具身智能 · 全部实体（第 13 / 100 页）

本页收录第 1201–1300 条，共 10000 条 · 返回 具身智能 首页

• NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulation
  Real-world deployment of Vision-Language-Action (VLA) models is often bottlenecked by efficiency-performance trade-offs, cross-embodiment generalization, and execution smoothness. We present NebulaVLA, an asynchronous dual-frequency architecture that decouples…
  datacite Zhao, Cong, Tian, Shuai, Zhang, Xu, Ni, Baocheng 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciencesI.2.9; I.2.10
• Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos
  Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of rare yet safety-critical scenarios. To address these challenges, we present a scalable framework for learni…
  datacite Xia, Bingyi, Bao, Han, Chen, Zhewei, Ye, Hanjing 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina
  Artificial intelligence-assisted ultrasound scanning enhances diagnostic reliability and efficiency by providing real-time guidance for standardized image acquisition and reducing operator dependence. However, existing reinforcement learning and learning-assis…
  datacite Zhang, Cheng, Wu, Xingzheng, Yan, Guihao, Hu, Xifeng 等 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
  Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured settings. Yet it remains an open question whether current VLA systems can benefit fr…
  datacite GigaBrain Team, Ye, Angen, Sun, Axiang, Jin, Can 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Robo-Dopamine 2.0: History-Conditioned and OOD-Aware Process Reward Modeling for Robotic Manipulation
  Vision-language-action (VLA) models improve robotic manipulation but remain vulnerable to compounding errors, scene changes, and off-trajectory states. Reinforcement learning can refine pretrained VLA policies, yet sparse success signals hinder exploration, wh…
  datacite Xu, Yijie, Jin, Haopeng, Zhou, Run, Liu, Shengbang 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Algorithm-Architecture Co-Design for Efficient VLA Inference via Speculative Inference and Verification
  Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in the field of embodied AI, but their high computational cost and limited predicted action length hinder real-time deployment. Although Dadu-Corki, a dedicated accelerator for effic…
  datacite Qi, Chunyu, Song, Zhuoran, Weng, Jian, Jiang, Haozhe 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
  Vision-Language-Action (VLA) models have emerged as a promising foundation for Embodied AI, but their high inference cost poses significant challenges for deployment in robotic systems. In practice, on-device inference is constrained by limited compute capacit…
  datacite Zhou, Ao, Dai, Bo, Yu, Le, Liu, Xingyu 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)Robotics (cs.RO)FOS: Computer and information sciences
• Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability
  Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to $0\%$, while hundreds…
  datacite Gao, Yudong, Chen, Linghan, Wu, Wenhan, Zhou, Mia 等 2026 置信度 0.66 Cryptography and Security (cs.CR)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
  Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temporally static updates throughout a control rollout, overlooking the phase-dependent nature of continuous-actio…
  datacite Guo, Yufei, Wu, Yinan, Duan, Haoran, Ding, Guiguang 等 2026 置信度 0.66 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• ForceU-VLA: A Force-Aware Vision-Language-Action Model for Embodied Ultrasound Scanning
  Embodied intelligent ultrasound scanning enables the automation and standardization of the ultrasound examination process by integrating perception, decision-making, and execution capabilities. However, existing methods suffer from loosely coupled modeling bet…
  datacite Wu, Xingzheng, Zhang, Cheng, Yan, Guihao, Hu, Xifeng 等 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• The Role of Mahatma Gandhi in Eradication of Untouchability
  Abstract The eradication of untouchability represents one of the most critical, contentious, and complex social reform agendas in modern Indian history. This article examines the multifaceted role of Mahatma Gandhi in conceptualizing, mobilizing, and leading t…
