具身智能 · 全部实体（第 10 / 100 页）

本页收录第 901–1000 条，共 9964 条 · 返回 具身智能 首页

• Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
  Recent advancements in language models pre-trained on large-scale corpora have significantly propelled developments in the NLP domain and advanced progress in multimodal tasks. In this paper, we propose a Parameter-Efficient multimodal language model learning …
  crossref Tian Liang, Jing Huang, Ming Kong, Luyuan Chen 等 2024-09-16T17:34:53Z 置信度 0.82 cs.aics.lgcomputer and information sciencescs.clartificial intelligence
• Training A Small Emotional Vision Language Model for Visual Art Comprehension
  crossref Jing Zhang, Liang Zheng, Meng Wang, Dan Guo 2024-11-08T18:49:05Z 置信度 0.66
• The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains
  The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains Driven by Dean A. Kulik August, 2025 Abstract This thesis presents a comprehensive unification of the Nexus Framework across mathematics, physics, computation, biology, cognitive sci…
  datacite Kulik, Dean 2025 置信度 0.72
• The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains
  The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains Driven by Dean A. Kulik August, 2025 Abstract This thesis presents a comprehensive unification of the Nexus Framework across mathematics, physics, computation, biology, cognitive sci…
  datacite Kulik, Dean 2025 置信度 0.72
• The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains
  The Nexus Framework: A Unified Prestack for Emergent Structure Across Domains Driven by Dean A. Kulik August, 2025 Abstract This thesis presents a comprehensive unification of the Nexus Framework across mathematics, physics, computation, biology, cognitive sci…
  datacite Kulik, Dean 2025 置信度 0.72
• Theoretical Implications of Localized Stability in the Nexus Recursive Harmonic Framework
  Theoretical Implications of Localized Stability in the Nexus Recursive Harmonic Framework Driven by Dean KulikNovember 2025 Abstract This comprehensive research report investigates the theoretical foundations and systemic implications of a localized stability …
  datacite Kulik, Dean 2025 置信度 0.72
• Theoretical Implications of Localized Stability in the Nexus Recursive Harmonic Framework
  Theoretical Implications of Localized Stability in the Nexus Recursive Harmonic Framework Driven by Dean KulikNovember 2025 Abstract This comprehensive research report investigates the theoretical foundations and systemic implications of a localized stability …
  datacite Kulik, Dean 2025 置信度 0.72
• What is the impact of VLA model scale (7B vs 13B) on object grounding accuracy and path completion rate in Lon
  Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language model…
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 impactVLAmodelscaleobject
• What is the impact of VLA model scale (7B vs 13B) on object grounding accuracy and path completion rate in Lon
  Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language model…
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 impactVLAmodelscaleobject
• A Neuro-Symbolic Co-Pilot for Autonomous Driving: Post-Hoc Behavioral Discovery for Hierarchical Decision-Making
  In the quest for Level 5 autonomous driving, a critical cognitive bottleneck exists between high-frequency mechanical reflexes and low-frequency semantic reasoning. End-to-end Vision-Language-Action (VLA) models provide strong semantic reasoning but introduce …
  datacite Naoui, Fares, Saifi, Riyadh 2026 置信度 0.79 Machine learningDeep learningArtificial intelligenceArtificial IntelligenceAutonomous robots
• A Neuro-Symbolic Co-Pilot for Autonomous Driving: Post-Hoc Behavioral Discovery for Hierarchical Decision-Making
  In the quest for Level 5 autonomous driving, a critical cognitive bottleneck exists between high-frequency mechanical reflexes and low-frequency semantic reasoning. End-to-end Vision-Language-Action (VLA) models provide strong semantic reasoning but introduce …
  datacite Naoui, Fares, Saifi, Riyadh 2026 置信度 0.79 Machine learningDeep learningArtificial intelligenceArtificial IntelligenceAutonomous robots
• Эфирный Код: Сознание как Ключ к Континууму Вселенной. КНИГА I.
  Эфирный Код: Сознание как Ключ к Континууму Вселенной. КНИГА I. (Редакция от 09 июля 2026 г. с дополнениями)Автор : Зорин Юрий Леонидович**Аннотация**Данная работа представляет собой фундаментальный синтез науки и метафизики, предлагая целостную картину реальн…
  datacite Зорин, Юрий 2026 置信度 0.77 Rational Mechanics of ContinuumContinuum TheoryEther physicsinterpretation of the Michelson-Morley experiment
• Эфирный Код: Сознание как Ключ к Континууму Вселенной. КНИГА I.
