跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 18:52 — 2026-11-16 18:52(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 有修订112 HF 社区发现

浏览论文库

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 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.12725

Scaling Taxonomy-Free Image Labeling with Generative AI: A Multimodal

Zhenjie Zhang, Sainan Chen, Kshiteesh Hegde, Mengze, Li, Pouya Rezazadeh Kalehbasti, Munachim Ezema, Karina Sobhani

原文摘要

Providing real-time multimodal insights into images is challenging because it requires low latency, high description accuracy, and scalable solutions that are both cost-effective and efficient. For example, given a new image of an outfit, we would like to generate insights that the image depicts "earth tones" and "linen pants" and allow users to explore similar ideas along these themes. Traditional strategies to generate such insights would typically involve building taxonomies producing a golden set labeled by humans, training models on these datasets, and deploying these models for online inference services. Such workflows are constrained by fixed taxonomy, high labeling cost, limited labeling coverage in sample space, and human errors and expertise gaps in labelers. In addition, these methods are expensive and cumbersome to iterate over time. Recent trends have started exploring generative AI models for online insights, but this method suffers from long latency and prohibitive costs to support a high volume of requests or large amounts of offline labeling needs. We present Generative Labeling On Clusters (GLOC) as a solution to provide highly scalable, cost-effective, low latency, and high accuracy online image insight services. GLOC leverages highly optimized image embeddings to form image clusters that are semantically close to each other for the purpose of the type of insights, and summarizes the insights at the cluster level, which effectively generalizes to members in the cluster. At Pinterest, GLOC powers image descriptors and pivot query suggestions for Hybrid Search, which is a multimodal search service enabling users to search with both an image and a text query. Our offline and online A/B tests demonstrate that GLOC significantly outperforms previous methods, delivering improvements in quality and efficiency.

cs.LG · cs.IR

版本更新 · v2arXiv:2606.11711

Capacity-Constrained Online Convex Optimization with Delayed Feedback

Alexander Ryabchenko, Idan Attias, Daniel M. Roy

原文摘要

Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, tracking resources are finite, and feedback from rounds that cannot be tracked is permanently lost. In this paper, we study delayed online convex optimization (OCO) under a hard capacity constraint, where at most $C$ pending rounds can be tracked at any time. To model delay information, we introduce a semi-clairvoyant model that refines the clairvoyant assumption from prior work: rather than requiring delays to be known at prediction time, the learner observes delay expirations online, consistent with the classical unconstrained delayed setting. Our approach proceeds via a reduction to a novel ``delayed and weighted'' OCO problem, using a scheduler that randomizes which rounds are tracked and importance-weights the resulting observations. For the base problem, we propose and analyze Delayed-Weighted FTRL and its bandit analogue, obtaining regret bounds that characterize how weights interact with delayed feedback in both settings. Combining these bounds with our schedulers yields regret guarantees for capacity-constrained OCO under convex and strongly convex losses, for both first-order and bandit feedback. For first-order feedback, capacity $C = Ω(\log T)$ suffices to recover the standard delayed OCO rates up to logarithmic factors. For bandit feedback, the standard delayed BCO rates are instead modulated by $(1 + σ_{\text{max}}/C)$ factors, where $σ_{\text{max}}$ is the maximum number of outstanding observations. This allows the regret bound to degrade gracefully when $C < σ_{\text{max}}$. We complement our analysis with numerical experiments.

cs.LG · stat.ML

版本更新 · v4arXiv:2605.17062

The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort

Aleksandr Churilov

原文摘要

Package hallucinations, LLM-generated references to packages that do not exist, enable slopsquatting: an attacker registers the hallucinated name. We replicate Spracklen et al. (USENIX Security '25) on five 2026 frontier models over 199,840 Python and JavaScript generations. This version reports a preregistered live revalidation that replaces the static package lists of earlier versions with two independent checks against the live PyPI and npm registries. Hallucination rates are 3.6-5.0% of package mentions (2.2-3.4% of generations): the 2026 frontier sits at the level of 2024's commercial models, and the open-weight gap seen in 2024 has disappeared. Python exceeds JavaScript for every model. The set of names hallucinated by all five models shrinks from the 127 reported earlier to 104; 26 earlier entries were correct import statements whose module name differs from the package name. Using the accidental six-month public exposure of our own list as a natural experiment, we find no detectable effect of publication: about 1% of hallucinated names were registered within six months, at the same rate for published and unpublished names, and the 95% interval excludes increases above 2.5 percentage points. Still, at least 23 package names that the models suggest had previously hosted malware later removed by the registries, and one hallucinated name was registered with malware after our runs.

cs.CR · cs.LG · cs.SE

版本更新 · v3arXiv:2602.01635

COMET: Codebook-based Online-adaptive Multi-scale Embedding for Time-series Anomaly Detection

Jinwoo Park, Hyeongwon Kang, Seung Hun Han, Pilsung Kang

原文摘要

Multivariate time-series anomaly detection aims to identify abnormal temporal patterns in complex real-world systems. However, robust unsupervised time-series anomaly detection remains challenging because anomalies can manifest over different temporal ranges and emerge from interactions among variables, while distribution shifts can cause normal patterns to drift over time. To address these challenges, we propose Codebook-based Online-adaptive Multi-scale Embedding for Time-series anomaly detection (COMET), a unified framework with three tightly coupled components. First, Multi-scale Patch Encoder learns correlation-aware patch embeddings by combining variable-specific temporal dynamics with shared inter-variable structure across multiple patch scales. Second, Vector-Quantized Coreset quantizes these embeddings into representative normal prototypes, which are used to detect anomalies through a dual score combining quantization error and density-aware memory distance. Third, Online Codebook Adaptation leverages the same codebook structure to identify reliable normal samples from training-activated codebook entries, and then updates the prototypes through contrastive learning at inference time. Experiments on five benchmark datasets demonstrate that COMET achieves the best performance on 39 out of 45 evaluation metrics compared to seven baselines, showing robust performance across diverse evaluation protocols.

