论文

提出 Vesta，一个统一的具身通用模型，将定位、空间推理、导航和长程规划能力整合到单个基础模型中，并证明通用模型能够达到或超越专家模型。Vesta is presented, a unified embodied generalist that consolidates localization, spatial reasoning, navigation, navigation, and long-horizon planning capabilities into a single foundation model and demonstrates that a generalist model can match or exceed specialists.

提出一种基于物体中心的残差强化学习框架，利用物体位姿精化 VLA 动作，使观测空间紧凑，在仿真与现实之间能够一致迁移。An object-centric residual RL framework is proposed that refines VLA actions using object poses, enabling a compact observation space that transfers consistently between simulation and reality.

提出一种多 Agent 框架，通过以确定性编排约束替代 "LLM-as-a-judge" 路由，解决可能在到达患者前未被发现的过早诊断交接与静默临床幻觉问题；观察到 OLDCARTS 完整度与语义熵之间存在统计显著的负相关，提示结构化信息采集与诊断不确定性降低相关。A multi-agent framework that addresses premature diagnostic handoff and silent clinical hallucinations that may go undetected before reaching the patient by replacing ``LLM-as-a-judge''routing with deterministic orchestration constraints is proposed and observes a statistically significant negative correlation between OLDCARTS completeness and semantic entropy, suggesting that structured information gathering is associated with reduced diagnostic uncertainty.

结果表明，由 LLM 编排的多 Agent 系统可将传统 AutoML 扩展为可信、自适应且面向生产的 BDaaS 生命周期自动化。The results suggest that LLM-orchestrated multi-agent systems can extend conventional AutoML toward trustworthy, adaptive, and production-oriented BDaaS lifecycle automation.

本文引入 trace-economic underwriting，将工具调用 trace 映射为客户风险敞口与可索赔损失，并以此表示用于定价、控制与风险转移，使用确定性经济标签而非 LLM 评判器。T trace-economic underwriting is introduced, which maps tool-use traces to customer exposure and claimable loss, then uses this representation for pricing, control, and risk transfer, and uses deterministic economic labels rather than an LLM judge.

CoRe（Context Relevance）被提出。该系统在一个大型短视频搜索引擎中每周重新部署，持续运行超过五个月，使用已部署的多模态相关性模型作为源，并以镜像生产融合代数的乘性比值形式来缩小仿真与生产之间的差距。CoRe (Context Relevance) is presented, such a system, redeployed weekly for over five months in a major short-video search engine, using the deployed multimodal relevance model as its source and a multiplicative ratio form mirroring the production fusion algebra to close the simulation-production gap.

FRAMe 展示了先进 LLM 如何被部署用于以人为本的任务规划，将自然语言指令转化为安全、高效且灵活的飞行路线。FRAMe signifies how advanced LLMs can be deployed for human-centric mission planning, translating natural language instructions into safe, efficient, and flexible flight routes.

该紧凑且量化原生、带内置控制的运行时为物联网音频场景下的端侧语义音频提供了实用基础；通过对转向接口的案例分析，可生成在部分属性上具有真实但有界控制的、承载口味联想的音乐。A compact, quantized runtime with built-in control a practical basis for on-device semantic audio in Internet-of-Sounds settings and a case study of the steering interface generates music carrying taste associations with genuine but bounded control for a subset of attributes.

提出 AgentKGV，一种用于知识图谱事实核查的智能体 LLM-RAG 框架，集成动态路由与迭代查询改写，以应对文档级检索中的表层形式不匹配问题。AgentKGV, the Agentic LLM-RAG framework for KG fact Verification, is proposed, that integrates dynamic routing and iterative query rewriting, which handles surface-form mismatch in document-level retrieval.

Motion4Motion 对视频中角色的 motion flow（而非骨骼）进行建模，使跨物种运动迁移更加容易。Motion4Motionmodels the motion flow of the character in a video instead of skeletons, which makes motion transfer across species easier, which makes motion transfer across species easier.

