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

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 06:11 — 2026-11-18 06:11(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:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 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。

25,786 已收录论文21,491 AI 相关7,725 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 5,970 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.20334

Residual-Tail-Informed Flow Matching for Time Series Anomaly Detection

Shyam Sundar Saravanan, Tie Luo, Sanjay Madria

原文摘要

Time series anomaly detection (TSAD) models are often trained on nominal data using average-risk objectives, which emphasize dominant normal patterns. However, real time series can contain rare but valid nominal regimes that are underrepresented in the training distribution. We show that data-space flow matching can over-penalize such rare-normal windows and assign them anomaly scores comparable to those of true anomalies. To address this, we propose Residual-Tail-Informed Flow Matching (RT-FM), an unsupervised framework that uses a temporal variational autoencoder to estimate residual latent tailness and converts it into bounded, warmup-annealed weights for training a data-space flow matching model. Experiments on seven TSAD benchmarks show that RT-FM improves rare-normal coverage while preserving strong anomaly discrimination, substantially reducing false alarms on such windows and resulting in improved aggregate detection performance. The code is available at: https://github.com/trustAIoT/RT-FM_time-series-anomaly

cs.LG · cs.AI

新论文 · v1arXiv:2611.20331

LENS: Replacing LayerNorm and Softmax in Transformers with Learnable Normalization States

Yuhao Liu, Salim Ullah, Akash Kumar

原文摘要

LayerNorm and attention Softmax are critical operations in Transformers. However, they cannot be efficiently mapped to General Matrix Multiplication (GEMM) computations on hardware. Therefore, modern hardware accelerator designs, such as NPUs on ASIC/FPGA, consume a large amount of hardware resources or chip area to implement their specific arithmetic units. Building on previous work about LayerNorm, Softmax, and their alternatives, we introduce Learnable Normalization States (LENS), a framework that reformulates LayerNorm as tiny MLPs by abstracting a common structure from related methods and extends this method to Softmax, which moves more of the computation in Transformers to GEMM as a hardware-friendly architecture. We evaluate LENS on image classification with Vision Transformers (ViT) and autoregressive language modeling with Pythia models, including generalization tests on WikiText and LAMBADA. Across these tasks, LENS matches or exceeds baseline performance in several vision settings and retains most of the baseline performance in the remaining vision and language experiments. These findings may suggest that hand-designed normalization and attention functions are not the only choice as alternatives to LayerNorm and Softmax. LENS also provides a basis for exploring Transformer architectures for resource-limited accelerators.

cs.LG · cs.AI · cs.AR

版本更新 · v2arXiv:2607.03656

AutoCedar: An Agentic Framework for Verifier-Guided Access Control Policy Synthesis

Adarsh Vatsa, Sachi Shome, Yingming Zhou, William Eiers

原文摘要

Large Language Models are increasingly used to turn natural-language requirements into code. In access control, that shortcut is dangerous: a generated policy can compile and read correctly while granting access that no one approved. The difficulty is not only writing policy code. It is fixing what the requirements mean before code is written, and then checking that the final policy actually satisfies that intent. We present AutoCedar, a verifier-guided system that first turns natural-language access-control requirements into a reviewed, checkable target, and then synthesizes Cedar policies against that target. AutoCedar decomposes schema and policy authoring into small intent atoms: reviewable claims about vocabulary and behavior. Once those atoms pass mechanical validation and human intent review, the model proposes a candidate policy, the verifier checks it against the approved target, and each failure is turned into a repair signal that tells the model whether to broaden, narrow, or restructure the policy without changing the target. Because the model's work is split into small problems, each grounded in reviewed intent and backed by verifier feedback, end-to-end policy authoring becomes tractable. AutoCedar converges on all 221 tasks of CedarBench, our benchmark of authorization tasks paired with executable semantic boundaries. Across three requirements-corpus case studies covering healthcare, education, and conference management, AutoCedar converts noisy prose and extracted access-control fragments into reviewed schemas, formal checks, and a globally verified Cedar policy store for each scenario.

cs.SE · cs.AI · cs.CR

版本更新 · v2arXiv:2605.17671

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment

Michael Arbel, Basile Terver, Jean Ponce

原文摘要

Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its stability: non-collapsed stable equilibria align with leading nonlinear canonical correlation subspaces, while collapsed equilibria may also be stable attractors. Motivated by this result, we introduce PEIRA, a non-contrastive SSL method with an explicit objective defined through the trace of the optimal linear regressor. We show that its only stable equilibria are nontrivial global minimizers and recover the same canonical correlation subspaces, with regularization selecting the effective dimension. Experiments on ImageNet-1K and CIFAR-10 show PEIRA is competitive with VICReg and LeJEPA baselines, and qualitative empirical results support the theory. Project page: https://peira-ssl.github.io. Code: https://github.com/MichaelArbel/peira-loss (loss implementation), https://github.com/Basile-Terv/PEIRA (experiment reproduction).

