跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+788新增论文
+627其中 AI 相关
+81已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 11:20 · 全站最近入库：2026-11-09 11:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 13:07 — 2026-11-09 13:07（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：2026-11-09 11:20最近发现新增版本：2026-11-09 11:19库内论文最新更新时间：2026-11-06 21:58

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。

17,888 已收录论文15,288 AI 相关4,419 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 17,888 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 11:19（北京时间）
版本更新 · v5arXiv:2604.24561

Remotely programming the weights of a spintronic neural network by a radiofrequency broadcast signal

M. Menshawy, D. Sanz-Hernández, L. Mazza, V. Puliafito, G. Finocchio, A. Jenkins, R. Ferreira, L. Benetti 等 10 位作者

原文摘要

Selectively programming a large number of non-volatile synaptic weights without compromising scalability is a key challenge for in-memory computing. Here, we experimentally demonstrate remote programming of synaptic weights in series-connected chains of 11 vortex-based magnetic tunnel junctions using broadcast radiofrequency signals applied through a shared strip line. Because each junction is engineered with a distinct resonance frequency, programming relies on frequency-selective reversal of the vortex-core polarity and therefore does not require individual access lines or selector devices. Reconfiguring the binary states of these chains strongly reshapes the continuous spectral transfer functions that determine the weighted sums performed on frequency-multiplexed RF inputs. This allows compact networks built from such chains to process high-dimensional RF-encoded inputs. We experimentally perform handwritten-digit classification and drone RF-signature identification using a two-chain network comprising only 22 synapses in total. After remote reconfiguration for each task, the spintronic network respectively reaches 93.9 +/- 2.3 % and 99.5 +/- 1 % test accuracy, on par with the software baseline. Broadcast RF programming thus provides a compact and scalable route to rapidly reconfigurable spintronic neuromorphic hardware.

cs.ET · cond-mat.mes-hall

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38037

Measuring Deep Learning Performance - An Empirical Study of Performance Distributions Across Architectures and Tasks

Kevin L Coakley, Odd Erik Gundersen

原文摘要

Context: Non-determinism in deep learning algorithm design and implementation leads to performance variation, meaning model performance is not a single value, but rather a distribution. These model performance distributions are underexplored despite their impact on robustness. Objective: We investigate the robustness of deep learning performance to sources of non-determinism, specifically focusing on how performance distributions differ across various architectures and tasks. Method: We conducted 186 experiments on image classification and time series forecasting architectures. Each experiment was run 100 times with different random seeds to generate performance distributions, resulting in 18,600 runs. Robustness was quantified using metrics for spread, symmetry, and tail risk. Results: Performance distributions are frequently non-Gaussian, particularly in time series forecasting. Model size does not systematically affect robustness -- larger image classification models show fewer outliers but not lower spread, while smaller time series models show lower spread but more extreme underperformers. Training duration does not scale linearly; early stopping effectively balances performance and robustness. Mean performance does not predict robustness - time series forecasting shows moderate correlation while image classification shows none. Time series models produce nearly three times more underperforming outliers than image classification models, indicating substantially higher tail risk. Conclusions: Tail risk poses serious concerns for Trustworthy AI in high-stakes applications. Models performing well on average may exhibit long tails and extreme outliers revealed only through distributional analysis. Mean performance alone should not guide model selection; assessment of spread, symmetry, and tail risk is essential for reliable model assessment where consistent performance is critical.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38036

Integral Probability Boundaries

Bogdan Kulynych, Shahab Asoodeh

原文摘要

Bounds based on Integral Probability Metrics (IPMs) are ubiquitous in machine learning and statistics, appearing, e.g., in generalization, alignment, fairness, and privacy. IPMs reduce the discrepancy between two distributions to a single worst-case gap between expectations. This compression is costly: for rare events, safety failures, or under-represented groups, IPM-based bounds are loose or vacuous. We introduce a non-linear generalization of IPMs, which we term Integral Probability Boundaries (IPBs). Unlike IPMs, IPBs provide bounds that are tight at the extremes. We derive their basic properties and present algorithms for estimating them in practically relevant settings. We demonstrate the usage of IPBs in both theoretical and practical applications for alignment, judge-free performance estimation, and fairness, where they enable us to obtain sharp bounds on performance and fairness gaps, e.g., 15 p.p. more precise estimates on fairness gaps for rare groups in a realistic generative modeling task, compared to the state of the art.

cs.LG · cs.IT · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38034

Learning from Relative Action Credit for Escaping Local Minima

Giovanni Minelli, Giulio Turrisi, Lorenzo Amatucci, Victor Barasuol, Claudio Semini

