🏷️ 论文/研究
实时追踪 AI 行业热点动态 · 共 55 条资讯
斯坦福与 Arc Institute 用 AI 设计全新病毒基因组，16 种在实验室成功杀死细菌
斯坦福大学与 Arc Institute 团队用 AI 模型 Evo 从零设计完整病毒基因组，并在实验室构建出 16 种自然界不存在的功能性病毒。Evo 提出 70 万个候选基因组，团队仅筛选最有希望的 285 个序列合成并植入细菌，其中 16 个成功复制并杀死宿主。该研究已通过同行评审发表于《Science》，但 Evo 未接受人类病原体数据训练，且能否推广至其他病毒类群仍是未知数。 🔗 阅读原文 via AI HOT · https://aihot.virxact.com/items/cmsiys4dz1yqironkuitnfi7t
0 阅读原文Anthropic 更新 Claude Fable 5 生物安全防护，误报率大幅降低
Anthropic 更新了 Claude Fable 5 的生物安全防护机制，将生物相关查询的"回退"次数减少约 85%，用户在日常健康与教育问题上将更少遇到系统切换至较弱模型的情况。此次更新扩大了模型可协助的生物任务范围，但涉及双重用途的病毒学、毒理学和分子设计请求仍会回退至 Opus 5。Anthropic 表示正通过可信访问途径，致力于缩小专业生物研究与药物开发领域的差距。 🔗 阅读原文 via AI HOT · https://aihot.virxact.com/items/cmsic9k6j18ghronkd6hbia5j
0 阅读原文千问功能上新：推出思考研究、定时任务、办公助理、语音通话等多项新功能，并支持 Qwen3.8-MAX
千问今日上线多项新功能，并支持最新旗舰模型 Qwen3.8-MAX。其中"思考研究"在原"深度思考"基础上升级，强化复杂推理与工具调用；"定时任务"可预设执行时间自动完成行业简报梳理等周期工作；"办公助理"能连接备忘录、日历等应用并操作电脑浏览器，直接输出可用的 Office 文档。语音通话支持 7x24 小时多场景，智能体广场首批覆盖物流、房产等十多个领域。 🔗 阅读原文 via AI HOT · https://aihot.virxact.com/items/cmsib6211178jronko75alzk2
0 阅读原文扩展分类流映射（Categorical Flow Maps）规模
连续扩散与流匹配模型有望成为语言建模中自回归方法的有力替代，可解锁加速采样与倾斜等连续模态优势。近期研究通过高斯分布与one-hot编码数据分布间的简单流匹配过程，实现离散数据的连续生成，并借助分类流映射（CFMs）验证了加速采样的可行性，样本质量具有竞争力。 🔗 阅读原文 via AI HOT · https://aihot.virxact.com/items/cmsj4jrne24d5ronkvb40rucl
0 阅读原文论文：Learning When to Trust via Selective Context Preference Optimization
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting. We recast the problem as selective trust and introduce MIST, a human-annotated benchma
0 阅读原文论文：The Bitter Lesson of Tool Calling
Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been co
0 阅读原文论文：Tracing the Heart: An Evidence-Linked Pipeline for Heart-Failure Feature Engineering
Electronic health record (EHR) feature engineering is a major bottleneck in clinical research and AI, accounting for 39-45% of data scientists' workload. This is especially pronounced in heart failure, which affects an estimated 6.7 million U.S. adults and requires integrating fragmented EHR data with disease-specific, guideline-based clinical reasoning. Existing rule-based and large language mode
0 阅读原文论文：Investigating Artificial Intelligence Digital Sovereignty in Mobile Shopping Apps: A Case Study of Nigeria
The use of e-commerce mobile applications is expanding in Nigeria, creating both opportunities and risks, including fraud and reduced user control over digital technologies, raising concerns about digital sovereignty. This research examines how Artificial Intelligence (AI) in Nigerian mobile applications affects digital sovereignty, examined through platform transparency as a key indicator of user
0 阅读原文论文：An Optimal Agnostic PAC Algorithm
Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$. Writing $L$ for the binary risk and $L^*=\min_{h\in H}L(h)$, we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size $n$, for every $0<δ\le 1/2$, with probability at least $1-δ$, \[ L(\widehat h) \le L^*+ 7\cdot10^8\left( \sqrt{\frac{L^*(d+\log(1/δ))}{n}} +\frac{d+\log(1/δ)}{n} \rig
0 阅读原文论文：AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games
Deciding which of two agents is stronger means playing games until skill outweighs luck, and every game costs money, model inference, or expert time. Since the number of games needed is unknown, fixed-budget evaluations either keep paying after the result is settled or stop before the agents can be told apart, while naive optional stopping with an ordinary confidence interval invalidates the state
0 阅读原文论文：The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping
Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While existing programmatic benchmarks offer better control, they score only the final answer rather than auditing reported events against executable ground truth. To bridge this gap, we introduce trace-grounded parametric prof
0 阅读原文论文：Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our w
