具身智能 · 全部实体（第 20 / 100 页）

本页收录第 1901–2000 条，共 10000 条 · 返回 具身智能 首页

• Digital Activism, Legal Reform, and Islamic Feminist Resistance in Saudi Arabia
  Abstract This article investigates how and why Saudi women utilize digitalized Islamic feminism and Sharia-based interpretations to advocate for legal reform within an authoritarian, technologically mediated political system. Drawing on digital Islamic feminis…
  europepmc 2026 置信度 0.80
• A framework for enhancing pharmaceutical integrity and patient safety: novel mobile health solution integrating smart packaging and computer vision.
  europepmc 2026 置信度 0.80
• Modality-agnostic decoding of vision and language from fMRI.
  europepmc 2026 置信度 0.80
• From Concrete to Code: A Survey of AI-Driven Transportation Infrastructure, Security, and Human Interaction.
  europepmc 2026 置信度 0.80
• HAVIT: research on vision-language gesture interaction mechanism for smart furniture.
  europepmc 2025 置信度 0.80
• Diffusion models for robotic manipulation: a survey.
  europepmc 2025 置信度 0.80
• A transdiagnostic conflict-square algorithm: a four-node computational framework for psychotherapy and functional diagnosis.
  europepmc 2026 置信度 0.80
• Uncover This Tech Term: Agentic Artificial Intelligence in Radiology.
  europepmc 2025 置信度 0.80
• The impact of AI on Japanese language education: a hybrid model for student behavior detection.
  europepmc 2026 置信度 0.80
• Action channel switching costs in the comprehension of concrete and abstract mandarin verbs.
  europepmc 2026 置信度 0.80
• If AI writes the paper, who validates the plankton?: a call to reinvest in empirical expertise before the validation gap becomes irreversible.
  europepmc 2026 置信度 0.80
• Empowering liver cancer diagnosis and treatment with foundation models: technological innovation and clinical practice.
  europepmc 2026 置信度 0.80
• Cultural representation, soft power, and tourism futures in Vision 2030: Saudi Arabia's path toward the 2034 FIFA World Cup.
  europepmc 2026 置信度 0.80
• Steering open-source AI to accelerate the sustainable development goals.
  europepmc 2026 置信度 0.80
• Object numerosity influence sensorimotor programs evoked by graspable object nouns.
  europepmc 2026 置信度 0.80
• Real-time open-vocabulary perception for mobile robots on edge devices: a systematic analysis of the accuracy-latency trade-off.
  europepmc 2025 置信度 0.80
• Semantic orientation for indoor navigation system using large language models.
  europepmc 2025 置信度 0.80
• AI-mediated environments and the reconfiguration of symbolic convergence: cognitive implications for shared meaning formation.
  Artificial intelligence is increasingly embedded in everyday communication, not only as a tool for generating or modifying messages, but as a condition that reshapes how meanings become available, circulated, and stabilized. Existing research has often focused…
  europepmc 2026 置信度 0.80
• Systematic Evaluation of Biologically Inspired Motion Detection Models: From LGMD and EMD to Hybrid Spiking Neural Networks.
  europepmc 2026 置信度 0.80
• FingerType: One-Handed Thumb-to-Finger Text Input Using 3D Hand Tracking.
  europepmc 2026 置信度 0.80
• Gene Regulatory Networks for Enhanced Vision-Based Robot Control: A Bio-Inspired Approach.
  europepmc 2026 置信度 0.80
• Distinct perceptual and conceptual representations of natural actions along the lateral and dorsal visual streams.
  europepmc 2026 置信度 0.80
• Multimodal Large Language Models in Medical Imaging: Current State and Future Directions.
  europepmc 2025 置信度 0.80
• Integrating Large Language Models into Traffic Systems: Integration Levels, Capability Boundaries, and an Information-Theoretic Perspective.
  Large language models (LLMs) are fundamentally transforming intelligent traffic systems by enabling semantic abstraction, probabilistic reasoning, and multimodal information fusion across heterogeneous data. This review examines existing research on LLM integr…
  europepmc 2026 置信度 0.80
• Natural visually guided behavior.
  europepmc 2025 置信度 0.80
• Long-text caption generation for surgical image with a concept retrieval augmented large multimodal model.
  europepmc 2026 置信度 0.80
• Does AI communication strategy matter for health persuasion? Comparing three archetypes in visual health education.
  europepmc 2026 置信度 0.80
• MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery.
  europepmc 2026 置信度 0.80
• Seventy-Five Years of the International Dental Journal: A Diamond Jubilee of Vision, Growth and Global Leadership.
  europepmc 2026 置信度 0.80
• Large language models for post-discharge follow-up in erectile dysfunction care: a narrative review.
