毫米波技术赋能人体测量，非接触高精度成像新方案，arXiv最新研究突破。
arXiv:2605.23064v1 Announce Type: cross Abstract: Body shape and circumferences are clinically informative biomarkers for risk stratification, includi…
无需训练即可编排多模态大模型，实现零样本协调多种能力，降低落地门槛
arXiv:2508.10016v4 Announce Type: replace Abstract: Building interactive omni-modal assistants often relies on end-to-end multimodal alignment to fuse…
大型语言模型的说服性和叙事性解释如何影响人类决策？这篇最新研究揭示答案。
arXiv:2605.23867v1 Announce Type: cross Abstract: Large language models (LLMs) have the potential to aid and improve human decision-making in classifi…
知识工作的设计与报告基准，为AI系统在真实办公场景中的表现提供量化评估新维度。
arXiv:2605.23262v1 Announce Type: new Abstract: The development of LLM agents has led to a growing body of work on knowledge-work AI, including coding…
获得了国际机器人研究共同体的高度认可
从研究论文看GitHub上的开发者行为，揭示面试中难以言说的真实一面
When I started working on my usability study project with KServe, I interacted with KServe users to understand the challenges they were experiencing w…
突破传统统一学习率，重尾分布指导LLM逐层自适应学习，大幅提升训练效率与模型性能。
arXiv:2605.22297v1 Announce Type: cross Abstract: Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice…
揭示大模型可能产生欺骗性推理链，对AI安全研究提出重要警示。
arXiv:2510.00319v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been demonstrating strong reasoning capability with their …
最新arXiv论文揭秘思维链如何一步步拆解复杂任务，深入剖析其内在分解机制。
arXiv:2604.08872v2 Announce Type: replace Abstract: Many language tasks can be modeled as classification problems where a large language model (LLM) i…
通过选择性几何控制，提升大模型安全对齐的鲁棒性，为AI防御攻击提供新思路。
arXiv:2602.07340v2 Announce Type: replace Abstract: Safety alignment of large language models remains brittle under domain shift and noisy preference …
无需引文数据库，让大模型“记住”你论文的影响力，这篇论文开创性地用LLM内在记忆衡量研究冲击力。
arXiv:2605.22176v1 Announce Type: new Abstract: Citation counts remain the dominant metric for assessing research impact, yet they suffer from well-do…
再看自主LLM智能体在CTF挑战中的表现，更新发现与能力边界。
arXiv:2605.21497v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, wi…
视频生成新范式，VChain用视觉思维链提升推理能力，获ICCV 2025 Workshop最佳论文奖，值得关注。
arXiv:2510.05094v2 Announce Type: replace Abstract: Recent video generation models can produce smooth and visually appealing clips, but they often str…
最新研究揭示数据时间顺序对LLM预训练的深刻影响，理解时序偏差是关键
arXiv:2605.22769v1 Announce Type: new Abstract: Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledg…
提出Agentic CLEAR框架，自动化评估LLM Agents多层次能力，提升评估效率与客观性。
arXiv:2605.22608v1 Announce Type: new Abstract: Agentic systems are becoming more capable: agents define strategies, take actions, and interact with d…
跳出传统图思维，用超图语言表达复杂关系，LLM建模迎来新范式。
arXiv:2605.21858v1 Announce Type: new Abstract: Large language models (LLMs) have recently shown strong potential in modeling relational structures. H…
论文提出ACC方法，编译智能体轨迹以高效进行长上下文训练，为AI大模型的长文本处理提供新思路。
arXiv:2605.21850v1 Announce Type: new Abstract: Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, …
颠覆常规认知！LLM的“锯齿状”缺陷竟能激发科学创造力，揭示AI与人类创新新路径。
arXiv:2605.10574v2 Announce Type: replace Abstract: As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds…
一种全新训练范式，通过反馈条件优化让LLM在所有训练阶段都获得更好的缩放能力，可能颠覆大模型训练方式。
arXiv:2605.20285v1 Announce Type: new Abstract: We tackle the question of how to scale more efficiently across the many, ever-growing stages of curren…
顶级会议ICML 2026收录，揭秘构建强视觉-语言-动作（VLA）模型的实用配方与技巧。
arXiv:2602.18532v2 Announce Type: replace Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, lever…