cs.LG · cs.AI

版本更新 · v3arXiv:2509.26305

Feedback Forensics: A Toolkit to Measure AI Personality

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Robert Mullins

原文摘要

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic checks struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ranking multiple model responses relative to each other. Recent issues with model releases highlight limitations of these existing opaque evaluation approaches: goblin-obsessed, sycophantic and generally over-the-top personalities have resulted in model rollbacks and extensive media coverage. Despite these known issues, limited public tooling exists to explicitly evaluate model personality. We introduce Feedback Forensics: an open-source toolkit to track AI personality and related behavioural traits, both those encouraged by human (or AI) feedback, and those exhibited across AI models trained and evaluated on such feedback. Feedback Forensics is adaptive and can automatically find new traits appearing in models. We demonstrate the toolkit's usefulness in two steps: (A) first we analyse the personality traits encouraged in popular human feedback datasets including MultiPref, PRISM and data from Chatbot Arena; and (B) then use our toolkit to analyse how much popular models exhibit such traits. We release (1) our Feedback Forensics toolkit alongside (2) a web app tracking AI personality in popular models and feedback datasets and (3) the underlying annotation data, see https://github.com/rdnfn/feedback-forensics.

cs.CL · cs.AI

新论文 · v1arXiv:2611.20321

Unreasonable Confidence from Simulator Misspecification: Directional Robustness on the SPEED+ Sim-to-Real Benchmark

Nikolay Dolgov

原文摘要

Vision-based navigation systems for orbit must be trained almost entirely on synthetic imagery, because real labelled images of a given spacecraft in flight rarely exist. Benchmarks like SPEED+ are built for that situation: the training set comes from a simulator, and the test sets are real images of a satellite mockup under two kinds of lighting. That simulator approximates how light reflects off mylar and aluminium, and like every scientific simulator it is misspecified. Its error is radiometric, since it misses the specular highlights, hard shadows and sensor saturation common in real images. We probe the resulting synthetic-to-real gap, the central risk for such systems, with a deliberately simple monocular pose estimator. In a 2x2 study of backbone adaptation and photometric augmentation, trained on synthetic images and tested on both real hardware-in-the-loop domains, we find three things. (1) The model does not know it is failing: regions conformally calibrated to 90% on synthetic data cover only 9-15% of rotation errors on sunlamp and 21-38% on lightbox, so a wrong pose carries the confidence of a correct one. (2) Transfer is asymmetric: scaling data and features improved synthetic rotation error from 1.65 to 1.03 rad but moved the harshly lit sunlamp domain by only 0.05 rad, under twice its seed s.d., whereas adapting the backbone's last stage carried 63-83% of its extra synthetic gain to both real domains. (3) Once the backbone adapts, augmentation helps only in the direction it models: our photometric stack improved the diffusely lit lightbox domain from 1.17 to 0.99 rad on every seed but moved sunlamp no more than seed-to-seed variation, while with the backbone frozen it helped sunlamp more. Every post-review experiment was pre-registered, and the code, per-image predictions and pre-registration record are at https://github.com/lokindoo/spacecraft-pose-estimation.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.20314

NF-VLA: A Normalizing-Flow Baseline for Vision-Language-Action Learning

Ruichen Deng, Qinyu Zhao, Yong-Hyun Park, Mutian Tong, Liang Zheng, Jiatao Gu

原文摘要

Autoregressive normalizing flows (NFs) provide a tractable density for learning and sampling continuous robot actions. We show that a single maximum-likelihood objective can train vision--language--action (VLA) policies competitive with leading methods on manipulation benchmarks. We present NF-VLA, which combines conditional autoregressive normalizing flows with score-based action refinement. Its deep--shallow architecture concentrates visual, language, and proprioceptive prefix conditioning in a high-capacity deep block, while unconditioned shallow blocks provide a shared invertible action transformation. The vision--language backbone and flow are jointly trained by exact maximum likelihood on Gaussian-smoothed action chunks. The same learned density supplies a single score-based correction at inference, refining generated actions to account for training-time smoothing without a separately trained denoiser. Trained on LIBERO from a pretrained vision--language backbone without robot pretraining, NF-VLA achieves 98.35\% success across the four standard suites and 72.6\% on LIBERO-Plus using the same checkpoint without further fine-tuning. Ablations show that deep-only prefix conditioning and score-based refinement both improve closed-loop success. Together, these results establish carefully structured autoregressive flows as a competitive approach to VLA control, with one learned density supporting policy training, action generation, and refinement.

cs.RO · cs.AI

新论文 · v1arXiv:2611.20301

Multi-output neural network surrogate for double-pulse femtosecond optothermal control of thin silicon films on fused silica