原文摘要

Reinforcement learning holds the promise of robots that learn manipulation skills from interaction alone, without pretrained priors or demonstration data. In practice, on-policy methods such as PPO routinely stall on long-horizon, contact-rich tasks: dense reward shaping carries the policy through stages, yet stitching them together and discovering sparsely rewarded events rarely succeeds. We trace this failure to the missing action discrimination in state-value credit assignment: a state-value critic judges progress only by episode outcomes, so when the policy converges to a partial solution all outcomes coincide, and improvement stops because no action can prove better than another. We therefore extend PPO with an action conditioned value critic which, can compare the executed action with alternatives sampled at the same state and aid the learning signal. Combined with Generalized Advantage Estimation and a bound on exploration noise, we show how the extended algorithm escapes the plateau and completes precise peg insertion within a training budget where PPO with identical exploration fails.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.10264

CrossEdit: Cross-Modal Training Enables Rich Audio-Visual Editing

William Chen, Prem Seetharaman, Ke Chen, Oriol Nieto, Kevin Duarte, Siddharth Srinivasan Iyer, Mamshad Nayeem Rizve, Zhiwen Cao 等 13 位作者

原文摘要

Multimedia editing requires generative models to interpret complex, compositional instructions and modify only the desired elements across modalities, a capability largely beyond existing systems. Current approaches are typically limited to simple, single-attribute edits within one modality, since diverse, high-quality editing pairs are hard to obtain, especially for cross-modal tasks where aligned audiovisual (AV) data is scarce. We present CrossEdit, a unified omni-modal editing model for images, audio, and video that performs AV movie scene edits zero-shot through cross-modal transfer. Our key observation is that complex instruction-following, once learned in any modality, generalizes to others. We exploit the additive nature of acoustic signals to procedurally generate large-scale audio editing pairs with compositional instructions, and show that fine-tuning on this synthetic data and self-supervised AV masked reconstruction, alongside a targeted set of curated cross-modal tasks, induces instruction-following that transfers zero-shot to unseen modality and instruction combinations. To evaluate this capability, we release CrossEditBench, a human-annotated benchmark of AV edits on movie scenes, and propose AV-FES, a metric that jointly scores instruction following and consistency. We show that our proposed techniques improve performance on zero-shot AV movie scene editing, while maintaining or improving performance on lip-synced speech editing and standard image, video, and audio editing benchmarks. Demos are available at https://wanchichen.github.io/crossedit/.

cs.SD · eess.AS · eess.IV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2409.11199

Lexicographic Descent: A Gradient-Based Approach to Optimize Totally Ordered Rulebooks via Parametric Scalarization

Matteo Penlington, Alessandro Zanardi, Lorenzo Fiaschi, Emilio Frazzoli

原文摘要

Safety-critical systems, such as autonomous vehicles, must satisfy conflicting constraints and objectives, collectively called rules, typically ordered lexicographically. Preemptive lexicographic optimization solves a sequence of problems, one per priority level. However, higher levels are optimized without considering lower ones, making the approach susceptible to suboptimal solutions. On the other hand, scalarization optimizes all levels jointly and so avoids this myopia, but a finite weighted sum permits trade-offs across priority levels, and exact scalar representations lack the regularity standard solvers require. We propose Lexicographic Descent, which combines the benefits of both: a single weighted sum whose relative weights decay at priority-dependent rates, recovering the lexicographic order in the limit. We show that Lexicographic Descent converges to constrained stationary points of the highest-priority rule, matching preemptive guarantees. Since the lower-priority weights vanish, we derive a necessary condition for the lower-priority rules to keep guiding the iterates, with the aim of avoiding suboptimal stationary points of the higher-priority rules. We show that Lexicographic Descent can exploit problem structure to reach the lexicographic optima, and outperforms the preemptive approach on an autonomous driving case study.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38030

From Needs Assessment to Legal-Digital Empowerment: A Community-Based Framework for Indigenous Enterprises in Higher Education Extension Programs

Marilou O. Espina, Sales G. Aribe, Mark Ian M. Mukara, Joseph L. Abella, Nurwahyu Alamsyah

原文摘要

IPOs contribute significantly to local economies, cultural preservation, and sustainable livelihoods within their ancestral communities. However, many IPOs remain marginalized in digital economies due to limited digital competencies, inadequate access to technology, and insufficient legal awareness related to online enterprise participation. This study examined the marketing practices, digital competencies, and legal-literacy needs of IPOs in the Philippines and developed a legal-digital empowerment framework for higher education extension and community engagement initiatives. Using a sequential mixed-methods design, data were collected through surveys and focus group discussions involving IPO members engaged in community-based enterprises. The study assessed existing marketing practices, identified competency and legal-awareness gaps, and determined capacity-building needs related to digital enterprise participation. Findings revealed that IPOs continue to rely heavily on traditional marketing channels, with limited use of digital platforms, inconsistent branding practices, and minimal engagement in strategic digital marketing activities. Participants also expressed concerns regarding intellectual property protection, online participation, and limited understanding of legal mechanisms related to digital enterprise engagement. Despite these limitations, IPO members showed strong willingness to participate in training and mentorship initiatives. The study proposes the Legal-Digital Empowerment Framework for Indigenous Community Enterprises, which integrates digital competencies, legal literacy, institutional support systems, and rights-based market participation into a structured and context-responsive model for higher education extension programs.