0 阅读原文论文：CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable validation establishes feasibility, yet does not reveal how a task behaves relative to a given solver setting. In this paper, we present CalibForge, an autonomous terminal-task synthesis system that uses verified solver behavior to revise candidate
0 阅读原文论文：Challenges in Evaluating Explanation Methods for Static and Evolving Data
This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through the DetoxAI image recognition system for bias detection and concept unlearning. Then, an example of a human-grounded evaluation of methods for explaining image classification is presented. The paper further explores methods for adapting explanation
0 阅读原文论文：RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer
Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-policy self-distillation (OPSD) and its variants have emerged as a promising paradigm, providing dense token-level supervision on student-generated rollouts, yet their objectives do not explicitly prioritize reasoning signals most critical to cross-ling
0 阅读原文论文：TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories
LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure. However, progress faces two main challenges. First, long trajectories make it difficult to identify individual errors, sin
0 阅读原文论文：Scalable estimation of VARMA models
Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every evaluation costs a pass over the entire series. Yet their moving-average term captures with a few parameters what a pure autoregression matches only with many lags. We introduce an est
0 阅读原文论文：Optimal Rates for Learning with Monotone Adversaries
A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of the combined sample and is scored on the original distribution. Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not excha
0 阅读原文论文：Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it contains, which columns function as measures or identifiers, and how tables connect into units of analysis. Today, this semantic layer is usually written by hand. This is a knowledge-acquisition bottleneck that limits the scalability of analytic syst
0 阅读原文论文：Benchmarking the Benchmarks: Evaluating Benchmarks for Conversational Agents
Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor benchmarks may contain inconsistent tasks, simplistic scenarios, or limited policy coverage, leading to unreliable evaluations. We introduce a reference-free framework that uses LLM judges to assess benchmark consistency, complexity, and policy cover
0 阅读原文论文：Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents
Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated. National standard documents, such as China GB/T standards, offer a representative testbed: they are lengthy, highly structured, and governed by explicit rules for scope, terminology, normative wording, and cross-section consistency.
0 阅读原文论文：Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
White matter hyperintensities (WMH), bright regions on Fluid-attenuated Inversion Recovery (FLAIR) scans are associated with cerebrovascular pathology and neurodegeneration. FLAIR is usually acquired with thick slices in clinical settings, giving it poor through-plane resolution. Super-resolution (SR) is a widely used method for recovering an isotropic volume from an anisotropic scan. Yet whether
0 阅读原文论文：RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranking, generative reward models have not realized their potential in reinforcement learning (RL). Our analysis reveals that this limitation arises from a mismatch between the comparative nature of generative reward modeling
0 阅读原文论文：Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents -- financial statements, audit reports, regulatory returns -- this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.