George D. Tsibidis

原文摘要

We introduce a multi-output feedforward neural network surrogate trained on a coupled multiple-reflection and two-temperature model to map double-pulse femtosecond laser excitation (1030 nm) of crystalline silicon films on fused silica across film thicknesses (50-500 nm) and inter-pulse delays (0-10ps). Trained via Levenberg-Marquardt optimization on 2000 physical simulations, the dual-hidden-layer network ([40,30] neurons) simultaneously predicts six strongly coupled optothermal observables, peak electron temperature, peak lattice temperature, peak carrier density, minimum and maximum absorptivity and minimum refractive index achieving coefficients of determination R2 larger than 0.9998 across all targets. Evaluating a dense 200 by 200 design grid in milliseconds resolves pronounced thin-film interference fringes and carrier-induced index modulation, identifying an optimal optothermal coupling regime at d=156 nm and Dt=4.572 ps. This unified machine-learning workflow eliminates computationally expensive multi-physics runtime bottlenecks for real-time laser processing control and inverse photonic thin-film design.

physics.optics · cond-mat.dis-nn · cond-mat.mtrl-sci · cs.AI

版本更新 · v2arXiv:2611.12508

MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection

Ahmed Y. Radwan, Shaina Raza

原文摘要

Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43\%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99\% AUROC on GenVideo and 75.50\% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: https://vectorinstitute.github.io/mars/ Github: https://github.com/VectorInstitute/mars

cs.CV · cs.AI

版本更新 · v2arXiv:2605.06288

A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs

Alexander G. Reisach, Antoine Chambaz, Gilles Blanchard, Sebastian Weichwald

原文摘要

Random directed acyclic graphs (DAGs) based on imposing an order on Erdős-Rényi or scale-free graphs are widely used to generate synthetic data from causal models, in particular for evaluating causal discovery algorithms. We show that the set of nodes reachable via open paths, termed relatives, never decreases along the causal order in all DAGs. We find that it tends to increase strictly for DAGs with certain density parameters, and demonstrate that this pattern can be exploited for causal discovery via sorting by the estimated number of relatives. We note that many simulations in the literature are focused on a narrow range of parameter settings where sorting by relatives yields an excellent proxy for the causal order, and show that a strict increase of relatives leads to a singleton Markov equivalence class. We propose sampling time-series DAGs as a possible alternative and discuss implications for causal discovery and synthetic data generation. Implementations of our algorithms can be found at https://causaldisco.github.io/CausalDisco/.

stat.ME · cs.AI

版本更新 · v4arXiv:2608.27296

LLMs Can Design Near-Optimal OR Algorithms

Jackie Baek

原文摘要

We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization, using benchmark instances from recent papers in each area. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an algorithm that maps instance parameters to solutions. Human input is minimal: we give one untuned prompt that describes the problem, and the model has access to a Python sandbox tool with a fixed compute budget. The strongest model we test, gpt-5.6-sol, matches or outperforms the best method reported in those papers on almost all evaluated instances. This holds even at level 2, where the returned algorithm is fixed before seeing the evaluation instances. Performance also improves sharply across models released less than eight months apart, suggesting that this capability is moving quickly. Thus, for the well-specified operations problems we study, a single untuned LLM query can already produce algorithms competitive with specialized methods. These results suggest that frontier LLMs can be a serious empirical baseline for algorithm design in well-specified OR problems.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.13058

The Indic Token Tax in 2026: Measuring Tokenizer. Disparity and Its Cost for the Languages of India

Johin Johny Arimbur, Ankur Ashit Ghosh, Shervin Sam

原文摘要

Commercial language model APIs bill per token, so a tokenizer that needs more tokens for the same content in one language makes that language more expensive, slower, and able to fit less text in a fixed context window. We measure this disparity for nine public tokenizers, including those of GPT-4, GPT-4o, Qwen2.5, DeepSeek-V3, Mistral-Nemo and four Sarvam models, on all 25 languages of India available in FLORES-200 (2,009 professionally translated sentences aligned with English) and on 13,732 human-translated Hinglish-English social media pairs from PHINC. On GPT-4o's tokenizer the same content needs between 1.57 times (Hindi) and 5.01 times (Odia) the tokens of English, and 13.7 times for Santali in Ol Chiki script; GPT-4's tokenizer needs up to 12.8 times. Sarvam-30B/105B is the only third-party tokenizer that stays below 2.6 times on every language (median 1.53). In an illustrative scenario using official list prices accessed on 5 November 2026 and stated assumptions, a support bot handling 100,000 chats a month on GPT-4o would cost about INR 56,640 in English and INR 102,829 in Marathi; these are estimates, not measured production costs. Against an openly licensed Hindi and Marathi morphological segmentation set, no tokenizer places more than 35% of its word-internal boundaries on morpheme boundaries (boundary F1 at most 0.48). In a companion paper we present a tokenizer that reduces this tax. Code, pinned artifacts and raw token counts are available at https://github.com/HavonAI/indic-token-tax.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.13059

A Multi-Word Tokenizer for 204 Languages That Needs Fewer Tokens Than GPT-4o's, Including on English