Xiaomi-Robotics-U0 是首个支持跨多种机器人本体的高质量多视角场景生成、并引入结构化、可控的具身迁移以实现细粒度编辑的模型，同时保持多视角一致性与交互动态。Xiaomi-Robotics-U0 is the first model to support high-quality multi-view scene generation across multiple robot embodiments and to introduce structured, controllable embodied transfer for fine-grained editing while preserving multi-view consistency and interaction dynamics.

GigaWorld-Policy-0.5 在保留未来视觉动力学训练收益的同时提升了机器人控制的推理效率，并引入 Mixture-of-Transformers 架构，将视觉动力学建模与动作生成分离到专门的专家模块中。GigaWorld-Policy-0.5 preserves the training benefits of future visual dynamics while improving inference efficiency for robot control, and introduces a Mixture-of-Transformers architecture that separates visual dynamics modeling and action generation into specialized experts.

PalmClaw 是一个开源 Agent 框架，原生运行于手机端，直接在设备上管理 session、memory、Skill、工具以及 agent loop，使 Agent 能够直接调用移动端能力，同时保证每一步操作的显式与可控。PalmClaw is an open-source agent framework that runs natively on mobile phones and manages the sessions, memory, skills, tools, and agent loop directly on the device, allowing agents to use mobile capabilities directly while keeping each action explicit and controlled.

SPEAR 是一个 Python 库，可通过模块化插件架构连接任意 Unreal Engine 应用并对其进行编程化控制；同时引入一种表达力强的高层编程模型，使用户能够以任意数据依赖关系指定复杂的 UE 工作图，并在单个 UE 帧内确定性执行这些图。SPEAR is a Python library that can connect to, and programmatically control, any Unreal Engine application via a modular plugin architecture, and introduces an expressive high-level programming model that enables users to specify complex graphs of UE work with arbitrary data dependencies among work items, and to execute these graphs deterministically within a single UE frame.

本文提出 VideoChat3，一个完全开放、高效且以视频为中心的通用 MLLM，仅以 4B 参数与更高效率，超越参数量相当或更大的已有开源模型。This work introduces VideoChat3, a fully open, efficient, and generalist video-centric MLLM, which surpasses prior open-source models with equal or larger parameter counts with only 4B parameters and higher efficiency.

本文提出 LongStraw，一个面向目标、感知架构的系统，用于 resident-state 虚拟化、response replay 和分布式梯度执行，它将实时训练图限制在 response 后缀范围内，同时在完整的 GRPO 组内复用代价高昂的 prompt 计算。This work presents LongStraw, an objective-aware, architecture-aware system for resident-state virtualization, response replay, and distributed-gradient execution that bounds the live training graph by the response suffix while reusing the expensive prompt computation across the complete GRPO group.

子空间对齐重连（SAR）表明，从参数几何中提取对推理有效的更新，可作为一种无需训练的机制来提升推理与多领域性能。Subspace-Aligned Rewiring (SAR) shows that extracting reasoning-effective updates from parameter geometry can serve as a training-free mechanism to improve reasoning and multi-domain performance.

SUFLECA（Scaling Up Feature LEarning for CAD-to-image Alignment），一种用于零样本 CAD 对齐的弱监督框架，含两项关键贡献，并提出一种几何一致的匹配算法以建立可靠的 CAD-图像对应。SUFLECA (Scaling Up Feature LEarning for CAD-to-image Alignment), a weakly supervised framework for zero-shot CAD alignment with two key contributions, and proposes a geometrically consistent matching algorithm that establishes reliable CAD-to-image correspondences.

Cross-encoder 在 RAG 流水线中具有较高的重排序准确率，但推理成本随序列长度呈二次增长，难以实时部署。本文通过两阶段流水线解决该问题：使用 Unsloth 框架与 LoRA 适配器，在自定义的查询-文档相关性数据集上对 LLaMA 3 (8B) 进行监督微调，随后进行 4-bit 量化以提升推理效率。该模型可替换双路检索 RAG 流水线中结合 BM25 与稠密向量检索的 cross-encoder，并在特定领域问答……Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage pipeline: supervised fine-tuning on a custom query-document relevance dataset via the Unsloth framework with LoRA adapters, followed by 4-bit quantization for efficient inference. The resulting model replaces the cross-encoder in a dual-retriever RAG pipeline combining BM25 and dense vector search. Evaluated on a domain-specific question-answering

本文提出 FlashRT，一种 Agent Harness，引导编码 Agent 将开发者编写的简易参考实现提升为优化的多 GPU 部署，并可灵活权衡时延与吞吐量等目标指标，证明在专家优化尚不成熟的平台上，由 Agent 驱动的优化具有更高的可扩展性。FlashRT is presented, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization.

