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

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 13:28 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 14:31 — 2026-11-08 14:31（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：2026-11-08 13:28最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 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 12,919 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 13:25（北京时间）
新论文 · v1arXiv:2611.07812

Different Corpora, Different Skills? A Paired Study of Small Language Models

Edoardo Vaira, Georgios Chavales, Pierre Nugues

原文摘要

Small language models are often trained under tight data budgets, where the choice of pretraining corpus may matter as much as model size or training recipe. We compare two contrasting corpora at matched 10-million- and 37-million-word budgets: the 1911 Encyclopaedia Britannica and the BabyLM 2026 strict pretraining corpus. For each corpus, we train teacher models, distilled 58-million-parameter Baby-Llama students, and no-distillation student ablations, using the same model families, training recipes, and evaluation protocol across corpora. Across BLiMP, BLiMP Supplement, EWoK, Entity Tracking, and COMPS, the corpora produce different skill profiles rather than a single quality ranking. BabyLM 2026 is consistently stronger on linguistic acceptability benchmarks, while Britannica is often stronger on Entity Tracking, a synthetic state-tracking task. The contrast appears across teacher and student models and at both budgets, with the cleanest cross-seed replication in the distilled student comparison. Targeted controls show that the central contrast persists after matching training exposure and at a longer diagnostic context; direct teacher ensembling also does not reproduce the 10M Britannica student's Entity Tracking behavior. Entity Tracking magnitudes nevertheless remain sensitive to training dynamics. For this corpus pair, corpus choice can therefore produce different relative skill profiles at small scale, motivating multi-benchmark evaluation when comparing pretraining data.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.23409

How Far Can a Trainable Frequency Move? Resolution, Grids and Coupling in Trainable-FrequencyQuantum Models

Michael Poppel, Markus Baumann, Sebastian Wölckert, Claudia Linnhoff-Popien, Jonas Stein

原文摘要

Trainable-frequency quantum models train the prefactors of their encoding gates so that the circuit's frequencies can move onto the target's. From the unit start of prior work, training rarely reaches a target more than one resolution step away. We show that the target-driven part of the prefactor gradient is a weighted sum of slopes of the overlap $\sin u/u$, where $u$ is the model-target frequency distance scaled by the window half-width. This gives each frequency a reach: under gradient flow, an isolated real frequency whose coefficient adapts optimally reaches its target from within half a step, for every target at least one step from zero frequency; with a fixed coefficient, a phase-dependent barrier can stop it. A ternary prefactor grid places a model frequency within half a step of every band frequency, with logarithmically many encoding gates. Single-frequency circuits trained with Adam and jointly trained amplitudes behave as predicted: inside the first side lobe, a frequency starts toward its target exactly when in phase with it in 98% of runs, and only 11 of 768 frequencies starting beyond the lobe reached their target. With several frequencies, the grid start raised successful fits on synthetic targets from 69% to 84% against the best random start. With many target frequencies, least squares on the fixed grid fits near-perfectly, but the circuit does not reach the coefficients; training the prefactors narrows this shortfall, but with 8 and 24 target frequencies, training the fixed grid ten times longer fitted better. On real series, training the frequencies improved held-out $R^2$ at equal budget by 0.010--0.045 on four of seven series, but a classical screen did not separate these from the others. A classical model with independently trainable frequencies shows the same dependence on the start; our results describe how to train such models, not an advantage of the circuit.

cs.LG · cs.AI · cs.ET · quant-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07811

MV-Sign: Multi-View 3D Motion Integration and Enhanced Text-to-Motion Conditioning for Sign Language Production

Singyu Muk, Kaustubh Kundu, Kunyuan Xie, Weijie Wang, Kalin Stefanov

原文摘要

Sign language production (SLP) aims to generate appropriate sign language motion from spoken language text. However, current 3D SLP methods suffer from noisy supervision and weak text conditioning. Specifically, these methods typically rely on pseudo-3D motion data fitted from single-view frontal videos, which introduces severe self-occlusion and loses fine-grained hand details, ultimately degrading downstream production. To overcome these limitations, we propose a comprehensive framework that jointly integrates multi-view 3D motion data and optimizes the text-conditioning pathway. First, we introduce How2Sign-MV3D, a high-fidelity dataset constructed via a novel cross-view curation pipeline that fuses multi-view estimates to resolve occlusions and filter non-signing segments. Second, we design a robust SLP model incorporating a sign-aware spatio-temporal VQ-VAE (ST-VQVAE) for joint body-hand tokenization, a pseudo-gloss adapter, and keyframe-aware retrieval to enhance text-to-motion alignment. Evaluated on the How2Sign benchmark, our framework reduces body and hand DTW-PA-JPE by 32.8% and 20.9% respectively compared to the state-of-the-art. Finally, we release two new high-quality 3D datasets, ASLCitizen-3D and MM-WAuslan-MV3D, alongside SGNify-MV as a multi-view video benchmark to support broader community research.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07810