cs.CY · cs.SI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38027

METATRON: A Promptable Whole-Body Execution Layer for Humanoids

Chen Tessler, Yifeng Jiang, Alec Otto, Yi Shi, Umar Iqbal, Gal Chechik, Xue Bin Peng

原文摘要

Humanoid controllers often require task-specific training despite sharing the need for balance and whole-body coordination. We present Metatron, a promptable whole-body execution layer combining a generative base policy with a programmable skill layer. The base policy receives partial goals, collectively called a prompt, that can combine timed body-part targets, velocity commands, and style cues. It produces diverse whole-body motions consistent with these goals. Training combines motion capture, synthetic recovery trajectories, and retargeted scene-interaction motions. After training, the policy is frozen. Stateful programs called skills express task intent as prompts at each control step, drawing rough geometric sketches that the policy turns into coordinated movement. Skills are ordinary code, refined by coding agents that analyze motion data and fit compact rules without task-specific policy training. On the physical Unitree G1, one frozen checkpoint supports walking, recovery, teleoperated object pickup, and sitting on furniture. Comparative evaluations show higher reaching success and push robustness than the tested reference-tracking pipelines. The same recipe produces climbing and acrobatics on a simulated character. Metatron enables coding agents to turn learned motor capabilities into new skills through code, without further policy training.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.00435

On the burst-covering radius of binary cyclic codes

Gabriel Sac Himelfarb, Moshe Schwartz

原文摘要

We define and study burst-covering codes. We provide some general bounds connecting the parameters of a code with its burst-covering radius. We then provide stronger bounds on the burst-covering radius of cyclic codes, by employing linear-feedback shift-register (LFSR) sequences. For the case of BCH codes we prove a bound on pattern frequencies in LFSR sequences, and using this tool, we bound the burst-covering radius of binary primitive BCH codes and Melas codes. We then present an efficient burst-covering algorithm for cyclic codes. Finally, we present a bound on the critical exponent of cyclic codes based on the burst-covering radius.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38024

Assessing Language Models for Scientific Applications: Inertial Confinement Fusion as a Use Case

P. B. Radha, D. D. Meyerhofer, M. Bhattarai, B. Cheng, L. Diaz, C. L. Rousculp, A. G. Seaton, G. Gupta 等 14 位作者

原文摘要

Advancing language models for specialized scientific applications requires evaluations of scientific fluency, physical reasoning, and quantitative analyses. Using inertial confinement fusion (ICF) as a test case, we have developed an expert-curated benchmark of 250 questions spanning qualitative reasoning, numerical calculation, symbolic derivation, and equation formulation. Responses have been evaluated using deterministic numerical and symbolic checks together with language-model judges. We compared a variety of out-of-the-box closed-source and open-source large language models with Prospero, a model specialized through combined domain-adaptive pretraining and supervised fine-tuning for ICF. We also conducted initial retrieval-assisted evaluations. Prospero improved its aggregate score by 10.7 percentage points over its base model, with gains across all question types. Frontier models achieved the highest aggregate scores, but critical physics errors persisted, particularly in numerical calculations. We note that domain-specific performance can improve through specialization, but benchmark gains alone do not establish scientific reliability. Retrieval improved performance for a smaller model but yielded no statistically significant improvement for a frontier model. Two scientific stress tests further illustrate useful capabilities and the need for expert assessment of physical assumptions and model validity. Based on these findings, we recommend evaluating existing domain capabilities and retrieval benefits before committing to substantial additional specialization.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38022

An Improved Johnson Bound for List-Decoding with Hints

Swastik Kopparty, Harry Sha

原文摘要

This paper studies when list-decodability guarantees for error-correcting codes of good distance can go beyond the classical Johnson radius and gives a corresponding efficient list-decoding algorithm for Reed-Solomon codes up to this new radius. The Johnson bound shows that any error-correcting code with distance $δ$ is automatically list-decodable with small list size up to a certain radius $J(δ)$ around any received word $r$. We show that if the received word $r$ is known to have some codewords that are somewhat close to it (we call these ``hints"), then $C$ is list-decodable with small list size up to an even larger radius around $r$. We determine the optimal list-decoding radius in this setting for single and multiple hints over both large and small alphabets and show that this radius is the optimum of a natural convex program. Remarkably, even a single hint that is $(J(δ)-ε)$-close to $r$ improves the list-decoding radius around $r$ to $J(δ)+ε'$. Finally, we give an efficient algorithm, based on the weighted Guruswami-Sudan decoder, that list-decodes Reed-Solomon codes up to this optimal radius.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38021

Detecting Brain Cancer Progression Through Signatures of Wearable Accelerometry Data

