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

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 07:46 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 07:52 — 2026-11-20 07:52(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 07:46最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 22 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 07:44(北京时间)
新论文 · v1arXiv:2611.23746

ZERITH V2.5: From Predictive Power to Policy Learnability

Chenxi Han, Ruby, Epoch, Orion, Luke, Bin, Dusk, Lyra 等 21 位作者

原文摘要

When humans learn to manipulate an unfamiliar object, they may already be able to anticipate how its state will change while still being unable to control it skillfully. This gap between prediction and control motivates us to study how the priors acquired by video generation models can be used effectively by an action policy. We present ZERITH V2.5, a video-action model (VAM) in which the action policy reads intermediate features of a video generation model, and use it to study, under fixed demonstrations and a fixed total number of updates, what kind of predictive training improves subsequent action learning. We find that the way video predictive training is supervised affects subsequent action learning. In our experiments, adapting at many noise levels yields a large gain, while adapting only at the noise level used at deployment yields none. Weight-transfer experiments further show that the gain stays with the adapted weights when they remain in the video generation model and disappears when they are used only to initialize the action policy. Initial loss and gradient measurements at the start of joint training indicate that target-domain predictive training gives the video model a better starting state, making subsequent joint learning of prediction and action easier. Under matched data and training budgets, predictive adaptation improves control. We evaluate the complete policy on LIBERO, LIBERO-Plus, Meta-World MT50, and real-robot tasks.

cs.RO

新论文 · v1arXiv:2611.23644

Polymorph: Operating System Kernel Optimization Through Artificial Intelligence

Dean Sysman, Georgios Liargkovas, Tal Zussman, Hasan Zengin, Petra Hedesiu, Hubertus Franke, Tamar Eilam, Kostis Kaffes 等 9 位作者

原文摘要

While popular operating systems such as Linux and Windows were originally designed as monolithic kernels, an increasing number of kernel subsystems have become extensible using eBPF. Users can now define custom policies for essential kernel mechanisms, such as the process scheduler, page cache, and network stack, without recompiling the kernel. These mechanisms give developers significant freedom to fit the kernel to their applications' workloads, but the question of which policy to deploy remains open. We study how to use agentic AI to automate kernel policy development, selection, and deployment, focusing on the page cache and the process scheduler as two representative subsystems. We show that existing approaches fall short: evolutionary and agentic search runs offline, is relatively expensive, and often fails to generalize to online workloads, while online knob tuners are encumbered by the knobs' lack of expressivity. In contrast, we propose Polymorph, which learns online: an AI agent writes a generalized, granular policy once, and a user mode tuner adjusts its parameters during runtime, with no LLM in the loop. For the page cache, Polymorph improves throughput over Linux's LRU by 8.4% on unseen data, nearly twice the gain of the best existing policy, while adapting to workload changes at runtime and costing only 16M tokens once, versus 125-240M tokens per workload for agentic offline search. For the process scheduler, it improves on Linux's default by 2.75x across six workloads, versus 2.27x for the best fixed sched_ext policy.

cs.OS

新论文 · v1arXiv:2611.23397

Which Tokens, in What Order, and How Fast? A Theoretical Analysis of On-Policy Distillation Objectives

Hubert Strauss, Liam Fowl, Noam Razin

原文摘要

On-policy distillation (OPD) trains a student language model to match a teacher model based on its own generations. When using OPD, one must choose whether to apply it at the sequence or token level and which divergence to minimize. However, despite the wide adoption of OPD in practice, the formal understanding of which OPD objective is appropriate for a given setting is limited. Toward addressing this gap, we theoretically analyze how the choice of OPD objective governs which tokens are prioritized, in what order, and how efficiently. Our analysis reveals that sequence-level OPD exhibits a future agreement bias, which myopic token-level objectives avoid. This bias induces a reverse learning order, in which sequence-level OPD first matches the teacher at later token positions, while at earlier positions it can favor tokens that are improbable under the teacher, and thus often undesirable. As for the choice of divergence, we prove that it strongly influences the amenability of OPD to gradient-based optimization. In particular, while the forward KL divergence enjoys a well-behaved objective landscape, other $f$-divergences, such as reverse KL, can suffer from vanishing gradients even when the student and teacher are far apart. Across language model post-training settings, we demonstrate the implications of these theoretical findings for which OPD objective is preferable, highlighting the importance of accounting for the interplay between the student, teacher, and task at hand.

