论文

首个面向预训练胸部 X 光报告生成器的无需训练 best-of-N 采样方案，显式建模"既往-当前-过渡"纵向先验，全面优于随机选择。This work presents the first training-free best-of-N sampling scheme for pre-trained chest X-ray report generators that is explicitly aware of this longitudinal prior to current transition, and outperforms random selection across the board.

提出 MEDIAREF：源自网络文档的公共知识库，支持跨 200 个媒体来源、可复现且低成本的 MBC 生成评估；给出可复现的构建与更新方法，并系统评测主流 LLM 在 MBC 生成任务上的表现。MEDIAREF, a publicly available knowledge store of web-sourced documents that enables reproducible, low-cost evaluation of MBC generation across 200 media sources, is introduced, describing a reproducible methodology for constructing and updating the collection, and assessing widely used LLMs on the MBC generation task.

提出 ATMA：在现有记忆系统之上的状态感知叠加层，保留被替换记录与过渡记录，为查询所需的"目标状态视图"构建证据包，并向问答模块暴露当前、历史与过渡三类标签。This work proposes ATMA, a state aware overlay for existing memory systems, which keeps superseded and transition records in the bank, builds evidence packets for the query's requested state view, and exposes current, historical, and transition labels to QA.

CheckRLM：通过 RAG 及时校验并修正事实错误的框架，有效提升推理过程的可靠性，大幅超越现有基线。CheckRLM is a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors, and substantially outperforms existing baselines.

VLA-Corrector：面向动作分块 VLA 策略的轻量级修正推理框架；引入轻量的潜空间视觉监控器，持续比对预测与实际视觉特征演化，可在线检测视觉动态偏差，缓解静态时域在执行鲁棒性与策略调用频率之间的权衡。VLA-Corrector, a lightweight corrective inference framework for action-chunked VLA policies, introduces a lightweight Latent-space Vision Monitor that continuously compares predicted and actual visual feature evolution, enabling online detection of visual dynamics deviations and mitigates the trade-off imposed by static horizons between execution robustness and policy-call frequency.

静脉识别是一种安全生物特征技术，常受限于标注数据稀缺与成像差异；而面向自然图像设计的增强策略可能破坏其关键的细粒度拓扑与纹理。本文提出 AGVBench，在 5 个公开掌/指静脉数据集、7 种骨干网络（含经典 CNN、视觉 Transformer 及静脉专用模型）上评测 30 种代表性增强策略。结果显示，多图混合类方法（如 MixUp、PuzzleMix……Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination. We present AGVBench, which evaluates 30 representative augmentation strategies on five public palm- and finger-vein datasets with seven backbone architectures, covering classic CNNs, vision transformers, and vein-specific recognition models. Our results show that multi-image mixing methods (e.g., MixUp, PuzzleMi

WARP：一个直接从已发布权重还原微调模型训练数据混合比例的框架，抽取几何特征并映射至各领域占比，可采用无参数 softmax 读出器，或基于合成混合训练的 MLP 投影器。WARP is introduced, a framework that recovers a fine-tuned model's training mixtures directly from its released weights and extracts geometric features and maps them to domain proportions using either a parameter-free softmax readout or an MLP projector trained on synthetic mixtures.

提出"自主策略演化"评估范式：在固定交互预算下，由 harness-model Agent 反复编辑可执行策略系统；并在 EvoPolicyGym 中实例化，该基准基于一组紧凑型交互式 RL 环境构建，用于评测 Agent 如何迭代改进已探索策略。This work introduces Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget, and instantiates this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies.

提出了一种 Agent 设计和一套经过验证、可复用的方法，用于研究显式记忆层如何影响长周期 LLM Agent 决策，并给出了一种替代的有界契约。An agent design and a validated, reusable methodology for studying how explicit memory layers shape long-horizon LLM-agent decisions, as well as an alternative bounded contract, are introduced.

