跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 10:37 — 2026-11-22 10:37(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

论文修订列表

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 8,992 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
版本更新 · v2arXiv:2509.07968Google Research

SimpleQA Verified: A Reliable Factuality Benchmark to Measure Parametric Knowledge

Lukas Haas, Gal Yona, Giovanni D'Antonio, Sasha Goldshtein, Dipanjan Das

原文摘要

We introduce SimpleQA Verified, a 1,000-prompt benchmark for evaluating Large Language Model (LLM) short-form factuality based on OpenAI's SimpleQA. It addresses critical limitations in OpenAI's benchmark, including noisy and incorrect labels, topical biases, and question redundancy. SimpleQA Verified was created through a rigorous multi-stage filtering process involving de-duplication, topic balancing, and source reconciliation to produce a more reliable and challenging evaluation set, alongside improvements in the autorater prompt. On this new benchmark, Gemini 2.5 Pro achieves a state-of-the-art F1-score of 55.6, outperforming other frontier models, including GPT-5. This work provides the research community with a higher-fidelity tool to track genuine progress in parametric model factuality and to mitigate hallucinations. The benchmark dataset, evaluation code, and leaderboard are available at: https://www.kaggle.com/benchmarks/deepmind/simpleqa-verified.

cs.CL

版本更新 · v7arXiv:2509.18057Google DeepMind

Reinforced Generation of Combinatorial Structures: Hardness of Approximation

Ansh Nagda, Prabhakar Raghavan, Abhradeep Thakurta

原文摘要

Can AI based methods help us make advances in complexity theory? We provide evidence towards answering this in the affirmative, using AlphaEvolve (an LLM code mutation agent) to obtain new results in three settings: a) We improve a recent result of Kunisky and Yu to obtain near-optimal upper and (conditional) lower bounds on certification algorithms for MAX-CUT and MAX-Independent Set on random 3- and 4-regular graphs. Our improved lower bounds are obtained by constructing nearly extremal Ramanujan graphs on as many as $163$ vertices, and our upper bounds are obtained via analytical arguments. b) We obtain new inapproximability results for MAX-4-CUT and MAX-3-CUT, proving that it is NP-hard to approximate them within factors of $0.987$ and $0.9649$ respectively, using AlphaEvolve to discover new gadget reductions. Our MAX-4-CUT result improves upon the SOTA of $0.9883$, and our MAX-3-CUT result improves on the current best gadget-based inapproximability result of $0.9853$, but falls short of the SOTA of $16/17$ that relies on a custom PCP (rather than a reduction from ``standard'' Håstad-style PCPs). c) Inapproximability for the metric Traveling Salesman Problem (TSP): We show that it is NP-hard to approximate the minimum cost tour within a factor of $111/110$ using AlphaEvolve to discover a new gadget, thus improving the SOTA of $117/116$. Along the way, we provide new modular soundness and completeness arguments that can be of independent interest. A key technical challenge we faced: verifying a candidate construction produced by AlphaEvolve is costly (sometimes requiring time exponential in the size of the construction). We used AlphaEvolve itself to evolve the verification procedure to be faster (sometimes by $10,000\times$ for our gadgets). Our results suggest that gadget based proofs would benefit from a pass through AI-based tools to obtain stronger results.

cs.LG · cs.AI · cs.CC · math.CO

版本更新 · v3arXiv:2602.03837Google DeepMindGoogle Research

Accelerating Scientific Research with Gemini: Case Studies and Common Techniques

David P. Woodruff, Vincent Cohen-Addad, Lalit Jain, Jieming Mao, Song Zuo, MohammadHossein Bateni, Simina Branzei, Michael P. Brenner 等 36 位作者

原文摘要

Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to contribute to novel, expert-level mathematical discovery is less understood. We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models, specifically Google's Gemini-based models (in particular Gemini Deep Think and its advanced variants), to solve open problems, refute conjectures, and generate new proofs across diverse areas in theoretical computer science, as well as other areas such as economics, optimization, and physics. Based on these experiences, we extract common techniques for effective human-AI collaboration in theoretical research, such as iterative refinement, problem decomposition, and cross-disciplinary knowledge transfer. While the majority of our results stem from this interactive, conversational methodology, we also highlight specific instances that push beyond standard chat interfaces. These include deploying the model as a rigorous adversarial reviewer to detect subtle flaws in existing proofs, and embedding it within a "neuro-symbolic" loop that autonomously writes and executes code to verify complex derivations. Together, these examples highlight the potential of AI not just as a tool for automation, but as a versatile, genuine partner in the creative process of scientific discovery.

cs.CL · cs.AI

版本更新 · v3arXiv:2602.10177Google DeepMind

Towards Autonomous Mathematics Research

Tony Feng, Trieu H. Trinh, Garrett Bingham, Dawsen Hwang, Yuri Chervonyi, Junehyuk Jung, Joonkyung Lee, Carlo Pagano 等 28 位作者