cs.LG · cs.AI · stat.ML

版本更新 · v2arXiv:2611.11249

Understanding When and Where Self-Supervised Speech Models Learn Phonemes and Prosodic Cues through Layer-Wise and Time-Resolved Probing

Masaru Tanibata, Shun Takahashi, Hiroki Ouchi, Sakriani Sakti

原文摘要

Self-supervised speech models (S3Ms) encode a rich hierarchy of acoustic, prosodic, and phonetic information, yet when and where it emerges during pretraining remains unclear. We train frozen-encoder probes on every Transformer layer across pretraining checkpoints of two matched models: HuBERT-Base, whose stage 2 is a separately initialized model trained on new pseudo-label targets, and single-objective wav2vec 2.0-Base. Our five tasks span an acoustic-to-abstract gradient: absolute pitch (F0), speaker-relative pitch, lexical stress, phoneme boundaries, and 38-way phoneme identity. Acoustic-prosodic cues and phone boundaries are decodable from the earliest checkpoints and barely shift across layers, whereas phoneme identity is constructed during pretraining, re-localizing to upper-middle layers under HuBERT's stage-2 targets at a matched update count. Acquisition order therefore tracks abstraction from the acoustic surface, not the segmental/suprasegmental distinction, extending to prosody an account established for phonetic, lexical and syntactic structure; the no-switch wav2vec 2.0 shows no comparable re-localization.

cs.CL

版本更新 · v2arXiv:2605.13171

Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics

Moritz Firsching, Paul Lezeau, Salvatore Mercuri, Miklós Z. Horváth, Yaël Dillies, Calle Sönne, Eric Wieser, Fred Zhang 等 11 位作者

原文摘要

As automated reasoning systems advance rapidly, there is a growing need for research-level formal mathematical problems to accurately evaluate their capabilities. To address this, we present Formal Conjectures (https://github.com/google-deepmind/formal-conjectures), an evolving benchmark of currently 7559 mathematical problem statements formalized in Lean 4. Sourced from areas of active mathematical research, the dataset features 1642 open research conjectures without known solutions for mathematical proof discovery, 2923 solved problems for proof auto-formalization, and 2994 supporting statements. Notably, the repository provides a structured interface connecting mathematicians who formalize and clarify problems with the AI systems and humans attempting to solve them. Demonstrating its immediate utility, the benchmark has already been leveraged for new mathematical discoveries, including the resolution of open research conjectures, and for the formal confirmation of major newly announced results. We describe our approach to ensuring the correctness of these formalizations in a collaborative open-source project where contributions stem from an active community. In this framework, AI-generated proofs and disproofs serve as a valuable auditing mechanism to iteratively improve the fidelity of the benchmark. Finally, we provide a standardized evaluation setup and report baseline results on frozen evaluation subsets, demonstrating a climbable signal that measures the current frontier of automated reasoning on research-level mathematics.

cs.AI

版本更新 · v2arXiv:2610.38386

Moments of Magic Squares: Line-Sum Conditions, a Permutation Threshold, and Random Energies

Kyle Elliott Mathewson

原文摘要

Every semi-magic square of order $n$ satisfies the axial moment identities $\sum_{i,j}s_{ij}j^m=\sum_{i,j}s_{ij}i^m=M(n)\sum_jj^m$ for all $m\ge1$, where $M(n)=n(n^2+1)/2$. For real matrices the converse requires $1\le m\le n-1$, whereas for arrangements of $\{1,\dots,n^2\}$ fewer moments suffice once $n\ge14$. We define the permutation threshold $k^*(n)$ as the least $k$ such that every arrangement satisfying these identities for $1\le m\le k$ is semi-magic. In terms of the column-sum deviations $γ_j$, the degree-$k$ conditions state that $\sum_jγ_jt^j$ is divisible by $(t-1)^{k+1}$, linking $k^*(n)$ to the Prouhet--Tarry--Escott problem. While Schur's bound on real zeros gives $k^*(n)\le\sqrt{2(n-1)\log(n^4/4)}$, we prove the converse realisability bound $k^*(n)\ge(\sqrt2-o(1))\sqrt n$ (and $k^*(n)\ge(\sqrt6-o(1))\sqrt n$ when $4\mid n$) by perturbing semi-magic squares with complementary row pairs via horizontal swaps. We also show that $k^*(n)=n-1$ for $3\le n\le13$, $k^*(n)=n-2$ for $14\le n\le17$, and $k^*(n)\le n-3$ for $n\ge18$, and determine $k^*(n)$ for $18\le n\le40$ with computer assistance. Finally, at the $k=1$ level of the hierarchy, we specialise the Mantel--Hubert quadratic assignment variance formula to obtain exact means, variances, and limit laws under a uniform random arrangement for the full line-sum energy $E_{\mathrm{full}}$, for the four-term energy $E_4$ combining the first moments and the two diagonals, and for Loly's moment of inertia, and find that $|L_4|=14,639,440$ arrangements of order $4$ satisfy $E_4=0$.

