AI 论文与研究

OpenAI 发布一批由内部前沿模型产出的新数学成果，成果以 GitHub 仓库形式公开，并附论文修订与引用协议，其中许多证明已用 Lean 形式化以便计算机验证。

Google 与 MIT 发布报告，介绍智能体平台 Coco，供 TPU 架构师用于硬件与模型协同设计。Coco 将每次仿真扫描登记进规范化关系数据库，智能体报告的每个数字都来自 SQL 查询，并可自主组合类型化工具、执行对比分析。近期目标是将架构师搭建仿真与获取洞察的时间减半。

Alan Kay 在 1993 年 HOPL-II 论文中回顾了 Smalltalk 从 1960 年代到 1980 年代的早期发展史。

OpenAI 发布由内部前沿模型产出的一批新数学结果，链接为 https://github.com/openai/math。发布前咨询了普林斯顿高等研究院（IAS）数学与人工智能独立顾问组，并依据其建议和公开建议决定发布方式。

AutomationBench Verified 发布，对 Zapier AutomationBench 全部 600 个公开任务的评分器逐一审计，Agent 标记 323 个可疑项，人工确认 206 个真实 bug 并全部修复。

Stanford 论文《Worse Together》研究多用户多智能体场景，覆盖 5 个前沿模型、77 个场景和 4 个环境，发现每用户一个智能体的团队在共享资源上表现差于单个服务所有人的协调智能体。

目标是让研究人员和公共卫生官员能够补充现有健康信息、弥合报告缺口，并主动应对健康挑战。 了解我们最新研究的更多内容 ↓ https://goo.gle/3TLTX73

Google Earth AI 可用于更快、更主动地应对公共卫生危机。新研究显示，将行为趋势、地理空间 AI 模型等洞察结合后，公共卫生团队能更好理解复杂公共卫生问题、弥合报告缺口，并把应急响应从被动管理转向主动预防。传统疫情传播预测通常需要数周拼接卫星影像、人口普查表和地方卫生记录。

林肯实验室超级计算中心（LLSC）的 Lincoln AI Computing Survey（LAICS）系列调查已从首篇覆盖 57 款 AI 加速器扩展到最新一篇的 120 多款，持续对比各款商用加速器的峰值性能与峰值功耗。

@friendliai @anacondainc @kilocode @novita_labs @ArtificialAnlys @NousResearch @radixark @vercel 在此查看我们的活动：https://luma.com/MiniMax

Parsewave 发布 AutomationBench Verified，对 Zapier AutomationBench 全部 600 个公开任务的验证器进行审计。

OmniReasoning 突破音视频联合推理的极限 论文：https://huggingface.co/papers/2609.39490

ALoDLM 自适应循环扩散语言模型 论文：https://huggingface.co/papers/2610.04198

Flow policies have become a standard policy class for learning robot behaviors from demonstrations, but reinforcement learning is still critical for improving pre-trained flow policies or learning them from scratch through interaction. We …

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 …

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…

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…

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…

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…

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…

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…

进步之路可能蜿蜒曲折。 Jennifer Neville 讲述了她在研究中原地打转的经历、走上多轮转折才进入计算机科学的路径，以及用更实用的评估推动当今 AI 系统。 收听最新一期 Microsoft Research Podcast 节目：https://msft.it/6183aW0lD

Databricks 发布 2026 基准测试与客户案例，论证湖仓（Lakehouse）在 SQL 性能上已追平数据仓库：其生产 SQL 工作负载较 2022 年基线快 77%，Performance Index 约提升 4 倍。

研究者提出 Harness-Aware Distillation，一种面向带 harness 部署的小语言模型智能体的蒸馏框架：用同一教师模型分别在有无 harness 信息下推理，训练学生模型偏好带 harness 时的动作，并用过滤器剔除与 harness 记录矛盾的样本，全程无需任务奖励或成功标签。

Microsoft 合伙人研究经理 Jennifer Neville 在 Microsoft Research Podcast 中讨论了评测如何推动 AI 系统突破传统 benchmark 的性能边界，以及模型在超出常规测试时出现的"意外失败"。她结合自身从数学、物理、认知科学到计算机科学的经历，分享了使用当前 AI 系统的实用建议，并强调当结果偏离预期时深入检查数据的重要性。

Stanford HAI 报道 Karunakaran 等人对律所、广告公司和 IT 服务公司的 AI 部署研究，发现把 AI 介绍为生产力工具时员工不愿使用，介绍为工作丰富化手段时使用意愿明显提升。在一家律所的对照观察中，以丰富工作为目标引入 AI 工具 LawBot 的部门，使用量比强调提效的部门高 58%，尝试新用法多 70%。研究还强调配套培训、探索时间和调整考核指标的重要性。