原文摘要

Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing long-horizon proofs. In this work, we introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language. Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research. We demonstrate the capability of Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research: (a) a research paper (Feng26) generated by AI without any human intervention in calculating certain structure constants in arithmetic geometry called eigenweights; (b) a research paper (LeeSeo26) demonstrating human-AI collaboration in proving bounds on systems of interacting particles called independent sets; and (c) an extensive semi-autonomous evaluation (Feng et al., 2026a) of 700 open problems on Bloom's Erdos Conjectures database, including autonomous solutions to four open questions. In order to help the public better understand the developments pertaining to AI and mathematics, we suggest quantifying standard levels of autonomy and novelty of AI-assisted results, as well as propose a novel concept of human-AI interaction cards for transparency. We conclude with reflections on human-AI collaboration in mathematics and share all prompts as well as model outputs at https://github.com/google-deepmind/superhuman/tree/main/aletheia.

cs.LG · cs.AI · cs.CL · cs.CY

版本更新 · v3arXiv:2506.04761Berkeley BAIR

对数线性注意力

Log-Linear Attention

Han Guo, Songlin Yang, Tarushii Goel, Eric P. Xing, Tri Dao, Yoon Kim

AI 速读 基于摘要

提出对数线性注意力,用对数增长的多隐藏状态替代固定大小隐藏状态,在保持矩阵乘法并行性的同时兼顾线性注意力效率与softmax注意力表达力。

cs.LG

查看原文摘要

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space models enable linear-time, constant-memory sequence modeling and can moreover be trained efficiently through matmul-rich parallelization across sequence length. However, at their core these models are still RNNs, and thus their use of a fixed-size hidden state to model the context is a fundamental limitation. This paper develops log-linear attention, an attention mechanism that balances linear attention's efficiency and the expressiveness of softmax attention. Log-linear attention replaces the fixed-size hidden state with a logarithmically growing set of hidden states. We show that with a particular growth function, log-linear attention admits a similarly matmul-rich parallel form whose compute cost is log-linear in sequence length. Log-linear attention is a general framework and can be applied on top of existing linear attention variants. As case studies, we instantiate log-linear variants of two recent architectures -- Mamba-2 and Gated DeltaNet -- and find they perform well compared to their linear-time variants.

版本更新 · v2arXiv:2602.19128Berkeley BAIR

K-Search:通过协同进化内在世界模型进行LLM内核生成

K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model

Shiyi Cao, Ziming Mao, Joseph E. Gonzalez, Ion Stoica

AI 速读 基于摘要

用协同进化的世界模型替代静态启发式搜索,让LLM显式规划GPU内核的多步结构优化。

cs.AI

查看原文摘要

Optimizing GPU kernels is critical for efficient modern machine learning systems yet remains challenging due to the complex interplay of design factors and rapid hardware evolution. Existing automated approaches typically treat Large Language Models (LLMs) merely as stochastic code generators within heuristic-guided evolutionary loops. These methods often struggle with complex kernels requiring coordinated, multi-step structural transformations, as they lack explicit planning capabilities and frequently discard promising strategies due to inefficient or incorrect intermediate implementations. To address this, we propose Search via Co-Evolving World Model and build K-Search based on this method. By replacing static search heuristics with a co-evolving world model, our framework leverages LLMs' prior domain knowledge to guide the search, actively exploring the optimization space. This approach explicitly decouples high-level algorithmic planning from low-level program instantiation, enabling the system to navigate non-monotonic optimization paths while remaining resilient to temporary implementation defects. We evaluate K-Search on diverse, complex kernels from FlashInfer, including GQA, MLA, and MoE kernels. Our results show that K-Search significantly outperforms state-of-the-art evolutionary search methods, achieving an average 2.10x improvement and up to a 14.3x gain on complex MoE kernels. On the GPUMode TriMul task, K-Search achieves state-of-the-art performance on H100, reaching 1030us and surpassing both prior evolution and human-designed solutions.

版本更新 · v2arXiv:2510.22037Google Research

ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality

Shayne Longpre, Sneha Kudugunta, Niklas Muennighoff, I-Hung Hsu, Isaac Caswell, Alex Pentland, Sercan Arik, Chen-Yu Lee 等 9 位作者

原文摘要

Scaling laws research has focused overwhelmingly on English -- yet the most prominent AI models explicitly serve billions of international users. In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model parameters, 400+ training languages and 48 evaluation languages. We introduce the Adaptive Transfer Scaling Law (ATLAS) for both monolingual and multilingual pretraining, which outperforms existing scaling laws' out-of-sample generalization often by more than 0.3 R^2. Our analyses of the experiments shed light on multilingual learning dynamics, transfer properties between languages, and the curse of multilinguality. First, we derive a cross-lingual transfer matrix, empirically measuring mutual benefit scores between 38 x 38=1444 language pairs. Second, we derive a language-agnostic scaling law that reveals how to optimally scale model size and data when adding languages without sacrificing performance. Third, we identify the computational crossover points for when to pretrain from scratch versus finetune from multilingual checkpoints. We hope these findings provide the scientific foundation for democratizing scaling laws across languages, and enable practitioners to efficiently scale models -- beyond English-first AI.

cs.CL · cs.LG

版本更新 · v2arXiv:2510.22512Berkeley BAIR

传递强化学习:通过分治法进行价值学习

Transitive RL: Value Learning via Divide and Conquer

Seohong Park, Aditya Oberai, Pranav Atreya, Sergey Levine

AI 速读 基于摘要

提出 TRL,将目标条件强化学习中的三角不等式结构转化为分治式价值更新规则,用于离线 GCRL 的价值学习。

cs.LG · cs.AI

查看原文摘要

In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. TRL is designed for offline goal-conditioned reinforcement learning (GCRL) problems, where the aim is to find a policy that can reach any state from any other state in the smallest number of steps. TRL converts a triangle inequality structure present in GCRL into a practical divide-and-conquer value update rule. This has several advantages compared to alternative value learning paradigms. Compared to temporal difference (TD) methods, TRL suffers less from bias accumulation, as in principle it only requires $O(\log T)$ recursions (as opposed to $O(T)$ in TD learning) to handle a length-$T$ trajectory. Unlike Monte Carlo methods, TRL suffers less from high variance as it performs dynamic programming. Experimentally, we show that TRL achieves the best performance in highly challenging, long-horizon benchmark tasks compared to previous offline GCRL algorithms.