Self-Supervised Diffusion Models for Handwritten Signature Verification via Ruin Reconstruction

Peirong Zhang, Zhenhua Yang, Jiaxin Zhang, Moises Diaz, Miguel A. Ferrer, Umapada Pal, Wei Zhou, Lianwen Jin

原文摘要

Handwritten signature verification (HSV) is a critical biometric technique in legal and forensic authentication, whose efficacy hinges on the discriminability of signature representations. Current HSV methods predominantly adopt supervised learning to enhance representation quality, leaving self-supervised learning largely unexplored. We propose \emph{SigDiffuser}, a diffusion-based self-supervised framework for signature representation and verification. At its core, \emph{SigDiffuser} introduces a novel pretext task termed \emph{Reconstruction from Ruins (RFR)}, which deliberately ``ruins'' signatures through severe crumpling, obliterating their structural integrity and writing styles. A visual encoder is employed to capture crucial handwriting patterns from intact signature regions, guiding the denoiser to reconstruct the ``ruined'' portions and learning meaningful representations. Additionally, we introduce a \emph{pyramidal feature aggregation module (PFAM)} to bridge the visual encoder and denoiser, enhancing representation quality via hierarchical aggregation and modulation. Extensive experiments on multilingual signature datasets demonstrate that \emph{SigDiffuser} significantly outperforms both state-of-the-art SSL methods and HSV models. We further show that increasing the crumpling severity on signatures effectively improves representation quality. Notably, our work demonstrates that extreme destruction, coupled with self-supervised diffusion models, can yield superior signature representation compared to traditional mild deformations, paving new avenues for HSV and other biometric domains. Code will be publicly available.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07808

A Sequential Framework for Urban Drone Delivery: Network Design, Vehicle Sizing, and Energy and Cost Assessment

Hong-Su Nam, Seokhwan Lee, Jungwoo Cho, Hak-Tae Lee

原文摘要

A sequential engineering framework is presented for urban drone delivery, linking hub location, route planning, mission-specific vehicle sizing, and energy and operating cost assessment. Aggregate origin-destination demand is assumed known a priori. For each hub configuration, the maximum required link distance is minimized, and feasible routes that return to their departure hubs are generated. Route frequencies are determined using mixed-integer linear programming to satisfy delivery demand. The resulting range requirement guides motor-propeller selection and battery sizing to minimize vehicle takeoff mass. Flight distances and frequencies, cruise performance, and vehicle dimensions are combined to estimate monthly energy consumption, fleet size, hub area, staffing, and operating cost. The framework is applied to district-level Seoul delivery data. Increasing the number of hubs from one to four reduces the required range from 30.6 to 21.9 km and vehicle takeoff mass from 8.12 to 6.12 kg. Despite a 21.5% increase in total flight distance, monthly flight energy consumption decreases by 13.1%, from 15.2 to 13.2 MWh. Battery replacement is the largest vehicle-related operating expense, while operating cost per delivery increases from USD 1.18 to USD 2.20 because of higher rent and labor costs at the hubs. Among the designs evaluated, range-matched vehicles achieve the lowest operating cost in the two- and four-hub networks; a longer-range vehicle is least costly in the three-hub network. Sensitivity analyses further examine the effects of delivery demand and operating assumptions. The results demonstrate that reductions in vehicle mass and energy consumption do not necessarily lead to lower system operating cost.

cs.RO · physics.soc-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07798

VocabulARy 2.0: A Generative AR System Enabling Personalised 3D Mnemonics for Vocabulary Learning in Context

Karolina Trajkovska, Matjaž Kljun, Maheshya Weerasinghe, Klen Čopič Pucihar

原文摘要

Mnemonics support vocabulary learning by linking unfamiliar words to familiar concepts through memorable verbal and visual associations. We present a generative AR system that enables learners to create personalised 3D mnemonics by transforming familiar objects in their surroundings into situated mnemonic anchors. The system scans the environment, detects visible objects, and generates bilingual flashcards. After selecting a word, the learner describes a personal association. The system combines this description with an image of the selected object to generate a textured 3D model using generative AI. Learners can then place the model relative to the real object, transforming it into a situated mnemonic anchor.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.25807

Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality

K S Sesh Kumar

原文摘要

Kolmogorov-Arnold Networks (KANs) learn univariate functions on edges, making the choice of edge response central to their design. Existing variants use basis expansions such as splines or polynomials, whose functional form is chosen before training. We introduce geometry-constrained KANs, which instead learn the shape of power-law edge responses through an exponent inspired by Banach duality maps. Banach-KAN combines this adaptive power-law response with a bounded hyperbolic tangent (tanh) component. We relate these responses to convex potentials and bound edge sensitivity on bounded input ranges. Across symbolic regression benchmarks, Banach-KAN is competitive with fixed-basis models, particularly with limited clean data. Learned power-law responses remain competitive under measurement noise, while splines are stronger with plentiful clean data. Fixed-exponent and branch-removal controls on a core subset support learning the exponent and retaining both Banach components. Learned exponents describe the shapes of the fitted edge responses.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07797