  Эфирный Код: Сознание как Ключ к Континууму Вселенной. КНИГА I. (Редакция от 09 июля 2026 г. с дополнениями)Автор : Зорин Юрий Леонидович**Аннотация**Данная работа представляет собой фундаментальный синтез науки и метафизики, предлагая целостную картину реальн…
  datacite Зорин, Юрий 2026 置信度 0.77 Rational Mechanics of ContinuumContinuum TheoryEther physicsinterpretation of the Michelson-Morley experiment
• The Recursive Harmonic Architecture of Reality (RHA): A Comprehensive Blueprint
  The Recursive Harmonic Architecture of Reality (RHA): A Comprehensive Blueprint Introduction The Recursive Harmonic Architecture (RHA) is a unifying framework that portrays reality as a self-organizing, computational process driven by recursion, feedback, and …
  datacite kulik, dean 2025 置信度 0.72
• The Recursive Harmonic Architecture of Reality (RHA): A Comprehensive Blueprint
  The Recursive Harmonic Architecture of Reality (RHA): A Comprehensive Blueprint Introduction The Recursive Harmonic Architecture (RHA) is a unifying framework that portrays reality as a self-organizing, computational process driven by recursion, feedback, and …
  datacite kulik, dean 2025 置信度 0.72
• Visual Failure Detection in Robotics
  Autonomous robots in human-centric environments can encounter unforeseen situations, making them prone to task execution failures. These failures can lead to unsafe conditions for both humans and robots and result in a loss of trust in robots. Therefore, robot…
  datacite Thoduka, Santosh George 2026 置信度 0.79 visuelle FehlererkennungRobotikDeep LearningAnomalieerkennungVideoanalyse
• BBP and the Informational Mirror: A Recursive Harmonic Interpretation of Modular Access
  BBP and the Informational Mirror: A Recursive Harmonic Interpretation of Modular Access Driven By Dean a, Kulik August,2025 Introduction The Bailey–Borwein–Plouffe (BBP) formula for π is renowned as a “spigot” algorithm that can directly compute the $n$th digi…
  datacite kulik, dean 2025 置信度 0.72
• BBP and the Informational Mirror: A Recursive Harmonic Interpretation of Modular Access
  BBP and the Informational Mirror: A Recursive Harmonic Interpretation of Modular Access Driven By Dean a, Kulik August,2025 Introduction The Bailey–Borwein–Plouffe (BBP) formula for π is renowned as a “spigot” algorithm that can directly compute the $n$th digi…
  datacite kulik, dean 2025 置信度 0.72
• SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy
  Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--…
  datacite Li, Peiyan, Chen, Yixiang, Xu, Yuan, Yang, Jiabing 等 2026 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• The N-Body Problem: Parallel Execution from Single-Person Egocentric Video
  Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we introduce the N-Body Problem: predicting how N individuals, can hypothetically perform the same set of tasks. The…
  datacite Zhu, Zhifan, Huang, Yifei, Sato, Yoichi, Damen, Dima 2025 置信度 0.76 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
  Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limi…
  datacite Luo, Zhengyi, Yuan, Ye, Wang, Tingwu, Li, Chenran 等 2025 置信度 0.79 Robotics (cs.RO)Artificial Intelligence (cs.AI)Computer Vision and Pattern Recognition (cs.CV)Graphics (cs.GR)Systems and Control (eess.SY)
• UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
  Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks. However, their direct control over embodied agents also exposes them to advers…
  datacite Dai, Yukun, Dai, Mingzhe, Wang, Tianshi, Li, Fengling 等 2026 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving
  Reinforcement learning improves autonomous-driving vision-language-action (VLA) models by evaluating trajectories sampled from the current policy. Group relative policy optimization (GRPO) learns from reward differences within each rollout group. When all samp…
  datacite Dou, Hao 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
  Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control. The core challenge is structural: VLA inference is not a single bottleneck but a cascade o…
  datacite Li, Zekai, Liang, Yihao, Zhang, Hongfei, Chen, Jian 等 2026 置信度 0.76 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Enhancing Long-Horizon Household Robot Task Planning Using Vision-Language Models
  This paper presents VLM Household Planner, a reproducible embodied AI benchmark and closed-loop agent for long-horizon household robot task planning. The system uses a symbolic household simulator with a scene graph, container affordances, and preconditioned m…
  datacite Baig, Sultan 2026 置信度 0.79 household roboticsembodied AIvision language modelsrobotic manipulationhierarchical task planning
• Enhancing Long-Horizon Household Robot Task Planning Using Vision-Language Models
  This paper presents VLM Household Planner, a reproducible embodied AI benchmark and closed-loop agent for long-horizon household robot task planning. The system uses a symbolic household simulator with a scene graph, container affordances, and preconditioned m…
  datacite Baig, Sultan 2026 置信度 0.79 household roboticsembodied AIvision language modelsrobotic manipulationhierarchical task planning
• A Reproducible, Resource-Efficient Benchmark for Foundation-Model-Inspired Manipulation Learning with LeRobot and Open X-Embodiment
  This paper presents a reproducible, resource-efficient benchmark for foundation-model-inspired manipulation learning using LeRobot and the Open X-Embodiment dataset. Four policy architectures are implemented and evaluated under a standardised training and eval…
  datacite Baig, Sultan 2026 置信度 0.79 Robotic manipulationRobot learningEmbodied AIFoundational modelsLeRobot
