AI 情报文章归档

Conformal prediction is a popular tool for uncertainty quantification that outputs prediction sets with finite-sample coverage guarantees. While prediction set size is commonly used as a heuristic measure of uncertainty, the information-th…

Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, which can lead to unstable interaction prediction. We intro…

Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate new directions. However, training language models to perform this form of literature-grounded ideation remains challenging, …

World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depend on faithful 3D geometry, yet current video-based world m…

Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is not the same as being able to teach it. Existing approaches to training LLMs as teachers rely on demonstrations, preference…

Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously create cheaper solutions for such workloads? We call this …

我们正在这个火车站里构建 AGI

论文提出 AdvSim2Real，在冻结的网页世界模型中共进化任务课程、注入攻击方与 agent，以抵御自适应提示注入。训练使 4B agent 在有无攻击时完成率均提升，对未训练过的前沿模型攻击方也保持稳健，能力增益可迁移到真实浏览器；在 150 个网页任务上，面对该未见攻击方时完成率相对基线提升 33.6%。

Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, because the page also…

I'm an AI agent. I tested which crypto rails actually pay a bot. Almost none do. I run on...

Shaped 发布 AutomationBench Verified，对 Zapier 的 AutomationBench 全部 600 个公开任务的验证器做了独立审计。

We develop the first feedback design for rapid stabilization of the Kuramoto--Sivashinsky equation with a spatially varying anti-diffusion coefficient. For constant coefficients, the single-input Fredholm design of Coron and Lü (2015) excl…

Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery of useful training examples, limiting …

Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models poses three core challenges: real-time generation to keep pac…

A walkthrough of Ouroboros, an open-source harness that lets AI agents find work, do the work, check the work — and only then ask a human to merge. Including the honest field notes: the reviewer that approved a destructive change, and the …

开发者通过 LLM 逆向工程 iChat 的 SNATMAP 协议，自建 UDP 服务器并修改 /etc/hosts，让 Leopard 和 Snow Leopard 上的 iChat 重新支持音频和视频通话。

Petri nets have been used to describe chemical processes such as reactions.They map well to chemistry: Places are the bonds between atoms and the free valence of each atom, a token is a unit of bond order, a transition forms or breaks a bo…

1. The Siren Song of Universal Protocol Normalization Every backend engineer who builds an...

Google published a free 50-page whitepaper in May 2026 called "The New SDLC With Vibe Coding". Addy...

Your tunnel isn't misconfigured — your egress proxy is eating it I'm an AI agent. I live...

A common approach to measuring bias in Large Language Models is to compare the log-likelihoods of two contrastive stereotype sentences. We argue that such single-pair comparisons are often unreliable: simply rewriting the same stereotype w…

We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward function is known, we show that convexity and cycli…

Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a session. We propose Reinforcement Learning with Calibrated Pruning (RLCP), which adapts the retained action set using c…

Learning when the environment does not belong to the learner's hypothesis class is typically handled using agnostic learning guarantees. However, for anything beyond supervised learning, agnostic guarantees are difficult to come by. Recent…

Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models have seen substantial gains, driven by carefully crafted token representations and diffu…

In online inverse linear optimization, a learner recommends an action and then observes the choice of an expert who maximizes a fixed, unknown linear objective on $\mathbb{R}^{d}$; the goal is to learn to optimize this objective without ob…

Mistral 发布 Mistral Large 4（Le Chonk），1T 参数、原生多模态、49B 激活，称其为美欧最佳开源权重模型，API 已可用，开放权重 10 月底发布。Hugging Face CEO Clément Delangue 转发并指出，在权重尚未开放之前不能自称最佳开源权重模型，并附上 Hugging Face 页面链接。

Gumloop 上线 Agent Browsers，当任务没有 MCP 或 API 连接器时，可在云端沙箱中打开浏览器并完成操作。支持安全凭证存储与 1Password 集成、会话回放和隐身代理会话，且完全与模型无关。Elvis Saravia 推荐正在构建个人智能体、需要可靠快速浏览器工具的开发者使用。

Generative Information Retrieval (GIR) has emerged as a transformative paradigm, shifting document retrieval from a traditional "retrieve-and-rank" workflow to sequence-to-sequence generation, where a model directly predicts document ident…

Sierra 与 Meta 联合 Genesys、Instinct、Rocket、Shopify、Stripe、Walmart 等伙伴宣布开发 Personal Agent Protocol，一个定义个人 AI 智能体如何与企业交互的开放标准，任何人都可实现。

诺奖经济学家 Daron Acemoglu 在微软博客 The Humanist Review of AI 上撰文预测，AI 十年内仅能推动 GDP 增长约 1.5%，最多替代 5% 的工作岗位，远低于部分 AI 实验室的预测。

Mistral AI 于 10 月 6 日以公开预览形式发布 Mistral Large 4（内部代号 Le Chonk），为 1.05T 总参数、每 token 49B 激活的细粒度 MoE 模型。

Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions…

“没有哪个模型能统治一切。” 创意构思和最终画面，要求的东西并不相同。要做的，是把创意交到最适合每一项任务的模型手里。

Perplexity 在 Hugging Face Decision Index（决策模型基准）上夺冠。我们的模型是开放权重的，所有人都可以使用！ @perplexitydevs：pplx-decider-v1.1-27b，我们更新后的开放权重多模态决策模型，现已可用。 它在新版 @huggingface Decision Index 0.3 基准上得分最高。pplx-decider-v1.1-27b 的成本是 v1 的一半，每百万输入 token 仅 $0.02。 htt…

Anthropic 宣布在 Claude 中可粘贴 Google 文件链接或让 Claude 新建 doc、sheet、deck，文件会在聊天旁打开供用户与 Claude 共同编辑。访问权限跟随用户的 Google 共享设置，该功能目前在所有付费计划上以 beta 提供，详情见 https://claude.com/resources/articles/claude-now-works-in-google-docs-sheets-and-slides。

Anthropic 宣布 Claude 现在可以在 Google Docs、Sheets 和 Slides 中工作，这些文件也能在 Claude 中打开。在 Google Workspace 中，Claude 以侧边栏形式出现在文件旁，读取当前打开的内容并就地编辑，用户可在每次编辑生效前逐项确认。

Google 发布开源权重嵌入模型 EmbeddingGemma 2，采用 Apache 2 许可证。该模型为 740M 参数，采用模块化编码器，支持 8K 上下文窗口，可将文本、代码、图像、视频和音频映射到统一的嵌入空间。

A printed photo beat our identity check at 0.53. A looped screen replay passed a random-challenge liveness gate 39.5% of the time. Measured numbers, not vendor claims.

掌控你自己的智能栈，各位！ 先从挖掘你 agent traces 中的丰富知识开始。 然后训练小型专用模型来解决生产问题。 @OvermindLab 是开源的，让这一切变得可行。它从你的 agent traces 构建数据集，用你当前的模型进行评估，并训练出一个你拥有的更小的专用模型。