提出 Attention Separation，在保留与 Self-Flow 相同的双时间步输入的同时，阻止被分配到不同噪声水平 token 之间的注意力，并表明 Attention Separation 本身通过将单张图像拆分为多个有效训练部分来扩充训练数据，从而带来增强效果。Attention Separation is introduced, which preserves the same dual-timestep input as Self-Flow while blocking attention between tokens assigned to different noise levels, and shows that Attention Separation itself provides an augmentation effect by splitting a single image into multiple effective training parts to expand the training data.

提出 TRACE，一个针对演化会话数据在时序证据图上的查询处理框架，将词汇召回与证据重建分离，从而在长会话历史中实现有界的查询时推理。TRACE is presented, a query processing framework over temporal evidence graphs for evolving conversational data that separates lexical recall from evidence reconstruction, enabling bounded query-time reasoning over long conversational histories.

本文提出基于检索增强生成的多模态大学聊天机器人，将 LLM 与语义检索相结合，从以学校为中心的资源（如大学手册）中生成基于上下文的回复。This work presents the multimodal university chatbot with retrieval-augmented generation, which combines the large language model with semantic retrieval to produce context-based responses from institution-centric resources, such as the university handbook.

提出 Logit 贡献度评分（LOCOS），一种可感知写入的检测器，通过将每个注意力头的 OV 电路输出投影到答案 token 的去嵌入方向进行打分，在单次前向传播中对比 needle 与非 needle 源位置。Logit-Contribution Scoring (LOCOS) is introduced, a write-aware detector that scores each head by the projection of its OV-circuit output onto the answer-token unembedding direction, contrasting needle and off-needle source positions in a single forward pass.

仅启用记忆（不修改模型的任务-动作行为）即可将基础 Agent 性能提升约 2–4 倍，使 32B 开源权重模型具备与 Claude Opus 4.5、Gemini 3.1 Pro Thinking 等前沿系统相竞争的能力。Opting memory alone--without modifying the model's task-action behavior--improved the base agent's performance ~2x-4x, bringing a 32B open-weight model competitive with frontier systems such as Claude Opus 4.5 and Gemini 3.1 Pro Thinking.

结果表明，在重建频繁或高维场景中（如 multiprobe grid 等）基于网格的方法可能具有竞争力，因为这些场景下索引成本与维度鲁棒性决定性能。The results suggest that grid-based methods such as multiprobe grid may be competitive in rebuild-heavy or high-dimensional settings where indexing cost and dimensional robustness dictate performance.

本文适配了一款专家混合扩散语言模型 DiffusionGemma-26B，并在医学视觉问答数据集上，使用相同的 LoRA 配置将其与同规模的自回归模型 Gemma-4-26B 进行基准对比，由对冗长度鲁棒的 LLM 裁判打分。This work adapts a mixture-of-experts diffusion language model, DiffusionGemma-26B, and benchmark it against its same-size AR sibling Gemma-4-26B under an identical LoRA recipe on medical visual question answering datasets, scored by a verbosity-robust LLM judge.

AMVL 在潜空间集成的 MLLM 中实例化，持续优于多种强离散和潜空间推理基线，在复杂 BLINK 基准上平均得分提升 +10.83，单个推理任务最高提升 +32.00，分析也确认了潜空间稳定性的改善。AMVL is instantiate in a latent-integrated MLLM and it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.

应在真实类别分布下使用跨网络评估来判断部署就绪度，而非仅依赖域内准确率。Deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone, to suggest deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone.

本文提出了 Graph-PRefLexOR，这是一族基于图结构的推理模型，使用 Group Relative Policy Optimization 进行微调，将推理过程组织为显式阶段，分别用于机理探索、图构建、模式提取和假设合成，确立了面向图结构的强化学习作为通向可解释 AI 系统的路径，可应用于材料设计及其他科学领域的科学假设生成。Graph-PRefLexOR is developed, a family of graph-native reasoning models fine-tuned with Group Relative Policy Optimization to organize reasoning into explicit phases for mechanism exploration, graph construction, pattern extraction, and hypothesis synthesis, establishing graph-native reinforcement learning as a pathway toward interpretable AI systems for scientific hypothesis generation in materials design and other scientific applications.

