具身智能 · 全部实体（第 91 / 100 页）

本页收录第 9001–9100 条，共 10000 条 · 返回 具身智能 首页

• Annotating Cognates and Etymological Origin in Turkic Languages
  Turkic languages exhibit extensive and diverse etymological relationships among lexical items. These relationships make the Turkic languages promising for exploring automated translation lexicon induction by leveraging cognate and other etymological informatio…
  arxiv Benjamin S. Mericli, Michael Bloodgood 2015-01-13T22:14:57Z 置信度 0.78 cs.CL
• Introducing MELI: the Mandarin-English Language Interview Corpus
  We introduce the Mandarin-English Language Interview (MELI) Corpus, an open-source resource of 29.8 hours of speech from 51 Mandarin-English bilingual speakers. MELI combines matched sessions in Mandarin and English with two speaking styles: read sentences and…
  arxiv Suyuan Liu, Molly Babel 2026-03-27T23:15:30Z 置信度 0.78 cs.CL
• LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning
  Designing realistic multi-object scenes requires not only generating images, but also planning spatial layouts that respect semantic relations and physical plausibility. On one hand, while recent advances in diffusion models have enabled high-quality image gen…
  arxiv Zezhong Fan, Xiaohan Li, Luyi Ma, Kai Zhao 等 2025-09-24T20:41:04Z 置信度 0.78 cs.CVcs.AIcs.LG
• LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
  Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their efficacy. This paper presents a comprehensive evaluation of publicly available …
  arxiv Peng Xu, Wenqi Shao, Kaipeng Zhang, Peng Gao 等 2023-06-15T16:39:24Z 置信度 0.78 cs.CVcs.AI
• Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Prompting
  Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources and privacy regulations. Recent advances …
  arxiv Phillip Richter-Pechanski, Philipp Wiesenbach, Dominic M. Schwab, Christina Kiriakou 等 2024-03-20T08:01:33Z 置信度 0.78 cs.CLcs.AIcs.LG
• Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
  While autoregressive Large Vision-Language Models (VLMs) have achieved remarkable success, their sequential generation often limits their efficacy in complex visual planning and dynamic robotic control. In this work, we investigate the potential of constructin…
  arxiv Jiacheng Ye, Shansan Gong, Jiahui Gao, Junming Fan 等 2025-12-27T14:46:24Z 置信度 0.78 cs.CVcs.CL
• Large Language Models and Multimodal Retrieval for Visual Word Sense Disambiguation
  Visual Word Sense Disambiguation (VWSD) is a novel challenging task with the goal of retrieving an image among a set of candidates, which better represents the meaning of an ambiguous word within a given context. In this paper, we make a substantial step towar…
  arxiv Anastasia Kritharoula, Maria Lymperaiou, Giorgos Stamou 2023-10-21T14:35:42Z 置信度 0.78 cs.CL
• Robust Language Identification for Romansh Varieties
  The Romansh language has several regional varieties, called idioms, which sometimes have limited mutual intelligibility. Despite this linguistic diversity, there has been a lack of documented efforts to build a language identification (LID) system that can dis…
  arxiv Charlotte Model, Sina Ahmadi, Jannis Vamvas 2026-03-16T22:42:10Z 置信度 0.78 cs.CL
• Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision
  Transformer architectures have brought about fundamental changes to computational linguistic field, which had been dominated by recurrent neural networks for many years. Its success also implies drastic changes in cross-modal tasks with language and vision, an…
  arxiv Andrew Shin, Masato Ishii, Takuya Narihira 2021-03-06T05:44:27Z 置信度 0.78 cs.CVcs.CL
• Fast Vocabulary Transfer for Language Model Compression
  Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our res…
  arxiv Leonidas Gee, Andrea Zugarini, Leonardo Rigutini, Paolo Torroni 2024-02-15T14:37:07Z 置信度 0.78 cs.CLcs.AIcs.LG
• Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models
  Recent incidents in certain online games and communities, where anonymity is guaranteed, show that unchecked inappropriate remarks frequently escalate into verbal abuse and even criminal behavior, raising significant social concerns. Consequently, there is a g…
  arxiv Ju-Young Kim, Ji-Hong Park, Se-Yeon Lee, Sujin Park 等 2025-12-09T10:55:33Z 置信度 0.78 cs.CL
• Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection
  Vision-language alignment learned from image-caption pairs has been shown to benefit tasks like object recognition and detection. Methods are mostly evaluated in terms of how well object class names are learned, but captions also contain rich attribute context…
  arxiv Kyle Buettner, Adriana Kovashka 2023-03-17T16:14:37Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• How Important Is Tokenization in French Medical Masked Language Models?
