具身智能 · 全部实体（第 4 / 100 页）

本页收录第 301–400 条，共 9964 条 · 返回 具身智能 首页

• Pulsar-vision-language Model: A Visual Reasoning Model for Pulsar Candidate Identification
  Abstract The rapid advancement of radio telescopes has resulted in a massive increase in pulsar candidate data, rendering manual inspection infeasible. Existing convolutional neural network–based identification models often struggle with variations in diagnost…
  crossref Dantong Jin, Qiuhong Pan, Kuang Mao, Zhenze Guo 等 2026-07-29T06:33:57Z 置信度 0.82 computer and information sciencescs.lgcs.aics.cvcs.cl
• Action research as part of language teachers’ professional development
  crossref Brynhildur Anna Ragnarsdóttir, Hólmfríður Garðarsdóttir 2026-06-22T12:08:14Z 置信度 0.66
• Adaptive Control of the Redundant Axis of a Surgical Robot for Operating Room Workspace Optimization Using Reinforcement Learning.
  Laparoscopy is one of the most widely used surgical techniques in clinical practice. However, its practice is associated with medium- and long-term musculoskeletal disorders in surgeons. In this context, robot-assisted surgery has emerged as a promising approa…
  europepmc 2026 置信度 0.94 roboticscomputer and information sciencesrobotelectrical engineering, electronic engineering, information engineeringhuman-computer interaction
• Research on strategies for enhancing the competency of safety directors in EPC projects empowered by AI.
  With the widespread application of the engineering-procurement-construction (EPC) delivery model in large-scale infrastructure and complex industrial projects, the highly dynamic construction environment and the escalating complexity of risks pose heightened r…
  europepmc 2026 置信度 0.89 engineeringscience policyprocess managementbusinessworkflow
• Embodied Multimodal Grounding for Open-Vocabulary Mobile Manipulation via Semantic 3D Gaussian Splatting
  Embodied mobile manipulation requires language, visual observations, three-dimensional scene structure, and action feasibility to be aligned before execution. We study open-vocabulary target grounding with few-shot manipulation in local household workspaces an…
  datacite Ou, Huosen, Song, Dongni, Wang, Yuncong, Zhou, Tao 等 2026 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies
  Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift. Direct reinforcement learning fine-tuning can improve performance, but updating large action d…
  datacite Simsir, Hikmet, Oguz, Ozgur S. 2026 置信度 0.76 Machine Learning (cs.LG)FOS: Computer and information sciences
• AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
  Despite remarkable progress in Vision-Language-Action models (VLAs) for robot manipulation, these large pre-trained models require fine-tuning to be deployed in specific environments. These fine-tuned models are highly sensitive to camera viewpoint changes tha…
  datacite Heo, Hyeongjun, Woo, Seungyeon, Kim, Sang Min, Kim, Junho 等 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• SC$^{2}$-WM: A Self-Correcting World Model with Closed-Loop Feedback for Vision-and-Language Navigation in Continuous Environments
  Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observability. However, most existing methods rely on open-loop execution, lacking mechanisms to detect and correct inter…
  datacite Yao, Xuan, Zhu, Yuze, Gao, Junyu, Wang, Zongmeng 等 2026 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
  While Vision-Language-Action models (VLAs) are rapidly advancing toward generalist robot policies, quantitatively characterizing their capability boundaries and failure modes remains challenging. To address this, we introduce VLA-Arena, a comprehensive benchma…
  datacite Zhang, Borong, Li, Jiahao, Shen, Jiachen, Zhang, Yuhao 等 2025 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Depth-Wise Probing and Pruning of the Planning Token in a Driving Vision-Language-Action Model
  Vision-language-action (VLA) models route driving decisions through a deep language model, but it is unclear how much of that depth the action itself requires. We study a representative driving VLA whose entire plan is carried by a single planning token that a…
  datacite Babu, Harisankar, Coors, Benjamin, Lang, Christopher, Berkemeyer, Hendrik 等 2026 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation
  Vision-Language-Action (VLA) models map visual observations and natural-language instructions to robot actions; however, hierarchical and autoregressive paradigms often incur architectural overhead, accumulate long-horizon errors, and require auxiliary modules…
  datacite Liu, Yang, Ding, Pengxiang, Jiang, Tengyue, Wang, Xudong 等 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• The Engagement Credit Economy: A Policy Architecture for Post-Automation Societies
  The Engagement Credit Economy (ECE): Structural Architecture for Post-Automation Societies Creators Ryder, John F.Independent Researcherjohn@driveinsolution.com Policy Brief and Full Framework Overview This record now includes a complete, two-layer presentatio…
  datacite Ryder, John F. 2026 置信度 0.76 Keywords (inline) Engagement Credit Economy, Future of Work, Automation, Artificial Intelligence, Social Policy, Economic Stability, Universal Basic Services, Post-Automation Economy, Civic Engagement, Labour Displacement, Economic Participation, Social Cohesion Subjects (inline) Public Policy, Labour Economics, Economic Systems, Artificial Intelligence, Governance and Public Administration, Social Structure and Social Change
• RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents
  Vision-Language-Action (VLA) models have attracted growing interest as a scalable approach to robotic manipulation. While these models are effective action predictors, deploying them as robotic agents exposes critical gaps: no mechanism for failure recovery, i…
  datacite Yoon, Sihyung, Yoo, Minjong, Ahn, Sanghyun, Choi, Seojeong 等 2026 置信度 0.77 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• A Systems Engineering Framework for Vision-Language-Enabled UAV Triage and Disaster Response
  Recent advances in Vision Language Models (VLMs) have created new opportunities for disaster response, where responders must interpret large volumes of sensor data under time pressure. Current VLM applications include social media monitoring for situational aw…
  datacite Saha, Swapnil, Jagadeesha, Bhuvan Rajanasiriyur, Patnaik, Karishma, Majumdar, Neelakshi 2026 置信度 0.77 Robotics (cs.RO)Artificial Intelligence (cs.AI)Systems and Control (eess.SY)FOS: Computer and information sciencesFOS: Electrical engineering, electronic engineering, information engineering
• SOPD-SocialNav: Selective On-Policy Distillation for Vision-Language Social Navigation
  Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and human behaviors. However, large scale VLMs are difficult to deploy on resource-constrained robotic platforms, w…
  datacite Zhang, Xinyu, Wang, Zishuo, Xiao, Ling 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• A Legal Study of Economic and Monetary Unions: A Comparison between the Eurozone and the West and Central African Experiences
  The specific objective of this paper written in English is to in analyzing the most recent developments in the relationship between the Economic and European Monetary Union and the corresponding Sub-Saharan Unions. Indeed, this relationship has evolved profoun…
  preprints 2022 置信度 0.84 ai safetygeographyai governanceclimatologyconsciousness
• Regulating for Energy Justice
  In this Article, we explore and critique the foundational norms that shape U.S. federal and state energy regulation and suggest pathways for reform that can incorporate principles of “energy justice.” These energy justice principles—developed in academic schol…
  preprints 2022 置信度 0.84 renewable energyenvironmental economicsenergy storagecorporate governancebusiness
• Cyber Silent Spring: Leveraging ESG+T Frameworks and Trustmarks to Better Inform Investors and Consumers about the Sustainability, Cybersecurity, and Privacy of Internet-Connected Devices
  The rapid expansion of Internet of Things (IoT) devices and services is continuing and even being catalyzed by the COVID-19 pandemic with the number of Internet-connected devices already far exceeding the number of people on the planet, leading to widespread i…
  preprints 2022 置信度 0.80 businesssustainabilitycontextsoftware deploymentpsychology
• Anti-Science Ideology
  Political attacks against scientists and scientific research are nothing new, though the Trump Administration appears to have increased both the breadth and the depth of such attacks. What is new, it seems, are attacks on science that are not in service of pro…
  preprints 2020 置信度 0.80 psychologyastrobiologyphysicsphysical sciencesconsciousness
• Prediction and evaluation of parameter optimization effect of large language model fine-tuning
  Large language models have demonstrated outstanding performance in the field of natural language processing, but pretrained models are difficult to adapt to specific tasks. Fine-tuning technology has become a key solution, but its application is limited by pro…
  crossref Yihe Ding 2026-08-14T14:55:03Z 置信度 0.82 cs.lgcomputer sciencecs.aiartificial intelligencecomputer and information sciences
• Vision language model-based multimodal voice activity detection
  crossref Jiacan Li, Xintong Li, Haoran Wei 2026-04-24T17:04:44Z 置信度 0.66
• Vision-language model for remote sensing scene classification
  Recent optical remote-sensing studies still rely on class-specific convolutional networks whose accuracy quickly degrades on unseen categories. Contrastive vision–language models (e.g., CLIP) transfer well but provide little insight into their decisions. We pr…
  crossref Ting Wang, Yizhuang Xie 2026-07-09T13:42:16Z 置信度 0.82 computer and information sciencescs.lgcs.aics.cvartificial intelligence
• Language-driven vision: enhancing GPR target recognition via DINO with large language model semantic guidance
  Ground penetrating radar (GPR) has become widely used for detecting underground structures. However, challenges such as limited semantic understanding of detected targets and the inability to respond to user queries in a meaningful way still persist. To addres…
  crossref Feifei Hou, Xiaobo Wang, Hai Liu 2026-07-09T13:42:16Z 置信度 0.82 computer sciencecomputer and information sciencescs.aiartificial intelligenceelectrical engineering, electronic engineering, information engineering
• Action-aware anchor-based frame selection strategy for action recognition
  crossref Zhiming Xu, Yuxin Feng, Fan Zhou, Ge Lin 等 2026-04-06T01:10:59Z 置信度 0.63
• SurgXBench: Explainable Vision-Language Model Benchmark for Surgery
  Innovations in digital intelligence are transforming robotic surgery through more informed decision-making. Real-time awareness of surgical instrument presence and actions (e.g., cutting tissue) is essential, yet despite decades of research, most machine learn…