版本更新 · v4arXiv:2502.02880Google Research

教练而非拐杖:证据表明AI虽减少努力却能提升写作技能

Coach not crutch: Evidence that AI can improve writing skill despite reducing effort

Benjamin Lira, Todd Rogers, Daniel G. Goldstein, Lyle Ungar, Angela L. Duckworth

AI 速读 基于摘要

多项预注册实验表明,使用AI写作工具虽降低练习时的努力程度,却能通过“示例教学”提升无AI写作测试中的表现。

cs.HC

查看原文摘要

In a series of highly-powered empirical studies, we examine the intuition that by sparing effort, using AI inevitably hinders learning. First, in a nationally representative survey of young adults, the majority expressed the view that using AI makes people lazier and less capable. Next, in a random-assignment experiment, we gave participants a tutorial on best practices in professional writing, then provided one group with access to an AI writing tool and asked another to practice writing on their own. Those who practiced with AI indeed exerted less effort while practicing -- yet wrote better cover letters in no-AI writing tests. In a second experiment with more rigorous control conditions, access to AI improved writing more than either googling cover letter examples and tips or receiving personalized feedback on their practice letters from experienced human editors. A third experiment explained these learning gains by showing that AI can teach by example: participants who viewed a cover letter that had been revised by the AI tool but did no further practice improved their writing as much as those who practiced writing with the original AI tool. Collectively, these pre-registered experiments suggest that AI can exert opposing effects on effort and learning rate -- making it possible in at least some cases to work less and learn more.

版本更新 · v4arXiv:2510.18318Google DeepMindGoogle Research

Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning

Aaron Bell, Amit Aides, Amr Helmy, Arbaaz Muslim, Aviad Barzilai, Aviv Slobodkin, Bolous Jaber, David Schottlander 等 60 位作者

原文摘要

Geospatial data offers immense potential for understanding our planet. However, the sheer volume and diversity of this data along with its varied resolutions, timescales, and sparsity pose significant challenges for thorough analysis and interpretation. This paper introduces Earth AI, a family of geospatial AI models and agentic reasoning that enables significant advances in our ability to unlock novel and profound insights into our planet. This approach is built upon foundation models across three key domains--Planet-scale Imagery, Population, and Environment--and an intelligent Gemini-powered reasoning engine. We present rigorous benchmarks showcasing the power and novel capabilities of our foundation models and validate that when used together, they provide complementary value for geospatial inference and their synergies unlock superior predictive capabilities. To handle complex, multi-step queries, we developed a Gemini-powered agent that jointly reasons over our multiple foundation models along with large geospatial data sources and tools. On a new benchmark of real-world crisis scenarios, our agent demonstrates the ability to deliver critical and timely insights, effectively bridging the gap between raw geospatial data and actionable understanding.

cs.AI

版本更新 · v2arXiv:2602.13521Berkeley BAIR

为数据智能体装备部落知识

Arming Data Agents with Tribal Knowledge

Shubham Agarwal, Asim Biswal, Sepanta Zeighami, Alvin Cheung, Joseph Gonzalez, Aditya G. Parameswaran

AI 速读 基于摘要

Tk-Boost 通过从智能体自身错误中积累并检索“部落知识”,在生成 SQL 时纠正其对数据库的误解,从而提升 NL2SQL 准确率。

cs.DB · cs.AI

查看原文摘要

Natural language to SQL (NL2SQL) translation enables non-expert users to query relational databases through natural language. Recently, NL2SQL agents, powered by the reasoning capabilities of Large Language Models (LLMs), have significantly advanced NL2SQL translation. Nonetheless, NL2SQL agents still make mistakes when faced with large-scale real-world databases because they lack knowledge of how to correctly leverage the underlying data (e.g., knowledge about the intent of each column) and form misconceptions about the data when querying it, leading to errors. Prior work has studied generating facts about the database to provide more context to NL2SQL agents, but such approaches simply restate database contents without addressing the agent's misconceptions. In this paper, we propose Tk-Boost, a bolt-on framework for augmenting any NL2SQL agent with tribal knowledge: knowledge that corrects the agent's misconceptions in querying the database accumulated through experience using the database. To accumulate experience, Tk-Boost first asks the NL2SQL agent to answer a few queries on the database, identifies the agent's misconceptions by analyzing its mistakes on the database, and generates tribal knowledge to address them. To enable accurate retrieval, Tk-Boost indexes this knowledge with applicability conditions that specify the query features for which the knowledge is useful. When answering new queries, Tk-Boost uses this knowledge to provide feedback to the NL2SQL agent, resolving the agent's misconceptions during SQL generation, and thus improving the agent's accuracy. Extensive experiments across the BIRD and Spider 2.0 benchmarks with various NL2SQL agents shows Tk-Boost improves NL2SQL agents accuracy by up to 16.9% on Spider 2.0 and 13.7% on BIRD