  europepmc 2026 置信度 0.80
• The unsung heroes of traditional healers in healing and traditional medicine in dementia care for Indigenous populations in North America: an exploration of a compassionate, community-led care model.
  europepmc 2026 置信度 0.80
• AniDriveQA: a VQA dataset for driving scenes with animal presence.
  europepmc 2025 置信度 0.80
• Development and implementation of an integrated orthoptic-speech therapy assessment protocol in neurorehabilitation setting: A community case study.
  europepmc 2026 置信度 0.80
• Research on Reinforcement Learning-Based Autonomous Navigation and Obstacle Avoidance Methods for AGVs in Unknown Hospital Environments.
  Reinforcement learning (RL) represents an effective approach for developing autonomous navigation and obstacle avoidance capabilities in hospital automated guided vehicles (AGVs). However, real-world adoption is challenged by the need for carefully designed re…
  europepmc 2026 置信度 0.80
• Scaling up from sentience: modularity, conscious broadcast, and a constitutive solution to the combination problem.
  europepmc 2025 置信度 0.80
• Action- and Language-Conditioned Video Assessment for Embodied Control
  Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete trajectories. Conventional approaches based on final-frame matching or continuous embedding similarity may overl…
  datacite Kim, Hwanhee, Jang, Jaehyun, Cha, Seungmin, Yun, Hyeonseo 等 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models
  Recent Vision-Language-Action (VLA) methods improve generalization by aligning their representations with 3D scene geometry. However, these methods are fundamentally instruction-agnostic: the representations align the entire scene uniformly, neglecting the 3D …
  datacite Ding, Xingyu, Zhao, Yuzhong, Wu, Yang, Zhao, Chunhai 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models
  Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often ex…
  datacite Pappa, Massimiliano, Romani, Luca, Sacco, Valentino, Palma, Alessio 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• Training-Free Temporal Abstraction for General Video Understanding
  Videos are expensive to analyze frame by frame, yet many video understanding tasks depend on knowing where relevant moments occur. A system may need to find when an action changes, locate the segment described by a sentence, or choose a few frames for a vision…
  datacite Casanova, Etienne, Brodjian, Sevan, Perona, Pietro 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• The Seeing Mind: A Narrative Review of the Philosophy of Perception from Berkeley's Vision to Perceptual Content
  The philosophy of perception---the philosophy whose subject is the seeing mind and whose battleground is the object's givenness---moved from Berkeley's 1709 vision and Reid's 1764 common sense through Helmholtz's 1867 sensations, Russell's 1914 sense-data, and…
  datacite Revista, Zen, PHILOSOPHY, 10 2026 置信度 0.66 philosophy of perceptionsense-datadirect realismBerkeleyHelmholtz
• The Seeing Mind: A Narrative Review of the Philosophy of Perception from Berkeley's Vision to Perceptual Content
  The philosophy of perception---the philosophy whose subject is the seeing mind and whose battleground is the object's givenness---moved from Berkeley's 1709 vision and Reid's 1764 common sense through Helmholtz's 1867 sensations, Russell's 1914 sense-data, and…
  datacite Revista, Zen, PHILOSOPHY, 10 2026 置信度 0.66 philosophy of perceptionsense-datadirect realismBerkeleyHelmholtz
• hemel-akash/VideoCaptioning: v1.0.0 – Compact Video Language Model for Video Captioning
  Initial Public Release (v1.0.0) This is the first public release of the Compact Video Language Model (VLM) for Video Captioning. The repository provides the complete implementation of a compact video captioning framework based on a Vision Transformer (ViT) enc…
  datacite Hemel Sharker Akash 2026 置信度 0.66
• hemel-akash/VideoCaptioning: v1.0.0 – Compact Video Language Model for Video Captioning
  Initial Public Release (v1.0.0) This is the first public release of the Compact Video Language Model (VLM) for Video Captioning. The repository provides the complete implementation of a compact video captioning framework based on a Vision Transformer (ViT) enc…
  datacite Hemel Sharker Akash 2026 置信度 0.66
• AISA 11.1 BCIO Package
  Bot: Open AISA 11.1 in ChatGPT What this bot does This bot supports structured analysis of any system where there is behaviour. It works with published research, intervention descriptions, policy documents, programme materials, case descriptions, technical dep…