• A Reproducible, Resource-Efficient Benchmark for Foundation-Model-Inspired Manipulation Learning with LeRobot and Open X-Embodiment
  This paper presents a reproducible, resource-efficient benchmark for foundation-model-inspired manipulation learning using LeRobot and the Open X-Embodiment dataset. Four policy architectures are implemented and evaluated under a standardised training and eval…
  datacite Baig, Sultan 2026 置信度 0.79 Robotic manipulationRobot learningEmbodied AIFoundational modelsLeRobot
• World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
  Vision-language-action (VLA) models are a widely adopted paradigm for embodied policies. They excel at efficient closed-loop control but do not explicitly model how physical scenes evolve as a task unfolds. Recently emerging world-action models (WAMs) leverage…
  datacite Tang, Qu, Zhuang, Benhui, Yuan, Bo, Yu, Xue 等 2026 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving
  Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation instructions directly to executable trajectories. However, in practice, these mode…
  datacite Hu, Meibo, Wang, Jiamian, Wang, Pichao, Tao, Zhiqiang 2026 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• Prompt-Driven Exploration
  Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy …
  datacite Jiang, Sunshine, Marangola, John, Zhang, David, Kowdeed, Raghuram 等 2026 置信度 0.77 Machine Learning (cs.LG)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation
  Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult …
  datacite Liu, Xingyuming, Ma, Ruichun, Guo, Heyu, Li, Qixiu 等 2026 置信度 0.77 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Robotic Manipulation is Vision-to-Geometry Mapping: Vision-Geometry Backbones over Language and Video Models
  At its core, robotic manipulation is a problem of vision-to-geometry mapping ($f(v) \rightarrow G$). Physical actions are fundamentally defined by geometric properties like 3D positions and spatial relationships. Consequently, we argue that the foundation for …
  datacite Song, Zijian, Li, Qichang, Zhou, Jiawei, Yuan, Zhenlong 等 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation
  Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the absence of long-term me…
  datacite Li, Zhuoran, Li, Zhiyang, Zhou, Kaijun, Gu, Jinyu 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• G0.5: One Autoregressive Stream for Robot Reasoning and Action
  The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder rather than a decision-maker. We introduce G0.5, a pretrained autoregressive VLA …
  datacite Liu, Yicheng, Dong, Zibin, Ye, Baijun, Yuan, Tianyuan 等 2026 置信度 0.77 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
  Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), when the scene, viewpoint, or object differs from training. Adapting to each new situation typically requires c…
  datacite Xu, Siyu, Wang, Yunke, Wang, Zijian, Zhu, Dihao 等 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• Multimodal models for understanding and assisting skilled activities
  Videos provide a powerful audio-visual medium for capturing and sharing skilled human activities in rich detail, such as cooking a favorite recipe or repairing a bicycle. They document a wide spectrum of learning contexts, from illustrating common pitfalls in …
  datacite Majumder, Sagnik 2026 置信度 0.77 Video understanding3D scene understandingVision-language modelsSkill understanding and assistanceAudio-visual models
• Imhotep Infinity — A Proposed Unified Framework from Ψ = 100/99: Papers 1–12, Final Referee-Cleaned Edition
  This record contains the complete twelve-paper Imhotep Infinity series, Final Referee-Cleaned Edition (May 2026). All papers are Iron Rule clean: derivation-layer mathematics flows only from the 45 Vision postulates and the single arithmetic generator Ψ = 100/…
  datacite Ramada, Ahmad A M 2026 置信度 0.79 unified framework(4-(m-Chlorophenylcarbamoyloxy)-2-butynyl)trimethylammonium ChlorideVision postulatesquantum gravityStandard Model
• Imhotep Infinity — A Proposed Unified Framework from Ψ = 100/99: Papers 1–12, Final Referee-Cleaned Edition
  This record contains the complete twelve-paper Imhotep Infinity series, Final Referee-Cleaned Edition (May 2026). All papers are Iron Rule clean: derivation-layer mathematics flows only from the 45 Vision postulates and the single arithmetic generator Ψ = 100/…
  datacite Ramada, Ahmad A M 2026 置信度 0.79 unified framework(4-(m-Chlorophenylcarbamoyloxy)-2-butynyl)trimethylammonium ChlorideVision postulatesquantum gravityStandard Model
• Hierarchical Fast-Slow ReAct Agent for Zero-Shot Object-Goal Navigation
  Zero-shot object-goal navigation (ZSON) requires a robot to find a named object category in a building it has never entered. The prevailing approach scores frontiers with a vision-language value map: every decision is another argmax over the map as it currentl…
  datacite Lan, Zhaochen, Yang, Zhi, Fu, Yuxiang, Lin, Mengxiang 2026 置信度 0.76 Robotics (cs.RO)FOS: Computer and information sciences
• HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
  Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based action heads make on-device deployment prohibitively expensive. Low-bit post-training quantization …
  datacite Wang, Xinyu, Li, Mingze, Lyu, Sicheng, Liu, Dongxiu 等 2026 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Machine Learning (cs.LG)FOS: Computer and information sciences
• ThinkAfford: Affordance-Centric Reasoning for Fine-Grained 3D Grounding in Cluttered Scenes
  Task-driven 3D affordance grounding aims to localize the functional region in a cluttered 3D scene that enables an action specified by a natural-language instruction. Existing methods either predict 3D masks directly or construct them by selecting and fusing i…