  Subword tokenization has become the prevailing standard in the field of natural language processing (NLP) over recent years, primarily due to the widespread utilization of pre-trained language models. This shift began with Byte-Pair Encoding (BPE) and was late…
  arxiv Yanis Labrak, Adrien Bazoge, Beatrice Daille, Mickael Rouvier 等 2024-02-22T23:11:08Z 置信度 0.78 cs.CLcs.AIcs.LG
• Multimodal Attention Networks for Low-Level Vision-and-Language Navigation
  Vision-and-Language Navigation (VLN) is a challenging task in which an agent needs to follow a language-specified path to reach a target destination. The goal gets even harder as the actions available to the agent get simpler and move towards low-level, atomic…
  arxiv Federico Landi, Lorenzo Baraldi, Marcella Cornia, Massimiliano Corsini 等 2019-11-27T19:00:24Z 置信度 0.78 cs.CVcs.CLcs.LG
• Can Vision Language Models Understand Mimed Actions?
  Nonverbal communication (NVC) plays an integral role in human language, but studying NVC in general is challenging because of its broad scope and high variance in interpretation among individuals and cultures. However, mime -- the theatrical technique of sugge…
  arxiv Hyundong Cho, Spencer Lin, Tejas Srinivasan, Michael Saxon 等 2025-06-17T13:37:42Z 置信度 0.78 cs.CLcs.AIcs.CV
• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks
  Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both storage and c…
  arxiv Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu 等 2024-08-23T13:00:10Z 置信度 0.78 eess.AScs.AIcs.CLcs.LG
• Toward More Reliable Artificial Intelligence: Reducing Hallucinations in Vision-Language Models
  Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through uncertainty-guided visual re-a…
  arxiv Kassoum Sanogo, Renzo Ardiccioni 2025-12-08T13:58:46Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• Chitrakshara: A Large Multilingual Multimodal Dataset for Indian languages
  Multimodal research has predominantly focused on single-image reasoning, with limited exploration of multi-image scenarios. Recent models have sought to enhance multi-image understanding through large-scale pretraining on interleaved image-text datasets. Howev…
  arxiv Shaharukh Khan, Ali Faraz, Abhinav Ravi, Mohd Nauman 等 2026-03-06T15:01:25Z 置信度 0.78 cs.CLcs.AIcs.CV
• Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models
  Consistency under paraphrase, the property that semantically equivalent prompts yield identical predictions, is increasingly used as a proxy for reliability when deploying medical vision-language models (VLMs). We show this proxy is fundamentally flawed: a mod…
  arxiv Binesh Sadanandan, Vahid Behzadan 2026-03-22T00:06:53Z 置信度 0.78 cs.CV
• Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning
  Large Vision-Language Models (LVLMs) typically follow a two-stage training paradigm-pretraining and supervised fine-tuning. Recently, preference optimization, derived from the language domain, has emerged as an effective post-training reinforcement strategy to…
  arxiv Yufei Zhan, Yousong Zhu, Shurong Zheng, Hongyin Zhao 等 2025-03-23T10:21:14Z 置信度 0.78 cs.CVcs.AI
• Unified Vision-Language-Action Model
  Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to genera…
  arxiv Yuqi Wang, Xinghang Li, Wenxuan Wang, Junbo Zhang 等 2025-06-24T17:59:57Z 置信度 0.78 cs.CVcs.RO
• Vision-Language Model Based Handwriting Verification
  Handwriting Verification is a critical in document forensics. Deep learning based approaches often face skepticism from forensic document examiners due to their lack of explainability and reliance on extensive training data and handcrafted features. This paper…
  arxiv Mihir Chauhan, Abhishek Satbhai, Mohammad Abuzar Hashemi, Mir Basheer Ali 等 2024-07-31T17:57:32Z 置信度 0.78 cs.CVcs.AIcs.CLcs.LG
• Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities
  The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) have shown their promise in solving a wide variety of language and vision understan…
  arxiv Jinhua Liang, Xubo Liu, Wenwu Wang, Mark D. Plumbley 等 2023-11-30T23:43:59Z 置信度 0.78 eess.AS