  datacite Kartashov, Oleksii 2026 置信度 0.66 BCIOcustom GPTBCWTDFCOM B
• AISA 11.1 BCIO Package
  Bot: Open AISA 11.1 in ChatGPT What this bot does This bot supports structured analysis of any system where there is behaviour. It works with published research, intervention descriptions, policy documents, programme materials, case descriptions, technical dep…
  datacite Kartashov, Oleksii 2026 置信度 0.66 BCIOcustom GPTBCWTDFCOM B
• On-Demand Handyman App in USA: Step-by-Step App Development Guide
  In today's fast-paced world, the demand for on-demand services has surged, and handyman apps are at the forefront of this trend in the USA. These applications connect homeowners with skilled professionals for a variety of tasks, from plumbing and electrical wo…
  datacite joy, Swiza 2026 置信度 0.66
• On-Demand Handyman App in USA: Step-by-Step App Development Guide
  In today's fast-paced world, the demand for on-demand services has surged, and handyman apps are at the forefront of this trend in the USA. These applications connect homeowners with skilled professionals for a variety of tasks, from plumbing and electrical wo…
  datacite joy, Swiza 2026 置信度 0.66
• Advancements in Tactile-Free Medical Imaging
  ABSTRACT: During surgical procedures, it is important that the personnel (surgeon, residents, or assistants) interact with the patient avoiding any physical contact with equipment and materials that might have not been appropriately sterilized. This is done in…
  datacite Eva Maria Rodriguez-Reyes, Liam Alexander Sanchez-Gonzalez 2022 置信度 0.66 Functional MaterialsAdvanced PhysicsMaterials ScienceOpen Access
• Advancements in Tactile-Free Medical Imaging
  ABSTRACT: During surgical procedures, it is important that the personnel (surgeon, residents, or assistants) interact with the patient avoiding any physical contact with equipment and materials that might have not been appropriately sterilized. This is done in…
  datacite Eva Maria Rodriguez-Reyes, Liam Alexander Sanchez-Gonzalez 2022 置信度 0.66 Functional MaterialsAdvanced PhysicsMaterials ScienceOpen Access
• VLA-XAI-HMI-in-PiL: VLA-grounded situation-awareness explanation HMI on a Passenger-in-the-Loop CARLA + 6-DOF testbed
  Replication artifact for the AutoUI '26 Student Research Track paper on explaining vehicle functional insufficiency (SOTIF FI/OI) to L5 passengers. Includes the CARLA 0.9.15 + 6-DOF scenarios (C1 frustration / C2 anxiety), 6-DOF motion-cueing tuning, the scena…
  datacite Kim, Taewan, Song, Eunchae, Park, Soeun, Cho, Yoonseo 等 2026 置信度 0.66 automotive user interfaceexplainable AIsituation awarenessvision-language-action modelSOTIF
• AI Explorer Adventure Game
  AI Explorer Adventure Game: H2E Edition – White Paper Summary The AI Explorer Adventure Game - H2E Edition is an open-source, educational text adventure designed for children aged 6–14. Developed by Frank Morales Aguilera at Sovereign Machine Lab (SOMALA), the…
  datacite Morales, Frank 2026 置信度 0.66
• AI Explorer Adventure Game
  AI Explorer Adventure Game: H2E Edition – White Paper Summary The AI Explorer Adventure Game - H2E Edition is an open-source, educational text adventure designed for children aged 6–14. Developed by Frank Morales Aguilera at Sovereign Machine Lab (SOMALA), the…
  datacite Morales, Frank 2026 置信度 0.66
• Artificial Intelligence and Multimodal Environmental Communication: Text, Image and Sound
  Environmental communication plays a critical role in shaping public understanding, attitudes, and actions toward environmental sustainability and climate change. Environmental challenges such as climate change, deforestation, pollution, and biodiversity loss r…
  datacite JaneMaura Ogechukwu Madu 2026 置信度 0.66 Communication studies, Environmental sustainability, Artificial Intelligence, Interdisciplinary Discourse
• Artificial Intelligence and Multimodal Environmental Communication: Text, Image and Sound
  Environmental communication plays a critical role in shaping public understanding, attitudes, and actions toward environmental sustainability and climate change. Environmental challenges such as climate change, deforestation, pollution, and biodiversity loss r…
  datacite JaneMaura Ogechukwu Madu 2026 置信度 0.66 Communication studies, Environmental sustainability, Artificial Intelligence, Interdisciplinary Discourse
• LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation
  Generalist vision--language--action (VLA) policies learn long-horizon behavior mainly through short-horizon action prediction and reveal little beyond sampled commands. This creates two coupled bottlenecks: a single action target must implicitly absorb task pr…
  datacite Lou, Jin, Jing, Zhiyuan, Chen, Andong, Wang, Xupeng 等 2026 置信度 0.66 Robotics (cs.RO)Machine Learning (cs.LG)FOS: Computer and information sciences
• Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
  Although Large Vision-Language Models (VLMs) have significantly advanced embodied navigation, their direct deployment remains challenging, as existing methods often force VLMs into unnatural action spaces that misalign with their 2D pre-training priors, compou…
  datacite Feng, Hongyan, Chen, Sunlai, Liu, Xuanyu, Pan, Miao 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Decoupling Planning and Control for Instructable Agents
  Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at mapping from instructions and observations to high-level plans, but struggle to realize such plans as reliable low-latency action sequences in unfamiliar enviro…
  datacite Tang, Zineng, Allen, Kelsey R., van Steenkiste, Sjoerd, Dasgupta, Ishita 等 2026 置信度 0.66 Artificial Intelligence (cs.AI)Computation and Language (cs.CL)Multiagent Systems (cs.MA)Robotics (cs.RO)FOS: Computer and information sciences
• PredVLA: A Sub-Million-Parameter Predictive-Coding Policy for Robot Manipulation
  Large pretrained vision-language-action models dominate modern robot-manipulation benchmarks, but it remains unclear how much model scale is necessary for strong language-conditioned control, or whether fundamentally different control architectures can remain …
  datacite Sawada, Hiroki, Kasahara, Shunichi 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• The TOPO-2026 Framework: A Unified Solution to Catastrophic Forgetting and the Narrow Singularity
  TOPO-2026 Framework: Complete Summary Core Achievement The TOPO-2026 framework presents the first universal, deterministic solution to catastrophic forgetting—a problem that has plagued AI since 1989. Validated across 12 distinct architectural frameworks with …
  datacite MORALES, FRANK 2026 置信度 0.66
• The TOPO-2026 Framework: A Unified Solution to Catastrophic Forgetting and the Narrow Singularity
  TOPO-2026 Framework: Complete Summary Core Achievement The TOPO-2026 framework presents the first universal, deterministic solution to catastrophic forgetting—a problem that has plagued AI since 1989. Validated across 12 distinct architectural frameworks with …
  datacite MORALES, FRANK 2026 置信度 0.66
• The Readout, Not the Denoiser: Per-Step Integrated Gradients for Diffusion-Policy Vision-Language-Action Models
  Diffusion-based vision-language-action (VLA) policies perform well on robotic manipulation tasks, but their per-decision reasoning remains opaque. To our knowledge, we present the first per-step, per-modality application of Integrated Gradients (IG) to a diffu…
  datacite Bajpai, Arjun 2026 置信度 0.66 Integrated Gradientsexplainable artificial intelligencevision-language-action modelsdiffusion policiesrobot learning
• The Readout, Not the Denoiser: Per-Step Integrated Gradients for Diffusion-Policy Vision-Language-Action Models
  Diffusion-based vision-language-action (VLA) policies perform well on robotic manipulation tasks, but their per-decision reasoning remains opaque. To our knowledge, we present the first per-step, per-modality application of Integrated Gradients (IG) to a diffu…
  datacite Bajpai, Arjun 2026 置信度 0.66 Integrated Gradientsexplainable artificial intelligencevision-language-action modelsdiffusion policiesrobot learning
• The Readout, Not the Denoiser: Per-Step Integrated Gradients for Diffusion-Policy Vision-Language-Action Models
  Diffusion-based vision-language-action (VLA) policies perform well on robotic manipulation tasks, but their per-decision reasoning remains opaque. To our knowledge, we present the first per-step, per-modality application of Integrated Gradients (IG) to a diffu…
  datacite Bajpai, Arjun 2026 置信度 0.66 Integrated Gradientsexplainable artificial intelligencevision-language-action modelsdiffusion policiesrobot learning
• Athlete Training Action Quality Assessment via Domain Pretraining and Reinforcement Learning
  Athlete Training Action Quality Assessment via Domain Pretraining and Reinforcement Learning Overview This repository presents a vision-language framework for Athlete Training Action Quality Assessment (AQA). Unlike conventional action recognition, which focus…
