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。
研究发现，现代多语言 tokenizer 对乌克兰语等代表性不足的西里尔字母语言切分更细，导致成本上升、可用上下文容量下降。在 BrUK 和 Brown 语料库上，乌克兰语相对英语的全文 token 开销在现代 tokenizer 中达到 68%—121%，较旧的 cl100k 中则达到 220%。研究测试的 LLMLingua-2 可在电商 RAG 基准中将乌克兰语输入长度减少 47%—49%，而采用均衡字节级 BPE 设计的 tokenizer 可将留出集的乌克兰语/英语 token 比从 2.22 倍降至 1.30 倍。结果表明，训练数据中的文字系统分配会影响分词效率，开发者可在推理压缩和 tokenizer 设计两个阶段进行缓解。
arXiv:2608.21377v1 Announce Type: new Abstract: Sycophancy in large language models, the tendency to prioritize user agreement over truthful responses, has been documented extensively but studied primarily in single-turn settings. This paper investigates a critical question: does subjecting LLMs to
arXiv:2608.21369v1 Announce Type: new Abstract: Nigerian Pidgin is one of Africa's most widely spoken languages, yet remains severely underrepresented in language model evaluation. Existing benchmarks primarily focus on translation, transcription, or generic sentiment analysis, leaving critical asp
arXiv:2608.21365v1 Announce Type: new Abstract: As a low-resource language, Khmer presents several retrieval challenges, including limited annotated data, ambiguous word boundaries, weak support in multilingual embedding models, and frequent mixed Khmer-English usage. This paper presents KSE-Web, a
arXiv:2608.21702v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity, optionally followed by reranking--often returns documents that share keywords with the query withou
arXiv:2608.21690v1 Announce Type: new Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations, committing to what to
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially when evaluation-aware models exhibit scheming or deception. However, if models can also control th
arXiv:2608.21614v1 Announce Type: new Abstract: Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usage. Mixture-of-Experts (MoE) models scale capacity through sparse exper
arXiv:2608.21610v1 Announce Type: new Abstract: Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, discarding the hierarchical structure of the source. We introduce Semantic Compression Trees (SCT), a h
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference solutions, or simulators with a known generative structure. Real scientific requests arrive differently. T
arXiv:2608.21449v1 Announce Type: new Abstract: Time series arise in a wide range of application domains and are analyzed using machine learning in decision-critical settings. Time series classification (TSC) is one of the most widely studied and relevant tasks. In this context, ensuring the transp
arXiv:2608.21444v1 Announce Type: new Abstract: Multi-drone systems are increasingly positioned for safety-critical missions such as search and rescue (SAR) and critical infrastructure monitoring. Yet, real-world adoption remains constrained not only by autonomy performance, but by the difficulty o
arXiv:2608.21430v1 Announce Type: new Abstract: Multimodal language models increasingly show promise for enabling the large-scale computational analysis of film, opening up new avenues for learning about film history and the evolution of narrative techniques. But the creation of stable benchmarks b
arXiv:2608.21418v1 Announce Type: new Abstract: Manufacturing knowledge graphs that integrate data from heterogeneous industrial systems face a trust deficit: consumers cannot determine whether queried data is valid, whether it was valid when a decision was made, where it originated, or how it was