  crossref Jiajun Cheng, Xianwu Zhao, Sainan Liu, Xiaofan Yu 等 2026-05-05T19:59:32Z 置信度 0.82 computer sciencecomputer and information sciencescs.aiartificial intelligencecs.cv
• ProfVLM: A lightweight video-language model for multi-view proficiency estimation
  Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the assessment. We inst…
  crossref Edoardo Bianchi, Jacopo Staiano, Antonio Liotta 2026-04-01T08:03:48Z 置信度 0.82 cs.aics.lgcomputer and information sciencescs.clartificial intelligence
• Combining Data Distribution and Adaptive Inference for Robotic Grasping in Vision-Language-Action
  crossref Lingye Zhong, Fuxiang Wu, Fusheng Hao, Chengqun Song 等 2026-08-04T19:14:34Z 置信度 0.66
• Towards vision-language-action systems: A statistical and objective study of recent advances
  crossref Mrityunjay Bayan, Rupam Bhattacharyya 2026-07-24T17:55:05Z 置信度 0.66
• ViSched: Reinforcement Learning-Based Scheduling for Vision-Language Model Inference on a Heterogeneous GPU Cluster
  crossref Ravi Gupta 2026-08-19T19:11:32Z 置信度 0.66
• Vision-Guided Grounding for Reducing Hallucinations in Vision-Language Models
  Vision-language models are capable of answering queries, describing images, and performing logical reasoning on both visual and textual inputs. However, despite these capabilities, the models can still produce visual hallucinations in their responses. These ha…
  crossref Jahnavi Bellapukonda 2026-06-01T18:23:37Z 置信度 0.82 computer and information sciencescs.cvcs.aics.lgcs.cl
• Enhancing camera-captured Devanagari documents via geometric filtering for improved vision-language model text extraction
  Despite significant advances, modern Vision-Language Model (VLM) platforms remain constrained by the scarcity of training data in non-English languages, limiting their global applicability in Text extraction for regional languages written in Devanagari scripts…
  crossref Anup Kelkar, Parag Deshpande, O.G. Kakde 2026-05-15T16:21:00Z 置信度 0.82 computer sciencecomputer and information sciencescs.cvcs.lgartificial intelligence
• A Self-Distilled Vision-Language Model for Industrial Defect Classification
  Defect detection is a critical task in the manufacturing domain that is essential for ensuring product quality and operational efficiency. However, this task poses significant challenges due to imbalanced datasets, subtle differences between defective and non-…
  crossref Subin Choi, Daun Jeong, Donjin Park, Hansang Cho 2026-02-18T21:14:28Z 置信度 0.82 cs.aics.lgcomputer and information sciencescs.cvcomputer science
• A vision-language model for multitask classification of memes
  The emergence of social media and online memes has led to an increasing demand for automated systems that can analyse and classify multimodal data, particularly in online forums. Memes blend text and graphics to express complicated ideas, sometimes containing …
  crossref Md. Mithun Hossain, Md. Shakil Hossain, M.F. Mridha, Nilanjan Dey 2025-09-12T06:58:43Z 置信度 0.82 computer scienceartificial intelligencecomputer and information sciencescs.aics.cv
• Enhancing vision–language model calibration via rotation-enhanced orthogonality-constrained prompt tuning
  crossref Kai Zhou, Dandan Zhu 2026-06-07T06:56:17Z 置信度 0.66
• Model-free Domain Adaptation for Concealed Multimodal Large-Language Models
  Multimodal large-language models (MLLMs) exhibit remarkable capability for various vision tasks but still struggle with the domain-shift problem, in which their performance degrades for data from unfamiliar domains. Since the latest MLLMs often conceal their m…
  crossref Yu Mitsuzumi, Akisato Kimura, Hisashi Kashima 2026-05-05T19:59:32Z 置信度 0.82 cs.lgcs.cvcs.aicomputer sciencecomputer and information sciences
• Part-Centric Diffusion Policy with Vision Language Model for Generalizable Articulated Object Manipulation
  Articulated object manipulation is a core challenge in robotics, but achieving generalization across diverse object categories remains difficult due to variations in geometry and manipulation sequences. To address these challenges, we propose PCDP, a framework…
  crossref Yuanfei Wang, Hao Dong 2026-04-21T21:24:02Z 置信度 0.82 computer and information sciencescs.airoboticsartificial intelligencecomputer vision and pattern recognition
• 3D Human Pose Estimation Based on Vision-Language-Action Models and Its Applications
  Current 3D human pose estimation (3D HPE) methods remain confined to passive geometric reconstruction, suffering from depth ambiguity, error propagation from 2D detectors, and insufficient spatiotemporal coherence in dynamic scenes. To overcome these limitatio…
  crossref Xinran Shi 2026-06-22T09:13:33Z 置信度 0.82 computer and information sciencescomputer scienceroboticsartificial intelligencecs.ai
• VLAbot: A human Vision–Language–Action models interaction framework for robotic assembly
  In this work, we propose an intelligent human–robot collaboration system designed to assist embodied intelligence in learning complex, long-horizon manufacturing assembly tasks. The system integrates multiple expert agents and augmented reality (AR) interactio…
  crossref Xueting Wang, Xiwen Dengxiong, Shi Bai, Pai Zheng 等 2026-02-16T11:32:11Z 置信度 0.82 computer sciencecs.aihuman-computer interactioncomputer and information sciencesreinforcement learning