Dataset Collection and Fine-Tuning of NLLB for German--English Translation

SK Deeraj, Yash Ingle, Pruthwik Mishra

原文摘要

This paper describes the curation of a high-quality parallel corpus from OPUS Books and the fine-tuning of Meta's NLLB-200 models for German--English translation. We detail a dataset extraction pipeline that filters 45k raw OPUS sentence pairs to 25k high-quality examples through encoding validation, length filtering, language identification, deduplication, and quality scoring. We present a reproducible fine-tuning methodology optimized for consumer GPUs using mixed precision, gradient accumulation, and gradient checkpointing. Our fine-tuned NLLB-600M model achieves statistically significant improvements (+3.4 BLEU, +2.6 chrF++, -3.2 TER) over the base model on literary and technical German-English translation. We demonstrate practical deployment by integrating the fine-tuned model into LinguaHaru, an existing open-source document translation system, achieving format-preserving translation across PDF and Office documents. All dataset preparation scripts, training code, and evaluation tools are provided for reproducibility. The fine-tuned model is available at HuggingFace.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.26683

PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images

Daniel Collin, Yuri Shprits, Luca Chiarabini, Stefan J. Hofmeister, Nadja Klein, Guillermo Gallego

原文摘要

Accurately predicting fast solar wind conditions is challenging, as uncertainties are large and unquantified by traditional single-value prediction models. In particular, the risks of high-speed solar wind streams (HSSs), which can cause damage to technological infrastructure, cannot be reliably assessed without probabilistic forecasts. We present PROSWIN, a probabilistic machine learning model that forecasts the hourly solar wind speed (SWS) at Earth with a four-day lead time. The approach combines solar images and magnetograms using a deep neural network coupled to a distributional regression algorithm. Because standard error metrics underweight the relevance of HSS peaks, we further introduce the prediction score, a model-selection metric that jointly rewards timeline and HSS peak accuracy. On 14 years of data, our forecast achieves very well-calibrated uncertainties (<1% average deviation). Using the continuous ranked probability score (CRPS), a metric that assesses distributional accuracy, we obtain a timeline CRPS of 41.0 km/s, an HSS peak CRPS of 45.3 km/s, and a prediction score of 42.3 km/s. We find that the 171 Å channel is an important complement to the typically used 193 Å and 211 Å channels and that the prediction score for model selection improves the applicability of the model. Compared to selected models from the literature, ours is the only one that is accurate for both timeline and HSS peak values, rather than trading one off against the other. These results support the advantages of probabilistic over single-value solar wind models. The introduced methods are also transferable to other forecasting problems.

astro-ph.SR · cs.LG · physics.data-an · physics.space-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07793

Rain Beyond Streaks: Cascaded Realistic Rain and Wet Surface Synthesis via Scene Priors

Melissa Tijink, Kirill Tolstobrov, Shunxin Wang, Estefania Talavera, Duc V. Le, Luuk Spreeuwers, Shaodi You, Nicola Strisciuglio

原文摘要

Realistic rain synthesis is a persistent challenge for vision systems operating in adverse weather. Existing methods primarily focus on generating rain streaks, often neglecting consequent surface effects such as reflections and puddles, which are critical for perceptual realism and robustness of downstream vision tasks. We introduce CascadeRS, a rain synthesis framework that leverages depth and segmentation priors to render scene-consistent rain and surface effects. In addition to rain streaks, CascadeRS produces reflections and puddles aligned with scene semantics through a physics-inspired zero-shot, controllable generative pipeline. It produces photorealistic rainy urban scenes, with high perceptual realism, which we validate qualitatively with an extensive user study and quantitatively. We produce the Cityscapes-CascadeRS dataset, to study downstream task performance under real rainy conditions. Our results establish CascadeRS as a scalable and realistic rain-generation framework for evaluating and enhancing the robustness of vision in adverse rainy weather. Code and dataset are available via https://github.com/nis-research/CascadeRainSynthesis

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07792

Thinking Is Not Writing: Designing AI Chatbots to Connect Reasoning and Revision

Lucile Favero, Tanja Käser, Juan Antonio Pérez-Ortiz, Nuria Oliver

原文摘要

Supporting students' argumentative writing with AI requires connecting reflection to their revision processes. We present Maike, a Socratic chatbot supporting writing through argument diagnosis, targeted questioning, and a student model across Think and Write modes. In a classroom study, 65 secondary-school students used Maike or a control chatbot sharing the interface, language model, and Think/Write modes. Approximately 40% of students improved their essay scores. However, Maike users engaged more in idea-level dialogue (56% vs. 44%) and moved iteratively between discussion and editing. Transitions from ideas discussed in dialogue to revisions were positively associated with score gains. These findings suggest a design target for AI writing support: coordinating reflection with revision. We contribute an architecture for supporting argumentative reasoning without generating essay text and an approach linking interaction patterns to writing processes and outcomes. As AI becomes embedded in classrooms, understanding these connections is essential to assessing (and designing for) its educational value.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.04757

