论文

本文对 LLM 的评估方法进行了全面综述，围绕三个关键维度展开：评估什么、在何处评估、如何评估，并为 LLM 评估领域的研究者提供了宝贵洞见。This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate, and offers invaluable insights to researchers in the realm of LLMs evaluation.

该报告主张并例证了一种严谨且基于经验的方法来研究 AI 意识：依据获得最佳支持的神经科学意识理论，详细评估现有 AI 系统。This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of best-supported neuroscientific theories of consciousness.

该模型在效果上匹配基于优化的方法，同时实现近 800 倍加速，并以明显更少的参数量和更低的训练/推理开销超越 SOTA 可泛化模型的零样本性能，整体效率显著提升。This model matches optimization-based methods while delivering nearly 800x speedup, and surpasses the zero-shot performance of state-of-the-art generalizable models with markedly fewer parameters and reduced training/inference overhead, achieving an overall efficiency improvement.

本文提出 token 时间连续扩散 (TTCD)，一种新的扩散语言模型，运行于连续空间，将高斯噪声确定性地映射到最终的 token canvas 而无需额外采样，并引入每个 token 时间的新概念。This paper introduces token time continuous diffusion (TTCD), a new diffusion language model which operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and incorporates a new notion of per-token times.

提出 Lucid，一个黑盒对抗框架，在严格的图像受限威胁模型下攻击多模态记忆管道，无需访问目标 MLLM、目标检索编码器或文本通道，揭示了多模态记忆管道中的结构性漏洞。Lucid is proposed, a black-box adversarial framework that compromises multimodal memory pipelines under a strictly image-bounded threat model, requiring no access to the target MLLM, target retrieval encoder, or the text channel, exposing a structural vulnerability in multimodal memory pipelines.

S1-Omni 基于 S1-Omni-Corpus 训练，覆盖 200 个科学任务并包含数百万推理样本，在 60 余个科学基准上进行了评估，为统一的科学建模提供了一条可行路径。S1-Omni is trained on S1-Omni-Corpus, which covers 200 scientific tasks and contains millions of reasoning samples, and is evaluated on over 60 scientific benchmarks, providing a practical path toward unified scientific modeling.

提出数据科学世界模型概念，通过基于当前工作流状态和候选操作预测环境状态转移来建模数据科学执行环境；提出DSWorld框架，结合结构化状态构建、成本感知路由、轻量级真实执行以及基于LLM的昂贵操作模拟器。The concept of Data Science World Model is introduced, which model the data science execution environment by predicting environment state transitions conditioned on current workflow states and candidate operations and proposes DSWorld, a practical framework that combines structured state construction, cost-aware routing, lightweight real execution, and an LLM-based simulator for expensive operations.

Xiaomi-Robotics-1是一个强大的机器人基础策略，能在复杂灵巧任务上以高数据效率高效微调，并在多个仿真基准上超越SOTA方法。Xiao-Robotics-1 serves as a strong robot foundation policy that can be efficiently fine-tuned on complex, dexterous tasks with high data efficiency and across multiple simulation benchmarks, Xiaomi-Robotics-1 outperforms state-of-the-art methods.

提出xHC（扩展型超连接），是首个在N=4之外实现有意义扩展的HC系列方法；引入xHC-Flash，将每个子层的内存访问量从73.5C降至40C（与mHC在N=4时的34C相当），同时保留完整xHC带来的性能增益。This work proposes xHC (Expanded Hyper-Connections), the first HC-family method to achieve meaningful expansion beyond $N{=}4$ and introduces xHC-Flash, which reduces the per-sublayer memory traffic from $73.5C$ to $40C, comparable to the $34C$ required by mHC at $N{=}4$, while retaining the gains of full xHC.

表明差值信号显著提升在策略蒸馏效果，提出新方法称为在策略差值蒸馏（OPD），使推理LLM仅需短暂的后训练即可获得强性能。It is shown that the delta signal substantially improves on-policy distillation and the new distillation method is referred to as On-Policy Delta Distillation (OPD), enabling reasoning LLMs to achieve strong performance with only a short post-training period.

VideoRAE 被提出——一种表征自编码器，将冻结视频基础模型的特征转换为紧凑、可重建的潜变量以用于视频生成，使冻结视频基础表征成为紧凑、通用且面向生成的视频潜变量。VideoRAE is introduced, a representation autoencoder that converts features from a frozen video foundation model into compact, reconstruction-capable latents for video generation, establishing frozen video foundation representations as compact, versatile, and generation-friendly video latents.