• On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
  Vision-Language Models (VLMs) are increasingly used as perceptual modules for visual content reasoning, including through captioning and DeepFake detection. In this work, we expose a critical vulnerability of VLMs when exposed to subtle, structured perturbatio…
  arxiv Jordan Vice, Naveed Akhtar, Yansong Gao, Richard Hartley 等 2025-07-30T05:41:29Z 置信度 0.78 cs.CV
• Domain Adaptation with a Single Vision-Language Embedding
  Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in real-world autonomous driving scenarios, especially under rare or adverse conditions. In…
  arxiv Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez 等 2024-10-28T17:59:53Z 置信度 0.78 cs.CVcs.LG
• Turkish Native Language Identification V2
  This paper presents the first application of Native Language Identification (NLI) for the Turkish language. NLI is the task of automatically identifying an individual's native language (L1) based on their writing or speech in a non-native language (L2). While …
  arxiv Ahmet Yavuz Uluslu, Gerold Schneider 2023-07-27T13:28:31Z 置信度 0.78 cs.CL
• Survey of Vision-Language-Action Models for Embodied Manipulation
  Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models…
  arxiv Haoran Li, Yuhui Chen, Wenbo Cui, Weiheng Liu 等 2025-08-21T03:30:04Z 置信度 0.78 cs.ROcs.AI
• Spatial Monitoring and Insect Behavioural Analysis Using Computer Vision for Precision Pollination
  Insects are the most important global pollinator of crops and play a key role in maintaining the sustainability of natural ecosystems. Insect pollination monitoring and management are therefore essential for improving crop production and food security. Compute…
  arxiv Malika Nisal Ratnayake, Don Chathurika Amarathunga, Asaduz Zaman, Adrian G. Dyer 等 2022-05-10T05:11:28Z 置信度 0.78 cs.CVq-bio.QM
• TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints
  Reasoning about fine-grained spatial relationships in warehouse-scale environments poses a significant challenge for existing vision-language models (VLMs), which often struggle to comprehend 3D layouts, object arrangements, and multimodal cues in real-world i…
  arxiv Vinh-Thuan Ly, Hoang M. Truong, Xuan-Huong Nguyen 2025-08-25T01:36:22Z 置信度 0.78 cs.CV
• DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
  Large vision-language models (VLMs) have made great achievements in Earth vision. However, complex disaster scenes with diverse disaster types, geographic regions, and satellite sensors have posed new challenges for VLM applications. To fill this gap, we curat…
  arxiv Junjue Wang, Weihao Xuan, Heli Qi, Zhihao Liu 等 2025-05-27T12:16:07Z 置信度 0.78 cs.CV
• Semi-Supervised Vision-Language-Action Model
  Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depends on costly action-labeled demonstrations. To reduce this dependence, we study s…
  arxiv Hongyang He, Jiuming Liu, Victor Sanchez 2026-06-19T14:42:52Z 置信度 0.78 cs.CVcs.ET
• Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
  Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational review presents a compr…
  arxiv Ranjan Sapkota, Yang Cao, Konstantinos I. Roumeliotis, Manoj Karkee 2025-05-07T19:46:43Z 置信度 0.78 cs.CV
• Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition
  Feature shifts have been shown to be useful for action recognition with CNN-based models since Temporal Shift Module (TSM) was proposed. It is based on frame-wise feature extraction with late fusion, and layer features are shifted along the time direction for …
  arxiv Ryota Hashiguchi, Toru Tamaki 2022-04-01T14:06:19Z 置信度 0.78 cs.CV
• Bootstrapping Vision-language Models for Self-supervised Remote Physiological Measurement
  Facial video-based remote physiological measurement is a promising research area for detecting human vital signs (e.g., heart rate, respiration frequency) in a non-contact way. Conventional approaches are mostly supervised learning, requiring extensive collect…