版本更新 · v2arXiv:2412.07962Google Research

Mayfly: Private Aggregate Insights from Ephemeral Streams of On-Device User Data

Christopher Bian, Albert Cheu, Stanislav Chiknavaryan, Zoe Gong, Marco Gruteser, Oliver Guinan, Yannis Guzman, Peter Kairouz 等 15 位作者

原文摘要

This paper introduces Mayfly, a federated analytics approach enabling aggregate queries over ephemeral on-device data streams without central persistence of sensitive user data. Mayfly minimizes data via on-device windowing and contribution bounding through SQL-programmability, anonymizes user data via streaming differential privacy (DP), and mandates immediate in-memory cross-device aggregation on the server -- ensuring only privatized aggregates are revealed to data analysts. Deployed for a sustainability use case estimating transportation carbon emissions from private location data, Mayfly computed over 4 million statistics across more than 500 million devices with a per-device, per-week DP $\varepsilon = 2$ while meeting strict data utility requirements. To achieve this, we designed a new DP mechanism for Group-By-Sum workloads leveraging statistical properties of location data, with potential applicability to other domains.

cs.CR · cs.DB

版本更新 · v4arXiv:2601.11516Google DeepMind

Building Production-Ready Probes For Gemini

János Kramár, Joshua Engels, Zheng Wang, Bilal Chughtai, Rohin Shah, Neel Nanda, Arthur Conmy

原文摘要

Frontier language model capabilities are improving rapidly. We thus need stronger mitigations against bad actors misusing increasingly powerful systems. Prior work has shown that activation probes may be a promising misuse mitigation technique, but we identify a key remaining challenge: probes fail to generalize under important production distribution shifts. In particular, we find that the shift from short-context to long-context inputs is difficult for existing probe architectures. We propose several new probe architectures that handle this long-context distribution shift. We evaluate these probes in the cyber-offensive domain, testing their robustness against various production-relevant distribution shifts, including multi-turn conversations, long context prompts, and adaptive red teaming. Our results demonstrate that while our novel architectures address context length, a combination of architecture choice and training on diverse distributions is required for broad generalization. Additionally, we show that pairing probes with prompted classifiers achieves optimal accuracy at a low cost due to the computational efficiency of probes. These findings have informed the successful deployment of misuse mitigation probes in user-facing instances of Gemini, Google's frontier language model. Finally, we find early positive results using AlphaEvolve to automate improvements in both probe architecture search and adaptive red teaming, showing that automating some AI safety research is already possible.

cs.LG · cs.AI · cs.CL

版本更新 · v5arXiv:2507.03152Google Research

MedVAL: Toward Expert-Level Medical Text Validation with Language Models

Asad Aali, Vasiliki Bikia, Maya Varma, Nicole Chiou, Sophie Ostmeier, Arnav Singhvi, Magdalini Paschali, Ashwin Kumar 等 27 位作者

原文摘要

With the growing use of language models (LMs) in clinical environments, there is an immediate need to evaluate the accuracy and safety of LM-generated medical text. Currently, such evaluation relies solely on manual physician review. However, detecting errors in LM-generated text is challenging because 1) manual review is costly and 2) expert-composed reference outputs are often unavailable in real-world settings. While the "LLM-as-a-judge" paradigm offers scalable evaluation, even frontier LMs can miss subtle but clinically significant errors. We propose MedVAL, a novel, self-supervised, data-efficient distillation method that leverages synthetic data to train evaluator LMs to assess whether LM-generated medical outputs are factually consistent with inputs, without requiring physician labels or reference outputs. To evaluate LM performance, we introduce MedVAL-Bench, a dataset of 840 physician-annotated outputs across 6 diverse medical tasks capturing real-world challenges. Across 10 state-of-the-art LMs spanning open-source and proprietary models, MedVAL distillation significantly improves (p < 0.001) alignment with physicians across seen and unseen tasks, increasing average F1 scores from 66% to 83%. Despite strong baseline performance, MedVAL improves the best-performing proprietary LM (GPT-4o) by 8% without training on physician-labeled data, demonstrating a performance statistically non-inferior to a single human expert on a subset annotated by multiple physicians (p < 0.001). To support a scalable, risk-aware pathway towards clinical integration, we open-source: 1) Codebase (https://github.com/StanfordMIMI/MedVAL), 2) MedVAL-Bench (https://huggingface.co/datasets/stanfordmimi/MedVAL-Bench), 3) MedVAL-4B (https://huggingface.co/stanfordmimi/MedVAL-4B). Our benchmark provides evidence of LMs approaching expert-level ability in validating AI-generated medical text.

cs.CL · cs.AI · cs.LG

版本更新 · v3arXiv:2601.22401Google DeepMind

Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erdős Problems

Tony Feng, Trieu Trinh, Garrett Bingham, Jiwon Kang, Shengtong Zhang, Sang-hyun Kim, Kevin Barreto, Carl Schildkraut 等 24 位作者