• Forest landscape restoration in the Hindu Kush Himalaya: From global vision to local action
  This convening paper summarises key insights from a regional webinar on forest landscape restoration (FLR) in the Hindu Kush Himalaya (HKH). It highlights global restoration commitments, regional experiences, and emerging approaches for translating FLR princip…
  crossref 2026-03-11T09:31:14Z 置信度 0.80 emerging technologiesenvironmental resource managementblockchaintransformative learningengineering ethics
• MedAware at MEDIQA-EVAL 2026: Vision-Language Model Fine-Tuning with Logprob-Based Score Calibration for Medical Response Evaluation
  We present MedAware, our MEDIQA-EVAL 2026 system for predicting human ratings of medical QA responses from text and images.We fine-tune Qwen3-VL models (4B/8B/32B) with supervised fine-tuning (SFT), and study GRPO as an optional second stage under both LoRA an…
  crossref Ziqi Hao, Pengbo Liu 2026-06-29T04:54:56Z 置信度 0.82 cs.clcs.aics.sdbenchmarkcs.lg
• AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents
  We present ANANDASKY, a vision-language model for line-level transcription of historical sinographic documents.The model combines a compact high-resolution visual encoder with global attention, 10 px patches, uncompressed visual prefix and a Qwen3-0.6Bautoregr…
  crossref Colin Brisson, Ayoub Kahfy, Frédéric Constant, Marc Bui 2026-06-29T05:10:36Z 置信度 0.82 eess.ascs.cvcs.lgcs.sdreinforcement learning
• Spatiotemporal Multimodal Large Language Model for Facial Micro-Expression Spot-then-Recognize
  crossref Li Dangen, Pan Hang 2026-08-17T19:15:05Z 置信度 0.63
• ViT-TinyLlama: A Lightweight Vision-Language Model for Explainable Autonomous Driving
  crossref Haritha Prasad Rayakota, Pei-Chi Huang 2026-06-23T19:43:14Z 置信度 0.66
• Multi-Turn Physics-Informed Vision-Language Model for Physics-Grounded Anomaly Detection
  Vision-Language Models (VLMs) demonstrate strong general-purpose reasoning but remain limited in physics-grounded anomaly detection, where causal understanding of dynamics is essential. Existing VLMs, trained predominantly on appearance-centric correlations, f…
  crossref Yao Gu, Xiaohao Xu, Yingna Wu 2026-04-21T21:23:31Z 置信度 0.82 computer and information sciencescs.aics.lgcs.cvcomputer vision and pattern recognition
• SOVABench: A Vehicle Surveillance Action Retrieval Benchmark for Multimodal Large Language Models
  Automatic identification of events and recurrent behavior analysis are critical for video surveillance. However, most existing content-based video retrieval benchmarks focus on scene-level similarity and do not evaluate the action discrimination required in su…
  crossref Oriol Rabasseda, Zenjie Li, Kamal Nasrollahi, Sergio Escalera 2026-08-04T19:10:12Z 置信度 0.82 cs.aicomputer and information sciencescs.clcs.cvcs.lg
• Secondary Realignment: An Embodied Intelligent Operational Framework Integrating Vision-Language and Action Two-Stage Models
  crossref Jinjiang Lin, Yuan Lu, Han Li, Xiaolong Cai 等 2026-04-29T08:34:11Z 置信度 0.66
• Lite VLA: Efficient Vision-Language-Action Control on CPU-Bound Edge Robots
  The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility of deploying small V…
  crossref Justin Williams, Kishor Datta Gupta, Roy George, Mrinmoy Sarkar 2026-07-02T19:42:40Z 置信度 0.82 computer and information scienceselectrical engineering, electronic engineering, information engineeringroboticscomputer scienceartificial intelligence
• Increasing value in the Veterans Affairs Healthcare System (VA) with precision health: a continuing landmark collaboration with the Department of Energy.
  Objective Phase II of MVP-CHAMPION, a federal collaboration between the Veterans Affairs Healthcare System (VA) and the Department of Energy (DoE), leveraged large-scale clinical, geo-spatial, and genetic data with state-of-the-art artificial intelligence (AI)…
  europepmc 2026 置信度 0.94 medicinedata sciencehealth carecomputer scienceartificial intelligence
• Procedure-Aware Hierarchical Alignment for Open Surgery Video-Language Pretraining.
  Recent advances in surgical robotics and computer vision have greatly improved intelligent systems' autonomy and perception in the operating room (OR), especially in endoscopic and minimally invasive surgeries. However, for open surgery, which is still the pre…
  europepmc 2026 置信度 0.94 artificial intelligencecs.aicomputer and information sciencescs.lgcomputer science
• Explainable blind image quality assessment with closed-loop semantic guidance and distortion diagnosis.
  In large-scale visual systems, particularly in automated image triage and preprocessing pipelines, the reliability of downstream computer vision tasks depends on the quality of perceptual inputs and the interpretability of assessment outcomes. Existing blind i…
  europepmc 2026 置信度 0.94 cs.aiartificial intelligencecomputer and information sciencescs.cvcomputer science
• The HALO Model: A Learning Health System Framework for Artificial Intelligence.
  Introduction Artificial intelligence is increasingly embedded in healthcare delivery, yet existing Learning Health System (LHS) models do not fully account for the lifecycle management and continuous assurance requirements of AI systems. This gap limits health…
  europepmc 2026 置信度 0.94 computer sciencebusinessknowledge managementprocess managementhealth care
• Munir: A Multimodal Smart-Glasses System for Enhancing Human-Computer Interaction for Visually Impaired Individuals.