  arxiv Zijie Yue, Miaojing Shi, Hanli Wang, Shuai Ding 等 2024-07-11T13:45:50Z 置信度 0.78 cs.CV
• Grounding Synthetic Data Generation With Vision and Language Models
  Deep learning models benefit from increasing data diversity and volume, motivating synthetic data augmentation to improve existing datasets. However, existing evaluation metrics for synthetic data typically calculate latent feature similarity, which is difficu…
  arxiv Ümit Mert Çağlar, Alptekin Temizel 2026-03-10T13:03:53Z 置信度 0.78 cs.CVcs.AI
• Effects of Language Modeling on Speech-driven Question Answering
  We integrate automatic speech recognition (ASR) and question answering (QA) to realize a speech-driven QA system, and evaluate its performance. We adapt an N-gram language model to natural language questions, so that the input of our system can be recognized w…
  arxiv Tomoyosi Akiba, Atsushi Fujii, Katunobu Itou 2004-07-10T11:57:17Z 置信度 0.78 cs.CL
• Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks
  The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability. However, SLMs often struggle with complex vision-based tasks, such as grading handwritten student exams, due to the…
  arxiv Lachlan McGinness 2026-07-21T06:49:24Z 置信度 0.78 cs.CVcs.AIcs.CL
• Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents
  Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines. However, LLMs are optimized for language generation instead of tool use during training or alignment, limiting their …
  arxiv Renxi Wang, Haonan Li, Xudong Han, Yixuan Zhang 等 2024-02-18T17:10:07Z 置信度 0.78 cs.CL
• Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality
  In this study, we delve into the validity of conventional personality questionnaires in capturing the human-like personality traits of Large Language Models (LLMs). Our objective is to assess the congruence between the personality traits LLMs claim to possess …
  arxiv Yiming Ai, Zhiwei He, Ziyin Zhang, Wenhong Zhu 等 2024-02-22T16:32:08Z 置信度 0.78 cs.CLcs.CY
• Does Explainable Machine Learning Uncover the Black Box in Vision Applications?
  Machine learning (ML) in general and deep learning (DL) in particular has become an extremely popular tool in several vision applications (like object detection, super resolution, segmentation, object tracking etc.). Almost in parallel, the issue of explainabi…
  arxiv Manish Narwaria 2021-12-18T10:37:52Z 置信度 0.78 cs.CVcs.LG
• GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models
  Recent large vision-language models (LVLMs) have advanced capabilities in visual question answering (VQA). However, interpreting where LVLMs direct their visual attention remains a significant challenge, yet is essential for understanding model behavior. We in…
  arxiv Guanxi Shen 2025-06-23T18:00:04Z 置信度 0.78 cs.CVcs.AI
• THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
  Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated and insufficient for domain-specific needs, lacking a standardized pipeline. This…
  arxiv Mengfei Liang, Archish Arun, Zekun Wu, Cristian Munoz 等 2024-09-17T16:55:25Z 置信度 0.78 cs.CL
• Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition
  Automatic dietary assessment based on food images remains a challenge, requiring precise food detection, segmentation, and classification. Vision-Language Models (VLMs) offer new possibilities by integrating visual and textual reasoning. In this study, we eval…
  arxiv Sergio Romero-Tapiador, Ruben Tolosana, Blanca Lacruz-Pleguezuelos, Laura Judith Marcos Zambrano 等 2025-04-09T14:33:59Z 置信度 0.78 cs.CVcs.AI
• Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces
  Vision-and-Language Navigation (VLN) refers to the task of enabling autonomous robots to navigate unfamiliar environments by following natural language instructions. While recent Large Vision-Language Models (LVLMs) have shown promise in this task, most curren…
  arxiv Vebjørn Haug Kåsene, Pierre Lison 2025-08-04T21:45:21Z 置信度 0.78 cs.CVcs.AIcs.CLcs.RO
• VLSlice: Interactive Vision-and-Language Slice Discovery