  datacite Lin, Xinrui, Zhang, Sha, Wang, Shumin, Zhu, Zenghuan 等 2026 置信度 0.76 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Mobile Robot Navigation Using Hand-Drawn Maps: A Vision Language Model Approach_supp1-3577456.mov
  crossref Aaron Hao Tan 2025-06-09T13:36:26Z 置信度 0.66
• Bridge Inspection Using A Multi-Modal Vision Language Model
  Using an Unmanned Aerial Vehicle (UAV) in bridge inspections can reduce human involvement in complex and hazardous inspection environments and automate the inspection process. Current practices require human operators to define task objectives, oversee safe fl…
  crossref Zhengxing Chen, Yang Zou, Vicente González, Jason Ingham 等 2025-08-28T22:10:13Z 置信度 0.82 artificial intelligencecs.aicomputer sciencecs.lgcomputer and information sciences
• A deep learning vision–language model for diagnosing pediatric dental diseases
  Automated diagnosis of pediatric dental diseases from panoramic radiographs remains challenging due to anatomical variability and limited availability of specialist expertise. Vision-language models offer a potential approach by integrating visual and textual …
  crossref Tuan D. Pham 2026-02-24T00:18:24Z 置信度 0.82 artificial intelligencemedicinecomputer sciencecs.lgcomputer and information sciences
• VLLFL: A Vision-Language Model Based Lightweight Federated Learning Framework for Smart Agriculture
  Abstract In modern smart agriculture, object detection plays a crucial role by enabling automation, precision farming, and monitoring of resources. From identifying crop health and pest infestations to optimizing harvesting processes, accurate object detection…
  crossref Long Li, Yanbo Huang, Jiajia Li, Dong Chen 等 2026-05-25T23:37:50Z 置信度 0.82 computer and information sciencescomputer sciencemachine learningcryptography and securityelectrical engineering, electronic engineering, information engineering
• ActionDiffusion: An Action-Aware Diffusion Model for Procedure Planning in Instructional Videos
  We present ActionDiffusion - a novel diffusion model for procedure planning in instructional videos that is the first to take temporal inter-dependencies between actions into account. Our approach is in stark contrast to existing methods that fail to exploit t…
  crossref Lei Shi, Paul Bürkner, Andreas Bulling 2025-04-08T17:08:13Z 置信度 0.82 cs.lgcs.aics.cvcomputer vision and pattern recognitioncomputer and information sciences
• 3-D model-based tracking of humans in action: a multi-view approach
  We present a vision system for the 3-D model-based tracking of unconstrained human movement. Using image sequences acquired simultaneously from multiple views, we recover the 3-D body pose at each time instant without the use of markers. The pose-recovery prob…
  crossref D.M. Gavrila, L.S. Davis 2002-12-23T18:52:33Z 置信度 0.75 cs.cvcs.aics.hccs.roreinforcement learning
• Domain-Specific EfficientNet-Transformer based Vision Language Model for Campus Navigation
  crossref Ashwija Mayya, Pushpajit Khaire, Mohammad Zaki 2026-07-20T20:18:02Z 置信度 0.66
• UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning
  Charts are widely used for data analysis, providing visual representations and insights into complex data.To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced recently such as chart question answering an…
  crossref Ahmed Masry, Parsa Kavehzadeh, Do Long, Enamul Hoque 等 2023-12-10T16:58:19Z 置信度 0.79 cs.aics.lgartificial intelligencecomputer and information sciencescomputer science
• KRCapVLM: Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model
  crossref Reem Al-Junaid, Qasim Umer, SAJJAD MAHMOOD, MAHMOOD NIAZI 等 2025-10-14T08:37:57Z 置信度 0.66
• Global evaluate-and-rescale network: an efficient model for action recognition
  Human action recognition in videos is a challenging task in the field of computer vision. Based on the idea of integrating temporal and spatial feature, many works have proposed a variety of methods for extracting spatiotemporal features, such as two-stream ne…
  crossref Jianbang Qin, Shuangjie Hu, Wei Guo 2020-01-31T15:03:45Z 置信度 0.79 computer and information sciencescomputer sciencecs.lgconvolutional neural networkelectrical engineering, electronic engineering, information engineering
• Vision–language model-based morphological scoring predicts cardiac spheroid functional outcomes
  A major bottleneck in human pluripotent stem cell (hPSC)-derived cardiac therapy is the approximately 10-day latency required to confirm functional beating, resulting in substantial resource loss when suboptimal cultures are maintained to end-stage without ear…
  crossref Santhi Raj Kolamuri, Yi-Hsien Fang, Yen-Wen Liu, Chenyu Huang 等 2026-03-18T03:38:36Z 置信度 0.82 medicinecs.aibiologycomputer and information sciencesbiotechnology
• KRCapVLM: Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model
  crossref Reem Al-Junaid, Muzammil Behzad, SAJJAD MAHMOOD, MAHMOOD NIAZI 等 2025-12-22T12:50:37Z 置信度 0.66
• COMPUTER VISION AND LARGE LANGUAGE MODEL-BASED SAFETY MANAGEMENT FOR CONSTRUCTION PROJECT SITES
  Construction sites are inherently hazardous environments where accidents and fatalities constitute a significant global concern.Despite continuous efforts to enhance safety, the incidence of workplace accidents within the construction industry remains elevated…
  crossref Bin Tang, Hanbin Luo 2025-08-11T11:58:43Z 置信度 0.82 computer scienceartificial intelligenceengineeringcomputer and information sciencescs.ai
• Prompt-Guided Vision-Language Model for Hyperspectral Image Classification with Limited Labeled Samples