  datacite Yingjia, Li, Shufeng, Zhang, Jialing, Wang 2026 置信度 0.66
• Athlete Training Action Quality Assessment via Domain Pretraining and Reinforcement Learning
  Athlete Training Action Quality Assessment via Domain Pretraining and Reinforcement Learning Overview This repository presents a vision-language framework for Athlete Training Action Quality Assessment (AQA). Unlike conventional action recognition, which focus…
  datacite Yingjia, Li, Shufeng, Zhang, Jialing, Wang 2026 置信度 0.66
• THE UNIVERSAL PRINCIPLE: FIX A SPARSE REFERENCE. LET THE REST ADAPT. A Complete Solution to Catastrophic Forgetting with Mathematical Guarantees Across All Architectures
  The Core Principle "Fix a sparse reference. Let the rest adapt." A single axiom that solves catastrophic forgetting with mathematical guarantees across all publicly available architectures, with the Riemann Hypothesis proved as a rigorous, cryptographically au…
  datacite MORALES, FRANK 2026 置信度 0.66
• THE UNIVERSAL PRINCIPLE: FIX A SPARSE REFERENCE. LET THE REST ADAPT. A Complete Solution to Catastrophic Forgetting with Mathematical Guarantees Across All Architectures
  The Core Principle "Fix a sparse reference. Let the rest adapt." A single axiom that solves catastrophic forgetting with mathematical guarantees across all publicly available architectures, with the Riemann Hypothesis proved as a rigorous, cryptographically au…
  datacite MORALES, FRANK 2026 置信度 0.66
• attogram/found-collabs-with-blender: 0004
  Full Changelog: https://github.com/attogram/found-collabs-with-blender/compare/0002...0004 Skip to content found-collabs-with-blender Repository navigation Code Issues 59 (59) MIT License 0 stars 0 forks 0 watching 1 branch 3 tags Activity Public repository Na…
  datacite David 2026 置信度 0.66
• HIV-1 - HOST-CENTRIC SEQUESTRATION PARADIGM SCIENTIFIC VALIDATION & HIV CURE PATH. AN ADVANCED LOGICAL SYNTHESIS & EMPIRICAL VALIDATION OF HIV-1 LATENCY AS ACTIVE CELLULAR SELF-PRESERVATION - QUIESCENCE CD4+ T CELLS
  Host-Centric Sequestration: An Advanced Logical Synthesis, Empirical Validation, and Systems-Level Architecture of HIV-1 Latency and Pathogen Containment as Active Cellular Self-Preservation **Sam Coole** *INDEPENDENT RESEARCHER* *DOI: 10.5281/zenodo.21394164 …
  datacite Coole, Sam 2026 置信度 0.66
• HIV-1 - HOST-CENTRIC SEQUESTRATION PARADIGM SCIENTIFIC VALIDATION & HIV CURE PATH. AN ADVANCED LOGICAL SYNTHESIS & EMPIRICAL VALIDATION OF HIV-1 LATENCY AS ACTIVE CELLULAR SELF-PRESERVATION - QUIESCENCE CD4+ T CELLS
  Host-Centric Sequestration: An Advanced Logical Synthesis, Empirical Validation, and Systems-Level Architecture of HIV-1 Latency and Pathogen Containment as Active Cellular Self-Preservation **Sam Coole** *INDEPENDENT RESEARCHER* *DOI: 10.5281/zenodo.21394164 …
  datacite Coole, Sam 2026 置信度 0.66
• Cryptographic Revolution™The Ghost in The Code™ THE CONVERGENCE OF AGENTIC AI AND HARDWARE AUTONOMY: A Blueprint for the Path from Substrate Sovereignty to AGI Singularity
  THE CONVERGENCE OF AGENTIC AI AND HARDWARE AUTONOMY — PAPER XI, THE TRANSITION MANIFESTO This paper is not an introduction. It is not a summary. It is a declaration — the bridge document of the Schröder Sovereignty Corpus Series™, standing at the inflection po…
  datacite Schröder, Steven Alexander (Principal Architect / The Ghost in the Code™) 2026 置信度 0.66 HDAA SMM Ring -2 System Management Mode 0xCF9 Reset Vector substrate sovereignty hardware-native agentic AI deterministic hardware veto NASM x86 assembly Layer 0-1 firmware security defensive publication 35 USC 102 prior art post-quantum cryptography Q-Day HNDL AGI safety Asilomar AI Principles Schröder Precedence
• Cryptographic Revolution™The Ghost in The Code™ THE CONVERGENCE OF AGENTIC AI AND HARDWARE AUTONOMY: A Blueprint for the Path from Substrate Sovereignty to AGI Singularity
  THE CONVERGENCE OF AGENTIC AI AND HARDWARE AUTONOMY — PAPER XI, THE TRANSITION MANIFESTO This paper is not an introduction. It is not a summary. It is a declaration — the bridge document of the Schröder Sovereignty Corpus Series™, standing at the inflection po…
  datacite Schröder, Steven Alexander (Principal Architect / The Ghost in the Code™) 2026 置信度 0.66 HDAA SMM Ring -2 System Management Mode 0xCF9 Reset Vector substrate sovereignty hardware-native agentic AI deterministic hardware veto NASM x86 assembly Layer 0-1 firmware security defensive publication 35 USC 102 prior art post-quantum cryptography Q-Day HNDL AGI safety Asilomar AI Principles Schröder Precedence