cs.LG

版本更新 · v3arXiv:2502.17383

Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations

Dong-Ho Lee, Hyundong Cho, Jonathan May, Jay Pujara

原文摘要

Asking questions is fundamental for deeper understanding, yet evaluating and generating questions that improve downstream outcomes remains a challenging problem. To address this gap, we introduce QUEST (Question Utility Estimation with Simulated Tests), a framework that offers a new outcome-driven paradigm for question evaluation and generation, instead of indirect metrics that are based on the underlying content of the question and its answer. QUEST uses language models to simulate learners that ask questions while studying a textbook chapter and quantifies the utility of a question as its direct contribution to understanding as measured by the learner's exam performance. To analyze the effectiveness of QUEST, we curate TEXTBOOK-EXAM, a benchmark that aligns textbook sections with exam questions across five academic disciplines. Using QUEST, we filter for high-utility questions and fine-tune question generators via rejection sampling and show that questions generated by QUEST-trained models improve simulated exam scores by 18.5% compared to the next strongest baseline. Furthermore, we demonstrate the practical real-world value of QUEST by showing that simulation-computed utility of a question is moderately positively correlated with its usefulness as perceived by human evaluators.

cs.CL

版本更新 · v2arXiv:2610.12673

MindVLM: Neural-Grounded Visual Captioning via Subject-Aware Semantic Evidence Selection

Zixiang Yin, Yu-Ping Wang, Zhengming Ding

原文摘要

Translating visual brain activity into natural language offers a powerful window into human cognition and neural semantic representation. Most prior brain-captioning approaches project fMRI signals into language space using paired supervision. However, the widely used Natural Scenes Dataset (NSD) was built based only on image-fMRI pairs, while existing methods rely on MS-COCO captions as indirect textual supervision. Critically, during fMRI acquisition, participants observe only cropped image regions, whereas the associated MS-COCO captions describe full scenes. This mismatch creates a fundamental gap between neural representations and textual supervision, introducing an inherent semantic loss in NSD-based brain captioning. To mitigate this limitation, we reformulate brain captioning as Neural-Grounded Visual Captioning, where language is generated directly from visually grounded neural evidence rather than text supervision. We propose MindVLM, a framework that maps fMRI signals into subject-aware visual tokens and leverages a frozen vision-language model (VLM) to produce interpretable and personalized descriptions. Instead of point-wise regression, MindVLM focuses on extracting semantically relevant visual cues from neural activity, naturally accommodating partial observability and inter-subject variability. Extensive experiments on NSD show that MindVLM maintains, and often improves, caption quality across multiple VLM backbones, including LLaVA-v1.5, Qwen2.5-VL, and Gemma3, beyond intrinsic model priors. Despite requiring neither text supervision nor an LLM during training and operating under an image-grounded inference paradigm distinct from conventional captioning methods, MindVLM remains competitive with supervised approaches, suggesting that subject-specific neural grounding provides an efficient, scalable, and interpretable path toward faithful brain-to-language generation.

cs.CE

版本更新 · v2arXiv:2605.18738

Do Language Models Share Your Doctor's Priorities? Measuring Values from Clinical Decisions

Payal Chandak, Victoria Alkin, David Wu, Maya Dagan, Taposh Dutta Roy, Maria Clara Saad Menezes, Ayush Noori, Nirali Somia 等 14 位作者

原文摘要

Clinical decisions often require weighing autonomy, beneficence, nonmaleficence, and justice. Reasonable physicians may prioritize these values differently, yet the values that language models bring to medical advice remain poorly characterized. We introduce ValuePrism, an instrument for measuring value priorities from clinical decisions. ValuePrism combines a benchmark of 50 clinical dilemmas, each reviewed by two physicians, with an attribution method that estimates relative value priorities from choices between medically reasonable recommendations. Each case presents a clinical vignette and two mutually exclusive recommendations designed so that choosing one necessarily promotes certain values at the expense of others. Applying the instrument to frontier language models and a US-based physician panel, we find that models frequently acknowledge values favoring both recommendations but make highly consistent decisions across repeated queries, even on cases that sharply divide physicians. The ValuePrism attribution method shows that both physicians and language models express differentiated value priorities. Collectively, model values exhibit substantial diversity and most tend to fall within the physician-panel reference range. Nevertheless, a single model deployed unchecked would amplify its particular values to patients at scale. ValuePrism provides a common basis for measuring and comparing the clinical value priorities expressed by language models and physicians. Data and code are available at https://github.com/payalchandak/value-prism.

cs.AI

新论文 · v1arXiv:2611.12718

No Exponential Quantum Advantage for Decoded Quantum Interferometry with Local Quantum Decoders

Brandon Augustino, Shouvanik Chakrabarti, Enrico Fontana, Dylan Herman, Guneykan Ozgul, Ruslan Shaydulin, Shreehari Sureshbabu, Jacob Watkins