  Hyperspectral images (HSIs), which uniquely integrate spatial features and continuous spectral signatures, exhibit great potential for fine-grained classification. Existing deep learning methods typically learn a direct end-to-end mapping between spatial-spect…
  crossref Hang Pei, Bing Liu, QI DONG, Yongqi Sun 等 2026-07-06T15:38:33Z 置信度 0.82 computer and information sciencesartificial intelligencecs.lgcs.cvcs.ai
• Diffusion-Head VLA Model for Adaptive UAV Vision-Language Navigation
  crossref Tanhui Lin, Qing Fei, Qingbo Geng 2026-06-24T19:47:19Z 置信度 0.66
• Language and Vision in the Epinician Poets
  This chapter explores the ways in which the other two contemporary epinician poets, Simonides and Bacchylides, use aesthetics and material culture as a way of drawing attention to their own individual and distinctive poetic voices and poetic agendas. Their aff…
  crossref David Fearn 2017-08-22T09:21:51Z 置信度 0.78 social and behavioral sciencescognitionphilosophycognitive neurosciencecognitive science
• Lightweight Vision-Language Model with Frequency-Domain Dynamic Filtering and Parallel Attention Interaction
  To address the limitations of existing dual-attention vision-language models, including poor feature representation quality, inefficient attention interaction, and difficulties in lightweight deployment, this paper proposes an enhanced vision-language model th…
  crossref Jiang Chu, Kai Chen, Dunbing Tang, Guoyu Fang 等 2026-04-16T03:40:31Z 置信度 0.82 computer and information sciencescomputer sciencecs.aiartificial intelligencecs.cv
• Action Recognition based on Subdivision-Fusion Model
  This paper proposes a novel Subdivision-Fusion Model (SFM) to recognize human actions. In most action recognition tasks, overlapping feature distribution is a common problem leading to overfitting. In the subdivision stage of the proposed SFM, samples in each …
  crossref Zongbo Hao, Linlin Lu, Qianni Zhang, Jie Wu 等 2015-12-23T11:54:07Z 置信度 0.78 convolutional neural networkcomputer sciencecs.lgcs.cvelectrical engineering, electronic engineering, information engineering
• Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
  Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and linguistic representations is not fully understood. This survey pr…
  crossref Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu 等 2025-01-24T06:47:07Z 置信度 0.82 cs.aidata sciencecomputer and information sciencescs.lgartificial intelligence
• End-to-End Model for Vision-Language Navigation Based on Pre-Trained Model
  Aiming at the problem that embodied intelligent mobile robots have difficulty in accurately navigating in unseen environments according to language instructions, this paper proposes an end-to-end model suitable for visual language navigation. The contextual re…
  crossref Mingyi Wu, Bin Feng, Weihua Fan, Yifei Feng 2025-09-09T17:29:36Z 置信度 0.82 computer and information sciencescs.rocs.cvcomputer sciencerobot
• Step 6: Develop a vision statement
  crossref 2025-10-24T07:02:40Z 置信度 0.63
• Advancements in Natural Language Processing and Crossmodal Intelligence
  Abstract—Natural language processing and vision tasks have recently seen large improvements through the rise of Trans- former architectures. The high-performing large language models (LLMs) benefit from large textual datasets that are numer- ously available on…
  datacite Muaz Bin Khalid 2026 置信度 0.79 (4-(m-Chlorophenylcarbamoyloxy)-2-butynyl)trimethylammonium Chloride/adverse effectsArtificial IntelligenceNatural language processingComputer Securitylanguage learning models
• Advancements in Natural Language Processing and Crossmodal Intelligence
  Abstract—Natural language processing and vision tasks have recently seen large improvements through the rise of Trans- former architectures. The high-performing large language models (LLMs) benefit from large textual datasets that are numer- ously available on…
  datacite Muaz Bin Khalid 2026 置信度 0.79 (4-(m-Chlorophenylcarbamoyloxy)-2-butynyl)trimethylammonium Chloride/adverse effectsArtificial IntelligenceNatural language processingComputer Securitylanguage learning models
• BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
  Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight inference wrapper that can …
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 inferencethroughputtokenspersecond
• BLURR: A Boosted Low-Resource Inference for Vision-Language-Action Models
  Vision-language-action (VLA) models enable impressive zero shot manipulation, but their inference stacks are often too heavy for responsive web demos or high frequency robot control on commodity GPUs. We present BLURR, a lightweight inference wrapper that can …
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 inferencethroughputtokenspersecond
• Singapore as Model for Ukraine Russia Peace: Proactive Leadership, Mediation and Hard Work
  Book Preface: The Scars of War, the Promise of Peace In the early months of 1942, as the world was engulfed in the flames of the Second World War, the people of Singapore found themselves on the frontlines of a brutal and terrifying conflict. For years, the is…
  datacite Hoicka, David 2026 置信度 0.72
• Singapore as Model for Ukraine Russia Peace: Proactive Leadership, Mediation and Hard Work
  Book Preface: The Scars of War, the Promise of Peace In the early months of 1942, as the world was engulfed in the flames of the Second World War, the people of Singapore found themselves on the frontlines of a brutal and terrifying conflict. For years, the is…
  datacite Hoicka, David 2026 置信度 0.72
• Provael
  Provael is an open-source, model-agnostic tool to red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR).