  datacite Dr. Venkatesha V 2019 置信度 0.66 Mahatma Gandhi, Untouchability, Caste System, Social Reform, B.R. Ambedkar, Sarvodaya, Hindu Tradition, Poona Pact
• The Role of Mahatma Gandhi in Eradication of Untouchability
  Abstract The eradication of untouchability represents one of the most critical, contentious, and complex social reform agendas in modern Indian history. This article examines the multifaceted role of Mahatma Gandhi in conceptualizing, mobilizing, and leading t…
  datacite Dr. Venkatesha V 2019 置信度 0.66 Mahatma Gandhi, Untouchability, Caste System, Social Reform, B.R. Ambedkar, Sarvodaya, Hindu Tradition, Poona Pact
• Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures
  Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure. In a fu…
  datacite HU, Haibo, Huang, Lianming, Li, Qiao, Guan, Nan 等 2026 置信度 0.66 Distributed, Parallel, and Cluster Computing (cs.DC)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• The Nexus Recursive Harmonic Framework (RHA) – A Triadic Harmonic Magnum Opus
  The Nexus Recursive Harmonic Framework (RHA) – A Triadic Harmonic Magnum Opus Driven by Dean A. Kulik November, 2025 1. Triangular Quantization and the Mark1 Harmonic Engine Triangular Archetypes 0–9: At the core of RHA is a triangular quantization model in wh…
  datacite Kulik, Dean 2025 置信度 0.66
• The Nexus Recursive Harmonic Framework (RHA) – A Triadic Harmonic Magnum Opus
  The Nexus Recursive Harmonic Framework (RHA) – A Triadic Harmonic Magnum Opus Driven by Dean A. Kulik November, 2025 1. Triangular Quantization and the Mark1 Harmonic Engine Triangular Archetypes 0–9: At the core of RHA is a triangular quantization model in wh…
  datacite Kulik, Dean 2025 置信度 0.66
• Learning Action Recognition Model from Depth and Skeleton Videos
  crossref Hossein Rahmani, Mohammed Bennamoun 2017-12-25T16:51:45Z 置信度 0.70
• ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
  Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. I…
  crossref Wenxuan Song, Ziyang Zhou, Han Zhao, Jiayi Chen 等 2026-03-18T00:58:55Z 置信度 0.70
• Conscious Vision for Action Versus Unconscious Vision for Action?
  crossref Berit Brogaard 2011-03-08T09:33:52Z 置信度 0.70
• IB-AMG: Aircraft Mission Generation With Inference-based Vision-Language-Action Model
  crossref JinHai Li, Peng Chen, MoHan Li, LuYi Ren 2025-09-12T17:28:12Z 置信度 0.70
• Continuous action segmentation and recognition using hybrid convolutional neural network‐hidden Markov model model
  Continuous action recognition in video is more complicated compared with traditional isolated action recognition. Besides the high variability of postures and appearances of each action, the complex temporal dynamics of continuous action makes this problem cha…
  crossref Jun Lei, Guohui Li, Jun Zhang, Qiang Guo 等 2016-02-19T07:58:53Z 置信度 0.70
• MMVLA-EXT: Multi-Modal Vision-Language-Action Model with Efficient Cross-Platform Task Transfer
  crossref Sheng Guo, Ruiteng Zhao, Jinxian Zhou, Chenchen Liu 等 2026-01-21T21:06:47Z 置信度 0.70
• Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action Model
  Abstract This study evaluates two leading approaches for teaching construction robots new skills to understand their applicability for construction automation: a vision-language-action (VLA) model and reinforcement learning (RL) methods. The goal is to underst…
  crossref Zhaofeng Hu, Hongrui Yu, Vaidhyanathan Chandramouli, Ci-Jyun Liang 2026-08-15T13:16:25Z 置信度 0.70
• A Vision-Language Foundation Model for Leaf Disease Identification
  Leaf disease identification often involves image classification. However, currently popular methods, such as pretraining the model on the ImageNet dataset, precisely a type of crop and limited data, or only using image or text classification without taking adv…
  crossref Khang Nguyen Quoc, Lan Le Thi Thu, Luyl-Da Quach 2025-02-26T23:15:16Z 置信度 0.70
• When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
  crossref Xuan Dong, Zhe Han, Tianhao Niu, Qingfu Zhu 等 2026-07-01T12:25:50Z 置信度 0.70
• Optimizing Vision-Language Model for Robust Road Damage Assessment via Parameter-Efficient Fine-Tuning