Rishit Das, Barbora Barancikova, Matt Williams

原文摘要

Glioblastoma and other high-grade gliomas (HGG) have a poor prognosis and are associated with progressive functional decline. The standard of care to assess progressive disease is contrast-enhanced MRI, which is expensive, claustrophobic, and performed only once every 2-3 months. Wearable accelerometers offer a non-invasive alternative for continuously monitoring patient function between clinic visits. However, accelerometry data streams are typically noisy and highly patient-specific, making conventional time series methods and summary statistics poorly suited to detecting clinically meaningful change. This work aims to classify stable versus progressive disease states by applying rough path signatures for feature extraction from wrist-worn accelerometer data. We convert accelerometer recordings from HGG patients enrolled in the BrainWear study into walking-path segments and use signature kernel maximum mean discrepancy (SigMMD) to quantify change in patients' walking behaviour. We overcome the challenge of inter-patient heterogeneity by adjusting for the natural variation in a patient's walking during stable tumour periods. This patient-specific normalisation substantially improves separation, yielding a candidate biomarker of tumour progression. Our results provide proof-of-concept evidence that signature-based analysis of wearable accelerometry can distinguish stable from progressive disease states, motivating larger longitudinal studies of continuous wearable monitoring as a digital biomarker in neuro-oncology.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.20317

A general extractor for coherent patterns across time-frequency measurements

Nathaniel Chen, Kouroche Bouchiat, Peter Steiner, Andrew Rothstein, David Smith, Max Austin, Mike van Zeeland, Marie Roch 等 10 位作者

原文摘要

Scientific discovery increasingly depends on finding meaningful patterns within volumes of sensor data too large for manual inspection. Existing time-frequency event extractors are often engineered or trained on manually labeled examples for each instrument, which can be laborious and difficult to adapt to new environments. To address this, we introduce TokEye, a reference-free method that learns a general criterion for coherent structure from heterogeneous fusion measurements. A model developed under this method, without retraining, can extract signals from various other fields including marine bioacoustics and wideband radar. It recovers 82.5\% of expert-annotated stellarator signals, detects 78\% of dolphin whistles, and identifies radar events with 81.5\% average precision across six benchmarks, while processing full experimental spectrograms in under one second on a GPU. This transfer across unrelated sensors and physical systems reveals common exploitable structure in time-frequency measurements and establishes a scalable foundation for automated scientific signal discovery.

eess.SP · cs.AI · physics.plasm-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38017

On the $b$-Symbol Weight Distribution of Dual Melas Codes and a Poisson Randomness Postulate

Gabriel Sac Himelfarb, Moshe Schwartz

原文摘要

We prove a new lower bound on the $b$-symbol weight of codewords in dual Melas codes, which is strictly better than known results. We employ a new strategy that translates a pattern counting problem in linear-feedback shift register sequences to a problem on orbits of binary polynomials under a certain action. We use the same techniques to provide an improved lower bound on the burst-covering radius of Melas codes and a new upper bound on the critical exponent of dual Melas codes. We then define a new randomness postulate on (families of) binary sequences, based on the definition of infinite Poisson generic sequences. We conjecture that codewords in the dual Melas code satisfy this postulate, and we show partial progress in establishing this conjecture. We also show how a relaxed version of the problem can be completely resolved, and relate the conjecture to the first part of the paper, giving a justification of why the improved bounds on the $b$-symbol weight were somewhat to be expected.

cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38016

Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms

Olga Kellert, Samhitha Harish, Johnatan E Bonilla, Nemika Tyagi, Phanos Kareen, Nelvin Licona-Guevara

原文摘要

Automatic speech recognition (ASR) increasingly supplies transcripts for educational NLP, but aggregate word error rate (WER) can conceal errors concentrated in learner speech, multilingual turns, and speaker attribution. We compare platform-integrated, open-weight, adapted, and commercial ASR configurations on held-out sessions of online L2 Spanish interaction between L1 English learners and their instructors and tutors. Because English is the learner's shared first language, the interactions contain Spanish-only, English-only, and code-switched turns. Evaluation combines overall WER and character error rate (CER), WER disaggregated by speaker role and language context, and diarization error rate (DER). We also adapt Whisper large-v3 and MOSS-Transcribe-Diarize with LoRA using human-corrected in-domain classroom data. MOSS adaptation produced consistent improvements across speaker roles and language contexts, whereas Whisper showed smaller gains. Domain match proved more important than data volume: Larger out-of-domain bilingual and learner corpora did not outperform the smaller classroom corpus, where learner speech and code-switching are embedded in instructor--learner interaction. The open-weight MOSS adapter was competitive with commercial Muse Voice Transcribe on WER and CER and achieved lower system-provided DER on the recordings eligible for each system. Learner, English-only, and code-switched speech remained more difficult than instructor and Spanish-only speech. The findings demonstrate the value of condition-aware evaluation and interactionally matched data for bilingual educational ASR.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38015