  Recent work in vision-and-language demonstrates that large-scale pretraining can learn generalizable models that are efficiently transferable to downstream tasks. While this may improve dataset-scale aggregate metrics, analyzing performance around hand-crafted…
  arxiv Eric Slyman, Minsuk Kahng, Stefan Lee 2023-09-13T04:02:38Z 置信度 0.78 cs.CVcs.CLcs.HCcs.LG
• Evaluation of Vision-LLMs in Surveillance Video
  The widespread use of cameras in our society has created an overwhelming amount of video data, far exceeding the capacity for human monitoring. This presents a critical challenge for public safety and security, as the timely detection of anomalous or criminal …
  arxiv Pascal Benschop, Cristian Meo, Justin Dauwels, Jelte P. Mense 2025-10-27T10:27:02Z 置信度 0.78 cs.CV
• Segment and Select: Vision-Language Segmentation in 3D Scenarios
  3D vision-language segmentation aims to segment target objects in 3D scenarios according to the linguistic instructions and visual observations. Prior art heavily relies on the coarse superpoint representation to reduce the computation complexity, which suffer…
  arxiv Yulin Chen, Zhihang Zhong, Yuenan Hou 2026-06-09T08:58:59Z 置信度 0.78 cs.CV
• A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility
  Vision-language navigation (VLN), in which an agent follows language instruction in a visual environment, has been studied under the premise that the input command is fully feasible in the environment. Yet in practice, a request may not be possible due to lang…
  arxiv Andrea Burns, Deniz Arsan, Sanjna Agrawal, Ranjitha Kumar 等 2022-02-04T18:51:50Z 置信度 0.78 cs.CLcs.CVcs.HC
• Ego: Embedding-Guided Personalization of Vision-Language Models
  AI assistants that support humans in daily life are becoming increasingly feasible, driven by the rapid advancements in multimodal language models. A key challenge lies in overcoming the generic nature of these models to deliver personalized experiences. Exist…
  arxiv Soroush Seifi, Simon Gardier, Vaggelis Dorovatas, Daniel Olmeda Reino 等 2026-03-10T15:10:41Z 置信度 0.78 cs.CVcs.AI
• Data Augmentation for Vision-Language-Action Models
  crossref Miaosen Zhou 2026-07-31T15:10:19Z 置信度 0.70
• On the mapping between spatial language and the vision and action systems
  crossref 2020-12-21T23:07:48Z 置信度 0.70
• Temporal Action Detection Using a Statistical Language Model
  crossref Alexander Richard, Juergen Gall 2016-12-13T01:38:49Z 置信度 0.70
• VLA-Touch: Enhancing Vision-Language-Action Model with Dual-Level Tactile Feedback_supp1-3692345.mp4
  crossref Jianxin Bi 2026-05-14T21:54:12Z 置信度 0.70
• A Vision of ‘Vision and Language’ Comprises Action: An Example from Road Traffic
  crossref Hans-Hellmut Nagel 2011-08-21T23:40:23Z 置信度 0.70
• A Dual-System Vision-Language-Action Model for Rational Manipulation_supp1-3658581.pdf
  crossref Haoang Li 2026-02-19T20:57:54Z 置信度 0.70
• Vision-Language-Action Model Enabling Continuum Robots in Aeroengine Blade In-Situ Inspection
  crossref Shaoxuan Suo, Changlong Zhang, Bing han, Zexi Jin 等 2025-07-14T21:37:47Z 置信度 0.70
• Transforming the vision into action
  crossref 2021-09-17T05:43:01Z 置信度 0.70
• The Interface of Language, Vision, and Action
  crossref John Henderson, Fernanda Ferreira 2014-03-14T08:48:13Z 置信度 0.70
• Time-aware failure detection for vision-language-action models in robot manipulation
  crossref Tianrui Ma 2026-08-06T04:42:20Z 置信度 0.70
• CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
  crossref Peng Chen, Pi Bu, Yingyao Wang, Xinyi Wang 等 2026-04-29T19:45:49Z 置信度 0.70
• CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
  crossref Ziyu Yao, Xuxin Cheng, Zhiqi Huang, Lei Li 2025-08-13T17:26:42Z 置信度 0.70
• Large Language Model‐Based Spatio‐Temporal Semantic Enhancement for Skeleton Action Understanding
  ABSTRACT Skeleton‐based temporal action segmentation aims to segment and classify human actions in untrimmed skeletal sequences. Existing methods struggle with distinguishing transition poses between adjacent frames and fail to adequately capture semantic depe…
