独立 AI 资讯库
从自动抓取数据库实时读取，适合快速浏览、检索和后续扩展成完整资讯站。
arXiv:2607.15295v1 Announce Type: cross Abstract: We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning. Using an early-fusion Vision Transformer and modality dropout as masking, the model is trained to align the embeddings of global and per-modality
arXiv:2607.16038v1 Announce Type: new Abstract: Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, au
arXiv:2607.15987v1 Announce Type: new Abstract: The ODRL policy language is emerging as the de-facto standard for policy modelling data access and usage preferences, AI governance policies and data workflows in European dataspaces. The current standard has no mathematical formal semantics to descri
arXiv:2607.15901v1 Announce Type: new Abstract: Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation. This bottleneck motivates models that can anticipate the effects
arXiv:2607.15845v1 Announce Type: new Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions. Existing large language model (LLM) approaches often treat this as a direct text-to-JSON gene
arXiv:2607.15781v1 Announce Type: new Abstract: Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or re
arXiv:2607.15776v1 Announce Type: new Abstract: OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world ontologies are often incomplete, wh
arXiv:2607.15715v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for complex information-extraction tasks, yet it remains unclear whether agentic components such as reflection and memory lead to observable and controllable improvements over fixed LLM workflows
arXiv:2607.15686v1 Announce Type: new Abstract: We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-specific models, tool-augmented LLMs, and scientific language models. Ho
arXiv:2607.15660v1 Announce Type: new Abstract: While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environments that demand seamless tool i
arXiv:2607.15647v1 Announce Type: new Abstract: LEED v4.1 BD+C certification remains a document-intensive process that requires reviewers to read hundreds of pages of project evidence and apply credit-specific threshold logic by hand. This paper investigates whether small, locally deployed language
arXiv:2607.15592v1 Announce Type: new Abstract: Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to
arXiv:2607.15550v1 Announce Type: new Abstract: Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks where a single erroneous action can lead to irreversible consequences. Existing safety mechani
arXiv:2607.15442v1 Announce Type: new Abstract: Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme u
arXiv:2607.15439v1 Announce Type: new Abstract: Our previous ARC-AGI-3 agent bundled executable world modeling, scheduled simplification, and exact replay verification, leaving unclear which idea accounted for its performance. We address this attribution question with four nested Codex-based agents
