新基准Artifact-Bench，专门评估多模态大模型识别AI视频伪影的能力，揭示模型真实短板。
arXiv:2605.18984v1 Announce Type: new Abstract: Recent video generative models have greatly improved the realism of AI-generated videos, yet their out…
重新思考高分辨率多模态大模型中的Zoom-IN方法，提出Hierarchical Decoupling框架，显著提升视觉理解性能。
arXiv:2510.00054v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tas…
深入探讨LLM在定性研究中的机会、局限与实践考量，为学术研究者提供宝贵参考。
arXiv:2605.16538v1 Announce Type: cross Abstract: This paper examines the opportunities, limitations, and practical considerations associated with the…
百万级临床笔记重写质量系统性评估，揭示LLM文本生成多维评价短板
arXiv:2605.17775v1 Announce Type: new Abstract: Large language models (LLMs) can generate or synthesize clinical text for a wide range of applications…
LLM能否生成考虑性别的多模态行为来校准用户对社交代理的信任？这篇研究切入了一个关键的人机交互问题。
arXiv:2605.19798v1 Announce Type: new Abstract: As Socially Interactive Agents (SIAs) become increasingly integrated into daily life, the ability to c…
新型扩散语言模型并行解码方法DMax，通过自精炼机制减少误差累积，实现高并行度高质量生成。
arXiv:2604.08302v3 Announce Type: replace-cross Abstract: We present DMax, a new paradigm for efficient diffusion language models (dLLMs). It mitigate…
巴西摇滚乐队竟完美实现llms.txt标准，跨界案例彰显AI文档规范的普适价值
How a Brazilian Rock Band Implemented llms.txt (And Why It Makes Sense) Most llms.txt implementations you'll find are SaaS products, developer tools, …
无需庞大AI团队，利用现有LLM即可快速为应用增添语义搜索、个性化推荐等7大AI功能，大幅提升用户体验与商业价值。
Imagine a customer finding the perfect item on your website in seconds—not because they know the jargon to search, but because your search bar underst…
把AI指令直接写进HTML响应里，比任何外部文档都更直接——Vercel提出的<script type="text/llms.txt">提案，让AI代理访问受保护页面时不再一头雾水。
How do you tell an AI agent what it needs to do when it hits a protected page? Most systems rely on external documentation or pre-configured knowledge…
LLM的溯因推理一直是短板，Graph of States用因果图+状态机构建结构化信念状态，把无头苍蝇式的探索变成定向搜索，一举解决证据虚构、上下文漂移等四大痛点。
arXiv:2603.21250v2 Announce Type: replace Abstract: Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language M…