math.CO · cs.DM · math.NT · math.PR

新论文 · v1arXiv:2611.11063

Target Recoverability under Selective Labels: A Failure Mode in ECG-Based Acute Coronary Syndrome Prediction

Alexander Schubert, Anton Håkansson, Ziad Obermeyer

原文摘要

Medical machine learning models often learn from diagnoses observed only in patients clinicians chose to test. The biases of such selective labels are well known, but less understood is what happens when a diagnosis includes cases the model's inputs cannot detect. Because testing decisions draw on information the model does not see, these cases can appear predictable among tested patients, producing relationships that fail, and can even reverse, among the untested. We formalize this mechanism and show in simulations that it worsens as testing becomes more selective or undetectable cases more common, while models trained only on detectable cases remain informative. We empirically study electrocardiogram (ECG)-based prediction of acute coronary syndrome (ACS), which is confirmed only by invasive testing and whose subtypes differ in how clearly they appear on the ECG. Three ECG foundation models fine-tuned on revascularization, our ACS proxy, performed well among catheterized patients (AUROC 0.740-0.770) but worse than chance for 30-day major adverse cardiovascular events among untested patients (AUROC 0.381-0.478). Models trained on ECG-visible subtypes retained discrimination (AUROC 0.680-0.709), whereas a model trained on unstable angina, which can occur without ECG changes, was inversely related to risk (AUROC 0.310). Under selective labels, effective learning therefore requires prediction targets that can be inferred from the model's inputs and evaluation in the intended deployment population, which often extends beyond the patients who were tested.

cs.LG · cs.AI

版本更新 · v2arXiv:2602.00123

Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models

Filip Nowicki, Hubert Marciniak, Jakub Łączkowski, Bartosz Wilczek, Krzysztof Jassem, Tomasz Górecki, Vimala Balakrishnan, Desmond C. Ong 等 9 位作者

原文摘要

Vision-language models (VLMs) show promise for large-scale affect inference from images, but their alignment with human affective ratings remains unclear. We benchmarked 16 proprietary and open-source VLMs on three validated affective image datasets: the International Affective Picture System, the Nencki Affective Picture System, and the Library of AI-Generated Affective Images. In a zero-shot setting, models performed two tasks: (i) top-emotion classification and (ii) prediction of human ratings on 1--7/9 Likert scales for discrete emotions and affective dimensions. We also evaluated rater-conditioned prompting on the LAI-GAI dataset using de-identified participant metadata. Best models showed strong discrete emotion classification (60%--80% on six-emotion tasks; 60%--75% on a 12-category task), with anger and surprise predicted least accurately. For continuous ratings, models aligned moderately to strongly with human judgments ($r > 0.75$) but showed consistent biases, especially weaker performance on arousal and overestimation of response intensity. Rater-conditioned prompting had only small, inconsistent effects. Overall, VLMs captured broad affective patterns but sometimes lacked the nuance, although newer model generations performed better.

cs.HC · cs.CV

新论文 · v1arXiv:2611.09313

Asymmetric Correspondence Learning for Lexical and Style Embeddings: Interpreting Latent Space via Acoustic Features

Michael Whealing, Robert Gaizauskas, Thomas Hain

原文摘要

Self-supervised speech embeddings jointly encode lexical, speaker, and prosodic information, complicating feature isolation. We introduce Asymmetric Correspondence Learning (ACL), distilling HuBERT features into separate Acoustic Word Embeddings (AWEs) and Acoustic Style Embeddings (ASEs) via a split-latent correspondence bottleneck. Through probing and clustering evaluations on single-word utterances, we demonstrate that substantial variance from extrinsic sources remains encoded within each latent space, despite linear probing indicating the information has been stripped. Whilst the AWE space exhibits cohesive lexical clustering (AP$\approx$0.90, Fisher$\approx$6.28), linear probing on the ASE space achieves 97.9\% speaker accuracy across a diffuse topology (Fisher$\approx$1.01), yet preserves substantial lexical variance (Fisher$\approx$0.86) that remains linearly unrecoverable (0.17\%). To explain these findings, we apply group-level permutation feature importance over eGeMAPS acoustic features, finding that AWEs partition by vocal tract filters and ASEs by $F_0$ dynamics. These findings suggest that standard diagnostic benchmarks may be insufficient for verifying feature isolation, as substantial speech structure can be retained even when it remains entirely hidden from probes.