arXiv:2607.15418v1 Announce Type: new Abstract: We introduce DrawingVQA, the first benchmark designed to evaluate multimodal large language models (MLLMs) on real-world construction drawings -- a core media in architecture, civil, and many other engineering practices. Unlike natural images or schem
arXiv:2607.15388v1 Announce Type: new Abstract: Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni
arXiv:2607.15367v1 Announce Type: new Abstract: Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop it
arXiv:2607.15314v1 Announce Type: new Abstract: Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited. A healthcare model must handle patient consultation, clinical reasoning over text and images
arXiv:2607.15281v1 Announce Type: new Abstract: Causal and intervention-based question answering is fundamental to advancing large language models (LLMs) toward reasoning beyond surface-level correlations and understanding underlying causal mechanisms. However, existing LLM-based methods often rely
arXiv:2607.15280v1 Announce Type: new Abstract: Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering. Existing Large Language Model (LLM) approaches exhibit a critical knowledge-reasoning gap: despite encoding extensive medical k
研究团队提出了全新基准 HAPACT，专注于电影视频中以人为中心的物理冲击事件定位。此前视频中的人体物理推理主要聚焦于日常交互（如接触、压力、姿态与运动），而针对短暂且高强度的物理冲击事件研究相对匮乏。HAPACT 填补了高动态剧烈碰撞场景下具身感知理解的数据空白，为具身智能物理推理、影视动作分析及交互算法评测提供了重要支持。
视觉问答（VQA）模型长期受困于偏差问题，往往容易过拟合训练数据中频繁出现的统计规律。过去学术界大多仅关注单纯的语言偏差，而近期多模态偏差问题逐渐引起关注。针对这一挑战，本研究（arXiv:2610.22845v1）提出了用于在鲁棒视觉问答中缓解双模态偏差的变分与分解方法。该成果有助于抑制跨模态交互中的虚假相关性，对开发更鲁棒、泛化能力更强的多模态大模型与 VQA 系统具有积极的参考价值。
文本与视频目标轨迹之间的细粒度对齐是多模态理解领域的核心难题。现有主流嵌入模型主要擅长视频级别的全局检索，但其单一的全局特征表示往往会将多个目标及其时空动态交织混淆，难以捕捉局部轨迹。研究团队提出了 VTrajEmbed，通过构建时空嵌入（Spatiotemporal Embeddings）来实现文本与视频中具体物体轨迹的精确对应。该工作为细粒度视频理解、视频目标跟踪检索以及具身智能交互等应用场景提供了新的技术支撑。
视障与低视力严重制约了许多人独立完成日常任务的能力，这也催生了能够提供实用指引的 AI 辅助技术的快速发展。然而，现有的视觉基准测试难以充分评估多模态模型在真实日常场景中提供有效辅助的能力。为此，研究团队推出了多模态第一人称视角基准测试 VISTA，专注于评估模型在面向目标的感知与实时辅助方面的综合表现。该基准为开发者检验多模态 Agent 与具身无障碍辅助系统的实用价值提供了关键评估标准。
该研究提出了用于评估视觉语言模型（VLM）在自动驾驶边缘长尾场景中时空推理能力的基准 STRIDE。研究指出，在自动驾驶中单纯感知周围物体并不足够，若无法理解物体随时间的运动与交互模式，可能导致灾难性的危险决策。这项工作针对 VLM 是否能将空间感知与时间维度推理相结合展开评测，对开发者构建高可靠性端到端驾驶模型及行业安全评测具有重要参考价值。
本研究针对跨中心免疫组织化学（IHC）图像分级中存在的域偏移问题，探索了输入与特征空间的校正方案。当前病理基础模型（FM）主要基于苏木精-伊红（H&E）图像训练，但常作为冻结特征提取器迁移至 IHC 任务中，医院间的染色与设备差异会显著影响分级准确率。该项研究为解决医疗基础模型在跨院异构场景下的泛化瓶颈提供了技术路径，对数字病理 AI 的实际临床部署具有重要参考价值。
视频编辑中的创意意图通常可以通过文本指令、图像参考（如主体外观）或视频参考（如镜头运镜）等多种模态及其组合来表达。为此，研究团队提出了统一框架 OmniXRef，旨在支持任意组合的多模态、多参考视频编辑任务。该研究打破了传统编辑模型仅支持单一输入模态或受限于特定参考类型的技术瓶颈。这项工作为下一代 AI 视频创作工具与自动化影视后期流水线提供了更灵活、更可控的技术范式。
现有视频多模态大语言模型（MLLM）主要在时间维度上组织观测信息，但在具身空间推理任务中，更需要在空间维度上整合全局环境。为此，研究团队探索利用鸟瞰图（BEV）视觉 Token 构建空间表征，克服了传统视频表征仅在相邻帧间保持局部一致的缺陷。该方法显著提升了空间几何推理的效率与一致性，为具身智能、机器人导航以及长时程空间决策提供了更高效的多模态架构方案。
本研究提出了针对第一人称视频空间推理任务的创新方法 EgoP²C。在第一人称（Egocentric）视频中解决复杂空间推理问题，需要系统性地确定所需证据、获取针对性的视觉线索并通过多步推理进行整合。现有视觉语言模型（VLM）在面对此类多阶段长链条空间推理时往往表现不佳。该研究通过内化“规划-感知-组合”（Plan-Perceive-Compose）流程，为具身智能与第一人称视频理解提供了更稳健的推理架构与范式。