原文摘要

We present a case study in semi-autonomous mathematics discovery, using Gemini to systematically evaluate 700 conjectures labeled 'Open' in Bloom's Erdős Problems database. We employ a hybrid methodology: AI-driven natural language verification to narrow the search space, followed by human expert evaluation to gauge correctness and novelty. We address 13 problems that were marked 'Open' in the database: 5 through seemingly novel autonomous solutions, and 8 through identification of previous solutions in the existing literature. Our findings suggest that the 'Open' status of the problems was through obscurity rather than difficulty. We also identify and discuss issues arising in applying AI to math conjectures at scale, highlighting the difficulty of literature identification and the risk of ''subconscious plagiarism'' by AI. We reflect on the takeaways from AI-assisted efforts on the Erdős Problems.

cs.AI · math.CO · math.NT

版本更新 · v2arXiv:2601.20245Google Research

AI如何影响技能形成

How AI Impacts Skill Formation

Judy Hanwen Shen, Alex Tamkin

AI 速读 基于摘要

随机实验发现AI辅助会损害开发者对新编程库的概念理解、代码阅读和调试能力,且平均未带来显著效率提升,但某些认知参与型交互模式可保留学习效果。

cs.CY · cs.AI · cs.HC

查看原文摘要

AI assistance produces significant productivity gains across professional domains, particularly for novice workers. Yet how this assistance affects the development of skills required to effectively supervise AI remains unclear. Novice workers who rely heavily on AI to complete unfamiliar tasks may compromise their own skill acquisition in the process. We conduct randomized experiments to study how developers gained mastery of a new asynchronous programming library with and without the assistance of AI. We find that AI use impairs conceptual understanding, code reading, and debugging abilities, without delivering significant efficiency gains on average. Participants who fully delegated coding tasks showed some productivity improvements, but at the cost of learning the library. We identify six distinct AI interaction patterns, three of which involve cognitive engagement and preserve learning outcomes even when participants receive AI assistance. Our findings suggest that AI-enhanced productivity is not a shortcut to competence and AI assistance should be carefully adopted into workflows to preserve skill formation -- particularly in safety-critical domains.

版本更新 · v2arXiv:2511.06411Google Research

SofT-GRPO:通过 Gumbel 重参数化软思考策略优化超越离散 Token 大语言模型强化学习

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization

Zhi Zheng, Yu Gu, Wei Liu, Yee Whye Teh, Wee Sun Lee

AI 速读 基于摘要

提出 SofT-GRPO 算法,用 Gumbel 噪声与重参数化技巧将 GRPO 强化学习扩展到软思考推理模式,并在 1.5B–7B 基座模型上报告了相对离散 Token GRPO 的小幅 Pass@1 提升与更明显的 Pass@32 提升。

cs.AI · cs.LG

查看原文摘要

The soft-thinking paradigm for Large Language Model (LLM) reasoning can outperform the conventional discrete-token Chain-of-Thought (CoT) reasoning in some scenarios, underscoring its research and application value. However, while the discrete-token CoT reasoning pattern can be reinforced through policy optimization algorithms such as group relative policy optimization (GRPO), extending the soft-thinking pattern with Reinforcement Learning (RL) remains challenging. This difficulty stems from the complexities of injecting stochasticity into soft-thinking tokens and updating soft-thinking policies accordingly. As a result, previous attempts to combine soft-thinking with GRPO typically underperform their discrete-token GRPO counterparts. To fully unlock the potential of soft-thinking, this paper presents a novel policy optimization algorithm, SofT-GRPO, to reinforce LLMs under the soft-thinking reasoning pattern. SofT-GRPO injects the Gumbel noise into logits, employs the Gumbel-Softmax technique to avoid soft-thinking tokens outside the pre-trained embedding space, and leverages the reparameterization trick in policy gradient. We conduct experiments across base LLMs ranging from 1.5B to 7B parameters, and results demonstrate that SofT-GRPO enables soft-thinking LLMs to slightly outperform discrete-token GRPO on Pass@1 (+0.13% on average accuracy), while exhibiting a substantial uplift on Pass@32 (+2.19% on average accuracy). Codes and weights are available on https://github.com/zz1358m/SofT-GRPO-master

版本更新 · v2arXiv:2601.06327Google Research

From Lagging to Leading: Validating Hard Braking Events as High-Density Indicators of Segment Crash Risk

Yechen Li, Shantanu Shahane, Shoshana Vasserman, Carolina Osorio, Yi-fan Chen, Ivan Kuznetsov, Kristin White, Justyna Swiatkowska 等 10 位作者

原文摘要

Identifying high crash risk road segments and accurately predicting crash incidence is fundamental to implementing effective safety countermeasures. While collision data inherently reflects risk, the infrequency and inconsistent reporting of crashes present a major challenge to robust risk prediction models. The proliferation of connected vehicle technology offers a promising avenue to leverage high-density safety metrics for enhanced crash forecasting. A Hard-Braking Event (HBE), interpreted as an evasive maneuver, functions as a potent proxy for elevated driving risk due to its demonstrable correlation with underlying crash causal factors. Crucially, HBE data is significantly more readily available across the entire road network than conventional collision records. This study systematically evaluated the correlation at individual road segment level between police-reported collisions and aggregated and anonymized HBEs identified via the Google Android Auto platform, utilizing datasets from California and Virginia. Empirical evidence revealed that HBEs occur at a rate magnitudes higher than traffic crashes. Employing the state-of-the-practice Negative-Binomial regression models, the analysis established a statistically significant positive correlation between the HBE rate and the crash rate: road segments exhibiting a higher frequency of HBEs were consistently associated with a greater incidence of crashes. This sophisticated model incorporated and controlled for various confounding factors, including road type, speed profile, proximity to ramps, and road segment slope. The HBEs derived from connected vehicle technology thus provide a scalable, high-density safety surrogate metric for network-wide traffic safety assessment, with the potential to optimize safer routing recommendations and inform the strategic deployment of active safety countermeasures.