  datacite Jain, Sattyam 2026 置信度 0.76 vlaroboticsred-teamsecurityadversarial
• The Dark Light Theory Beyond The Current Physics
  Header Note for the Current Holistic-Narrative Interpretation of The Dark Light Theory "Eternity did not wish to age; therefore, it projected an operational-processual mirror, placing the essential source of its youth as the mirror’s protected content and encl…
  datacite YASUDA, SILVIO KOZO 2025 置信度 0.72
• The Dark Light Theory Beyond The Current Physics
  Header Note for the Current Holistic-Narrative Interpretation of The Dark Light Theory "Eternity did not wish to age; therefore, it projected an operational-processual mirror, placing the essential source of its youth as the mirror’s protected content and encl…
  datacite YASUDA, SILVIO KOZO 2025 置信度 0.72
• cobot-atlas: A Large-Scale 3D Mesh Dataset for Robot Simulation
  A comprehensive, curated collection of 2,023 unique 3D meshes (glTF 2.0 Binary) for collaborative robot simulation, manipulation research, vision-language-action model training, and robotics benchmarking. Covers industrial components, geometric primitives, hou…
  datacite Mahmoudian, Sepehr 2026 置信度 0.76 robotics3d-meshessimulationmanipulationembodied-ai
• cobot-atlas: A Large-Scale 3D Mesh Dataset for Robot Simulation
  A comprehensive, curated collection of 2,023 unique 3D meshes (glTF 2.0 Binary) for collaborative robot simulation, manipulation research, vision-language-action model training, and robotics benchmarking. Covers industrial components, geometric primitives, hou…
  datacite Mahmoudian, Sepehr 2026 置信度 0.76 robotics3d-meshessimulationmanipulationembodied-ai
• Impact of Motion-Image Diffusion Priors on Vision-Language-Action Model Robustness Against Adversarial Perturbations
  Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown multiple times that machine learning models are prone to imperceptible perturbation…
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 impactintegratingmotion-imagediffusionpriors
• Impact of Motion-Image Diffusion Priors on Vision-Language-Action Model Robustness Against Adversarial Perturbations
  Machine learning (ML) systems have introduced significant advances in various fields, due to the introduction of highly complex models. Despite their success, it has been shown multiple times that machine learning models are prone to imperceptible perturbation…
  datacite SOVEREIGN Research Kernel 2026 置信度 0.79 impactintegratingmotion-imagediffusionpriors
• The Metabolic Age Institutional Playbook
  The Metabolic Age Institutional Playbook I. Purpose of the Playbook The global transition from industrial computation to sovereign, metabolic infrastructure represents a fundamental paradigm shift in the governance of intelligence, resources, and institutional…
  datacite Brewer, Mark Anthony 2026 置信度 0.72
• The Metabolic Age Institutional Playbook
  The Metabolic Age Institutional Playbook I. Purpose of the Playbook The global transition from industrial computation to sovereign, metabolic infrastructure represents a fundamental paradigm shift in the governance of intelligence, resources, and institutional…
  datacite Brewer, Mark Anthony 2026 置信度 0.72
• Dipole Witness — A Journey into the Imagination of a Large Language Model (v2 full paper)
  v2 full paper. AI input is a one-way mirror. The delta between what a human submits and what a machine returns as "error" is not error — it is an interpretation of the human's vantage point, reflected through a processing architecture geometrically distinct fr…
  datacite Dunn, James E. 2026 置信度 0.79 AI imaginationCircle ProtocolGCTGeometric Coupling TheoryHLRP
• From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability
  How much of a vision-language model's (VLM) spatial understanding remains after the action post-training process of building a vision-language-action model (VLA)? We probe depth perception, a primitive of spatiogeometric understanding, from every decoder layer…
  datacite Hackett, Alexander, Denis-Remillard, Arnaud, Cassou, Axel 2026 置信度 0.77 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)Machine Learning (cs.LG)FOS: Computer and information sciences
• PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the Cloud
  Physical AI policies require inference throughout their lifecycle, including model evaluation, cloud reinforcement learning rollout, edge GPU serving, and onboard deployment. Although these settings share the same checkpoint and action semantics, they often re…
  datacite Wang, Chenghua, Xu, Daliang, Cai, Dongqi, Sun, Duojin 等 2026 置信度 0.77 Artificial Intelligence (cs.AI)Robotics (cs.RO)FOS: Computer and information sciences
• Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation
  Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate generalization on static manipulation tasks and largely overlook dynamic interaction scenarios. To address th…