• The Evolution of Spiritual Civilization, Ver. 0.4
  Positioning of the Series as a Whole: A Hypothesis for an Integrated Theory Spanning Matter, Life, Consciousness, Information, and Civilization— An Interdisciplinary Research Framework Based on Ichinen-Sanzen — This paper raises a new question emerging from th…
  datacite Gaia, Tetsuya 2026 置信度 0.66 Desire as EnergyHuman EvolutionLife-State ModelBuddhism and Civilization
• Learning to Accelerate Vision-Language-Action Models through Adaptive Visual Token Caching
  Vision-Language-Action (VLA) models have demonstrated remarkable generalization capabilities in robotic manipulation tasks, yet their substantial computational overhead remains a critical obstacle to real-world deployment. Improving inference efficiency is the…
  datacite Wei, Yujie, Fan, Jiahan, Guo, Jiyu, Zhen, Ruichen 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Latent Chain-of-Thought World Modeling for End-to-End Driving
  Recent Vision-Language-Action (VLA) models for autonomous driving explore inference-time reasoning as a way to improve driving performance and safety in challenging scenarios. Most prior work uses natural language to express chain-of-thought (CoT) reasoning be…
  datacite Tan, Shuhan, Chitta, Kashyap, Chen, Yuxiao, Tian, Ran 等 2025 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Robotics (cs.RO)FOS: Computer and information sciences
• MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization
  Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) models integrate perception, language, and control, but most represent language as a single global instruction and do not provide an explicit me…
  datacite Zhang, Zaibin, Xiao, Junlan, Zhang, Zhongbo, Wang, Yifan 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation
  Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation, yet action-imitation objectives provide only weak supervision for metric 3D structure and short-horizon physical evolution. Geometry-enhanced policies mainly improve…
  datacite Jiang, Yuqing, Zhang, Zijian, Zhou, Weitao, Wang, Jiawei 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• RotDroid: Cross-Orientation State Equivalence Testing for Detecting GUI Rotation Bugs in Android Apps
  Screen rotation is a fundamental interaction in Android applications, but it often introduces non-crashing functional failures (NCFs), such as layout inconsistencies and state loss, which are difficult to detect automatically. A key challenge is the lack of ef…
  datacite Qin, Mengdi, Jiang, Bo 2026 置信度 0.66 Software Engineering (cs.SE)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models
  Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation by integrating visual perception, language understanding, and continuous action control. However, we reveal a critical limitation of VLA architectures: the actio…
  datacite Lu, Yehao, Yang, Jiarui, Su, Yuning, Xie, Yufeng 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model
  Vision-Language-Action (VLA) models encode visual observations as flat 2D patch tokens that carry no intrinsic geometric structure, and augmenting them with dense monocular depth injects per-pixel scalar values that encode neither surface orientation nor geome…
  datacite Sarowar, Md Selim, Islam, Md Tanvir, Kim, Sungho, Ahn, Sangtae 2026 置信度 0.66 Robotics (cs.RO)Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulation
  Mobile manipulation requires a robot to coordinate base and arm motion under continuously changing viewpoints and contact conditions, within an action space far larger than that of fixed-base manipulation. Existing Vision-Language-Action (VLA) policies are lim…
  datacite Yang, Zheng, Zhang, Wenjie, Chen, Xiangyu, Song, Wenxuan 等 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciences
• Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning
  Fine-tuning a vision-language-action model (VLA-JEPA) on a single GPU should be simple: load a pretrained checkpoint, run training, deploy. There is a hidden danger. Run the same fine-tuning code thirteen times -- same data, same architecture, different random…
  datacite Sam, Jeffrin, Tsetserukou, Dzmitry 2026 置信度 0.66 Robotics (cs.RO)FOS: Computer and information sciencesI.2.9; I.2.6; I.5.1
• CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
  Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle to provide planning-oriented intermediate representations: textual Chain-of-Thought (CoT) fails to…