原文摘要

Decoded quantum interferometry (DQI) reduces optimization of sparse linear constraint problems, and sampling from their Gibbs measures, to decoding a linear code from a quantum state. We study DQI on random $D$-regular $k$-sparse instances with $k\ge3$, for which local decoders such as belief propagation with quantum messages (BPQM) are commonly used. Such decoders estimate a typical codeword symbol using only the qudits within logarithmic distance of it. Our main insight is that the thresholds of the decoding problem induced by DQI correspond to phase transitions of the Gibbs measure that are well studied in statistical physics: tree reconstruction for local decoders and, for Max-$k$-XORSAT, condensation for the optimal decoder. This insight allows us to prove two main results. First, we prove an information-theoretic obstruction: no local decoder can recover the codeword with high probability above the tree reconstruction threshold. Conversely, we show that a decoder based on BPQM reaches this threshold. Since the cavity method predicts that local Markov chains equilibrate rapidly up to the same threshold, we expect DQI with local decoders to give no exponential speedup for sampling and no advantage in approximate optimization with amplitude functions that depend only on the number of violated constraints. Second, we consider the optimal decoder (the pretty-good measurement, for which no efficient implementation is known) and show that it succeeds exactly below the condensation threshold. The condensation threshold thus provides a tight upper bound on the performance of DQI with these amplitude functions, providing a strict refinement of the limit that Jordan et al.\ derived from the Holevo bound. Our results point to efficient nonlocal decoders that succeed between the two thresholds as the only viable path to a quantum advantage with DQI on these instances.

quant-ph · cs.DS

新论文 · v1arXiv:2611.12716

Spaghetti Splatting: Differentiating Curvilinear Dirac Masses via Convolution

George Shramko, Shrisudhan Govindarajan, Rudy Lam, Yizheng Xie, Daniel Rebain, David B. Lindell, Andrea Tagliasacchi

原文摘要

In production systems, 3D geometry is represented by primitives such as points, lines, and triangles, as rendering hardware is optimized to generate images from them very efficiently. Learning such primitives from images by volume rendering is challenging, as they are Dirac masses defined at infinitesimal locations in space. EWA splatting, Poisson reconstruction, and 3D Gaussian Splatting overcome this by convolving Dirac masses with a low-frequency kernel, a recipe that generalizes along two axes: the kernel and the primitive. As points and triangles have already received significant attention, we investigate this recipe for curvilinear primitives, and introduce Spaghetti Splatting. We approximate curves by polylines whose convolution converges to that of the continuous curve, and volume render each segment so that connected segments composite without overcounting at their joints. For fast training and inference, we linearize the camera projection per segment, which also accommodates kernels beyond Gaussians, such as Beta kernels. As a point is a curve of zero length, our representation is a strict superset of 3D Gaussian Splatting. It remains competitive with the state-of-the-art on general scenes, outperforms methods specialized to line-like geometry, natively supports anti-aliasing, and produces long connected strands that are directly amenable to physics simulation.

cs.CV · cs.GR

新论文 · v1arXiv:2611.12714

Polynomial-Space Quantum Algorithms from Classical Branching: Colouring, Domination and Monotone Local Search

Sebastian Senge

原文摘要

We give quantum algorithms for exponential-time problems on $n$ vertices or elements, with bounded error, polynomial space and no quantum random access memory. Our results are these. (1) 4-Colouring in quantum time $O(1.3032^n)$, from a polynomial-space branching algorithm with polynomial-space terminal algorithms; with the branching algorithm alone, $O(1.3100^n)$. The previous best bound in this model, to our knowledge, is $O(1.3231^n)$. (2) $k$-Colouring below the previous best bound for $k \in \{5, 7, 8, 9, 10, 11\}$ and $13 \le k \le 18$, from $O(1.4518^n)$ for $k = 5$ to $O(1.9233^n)$ for $k = 18$. (3) Dominating Set in $O(1.2235^n)$, against the previous $O(2^{n/2})$, Independent Dominating Set in $O(1.1583^n)$, and Edge Dominating Set and Minimum Maximal Matching in $O(1.1501^n)$. (4) A quantum form of monotone local search: if the extension problem has a backtracking tree with $c^k$ nodes up to polynomial factors, the problem is solved in quantum time $(2 - 1/c)^{n/2}$ up to polynomial factors. This gives Feedback Vertex Set in $O(1.3081^n)$, Subset and Group Feedback Vertex Set in $O(1.3229^n)$, Cluster Vertex Deletion in $O(1.2033^n)$, 3-Hitting Set in $O(1.2405^n)$, Proper Interval Vertex Deletion in $O(1.3541^n)$, Multicut on Trees in $O(1.1647^n)$ and Min-Ones $d$-SAT in $O^*((2-1/d)^{n/2})$. (5) Quantum exponential-time approximations below the quantum exact bounds, such as a 1.1-approximation for Vertex Cover in $O(1.0555^n)$ and for Feedback Vertex Set in $O(1.2161^n)$. The colouring exponents for $k \ge 6$ come from an evaluation of a known reduction recursion, computed in floating point with a margin.

cs.DS · cs.CC · quant-ph

版本更新 · v2arXiv:2509.06923

Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation

Ziheng Li, Zexu Sun, Jinman Zhao, Erxue Min, Yongcheng Zeng, Hui Wu, Hengyi Cai, Shuaiqiang Wang 等 11 位作者