  crossref Ran Wei, Hui Jie Zhang, Chang Cao, Fang Zhang 等 2025-09-14T17:35:32Z 置信度 0.70
• DiTEA: Mixture-of-Experts for Vision-Language-Action Model in Robotic Manipulation
  The current diffusion-based Vision-Language-Action (VLA) models have faster inference speed and the ability to solve the action muti-modality problem in robot manipulation tasks compared to traditional autoregressive models after large-scale pre-training and p…
  crossref Chengxuan Li, Xingwan Wang 2026-03-18T01:00:28Z 置信度 0.70
• Data-Driven Robotics: Vision–Language–Action Learning for Robust Manipulation and Autonomy
  Abstract: This manuscript develops a rigorous academic framework for data-driven robotics with particular emphasis on vision-language-action learning for robust manipulation and autonomy. It brings together foundations of embodied intelligence, uncertainty man…
  crossref Murali Krishna Pasupuleti 2026-03-23T02:44:41Z 置信度 0.70
• ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
  crossref Thinh Phan, Khoa Vo, Duy Le, Gianfranco Doretto 等 2024-04-09T13:36:09Z 置信度 0.70
• MiniUAV-VLA: A Compact Vision–Language–Action Model for Cooperative Multi-UAV Search and Elimination via MARL Expert Distillation
  Coordinating multiple unmanned aerial vehicles (UAVs) for cooperative missions requires agents that perceive their environment, reason about objectives, and generate joint actions. Vision–language–action (VLA) models unify these capabilities but lack a princip…
  crossref Hongwei Han, Guanghong Gong, Ni Li 2026-07-27T14:08:14Z 置信度 0.70
• Digital Hieroglyphs: Orthogonal Composite Tokens for Vision-Language-Action Models
  Vision-Language-Action (VLA) models for embodied AI face a fundamental representation challenge: text, images, and motor commands exist in incompatible modality spaces that must be "translated" through separate encoders and adapters. Current approaches either …
  crossref Xinmin Fang, Lingfeng Tao, Zhengxiong Li 2026-02-06T23:19:02Z 置信度 0.70
• Language Model Guided Interpretable Video Action Reasoning
  crossref Ning Wang, Guangming Zhu, HS Li, Liang Zhang 等 2024-09-16T13:34:53Z 置信度 0.70
• Biophysically plausible neural model for the interaction between action observation and action execution
  crossref Mohammad Hovaidi Ardestani, Martin Giese 2016-09-06T19:42:21Z 置信度 0.70
• Multi-Modal Alignment in AGI: Ensuring Coherent Safety Across Vision, Language, and Action Systems
  crossref Soham Khadse 2025-09-19T09:21:13Z 置信度 0.70
• Context-Aware Vision Language Model for Action Recognition
  crossref Eddie Zhang, Yupeng Zhuo, Juan Wachs 2026-01-02T00:07:58Z 置信度 0.70
• Generating Tennis Action Instruction Based on a Large Language Model
  crossref Zhiyuan Wang, Zhiqian Xia, Guangyao Zhao, Kaiyue Lu 等 2026-02-23T20:44:02Z 置信度 0.70
• 'Vision in Action': a Note on Syntax
  crossref 2020-12-22T05:49:44Z 置信度 0.70
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
  crossref Borong Zhang, Yuhao Zhang, Jiaming Ji, Yingshan Lei 等 2026-08-06T14:44:29Z 置信度 0.70
• VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
  crossref Yating Wang, Haoyi Zhu, Mingyu Liu, Jiange Yang 等 2026-04-29T19:45:49Z 置信度 0.70
• ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
  crossref Zhongyi Zhou, Yichen Zhu, Xiaoyu Liu, Zhibin Tang 等 2026-08-06T14:44:29Z 置信度 0.70
• AN ASSOCIATIVE MODEL OF CORTICAL LANGUAGE AND ACTION PROCESSING
  crossref ANDREAS KNOBLAUCH, HEINER MARKERT, GUENTHER PALM 2007-06-08T01:49:12Z 置信度 0.70
• Assessment of a Fine-Tuned Vision-Language-Action Model for Robotic Feature-Following Inspection
  Abstract Modern manufacturing increasingly relies on robotics to achieve high throughput and quality, especially as production lines become more flexible and parts more customized. Robotic inspection is a critical enabler for quality assurance as it supports r…
  crossref Martin Krüger, Mahmoud Salem, Markus Reischl 2026-05-29T14:24:53Z 置信度 0.70
• BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Model
  crossref Xiaoyu Ma, Zhengqing Yuan, Zheyuan Zhang, Kaiwen Shi 等 2026-05-28T17:14:56Z 置信度 0.70