cs.OH · stat.AP

版本更新 · v2arXiv:2508.04665Google Research

Perch 2.0: The Bittern Lesson for Bioacoustics

Bart van Merriënboer, Vincent Dumoulin, Jenny Hamer, Lauren Harrell, Andrea Burns, Tom Denton

原文摘要

Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for transfer learning. In this new release, Perch 2.0, we expand from training exclusively on avian species to a large multi-taxa dataset. The model is trained with self-distillation using a prototype-learning classifier as well as a new source-prediction training criterion. Perch 2.0 obtains state-of-the-art performance on the BirdSet and BEANS benchmarks. It also outperforms specialized marine models on marine transfer learning tasks, despite having almost no marine training data. We present hypotheses as to why fine-grained species classification is a particularly robust pre-training task for bioacoustics.

cs.LG · cs.SD · eess.AS

版本更新 · v2arXiv:2509.08713Google Research

The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems

Ziming Luo, Atoosa Kasirzadeh, Nihar B. Shah

原文摘要

AI scientist systems, capable of autonomously executing the full research workflow from hypothesis generation and experimentation to paper writing, hold significant potential for accelerating scientific discovery. However, the internal workflow of these systems have not been closely examined. This lack of scrutiny poses a risk of introducing flaws that could undermine the integrity, reliability, and trustworthiness of their research outputs. In this paper, we identify four potential failure modes in contemporary AI scientist systems: inappropriate benchmark selection, data leakage, metric misuse, and post-hoc selection bias. To examine these risks, we design controlled experiments that isolate each failure mode while addressing challenges unique to evaluating AI scientist systems. Our assessment of two prominent open-source AI scientist systems reveals the presence of several failures, across a spectrum of severity, which can be easily overlooked in practice. Finally, we demonstrate that access to trace logs and code from the full automated workflow enables far more effective detection of such failures than examining the final paper alone. We thus recommend journals and conferences evaluating AI-generated research to mandate submission of these artifacts alongside the paper to ensure transparency, accountability, and reproducibility.

cs.AI · cs.DL

版本更新 · v2arXiv:2505.22657Google Research

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

Wenbo Hu, Yining Hong, Yanjun Wang, Leison Gao, Zibu Wei, Xingcheng Yao, Nanyun Peng, Yonatan Bitton 等 10 位作者

原文摘要

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments. We posit that part of this limitation is due to the lack of proper 3D spatial-temporal memory modeling in LLMs. To address this, we first introduce 3DMem-Bench, a comprehensive benchmark comprising over 26,000 trajectories and 2,892 embodied tasks, question-answering and captioning, designed to evaluate an agent's ability to reason over long-term memory in 3D environments. Second, we propose 3DLLM-Mem, a novel dynamic memory management and fusion model for embodied spatial-temporal reasoning and actions in LLMs. Our model uses working memory tokens, which represents current observations, as queries to selectively attend to and fuse the most useful spatial and temporal features from episodic memory, which stores past observations and interactions. Our approach allows the agent to focus on task-relevant information while maintaining memory efficiency in complex, long-horizon environments. Experimental results demonstrate that 3DLLM-Mem achieves state-of-the-art performance across various tasks, outperforming the strongest baselines by 16.5% in success rate on 3DMem-Bench's most challenging in-the-wild embodied tasks.

cs.CV · cs.AI · cs.CL · cs.LG

版本更新 · v2arXiv:2506.15924Google Research

SNPeek:面向机密虚拟机隐私应用的侧信道分析

SNPeek: Side-Channel Analysis for Privacy Applications on Confidential VMs

Ruiyi Zhang, Albert Cheu, Adria Gascon, Daniel Moghimi, Phillipp Schoppmann, Michael Schwarz, Octavian Suciu

AI 速读 基于摘要

作者提出开源工具包 SNPeek,在生产级 AMD SEV-SNP 硬件上提供可配置的侧信道追踪原语,并结合统计与机器学习分析流程,自动估计隐私应用在机密虚拟机中的泄漏。

cs.CR

查看原文摘要

Confidential virtual machines (CVMs) based on trusted execution environments (TEEs) enable new privacy-preserving solutions. Yet, they leave side-channel leakage outside their threat model, shifting the responsibility of mitigating such attacks to developers. However, mitigations are either not generic or too slow for practical use, and developers currently lack a systematic, efficient way to measure and compare leakage across real-world deployments. In this paper, we present SNPeek, an open-source toolkit that offers configurable side-channel tracing primitives on production AMD SEV-SNP hardware and couples them with statistical and machine-learning-based analysis pipelines for automated leakage estimation. We apply SNPeek to three representative workloads that are deployed on CVMs to enhance user privacy-private information retrieval, private heavy hitters, and Wasm user-defined functions-and uncover previously unnoticed leaks, including a covert channel that exfiltrates data at 497 kbit/s. The results show that SNPeek pinpoints vulnerabilities and guides low-overhead mitigations based on oblivious memory and differential privacy, giving practitioners a practical path to deploy CVMs with meaningful confidentiality guarantees.