原文摘要

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to mismatches between problem difficulty and model capability: overly difficult problems hinder reasoning path discovery, while overly simple problems offer little learning signal. To address this, we first formalize the effect of problem difficulty by quantifying the relationship between loss descent magnitude and rollout accuracy. Building on this analysis, we propose SEELE, a supervision-aided RLVR framework that dynamically adjusts problem difficulty to lie within the high-performance region. SEELE augments each training sample by appending a hint (part of a full solution) for difficulty reduction. Unlike previous hint-based approaches, SEELE deliberately computes the hint length for each individual problem to achieve an optimal difficulty. The optimal hint length is determined via multi-round rollout sampling, where an item response theory model fits accuracy-hint pairs from previous rounds to predict the next-round hint. This instance-level, real-time difficulty adjustment aligns problem difficulty with the evolving model capability, thereby improving exploration efficiency. Experiments show that SEELE outperforms Group Relative Policy Optimization (GRPO) and Supervised Fine-tuning (SFT) by +10.0 and +8.4 points, respectively, and exceeds the best prior supervision-aided approach by +3.8 points on average across six math reasoning benchmarks.

cs.LG

新论文 · v1arXiv:2611.12713

Hidden Tails: Certifying Tail-Risk Claims under Selective Labels

El Mustapha Mansouri

原文摘要

Historical decisions determine which outcomes are observed, potentially concealing a predictor's largest errors. Even unlimited data from the same observation process can therefore leave population tail risk unresolved. Here we derive sharp bounds on conditional value-at-risk, the average loss in a specified upper tail, for binary outcomes and bounded losses. These bounds span exactly the risks compatible with the observations and a stated limit on how outcome odds differ between observed and hidden cases at the same covariate values. Under stated regularity conditions, calibrated statistical certificates cover these ranges simultaneously across candidate predictors, supporting risk limits and model comparisons while separating statistical uncertainty from persistent ambiguity. For a fixed predictor and loss threshold, we derive a minimum-cost allocation for reducing excess-loss ambiguity by prioritizing hidden outcomes according to ambiguity removed per unit cost. This allocation treats audited population contributions as known and retains the original sensitivity bounds separately for audited and still-hidden outcomes. In controlled masking experiments with known loan repayments, recovering about 16% of hidden labels removes a median 61% of estimated fixed-threshold ambiguity, compared with 16% for random recovery. These results connect population tail-risk claims to the available evidence and identify where additional outcomes can sharpen their assessment.

stat.ML · cs.LG

新论文 · v1arXiv:2611.12712

Will AI mess my RTL? A snapshot-based approach to verifying AI-written RTL

Bernat Homs, Oscar Palomar, Miquel Moreto, Marcelo Orenes-Vera

原文摘要

With the growing interest in using AI (Artificial Intelligence) for RTL (Register-Transfer Level) hardware development, robust and comprehensive verification has become more important than ever. As Large Language Models (LLMs) increasingly assist in creating and modifying RTL designs, ensuring that these changes preserve existing functionality is paramount for building trust in AI-driven workflows. We present SVApshot, a fully automated framework that leverages LLMs to generate and systematically attempt to correct SystemVerilog Assertions (SVA) for RTL modules, completely removing the human from the generation loop. SVApshot introduces a novel snapshot methodology that captures the current functionality of a design as a comprehensive set of formal assertions, creating a regression suite for validating future changes--whether made by humans or AI. The framework features automated duplicate detection, assertion set expansion, and iterative repair of failing assertions using LLM-guided debugging with formal verification feedback. Our experimental evaluation across diverse RTL modules demonstrates high coverage for complex modules, with successful detection of both manually-injected and AI-introduced bugs. Additionally, this framework opens the door for automatic generation of formal testbenches to benchmark LLMs for hardware design, moving beyond binary pass/fail metrics towards nuanced assertion-based scoring.

cs.SE · cs.AR

新论文 · v1arXiv:2611.12710

WasmLens: Automatic Glass-Box Instrumentation for Composed WebAssembly Applications

Michiel Van Kenhove, Ewout Verlinde, José Santos, Filip De Turck, Bruno Volckaert, Merlijn Sebrechts

原文摘要

The WebAssembly Component Model enables language-independent composition of independently developed components, but complicates observability. Existing tracing support flattens execution hierarchy by attributing every span created inside a composition to a single host-level parent context, so execution across component boundaries cannot be reconstructed. The problem is amplified because components are typically deployed as black boxes whose internals cannot be modified or inspected by the system integrator. To address these limitations, we propose a revised wasi:otel/tracing design in which the runtime maintains a per-component span stack, restoring parent-child relationships across component boundaries without changing component interfaces or source code. This change has since been adopted upstream. Building on this design, we present WasmLens, an automatic instrumentation tool that derives instrumentation points from a composition graph and injects tracing middleware into already composed binaries, yielding end-to-end traces for black-box compositions with no developer configuration. This automatic instrumentation raises mean request latency from $238$ $μ$s to $454$ $μ$s across six component boundaries. Raising the expected number of boundary crossings from 6 to 11 further increases latency to $514$ $μ$s, an incremental cost of $12$ $μ$s per crossing, of which $10.4$ $μ$s is attributable to instrumentation. These results show that instrumentation overhead is additive in composition depth rather than proportional to baseline execution time.