RAGU是一个开源模块化GraphRAG引擎，通过将抽取与整合分离来解决抽取-整合问题：实体和关系经过两阶段类型化抽取、基于DBSCAN的去重、LLM摘要和Leiden社区检测。RAGU, an open-source modular GraphRAG engine, addresses extraction from consolidation by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection.

对一个旨在使魁北克汽车保险合同更易理解的SOTA RAG系统进行以人为中心的外在评估，结果显示该系统被视为认知均衡器，用户对系统所提供的自主感的重视程度甚至超过知识本身。A human-centric, extrinsic evaluation of a state-of-the-art Retrieval-Augmented Generation system, designed to make Quebec automobile insurance contracts more understandable, shows the system is perceived as a cognitive equalizer, and users value the sense of autonomy the system provides even more than the knowledge itself.

TARS是一个集成在Visual Studio Code中的LLM驱动Agent，通过直接锚定到被分析代码的自主解释来支持程序理解，基于轻量级心智理论范式构建。TARS is an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis, built around a lightweight Theory of Mind paradigm.

在一个 recipe 级操作机制中，fan-in Muon 在共享 KL 与 clipping 下支持更激进的稳定有效步长：该余量在优化仍有空间时最大，而在接近饱和、经 AdamW 调参后或使用 magnitude matching 时收缩。A recipe-level operating regime in which fan-in Muon supports a more aggressive stable effective step under shared KL and clipping is identified: the margin is largest when optimization headroom remains and contracts near saturation, after AdamW tuning, or under magnitude matching.

提出RESOURCE2SKILL框架，将教程视频、仓库、文章和参考制品等多模态资源蒸馏为软件Agent的可执行技能，并验证了多模态技能格式、层次化组织、来源多样性、选择策略与在线获取的价值。RESOURCE2SKILL is presented, a framework that distills multimodal resources, including tutorial videos, repositories, articles, and reference artifacts, into executable skills for software agents, and confirms the value of multimodal skill format, hierarchical organization, source diversity, selection strategy, and online acquisition.

本文回顾现有方法，并融合多种技术从数据与模型规模两方面扩展预训练，提出一条自动化流水线以构建专用、多样且经过筛选的图像数据集，替代自监督文献中常用的未筛选数据。This work revisits existing approaches and combines different techniques to scale the pretraining in terms of data and model size, and proposes an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.

BLIP-2 在多种视觉-语言任务上取得 SOTA 性能，可训练参数远少于现有方法，并展现出遵循自然语言指令进行零样本图生文的新兴能力。BLIP-2 achieves state-of-the-art performance on various vision-language tasks, despite having significantly fewer trainable parameters than existing methods, and is demonstrated's emerging capabilities of zero-shot image-to-text generation that can follow natural language instructions.

一种面向语言模型推理的新框架 Tree of Thoughts (ToT)，推广了流行的 Chain of Thought 提示方法，允许在作为问题求解中间步骤的连贯文本单元（thoughts）上进行探索。A new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.

在 BIG-bench 上对 OpenAI 的 GPT 模型、Google 内部稠密 Transformer 架构及 Switch 风格稀疏 Transformer 进行评估，模型规模跨越百万至千亿参数，结果显示性能与校准均随规模提升而改善，但绝对水平仍然欠佳。Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.

本文推出 ScanNet，一个 RGB-D 视频数据集，包含 1513 个场景中的 250 万视角，标注有三维相机位姿、表面重建与语义分割，并表明使用该数据可在多项三维场景理解任务上取得 SOTA 性能。This work introduces ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations, and shows that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks.

对 SOTA LLM GPT-4 在医学能力考试与基准数据集上进行全面评估，并通过案例研究定性探索其行为，展示了 GPT-4 解释医学推理、为学生定制个性化讲解以及围绕病例交互式构造新反事实场景的能力。A comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets and explores the behavior of the model qualitatively through a case study that shows the ability of G PT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case.

本文提出 Toolformer，训练其决定调用哪些 API、何时调用、传入什么参数，以及如何将结果最佳地融入后续 token 预测，在多种下游任务上显著提升零样本性能。This paper introduces Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction, which achieves substantially improved zero-shot performance across a variety of downstream tasks.

研究发现 ChatGPT 在大多数任务上以零样本学习优于其他 LLM，在部分任务上甚至超过微调模型，并且对非拉丁文字语言的理解能力优于生成能力。It is found that ChatGPT outperforms LLMs with zero-shot learning on most tasks and even outperforms fine-tuned models on some tasks and is better at understanding non-Latin script languages than generating them.

