large language models encode clinical knowledge
  Abstract Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to ad…
  openalex Karan Singhal, Shekoofeh Azizi, Tao Tu, S. Sara Mahdavi 等 2023-07-12 置信度 0.72 Computer scienceBenchmark (surveying)Language modelComprehensionArtificial intelligence
• Information-theoretic graph fusion with vision-language-action model for policy reasoning and dual robotic control
  openalex Shunlei Li, Longsen Gao, Jin Wang, Chang Che 等 2026-01-29 置信度 0.72 Computer scienceArtificial intelligenceVisual reasoningRobotTransformer
• Bi-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Dexterous Manipulations
  This research introduces the Bi-VLA (Vision-Language-Action) model, a novel system designed for bimanual robotic dexterous manipulation that seamlessly integrates vision for scene understanding, language comprehension for translating human instructions into ex…
  openalex Koffivi Fidèle Gbagbe, Miguel Altamirano Cabrera, Ali Alabbas, Oussama Alyunes 等 2024-10-06 置信度 0.72 Computer scienceAction (physics)Computer visionArtificial intelligenceHuman–computer interaction
• The job demands-resources model of burnout.
  The job demands-resources (JD-R) model proposes that working conditions can be categorized into 2 broad categories, job demands and job resources. that are differentially related to specific outcomes. A series of LISREL analyses using self-reports as well as o…
  openalex Evangelia Demerouti, Arnold B. Bakker, Friedhelm Nachreiner, Wilmar B. Schaufeli 2001-06-01 置信度 0.72 LISRELDisengagement theoryBurnoutPsychologyOccupational burnout
• VisualBERT: A Simple and Performant Baseline for Vision and Language
  We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an associated input image with s…
  openalex Liunian Harold Li, Mark Yatskar, Da Yin, Cho‐Jui Hsieh 等 2019-08-09 置信度 0.72 Computer scienceTransformerImage (mathematics)Language understandingBaseline (sea)
• ShowUI: One Vision-Language-Action Model for GUI Visual Agent
  Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they …
  openalex Kevin Qinghong Lin, Linjie Li, Difei Gao, Zhengyuan Yang 等 2025-06-10 置信度 0.72 Computer scienceAction (physics)Artificial intelligenceHuman–computer interactionProgramming language
• Improving Vision-Language-Action Model with Online Reinforcement Learning
  Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models. Although the VLA models …
  openalex Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji 等 2025-05-19 置信度 0.72 Reinforcement learningComputer scienceAction (physics)Artificial intelligenceHuman–computer interaction
• 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 Sicong Jiang, Menglin Kong, Yihong Tang, Lijun Sun 等 2025-10-19 置信度 0.72 Computer scienceTRACE (psycholinguistics)Control (management)Measure (data warehouse)Human–computer interaction
• MoManipVLA: Transferring Vision-language-action Models for General Mobile Manipulation
  Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation approaches often struggle to generalize across different tasks and environments becau…
  openalex Zhenyu Wu, Yuheng Zhou, Xiuwei Xu, Ziwei Wang 等 2025-06-10 置信度 0.72 Computer scienceAction (physics)Human–computer interactionArtificial intelligenceComputer vision
• PointVLA: Injecting the 3D World Into Vision-Language-Action Models
  Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with 3D data is computat…
  openalex Chengmeng Li, Junjie Wen, Yaxin Peng, Yan Peng 等 2026-01-12 置信度 0.72 Computer sciencePoint cloudArtificial intelligenceKey (lock)Table (database)
• Internet of things: Vision, applications and research challenges
  openalex Daniele Miorandi, Sabrina Sicari, Francesco De Pellegrini, Imrich Chlamtac 2012-04-21 置信度 0.72 Software deploymentThe InternetRealmComputer scienceInternet of Things
• LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action
  Goal-conditioned policies for robotic navigation can be trained on large, unannotated datasets, providing for good generalization to real-world settings. However, particularly in vision-based settings where specifying goals requires an image, this makes for an…
  openalex Dhruv Shah, Błażej Osiński, Brian Ichter, Sergey Levine 2022-07-10 置信度 0.72 Computer scienceGeneralizationInterface (matter)Modality (human–computer interaction)Code (set theory)
• Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
  A practical navigation agent must be capable of handling a wide range of interaction demands, such as following instructions, searching objects, answering questions, tracking people, and more. Existing models for embodied navigation fall short of serving as pr…
  openalex Jiazhao Zhang, Kunyu Wang, Shaoan Wang, Minghan Li 等 2025-06-21 置信度 0.72 Computer scienceEmbodied cognitionArtificial intelligenceHuman–computer interactionField (mathematics)
• A Survey of Large Language Models
  Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advan…
  openalex Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang 等 2026-05-09 置信度 0.72 Language modelComputer scienceMainstreamScale (ratio)Artificial intelligence
• VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation
  The rapid advancement of generative AI and multi-modal foundation models has shown significant potential in advancing robotic manipulation. Vision-language-action (VLA) models, in particular, have emerged as a promising approach for visuomotor control by lever…
  openalex Zhijie Wang, Zhehua Zhou, Jiayang Song, Yuheng Huang 等 2025-06-19 置信度 0.72 Computer scienceRobustness (evolution)Artificial intelligenceSoftware deploymentMachine learning
• A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter
  We focus on the task of language-conditioned grasping in clutter, in which a robot is supposed to grasp the target object based on a language instruction. Previous works separately conduct visual grounding to localize the target object, and generate a grasp fo…
  openalex Kechun Xu, Shuqi Zhao, Zhongxiang Zhou, Zizhang Li 等 2023-05-29 置信度 0.72 Computer scienceGRASPClutterArtificial intelligenceObject (grammar)
• RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
  A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) …
  openalex Jiaming Liu, Mengzhen Liu, Zhenyu Wang, Pengju An 等 2024 置信度 0.72 State spaceSpace (punctuation)RobotComputer scienceState (computer science)
• ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model
  Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen, Ning Liu, Zhiyuan Xu, Weibin Meng, Yaxin Peng, Chaomin Shen, Feifei Feng, Yi Xu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
  openalex Zhongyi Zhou, Yichen Zhu, Minjie Zhu, Junjie Wen 等 2025-01-01 置信度 0.72 Computer scienceArtificial intelligenceControl (management)RobotNatural language
• Evaluating Large Language Models Trained on Code
  I created a basic proof of concept of LMVM (Language Model Virtual Machine), a command line toolchain that English instructions into native binaries without intermediary high-level language compilation. The command line uses a large language model (LLM) as IR …
  openalex Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan 等 2021-07-07 置信度 0.72 CorrectnessPython (programming language)Computer scienceCode (set theory)Programming language
• Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action
  We present Unified-IO 2,the. first autoregressive multi-modal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs - images, text, audio, action, bounding boxes etc.…
  openalex Jiasen Lu, Christopher M. Clark, Sang-Ho Lee, Zichen Zhang 等 2024-06-16 置信度 0.72 Computer scienceAutoregressive modelAction (physics)Speech recognitionAudio visual
• Attention mechanisms in computer vision: A survey
  Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism …
  openalex Meng-Hao Guo, Tian-Xing Xu, Jiangjiang Liu, Zheng-Ning Liu 等 2022-03-15 置信度 0.72 Computer scienceCategorizationArtificial intelligenceComputer graphicsProcess (computing)
• Gradient-based learning applied to document recognition
  Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a comp…
  openalex Yann LeCun, Léon Bottou, Yoshua Bengio, Patrick Haffner 1998-01-01 置信度 0.72 Computer scienceArtificial intelligenceConvolutional neural networkIntelligent character recognitionHandwriting recognition
• Unified Vision-Language Pre-Training for Image Captioning and VQA
  This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it us…
  openalex Luowei Zhou, Hamid Palangi, Lei Zhang, Houdong Hu 等 2020-04-03 置信度 0.72 Closed captioningComputer scienceTransformerQuestion answeringLanguage model
• Flamingo: a Visual Language Model for Few-Shot Learning
  Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose k…
  openalex Alayrac, Jean-Baptiste, Jeff Donahue, Pauline Luc, Antoine Miech 等 2022-04-29 置信度 0.72 Computer scienceClosed captioningContext (archaeology)Flexibility (engineering)Variety (cybernetics)
• Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: a systematic review and meta-analysis
  BACKGROUND: Global and regional prevalence estimates for blindness and vision impairment are important for the development of public health policies. We aimed to provide global estimates, trends, and projections of global blindness and vision impairment. METHO…
  openalex Rupert Bourne, Seth Flaxman, Tasanee Braithwaite, Maria Vittoria Cicinelli 等 2017-08-03 置信度 0.72 Visual impairmentVisual acuityPresbyopiaMedicineMeta-analysis
• Speaker-Follower Models for Vision-and-Language Navigation
  Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete low-level motor behaviors…
  openalex Daniel Fried, Ronghang Hu, Volkan Cirik, Anna Rohrbach 等 2018-06-07 置信度 0.72 Computer scienceHuman–computer interactionLinguisticsSpeech recognitionArtificial intelligence
• Translanguaging as a Practical Theory of Language
  This article seeks to develop Translanguaging as a theory of language and discuss the theoretical motivations behind and the added values of the concept. I contextualize Translanguaging in the linguistic realities of the 21st century, especially the fluid and …
  openalex Li Wei 2017-10-06 置信度 0.72 TranslanguagingLinguisticsSociologySociocultural evolutionBiosemiotics