cs.CL · cs.SD

版本更新 · v2arXiv:2607.10456

Integrating Background Knowledge for Scalable Causal Discovery

Mátyás Schubert, Theofanis Aslanidis, Tom Claassen, Sara Magliacane

原文摘要

Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy of the learned structure, but also in reducing the space of candidate causal graphs. As causal discovery can become computationally expensive for large number of variables, it is crucial to utilize background knowledge effectively during the causal discovery process. However, most current methods only use background knowledge in a postprocessing step after causal discovery to refine the learned graph. In this work, we develop a framework for utilizing background knowledge during the causal discovery process, focusing especially on scalable causal discovery methods that recover only a subset of the whole graph. We implement our framework for multiple algorithms and empirically show that utilizing background knowledge can both reduce computational requirements and increase the quality of the learned structures.

stat.ML · cs.LG

版本更新 · v2arXiv:2610.23975

FrameScout: Scouting Query-Relevant Frames for Long Video Understanding

Haonan Hu, Shuhao Chen, Weisen Jiang, Lizhao Gao, James Kwok, Yu Zhang

原文摘要

Long video understanding requires VideoLLMs to answer queries about videos spanning tens of minutes to hours, but such long videos produce far more visual tokens than current VideoLLMs can process. To address this issue, keyframe selectors are proposed to select the most query-relevant frames by computing the similarity between frame and query embeddings. Existing selectors either encode frames independently without temporal context or process chunks in isolation with ranking objectives that are difficult to optimize. To alleviate those limitations, we propose FrameScout with two core designs: (i) a streaming selector architecture that leverages a sliding-window KV cache and successor aggregation to produce temporally-contextualized frame embeddings; (ii) a frame-query contrastive objective that aligns frame and query embeddings in a shared space, directly training the selector to distinguish relevant frames from irrelevant ones. Extensive experiments on three long-video benchmarks and six base VideoLLMs demonstrate that FrameScout consistently achieves state-of-the-art performance. Code is available at https://github.com/Hubert-1102/FrameScout.

cs.CV · cs.LG

版本更新 · v2arXiv:2609.18772

手语手形的零样本跨语言识别

Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes

Marcel Granero-Moya, Carolina del Corral Farrarós, Gloria Haro, Coloma Ballester, Ricardo Marques

AI 速读 基于摘要

作者提出首个手形零样本跨语言框架,将 ASL 模型迁移到加泰罗尼亚手语(LSC),并借助共享的音系特征分解实现无目标语言训练标签的识别。

cs.CL · cs.CV

查看原文摘要

Sign language processing advances rapidly for high-resource languages such as American Sign Language (ASL), yet most of the world's sign languages lack the phonological annotations new methods require. We present the first zero-shot cross-lingual framework for handshape recognition, transferring from ASL to Catalan Sign Language (LSC). Our approach leverages the decomposition of handshapes into five phonological features -- selected fingers, flexion, spread, thumb position, and thumb contact -- shared across both languages, to decode LSC handshapes from predicted features via a composite phonological distance metric. We evaluate three architectures (MLP, SL-GCN, SHuBERT) trained on two ASL corpora (PopSign, Sem-Lex) against a 37-handshape, single-signer LSC benchmark. Zero-shot transfer proves viable once recording-format disparities are harmonized, reaching 80.0% phonological feature accuracy and 54.5% expected handshape accuracy. Phonological decomposition thus offers a bridge for extending sign language technologies to low-resource languages without any target-language video training labels.