arXiv:2608.21417v1 Announce Type: new Abstract: Flexible manufacturing requires industrial robots to be reprogrammed rapidly as product variants change. This paper presents a language-model-based workflow that generates, validates, and iteratively corrects ABB RAPID robot programs from natural lang
arXiv:2608.21412v1 Announce Type: new Abstract: Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degrade under these conditions, often yielding unstable or incorrect attributions. We present \textsc
arXiv:2608.21393v1 Announce Type: new Abstract: Running large language models inside enterprise environments has always bumped up against a practical wall: the data lives in one place, the AI horsepower sits somewhere else, and moving sensitive records between the two creates real headaches around
arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph stores. Exposing all tool descriptions to an LLM agent, or selecting tools only by vector similarit
arXiv:2608.21374v1 Announce Type: new Abstract: Literature reviews are essential to scientific progress, but rigorously evaluating automatically generated reviews remains difficult because many aspects of research utility depend on expert judgment rather than reference-overlap metrics. We introduce
arXiv:2608.21372v1 Announce Type: new Abstract: This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback, representation design, rule difficulty analysis, transfer learning, ge
Vision2CAD 是一项面向参数化 CAD 建模的研究工作，发表于 arXiv:2609.22688v1。论文聚焦于生成参数化 CAD 模型时所需的准确几何表达与稳定特征依赖关系。原文指出，现有方法在选择几何参考、理解草图平面的局部坐标，以及建立草图约束等方面仍面临挑战。该研究对开发能够可靠生成和编辑参数化 CAD 模型的视觉 Agent 具有参考意义。
论文提出 ConsistWorld，旨在解决多智能体世界模型中的一致性问题。自回归视频世界模型能够为单一观察者生成时间连贯的内容，但扩展到多个独立控制的智能体视角时，需要在因果流式生成条件下保持跨视角及时间间隔的一致性。该工作聚焦通过“证据路由”机制构建一致的多智能体世界模型，对多智能体仿真、具身智能和交互式视频生成具有潜在意义。
这篇 arXiv 预印本提出了 X-Beat，一个面向心电图（ECG）图像分类的可解释框架。研究聚焦于心肌梗死、心律异常等心脏疾病的自动化 ECG 解读，以支持更早期的检测。论文指出，许多高性能深度学习模型仍存在难以解释的问题，X-Beat 旨在提升模型预测结果的可理解性。对于开发者和医疗 AI 行业而言，该工作强调了在保持分类性能的同时提供可信解释的重要性。
论文指出，视觉语言模型（VLM）在视觉问答基准测试中表现强劲，但其最终决策常常与已经正确识别出的视觉证据相矛盾。作者将这类问题区分为“感知失败”与其他决策层面的失败：前者是模型未能识别相关证据。研究强调，仅以视觉问答准确率衡量模型能力并不充分，还应评估模型能否将已感知到的证据一致地转化为行动或决策。该结论对需要可靠视觉推理与自主决策的 Agent、应用开发者及评测体系设计者具有重要意义。
AdaMerge 提出了一种用于多向量视觉文档检索（VDR）的免调优图像块压缩方法。ColPali、ColNomic 等 VDR 模型通常以数百至数千个图像块级嵌入表示一份文档，因此虽然检索准确率较高，但会带来显著的存储与推理延迟成本。该工作聚焦于在无需额外调优的情况下压缩这些图像块表示，对希望降低视觉文档检索系统部署成本的开发者具有参考意义。
论文介绍了 MarsRecon，一套用于学习火星表面视觉与多模态表征的地理空间感知管线。研究背景是高分辨率轨道影像记录了丰富的火星表面信息，但可用于监督学习的地质标签较为稀缺。MarsRecon 旨在利用自监督学习与多模态数据缓解标签不足问题。该方法可能为火星遥感分析、地质特征识别及行星科学相关 AI 开发提供更通用的基础表征能力。
该研究聚焦木材回收流程中材料回收率有限的问题，尝试利用基于人工智能的降维方法加以应对。研究探索了将卷积神经网络（CNN）应用于高光谱图像处理与分类任务。论文以可解释人工智能（XAI）为题目中的关键方向，但所提供的摘要文本在“mu”处截断，未包含具体方法、实验数据或结论。该工作或可为开发者将高维高光谱数据用于木材回收材料识别提供参考。
GameReplica 是一个用于评估视觉语言 Agent 黑盒复刻视觉游戏能力的基准。论文摘要指出，传统 Coding Agent 基准通常在目标行为已通过文本、代码或演示明确指定的前提下，评估 Agent 的实现能力。该研究将评估重点转向更接近真实交互软件复刻场景的视觉观察与行为推断任务，对开发者构建具备视觉理解、界面交互和程序生成能力的 Agent 具有参考意义。所提供原文片段未包含该基准的具体任务设置、数据规模或实验结果。
该论文提出对医疗视觉语言助手进行“权威保留式评估”的思路。医疗视觉语言模型可以针对皮肤病变提出应被多紧急复查的建议，但本地医疗服务机构仍保留接受、替换或调整该建议的最终权力。相关决策还需结合转诊政策、服务容量以及本地掌握的患者背景信息。该框架强调，评估医疗 AI 时不仅应关注模型建议质量，也应衡量其与临床机构决策权和实际工作流程的协同方式。
这篇 arXiv 预印本研究如何利用生成对抗网络（GAN），从脑电图（EEG）信号中重建受试者所见的视觉刺激。论文指出，EEG 虽具有较高的时间分辨率，但头皮测量的空间分辨率有限；同时，配对的 EEG—图像数据集规模仍远小于现代生成模型通常依赖的训练语料。该研究聚焦脑机接口与神经影像解码场景，为基于非侵入式脑信号的视觉内容重建提供了探索方向。对开发者而言，相关工作也凸显了数据规模、信号空间精度与生成模型训练之间的关键限制。