Near-Optimal Decentralized Stochastic Convex Optimization over Networks

Nitai Kluger, Amit Attia, Tomer Koren

原文摘要

We study decentralized stochastic smooth convex optimization, where $M$ workers minimize an average objective using local stochastic gradients and neighbor-only communication over a fixed gossip network. A central question in this setting is to determine the largest number of workers that can be used under a total budget of $N$ gradient samples while still preserving the centralized $O(1/\sqrt N)$ statistical rate. We introduce an accelerated decentralized method that preserves this rate for up to $\smash{M\lesssim \sqrtρ\,N^{3/4}}$ workers, where $ρ$ is the spectral gap of the gossip network, improving the best prior maximal scaling of $\smash{M\lesssim ρ\sqrt N}$. The method is based on a one-step-delayed stochastic acceleration scheme that enables workers to interleave minibatching with accelerated gossip while controlling residual disagreement, and its guarantee depends only logarithmically on the optimum-local heterogeneity. We also establish a matching lower bound for linear-span decentralized first-order methods, showing that the method is optimal up to logarithmic factors.

math.OC · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.24737

Learning to Think from Multiple Thinkers: How Chain-of-Thought Heterogeneity Affects Efficient Learnability

Nirmit Joshi, Roey Magen, Nathan Srebro, Nikolaos Tsilivis, Gal Vardi

原文摘要

Chain-of-thought (CoT) supervision makes computationally hard learning problems tractable by exposing intermediate steps that are easy to learn via next-token prediction. However, in practice, CoT datasets draw on heterogeneous sources with different reasoning styles, and substantial effort goes into curating supervision suitable for next-token training. What role does this curation play in enabling the computational advantage of CoT supervision? In this work, we take a first step toward understanding this question from a learning-theoretic perspective. We introduce several models of $heterogeneous$ $CoT$ $supervision$ from multiple sources, each providing correct traces with the same final answer but different intermediate steps. Assuming that fitting a next-token predictor to $homogeneous$ traces from any single source is computationally tractable, we ask when this suffices for efficient learning from heterogeneous supervision. We show $cryptographic$ $hardness$ of learning from $passively$ collected traces from multiple sources, even though learning from homogeneous CoTs is easy. This hardness can stem either from $hard$-$to$-$learn$ $contribution$ $biases$ determining which sources contribute traces on different parts of the domain, or from receiving an $unfiltered$ heterogeneous mixture (though a filtered subset of homogeneous traces is sufficient for efficient learning). On the positive side, inspired by iterative and adaptive fine-tuning of language models, we give a computationally efficient learning algorithm that $actively$ and $adaptively$ collects CoTs from multiple sources with a per-source CoT budget completely independent of the target error $\varepsilon$. We argue that our results illuminate data collection and curation practices central to making CoT supervision effective for learning.

cs.LG · cs.AI · cs.CC · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07786

On computing the determinant over a ring

Gilles Villard

原文摘要

An algorithm is presented for computing the determinant and the characteristic polynomial of a matrix $A$ over an arbitrary commutative ring R. The algorithm uses $O(n^ω)$ ring additions, subtractions and multiplications, where $ω>2$ is a feasible exponent for matrix multiplication, that is, such that two $n\times n$ matrices over R can be multiplied using $O(n^ω)$ ring operations. The algorithm involves no division and no zero test, and its control depends only on $n$: for each $n$ it is a straight-line program. The approach combines a polynomial matrix point of view and a block Krylov point of view on the characteristic polynomial, which makes Strassen's elimination of divisions efficient. A bivariate matrix $λI-L(t)$, obtained from $A$ by a homotopy, is compressed in $\log n$ steps, each of which halves the dimension while only doubling the degree in $λ$. The cost of the homotopy is controlled by truncating the power series in $t$ at an order that only grows with the compression steps, from a constant to $n$.

cs.SC · cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07784

EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets

Evgenii Genov, Ander Martinez Alonso, Christoph Bergmeir

原文摘要

Energy forecasting models are usually compared on backtests and fixed public datasets. Backtests can use data that did not yet exist when the forecast would have been made, and a fixed test set, reused across studies and possibly contained in the pretraining data of foundation models, invites overfitting to the benchmark. EnergyBench evaluates every entry live instead. Each day at 11:30 CET/CEST, thirty minutes before the day-ahead (SDAC) gate closes, every model forecasts the next day's price, wind and solar generation and load on the 15-minute grid for six bidding zones (BE, NL, FR, DE-LU, DK1, DK2). Unlike existing live benchmarks, EnergyBench runs the models itself, on one information set that it freezes at the cut-off and publishes, including three numerical weather prediction models, so that foundation models can be compared with and without the same weather covariates under the actual market deadline. Errors are pooled per series against a seasonal-naive baseline, and models are ranked by a Bradley-Terry rating on the Elo scale with a day-bootstrap interval. The field spans baselines, linear and gradient-boosted models on the frozen weather, eighteen time-series foundation models from eleven families, ensembles, and the grid operators' own forecasts. Over the first thirty-two live days, the covariates reduced the error of each of the ten foundation models run with and without them by 37-51% on matched races (64-73% on wind, 48-61% on solar). Used zero-shot, these models match or outperform a LightGBM model trained on the same covariates. Model size, from 3M to 331M parameters, has a much smaller effect, and median ensembles of the covariate models rank highest. The grid operators' pre-gate forecasts remain ahead on wind and solar, where the best single foundation models have 16-22% more error; on load the gap is 4-6%, within the intervals.