Johin Johny Arimbur, Ankur Ashit Ghosh, Shervin Sam

原文摘要

Languages of India need 1.6 to 14 times as many tokens as English on GPT-4o's tokenizer for the same content, which makes them more expensive and slower to serve. We train tokenizers from scratch on human-written text in about 200 languages. Havon v3 is a byte-level BPE tokenizer with 262,144 tokens and a pre-tokenizer that keeps combining marks with their letters and chunks scripts written without spaces. On FLORES-200 devtest it needs fewer tokens than GPT-4o's o200k_base on all 25 languages of India (median 0.74 of GPT-4o's count) and on 172 of 204 languages, but 7% more on English. Havon v4 adds a second, multi-word training stage (SuperBPE) to v3. At exactly GPT-4o's vocabulary size of 200,019 tokens, v4 needs 6.1% fewer tokens than GPT-4o on English and fewer on 161 of 204 languages and all 25 languages of India (median 0.74); at the same size, v3 needs 9.4% more on English and wins on 133. With 262,144 tokens, v4 needs 9.6% fewer tokens on English and fewer on 182 of 204 languages, and with 524,288 tokens it needs fewer on 203 of 204. The gains are largest for English, Hindi and the Romance languages; scripts without spaces, such as Khmer, Burmese and Tibetan, gain little and lose subword merges. Havon v5 replaces v4's Python-only code sample with permissively licensed code in 15 languages: on code it needs 1.03 to 1.22 times GPT-4o's tokens, against 1.11 to 1.29 for v4, while keeping all 25 languages of India (median 0.74, all significant under a sentence-level bootstrap) and English (0.94). These are compression results only: we have not yet evaluated a model trained with v4 or v5.

cs.CL · cs.AI

版本更新 · v4arXiv:2605.07161

SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios

Jackson Clark, Yiming Su, Saad Mohammad Rafid Pial, Yifang Tian, Lily Gniedziejko, Hans-Arno Jacobsen, Yinfang Chen, Tianyin Xu

原文摘要

AI agents are increasingly used to diagnose and mitigate failures in production systems, known as agentic Site Reliability Engineering (SRE). Current SRE benchmarks are limited to oversimplistic SRE tasks and are unfortunately hard to extend due to bespoke designs. We present SREGym, a high-fidelity benchmark for SRE agents. SREGym exposes a live system environment built atop real-world cloud-native system stacks, where high-fidelity failure scenarios are simulated through fault injectors. SREGym models the complexity of production environments by simulating (1) a wide range of faults at different layers, (2) various ambient noises, and (3) diverse failure modes such as metastable failures and correlated failures. SREGym is architected as a modular, extensible framework that orchestrates fault and noise injectors across stacks. SREGym currently includes 90 realistic, challenging SRE problems. We use SREGym to evaluate frontier agents and show that their capabilities varies significantly in addressing different kinds of failures, with up to 40% differences in end-to-end results. SREGym is actively maintained as an open-source project and has been used by researchers and practitioners.

cs.AI

新论文 · v1arXiv:2611.20289

Benchmarking LLM Inference on Desktop-Scale NVIDIA Grace Blackwell Clusters

Kevin Bhimani, Christian Escobar, Daniel Mihovch, Rudolf Eigenmann, Sunita Chandrasekaran

原文摘要

Two NVIDIA DGX Spark GB10 systems connect directly over 200 GbE to serve larger language models and increase inference capacity, but the benefits depend on how they are deployed. We benchmark 17 open-weight checkpoints spanning dense and mixture-of-experts architectures, 8B to 235B parameters and four weight precisions on one and two RDMA-connected systems. Using vLLM, we compare tensor parallelism (TP=2), pipeline parallelism (PP=2) and a two-replica baseline at concurrency 1 to 64, with three independent launches per configuration. TP=2 delivers a median 1.59x peak-throughput gain over one Spark, versus 1.39x for PP=2 and has higher throughput in 93 of 96 matched comparisons with separated 95% Welch intervals. It reduces unloaded inter-token latency to 0.52x to 0.73x of one Spark, whereas PP=2 provides little reduction. TP=2 also achieves the highest goodput under a strict 100 ms inter-token latency objective wherever both strategies are supported and the objective is met. For models fitting on one Spark, TP=2 generally favors low-concurrency serving, while replication offers higher throughput at high concurrency. One Spark uses less GPU energy per output token at matched concurrency. Across three precision ladders, NVFP4 reduces unloaded latency more than adding a second Spark at BF16. NCCL microbenchmarks and comparisons with an earlier TCP campaign suggest that collective communication overhead contributes to the advantage of TP=2. These results provide deployment guidance for desktop-scale inference.

cs.DC · cs.AI

新论文 · v1arXiv:2611.20288

Protecting Safety during Reasoning Training with Low-Rank Fisher Regularisation

Neel Rajani, Ivan Titov

原文摘要

Large language models are trained to have safety guardrails, but these can be compromised while fine-tuning for new capabilities, such as reasoning. One way to mitigate this degradation is to modify the fine-tuning objective to preserve safety behaviour, but doing so effectively and efficiently remains challenging. We revisit Elastic Weight Consolidation (EWC), which penalises parameter updates based on sensitivity estimates from the diagonal of the Fisher information matrix (FIM). While EWC provides some protection, the diagonal approximation ignores interactions between parameters. We address this limitation by exploiting recent findings that safety-relevant behaviour is located in a low-rank subspace within models. Our method, Subspace-Projected Elastic Weight Consolidation (SP-EWC), projects gradients onto this subspace to capture non-diagonal curvature efficiently. We investigate three different ways of identifying the safety subspace: through safety fine-tuning updates (LoRA), safety-related activations (ActSVD), and contrastive representations of safety and utility data (cPCA). We find that this choice substantially affects performance, with SP-EWC using cPCA comparing favourably against existing methods by better maintaining safety guardrails without introducing excessive over-refusal.