  This study investigates the domain adaptation of the Vision-Language Model (VLM) for road damage assessment, focusing on a fine-tuning strategy optimized for resource-constrained engineering environments. Unlike conventional object detection models that operat…
  crossref Donghwi Kim, Heejung Youn 2026-03-13T20:54:38Z 置信度 0.70
• Multimodal Detection of Hateful Memes by Applying a Vision-Language Pre-Training Model
  Abstract Detrimental to individuals and society, online hateful messages have recently become a major social issue. Among them, one new type of hateful message, named “hateful meme”, has emerged and brought difficulties in traditional deep learning-based detec…
  crossref Yuyang Chen, Feng Pan 2022-04-11T15:01:46Z 置信度 0.70
• Perception to Action with Vision-Language-Action Models for Fast and Reliable Decision Making in Dynamic Environments
  crossref Yeryeong Cho, Jaeyoung Choe, Joongheon Kim 2026-02-19T20:55:29Z 置信度 0.70
• MarkingVLM: Vision-Language Model for Few-Shot IC Marking Detection_supp1-3638609.pdf
  crossref Yu Liu 2025-12-25T18:29:17Z 置信度 0.70
• Translating Perceptions into Action: Vision Language and TrueSkill Integration for Urban Livability Mapping
  crossref Mirsalar Kamari, Mahdi Ghafoori, Mohammadsoroush Tafazzoli 2026-08-27T10:05:07Z 置信度 0.70
• Automatic Recording System for Tag-less Lost-Item Retrieval Support Using a Vision-Language Model
  crossref Yuya Mukose, Tatsuya Sasaki, Tatsuhito Hasegawa 2026-05-18T08:53:16Z 置信度 0.70
• V2A - Vision to Action: Learning Robotic Arm Actions Based on Vision and Language
  crossref Michal Nazarczuk, Krystian Mikolajczyk 2021-02-24T15:13:11Z 置信度 0.70
• VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
  crossref Ravi Ranjan, Agoritsa Polyzou 2026-07-01T12:25:50Z 置信度 0.70
• Integrating World Models into Vision Language Action and Navigation: A Comprehensive Survey
  World models are a transformative paradigm in embodied AI, enabling agents to learn efficiently and plan by simulating environmental dynamics. As vision-language action and navigation systems grow more sophisticated, integrating world models is crucial for bri…
  crossref Jingwen Sun, Hongjin Chen, Zezhi Liu, Xin Jin 等 2025-12-09T22:38:02Z 置信度 0.70
• From vision to action: Inquiring into the conditions for the motivational capacity of ideal second language selves
  crossref Gianna Hessel 2015-06-20T04:45:22Z 置信度 0.70
• Systematic Literature Review of Vision-Language-Action Models for Generalist Robots
  Generalist robots need to perform diverse tasks while operating in dynamic, uncertain, and unstructured environments, often around human beings. Vision-language-action (VLA) models have recently emerged as a promising and flexible framework for integrating per…
  crossref Umair Cheema, Youakim Badr, Thao Minh Le, Katie Fitzsimons 2026-08-17T13:42:17Z 置信度 0.70
• From vision to action
  crossref 2026-04-28T13:34:43Z 置信度 0.70
• Human action recognition model reuse for word-level sign language recognition
  crossref Gulchin Abdullayeva, Nigar Alishzade 2024-12-26T13:48:23Z 置信度 0.70
• Remote sensing image captioning: a survey from encoder-decoder model to large vision-language model
  crossref Chenfei Liu, Dong Lin, Pengyi Tian, Na Yang 2026-02-13T19:04:59Z 置信度 0.70
• 13 Building Future Language Leaders in a Participatory Action Research Model
  crossref Robert Elliott, Janne Underriner 2022-10-12T11:34:09Z 置信度 0.70
• Summary: Language as Social Action
  crossref 2021-03-06T03:04:25Z 置信度 0.70
• Parameter-efficient action planning with large language models for vision-and-language navigation
  crossref Bahram Mohammadi, Ehsan Abbasnejad, Yuankai Qi, Qi Wu 等 2025-09-29T16:12:07Z 置信度 0.70
• THE CONSTRAINTS OF THE IMPLEMENTATION OF TEAM-BASED LEARNING IN CLASSROOM ACTION RESEARCH CLASS
  The previous research that I conducted, the use of Team-Based Learning in Classroom Action Research (CAR) class is well accepted and gives a good influence on the students’ learning. To have a responsibility to teach Action Research and to keep being reflective …
  crossref Rusiana Rusiana 2017-08-30T05:27:20Z 置信度 0.70
• David D. Clarke, Language and action: A structural model of action. (International Series in Experimental Social Psychology 7.) Oxford: Pergamon, 1983. Pp. xiv + 318.