cs.LG · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.21582

Depth-Recurrent Attention Mixture (Dreamer): Giving Latent Reasoning the Attention it Deserves

Jonas Knupp, Jan Hendrik Metzen, Jeremias Bohn, Georg Groh, Kristian Kersting

原文摘要

Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes depth-recurrence due to partially fixed layer stacks, and ignores the bottleneck of constant hidden-sizes that restricts many-step latent reasoning. To address this, we introduce a modular framework of depth-recurrent attention mixtures (Dreamer), combining sequence attention, depth attention, and sparse expert attention. It alleviates the hidden-size bottleneck through attention along depth, decouples scaling dimensions, and allows depth-recurrent models to scale efficiently and effectively. Across language reasoning benchmarks, our models require 2 to 8x fewer training tokens for the same accuracy as FLOP-, parameter-, and memory-matched SOTA, and outperform ca. 2x larger SOTA models with the same training tokens. We further present insights into knowledge usage across depths, e.g., showing 2 to 11x larger expert selection diversity than SOTA MoEs.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02775

Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation

Subodh Lonkar

原文摘要

Financial document recognition is often assessed using character and word error rates, although these metrics do not express whether a system preserves the financial facts on which people and organisations act. This paper develops a human-centred, risk-constrained framework for evaluating financial document recognition as evidence recovery and decision support. It defines typed financial facts linked to visible source regions and separates verbatim transcription, deterministic normalization, and business interpretation. A layered quality model covers text, localization, layout, tables, fields, fact correctness, evidence grounding, uncertainty, robustness, and operational performance. Non-compensatory acceptance gates use one-sided uncertainty bounds for critical-field errors, preventing strong aggregate scores from masking failures in amounts, identifiers, signs, periods, or entity associations. Selective automation is formulated as a constrained routing problem that accounts for residual risk, human-review capacity, and review cost. The framework further specifies annotation and adjudication procedures, leakage-resistant benchmark partitions, statistical estimands, subgroup analyses, and a reproducibility card. Formal results establish the limitations of compensatory scoring, the non-zero upper risk bound after zero observed errors, and a loss sensitive decision rule for routing uncertain cases to human review. The contribution is theoretical and methodological; no new model, dataset, or empirical performance result is claimed.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07783

PBPO: Prefix-Block Policy Optimization for Diffusion Language Models

Katherine Tieu, Dongqi Fu, Si Zhang, Hanqing Zeng, Tianxin Wei, Chenglin Wei, Yinglong Xia, Hong Li 等 9 位作者

原文摘要

Diffusion Large Language Models (dLLMs) commonly decode responses by proceeding autoregressively across blocks while iteratively denoising multiple tokens within each block. This structure makes block-level policy optimization a natural adaptation of autoregressive policy optimization. However, the exact likelihood of a completed block is intractable because it marginalizes over the intermediate states and reveal orders of the denoising process. To realize the block-level formulation, we construct a prefix-block state and use a single model evaluation to define a factorized one-step surrogate for the block likelihood. The resulting block surrogate ratio is a product of its token surrogate ratios, allowing variation at individual positions to propagate across the entire block before clipping. We therefore introduce Prefix-Block Policy Optimization (PBPO), which preserves block-level conditioning but applies surrogate importance weighting and clipping separately to each token. PBPO further diversifies repeated updates by resampling corrupted views of the prompt and revealed prefix, a design motivated by masked-dLLM pre-training. Under our analysis assumptions, block-product weighting amplifies the variance of gradient contributions relative to token-local weighting. Across two LLaDA-family initializations, six benchmarks, and three generation lengths, PBPO achieves competitive performance against existing dLLM RL methods.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07780

Bridging Structure and Semantics: Knowledge Graph Verification via Triple-to-Text Alignment

Ziang Cui

原文摘要

Semantic accuracy is an important dimension of knowledge graph quality. Graph-based scoring methods exploit relational structure, while textual representations allow classifiers to draw on knowledge encoded by pre-trained language models (PLMs). We present GenVer, a generative verifier that scores triples using both their serialized form and generated natural language representations (NLRs). A triple-text alignment procedure selects training pairs for a sequence-to-sequence generator; a BERT-based classifier then combines features from each triple and its generated NLR. On four FactFB variants, constructed from FB15k using perturbed negative triples, GenVer obtains the highest classification accuracy among the evaluated baselines, ranging from 88.56% to 91.52%. The experiments suggest that generated representations can help triple classification, while the case analysis also exposes semantic drift and high-confidence errors.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07778