本文介绍 Matterport3D，一个大规模 RGB-D 数据集，包含来自 90 个建筑物级场景共 194,400 张 RGB-D 图像的 10,800 个全景视图，可支持多种监督与自监督计算机视觉任务，包括关键点匹配、视角重叠预测、由彩色图像预测法线、语义分割和区域分类。Matterport3D is introduced, a large-scale RGB-D dataset containing 10,800 panoramic views from 194,400RGB-D images of 90 building-scale scenes that enable a variety of supervised and self-supervised computer vision tasks, including keypoint matching, view overlap prediction, normal prediction from color, semantic segmentation, and region classification.

本文对上述解决方案进行了详细综述，总结了其技术创新与实验结果，比较了各方法的优势与适用条件，并给出推荐方案。This article provides a detailed review of the solutions above, summarizing both the technical novelties and empirical results, and compares the benefits and requirements of the surveyed methodologies and provides recommended solutions.

本文详细介绍了 CNN 在多个方面的改进，包括层设计、激活函数、损失函数、正则化、优化与快速计算，并阐述了卷积神经网络在计算机视觉、语音与自然语言处理中的多种应用。This paper details the improvements of CNN on different aspects, including layer design, activation function, loss function, regularization, optimization and fast computation, and introduces various applications of convolutional neural networks in computer vision, speech and natural language processing.

本文介绍了 NOWJ 团队参加 COLIEE 2026 全部五项任务的方法与结果，采用基于稠密检索、注意力重排序和小样本提示 LLM 推理的检索增强生成框架。This paper presents the methodologies and results of the NOWJ team's participation across all five tasks of the COLIEE 2026 competition and adopts a retrieval-augmented generation framework with dense retrieval, attention-based reranking, and few-shot-prompted LLM reasoning.

本文认为安全 Agent 基准应在任务成功率之外，同时衡量经济效率与运维适配性，并提出成本感知、SOC 原生的评估方法，以更清晰地反映当前哪些模型具有实际可用价值，以及防御性 Agent 仍需改进的方向。It is argued that security-agent benchmarks should measure economic efficiency and operational fit alongside task success alongside task success, and cost-aware, SOC-native evaluations provide a clearer picture of which models are practically useful today and where defensive agents still need to improve.

SeeR-VLA 将点图变换到以末端执行器为原点、机器人基座轴对齐的机器人中心坐标系，并由基于预训练 RGB 权重初始化的编码器提取点图特征，将其在不增加 token 数的情况下叠加到对应的 RGB token 上。SeeR-VLA is proposed, which transforms pointmaps into a robot-centric frame with an end-effector origin and robot-base-aligned axes, and an encoder initialized from pretrained RGB weights extracts pointmap features, which are added to corresponding RGB tokens without increasing the token count.

本文提出自验证推理器 SVR-R1，一种多轮强化学习框架，将模型自身的验证转化为多模态推理的学习信号，提供了一种简洁而有效的多模态推理自举方案。Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning, is introduced, offering a simple yet effective recipe for bootstrapping multimodal reasoning.

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

本文从参考图像中识别低秩背景特征子空间，并以闭式方式将参考与查询特征投影到其正交补空间，从而获得更清晰的语义匹配，并在 PACO-Part、FSS-1000 以及 ISIC2018 等跨域数据集的无训练方法中达到新的 SOTA，表明显式去除背景子空间是一次性定位中极为有效的原则。This paper identifies the low-rank background feature subspace from the reference image and project the reference and query features onto its orthogonal complement in closed form, yielding cleaner semantic matching, and establishes a new state of the art among training-free methods on PACO-Part, FSS-1000, and cross-domain datasets such as ISIC2018, demonstrating that explicit background subspace removal is a highly effective principle for one-shot localization.

HOMIE 提出了一种更优的 MLLM 集成策略，可在不损害文本编码器可控性或引入昂贵重新对齐的前提下，提取参考级关系知识，并在 self-attention 中引入全局多模态引导，使 MLLM 派生的语义特征与 VAE token 更好对齐。HOMIE proposes a better MLLM integration strategy to extract knowledge of reference-level relationships without compromising the controllability of text encoders or incurring costly re-alignment, and introduces global multimodal guidance within self-attention to better align MLLM-derived semantic features with VAE tokens.

本文提出 SWE-Pruner Pro，在 Agent 内部直接对工具输出进行剪枝，通过一个小型 head 将 Agent 自身的内部表征转化为针对每一行的 keep-or-prune 标签，并采用以每段工具输出行数为键的长度感知嵌入。SWE-Pruner Pro is proposed, which prunes tool outputs directly inside the agent, with a small head turns the agent's own internal representations into a keep-or-prune label for each line, with a length-aware embedding keyed to each tool output's line count.