版本更新 · v2arXiv:2609.28226

Pinpointing Super-Quadratic Quantum Enumeration Speedups: Exact and Certified Evaluation of the Guessing-Moment Exponent under Product-Distribution Advice

Carsten Schubert, Niklas Paskarbeit, Maximilian J. Kramer, Jean-Pierre Seifert, Marian Margraf

原文摘要

Grover's algorithm gives an optimal quadratic query advantage for black-box search. In cryptanalysis, however, the search often comes with additional probabilistic advice over the candidates, frequently of product form, e.g. from side-channel leakage on independent key coordinates. Classically, guessing in likelihood order is optimal in expectation. In the quantum setting, Montanaro showed how to achieve an optimal expected query complexity, beating plain Grover on every non-uniform advice distribution (up to a constant overhead factor). What has been missing so far is a finite-size method for evaluating the quantum-classical guessing-moment separation induced by a given advice distribution. We provide such a method for product-distribution advice, thereby sharpening the previous entropy-based estimate of Bashiri et al. We reduce the classical and quantum guessing moments to functionals of the one-dimensional surprisal distribution, obtained for product advice by convolving the per-coordinate surprisal laws. When the surprisals lie on a common arithmetic grid (the commensurate case), the logarithmic moments and hence the speedup exponent can be evaluated as finite sums without discretization error; exponential tilting makes this computation numerically stable. For general product advice, we discretize the surprisals onto a common grid and derive an a-posteriori bound on the resulting binning error. We apply the framework to cold-boot leakage on seeds and block-cipher keys, to template-attack posteriors, and to synthetic i.i.d. Bernoulli posteriors calibrated to average residual ranks reported for Keccak side-channel attacks on ML-KEM and ML-DSA. The resulting exponents substantially exceed 2 in several skewed-advice settings, reaching 3.92 for cold-boot advice and 3.12 in the synthetic models, and include cases where the previous entropy-based bound did not establish an exponent above 2.

cs.CR

新论文 · v1arXiv:2610.37585HF 社区推荐

Timestral

Adrien Petralia, Alexandre Gavaudan, Artjom Joosen, Etienne Goffinet, Richard Kurle, Yassine El Ouahidi, Yassir Bendou, Abdelaziz Bounhar 等 356 位作者

原文摘要

We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with three ingredients: Decoupled Horizon Forecasting (DHF), which separates prediction tokens from the causally encoded context, so that longer horizons are trained without masking context and each observed value is both a forecast target and context for later forecasts; a covariate framework that natively supports known-future covariates within a causal architecture; and a two-stage pipeline that pretrains exclusively on a diverse, large-scale synthetic corpus before post-training on a mix of real and synthetic data with extended context. This report describes the model design and its benchmark results. Weights for all four models are available on Hugging Face and inference code on GitHub.

cs.AI

新论文 · v1arXiv:2610.37390

LinMix: Data Mixing as Linear Domain Attribution

Hubert Baniecki, Przemyslaw Biecek, Martin Pawelczyk

原文摘要

Language model performance depends strongly on the mixture of domains in the pretraining data corpus. Popular data mixing methods select these domain weights by training many small proxy models on random mixes and then fitting a regression model to predict performance from the mix. We recognize this practice as a domain attribution problem, where the regression measures each domain's contribution to the target metric. Through this lens, the standard Dirichlet sampling of proxy data mixes is a poor regression design that requires tuning and cannot support a linear fit for hundreds of domains. Building on classical optimal experimental design, we introduce LinMix, which samples mixes at the vertices of the capped simplex so that each domain is at its cap or absent. This hyperparameter-free vertex sampling decorrelates domain effects, enabling an interpretable linear model whose coefficients are the domain attributions. The optimal mix given by LinMix provably keeps only domains with positive attribution values and requires no search over candidate mixes. We further establish the optimality of vertex sampling, and prove that Dirichlet sampling inflates the attribution error when its mixes concentrate around the prior data mix. Pretraining experiments with 1B-parameter OLMo2 and 4B Qwen3.5 language models show that LinMix outperforms Dirichlet-based data mixing across reasoning, code, and math benchmarks, with relative gains of 46% on MBPP and 14% on GSM8K. At 288 fine-grained domains, only vertex sampling supports a linear fit, and LinMix improves benchmark accuracy by 11% on average over the best nonlinear baseline.

cs.LG · cs.CL · stat.ML

版本更新 · v2arXiv:2610.18726Apple ML Research

通过语音基础模型中的语言选择性维度进行语码转换检测

Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models

Jie Chi, Zakaria Aldeneh, Masha Fedzechkina, Maureen de Seyssel, Natalie Schluter