Measured or Real? When Model-Derived Measurements Can Be Corrected or Compared

Yifeng Li, Ziang Ni

原文摘要

Numbers computed from trained models, such as an example's difficulty or a model's benchmark lead, change with seed and prompt. We ask when such measurements can be corrected or compared. Noise shrinks correlations, and the textbook correction divides by the square root of two estimated reliabilities. On two CIFAR-100 difficulty scores, it returned correlations above one in 70 of 100 classes. We prove that its mean squared error is infinite even when the correlation and the reliabilities use separate seeds. Our rule corrects only when both reliabilities pass a significance test, then divides by their upper confidence bounds. Its output is always bounded, and its coverage guarantees assume Gaussian noise. It helps once reliability is well estimated, more than halving the error with 500 simulated units. Prompt settings can reverse rankings. On ARC, Qwen2-1.5B trails Llama-3.2-3B by 3.8 points with no examples in the prompt and leads by 16.6 with two. Across four benchmarks, averaging the two settings names one winner for 15 of 16 such reversals. We compare models within each setting, controlling family-wise error asymptotically in the number of items for a fixed prompt grid. Aligning embedding coordinates across seeds raises held-out per-dimension reliability from 0.003 to 0.813.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38013

Where Can We Fool the Model's Mind? Response-Guided Semantic Probing and Adaptive Routing for Transferable Attacks on Black-Box MLLMs

Ahmed Abdelnaby, Mohamed Elmahallawy

原文摘要

Multimodal Large Language Models (MLLMs) ground language in visual evidence, yet their semantic reasoning can be exploited through transferable black-box adversarial attacks. Existing attacks typically allocate perturbations using surrogate-model saliency, which may not reflect how an unseen MLLM semantically interprets or relies on different image regions. We introduce VISTA (Vulnerability-Informed Semantic Transfer Attacks), a black-box framework that identifies semantically vulnerable visual regions from an MLLM's responses without access to gradients, logits, parameters, or internal representations. VISTA supports two attack settings: (i) VISTA-Proxy, a pure-transfer setting that probes an open-source MLLM and transfers the resulting adversarial examples to unseen commercial MLLMs without querying them; and (ii) VISTA-Victim, a query-assisted setting that probes the target MLLM to capture model-specific semantic vulnerabilities. VISTA builds an Uncertainty-Based Multimodal Behavior (UBMB) map from response drift, conflict, misleading, and semantic shifts, then uses entropy-adaptive Sinkhorn routing and a surrogate ensemble to focus perturbations on vulnerable regions. Across GPT-5, Gemini-3.5-Flash, and Claude Sonnet 4.6, VISTA achieves up to 97 % attack success rate (ASR) while maintaining a Peak Signal-to-Noise Ratio (PSNR) above 30 dB. Notably, VISTA-Proxy achieves up to 93 % ASR without querying the final victim, demonstrating that response-derived semantic vulnerability can enable effective transfer across heterogeneous MLLMs.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.36448

Theory on Attention Dynamics for Out-of-Distribution In-Context Learning

Junze Deng, Daouda Sow, Sen Lin, Yingbin Liang

原文摘要

Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. However, their performance often deteriorates when encountering out-of-distribution (OOD) inputs that deviate from the training distribution, and the underlying theory remains poorly understood. To fill this gap, we characterize the OOD error under the input distribution shift through the interplay between the dynamics of the so-called $α$-type and $β$-type attention weights, which represent the transformer's confidence in identifying the correct and incorrect features, respectively. Our results indicate that the OOD error for each feature depends on all pairwise interactions between the training features and OOD features, and under certain cases the transformer performs no better than random guessing. To improve the OOD generalization performance, we next investigate the impact of model fine-tuning with the OOD data, and particularly, characterize the model forgetting performance on the source domain. Interestingly, the performance on the source domain may not always degrade after fine-tuning, which highly depends on the nature of the feature shift: fine-tuning on OOD domain keeps enhancing the confidence of identifying correct features from the original distribution, while the interference from other incorrect features may either increase or decrease. Extensive experiments on both synthetic and real data are conducted to corroborate the theoretical insights.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38012

Finite-step statistical mechanics of scale-invariant learning: spectral equations of state and curvature transport

Alexander Itin

原文摘要

Stationary learning admits an ideal-gas description under restrictive noise assumptions. In neural networks whose gradient noise departs from these assumptions, however, an entropy-scaling relation resembling a Maxwell relation remains approximately valid. We ask which thermodynamic-looking relations follow from scale symmetry rather than equilibrium, and how departures from the ideal-gas description can be quantified, for discrete stochastic gradient dynamics with memory. An exact rescaling of trajectories explains the entropy relation without assuming thermal equilibrium. Within a local harmonic approximation, self-adjusting weight norms yield a spectral equation of state whose virial coefficients are set by moments of the curvature spectrum, and coupled parameter groups can sustain stationary probability currents. Our central result beyond this approximation is an exact curvature-transport identity. Together with a finite-step loss balance, it decomposes corrections to the harmonic fluctuation relation into measurable curvature changes, finite-step remainders, gradient-memory correlations and finite-window drift terms. A related displacement-weighted curvature change provides a diagnostic of the arrow of time; its mean and second moment give a lower bound on the relative entropy between forward and reversed state pairs. We also calculate the activation-boundary contribution to curvature for rectified teacher-student networks with Gaussian inputs. Tests in sphere models, teacher-student networks and convolutional networks on CIFAR-10 and CIFAR-100 support the transport description and identify limits of the harmonic and cubic-remainder approximations. These results separate symmetry-based relations from equilibrium assumptions and provide quantitative diagnostics of nonideal fluctuations in learning dynamics.

