AI 论文与研究

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。

Meta AI 提出 MIRA，将长周期研究智能体拆成外层 meta-reasoner 与执行器：前者读取持久研究记录并生成下一项调查的工作单，后者负责执行，决策只发生在工作单边界。

用 Jev-as-a-Judge 提升智能体评估的可靠性。 https://x.com/omarsar0/status/2107472222398886011?s=20

上海人工智能实验室推出 SpatialASM 框架，通过两阶段训练将主动空间心理化（ASM）内化进 LVLM，使其能主动规划视角并想象对应观测。该框架包含 Allocentric Novel-View Generator、ASM 轨迹合成与视角想象强化学习三部分，在 Qwen3-VL 和 Qwen3.5 四个骨干模型上完成训练。

Meta 论文《RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models》（arxiv.org/abs/2609.39551）发现，让 2 个不同编码智能体互相审查补丁，比给单个智能体更大预算更能发现静默缺陷。

PhAI Labs 联合 Stanford、Oxford 和 Princeton 的团队发布 JEPA-Anything，将 Yann LeCun 提出的 JEPA 架构扩展为可覆盖物理、机器人、天气、生物等七个领域的统一世界模型，方法是把预测状态拆成四个正交因子分别预测再重组。

Google 新论文提出 AIM 方法，让研究智能体维护按主题排序的想法地图，并核查代码与想法是否匹配，避免代码偏离想法时学到错误经验。AIM 在两组任务上分别比此前最佳智能体 ScientistOne 高出 1.6 和 4.9 分，并以最高 3.1 倍的速度追平其最佳成绩。该方法在可能方案多、优质方案少的任务上收益最大。

Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting …

Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. However, real-world legal deployment exhibits substantial case heterogeneity in facts, evide…

Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-characterized. Existing benchmarks rarely address the hundreds of millions of rows and high-c…

Achieving compositional concept generalization (CoCoGen), the ability to understand novel situations by recombining learned primitives, remains a fundamental challenge in artificial intelligence. Compositional semantic models such as Compo…

Cooperation with unfamiliar partners requires adapting to communication conventions that are not known in advance. We study this problem in a controlled Hanabi-derived environment with scripted hint generation, LLM-controlled receiving dec…

Product Identification has sprung up to become one of the most challenging problems in the automation of the retail industry. With the new industry 5.0 standards, automated inventory management, and catalog creation tasks are vitally impor…

Full-duplex spoken dialogue models listen and speak at the same time, enabling voice agents to have natural, low-latency interactions that turn-based systems cannot offer. However, they are commonly evaluated against single-sided interlocu…

End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain difficult to adapt to deployment-time safety constraints. We propose a query-based cost-learni…