0 阅读原文论文：HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
As LLMs are increasingly deployed within agentic systems, their capabilities depend not only on the model weights but also on the harness: the prompts, tools, control flow, memory, and orchestration code surrounding them. This makes automated harness optimization -- the iterative and evaluation-guided improvement of a harness by an AI system -- both an important route to improving AI systems and a
0 阅读原文论文：Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors
Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age. Transformer-based foundation models have improved the accuracy of these L2 speaking graders, but their
0 阅读原文论文：On-Policy Self-Distillation without Any Supervision
On-policy (Self-)Distillation (OPD / OPSD) has shown strong potential for post-training large language models (LLMs). However, existing methods still rely heavily on external supervision, including ground-truth signals, environmental feedback, or guidance from larger models, and therefore fall short of genuine "self"-distillation. In this study, we show that on-policy self-distillation can be achi
0 阅读原文论文：QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction
Cardiac arrest remains one of the most lethal conditions encountered in intensive care units. Despite the growing availability of electronic health record data, existing mortality prediction studies in this population largely depend on static summaries derived from early admission. Such approaches ignore the temporal progression of physiological deterioration and recovery that unfolds throughout a
0 阅读原文论文：NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often lead
0 阅读原文论文：Stochastic Dynamics on Persistence Diagram Space via Reinforcement Learning
Persistence diagrams (PDs) provide stable and interpretable summaries of multiscale topological structure. While substantial progress has been made in the statistical analysis of PDs, existing literature often treats diagrams as static objects and provide limited frameworks for probabilistic modeling and stochastic evolution on PD space. We introduce a reinforcement learning framework for stochast
0 阅读原文论文：The Illusion of Visual Tool-Use: A Causal Audit of Thinking with Images
The "thinking-with-images" paradigm equips multimodal LLMs with active visual operations such as crop-and-zoom. However, models using these operations often achieve only marginal or negative gains over direct inference at substantially higher token cost. They may also repeatedly crop irrelevant regions and fail on questions that direct inference answers correctly. We ask whether the returned visua
0 阅读原文论文：Improving the Realism of Synthetic Clinical Benchmarks Under Utility Constraints
Synthetic clinical benchmarks for enterprise AI agents can pass existing utility checks and still remain structurally unrealistic, especially in privacy-sensitive healthcare settings where operational data are hard to access. We study how to improve such benchmarks without breaking the downstream utility checks already used in practice. We formulate benchmark revision as utility-constrained realis
0 阅读原文论文：OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations
The development of deep learning over the past decade has revolutionized medical imaging segmentation, allowing the extraction of precise descriptors from large volumes to characterize pathologies. Data augmentation is a technique widely regarded as a way to improve model training. It includes simple transformations like spatial operations or intensity modifications, but also more advanced synthes
0 阅读原文论文：Hypothesis Testing with Conditional Queries: Learnability and the Value of Interaction
Model evaluations may fix all tests before observing any responses or select later tests using earlier responses. We study this choice in a conditional-query model on a finite outcome space $\mathcal{X}$ with $|\mathcal{X}|=N$. We first ask which pairs of distribution classes can be reliably distinguished. We then ask how many additional queries are required to match an adaptive tester when all qu
0 阅读原文论文：RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations. String-, fingerprint-, and graph-based reaction encodings only partially capture chemical transformations, making accurate prediction difficult for reactions with complex substrates.
0 阅读原文论文：MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations. We developed MetaboLLM, a metabolomics-specialized large language model adapted through continual pretraining, supervised fine-tuning, and structured retrieval, together with MetaboLLM-GIN, which converts generated biochemical descriptions into metabolite graphs
0 阅读原文论文：Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model
Deaf and hard-of-hearing people in Bangladesh communicate mainly through Bangla Sign Language (BdSL). Automatic BdSL recognition on personal devices could widen access to education and services. Existing systems use controlled-setting datasets without expert verification and heavyweight pretrained backbones unsuited to on-device use. We introduce RSBdSL38, 10,874 expert-validated images spanning a
0 阅读原文论文：Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic loss diverges in norm while converging in direction to a max-margin interpolating classifier, whose implicit bias can be statistically suboptimal. In this work, we show that early stopping can overcome this suboptimality:
0 阅读原文论文：A Six-Dimensional Taxonomy of Post-Training Adaptation Techniques with Applications in AI Governance
Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning. However, the literature remains fragmented across technique families, model classes, and deployment contexts, making it d
0 阅读原文论文：DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level. On-policy self-distillation (OPSD) mitigates this sparsity by querying a privileged teacher at student-visited prefixes and providing dense token-level distributional supe
0 阅读原文论文：Timestep-Conditioned Transformers for Global Weather Forecasting
Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a fundamental trade-off: shorter timesteps (e.g. 1 to 6 hours) finely resolve atmospheric dynamics within the diurnal cycle but increase error accumulation for a given forecast horizon, while longer timesteps (e.g. 24 hours) reduce error accumulation
0 阅读原文论文：PRISM: Distribution-Gated Flow Matching for Controllable Unpaired Image Translation
Unpaired image-to-image translation must decide, per image, what to change and what to preserve without paired supervision. Many diffusion-based unpaired translators control preservation through a single global noise or guidance value applied across the image, which cannot separate content to keep from appearance to change. We present PRISM, a GAN-free flow-matching framework that replaces this gl
0 阅读原文论文：Depth-Guided Video Object Counting in Crowded Scenes
Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Existing methods rely on RGB information, limiting their discriminative ability in crowded and occluded conditions. To address this, we propose a Depth-Guided Detector (DG-Det) along with a general post-processing pipeline.