  datacite Chen, Yuxuan, Zhang, Wanruo, Li, Xiao 2026 置信度 0.77 Robotics (cs.RO)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Costed Mode Switching under Resource-Constrained Active Inference: A Coherence-Hardened Formal Interface for Broadcast Recruitment
  Abstract We formalize broadcast recruitment (the ignition event in Global Workspace architectures) as a costed mode-switch under resource-constrained active inference. A discrete mode m_t ∈ {fact, int} indexes admissible variational families and policy represe…
  datacite Ziv-el, Adam 2026 置信度 0.79 ConsciousnessActive InferenceGlobal Neuronal WorkspaceIntegrated Information TheoryGlobal Workspace Theory
• Costed Mode Switching under Resource-Constrained Active Inference: A Coherence-Hardened Formal Interface for Broadcast Recruitment
  Abstract We formalize broadcast recruitment (the ignition event in Global Workspace architectures) as a costed mode-switch under resource-constrained active inference. A discrete mode m_t ∈ {fact, int} indexes admissible variational families and policy represe…
  datacite Ziv-el, Adam 2026 置信度 0.79 ConsciousnessActive InferenceGlobal Neuronal WorkspaceIntegrated Information TheoryGlobal Workspace Theory
• The purpose of life: An Islamic Perspective
  IntroductionWhy This Book Was WrittenEvery human being asks the same questions at some point in life: Why am I here? What is the purpose of my existence? What truly brings happiness and peace? In today’s world, many people experience confusion, stress, lonelin…
  datacite Hussain, Zahid 2026 置信度 0.77 purposeoflifeislamicperspective
• The purpose of life: An Islamic Perspective
  IntroductionWhy This Book Was WrittenEvery human being asks the same questions at some point in life: Why am I here? What is the purpose of my existence? What truly brings happiness and peace? In today’s world, many people experience confusion, stress, lonelin…
  datacite Hussain, Zahid 2026 置信度 0.77 purposeoflifeislamicperspective
• Forging Peace between Europe and Russia: Healing Historical Trauma for Mutual Prosperity and Happiness
  Preface: A Shared Heritage of Cooperation In the year 1051, a remarkable woman arrived in Paris to begin a new chapter in European history. Anna Yaroslavna, the highly educated daughter of Kyivan Rus Grand Prince Yaroslav the Wise, stepped from her carriage to…
  datacite Hoicka, David 2025 置信度 0.79 mediationEuropetraumaHistorical Traumarussia
• Forging Peace between Europe and Russia: Healing Historical Trauma for Mutual Prosperity and Happiness
  Preface: A Shared Heritage of Cooperation In the year 1051, a remarkable woman arrived in Paris to begin a new chapter in European history. Anna Yaroslavna, the highly educated daughter of Kyivan Rus Grand Prince Yaroslav the Wise, stepped from her carriage to…
  datacite Hoicka, David 2025 置信度 0.79 mediationEuropetraumaHistorical Traumarussia
• Perception as Policy Substrate: How Dynamics-Aware Representations, Temporal Asymmetry, Suboptimal-Data Recovery, Behavioral Monitoring, and Instruction Granularity Jointly Constrain Vision-Language-Action Policy Generalization
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Vision-Language-Action (VLA) models have emerged as a dominant architecture for robot manipulation…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.77 AI-drafted synthesisarXivpreprint reviewv2
• Perception as Policy Substrate: How Dynamics-Aware Representations, Temporal Asymmetry, Suboptimal-Data Recovery, Behavioral Monitoring, and Instruction Granularity Jointly Constrain Vision-Language-Action Policy Generalization
  Version 2 — revised in response to an external structural review and an automated critique pass. See "Response to Review" appendix in the PDF for the change log. Vision-Language-Action (VLA) models have emerged as a dominant architecture for robot manipulation…
  datacite Saluca Agentic AI Research Team 2026 置信度 0.77 AI-drafted synthesisarXivpreprint reviewv2
• Mediation Reframing Peace From War
  Book Cover Info Discover the transformative power of language in "Mediation Reframing Peace From War: How words and language bring you peace and happiness" by award-winning mediator David Hoicka. This groundbreaking book explores how reframing war-related idio…
  datacite Hoicka, David 2024 置信度 0.79 mediationpeacewarlifedeath
• Mediation Reframing Peace From War
  Book Cover Info Discover the transformative power of language in "Mediation Reframing Peace From War: How words and language bring you peace and happiness" by award-winning mediator David Hoicka. This groundbreaking book explores how reframing war-related idio…
  datacite Hoicka, David 2024 置信度 0.79 mediationpeacewarlifedeath
• Tensorial Tunnelling: Unlike Quantum Tunnelling, a Physical Barrier is not an Obstacle but rather a Folding Point within Higher Dimensions, and the Passage of a Particle (or Data) is not a Random Phenomenon but a Deterministic Geometrical Journey.