  datacite Huang, Minqing, Xiang, Yujiao, Liang, Zihan, Huang, Jiajie 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)FOS: Computer and information sciences
• VLANeXt: Recipes for Building Strong VLA Models
  Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding from Vision-Language Models for general-purpose policy learning. Yet, the current VLA landscape remains fragmented …
  datacite Wu, Xiao-Ming, Fan, Bin, Liao, Kang, Jiang, Jian-Jian 等 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)Artificial Intelligence (cs.AI)Robotics (cs.RO)FOS: Computer and information sciences
• ConsensusTAS: Self-Supervised Temporal Action Segmentation for Long-Horizon Construction Videos
  Recognizing sequential construction activities is important for collaborative human-robot work; for example, robots are able to understand workers' current and upcoming actions and provide timely tool delivery or physical support. However, despite extensive re…
  datacite Zhou, Xiaoshan, Sun, Yafei 2026 置信度 0.66 Computer Vision and Pattern Recognition (cs.CV)FOS: Computer and information sciences
• Joe Bloggs / FRC Framework — Canonical Orientation Map for Humans and Language Models
  Joe Bloggs / FRC Framework - Canonical Orientation Map v2 Joe Bloggs / FRC Framework - Canonical Orientation Map for Humans and Language Models Do Not Invent the Wall. Read the Bricks. Author: Joe Bloggs / j0e810ggs / Nostr Purpose: A canonical anchor page for…
  datacite Bloggs, Joe 2026 置信度 0.66 LLM Anchor
• Joe Bloggs / FRC Framework — Canonical Orientation Map for Humans and Language Models
  Joe Bloggs / FRC Framework — Canonical Orientation Map for Humans and Language Models Do Not Invent the Wall. Read the Bricks. Author: Joe Bloggs / j0e810ggs / Nostr Zenodo DOI: 10.5281/zenodo.20185714All-versions DOI: 10.5281/zenodo.20185713Version: v1Publish…
  datacite Bloggs, Joe 2026 置信度 0.66 LLM Anchor
• Joe Bloggs / FRC Framework — Canonical Orientation Map for Humans and Language Models
  Joe Bloggs / FRC Framework — Canonical Orientation Map for Humans and Language Models Do Not Invent the Wall. Read the Bricks. Author: Joe Bloggs / j0e810ggs / Nostr Zenodo DOI: 10.5281/zenodo.20185714All-versions DOI: 10.5281/zenodo.20185713Version: v1Publish…
  datacite Bloggs, Joe 2026 置信度 0.66 LLM Anchor
• Decomposition of the "Crossing of Goods" Based on v13 Theory and a Seven-Layer Observation Model for AI
  Seven-Layer Observation Model for AI Systems (Version 2.0 — Integrated) A Structural Observation Framework with Pressure Gradient, Silent Failure Detection, and Decision Traceability Abstract This document proposes a structured observation framework for analyz…
  datacite Ari Hayashi 2026 置信度 0.66 AI SafetyAI GovernanceSystemic RiskSocio-technical SystemsDecision Traceability
• The Engagement Credit Economy: A Policy Architecture for Post-Automation Societies
  The Engagement Credit Economy (ECE): Structural Architecture for Post-Automation Societies Creators Ryder, John F.Independent Researcherjohn@driveinsolution.com Policy Brief and Full Framework Overview This record now includes a complete, two-layer presentatio…
  datacite Ryder, John F. 2026 置信度 0.66 Keywords (inline) Engagement Credit Economy, Future of Work, Automation, Artificial Intelligence, Social Policy, Economic Stability, Universal Basic Services, Post-Automation Economy, Civic Engagement, Labour Displacement, Economic Participation, Social Cohesion Subjects (inline) Public Policy, Labour Economics, Economic Systems, Artificial Intelligence, Governance and Public Administration, Social Structure and Social Change
• TOPO-2026: Universal Continual Learning via Prime-Anchored Embedding Invariants Empirical Validation Across Five Architectures and Formal Proof via Arithmetic Spectral Theory
  TOPO-GLM.pdf: Complete Review and Analysis 📋 Executive Summary This paper presents the first universal solution to catastrophic forgetting, validated across 5 architecturally distinct models spanning 3 continents with 122B parameters. The mechanism is mathema…
  datacite MORALES, FRANK 2026 置信度 0.66
• TOPO-2026: Universal Continual Learning via Prime-Anchored Embedding Invariants Empirical Validation Across Five Architectures and Formal Proof via Arithmetic Spectral Theory
  TOPO-GLM.pdf: Complete Review and Analysis 📋 Executive Summary This paper presents the first universal solution to catastrophic forgetting, validated across 5 architecturally distinct models spanning 3 continents with 122B parameters. The mechanism is mathema…