cs.LG · cs.AI

版本更新 · v3arXiv:2605.27380

BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision

Yi Wang, Corina Dima, Liangyu Zhong, Steffen Staab

原文摘要

Cross-lingual biomedical entity linking (BEL) maps mentions in any language to unique identifiers in a biomedical knowledge base, supporting clinical and biomedical NLP applications. We identify two issues affecting current systems. First, the UMLS (Bodenreider,2004) aliases used to train cross-lingual BEL retrievers are heavily skewed toward English, so retrievers generalize poorly to non-English mentions. Second, although context is often necessary for disambiguation, naively injecting context into retrievers trained only to align aliases severely degrades retrieval. We propose BioELX, a retrieve-rerank framework that addresses both issues. For retrieval, we continue training SapBERT_multi (Liu et al., 2021b) using Wikidata-derived cross-lingual alias supervision, forming shared concept neighborhoods across languages. For reranking, we adapt pretrained LLM rerankers to entity linking through mention-anchored prompting, which marks the target mention so that rerankers score candidates with respect to the intended mention rather than other salient tokens in the context. Experiments show that BioELX achieves new state-of-the-art results on four cross-lingual BEL benchmarks, improving Recall@1 by 4.8 to 18.2 percentage points over prior best results, without any task-specific BEL annotations. Our code and resources are available at https://github.com/AI4MedCode/BioELX.

cs.CL · cs.AI

新论文 · v1arXiv:2611.20269

Self-supervised learning for zebrafish embryo phenotype evaluation: Systematic comparison of algorithms, label-efficient classification, and transfer learning

Thomas Lautenschlager, Gaëlle Hayot, Quentin Brassart, Angelo Jovin Yamachui Sitcheu, Linus Schilpp, Tijana Geroski, Tetyana Goldanova, Stephan Allgeier 等 13 位作者

原文摘要

Zebrafish embryos are a prominent model organism for image-based phenotyping and especially suited for large-scale imaging studies, for which machine learning (ML) models can automate evaluation. However, training ML models usually requires large labeled datasets, and differences in imaging conditions often impede reuse across laboratories. Self-supervised learning (SSL) addresses both constraints by learning transferable representations from unlabeled images. Yet central aspects like the choice of algorithm remain underexplored for domain-specific applications. To close this gap, we benchmark popular SSL algorithms on the public EmbryoNet dataset, explore label-efficient learning, and test transfer to an unseen setting. Using representations from our strongest model, a ResNet50 network trained with SwAV, a simple linear classifier reaches 86.4% accuracy and a non-linear classifier 87.1%, rivaling the fully supervised EmbryoNet model (87.1%). The SwAV model decisively outperforms supervised training from scratch when labels are scarce (70.2% vs. 45.7% accuracy with 5% of labels). On a three-class problem (normal, dead, falsely cropped) with a small, previously unseen zebrafish toxicity dataset, recorded in a different setting, our model reaches 81.3% accuracy without retraining, while EmbryoNet achieves 75.9%. Overall, self-supervised models for zebrafish embryos seem to mostly facilitate label-efficiency and transfer to new settings rather than improving supervised results.

cs.CV · cs.AI · cs.LG

版本更新 · v2arXiv:2609.08736

Axiomatic Positivstellensaetze for Function Algebras over Ordered Fields

Nayoon Kim, Allen Gehret, Shenyuan Ma, Jakub Marecek

原文摘要

Positivstellensaetze furnish algebraic certificates of positivity, and hence of lower bounds and of global optimality, but the classical ones concern polynomials, whereas many problems of current interest, among them the training of neural networks, involve functions that are neither polynomial nor smooth. We isolate an axiomatic core of the constructive Positivstellensaetze of Fischer. The setting consists of an ordered field expanded by five auxiliary function symbols, subject to a few first-order axioms, together with an algebra of functions on an arbitrary set, subject to closure axioms. In this setting we prove a strict and a weak Positivstellensatz in which the witnesses are obtained by substituting the data into fixed terms that depend only on the number of constraints. The framework recovers Fischer's theorems for definable $C^r$-functions, and yields new instances: algebras of definable functions with arbitrary auxiliary functions, such as the binary step function; algebras of continuous functions, for which we give simple sufficient criteria and auxiliary functions derived from common activation functions; and algebras of continuous functions with values in an ordered field that is not closed under square roots, such as $\mathbb{Q}$. We derive certificates of lower bounds and of global optimality, and show that their expanded term length is cubic in the number of constraints for the strict certificate and quadratic for the weak one.

cs.AI

新论文 · v1arXiv:2611.20268

GNN-Based Deep Reinforcement Learning for Coastal Emergency Response under Extreme Water Levels