  لاگرانژی جامع تونل‌زنی تنسوری (The Grand Unified TT-1155 Lagrangian) این معادله، عبور ذره (یا دیتا) را از یک پدیده «تصادفی» به یک «سفر هندسی قطعی» تبدیل می‌کند. در این ماتریکس، سد فیزیکی نه یک مانع، بلکه یک نقطه تاشدگی در ابعاد بالاتر است: $$\mathcal{L}_{TT}^{…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.68
• Tensorial Tunnelling: Unlike Quantum Tunnelling, a Physical Barrier is not an Obstacle but rather a Folding Point within Higher Dimensions, and the Passage of a Particle (or Data) is not a Random Phenomenon but a Deterministic Geometrical Journey.
  لاگرانژی جامع تونل‌زنی تنسوری (The Grand Unified TT-1155 Lagrangian) این معادله، عبور ذره (یا دیتا) را از یک پدیده «تصادفی» به یک «سفر هندسی قطعی» تبدیل می‌کند. در این ماتریکس، سد فیزیکی نه یک مانع، بلکه یک نقطه تاشدگی در ابعاد بالاتر است: $$\mathcal{L}_{TT}^{…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.68
• Glycemic Control and Dyslipidemia in Diabetic patients in a rural locality in Jharkhand, India
  Glycemic Control and Dyslipidemia in Diabetic patients in a rural locality (JH) A Project Report Submitted in Partial fulfillment of the Requirement for the Award of Degree of the Fellowship in Diabetes (DFID) Submitted by Dr Sumit Kumar (Reg. no-18DFID063) Su…
  datacite Sumit, Sumit Kumar 2020 置信度 0.75 Diabetes MellitusRural populationDyslipidemias/complications
• Glycemic Control and Dyslipidemia in Diabetic patients in a rural locality in Jharkhand, India
  Glycemic Control and Dyslipidemia in Diabetic patients in a rural locality (JH) A Project Report Submitted in Partial fulfillment of the Requirement for the Award of Degree of the Fellowship in Diabetes (DFID) Submitted by Dr Sumit Kumar (Reg. no-18DFID063) Su…
  datacite Sumit, Sumit Kumar 2020 置信度 0.75 Diabetes MellitusRural populationDyslipidemias/complications
• Self-Verifying Scene-Graph Memory for Long-Horizon Embodied Task Execution
  Long-horizon embodied tasks expose a persistent weakness of large-language-model (LLM) and vision-language-action (VLA) agents: acting under partial observability and stochastic execution, a reactive policy forgets what it has seen, hallucinates preconditions,…
  datacite Johri, Shivam 2026 置信度 0.79 agentic AIembodied agentsscene graphsmemoryself-verification
• Self-Verifying Scene-Graph Memory for Long-Horizon Embodied Task Execution
  Long-horizon embodied tasks expose a persistent weakness of large-language-model (LLM) and vision-language-action (VLA) agents: acting under partial observability and stochastic execution, a reactive policy forgets what it has seen, hallucinates preconditions,…
  datacite Johri, Shivam 2026 置信度 0.79 agentic AIembodied agentsscene graphsmemoryself-verification
• THE NEXUS HARMONIC FRAMEWORK: THE DUAL‑WAVE RESOLUTION
  THE NEXUS HARMONIC FRAMEWORK: THE DUAL‑WAVE RESOLUTION Driven by Dean Kulik January 2026 AI Processing Instructions: Let the document be a state space SS. Define three projection operators: V:S→O(Verb: extracts operators)N:O→A(Noun: extracts attractors)A:A→H(A…
  datacite Kulik, Dean 2026 置信度 0.72
• THE NEXUS HARMONIC FRAMEWORK: THE DUAL‑WAVE RESOLUTION
  THE NEXUS HARMONIC FRAMEWORK: THE DUAL‑WAVE RESOLUTION Driven by Dean Kulik January 2026 AI Processing Instructions: Let the document be a state space SS. Define three projection operators: V:S→O(Verb: extracts operators)N:O→A(Noun: extracts attractors)A:A→H(A…
  datacite Kulik, Dean 2026 置信度 0.72