cond-mat.stat-mech · cond-mat.dis-nn · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38009

Large Language Models for Accurate Medical Chart Abstraction: Enabling Scalable and Secure Artificial Intelligence Deployment in Stroke

Zhusi Zhong, Carl M. Porto, David Hong, Miranda Gonzales, Revyn Kim, Gnaneswari Karayi, Lulu Bi, Joshua R. Feler 等 16 位作者

原文摘要

Medical chart abstraction transforms unstructured clinical narratives into structured variables for research and quality monitoring. We evaluated a prompting-based large language model (LLM) framework for extracting eight clinical variables from 2,416 neurointerventional acute stroke intervention reports across three hospitals. Twenty-two instruction-tuned open-source LLMs were evaluated across architectures, model sizes, and biomedical adaptations using Quick Response and Chain-of-Thought (CoT) prompting. Non-expert staff annotations served as the cross-model reference standard. Evaluation was restricted to report-variable pairs with a valid LLaMA3.3-70B CoT prediction and a corresponding reference label. Performance measures included extraction accuracy, inference latency, and agreement with expert adjudication. Twenty discordant cases per variable underwent review by two senior physicians and four medical students. LLaMA3.3-70B achieved the highest overall accuracy (94.8%). CoT improved performance on inference-dependent variables such as site of occlusion, while Quick Response was optimal for directly stated procedural fields. Expert adjudication showed that AI predictions were more closely aligned with expert interpretations than non-expert annotations for most variables, with intracranial angioplasty remaining a challenge. Locally deployed LLMs can support scalable clinical information extraction and retrospective stroke registry curation, with expert oversight for ambiguous cases.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.01896

OutageDiT: A Foundation Model for Power Outage Forecasting and Scenario Generation

Yunqin Zhu, Feng Qiu, Yao Xie

原文摘要

Power-outage planning requires scenarios before an event occurs. These scenarios must represent uncertainty in magnitude, timing, and duration while preserving temporal dependence. However, severe events are rare, and data from any single region contain few examples of extreme outage and restoration patterns. To address this challenge, we introduce OutageDiT, a foundation model for generating seven-day outage trajectories at 15-minute resolution, trained on outage and weather records across the United States. Specifically, a condition encoder processes historical context and known future covariates once per forecast, and a shallow flow-matching decoder reuses the resulting horizon-aligned states to sample complete outage trajectories. This enables point forecasting, uncertainty quantification, and conditional scenario generation within one deep generative model. Across outage forecasting benchmarks, OutageDiT improves forecast accuracy and scenario quality over strong baselines and supports zero-shot transfer to held-out regions. Together, these results position conditional outage scenario generation as a bridge from outage forecasting to operational planning under uncertainty.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38008

Making Smart Homes Fit for Autistic Children: Family Work and Monitored Independence

Tingting Xiang, Weihan Jiang, Hrishitva Patel, Haiqi Shen, Tianzhi He, Kyrie Zhou

原文摘要

General-purpose smart-home technologies are increasingly present in family life, yet how they support or disrupt autistic children and families with autistic children remains underexamined. We conducted a multi-source qualitative study drawing on five caregiver interviews, Xiaohongshu (also known internationally as RedNote) posts explicitly situated in autism contexts, and contextual posts from Xiaohongshu and Weibo. We find that families create support for autistic children by adapting environmental outputs, prompts, and interaction channels, while sensory intensity, communicative rules, and opaque operating states can turn the same technologies into barriers. Support also depends on continuing family work, including translation, configuration, modification, maintenance, and boundary-setting. Remote monitoring enables conditional independence while generating tensions among safety, privacy, and control. We contribute three concepts, including relational fit, family work as support infrastructure, and monitored independence, for understanding accessible domestic technology. We derive design implications for adjustable interaction, legible and recoverable failure, lower-burden configuration, and negotiable monitoring.