  crossref Rita T. Denny 2008-12-19T09:05:44Z 置信度 0.70
• One Last Attention for Your Vision-Language Model
  crossref Liang Chen, Ghazi Shazan Ahmad, Tianjun Yao, Lingqiao Liu 等 2026-04-29T19:45:49Z 置信度 0.70
• Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model
  crossref Shiming Chen, Bowen Duan, Salman Khan, Fahad Shahbaz Khan 2026-04-29T19:45:49Z 置信度 0.70
• Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
  crossref Alaa Asfour, Christopher Indris, Leihan Chen, Tejas Vyas 等 2026-05-14T04:53:35Z 置信度 0.70
• RSUniVLM: A Unified Vision-Language Model for Remote Sensing via Granularity-oriented Mixture of Experts
  crossref Xu Liu, Zhouhui Lian 2025-12-23T18:00:51Z 置信度 0.70
• The Perception‐Action Model: Counting Computational Mechanisms
  Abstract Milner and Goodale's Two Visual Systems Hypothesis (TVSH) is regarded as common ground in recent discussions of visual consciousness. A central part of TVSH is a functional model of vision and action (a functional perception‐action model, PAM for shor…
  crossref Thor Grünbaum 2017-07-14T10:52:36Z 置信度 0.70
• A Vision-Language Agentic Pipeline for Lead Optimization: Defence-in-Depth Chemistry Gates and Cross-Provider Model Evaluation
  Background: Lead optimization in small-molecule drug discovery is a constrained search problem: from a chemical starting point and the structural cues of its binding pose, propose analogs that preserve the pharmacophore, satisfy ADMET liabilities, and remain s…
  crossref Toluwanimi Odunewu 2026-06-15T11:03:08Z 置信度 0.70
• The Dual-System Hierarchical Architecture: A Future Paradigm for Vision-Language-Action Models
  crossref Wenlong Chen, Zhen Tian, Zhou Zhou, Youhua Xia 2026-02-20T21:14:29Z 置信度 0.70
• Avoid Wasted Annotation Costs in Open-Set Active Learning with Pre-Trained Vision-Language Model
  crossref Jaehyuk Heo, Pilsung Kang 2025-01-10T16:41:59Z 置信度 0.70
• Vision Language Action Models for Autonomous Driving and 3D Environment: Towards Agentic Intelligence, Frameworks, Benchmarks, and Open Challenges
  Multimodal Large Language Models (MLLMs) have attracted significant attention in recent years due to their broad applicability across fields, including healthcare, autonomous vehicles (AVs), robotics, 3D reconstruction, and human-computer interaction. The usef…
  crossref Gulraiz Khan, Waqas Ahmed, K.Y. Wertheim, Kevin Pimbblet 等 2026-06-25T01:47:17Z 置信度 0.70
• Improving Trustworthiness in Vision-Language Model with Synthetic Preference Data Alignment
  Large Vision-Language Models (LVLMs) have shown promising capabilities in understanding and generating information by integrating both visual and textual data. However, current models are still prone to hallucinations, which degrade the performance and greatly…
  crossref Robert Wijaya, Ngoc-Bao Nguyen, Ngai-Man Cheung 2026-07-01T18:30:17Z 置信度 0.70
• Vision Language Action for TurtleBot Mobile Robot Path Planning
  crossref Noor Oush, Reza Alirezaee, Saeed Mozaffari, Shahpour Alirezaee 2026-07-07T19:43:15Z 置信度 0.70
• Metamorphic Testing of Vision–Language Action–Enabled Robots
  crossref Pablo Valle, Sergio Segura, Shaukat Ali, Aitor Arrieta 2026-07-16T21:48:20Z 置信度 0.70
• Exploring Policy Distillation for Vision-Language-Action Generalist Robotic Policies
  crossref Ingook Jang, Samyeul Noh, Seonghyun Kim 2026-02-19T20:55:29Z 置信度 0.70
• <b>VLA-Touch: Enhancing Vision-Language-Action Model With Dual-Level Tactile Feedback</b>
  crossref Jianxin Bi, Kevin Yuchen Ma, Ce Hao, Mike Shou Zheng 等 2026-05-11T19:48:18Z 置信度 0.70
• From Language to Action: Small Language Model—Driven Humanoid Control with Visual Grounding Under the Model Context Protocol
  crossref Rhimesh Lwagun, John Yare, Justin Lukose, Olasubomi Rufai 等 2026-04-20T20:01:37Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2026-06-19T09:22:57Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2026-06-19T09:22:57Z 置信度 0.70
• Edge-based multimodal sensor data fusion with Vision-Language-Action (VLA) model for real-time autonomous vehicle accident avoidance