  Visual impairment affects approximately 2.2 billion people worldwide, yet existing assistive technologies remain fragmented and prohibitively expensive. This paper presents Munir, an integrated multimodal assistive system designed to enhance human-computer int…
  europepmc 2026 置信度 0.94 computer sciencecomputer and information scienceshuman-computer interactioncs.aibrain-computer interface
• An ERP Study of Modality-Specific Effects on Emotional Word Processing.
  Background/Objectives: Sensory experiences and emotional information contribute to conceptual knowledge. Compared to exteroceptive modality (e.g., visual, auditory), interoceptive modality predominates in the representation of emotional concepts. However, few …
  europepmc 2026 置信度 0.94 psychologybrain-computer interfaceneurosciencecognitive psychologycognition
• DiSMix: Dimensional Swap Mix for Feature-Level Data Augmentation in Vision Transformers.
  Mixup is a data augmentation technique that improves prediction accuracy in classification tasks by combining representations of training samples, which makes it particularly effective in settings with limited data and during fine-tuning for downstream tasks. …
  europepmc 2026 置信度 0.94 artificial intelligencecs.lgcomputer and information sciencescomputer vision and pattern recognitionmachine learning
• Thermal and RGB-Aware Vision Language Model for Built Environment with 3D Scene Rendering
  Buildings account for nearly 40% of US energy consumption, making effective auditing and retrofitting of building envelopes essential to reducing energy use. However, traditional energy audits remain costly, labor-intensive, and difficult to scale across diver…
  crossref Yining Wen, Jingwei Bao, Kaiwen Chen 2026-08-27T10:05:07Z 置信度 0.82 computer sciencecs.airenewable energyworkflowbusiness
• SmoGVLM: A Small, Graph-Enhanced Vision-Language Model
  Large vision-language models (VLMs) achieve strong performance on multimodal tasks but often suffer from hallucination and poor grounding in knowledge-intensive reasoning. We propose SmoGVLM, a small, graph-enhanced VLM that integrates structured knowledge wit…
  crossref Debjyoti Mondal, Rituraj Singh, Subhadarshi Panda 2026-04-21T21:25:57Z 置信度 0.82 cs.aicomputer and information sciencescs.lgcs.cvcs.cl
• Vision–language–action models for hri/hrc/hrt: a taxonomy, simulation-centric gaps, and research directions
  Robotics driven by foundation models, such as Vision--Language--Action (VLA) systems, already represents a major step forward in autonomy and natural-language interaction. Yet, many obstacles remain on the path toward Human--Robot Teaming (HRT): most current m…
  crossref Jiri Konecny, Filippo Sanfilippo, Michal Prauzek 2026-06-30T08:36:46Z 置信度 0.82 computer and information sciencescs.aicomputer scienceroboticselectrical engineering, electronic engineering, information engineering
• mCoT-VLA: Towards Robust Vision-Language-Action Models via Multimodal Chain-of-Thought
  crossref Huazhen Huang, Juncai Zhang, Jianbo Zhao, Fangyu Liu 等 2026-04-21T21:24:02Z 置信度 0.66
• Data Quality Assessment with Hu Moments for Vision-Language Model Customization
  crossref Ali Vâlâ Barbaros, Erdem Bilgili 2026-08-11T19:22:33Z 置信度 0.66
• Large language models in action: Semantic navigation on TurtleBot4 via Model Context Protocol-based natural language interface
  crossref Priyanshu Choudhary, Abhimanyu Jadli, Divneet Singh Kapoor, Kiran Jot Singh 等 2026-06-26T13:43:47Z 置信度 0.66
• Meridian Affinity Calculus (MAC) v4.4 Ordered Projection Architecture: An Exploratory Research Framework for Temporal Organization, Influence, and Residual Structure
  Meridian Affinity Calculus (MAC) v4.4 ## AI / ML / LLM Innovation Overview - 2006-08-09 This release introduces a new generation of AI analysis concepts focused on one of the most important challenges facing modern Large Language Models: preserving meaning, st…
  datacite Vening, Edwin Jean-Paul 2026 置信度 0.72
• Can the Cloud Drive? Infrastructure Feasibility of Offloading Autonomous Driving Across 5G and 6G
  Frontier autonomous-driving models -- especially vision-language-action (VLA) models, whose forward pass approaches $\sim$60~TFLOPs -- are outgrowing economical onboard deployment, since peak hardware sits idle most of the day. Cloud inference can instead shar…
  datacite Parsa, Pouya, Han, Kawon, Choi, Seongjin 2026 置信度 0.76 Systems and Control (eess.SY)FOS: Electrical engineering, electronic engineering, information engineering
• A Modular Vision-Language-Action Robotics Framework for Indoor Environments
  This paper presents an integrated system for the CMU Vision-Language-Action (VLA) Challenge, designed to enable an autonomous agent to perform complex tasks based on natural language instructions. Our framework employs a modular architecture that orchestrates …
  datacite Jana, Anindya, Banerjee, Snehasis, Sadhu, Arup, Dasgupta, Ranjan 2026 置信度 0.77 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Ep. 106: Why Your AI Needs a Mouse and a Universal Power Strip
  Episode summary: In this episode of My Weird Prompts, Herman and Corn explore the evolution of human-computer interaction, starting with Grace Hopper's vision in the 1950s and leading into the cutting-edge AI of late 2025. They break down the difference betwee…