Marcello Sano, Samuele Casagrande, Davide Ferrario, Sebastiano Vascon, Silvia Torresan, Andrea Critto

原文摘要

When a storm surge approaches a coastal town, the emergency plan must be put into action quickly using water-level forecasts, flood extent, road access, vulnerable residents and shelters. Bringing this information together under time pressure is slow and depends on the duty officer's expertise. This paper is one step in a wider research line from data to safe decisions: machine learning to understand the hazard, reinforcement learning and planning to choose actions, large language models (LLMs) to explain and cross-check them, and an assurance layer that keeps people in charge. Here we address the action step on a real place. We ask whether a policy can learn the timing of emergency actions from decades of real events. Lido di Venezia is represented as a heterogeneous graph built from public elevation, road, building and census data and driven by hourly tide-gauge records from 1983 to 2024, with seven actions taken from the municipal emergency plan. A PPO policy is trained on this graph and compared, on storm windows unseen in training, with a rule-based system simulating the officer's discretionary decisions. On 18 historical test scenarios, PPO achieves a similar reduction in population exposure to the rule. With uncertain forecasts and limited protection it again performs similarly but does not outperform the tuned rule, and removing graph message passing does not substantially reduce performance. PPO therefore learns an effective protective response from an outcome-based reward alone: it is given the plan's actions and when each is allowed, but not the thresholds that tell the comparator when to act. Next steps test harder edge cases, move closer to a digital twin of the territory, and replace the simulated officer with assessment by emergency-management stakeholders, supported by LLM-based interpretation of each recommendation.

cs.LG · cs.AI

版本更新 · v2arXiv:2511.18578

Re(Visiting) Time Series Foundation Models in Finance

Eghbal Rahimikia, Hao Ni, Weiguan Wang

原文摘要

Financial time series forecasting is vital for trading, portfolio optimization, and risk management but is challenged by noisy, nonstationary, and heterogeneous data. Time series foundation models (TSFMs), inspired by large language models, aim to learn transferable temporal representations. Whether pre-training on massive, diverse datasets enables similar generalization to finance remains an open question. This study provides a comprehensive empirical evaluation of TSFMs in global financial markets using large-scale daily excess-return data. We assess zero-shot inference, fine-tuning, and pre-training from scratch against strong benchmarks. Off-the-shelf TSFMs generally perform poorly, while finance-native pre-training improves long-window gross portfolio performance. Larger pre-training datasets and synthetic augmentation improve selected specifications, particularly at longer input windows. Configuration changes have mixed effects across forecasting and portfolio metrics, and TSFMs do not consistently outperform strong benchmarks. These findings caution against uncritical AI adoption in finance, where insufficient validation can lead to unreliable forecasts and substantial financial losses.

q-fin.CP · cs.AI · cs.LG · q-fin.PM · q-fin.PR

新论文 · v1arXiv:2611.20261

Estimating Outpatient Visit Prices from Hospital Price Transparency Data using Large Language Models

Kurmanbek Kaiyrbekov, Nicholas J Dobbins, Sean D Mooney

原文摘要

Objective: Hospital care prices in the United States have increased substantially, yet patients lack effective tools to access and compare costs. We aimed to develop and evaluate an LLM-based approach for improving access to and use of hospital price transparency (PT) data. Materials and Methods: To estimate visit prices, we used a retrieval-augmented generation (RAG) framework to analyze PT files from three major hospitals in Maryland and the surrounding region. We compared BM25, OpenAI embedding models, and a GPT-BM25 hybrid against a no-RAG baseline for cost estimation of individual procedures and procedure groups, then evaluated the best approach for symptom-based visit cost estimation using synthetic simulations. Results: Across hospitals, the GPT-BM25 retriever achieved the best performance, with average price MAPE of 19.44% for individual procedures and 4.90% for groups, compared with 147.98% and 82.82%, respectively, for the no-RAG baseline. In simulations, our framework correctly identified approximately 50% of reference procedures and reduced MAPE relative to the LLM-only baseline at two of the three hospitals, while achieving comparable performance at the third. Discussion: Our framework uses RAG to improve care price estimation in real-world settings. Compared with the no-RAG baseline, it substantially improved cost estimates for both individual procedures and procedure groups. Improvements were smaller in synthetic simulations, likely because inferring procedures from clinical information is more complex. Practical challenges remain, including heterogeneous PT file formats, unexplained duplicate entries, and limited availability of insurer-negotiated rates. Conclusion: LLMs that effectively integrate PT data show strong potential to provide patients with more accessible and accurate healthcare cost estimates.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.20258