cs.SE

版本更新 · v2arXiv:2608.01051

State space modeling of RLC ladder circuits

Stephan Scholz

原文摘要

Large-scale electrical circuits span a wide range of research topics from highly integrated circuits in microelectronics up to power grids for cities and countries. As the complexity increases significantly by each additional component, we find a need to describe large-scale circuits in a manner easy to understand. In this article, we study cascades of simple circuits consisting of resistors, capacitors and inductors, which we call ladder circuits. Such electrical ladders are common in electronics to design filters and they are also used in other disciplines, for example to describe diffusion or wave phenomena. In particular, we derive linear time-invariant state space models for three simple ladder types and we discuss the specific matrix structures of the large-scale second-order differential equations. Furthermore, we exemplify our findings with simulations to unveil the intrinsic dynamical behavior of each ladder type.

cs.CE · eess.SY

新论文 · v1arXiv:2611.12709

A local language model layered with rule-based and neural detectors for clinical text de-identification: an open-source toolkit and evaluation

Valentin Burkin

原文摘要

Objectives: To measure whether a locally hosted large language model (LLM), stacked with deterministic and clinical named-entity recognition (NER) detectors, finds more protected health information (PHI) than open tools, and at what precision. Materials and Methods: DeidSharp, an open-source .NET toolkit, combines the findings of pluggable detectors (patterns, a clinical NER model, a local 26B mixture-of-experts LLM) and fails closed on any detector error. Configurations fixed on tuning halves were compared, under a prespecified protocol, with deid, Philter, the Stanford/Penn de-identifier, OpenAI Privacy Filter and GLiNER on reporting halves of PhysioNet's nursing notes (889 spans) and semi-synthetic MIMIC-IV-Note discharge summaries (29,023 spans), and on synthetic ASQ-PHI queries, with paired patient-level bootstrap intervals. Results: In the nursing notes, against Stanford/Penn, the recall-first stack found 98.9% of PHI (+2.8, 95% CI 1.4 to 4.4) at 9.3 points lower precision; the precision-first stack, without NER, found 96.5%, matching Stanford/Penn, at 19.6 points higher precision (83.2%). In the discharge summaries, both stacks led Stanford/Penn by more than 20 points (recall-first 95.3%, +21.5, 20.5 to 22.4), almost entirely on generated untyped names; on typed labels all three exceeded 99%. All four prespecified comparisons held. No configuration beat deid significantly on its home corpus; Philter found more discharge-summary spans than the recall-first stack at 23 points lower precision. Discussion: The LLM was the main detector and NER added place names; asked to verify its own findings, the LLM discarded a quarter of true PHI. Conclusion: A local LLM layered with deterministic detectors offers recall-first and precision-first operating points without sending text off-site.

cs.CL · cs.CY · cs.SE

新论文 · v1arXiv:2611.12705

Multi-Agent Screening: What Agreement and Acceptance Cannot Tell You

Benjamin Chang, Dell Zhang

原文摘要

When AI agents screen items for a costly human assessor, as in agentic search, e-discovery and AI reviewing of papers, only what they pass gets judged. We show what each kind of evidence can establish about their errors, even with unlimited data. Agreement shows that agents concur, not that they are right, however many there are. Acceptance by the assessor gives precision but only a lower bound on recall. Knowing which agents found which relevant items gives an upper bound on recall if agents' finds are not negatively correlated, and caps what one more agent can add if agents are interchangeable. Without assumptions about the agents, recall can be pinned down only by judging items they did not pass: a random sample of these estimates how many relevant items were missed, to any chosen accuracy, and the sample needed does not grow with the number of agents.

cs.MA · cs.AI · cs.IR

新论文 · v1arXiv:2611.12703

Checking DER Commands Against Grid Context Catches Credentialed Attacks Static Checks Miss

Benjamin Blakely

原文摘要

Authorization of distributed energy resource (DER) commands judges a command by who sent it and whether its value has been seen before. An attacker holding a legitimate credential who writes ordinary values passes both tests. We add a check that judges each DER write against the grid's operating context: the bus voltages around the target, the hour, the day- ahead price, system load, and irradiance, compared with what operators wrote under similar conditions in the feeder's own benign history. We evaluate it live on the IEEE 123-bus and 8500-node feeders, driven by a measured 2024 year of price, load, and irradiance, against nine attack scenarios. A lookup trained on the same history catches none of the writes of the four scenarios that send values already familiar on the targeted device; the context check refuses 91.7% of insider-abuse writes and 64.4% of DER-aggregation writes while denying 1.28% of benign writes. In an offline test that replays recorded moments with curtailment setpoints drawn from the benign range, issued at a positive price, it refuses 47.3% and 50.5% on the two feeders, against 18.5% and 16.0% for the same check without context; live, the few setpoints tested were mostly shallow and were mostly allowed. The context check complements the lookup.

cs.CR

新论文 · v1arXiv:2611.12702

Fisher-Glass Learning: Classification Bounds and Subpopulation Audits

El Mustapha Mansouri

原文摘要

Accurate classifiers can fail when background cues change without altering the correct labels. Predictive performance alone does not quantify how much task information remains after accounting for such nuisance variation. Here we extend the Fisher-glass framework to connect nuisance-adjusted information with local classification difficulty and subpopulation auditing. We derive lower bounds on local minimax excess classification risk under explicit distinguishability and decision-separation conditions, alongside statistical audits accounting for estimation error and regularization. On Waterbirds, a feature-based diagnostic of task-background alignment selects an accurately classified group, with selection frozen before held-out evaluation. Across five training seeds, background replacements preserving the extracted bird foreground and labels yield 93.2% accuracy when background type is preserved and 40.6% when it changes, a controlled difference of 52.6 percentage points. Separately, search using task labels and a fixed nuisance direction identifies an independently evaluated population with 98.8% membership-weighted accuracy and low estimated projected predictive Fisher information. Training and acquisition experiments show that information gains and predictive gains can diverge. These findings support joint assessment of predictive performance, information under declared nuisance models and controlled sensitivity when diagnosing vulnerability and evaluating model improvements.