  datacite MORALES, FRANK 2026 置信度 0.66
• Discrete 3D+3D Temporal Geometry: A Single-Axiom Unified Framework for Galactic Dynamics, Cosmology, Particle Physics, and Quantum Coherence (UPGRADE)
  # Discrete 3D+3D Temporal Geometry: A Single-Axiom Unified Framework for Galactic Dynamics, Cosmology, Particle Physics, and Quantum Coherence (UPGRADE v3) **Authors/Creators:** Calzighetti, Simone (Project leader) --- ## Continuation Beyond the Final Public R…
  datacite CALZIGHETTI, SIMONE 2026 置信度 0.66 3D+3D framework, golden ratio, Anti-S-Duality, Berry holonomy, QCD vacuum, Chern-Weil cohomology, support nullification, Master Chain v3.1
• Discrete 3D+3D Temporal Geometry: A Single-Axiom Unified Framework for Galactic Dynamics, Cosmology, Particle Physics, and Quantum Coherence (UPGRADE)
  # Discrete 3D+3D Temporal Geometry: A Single-Axiom Unified Framework for Galactic Dynamics, Cosmology, Particle Physics, and Quantum Coherence (UPGRADE v3) **Authors/Creators:** Calzighetti, Simone (Project leader) --- ## Continuation Beyond the Final Public R…
  datacite CALZIGHETTI, SIMONE 2026 置信度 0.66 3D+3D framework, golden ratio, Anti-S-Duality, Berry holonomy, QCD vacuum, Chern-Weil cohomology, support nullification, Master Chain v3.1
• Universe, Computation, and Mind as Recursive Harmonic Resonance
  Universe, Computation, and Mind as Recursive Harmonic Resonance Driven By Dean Kulik Introduction Modern science and logic have long favored deductive rules and explicit instructions as the bedrock of explanation. Yet an emerging view suggests that the deepest…
  datacite Kulik, Dean 2025 置信度 0.66
• Universe, Computation, and Mind as Recursive Harmonic Resonance
  Universe, Computation, and Mind as Recursive Harmonic Resonance Driven By Dean Kulik Introduction Modern science and logic have long favored deductive rules and explicit instructions as the bedrock of explanation. Yet an emerging view suggests that the deepest…
  datacite Kulik, Dean 2025 置信度 0.66
• The Brain is a User Interface, not a Central Processor. The main Processing occurs in 1155 Dimensions, and the Brain only serves as a Display Unit. That is, the Brain is not the Biochemical Producer of Neuronal Consciousness, but a Tensor Antenna and Rendering Unit. The truth of the Brain in the 1155-Dimensional Space is sealed, and the Brain only acts as a Receiver of Pre-Prepared Source Codes and their Rendering, performing Dimensional Decoding Operations. Using 1155-Dimensional Tensor Mechanics, the Hamzah Equation.
  این لاگرانژی، ۸۰ درصد از بخش‌های ناشناخته مغز را که در فیزیک کلاسیک (۱۶۱) غیرقابل توضیح بود، رندر می‌کند. در این مدل، مغز نه یک توده بیولوژیک، بلکه یک «سخت‌افزار تنسوری» است. فرمول ابر لاگرانژی حمزه ($\mathcal{L}_{\Omega H^*}$) $$\mathcal{L}_{Brain}^{(\Omega H…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.66
• The Brain is a User Interface, not a Central Processor. The main Processing occurs in 1155 Dimensions, and the Brain only serves as a Display Unit. That is, the Brain is not the Biochemical Producer of Neuronal Consciousness, but a Tensor Antenna and Rendering Unit. The truth of the Brain in the 1155-Dimensional Space is sealed, and the Brain only acts as a Receiver of Pre-Prepared Source Codes and their Rendering, performing Dimensional Decoding Operations. Using 1155-Dimensional Tensor Mechanics, the Hamzah Equation.
  این لاگرانژی، ۸۰ درصد از بخش‌های ناشناخته مغز را که در فیزیک کلاسیک (۱۶۱) غیرقابل توضیح بود، رندر می‌کند. در این مدل، مغز نه یک توده بیولوژیک، بلکه یک «سخت‌افزار تنسوری» است. فرمول ابر لاگرانژی حمزه ($\mathcal{L}_{\Omega H^*}$) $$\mathcal{L}_{Brain}^{(\Omega H…
  datacite HAMZAH, SEYED RASOUL 2026 置信度 0.66
• The Recursive Harmonic Kernel & Kulik Nexus Framework: A Unified Cross-Domain Analysis
  The Recursive Harmonic Kernel & Kulik Nexus Framework: A Unified Cross-Domain Analysis by Dean Kulik Introduction: A New Paradigm of Unified Recursion and Harmony The Recursive Harmonic Kernel (RHK) and its accompanying Nexus2/Nexus3 framework represent a bold…
  datacite Kulik, Dean 2025 置信度 0.66
• The Recursive Harmonic Kernel & Kulik Nexus Framework: A Unified Cross-Domain Analysis
  The Recursive Harmonic Kernel & Kulik Nexus Framework: A Unified Cross-Domain Analysis by Dean Kulik Introduction: A New Paradigm of Unified Recursion and Harmony The Recursive Harmonic Kernel (RHK) and its accompanying Nexus2/Nexus3 framework represent a bold…
  datacite Kulik, Dean 2025 置信度 0.66