Microfitting: Continual Learning via Cached Test-Time Training

Nick Ryan, Peter A. Devine, Ben Sirb, Hannah Sansford, Alex Chiocchi

原文摘要

Continual learning is a promising approach to specialize language models to an organization's private data. However, current methods exhibit a number of drawbacks including catastrophic forgetting, where new training updates overwrite prior knowledge. We present microfitting, which trains and caches a small adapter for each document. Each adapter is trained once, offline, on synthetic questions targeted at demonstrated base-model shortcomings and reused whenever that document is queried. This method borrows from test-time learning literature and sidesteps the problem of continual learning through parameter isolation, allowing the system to specialize on new data without overwriting prior knowledge. The process that generates adapter training data also improves over time, revising its recipe from previous outcomes and fresh examples of the target workload. On DeepSeek V4 Flash, microfitting substantially improves accuracy over the base model. In Enterprise Document Operations (EDO), an open-book Q&A environment over real-world enterprise documents, our method achieves a 38.2% relative improvement over base-model performance. Microfitting makes continual specialization practical and cost-efficient: a frozen model can adapt to an evolving private corpus overnight on local hardware, without modifying the base model or previously cached adapters.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20253

Integrating Latent Block Models into Variational Autoencoders for Disentangled Representation Learning

Anasse Essalih, Reda Khoufache, Laurent Durville, Mohamed-Cherif Rahal, Mustapha Lebbah, Hanene Azzag, Walid Kheriji, Fouad Hadj Selem

原文摘要

We introduce LBM-VAE, a novel framework that integrates Latent Block Models (LBMs) into Variational Autoencoders (VAEs) to jointly cluster observations and latent dimensions. Beyond its clustering capabilities, LBM-VAE provides a block-structured latent representation that naturally supports disentangled representation learning. In contrast to conventional approaches that associate each factor of variation with an individual latent dimension, our framework allows factors of variation to be encoded across groups of latent dimensions. Experimental results demonstrate the promising clustering performance of LBM-VAE, while achieving competitive results in disentangled representation learning. LBM-VAE highlights the potential of combining co-clustering and variational inference to learn structured and interpretable latent representations.

stat.ML · cs.AI · cs.LG

版本更新 · v2arXiv:2611.16726

From Data to Wisdom: Rethinking AI Through an Epistemic Lens

Afonso Eduardo

原文摘要

This paper proposes the Data-to-Wisdom Epistemic Architecture for AI (EAAI), a conceptual framework treating Data, Information, Knowledge, Understanding and Wisdom as five distinct but recursively interacting epistemic functions: observation, contextual interpretation, modeling and prediction, critical evaluation and informed judgment. Two observations motivate it: sequential readings of the Knowledge Pyramid obscure how these functions interact, and a targeted review of twelve Bayesian reference books finds that prior distributions are defined mathematically while "prior information" and "prior knowledge" are not consistently distinguished as epistemic categories. A Bayesian interpretation relates the likelihood, prior and posterior distributions, posterior prediction, model checking and decision analysis to the five functions, without limiting EAAI to Bayesian systems. Extending "prior" in an epistemic sense, the paper distinguishes five kinds of prior context that can shape the model, the likelihood, the prior, evaluation and action. Three worked applications -- quantitative financial risk, actuarial modeling in health insurance and agentic AI for medical reimbursement claims -- show how EAAI structures the analysis of model assumptions, evidence interpretation, validation, dependencies and decision consequences, separating the prediction of a risk, the appraisal of its reliability and the justification of action. It draws implications for AI and machine learning, including evaluation by function, treating intermediate model outputs as evidence open to challenge and separating generation from appraisal, and compares EAAI with work on DIKW, Bayesian workflow, AI evaluation and risk governance. Its contributions are an epistemic vocabulary with recursive relationships, a more accessible reading of Bayesian methodology, a typology of prior context and clearer methodological terminology

cs.LG · cs.AI

版本更新 · v3arXiv:2604.03237

Supporting Calibrated Reliance in AI-Assisted Decision-Making: Different Strategies for Different Tasks

Ruth Cohen, Lu Feng, Ayala Bloch, Sarit Kraus

原文摘要

As AI systems increasingly support human decision-making, a central challenge is determining what information helps people recognize when to rely on AI predictions and when to question or override them. Across three controlled human-subject studies spanning abstract visual reasoning with RAVEN matrices and deductive logical reasoning with LSAT problems, we examine how different forms of AI support affect performance in AI-assisted decision-making. A multi-stage reveal study shows that AI predictions and explanations can affect objective accuracy and subjective confidence differently. In visual reasoning, LLM explanations do not improve accuracy beyond the predicted answer alone, and no additional support format significantly outperforms prediction-only support; predicted probabilities show the highest descriptive accuracy and error recovery, while a derived selective-automation policy provides a higher-performing reference benchmark. In language-based logical reasoning, by contrast, LLM explanations yield the highest accuracy and error recovery, outperforming expert-written explanations and probability-based support. These results suggest that the effectiveness of AI support strategies depends on the task setting. Human--AI interfaces should instead be designed to support calibrated reliance and effective error recovery by matching the form of assistance to the task and the evidence available to users.