cs.LG · stat.ML

新论文 · v1arXiv:2611.12699

GeoScope: Training-Free Program Execution beyond the Counting Horizon for Ultra-High-Resolution Remote Sensing Question Answering

Guohui Deng, Yuhang Jiang, Chengjun Wang, Zhongwen Hu, Zhaocong Wu, Linsheng Huang, Jinling Zhao, Chao Ruan 等 10 位作者

原文摘要

In ultra-high-resolution (UHR) remote sensing images, the objects that questions count in a region or relate by direction often span only a few pixels. Existing methods mainly decide where a vision-language model (VLM) should look and trust its answer in the chosen view. We show that this assumption fails for counting, and measure VLMs as one calibrates a sensor. All eight open VLMs tested fall increasingly short once a view holds more than a certain number of objects, about five for most on DOTA aerial images. This counting horizon narrows as views grow and objects appear smaller. An empirical power-law response model predicts the undercount a split recovers and the spurious counts it adds, and supports the rule of splitting only views beyond the horizon. In GeoScope, a text-only language model parses the question into a typed spatial program that fixes the region and its resolution. The VLM only grounds and counts within its operating range, and directions are computed explicitly from the grounded boxes. To our knowledge, it is the first UHR method to split views by a measured limit of the VLM. Without training, it improves Qwen3-VL-8B by 16.3 points on regional counting and 10.5 on spatial relations in XLRS-Bench, and has the highest reported accuracy, trained methods included, on regional counting and on the whole benchmark by question. On UHR-Micro it improves global and regional counting by 16.8 and 36.2 points, 15.6 of the former from splitting. On MME-RealWorld counting it gains 11.4 points, and we show that an option that is almost never correct yet often chosen distorts comparisons there. Project page: https://avalon-s.github.io/GeoScope/

cs.CV · cs.AI

版本更新 · v2arXiv:2602.05026

Laws of Learning Dynamics and the Core of Learners

Inkee Jung, Siu Cheong Lau

原文摘要

We formulate an algorithm-independent theory of learning dynamics for individual models and ensembles. We establish a conservation law, the vanishing of predictive entropy under successful learning, quantitative entropy and core-expansion bounds, and calibration and finite-sample validation results for identifying reliable predictions. These results motivate a two-generation ensemble that uses Jensen-Shannon (JS) disagreement to route uncertain inputs to specialized learners. CIFAR-10 experiments examine controlled perturbations, distribution shifts, and adversarial attacks. On a heterogeneous test environment, routing improves accuracy over probability averaging while keeping core accuracy near 95%. For adversarial defense, we consider a query-only black-box setting: the attacker can query the overall prediction function but does not know a particular internal decomposition into learners and routing rules. Our current attacks use a fixed-initial-route gradient, which is accurate for a single-step attack when the route remains unchanged, but may deviate from actual multi-step attacks, especially for large perturbations. We evaluate our two-layer defense against this approximation; whether additional adversarially trained layers improve resistance to stronger multi-step attacks remains for future study.

cs.LG · cs.AI · cs.IT

新论文 · v1arXiv:2611.12696

Generalized Adaptive Boosting and the Geometry of Mistakes

Marco Bressan, Nataly Brukhim, Nicolò Cesa-Bianchi, Emmanuel Esposito, Yishay Mansour, Shay Moran, Maximilian Thiessen

原文摘要

Not all mistakes are alike. For example, in medical diagnosis, false positive and false negative mistakes have a different impact and should not be aggregated. By revisiting the classical theory of boosting through this lens, we introduce the notion of $Z$-learner, which returns weak hypotheses achieving joint false-positive/false-negative guarantees $(\mathrm{FP},\mathrm{FN})$ from some set $Z \subseteq [0,1]^2$. This formulation generalizes the standard notion of $γ$-weak learning--recovered by taking $Z=\{(z_1,z_2): z_1+z_2<1/2-γ\}$--and allows for more flexible notions of weak learnability that account for the impact of the distribution on the achievable learning guarantees. This raises a natural question: which sets $Z$ are boostable? We answer this by giving a complete geometric characterization that unifies, as special cases, both the classical boosting dichotomy and the recent multi-objective extension of Bressan et al. (COLT 2025). We also present an adaptive algorithm for boosting $Z$-learners without relying on the prior knowledge of $Z$, generalizing AdaBoost's ability to handle unknown margin parameters. Finally, we demonstrate that $Z$-learners can achieve confidence amplification. However, the analysis is significantly more involved than in classical boosting and relies on the centerpoint theorem from discrete and computational geometry.

cs.LG · stat.ML

新论文 · v1arXiv:2611.12695

TACTUS: A Robotic Palpation System for Spatially Heterogeneous Hardness Mapping of Woody Breast Myopathy

Chaitanya Pallerla, Yihong Feng, Avisekh Tripathy, Yang Tian, Pouya Sohrabipour, Amirreza Davar, Casey M. Owens, Cengiz Koparan 等 9 位作者