版本更新 · v2arXiv:2512.08924CVF · CVPR 2026Google DeepMind

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time

Chuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco, Liliane Momeni, Junyu Xie, Shuyang Sun, Rahul Sukthankar 等 14 位作者

原文摘要

Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently solve this task. D4RT utilizes a unified transformer architecture to jointly infer depth, spatio-temporal correspondence, and full camera parameters from a single video. Its core innovation is a novel querying mechanism that sidesteps the heavy computation of dense, per-frame decoding and the complexity of managing multiple, task-specific decoders. Our decoding interface allows the model to independently and flexibly probe the 3D position of any point in space and time. The result is a lightweight and highly scalable method that enables remarkably efficient training and inference. We demonstrate that our approach sets a new state of the art, outperforming previous methods across a wide spectrum of 4D reconstruction tasks. We refer to the project webpage for animated results: https://d4rt-paper.github.io/.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

版本更新 · v2arXiv:2509.00997Berkeley BAIR

支持我们的AI霸主:将数据系统重新设计为智能体优先

Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First

Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito 等 15 位作者

AI 速读 基于摘要

作者主张未来数据系统应以LLM智能体为主要工作负载,并基于智能体推测过程的特征提出智能体优先的数据系统架构研究方向。

cs.AI · cs.DB

查看原文摘要

Large Language Model (LLM) agents, acting on their users' behalf to manipulate and analyze data, are likely to become the dominant workload for data systems in the future. When working with data, agents employ a high-throughput process of exploration and solution formulation for the given task, one we call agentic speculation. The sheer volume and inefficiencies of agentic speculation can pose challenges for present-day data systems. We argue that data systems need to adapt to more natively support agentic workloads. We take advantage of the characteristics of agentic speculation that we identify, i.e., scale, heterogeneity, redundancy, and steerability - to outline a number of new research opportunities for a new agent-first data systems architecture, ranging from new query interfaces, to new query processing techniques, to new agentic memory stores.

版本更新 · v2arXiv:2510.19732Berkeley BAIR

Memo:用强化学习训练记忆高效的具身智能体

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Gunshi Gupta, Karmesh Yadav, Zsolt Kira, Yarin Gal, Rahaf Aljundi

AI 速读 基于摘要

提出 Memo——一种基于 transformer 的架构与强化学习训练方法,通过周期性摘要 token 构建和检索记忆,使具身智能体在长时程、记忆密集型任务中更高效地保持上下文。

cs.AI · cs.CV · cs.RO

查看原文摘要

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based policies for embodied sequential decision-making tasks, visual inputs often overwhelm the context limits of transformers, while humans can maintain and utilize a lifetime of experience compressed as memories. Significant compression is possible in principle, as much of the input is irrelevant and can be abstracted. However, existing approaches predominantly focus on either recurrent models with fixed-size memory or transformers with full-context reliance. In this work, we propose Memo, a transformer-based architecture and training recipe for reinforcement learning (RL) on memory-intensive, long-horizon tasks. Memo incorporates the creation and retrieval of memory by interleaving periodic summarization tokens with the inputs of a model during training. We demonstrate Memo's effectiveness on a gridworld meta-RL benchmark and a multi-object navigation task in photo-realistic indoor settings. Memo outperforms naive long-context transformer baselines while being more compute and storage efficient. Additionally, Memo generalizes better to longer contexts at inference time and remains robust in streaming settings, where historical context must be truncated to fit inference constraints. Our code is available at: https://github.com/gunshi/memo.

版本更新 · v3arXiv:2409.14980Google Research

(De)-regularized Maximum Mean Discrepancy Gradient Flow

Zonghao Chen, Aratrika Mustafi, Pierre Glaser, Anna Korba, Arthur Gretton, Bharath K. Sriperumbudur

原文摘要

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractable numerical implementation ($f$-divergence flows) or require strong assumptions, and modifications such as noise injection, to ensure convergence (Maximum Mean Discrepancy flows). In contrast, DrMMD flow can simultaneously (i) guarantee near-global convergence for a broad class of targets in both continuous and discrete time, and (ii) be implemented in closed form using only samples. The former is achieved by leveraging the connection between the DrMMD and the $χ^2$-divergence, while the latter comes by treating DrMMD as MMD with a de-regularized kernel. Our numerical scheme uses an adaptive de-regularization schedule throughout the flow to optimally trade off between discretization errors and deviations from the $χ^2$ regime. The potential application of the DrMMD flow is demonstrated across several numerical experiments, including a large-scale setting of training student/teacher networks.