  crossref Fengze Yang, Bo Yu, Yang Zhou, Xuewen Luo 等 2026-05-26T12:19:49Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2020-11-13T16:04:15Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2020-11-13T21:04:15Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2026-06-19T09:22:57Z 置信度 0.70
• A neural model of the visual tuning properties of action-selective neurons in STS and area F5
  crossref F. Fleischer, A. Casile, M. Giese 2010-06-04T12:30:50Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2020-11-13T16:04:15Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2020-11-13T21:04:15Z 置信度 0.70
• Innovating sentences model
  crossref Alison Wilcox, Adam Bushnell 2026-06-19T09:22:57Z 置信度 0.70
• MDS-based Multi-axial Dimensionality Reduction Model for Human Action Recognition
  crossref Redha Touati, Max Mignotte 2014-05-30T14:26:22Z 置信度 0.70
• APEC Vision: Action Agenda/Action Plan
  crossref 2013-10-07T13:04:52Z 置信度 0.70
• Hierarchical vision-language model with comprehensive language description for video anomaly detection
  crossref Muaz Al Radi, Sajid Javed 2026-02-02T16:34:02Z 置信度 0.70
• Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations
  crossref Sparsh Garg, Abhishek Aich 2026-02-23T20:44:02Z 置信度 0.70
• CoMAP: Cross-Modal Attentive Prompt Generation for Vision-Language Model Adaptation
  crossref Hongyu Bai, Haolong Wang, Genke Yang 2026-08-17T19:14:40Z 置信度 0.70
• NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation
  crossref Peiran Xu, Xicheng Gong, Yadong Mu 2026-04-29T19:45:49Z 置信度 0.70
• VisionCube: 3D-Aware Vision-Language Model for Multi-Step Spatial Reasoning
  crossref Feiyang Wang, Nan Luo, Wangyu Wu 2025-09-15T17:35:52Z 置信度 0.70
• When Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and Noise
  crossref Philip Wootaek Shin, Ajay Narayanan Sridhar, Lakshmi Sivani Devarapalli, Rui Zhang 等 2026-07-01T12:25:50Z 置信度 0.70
• VLA-Bridge: A Parameter-Efficient Adaptation Framework for Lightweight Vision-Language-Action Modeling
  The integration of visual perception, natural language understanding, and continuous motor control has led to the emergence of Vision-Language-Action models. These models demonstrate unprecedented generalization capabilities in embodied artificial intelligence…
  crossref Michael Reynolds, Noah Sato 2026-07-09T04:42:21Z 置信度 0.70
• Vision-Language Model with Multimodal Alignment using Variational AutoEncoder and Contrastive Learning
  crossref Eunseo Jeong, Gyunyeop Kim, Sangwoo Kang 2023-11-24T03:44:03Z 置信度 0.70
• MVLP: Multi-perspective Vision-Language Pre-training Model for Ethically Aligned Meme Detection
  Ethically aligned design aims to ensure that intelligent systems remain human-centric, serving humanity’s values and ethical principles. Moderating content for achieving ethically aligned design is a critical step toward the realization of trustworthy AI. Howe…
  crossref Ning Zhang, Xuan Feng, Tianlong Gu, Liang Chang 2023-07-20T15:42:46Z 置信度 0.70
• Foundation Models for Construction Robotics: Transfer Learning and Vision-Language-Action Integration
  Abstract: This paper investigates the adaptation of pre-trained robotics foundation models, specifically RT-2 and PaLM-E, for construction automation applications. This research explores transfer learning methodologies across diverse construction tasks, develo…
  crossref Sai Kothapalli 2025-12-25T12:52:21Z 置信度 0.70
• Review of: "Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability"
  crossref Ravi Varma Kumar Bevara Bevara 2025-02-15T09:36:16Z 置信度 0.70
• Bridging Slow Reasoning and Fast Acting: A Dual-System Survey of Vision-Language-Action Architectures
  The Vision-Language-Action (VLA) model faces basic challenges in actual physical deployment, including reasoning delay, opaque decision-making, and insufficient generalization ability. Existing research mainly focuses on data size and training strategies, and …
  crossref Zan Zheng, Jin Huang, Chao Wang, Xi Tan 等 2026-07-18T20:45:10Z 置信度 0.70
• Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task