The Intrusion Pathway: How Non-Evidential Context Degrades Language Model Performance

Dikshant Kukreja, Gautam Gupta, Avni Mittal, Avinash Anand, Kritarth Prasad, Zhengkui Wang, Timothy Liu, Rajiv Ratn Shah 等 11 位作者

原文摘要

Language models lose accuracy when a prompt contains non-evidential context: irrelevant statements from unrelated domains, or random off-distribution tokens, with no competing answer and no semantic overlap with the query. Such noise pervades retrieval-augmented, tool-using, and long-context deployments, yet the failure has lacked a mechanistic account. We trace the corruption to the Intrusion Pathway, which starts with MLPs enriching both query-subject and irrelevant-token representations, parroting heads carry prefix-token content to the prediction position, and relational readers largely avoid unrelated sources. Nevertheless, preserved subject enrichment and selective reading do not prevent intrusion in the broader computation. We then localize part of this interference to a sparse set of attention heads, which we call intrusion heads. Their prefix-derived writes promote distractor-related content, while their reduced support for the correct answer arises primarily from weaker non-prefix contributions rather than direct suppression by the prefix. The same heads transfer across tasks and distractor types and are largely weight-disjoint from the heads that integrate relevant contextual evidence, enabling a class-conditional intervention. Replacing the corrupted last-token residual with its clean counterpart, an oracle probe that requires a matched clean forward pass, recovers 97.6% on average of the distractor-induced drop across four downstream tasks. A deployable mask level knockout of about ten heads, roughly 1% of the model's attention heads, recovers 57% at bounded cost to helpful context.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.04314

MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification

William Grolleau, Achraf Chaouch, Astrid Sabourin, Guillaume Lapouge, Catherine Achard

原文摘要

Animal re-identification (ReID) faces critical challenges due to viewpoint variations, particularly in Aerial-Ground (AG-ReID) settings where models must match individuals across drastic elevation changes. However, existing datasets lack the precise angular annotations required to systematically analyze these geometric variations. To address this, we introduce the Multi-view Oriented Observation (MOO) dataset, a large-scale synthetic AG-ReID dataset of $1,000$ cattle individuals captured from $128$ uniformly sampled viewpoints ($128,000$ annotated images). Using this controlled dataset, we quantify the influence of elevation and identify a critical elevation threshold, above which models generalize significantly better to unseen views. Finally, we validate the transferability to real-world applications in both zero-shot and supervised settings, demonstrating performance gains across four real-world cattle datasets and confirming that synthetic geometric priors effectively bridge the domain gap. Collectively, this dataset and analysis lay the foundation for future model development in cross-view animal ReID. MOO is publicly available at https://github.com/TurtleSmoke/MOO.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07775

Adapters as Data: The Latent Space of LoRAs

Moritz Grävinghoff, Konstantin Wehmeyer, Aron Asefaw, Boris Knyazev, Damian Borth

原文摘要

LoRA adapters are usually treated as finished artifacts rather than as a data modality. Prior work has shown that LoRA adapters populate a low-dimensional manifold that a linear PCA basis already organizes well enough to support different operations such as sampling, editing, and inversion. We ask what a learned, nonlinear latent adds beyond this. We train a transformer autoencoder on the same population of LoRA identity adapters, mapping each into a latent space and compare every operation against the identical operation applied directly to the raw adapter weights. The latent preserves the capabilities already available in weight space, sampling diverse identities and editing individual attributes. Beyond preservation, we show that the latent is far more robust to displacement than weight space, degrading into distorted but still valid faces rather than texture. Fixed-dimensional weight-space representations cannot natively host adapters of more than one rank, so we extend our sequential autoencoder to hold mixed-rank adapters within one shared latent. This gives a path toward treating adapter weights of varying architecture as a single, general modality rather than one tied to a fixed rank, and points to a learned, nonlinear latent as the mechanism that could carry this generalization further, toward heterogeneous populations of adapters.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2604.20575

A Quadratic Lower Bound for Noncommutative Circuits

Pratik Shastri, Sophus Valentin Willumsgaard

原文摘要

We prove that every fan-in 2 noncommutative arithmetic circuit computing the palindrome polynomial $\mathrm{Pal}_{n,d}(X,Y)$ of degree $2d$ in $2n$ variables has size $Ω(nd)$, which is tight up to a constant. In particular, when $d = n$ we obtain an $Ω(n^2)$ lower bound, improving the previous lower bound of $Ω(n \log n)$ by Nisan and concurrent work of $Ω(n^{1.5})$ by Raz (FOCS 2026). The proof builds on and refines a previous work of the first author, by constructing for every gate a small set that spans a subset of the coefficients of the polynomial computed by that gate. We show that the structure of the set depends only on the subsets of multiplication gates along paths going from that gate to a leaf. From this description, we are then able to get an upper bound on this set based on the amount of product gates in the circuit. The proof is surprisingly short and simple to understand, considering that improving Nisan's $Ω(n \log n)$ lower bound for noncommutative circuits has been an open problem for decades.

cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07773

Optimal Learning in Games with Arbitrary Delays: Best-of-Both-Worlds for Self-Play and Adversarial Opponents

Emmanuel Esposito, Andrew Jacobsen, Hao Qiu, Alexander Ryabchenko, Mengxiao Zhang

原文摘要

We study learning in zero-sum games with delayed feedback. We introduce Multi-Anchor Optimistic Online Mirror Descent (MAO-OMD), a single algorithm which obtains optimal fast rates in self-play on smooth games, while simultaneously maintaining minimax optimal guarantees against arbitrary opponents. In particular, in smooth zero-sum games with arbitrary and unknown feedback delays, MAO-OMD obtains $O(σ_{\max}+1)$ social and individual regrets when used by both players, where $σ_{\max}$ denotes the maximum number of outstanding gradients, while also guaranteeing minimax optimal $O(\sqrt{T+d_{\mathrm{tot}}})$ individual regret against arbitrary opponents, where $d_{\mathrm{tot}}$ is the total delay. Moreover, we show that these optimal rates cannot be obtained simultaneously using the standard black-box reduction to the undelayed setting. We also extend our results to multi-player games, and to games with player-dependent delay sequences.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07772

Adapt the Object to the Subject: Representative Study Material for Empirical Software Engineering

Max Unterbusch, Julian Frattini, Michael Mircea, Alexander Korn, Kurt Schneider, Jonathan Ullrich, Andreas Vogelsang

原文摘要

External validity is a central concern in empirical software engineering, yet the debate has largely focused on whether study participants are representative. How well the study objects they reason about - code, models, or requirements - are representative of each participant's own work is often overlooked. Practitioners' own artifacts would be ideal, but are often out of reach, so researchers sample from public datasets or construct objects artificially. Whether this lack of subject-object fit affects participants' ability to act on the material remains unknown. We take a first step toward answering this question for requirements. We propose an approach that uses an LLM to generate context-adapted synthetic requirements just-in-time during an online survey from a short, participant-supplied context description, optionally injecting requirements smells as controlled stimuli. To validate the approach, we conducted a controlled experiment with 31 industry practitioners in a 2x2 design that crosses stimulus generation (static vs. synthetic) with quality (clean vs. smelly). Each participant rated the perceived representativeness and assessability of 20 requirements. Using Bayesian data analysis within a statistical causal-inference framework, we find that perceived representativeness has a strong positive effect on assessability. Synthetic requirements are rated as more representative and, primarily due to this gain, more assessable than static ones sourced from public datasets; smell injection leaves both perceptions unchanged. Our results support treating a lack of study-object representativeness as a first-class validity threat and position context-adapted synthetic study objects as a practical addition to the empirical methodology toolbox.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.20171

FreeSBee: A Constant-Time Compilation Pipeline

Julian Ganz, David Knothe, David Oswald, Sebastian Reiter, Thorben Schneider, Simon Wegener

原文摘要

Constant-time execution is an important security property, especially for IoT devices, that prevents the leakage of sensitive information over timing side-channels. However, achieving constant-time execution is very hard when going down to the cycle level, at least on realistic devices. A lot of research is concerned with producing tools that either determine whether code is constant-time or that ensure it is compiled into a constant-time binary, with various degrees of accuracy. In this work, we present and evaluate a full workflow for hardening against timing side-channels during compilation. It starts with taint analysis to determine the code locations that depend on sensitive information. These are then the object of automated control-flow transformations inside the compiler to seal possible timing side-channels. We evaluate our workflow in detail on a realistic application running on a RISC-V core using both static timing analysis and statistical methods. Even though we do not reach cycle-accurate constant-time execution, our statistical results suggest that our hardened binary is safe against timing attacks.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.31140

Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?

Ziyi Wang, Li Li, Aolin Zhou, Yankun Shen, Chonghan Liu, Shuxia Lin, Xu Yang

原文摘要

Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However, this multimodal scaling often degrades the language-side reasoning ability originally encoded in the base LLM. While the base LLM retains usable reasoning after scaling, the aligned VLM itself cannot reliably access this ability. Therefore, recovering the degraded reasoning capability in VLMs would benefit more from seeking help from the base LLM than from the VLM alone. Motivated by this, we propose LIFT (Language-side reasonIng Facilitation and Transfer), a lightweight vector-intervention method that transfers reasoning capability from the base LLM to the VLM without retraining the backbone. LIFT defines Reasoning Vectors as answer-token hidden-state differences between a Reasoner path with an explicit reasoning trace and a Solver path without it, and injects these vectors into language-side activations of the target VLM. LIFT further supports learnable vector adaptation while keeping the VLM backbone frozen. We evaluate LIFT on two VLMs across six reasoning benchmarks, comparing Reasoning Vectors extracted from the base LLM and from the aligned VLM under matched protocols. Results show that LLM-derived vectors consistently outperform VLM-derived vectors, confirming that the base LLM is a more effective source for recovering reasoning. LIFT partially recovers degraded reasoning through lightweight language-side interventions. Further analyses show that Reasoning Vectors influence intermediate reasoning behavior rather than merely altering final answers. The source code will be released soon.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07765