本文将 PSP 形式化为逆向规划问题，并提出 SPIRE，一个通过有意破坏干净幻灯片的视觉结构来近似求解 PSP 的原则性框架，从而构建一个可验证的去噪任务。This work formulates PSP as an inverse planning problem, and proposes SPIRE, a principled framework to solve PSP approximately, by intentionally corrupting the visual structures of clean slides, which creates a verifiable task to denoise the corruption.

AdaTrans 是一个通过三大核心机制解决 C 代码到 Rust 自动转换的框架：策略驱动的检索增强生成（RAG）机制，用于将编译器错误映射到具体修复；错误分层转换策略（ESTS），可根据错误类型自适应调整行为；以及多阶段验证流水线，以确保可编译性与功能等价性。AdaTrans is a framework that addresses the automated transformation of C code to Rust through three core mechanisms: a Strategy-Driven Retrieval-Augmented Generation (RAG) mechanism to map compiler errors to specific repairs, an Error-Stratified Transformation Strategy (ESTS) that adapts its behavior based on error types, and a multi-stage validation pipeline to ensure both compilability and functional equivalence.

实验结果表明，所得参数集可生成可区分的个性化换道行为，同时 RAG 始终提升偏好理解效果，尤其对隐式指令效果显著，表明将基于 LLM 的自然语言交互与 Apollo 集成以支持个性化换道行为生成具有潜力。Experimental results show that the derived parameter sets generate distinguishable personalized lane-change behaviors, while RAG consistently improves preference interpretation, particularly for implicit commands, indicating the potential of integrating LLM-based natural-language interaction with Apollo to support personalized lane-change behavior generation.

本文提出 AI-Infra-Guard，一个围绕单一观测组织 AI 红队测试的开源框架，是目前唯一覆盖所有层面（包括对日益扩展 AI Agent 能力的 Agent Skills 供应链审计）的开源框架。AI-Infra-Guard is presented, an open-source framework that organizes AI red teaming around a single observation, and is the only open-source framework to span all of these, including supply-chain auditing of the agent skills that increasingly extend AI agents.

AGE 专注于预测关键节点以外的节点，采用可学习节点采样器，在基于非参数检索组件的 GraphQA 任务上取得显著提升，在四个具有不同特征的基准数据集上均达到更高的准确率。AGE focuses on predicting nodes apart from key nodes, utilizing a learnable node sampler, and significantly improves approaches using non-parametric search component in GraphQA tasks, achieving superior accuracy across four benchmark datasets with distinct characteristics.

在三种多模态 LLM 主干模型上，MRPO 均稳定优于标准 GRPO 及一项最新的 RL 基线；在 Qwen3-VL-8B-Instruct 上甚至超越规模显著更大的医学 MLLM（如 HuatuoGPT-Vision-34B）2.79 分。Across three multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Instruct even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 2.79 points.

本文探索多轮视觉推理，观察到 MLLM 反复无法定位目标，导致冗长的推理轨迹，进而提出 PixelEyes，一种将推理与感知显式解耦的多轮视觉推理 Agent。This paper explores multi-turn visual reasoning and observes that MLLMs repeatedly fail to localize the target, leading to long, redundant trajectories, and proposes PixelEyes, a multi-turn visual reasoning agent that explicitly decouples reasoning from perception.

在富文本图像生成基准上的实验表明，在数据预算匹配条件下，DataEvolver 比固定数据集基线生成更有用的训练数据，且结果表明被拒绝的样本可为改进富文本图像数据构建提供可操作的反馈信号。Experiments on text-rich image generation benchmarks show that DataEvolver produces more useful training data than fixed-dataset baselines under matched data budgets, and results suggest that rejected samples can provide actionable feedback for improving text-rich image data construction.