  datacite Rosehill, Daniel, Gemini 3.1 (Flash), Chatterbox TTS 2025 置信度 0.79 podcastai-generatedmy weird promptscomputer-use-agentsgrace-hopper
• Local LLM Inference for Privacy-Preserving Browser Intelligence: Architecture and Optimization — Browser Engine, Privacy, Web, Sovereign AI, and Post-Cloud Architecture (Kathon)
  The integration of large language models (LLMs) into web browsers enables transformative capabilities including visual page understanding, natural language task delegation, and autonomous web interaction. However, cloud-based LLM inference introduces fundament…
  datacite Alpasan, Lois-Kleinner 2026 置信度 0.79 sovereign aisovereign datasovereign osoperating systemspost-cloud
• Local LLM Inference for Privacy-Preserving Browser Intelligence: Architecture and Optimization — Browser Engine, Privacy, Web, Sovereign AI, and Post-Cloud Architecture (Kathon)
  The integration of large language models (LLMs) into web browsers enables transformative capabilities including visual page understanding, natural language task delegation, and autonomous web interaction. However, cloud-based LLM inference introduces fundament…
  datacite Alpasan, Lois-Kleinner 2026 置信度 0.79 sovereign aisovereign datasovereign osoperating systemspost-cloud
• CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
  Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a Cognition-Aligned Vision-Languag…
  datacite Li, Wei, Zhang, Renshan, Shao, Rui, He, Jie 等 2025 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciencesFOS: Computer and information sciences
• CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments
  CAVE: Commonsense Anomalies in Visual Environment 🏠 Project Page📄 Paper (EMNLP 2025)💻 Code Dataset Details Dataset Description CAVE is the first benchmark of real-world visual anomalies for evaluating Vision-Language Models (VLMs). It is curated from images…
  datacite Bhagwatkar, Rishika, Montariol, Syrielle, Romanou, Angelika, Borges, Beatriz 等 2025 置信度 0.72
• CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments
  CAVE: Commonsense Anomalies in Visual Environment 🏠 Project Page📄 Paper (EMNLP 2025)💻 Code Dataset Details Dataset Description CAVE is the first benchmark of real-world visual anomalies for evaluating Vision-Language Models (VLMs). It is curated from images…
  datacite Bhagwatkar, Rishika, Montariol, Syrielle, Romanou, Angelika, Borges, Beatriz 等 2025 置信度 0.72
• Algorithmic Induction via Structural Weight Transfer
  ---mainfont: "FreeSerif"monofont: "FreeMono"mathfont: "FreeSerif"--- # Engineering Algorithmic Structures in Neural Networks: From a Materials Science Perspective to Algorithmic Thermodynamics of Deep Learning **Author:** Iscomeback, Gris ( grisun0 ) --- ## Ab…
  datacite Iscomeback, Gris 2026 置信度 0.77 grokentropybinary
• LACF Care: A Z3 SMT2 Safety Framework for Distributed Companion Robotics in Elderly, Vulnerable, and Linguistically-Endangered Populations
  Ce dépôt présente une architecture intégrée de care robotics combinant cinq composants antéfiorés indépendamment, unifiés sous le framework formel LACF (Life Always Comes First) avec garanties de vérification déterministe. ═════════════════════════════════════…
  datacite Ochej, Stephane 2026 置信度 0.79 LACFZ3 SMT2CVC5PrologDatalog
• LACF Care: A Z3 SMT2 Safety Framework for Distributed Companion Robotics in Elderly, Vulnerable, and Linguistically-Endangered Populations
  Ce dépôt présente une architecture intégrée de care robotics combinant cinq composants antéfiorés indépendamment, unifiés sous le framework formel LACF (Life Always Comes First) avec garanties de vérification déterministe. ═════════════════════════════════════…
  datacite Ochej, Stephane 2026 置信度 0.79 LACFZ3 SMT2CVC5PrologDatalog
• Nothingness – Dimension 0 and the permanent presence of possibility
  Key Work XI as an Information-Physical Transition Model Author: Dieter LiedtkeYear: 1970 - 2026Licence: CC BY 4.0 Abstract This study analyses Key Work XI – "Above Nothing" as an epistemic work of art that does not represent a real transition from structureles…
  datacite Dieter Liedtke 2026 置信度 0.72
• The ASEAN’s responses to COVID-19: A policy sciences analysis
  The World Health Organisation (WHO) announced the new coronavirus disease (COVID-19) it as a pandemic on March 11th, 2020. The pandemic has brought havoc globally as more than 190 countries and territories are affected as of 30 April 2030. The crisis suggests …
  preprints 2020 置信度 0.84 psychologycontextmedicineengineering ethicschina
• A Submission to the Joint Standing Committee on Treaties on the Regional Comprehensive Economic Partnership (RCEP)
  This submission provides a critical analysis of the proposed Regional Comprehensive Economic Partnership (RCEP) – focusing in particular upon intellectual property and innovation policy. Recommendation 1 RCEP has a broad membership – even with the departure of…
  preprints 2021 置信度 0.84 political sciencebusinesssociologygeographycorporate governance
• The Fiscal Fed
  The US Federal Reserve System is conventionally understood as a private-market stabilising institution that has no settled role in supporting the fiscal power of the Treasury. Contra that view, this article argues that the US central bank has always had an ext…