stat.ML · cs.LG

版本更新 · v5arXiv:2504.13837Google Research

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly on mathematics and programming tasks. Similar to how traditional RL helps agents explore and learn new strategies, RLVR is believed to enable LLMs to continuously self-improve, thus acquiring novel reasoning abilities beyond those of the corresponding base models. In this study we critically examine the current state of RLVR by systematically probing the reasoning capability boundaries of RLVR-trained LLMs across various model families, RL algorithms, and math, coding, and visual reasoning benchmarks, using pass@k at large k values as the evaluation metric. Surprisingly, we find that the current training setup does not elicit fundamentally new reasoning patterns. While RLVR-trained models outperform their base models at small k (e.g., k = 1), the base models achieve a higher pass@k score when k is large. Coverage and perplexity analyses show that the observed reasoning abilities originate from and are bounded by the base model. Treating the base model as an upper bound, our quantitative analysis shows that six popular RLVR algorithms perform similarly and remain far from optimal in leveraging the potential of the base model. By contrast, we find that distillation can introduce new reasoning patterns from the teacher and genuinely expand the model's reasoning capabilities. Overall, our findings suggest that current RLVR methods have not yet realized the potential of RL to elicit truly novel reasoning abilities in LLMs. This highlights the need for improved RL paradigms, such as continual scaling and multi-turn agent-environment interaction, to unlock this potential.

cs.AI · cs.CL · cs.CV

版本更新 · v2arXiv:2507.16795Google DeepMind

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

Helena Casademunt, Caden Juang, Adam Karvonen, Samuel Marks, Senthooran Rajamanoharan, Neel Nanda

原文摘要

Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying training data, for example by adding data that better specify the intended generalization. However, this is not always practical. We introduce Concept Ablation Fine-Tuning (CAFT), a technique that leverages interpretability tools to control how LLMs generalize from fine-tuning, without needing to modify the training data or otherwise use data from the target distribution. Given a set of directions in an LLM's latent space corresponding to undesired concepts, CAFT works by ablating these concepts with linear projections during fine-tuning, steering the model away from unintended generalizations. We successfully apply CAFT to three fine-tuning tasks, including emergent misalignment, a phenomenon where LLMs fine-tuned on a narrow task generalize to give egregiously misaligned responses to general questions. Without any changes to the fine-tuning data, CAFT reduces misaligned responses by 10x without degrading performance on the training distribution. Overall, CAFT represents a novel approach for steering LLM generalization without modifying training data.

cs.LG · cs.AI · cs.CL

版本更新 · v5arXiv:2405.20559Berkeley BAIR

信息驱动的成像系统设计

Information-driven design of imaging systems

Henry Pinkard, Leyla Kabuli, Eric Markley, Tiffany Chien, Jiantao Jiao, Laura Waller

AI 速读 基于摘要

提出直接量化成像系统测量与未知物体之间互信息的方法,并基于此开发IDEAL技术来设计成像系统。

cs.CV · cs.IT · eess.IV

查看原文摘要

Imaging systems have traditionally been designed to mimic the human eye and produce visually interpretable measurements. Modern imaging systems, however, process raw measurements computationally before or instead of human viewing. As a result, the information content of raw measurements matters more than their visual interpretability. Despite the importance of measurement information content, current approaches for evaluating imaging system performance do not quantify it: they instead either use alternative metrics that assess specific aspects of measurement quality or assess measurements indirectly with performance on secondary tasks. We developed the theoretical foundations and a practical method to directly quantify mutual information between noisy measurements and unknown objects. By fitting probabilistic models to measurements and their noise characteristics, our method estimates information by upper bounding its true value. By applying gradient-based optimization to these estimates, we also developed a technique for designing imaging systems called Information-Driven Encoder Analysis Learning (IDEAL). Our information estimates accurately captured system performance differences across four imaging domains (color photography, radio astronomy, lensless imaging, and microscopy). Systems designed with IDEAL matched the performance of those designed with end-to-end optimization, the prevailing approach that jointly optimizes hardware and image processing algorithms. These results establish mutual information as a universal performance metric for imaging systems that enables both computationally efficient design optimization and evaluation in real-world conditions. A video summarizing this work can be found at: https://waller-lab.github.io/EncodingInformationWebsite/

版本更新 · v4arXiv:2506.16791Google Research

TabArena: A Living Benchmark for Machine Learning on Tabular Data

Nick Erickson, Lennart Purucker, Andrej Tschalzev, David Holzmüller, Prateek Mutalik Desai, David Salinas, Frank Hutter

原文摘要

With the growing popularity of deep learning and foundation models for tabular data, the need for standardized and reliable benchmarks is higher than ever. However, current benchmarks are static. Their design is not updated even if flaws are discovered, model versions are updated, or new models are released. To address this, we introduce TabArena, the first continuously maintained living tabular benchmarking system. To launch TabArena, we manually curate a representative collection of datasets and well-implemented models, conduct a large-scale benchmarking study to initialize a public leaderboard, and assemble a team of experienced maintainers. Our results highlight the influence of validation method and ensembling of hyperparameter configurations to benchmark models at their full potential. While gradient-boosted trees are still strong contenders on practical tabular datasets, we observe that deep learning methods have caught up under larger time budgets with ensembling. At the same time, foundation models excel on smaller datasets. Finally, we show that ensembles across models advance the state-of-the-art in tabular machine learning. We observe that some deep learning models are overrepresented in cross-model ensembles due to validation set overfitting, and we encourage model developers to address this issue. We launch TabArena with a public leaderboard, reproducible code, and maintenance protocols to create a living benchmark available at https://tabarena.ai.

cs.LG · cs.AI