  crossref Shailaja Keyur Sampat, Pratyay Banerjee, Yezhou Yang, Chitta Baral 2023-08-04T16:21:02Z 置信度 0.70
• MVLP: Multi-perspective Vision-Language Pre-training Model for Ethically Aligned Meme Detection
  &lt;p&gt;Ethically aligned design aims to ensure that intelligent systems remain human-centric, serving humanity’s values and ethical principles. Moderating content for achieving ethically aligned design is a critical step toward the realization of trustworthy…
  crossref Ning Zhang, Xuan Feng, Tianlong Gu, Liang Chang 2023-07-20T19:42:47Z 置信度 0.70
• DiffV2IR: Visible-to-Infrared Diffusion Model via Vision-Language Understanding
  crossref Lingyan Ran, Lidong Wang, Guangcong Wang, Peng Wang 等 2026-01-12T14:49:29Z 置信度 0.70
• Space and the Vision–Language Interface: A Model-Theoretic Approach
  The relation between spatial vision and spatial language has always been a source of controversy. Three problems can be identified as in need of a solution. A first problem pertains to the nature of the minimal information units that make up spatial vision and…
  crossref Francesco-Alessio Ursini 2022-04-08T07:17:38Z 置信度 0.70
• X-VLM: All-In-One Pre-trained Model For Vision-Language Tasks_supp1-3339661.pdf
  crossref Yan Zeng 2024-01-08T14:42:04Z 置信度 0.70
• The catchment feature model for multimodal language analysis
  crossref Quek 2005-03-21T20:07:39Z 置信度 0.70
• Enhancing Clinical Reasoning in Medical Vision-Language Model through Structured Prompts
  Abstract Medical Vision-Language Models (MVLMs) are emerging as powerful tools for tasks such as Visual Question Answering (VQA); however, they often struggle with hallucination and limited reasoning transparency, particularly in complex diagnostic scenarios. …
  crossref Kavya Dasaramoole Prakash, Kiseong Kim, Youngmahn Han 2025-08-01T23:45:19Z 置信度 0.70
• (Lift) Lightweight Fitness Transformer: A Language-Vision Model for Remote Monitoring of Physical Training
  crossref Alex Postlmayr, Pamela Cosman, Sujit Dey 2025-07-02T14:37:38Z 置信度 0.70
• Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model
  We propose general visual inspection model using Vision-Language Model (VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high performance across vari…
  crossref Shiryu Ueno, Yoshikazu Hayashi, Shunsuke Nakatsuka, Yusei Yamada 等 2025-02-19T08:01:50Z 置信度 0.70
• FarSLIP: A Vision-Language Foundation Model for Fine-Grained Remote Sensing Understanding
  Vision-language foundation models (VLFMs), such as CLIP, have demonstrated remarkable generalizability across diverse downstream tasks, including both cross-modal and vision-centric tasks. Leveraging large-scale textual supervision, VLFMs capture a broad spect…
  crossref Zhenshi Li, Xueliang Zhang, Pengfeng Xiao, XiaoXiang Zhu 2026-03-14T01:11:56Z 置信度 0.70
• A vision–language foundation model for clinical oncology
  crossref Eleni Skourti 2025-02-18T10:03:19Z 置信度 0.70
• A Vision for Innovation in Preservice Teaching: The Evaluation of a Model Program
  crossref G. Linda Rikard, Betty Beacham 2012-01-05T21:26:52Z 置信度 0.70
• CAL: USING CONSTRAINTS WITH ACTION LANGUAGE FOR AUTOMATING MODEL EVOLUTION1
  crossref Shahid Alam 2013-07-03T18:22:14Z 置信度 0.70
• Using Model Transformation Language Semantics for Aspects Composition
  crossref Samuel A., Dorina Petriu, Pantanowitz Motshegw 2012-05-04T10:50:57Z 置信度 0.70
• Vision Language Model Helps Private Information De-Identification in Vision Data
  crossref Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen 等 2025-08-04T09:54:03Z 置信度 0.70
• Learning Visual Grounding from Generative Vision and Language Model
  crossref Shijie Wang, Dahun Kim, Ali Taalimi, Chen Sun 等 2025-04-08T17:08:13Z 置信度 0.70
• Research on vision-sensor-language multimodal model for knee joint risk early warning in squat training
  crossref Guanxiong Wang 2026-07-26T16:14:39Z 置信度 0.70
• Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation
  crossref Difei Gu, Yunhe Gao, Mu Zhou, Dimitris Metaxas 2026-05-05T19:59:32Z 置信度 0.70