分析表明，借助 LLM，美国约 15% 的工作任务可在保持同等质量的前提下显著提速完成，意味着 LLM 驱动的软件将对底层模型经济影响的规模化产生实质性作用。The analysis suggests that, with access to an LLM, about 15% of all worker tasks in the US could be completed significantly faster at the same level of quality, implying that LLM-powered software will have a substantial effect on scaling the economic impacts of the underlying models.

本文提出 Chunk Coverage (CC)，一种独立于 oracle 的 RAG 系统检索组件测试充分性准则，结果表明 CC 在无需测试 oracle 的情况下捕获了与有效测试相关的检索多样性。Chunk Coverage (CC), an oracle-independent test adequacy criterion for testing the retrieval component of RAG systems, is introduced and results show that CC captures retrieval diversity relevant to effective testing without requiring test oracles.

本文提出 HACO，一种运行时控制方案，将每次角色请求视为在候选 agent 实例上的可靠性约束选择问题，每个候选实例耦合了角色类型、LLM 与具体执行环境。HACO is proposed, a runtime control scheme that treats each role request as a reliability-constrained selection problem over candidate agent instances, each coupling a role type, an LLM, and a concrete execution environment.

本文为两部分组成的专题论文，介绍物理信息神经网络——一类在训练求解监督学习任务时遵循由一般非线性偏微分方程所描述的物理定律的网络；并展示如何利用这些网络推断偏微分方程的解，以及获得对所有输入坐标和自由参数完全可微的物理信息代理模型。This two part treatise introduces physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations and demonstrates how these networks can be used to infer solutions topartial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.

本文提出一个框架，将静态的单轮任务转化为动态多轮对话，其中用户意图在多轮间持续演化，同时保留每个任务原有的评估协议，使现有基准能够在无需新增标注的情况下作为受控测试平台被复用。This work introduces a framework that transforms static, single-turn tasks into dynamic multi-turn conversations in which the user's intent evolves across turns, while preserving each task's original evaluation protocol, enabling existing benchmarks to be reused as controlled testbeds without new annotation.

提出 Robostral Navigate，一个围绕该可扩展性目标构建的 8B 视觉语言模型，仅消费单目 RGB 图像流——这是机器人平台中最普及的传感器——通过在当前相机画面中指向下一目标位置来预测航点。Robostral Navigate, an 8B vision-language model built around this scalability objective, is introduced, which consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view.

结果表明，通过结合基础 LLM 改进（PaLM 2）、医学领域微调以及包括新颖集成精化方法在内的提示策略，医学问答正快速接近医生水平的表现。Results highlight rapid progress towards physician-level performance in medical question answering by leveraging a combination of base LLM improvements (PaLM 2), medical domain finetuning, and prompting strategies including a novel ensemble refinement approach.

近期条件视频生成模型已展现出将 3D 引擎渲染（如深度图与无纹理几何体）转化为照片级真实视频的潜力，可应用于游戏与沉浸式内容创作。此类应用要求长时程自回归生成，在持续合成新帧的同时维持持久的 3D 世界。自回归生成器以有界 KV cache 逐 chunk 合成视频，因此当相机再次访问已从上下文中驱逐的位置时，模型常会重新生成不一致的外观，尽管该Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry, into photorealistic videos for gaming and immersive content creation. These applications require long-horizon auto-regressive generation that continuously synthesizes new frames while preserving a persistent 3D world. Auto-regressive generators synthesize video chunk by chunk with a bounded KV cache, so when the camera revisits a location after its context has been evicted, the model often regenerates inconsistent appearance, even though the

提出 Multi-Head Latent Control，一种轻量级层，读取冻结 LLM 或 VLM 的隐状态轨迹以生成部署时的控制信号，从而支持从部分生成的提前交接，并在多模型系统中实现更准确的干预决策。Multi-Head Latent Control is introduced, a lightweight layer that reads hidden-state trajectories from a frozen LLM or VLM to produce deployment-time control signals, enabling early handoff from partial generations and more accurate intervention decisions in multi-model systems.