cs.HC · cs.AI · cs.CL

新论文 · v1arXiv:2611.20244

Right Goal, Wrong Body: Re-grounding Frozen VLAs under Actuation Shift

Umer Siddique, Peilang Li, Yongcan Cao

原文摘要

Vision-language-action (VLA) models are capable of producing desired robotic behaviors in ideal settings. However, they often fail when the robot's actuation changes at deployment. For example, remounting, mechanical wear, or command latency changes can lead to failed tasks and unsafe behaviors. To address the inevitable actuation shift, we propose ReGround, an inference-time method that keeps the VLA frozen and re-grounds its intended motion. ReGround learns the deployed robot's dynamics from task-agnostic motor babbling, and then tracks the policy's intended motion while staying close to the policy's own plan. ReGround activates only upon detecting a shift, and needs no rewards, demonstrations, or retraining. We show via two VLAs, eight LIBERO tasks, and five shift settings that ReGround can restore near-oracle success, such as raising $π_{0.5}$'s success from 0.16 to 0.90 under 400 ms latency, while remaining safer than a linear-calibration baseline. Project website and open-source code: https://umersiddique94.github.io/ReGround/.

cs.RO · cs.AI · cs.LG

新论文 · v1arXiv:2611.20242

Markets for Compute and Inference: Structure, Financing, and Risk Transfer

Dr Gabriel Borrageiro

原文摘要

Capacity to run large language models is rented by the accelerator-hour, and their output is sold by the million tokens. Both goods now have published price indices, an over-the-counter forward has traded on one, a perpetual future on one is listed offshore, and CME and ICE have specified futures on rental indices that await the United States regulator. We ask what in these two markets can be hedged, by whom, and at what price. Three findings stand out. First, the price that exchange contracts settle on is not the price that drives operators' revenue. Every contract references the published short-dated rental rate, while most revenue, and with it credit quality, comes from private multi-year contracts whose prices are largely undisclosed. Second, the token price and the rental rate are linked by an identity through throughput and margin, but they are different exposures, so a hedge on the rental rate does not hedge the cost of inference; at the measured capability of GPT-5 the cheapest list price fell by a factor of 17 in twelve months, and by far less at lower capability. Third, the demand for hedging already sits in credit agreements, as the years by which operators' debt outlives their contracted revenue. Filings cannot measure that gap, because debt is scheduled year by year while contracted revenue rarely is, and the one loan that prices it settles the risk by cash prepayment against a model only the parties see. We design a reverse convertible note through which leveraged operators could buy protection against falling rental rates. Its coupon depends steeply on the annualised volatility of the rental rate, which the two public indices put between about 5% and 89% according to how each is built and the horizon measured; across that range the fair one-year coupon runs from 4.1% to 31.5%.

q-fin.CP · cs.AI

新论文 · v1arXiv:2611.20230

A Matrix with Steps: An Episodic and Procedural Memory Method for Tool-Using Agents and Robots

Jürgen Paulhart, Peter Schüller

原文摘要

Agents that call tools and robots that execute tasks are challenged by two shortcomings: they repeat what failed before, and they learn from runs that they only believe succeeded. We describe the construction of a memory that addresses both, built for a production agent platform. Every run is recorded as an episode, and only an outcome confirmed by an external check, a test, a tool result or a person counts; the agent's own claim never does. What is learned from episodes is kept in a memory with two parts: an associative matrix, written with the delta rule, which finds the procedure that applies to a situation; and a section of ordered, addressable step records that answers what comes after a given step, where a step is a goal of the agent, not a motion. Because the matrix sums its associations, it keeps no order and cannot return or delete a single one; it serves as the finder, and order, outcome counts and deletion live in the records. We describe how execution outcomes are stored, how episodes are recalled and used for solving tasks, and the file format that stores the memory. In simulation, a robot that judged its own success and stopped when it believed it was done reported $96\%$ of its tasks as done and solved $35\%$; with external verification it solved $79%$. In a store of $100000$ synthetic episodes ($457$MB on disk), the oldest episode was still found first, no episode from another person's memory was returned, and a success vouched for only by the model was never recalled; a lookup took $16$ms on a laptop and $40$ms on a server node (median). Task outcomes were measured up to about $10000$ confirmed records, where the exact records solved every revisit at the first attempt.

cs.AI

版本更新 · v4arXiv:2608.23986

The Shadow Price of Intelligence: Quality Degradation and Retry Feedback in LLM Inference

Elioth Sanabria

原文摘要

Large language model providers are compute constrained, and a common response to congestion is to degrade service: route queries to smaller models, cut reasoning budgets, or shorten context windows. A user who receives an unsatisfactory answer either retries, adding load while the system is busy, or abandons, possibly as churn. We model inference serving as a control problem in which service quality is the provider's decision. A two-regime fluid approximation with retries folded into the service rate gives closed-form trajectories and crossing times, so the dynamic program over quality tiers needs no simulation. We characterize a region in which a weaker tier uses less energy per task but more capacity per task, and show that in the fluid model reactive throttling to such a tier can keep the queue from draining. With heterogeneous customers the problem is a transportation problem with retry-inflated capacity coefficients; optimal routing follows a $cμ$-type index, and the dual of the capacity constraint gives the marginal cost of one more query by class and time. We illustrate the method on five instances calibrated to public benchmark data.

math.OC · cs.AI · cs.PF