本文提出 QVal，一个无需训练即可直接评估密集监督信号的测试平台，发现简单提示基线始终优于文献中近期提出的密集监督方法，且性能按模型家族高度聚类。QVal, a training-free testbed for directly evaluating dense supervision signals, is introduced, finding that simple prompting baselines consistently outperform recent dense supervision methods from the literature, and that performance clusters strongly by family.

本工作提出 MuSViT (Music Score Vision Transformer)：首个面向乐谱表征的基础视觉模型——一个通过 Masked Autoencoders 在 IMSLP 970 万页数据上预训练的 ViT 编码器。This work introduces MuSViT (Music Score Vision Transformer): the first foundation vision model for sheet music representation -- a ViT encoder pre-trained via Masked Autoencoders on 9.7 million pages from the IMSLP.

本文提出 DuoMem，一种双空间蒸馏框架，可将程序化问题求解能力从大型教师模型迁移到紧凑学生模型，并适用于实时边缘部署，而这一点对教师模型而言颇具挑战。DuoMem is introduced, a dual-space distillation framework that transfers procedural problem-solving ability from a large teacher model to compact student models and is viable for real-time edge deployment, which would be challenging for the teacher.

BeyondArena 是首个面向表格数据的统一整体基准，支持多种任务类型（IID、时序、分组），覆盖样本量与特征维度的不同尺度，并涵盖来自广泛学科的多样化特征类型。BeyondArena is the first unified holistic benchmark for tabular data that supports diverse task types (IID, temporal, grouped), across sample size and feature dimensionality scales, with diverse feature types from a broad range of disciplines.

本文提出 ILLUME-X，一种先进的统一多模态范式，通过提升多模态数据效率并稳定多模态训练过程，实现高质量、自由形式的交错图文生成。This paper introduces ILLUME-X, an advanced unified multimodal paradigm that enables high-quality, free-form interleaved text-image generation by improving multimodal data efficiency and stabilizing the multimodal training process.

本文提出 Monotonic Inference Policy Update (MIPU)，一种两步式 LLM 强化学习框架：构建采样器引用的候选更新，并使用推理侧差距代理选择性接受同步候选；实验表明 MIPU 提升了平均推理性能与训练稳定性。Monotonic Inference Policy Update (MIPU) is introduced, a two-step LLM RL framework that constructs sampler-referenced candidate updates and selectively accepts synchronized candidates using an inference-side gap proxy, and experiments show that MIPU improves average reasoning performance and training stability.

本文提出 MultiDepth-3k (MD-3k)，一个用于衡量深度层偏好与多层空间关系准确率 (ML-SRA) 的稀疏双层序数基准；领先的深度基础模型在标准 RGB 输入下表现出不同的层偏好，表明同一分层几何可在不同模型中被差异化地解析。MultiDepth-3k (MD-3k), a sparse two-layer ordinal benchmark for measuring depth-layer preference and multi-layer spatial relationship accuracy (ML-SRA), is introduced and leading depth foundation models exhibit diverse layer preferences under standard RGB input, showing that the same layered geometry can be resolved differently across models.

研究发现，模型规模、推理能力与 Agent 脚手架以不同方式影响弃答行为，能力更强或更大的模型有时反而在及时弃答上表现更差。It is found that model scale, reasoning, and agent scaffolding affect abstention in different ways, where larger or more capable models sometimes perform worse at timely abstention.

本文探讨了具身集体智能 (ECI) 这一未来多机器人范式，其中机器人团队将世界上下文、任务进度与技能经验作为共享资源进行累积与利用。This article explores Embodied Collective Intelligence (ECI), a future multi-robot paradigm in which a robot team accumulates and uses world context, task progress, and skill experience as shared resources.