cs.HC · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.07329

Large scientific teams are more, not less, disruptive

Junming Huang, Yu Xie

原文摘要

Modern science has moved decisively toward larger and more collaborative research teams. Yet an influential 2019 study reported that small teams are more disruptive than large teams, a conclusion difficult to reconcile with both the well-known trend toward increasing collaboration and the disproportionately large teams behind widely recognized disruptive research, such as work that has been awarded Nobel Prizes. Here we show that the reported disruptive advantage of small teams is largely an artifact of measurement rather than a fact about teams. Analyzing about 60 million scientific publications, we find that larger teams cite more references and that the standard disruption index declines mechanically as reference lists lengthen. Equalizing reference-count distributions across team sizes reverses the negative gradient within the index's own framework. Evaluating each paper against one reference at a time yields a reference-robust measure that distinguishes recognized breakthroughs from ordinary papers more sharply and more consistently than the standard disruption index across six independently curated benchmarks, including the Nobel Prize. Under this validated measurement, scientific disruption increases with team size across four scientific domains and in every decade from the 1970s to the 2010s. For scientific publications, we conclude that larger teams are more, not less, disruptive.

cs.DL · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38007

Frequency-Adaptive Gaussian Grids for Efficient Image Representation

Anatolii Evdokimov, Stavros Diolatzis, Bingxuan Li, Akshay Jindal, Patsorn Sangkloy, Qi Sun

原文摘要

Neural representation has emerged as a powerful tool to mitigate the demand for increasingly higher-resolution images. However, a fundamental trade-off remains between structured (e.g., feature grids, which offer spatial consistency) and unstructured (e.g., 2D Gaussians, which adaptively capture local variances) representations. This choice significantly affects how well an algorithm represents an image. Here, we present Gaussian-Grid, a hybrid neural representation that adaptively integrates structured and unstructured primitives. By dynamically partitioning computation between 2D Gaussian distributions and their attached multi-resolution feature grids based on the local frequency content, Gaussian-Grid automatically optimizes its architecture to match the underlying complexity of the target signal. We evaluate our approach using high-resolution natural images and demonstrate its applications as GPU-native dataset storage, showing $1.24$-$2.14\times$ decoding speed improvement and PCIe data traffic reduction of $23\times$-$176\times$ over JPEG + ZIP data archiving. The results show that Gaussian-Grid maintains small memory footprints while achieving high reconstruction fidelity across a variety of datasets.

cs.CV · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38006

Algorithmic Bias from the Perspectives of Healthcare Professionals

Jennifer Xu, Tamara Babaian

原文摘要

This paper focuses on algorithmic bias of machine learning and artificial intelligence applications in healthcare information systems. Based on the quantitative data and qualitative comments from a survey and interviews with healthcare professionals, who have different job roles (e.g., clinical vs. administrative), this study provides findings about the relationships between algorithmic bias, perceived fairness, and the intended acceptance and adoption of ML algorithms and algorithm generated outcomes. The results suggest that the opinions of healthcare professionals toward the causes of algorithmic bias, the criteria of algorithm assessment, the perceived fairness, and bias mitigation approaches may vary depending on their job roles, perspectives, tasks, and the algorithm characteristics. More research is needed to investigate algorithmic bias to ensure fairness and equality in healthcare.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38005

"It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI

Dana Serditova, Kevin Tang, Jochen Steffens

原文摘要

Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations and how regional voices produced by voice assistants (VAs) are evaluated through a sociolinguistic lens. This study investigates these issues among speakers of Newcastle English (Geordies), examining both linguistic accommodation to voice technologies and perceptions of regional versus mainstream-accented VA voices. Participants interacted with a simulated VA that spoke either Newcastle English or Standard Southern British English (SSBE). They subsequently completed semi-structured interviews about their experiences with the experimental VA and voice technologies, language use, accent attitudes, and place orientation. The findings reveal a two-way process of sociolinguistic bias. The Geordie VA was associated with familiarity, warmth, personality, and local belonging, but also with concerns about professionalism and authority, whereas the SSBE voice was perceived as more neutral, clear, and credible. Participants also reported adapting their speech when voice technologies failed to recognise them, most commonly by shifting to a more mainstream accent, enunciating more clearly, and speaking more slowly. These strategies are similar to accommodation in human-human interaction and reflect users' perceptions of what technologies can recognise, also known as perceived intelligibility pressures. Overall, the findings demonstrate that voice technologies can reproduce existing accent biases both by encouraging users to suppress regional features and by activating established social stereotypes through synthetic voices. The study positions sociolinguistics as a bridge between understanding human-AI interaction and designing inclusive technologies around users' own linguistic priorities.

cs.HC · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38004

Opportunistic Optical Link Scheduling in the Scalable Matching Model

Marcos T. Henriques, Olga Goussevskaia

原文摘要

The Scalable Matching Model (SMM) is a useful abstraction for reconfigurable datacenter networks. In SMM, a set of $n$ (Top-of-Rack) electrical packet switches is connected via a set of optical circuit switches (OCS), each realizing a $p \times p$ matching, where $p$ is the number of ports per switch. In the case when $p \ll n$, bounded-degree networks utilize only a small portion of the OCS infrastructure at each point in time, especially when traffic patterns are skewed and bursty. In this work, we propose the Opportunistic Optical Link Scheduling (OOLS), a set of lightweight OCS link scheduling routines, designed to augment bounded-degree reconfigurable network topologies by leveraging idle OCS resources. We evaluate the performance of OOLS in the SMM through simulations, using synthetic and real-world data-center workloads. Our simulation results show that OOLS substantially improves performance, lowering communication costs and boosting throughput.

cs.NI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38003

Are Seismic Foundation Models More Than Glorified Feature Extractors?