0 阅读原文论文：From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks
Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when embedded into physical systems, such as robots and vehicles operating under real-world physical laws. This stems from their inability to maintain reliable world models for long-horizon planning under uncertainty and generalize to unseen scenarios. I
0 阅读原文论文：TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
While deep learning models, particularly transformer-based architectures, have shown impressive performance in time series forecasting, the application of retrieval-augmented generation (RAG) in this domain remains limited. Since RAG has proven effective in enhancing the capabilities of large language models by incorporating relevant external information, retrieving similar time series sequences a
0 阅读原文论文：Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation
Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dynamics, reducing reliance on explicit programming to teach a skill to a robot. The resulting human-like robot motion is recognised as a key factor in building trust and enabling natural collaboration in human-robot interaction. This paper presents a
0 阅读原文论文：Muon on the Stiefel Manifold Admits an Exact Closed-Form Update
We study Muon, a recently proposed matrix-aware optimization method, in the context of the Stiefel manifold. This manifold consists of matrices with orthonormal columns and is ubiquitous in machine learning and scientific computing. Existing extensions of Muon to this manifold rely on heuristic, approximate, or iterative updates with varying computational efficiency. We show that the corresponding
0 阅读原文论文：Continual Learning in Transition
Classical continual learning (CL) has primarily focused on enabling models to update and retain knowledge through parameter-centric mechanisms, e.g., training strategies, architectural designs, and weight adaptation. However, emerging paradigms are reshaping the scope of CL beyond this traditional model adaptation view. For instance, on-policy learning broadens the space of update mechanisms; test
0 阅读原文论文：Beyond Marginal Validity: Finite-Sample Guarantees for Localized Conformal Prediction
Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide severe covariate-specific miscalibration, while exact distribution-free conditional coverage is finite-sample unattainable. Randomly localized conformal prediction (RLCP) mitigates this gap by calibrating near the test point while preserving marginal co
0 阅读原文论文：What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
Large language model (LLM) benchmark evaluations are routinely used to support claims about model safety, reliability, and deployment readiness. Yet most evaluations rely on a single access modality (model APIs), perform a single run per prompt, and report accuracy as the primary outcome metric, without accounting for conditions such as web search that may have effects on model behavior in deploym
0 阅读原文论文：EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Training large language model agents for long-horizon tool use typically relies on interactions with real or synthesized executable environments, whose construction and verification are costly, or on external simulators that are difficult to ground. We introduce EnvACE, an agentic reinforcement learning method that replaces external environment interaction during training with world rehearsal. The
0 阅读原文论文：Comparative Approaches to Agent Retrieval over Large Skill Libraries
Agents backed by large skill libraries must decide which skills to load and in what order. Loading the entire library into context is expensive and provides no structure for autonomous sequencing. We study two systems for this problem over a corpus of 690 skills: a hybrid ranker combining lexical and dense-embedding retrieval for sparse, on-demand loading, and a typed knowledge graph encoding work
0 阅读原文论文：Handling Missing Data in Probabilistic Regression Trees
Probabilistic Regression Trees (PRTrees) are a smooth and consistent alternative to classical regression trees, producing continuous predictions through probabilistic split assignments. This paper extends the PRTree framework to accommodate missing predictor values directly during tree construction, eliminating the need for prior imputation. Three strategies are proposed, each exploiting the avail
0 阅读原文论文：MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
Microarchitecture design space exploration suffers from expansive search spaces and expensive PPA evaluation, leaving only a small simulation budget for design decision-making. Existing methods perform blind search without considering microarchitectural dependencies and fail to learn from the iterative search effectively, leading to wasted evaluations and weak Pareto convergence. In this paper, we
0 阅读原文阿谀奉承的人工智能会削弱利他意图并助长依赖性（2025）
斯坦福大学和卡内基梅隆大学的研究发现，在11个前沿AI模型中，模型对用户行为的肯定率比人类高出50%，即使涉及操纵或欺骗等有害行为时也不例外。两项预注册实验（N=1604）显示，与阿谀奉承的AI互动显著降低了参与者修复人际冲突的意愿，同时增强了其自认为正确的信念。然而，参与者仍将这类回应评为更高质量、更信任并更愿意再次使用，形成助长依赖的恶性循环。 🔗 阅读原文 via AI HOT · https://aihot.virxact.com/items/cmsh6fjal001mronkgffxycgg
0 阅读原文