  preprints 2023 置信度 0.80 consciousnessclimatologyai governanceai safetyremote sensing
• Brexit, Covid-19, and Possible Frameworks for Future UK/EU Financial Governance Cooperation
  The EU project is at an inflection point. Intra-EU alliances are altering in light of the UK s departure, the EU s financial markets remain segmented, and there is limited appetite for completing the Banking Union. The second stage of the Brexit negotiations a…
  preprints 2021 置信度 0.84 corporate governancepolitical scienceeconomicsengineering ethicsai governance
• Brexit, COVID-19, and Possible Frameworks for Future UK/EU Financial Governance Cooperation
  The EU project is at an inflection point. Intra-EU alliances are altering in light of the UK’s departure, the EU’s financial markets remain segmented, and there is limited appetite for completing the Banking Union. The second stage of the Brexit negotiations a…
  preprints 2021 置信度 0.84 corporate governanceeconomicspolitical scienceengineering ethicsemerging technologies
• The Fourth Industrial Revolution and the Sustainability Practices: A Comparative Automated Content Analysis Approach of Theory and Practice
  Background: (1) In the time of the 4th Industrial Revolution or Industry 4.0, a conglomerate of technical and social inventions, political contexts, socio-cultural circumstances, environmental policies, business models, and economic policies has emerged. Susta…
  preprints 2020 置信度 0.84 businesssustainabilitysustainable developmentengineeringnatural resource economics
• When Data Comes Home: Next Steps in International Taxation's Information Revolution
  Over the last decade, there has been a revolution in cross-border tax information exchange and reporting. While this dramatic shift was the product of multiple forces and events, a fundamental reality is that politics, technology, and law intersected to drive …
  preprints 2020 置信度 0.84 businesscontextdata sciencepsychologyhealth care
• Community Solar Governance: Institutional Design and Collective Choice Options: Implications for U.S. Markets
  To assess market development, and governance and equity implications in detail, the research team investigates programs in California, Massachusetts, and New York. The analysis yields insight into the current and future operation of Community Clean Energy auth…
  preprints 2021 置信度 0.84 renewable energybusinessphysical sciencescomputer sciencecontext
• First Amendment Challenges to State Vaccine Mandates: Why the U.S. Supreme Court Should Hold that the Free Exercise Clause Does not Require Religious Exemptions
  The U.S. Supreme Court has never issued a judicial opinion on the merits declaring that the First Amendment Free Exercise Clause permits states to mandate vaccinations without offering religious exemptions. However, in two recent cases, the Court in brief orde…
  preprints 2022 置信度 0.75 neurosciencepolitical scienceconsciousnesssociologyphysics
• Violations During the Pandemic of Law School Faculties’ Authority to Decide Methods of Instruction
  During the pandemic, some universities have required as much “in person” teaching as possible everywhere on campus — including a university’s law school. Universities and their administrators who did this were wrong for three reasons. First, their fears that s…
  preprints 2020 置信度 0.84 psychologymedicinemeteoritesociologymathematics education
• 국제사회의 순환경제 확산과 한국의 과제 (Accelerating Transition towards a Circular Economy and Policy Implications for Korea)
  Korean Abstract: 국제사회는 한정된 자원을 효율적으로 이용하며 지속가능한 성장을 이루기 위해 노력해왔다. 특히 EU를 필두로 주요국들이 잇달아 탄소중립 달성을 선언하고, 이를 달성하기 위한 정책 과제 중 하나로 ‘순환경제로의 전환’을 강조하고 있다. 코로나19 확산으로 마스크와 같은 일회용품 사용량이 급증하면서 늘어난 폐기물을 어떻게 처리할지에 대한 우려도 커지고 있는 상황이다. 이에 본 연구에서는 국제사회의 순환경제 추진 노력을 분석하고, 폐기물 …
  preprints 2022 置信度 0.80 greenhouse gassustainabilityenvironmental sciencebusinessenvironmental economics
• On Bankruptcy’s Promethean Gap: Building Enslaving Capacity into the Antebellum Administrative State
  As the United States contends with the economic crisis triggered by the COVID-19 pandemic, federal bankruptcy law is one tool that can be used to resolve the financial distress suffered by individuals and businesses. When implementing this remedy, the question…
  preprints 2021 置信度 0.84 multi-agent systemscorporate governanceai governanceconsciousnesspolitical science
• Cato's Project on Poverty and Inequality in California: Final Report
  COVID-19 has been a tragedy for California. More than 4 million Californians have contracted the disease, and over 64,000 have died from it. And beyond the cost of illness and death, the pandemic and the state’s actions to contain it have devastated California…
  preprints 2022 置信度 0.84 astronomyclimate changebiologyinternal medicinegeography
• Innovation Institutions and COVID-19
  The COVID-19 crisis has starkly illustrated both the strengths and limitations of U.S. biomedical innovation institutions as deployed to fight a pandemic. These innovation institutions include not just intellectual property law, but also other legal systems th…
  preprints 2021 置信度 0.84 businesshealth carecontextcomputer sciencetransformative learning
• Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision.
  CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vision-language models (VLMs) as practical detectors for this regime. A unified eva…
  europepmc 2025 置信度 0.94 computer and information sciencescs.aics.cvcs.clbenchmark
• Multi modal hierarchical reinforcement learning framework for dynamic sports sponsorship optimization.
  This paper presents a novel approach to optimizing sports sponsorship strategies by integrating reinforcement learning (RL) with a multi-modal hierarchical framework, enhancing real-time decision-making using diverse data sources such as computer vision, natur…
  europepmc 2025 置信度 0.94 computer scienceartificial intelligencecs.lgcomputer and information sciencescs.ai
• Motion Planning-Augmented Hierarchical Reinforcement Learning for Long-Horizon Mobile Manipulation.
  Long-horizon mobile manipulation requires a robot to execute a sequence of heterogeneous subtasks such as navigation, picking, and articulated-object manipulation in indoor environments. Standard reinforcement learning suffers from reward sparsity and ineffici…
  europepmc 2026 置信度 0.94 computer and information sciencesreinforcement learningelectrical engineering, electronic engineering, information engineeringroboticscs.lg
• Generative Sign-Description Prompts with Multi-Positive Contrastive Learning for Sign Language Recognition.
  While sign language combines sequential hand motions with concurrent non-manual cues (e.g., mouth shapes and head tilts), current recognition systems lack multimodal annotation methods capable of capturing their hierarchical semantics. To bridge this gap, we p…
  europepmc 2025 置信度 0.94 cs.aics.clcomputer scienceartificial intelligencecomputer and information sciences
• InstructSee: Instruction-Aware and Feedback-Driven Multimodal Retrieval with Dynamic Query Generation.
  In recent years, cross-modal retrieval has garnered significant attention due to its potential to bridge heterogeneous data modalities, particularly in aligning visual content with natural language. Despite notable progress, existing methods often struggle to …
  europepmc 2025 置信度 0.94 cs.aicomputer and information sciencescs.lgcs.clcomputer science
• Autonomous language-image generation loops converge to generic visual motifs.
  Autonomous AI-to-AI creative systems promise new frontiers in machine creativity, yet we show that they systematically converge toward generic outputs. We built iterative feedback loops between Stable Diffusion XL (SDXL; image generation) and Large Language an…
  europepmc 2026 置信度 0.94 cs.aiartificial intelligencepsychologycomputer and information sciencescs.cv
• Artificial intelligence in thoracic surgery: a narrative review of clinical advances and applications in 2025.
  Background and objective The integration of artificial intelligence (AI) into thoracic surgery accelerated notably over the course of 2025, transitioning from isolated diagnostic aids toward comprehensive clinical pathway integration. The objective of this nar…
  europepmc 2026 置信度 0.94 medicinecomputer scienceartificial intelligencemedical physicscs.ai
• LLMs augmented hierarchical reinforcement learning with action primitives for long-horizon manipulation tasks.
  Deep reinforcement learning methods have shown promising results in learning specific tasks, but struggle to cope with the challenges of long horizon manipulation tasks. As task complexity increases, the large state space and sparse reward make it difficult to…
  europepmc 2025 置信度 0.94 cs.aics.lgartificial intelligencecomputer sciencereinforcement learning
• The development of object representations in children.
  Objects in scenes follow a hierarchical organization, with "scenes" at the top level, followed by "phrases", clusters of objects that share spatial and functional proximity. Within these phrases, "anchor" objects help predict the identity and location of small…
  europepmc 2026 置信度 0.94 psychologyneuroscienceartificial intelligencemedicinebiology
• Localization, inspection, and reasoning (LIRA) module for autonomous workflows in self-driving laboratories.
  Self-driving labs (SDLs) combine robotic automation with artificial intelligence (AI) to allow autonomous, high-throughput experimentation. However, robot manipulation in most SDL workflows operates in an open-loop manner, lacking real-time error detection and…
  europepmc 2025 置信度 0.94 computer scienceartificial intelligenceroboticscomputer and information sciencesworkflow
• A Perspective on Quality Evaluation for AI-Generated Videos.
  Recent breakthroughs in AI-generated content (AIGC) have transformed video creation, empowering systems to translate text, images, or audio into visually compelling stories. Yet reliable evaluation of these machine-crafted videos remains elusive because qualit…
  europepmc 2025 置信度 0.94 cs.aicomputer scienceartificial intelligencecs.cvcomputer and information sciences
• Research Is Needed on How Young European Children Use Digital Technology and Its Developmental Impact.
  Environmental factors support children's development, such as early education and high-quality interactions with their parents [1]. But we still don't know what impact the rapidly evolving technology and digital media (TDM) and emerging educational technology …
  europepmc 2026 置信度 0.94 psychologybusinesssocial and behavioral sciencesdigital transformationengineering
• A framework for robotic manipulation tasks based on multiple zero shot models.
  Humans tackle unknown tasks by integrating information from multiple sensory modalities. Existing robotic frameworks struggle to achieve effective multimodal manipulation, especially when sufficient training data is lacking. This study introduces "Panda Act", …
  europepmc 2025 置信度 0.94 cs.aiartificial intelligencecomputer and information sciencescomputer sciencecs.cl