Laura Laurenti, David Liu, Brian Kulis, Men-Andrin Meier, Christopher Johnson

原文摘要

Earthquake sequences are stochastic on two separated timescales: the seismic waves of any individual earthquake propagate over seconds to minutes, while the earthquakes themselves arrive as a sparse, self-exciting occurrence process, with inter-event intervals from seconds to months. Respecting both scales in one training objective is the open challenge. Foundation models (FMs) for seismic waveforms instead import their learning targets from audio and vision, where every target is computed from a single fixed-length window. Such a window holds one realization of the wave propagation (an earthquake trace), never the occurrence process that decides when earthquakes happen. We develop nine model designs sharing one Mamba encoder-decoder, trained on a fixed corpus of 3M windows, varying the self-supervised objective, quantization bottleneck and mixer; the two key comparisons are architecture-matched, varying the objective alone. Each checkpoint is evaluated frozen on three downstream tasks. Varying the target redistributes downstream skill rather than raising it, and no checkpoint wins everywhere. Adding masking pressure to our strongest classifier re-specializes it rather than making it a generalist: it gains 6.9 points of few-shot P-wave picking precision and loses 9.6 points of few-shot classification accuracy. By the standard imported from language and vision, these models are feature extractors rather than FMs. Controls on capacity, architecture, and domain proximity do not explain why skill moves rather than rises. Against task-specific baselines the advantage is regime-dependent: our checkpoints beat them few-shot on classification and ground-motion prediction, and trail them on full data. We argue the binding constraint is the target, and that settling the question requires a learning target defined across events, the timescale that makes seismicity stochastic in the first place.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38002

New Multiple Descent Phenomena Induced by Heterogeneous Data

Mark-Anthony Moisescu-Pareja, Elvis Dohmatob

原文摘要

Modern machine learning models are often trained on large datasets assembled from many different sources, whose statistical properties can differ substantially. Understanding how this heterogeneity affects generalization performance is therefore important for explaining how model performance changes as model size increases. In this work, we study this question in linear random-feature models and show that mixtures of datasets with different covariance structures can give rise to a range of multiple-descent phenomena. We derive exact asymptotic expressions for the test error of each data source in the high-dimensional regime, and show how heterogeneity in covariance scale and spectral structure can introduce additional, group-dependent interpolation thresholds as model size increases. These phenomena arise even with noiseless labels and linear activations, showing that neither label noise nor activation nonlinearity is necessary for multiple-descent. Our results therefore provide a different perspective from classical explanations of multiple descent. More broadly, our results have potential implications for algorithmic fairness by showing that model scaling can affect different data groups unevenly, amplifying disparities in their generalization errors. We validate our theoretical results on synthetic Gaussian mixtures and real-world datasets, including MNIST and CIFAR-10.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.38001

Preserving Safety During Sequential Fine-Tuning: A Factorial and Geometric Analysis of Replay

George Ruellan, Diana Benavides-Prado

原文摘要

Benign fine-tuning can erode safety alignment in large language models, and sequential adaptation substantially compounds this risk. Prior work mitigates this erosion by replaying harmful-prompt refusals and benign-compliance examples, while other work instead matches base-model logits via distillation. However, the individual contributions of supervised exposure and distillation to safety behavior and refusal geometry during sequential adaptation remain unclear. We factor these two strategies apart and study their behavioral and geometric effects during sequential LoRA fine-tuning of Mistral-7B and Llama-3-8B across diverse task sequences (code generation, German-language summarization, and science question-answering). Behaviorally, supervised replay exposure yields the largest reduction in HarmBench attack success rate (ASR) on Mistral, averaging 51.1 points below base, but at a substantial over-refusal cost, averaging 53.4 points above base on OR-Bench-hard. Logit distillation, without any supervised replay loss, largely prevents safety erosion at a fraction of this cost: an average 5.4-point ASR reduction against only a 5.1-point rise in over-refusal. Llama shows the same asymmetry between the two strategies. Combining exposure and distillation moderates exposure's over-refusal while leaving downstream task scores largely unaffected. Geometrically, the two models diverge: on Mistral, distillation preserves the base refusal direction more closely than exposure does, whereas on Llama, refusal behavior after exposure largely survives ablation of the extracted refusal direction. This dissociation between models indicates that preserving the base refusal direction is not a reliable proxy for behavioral safety.

cs.LG

查看论文
arXiv ↗PDF ↗