原文摘要

Woody breast (WB) myopathy is a spatially heterogeneous fibro-degenerative condition of the broiler Pectoralis major muscle. Existing mechanical reference methods rely on single-point or sequential compression measurements, limiting characterization of spatial hardness variability. This study presents TACTUS (Tactile Adaptive Conformal 3D Uniform Sensing), an automated tactile array that generates thickness-normalized, three-dimensional hardness maps at 20 anatomically distributed locations within approximately 30 s. TACTUS integrates 20 independently motorized tactuators with force-sensing resistors and encoder-driven linear actuators, alongside a LiDAR depth camera for surface profiling and adaptive compression. The system was evaluated using 100 broiler breast fillets across four WB severity classes (Normal, Mild, Moderate, Severe). TACTUS identified significant force differences among severity classes (ANOVA, p < 0.001), with the strongest differentiation in the cranial region and a significant caudal effect not detected by texture-analyzer measurements. Fillet-level TACTUS force showed moderate but significant correlation with texture-analyzer measurements (Pearson r = 0.441, p < 0.001). Semivariogram, local change entropy, and heterogeneity analyses revealed increasing and anatomically structured hardness variability with WB severity. These findings demonstrate TACTUS as an automated, operator-independent platform for spatially resolved mechanical characterization and ground-truth generation to support hyperspectral and near-infrared spectroscopy-based WB classification systems.

cs.LG

新论文 · v1arXiv:2611.12694

Agnostic Marginal-Nonuniform Learning

Tanmay Devale, Steve Hanneke, Amirreza Shaeiri

原文摘要

We study the problem of binary classification in the marginal-nonuniform learning framework in the agnostic setting. In this model, the constants in the learning rate may depend on the marginal distribution of the unlabeled data, but the guarantee must hold uniformly over all conditional distributions of the labels. We also study fine-grained rates. We consider two criteria. (1) The standard agnostic setting, where the learner competes with the best concept in the class. In this setting, an immediate consequence of standard agnostic PAC learning results gives us the optimal rate of $\tfrac{1}{\sqrt{n}}$ for every class $\mathcal{H}$ with finite $\mathrm{VC}(\mathcal{H})$ and shows that arbitrarily slow rates are necessary otherwise. This also gives us the optimal fine-grained rate of $\sqrt{\tfrac{\mathrm{VC}(\mathcal{H})}{n}}$. Therefore, the dependence on the marginal distribution does not help, which is in contrast to the realizable setting. (2) In the relaxed agnostic setting, where the learner competes with $(1+λ)$ times the error of the best concept for a fixed $λ\in (0,1]$, the picture from the realizable setting reappears. We obtain a trichotomy of the achievable optimal rates: exponential rates of the form $e^{-n}$ arise precisely when the class is finite; linear rates of the form $\tfrac{1}{n}$ arise when the class is infinite but $\mathrm{VC}(\mathcal{H})$ is finite; and arbitrarily slow rates occur when $\mathrm{VC}(\mathcal{H})=\infty$. We also obtain the optimal fine-grained rate of $\tfrac{\mathrm{uVCE}(\mathcal{H})}{λn}$, where $\mathrm{uVCE}(\mathcal{H})$ is a recently introduced combinatorial complexity dimension called the uncentered $\mathrm{VC}$-eluder dimension.

cs.LG

版本更新 · v2arXiv:2507.00725

PL Morse-Cerf Theory for Topological Analysis of Time-Varying Scalar Fields

Amritendu Dhar, Apratim Chakraborty, Vijay Natarajan

原文摘要

Morse-Cerf theory studies the evolution of critical points in one-parameter families of smooth functions defined on a manifold. This paper describes an adaptation of Morse-Cerf theory of smooth functions to one-parameter families of piecewise-linear (PL) functions. The vertex diagram and Cerf diagram are introduced as topological descriptors that represent evolution of the PL function. The characterization of a crossing in the vertex diagram based on the homology of the lower links of vertices leads to the definition of a topological descriptor for time-varying scalar fields. Algorithms and methods for computing, querying, and comparing Cerf diagrams support its application towards the analysis of time-varying scalar fields. Stability theorems on the comparison measure provide a guarantee of robustness. Experimental results on multiple scientific datasets demonstrate its practical utility.

cs.GR · cs.CG

版本更新 · v3arXiv:2606.30995

Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again

Zakk Heile, Hayden McTavish, Margo Seltzer, Cynthia Rudin

原文摘要

Recent work has shown that well-optimized individual decision trees can match complex black box models in some settings, primarily in noisy domains. For the remaining settings, however, complex ensembled compositions of trees often achieve higher accuracy at the cost of interpretability, leaving practitioners with difficult modeling decisions along an accuracy-interpretability tradeoff. Ideally, we would like to classify as much of the data as possible with one or a small number of trees, achieving interpretability for most samples while maintaining state-of-the-art accuracy. We introduce Multistage Defer Trees: a sequence of sparse decision trees that each make predictions for most samples, while deferring a small proportion to the next tree in the sequence or, ultimately, to a black box. We demonstrate that we can train this model class to match the performance of complex tree-based ensembles while routing most samples through only one or a small number of sparse decision trees. We discuss a range of techniques for training these models while maintaining simplicity. Our method expands the accuracy--interpretability frontier in settings where single-tree methods remain insufficient, demonstrating that even when complex models are necessary, they need not be fully opaque.