BiGrounder: Bidirectional Training Unlocks the Potential of GUI Grounding

Dengyao Shi, Tianyu Fu, Fei Hu, Anyang Su, Hanning Wang, Shuo Wang, Minghui Wu, Chenxu Zhao 等 9 位作者

原文摘要

Graphical User Interface (GUI) grounding aims to map natural language instructions to precise operational coordinates, serving as a critical task for autonomous agent interaction. Current approaches formalize GUI grounding as predicting action-coordinate pairs from instructions, with end-to-end training supervised solely by final coordinates. Training datasets typically provide only a small number of descriptions per target coordinate, whereas real-world scenarios involve a much larger set of varied descriptions for the same target, which limits robustness to linguistic variation. While recent GUI grounding paradigms have begun employing reinforcement learning to enhance localization accuracy, models with limited exploratory capability before reinforcement yield constrained improvements even with identical training data during the reinforcement phase. To overcome these limitations, we propose a bidirectional reward paradigm that enables model self-reinforcement. During SFT, bidirectional training equips the model to generate action descriptions from target coordinates. During RL, the model samples semantically consistent instruction variations on-policy and grounds each variation back to its target. A cycle-consistency gate couples semantic quality to grounding success, turning the model's own instruction policy into a source of continually refreshed reinforcement trajectories. Our 4B-parameter model achieves competitive accuracy across five grounding benchmarks in our evaluation, indicating the effectiveness of the proposed training paradigm. https://github.com/Spell-shi/BiGrounder

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07760

Fast Unsupervised Anomaly Detection Methods on Software Logs - An Empirical Study

Jesse Nyyssölä, Mika Mäntylä, Yuqing Wang

原文摘要

Anomaly detection on software logs ensures system reliability through failure identification, root cause analysis and fault localization. While supervised models show excellent performance, in a practical setting there rarely are labeled training data available. This calls for the use of unsupervised models. We study effects of data preprocessing, anomaly detection method, and the dataset. For preprocessing, we examine three options: The use of anomaly-free training data, using randomized as opposed to chronologically selected training data, and the use of a custom loader to extract log message from the log line. Regarding anomaly detection we use four models (KMeans, IsolationForest, RarityModel, Out-Of-Vocabulary Detector) and three representations (Words, trigrams, and parsed events). We evaluate these approaches on seven datasets: BGL, HDFS, Hadoop, Spirit, Thunderbird, Liberty, and LO2Token. We run each combination of the selected factors and measure performance with AUCROC and F1-score metrics. Then we utilize a generalized linear model to establish relationships between the factors. Furthermore, we address execution times. Our evidence reveals large variability across all datasets, preventing us from making recommendations that apply universally. For instance, log parsing enhances performance on some datasets but reduces it on others. The evidence suggests that using anomaly-free data for training unsupervised models can improve anomaly detection performance, though this requires extra effort to identify such data.Previous work has argued that shuffling data leads to unrealistic model performance (data leakage). Yet, our results show this does not hold for the unsupervised models we tested, while it remains true for supervised models in the same setup. For fast execution of the pipeline, use word representation and avoid IsolationForest model.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.07759

ReConMem: A Graph-Based Dual Memory System for Repository-Oriented Conversations

Zhishuo Yang, Li Zhang, Yang Liu, Donghao Yang, Fang Liu

原文摘要

LLM-based code assistants are increasingly used in iterative repository-level development, where effective assistance requires jointly leveraging evolving conversational history and repository context. Existing memory systems, however, are primarily designed for general-purpose conversations and do not sufficiently coordinate conversational information with the structured code entities to which it refers. We propose ReConMem, a graph-based dual memory system for repository-oriented conversations. ReConMem organizes distilled conversational memories and conversation-relevant code entities into interconnected semantic and structural memory graphs, while maintaining their cross-graph associations as interactions evolve. For memory recall, ReConMem combines natural-language and code-aligned retrieval through code-draft-based query grounding, expands retrieved information over intra- and inter-graph relations, and compresses retrieved code according to its structural granularity. We evaluate ReConMem on two repository-oriented conversational benchmarks spanning long-horizon context management and realistic project-grounded multi-turn assistance. On LoCoEval, ReConMem improves Pass@1 over the strongest baseline by 7.917 and 7.292 percentage points on single-hop and multi-hop subsets, respectively, with comparable context compression. On CodeAssistBench, it achieves 27.61% Correct and 44.03% Partially Correct, exceeding Full History by 4.10 and 7.09 percentage points, respectively, while improving interaction quality. These results demonstrate that aligning conversational memory with repository structure improves context management for repository-oriented multi-turn interactions.

cs.SE

查看论文
arXiv ↗PDF ↗