研究表明，当冻结模型与外部记忆配合、且该记忆将每个 episode 提炼为可检索的自然语言规则时，反馈信号足以支撑持续学习。It is shown that feedback is a sufficient signal for continual learning when the frozen model is paired with an external memory that distils each episode into retrievable natural-language rules when the frozen model is paired with an external memory.

实验跟踪器能够展示训练的进展，但更改正在运行的训练通常仍需编写特定于训练器的代码。我们提出了 Interactive Training 2，一个通过共享协议引导训练的开源控制平面。训练应用声明其暴露的设置和操作，人类与自动化控制器通过同一接口提交请求，训练循环在安全的控制点对请求进行验证并应用。定制的 Aim 工作区将实时指标与控制面板以及请求和结果的时序记录整合在一起。我们在 a[……]上展示了该系统。Experiment trackers show how training is progressing, but changing a live run still usually requires trainer-specific code. We present Interactive Training 2, an open-source control plane for steering training through a shared protocol. Training applications declare which settings and actions they expose, humans and automated controllers submit requests through the same interface, and the training loop validates and applies them at safe control points. A customized Aim workspace combines live metrics and controls with a chronological record of requests and outcomes. We demonstrate the system a

已部署的平台与其面向运维的评估共同构成了一条可信赖、统计上可靠的 AI 辅助工作流，适用于设施运维，并可推广到其他大型科学仪器。Together, the deployed platform and its operations-grounded evaluation present a promising workflow for trustworthy, statistically grounded AI assistance in facility operations, transferable to other large scientific instruments.

结果表明，RAG 增强的 LLM 能显著提升生成文本的事实一致性、领域专属性与规范精度，同时降低产生无支持内容的风险；本地部署的 RAG 增强 LLM 不应仅被视为文本生成工具，而应作为认知计算基础设施中的语义处理模块，在法律和信息高度动态的环境中支撑合规与组织决策。The results demonstrate that augmenting LLMs with RAG significantly improves the factual consistency, domain specificity and normative precision of generated texts while reducing the risk of unsupported content generation and indicate that locally deployed LLMs enhanced with RAG should be regarded not merely as text generation tools but as semantic processing modules within cognitive computing infrastructures supporting regulatory compliance and organizational decision-making in environments characterized by high legal and informational volatility.

大量实验表明，结合端上延迟感知设计与定制化训练策略，建立了高效 LVLM 编码的新 SOTA，在端上以近 1.7 倍速度运行的同时显著优于现有以编码器为中心的基线。Extensive experiments demonstrate that the on-device latency-informed design combined with the tailored training strategy establishes a new state-of-the-art for efficient LVLM encoding, significantly outperforming existing encoder-centric baselines while operating on-device at nearly 1.7xthe speed.

本文提出问题：与其缩减真实机器人数据占比，不如提高无机器人 UMI 数据的保真度，从而在后训练阶段移除该 anchor；并开源 HiFi-UMI，一套面向轨迹精度、夹爪间相对位姿、同步与视场协同设计的便携式 UMI 数据生产系统。It is asked whether raising the fidelity of robot-free UMI data, rather than shrinking the real-robot fraction, can remove that anchor at post-training, and open-source HiFi-UMI, a portable UMI data-production system co-designed for trajectory accuracy, inter-gripper relative pose, synchronization, and field of view.

本文研究无人机（UAV）可见光-近红外（VNIR）高光谱图像中 PFM-1 地雷的检测，使用光谱角制图（SAM）、匹配滤波器（MF）、自适应相干估计器（ACE）和约束能量最小化（CEM）。This paper studies PFM-1 landmine detection in unmanned aerial vehicle (UAV) visible and near-infrared (VNIR) HSI using spectral angle mapper (SAM), matched filter (MF), adaptive coherence estimator (ACE), and constrained energy minimization (CEM).