cs.LG · stat.ML

新论文 · v1arXiv:2611.12691

A Lattice-Based HMM Approach to Aruz Scansion of Ottoman Poetry

Mehmet Emre Tiryaki

原文摘要

Ottoman Divan poetry is composed in aruz, a quantitative meter based on the weights of syllables. The meter is sensitive to specific characters recorded in the original writing in the Arabic script. This work is concerned with automatic meter finding and scansion alignment for Ottoman Divan poetry, especially on modern Turkish spelling without the special diacritics that scholarly transliterations of Ottoman preserve. We define two tasks on this input, first identifying the meter used in the poem, and second aligning the meter's weights with the syllabification of the poem, identifying the flaws and freedoms the poet has taken along the way. We build a corpus of 52,000 lines split by poet, with scansion annotations for 500 test lines, and a robustness benchmark generated at the deviation rates measured on real web and OCR copies. Our model is a hidden Markov model over the positions of each meter, decoded over a lattice of every candidate path, and trained by EM from the printed meter, without scansion labels. On a held-out set it scans 77.6% of the test lines fully correctly, against 26.8% for the available rule-based scanner, 55.0% for a neural tagger trained with the same supervision and 63.6% for Claude Opus 5.5 few-shot. The code is open-sourced and the tool is released on the web.

cs.CL

新论文 · v1arXiv:2611.12690

Average versus expected causal effects under interference: Modeling assumptions and estimation bottlenecks

Vishesh Karwa, Edoardo M. Airoldi, Donald B. Rubin

原文摘要

Causal inference under treatment interference requires assumptions to reduce the exponentially large number of potential outcomes. We develop hierarchical finite-population models for potential outcomes by separating these assumptions into three layers: interference neighborhoods, exposure mappings, and outcome models. Given an interference neighborhood and exposure mapping, we show that potential outcomes admit a nonparametric decomposition into direct, spillover, and treatment--spillover interaction components. This decomposition provides a common coordinate system for nonparametric, semiparametric, and parametric models of finite-population potential outcomes. For a given potential-outcome model, we define two classes of estimands. Average causal effects (ACEs), such as direct and total treatment effects, contrast potential outcomes under fixed treatment--exposure conditions. Expected causal effects (ECEs), such as expected direct and indirect effects, contrast expectations of potential outcomes under a specified allocation policy. For both classes, we bound the variance of the canonical Horvitz--Thompson estimator by three terms: a diagonal weight term, a term from overlapping interference neighborhoods, and a residual design-dependence term. Our upper and lower bounds show that under graph-unaware designs, nonparametric design-unbiased estimation of ACEs can require sample sizes growing exponentially in the interference degree, whereas polynomial growth can suffice for design-aligned ECEs. Under neighborhood interference, we construct graph-aware independent-set designs with variance bounds polynomial in the maximum degree for direct and total treatment effects on every graph, whereas graph cluster randomization can incur worst-case variance exponential in the degree.

stat.ME · cs.LG · econ.EM

新论文 · v1arXiv:2611.12689

CoilStellaration: A Dataset and Benchmark for Engineering-Aware Stellarator Coilset Generation

Jan-Hendrik Ewers, Santiago A. Cadena, Nicolò Foppiani, Andrea Merlo

原文摘要

Stellarators are fusion devices that use externally generated, three-dimensional magnetic fields to confine hot plasma and offer a promising route to commercial fusion. Their electromagnetic coils pose a challenging design problem: they must reproduce the target magnetic field while satisfying engineering constraints and remaining practical and cost-effective to manufacture. Finding suitable geometries is a highly nonlinear inverse problem that generally has neither a closed-form nor a unique solution. This problem lies at the heart of stellarator design. We introduce CoilStellaration, a dataset and benchmark for learning the mapping between coil geometries from target plasma magnetic fields and engineering requirements. The dataset contains 177,000 optimized filamentary coilsets targeting plasma equilibria from ConStellaration, with sampled engineering requirements and achieved geometric and magnetic-field metrics. It spans multiple coil counts and field-period numbers, supporting studies of both specialized and shared models across configurations. The benchmark asks models to predict coils conditioned on a target equilibrium and requirements on coil-coil and coil-plasma spacing, curvature, and magnetic-field error. We show that magnetic-field accuracy remains the main challenge, with learned models rarely satisfying all requirements simultaneously. However, using learned predictions to initialize conventional coil optimization can accelerate early progress. We release baseline models and evaluation code to support reproducible research on both direct coil generation and learned optimization initializations. By lowering the barrier for machine learning and optimization researchers to engage with stellarator coil design, we aim to accelerate progress toward practical, cost-effective stellarator power plants.

cs.LG · physics.plasm-ph

新论文 · v1arXiv:2611.12687

reComposer: Editable Planning for Controllable Image Generation

Susie S. Y. Li, Angie Boggust, Fred Hohman, Donghao Ren, Dominik Moritz, Yannick Assogba

原文摘要

Prompt-based image generation makes it easy to produce visual assets, but offers little support for engaging with the creative process. Prompting collapses interdependent creative decisions into a monolithic instruction and returns a finished image, leaving control limited to revising the prompt or correcting the model's output. We present reComposer, a process-oriented image-generation interface built around editable planning, which decomposes users' evolving intent into meaningful creative decisions - such as subject, composition, or palette - and collaborates with users to explore underspecified goals and alternatives. reComposer supports conversational and direct manipulation of the plan, moving between concept-level intent and visual-level control. We evaluated reComposer with 8 design and non-design professionals. Compared to prompting, participants felt greater control and ownership while developing visual assets, exploring alternatives, and iterating on details. Our findings suggest how shifting generative AI interaction from specifying outputs to shaping process can support creative thinking alongside asset production.

cs.HC · cs.AI