研究揭示人类心理想象网络在不同人群间存在稳定结构，而大语言模型无法复现这种对齐，暴露了AI与人类认知的核心差异。
arXiv:2510.04391v5 Announce Type: replace Abstract: Mental imagery vividness is a stable individual trait, yet whether imagined scenarios share relati…
混合LLM代理实现通用指南驱动的图像聚类，突破传统方法对特定数据的依赖。
arXiv:2606.24094v1 Announce Type: new Abstract: Unifying image clustering across different clustering scenarios remains challenging due to fundamental…
新方法PROMPT2BOX揭示LLM提示词间蕴含结构，比向量聚类更精准捕捉难度差异
arXiv:2603.21438v2 Announce Type: replace Abstract: To discover the weaknesses of LLMs, researchers often embed prompts into a vector space and cluste…
通过KV缓存聚类实现长上下文LLM推理效率突破，降低显存占用同时保持精度。
arXiv:2506.11418v2 Announce Type: replace Abstract: Large language models (LLMs) with extended context windows have become increasingly prevalent for …
LLM路由技术遭遇精度瓶颈？21种方法深度研究揭示突破之道。
arXiv:2606.07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dyn…
用无监督学习揭开亨廷顿病分期之谜，模型表征与聚类分析解读疾病进展规律
arXiv:2606.07135v1 Announce Type: new Abstract: Huntington's disease (HD) is a progressive neurodegenerative disorder that affects motor, cognitive, a…
用贝叶斯层次模型结合嵌入空间聚类，从根源上修正LLM基准测试的提示敏感性，让模型评估更公平可靠。
arXiv:2510.05709v2 Announce Type: replace-cross Abstract: LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assu…
攻克多视图聚类在数据缺失、噪声等不完美信息下的鲁棒性难题，提供理论保障与算法方案。
arXiv:2606.04343v1 Announce Type: new Abstract: Real-world multi-view data always suffer from imperfect information problem, where the view-specific o…
LLM可靠性新突破：聚类自评估方法简单有效，无需额外训练即可量化不确定性，ACL 2026研究成果。
arXiv:2606.03846v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate remarkable performance across diverse tasks, but they often…
将5000家YC初创公司聚类成2D地图，快速发现行业分布与相似企业。
Hi! This is embedding each company into 2 dimensions based on its details, so companies doing similar things land near each other. A map is then deriv…
多智能体协作的文本聚类新范式，让分类更可控且精准。
arXiv:2606.01255v1 Announce Type: new Abstract: Recent text-clustering methods use large language models to propose a cluster taxonomy from a corpus a…
用LLM辅助聚类发现新意图，论文提出NILC方法，提升聚类准确性与可解释性。
arXiv:2511.05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user…
从问题原型中聚类蒸馏出可泛化的优化技能，让算法学会举一反三，大幅提升求解效率。
arXiv:2605.29829v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems fro…
ICML 2026 接收论文，将 k-means 聚类重新诠释为链式思维推理，为图学习提供全新数学视角。
arXiv:2605.24867v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large la…
评估大语言模型在描述文献计量聚类时对结构化提示的实际需求程度，揭示不同结构水平对生成质量的影响。
arXiv:2605.24351v1 Announce Type: new Abstract: Large language models (LLMs) can support scientific literature synthesis, but remain prone to hallucin…
ICML 2026观点文章：LLM不确定性量化本质是无监督聚类，颠覆传统认知。
arXiv:2605.19220v1 Announce Type: cross Abstract: Uncertainty Quantification (UQ) is widely regarded as the primary safeguard for deploying Large Lang…
通过证据校准的查询聚类精准捕捉大模型能力边界，为LLM评估提供全新方法论。
arXiv:2605.17110v1 Announce Type: cross Abstract: Query clustering organizes queries into groups that reflect shared latent capability demands, enabli…
电商搜索新范式，生成式检索结合语义聚类ID与专家引导强化学习，实现端到端高效检索
arXiv:2605.14434v1 Announce Type: cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval…
开源工具Big Indexer通过行为聚类而非导入关系索引代码，旨在提升大型代码库中AI代理的响应准确率与速度，欢迎试用反馈。
Static Architectural analysis for large codebases, Big Indexer do behavioral code clustering for the purpose of more accurate/faster agentic tools res…