• PeVL: Pose-Enhanced Vision-Language Model for Fine-Grained Human Action Recognition
  crossref Haosong Zhang, Mei Chee Leong, Liyuan Li, Weisi Lin 2024-09-16T13:34:53Z 置信度 0.70
• NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
  crossref Fawaz Sammani, Tanmoy Mukherjee, Nikos Deligiannis 2022-09-27T15:56:41Z 置信度 0.70
• RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing_supp1-3449154.pdf
  crossref Tiancheng Zhao 2024-09-13T13:59:56Z 置信度 0.70
• 11. The Language Model, the Geometric Model, and Common Sense
  crossref 2019-11-05T17:03:11Z 置信度 0.70
• Real-Time Language Processing as Embodied and Embedded in Joint Action
  crossref Lillian Rigoli, Michael J. Spivey 2015-07-13T09:01:15Z 置信度 0.70
• 7. The Action-oriented Approach
  crossref 2019-10-30T17:03:00Z 置信度 0.70
• Aerial Video Action Recognition with Pretrained Vision-Language Model
  crossref Yungeng Zhang, Yuan Chang, Zijian Cao, Xiaohou Shi 等 2026-04-21T21:25:57Z 置信度 0.70
• Quality-Guided Vision-Language Learning for Long-Term Action Quality Assessment_supp1-3599078.pdf
  crossref Xiao Ke 2025-08-20T18:43:09Z 置信度 0.70
• Bridging Retrospection and Prospection: A Vision-Language-Action Framework for Long-Horizon Manipulation
  Vision-language-action (VLA) models have achieved strong progress in language-conditioned robotic manipulation, but long-horizon tasks still require temporal information beyond the current observation. Existing methods explore temporal information from differe…
  crossref Chenyao Sun, Jiajun Li, Jian Zhang 2026-07-29T16:42:45Z 置信度 0.70
• MambaVLA: A Scalable and Efficient Vision-Language-Action Model with State Space Architecture
  crossref Sai Navaneet Peddapalli, Manisha Lingala, Sangmoon Lee, Ju H. Park 2026-02-04T20:45:15Z 置信度 0.70
• Soccer-CLIP: Vision Language Model for Soccer Action Spotting
  crossref Yoonho Shin, Sanghoon Park, Youngsub Han, Byoung-Ki Jeon 等 2025-03-06T18:44:47Z 置信度 0.70
• Dynamic Maclaurin-Series-Based Vision-Language-Action Model
  crossref Chong Yu, Zhongxue Gan 2026-04-13T19:38:01Z 置信度 0.70
• Attacks on Vision-Language-Action Robotic Systems: Mechanisms, Evaluation, and OpenProblems
  Vision-Language-Action (VLA) systems couple semantic perception and language conditioning to physical control, so a modellevel deviation does not by itself establish a robot-level attack. This survey studies VLA attacks as closed-loop causal processes. We trac…
  crossref Zijian Liu, Xutao Li, Jinhua Xie, Jian Fu 2026-07-22T07:08:09Z 置信度 0.70
• Feature distillation from vision-language model for semisupervised action classification
  The training of supervised machine learning approaches is critically dependent on annotating large-scale datasets. Semisupervised learning approaches aim to achieve compatible performance with supervised methods using relatively less annotation without sacrifi…
  crossref ASLI ÇELİK, AYHAN KÜÇÜKMANİSA, OĞUZHAN URHAN 2023-10-31T13:55:34Z 置信度 0.70
• Safety-Savvy Intersection Control Harnessing Vision Language Model
  crossref Abolfazl Afshari, Joyoung Lee, Yousef Mashal 2026-05-22T10:03:18Z 置信度 0.70
• Foundation Model Adaptation: From Vision-Language Pretraining to Medical Image Understanding
  crossref Hualiang Wang 2026-06-29T23:02:15Z 置信度 0.70
• VLA4CoDrive: Vision-Language-Action Dataset for Cooperative Autonomous Driving
  crossref Sayed Pedram Haeri Boroujeni, Abolfazl Razi 2026-08-04T19:18:49Z 置信度 0.70
• Sarashina2-Vision: Toward Vision – Language Models for Understanding Japanese Figures and Conceptual/Explanatory Diagrams
  crossref Seitaro Shinagawa 2025-10-24T14:57:49Z 置信度 0.70
• VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model
  crossref Beichen Wang, Juexiao Zhang, Shuwen Dong, Irving Fang 等 2025-11-27T18:54:45Z 置信度 0.70
• SPATIAL COGNITION IN ACTION - SCA MODEL: CHILDREN'S GESTURAL IMAGERY IN ACTION
  crossref M. PANAYI, D.M. ROY 2007-06-08T05:49:12Z 置信度 0.70
• Vision-Language Models for Vision Tasks: A Survey_supp1-3369699.pdf
  crossref Jingyi Zhang 2024-02-28T13:53:36Z 置信度 0.70