AI 速读 基于摘要

利用预训练语音编码器中语言选择性的隐状态维度,直接从语音帧级激活判断一句话内是否出现语码转换。

cs.CL

查看原文摘要

Code-switching (CS), the alternation between languages within an utterance, is common in multilingual speech but underrepresented in pretraining corpora. Increasing CS coverage requires finding relevant utterances in large speech collections so that they can be included in training data. One way to find such utterances is to transcribe the speech and detect language alternation in the text, but this depends on obtaining accurate multilingual transcriptions. We propose a lightweight method that detects CS directly from speech. It uses frame-level language information in pretrained speech encoders to determine whether both languages are present within an utterance. Specifically, we identify language-selective hidden-state dimensions using monolingual recordings and aggregate their frame-level activations into a CS prediction. With a small CS set used to tune a decision rule, we show that the Whisper-small encoder achieves a mean F1 of $0.798$ across 14 language pairs in CS-FLEURS, compared with $0.776$ for a CNN and $0.751$ for a HuBERT linear baseline trained for monolingual language identification. Our findings suggest that pretrained speech encoders already encode the information needed to identify CS utterances, and they provide a lightweight tool for building more representative multilingual corpora.

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.24ACL Anthology · ACL 2026

MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery

Angelo Ortiz Tandazo Ecole Normale Supérieure – PSL, Manel Khentout L'École des hautes études en sciences sociales, Youssef Benchekroun Facebook, Thomas Hueber CNRS, Emmanuel Dupoux EHESS

原文摘要

This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the-art multilingual self-supervised learning models. Additionally, the models effectively adapt to unseen languages and casual speech with minimal self-supervised fine-tuning (10 hours of speech). This establishes an effective approach for instilling linguistic inductive biases in self-supervised speech models.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.470ACL Anthology · ACL 2026

An Exploration of Mamba for Speech Self-Supervised Models

Tzu-Quan Lin National Taiwan University, Heng-Cheng Kuo, Tzu-Chieh Wei University of Michigan - Ann Arbor, Hsi-Chun Cheng National Taiwan University, Chun Wei Chen National Taiwan University, Hsien-Fu Hsiao, Yu Tsao Academia Sinica, Hung-yi Lee National Taiwan University

原文摘要

While Mamba has demonstrated strong performance in language modeling, its potential as a speech self-supervised learning (SSL) model remains underexplored, with prior studies limited to isolated tasks. To address this, we explore Mamba-based HuBERT models as alternatives to Transformer-based SSL architectures. Leveraging the linear-time Selective State Space, these models enable fine-tuning on long-context ASR with significantly lower compute. Moreover, they show superior performance when fine-tuned for streaming ASR. Beyond fine-tuning, these models show competitive performance on SUPERB probing benchmarks, particularly in causal settings. Our analysis shows that they yield higher-quality quantized representations and capture speaker-related features more distinctly than Transformer-based models. These findings highlight Mamba-based SSL as a promising and complementary direction for long-sequence modeling, real-time speech modeling, and speech unit extraction. The codebase is available at https://github.com/hckuo145/Mamba-based-HuBERT.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-short.26ACL Anthology · ACL 2026

Privacy-preserving Prosody Representation Learning

Kevin Everson University of Washington, Mari Ostendorf University of Washington

原文摘要

Speech representations that capture prosodic information can be useful for both understanding and generation. However, speaker characteristics are reflected in acoustic-prosodic features (e.g., pitch). To address privacy concerns from the leakage of identity information, we propose a new self-supervised approach to learning prosody representations that incorporates speaker disentanglement strategies. We evaluate our encoder on three tasks to probe representation capabilities, including pitch reconstruction and detection of different prosodic events. Our encoder outperforms raw prosody and HuBERT-base baselines, achieving strong speaker disentanglement without adverse impact on prosody-related downstream tasks.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · 2026 · 正式发表

首次观测 · 记录 #1CVF · CVPR 2026:cvf:ef33cd5575725083801cca53a255d578CVF · CVPR 2026

WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios

Xu, Runsheng, Lin, Hubert, Jeon, Wonseok, Feng, Hao, Zou, Yuliang, Sun, Liting, Gorman, John, Tolstaya, Kate 等 14 位作者

原文摘要

Vision-based end-to-end (E2E) driving has garnered interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios paired with existing open-loop evaluation metrics that fall short in capturing the multimodal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that are rare in daily life with an occurring frequency of less than 0.03%. Each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional distance-based metrics, RFS measures how closely a predicted trajectory matches rater-annotated trajectory preference labels. WOD-E2E includes rater preference labels for validation, and a separate held out test set is used for the 2025 WOD-E2E Challenge benchmark leaderboard.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

版本更新 · v3arXiv:1912.04977Google Research

联邦学习的进展与开放问题

Advances and Open Problems in Federated Learning

Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles 等 59 位作者

AI 速读 基于摘要

一篇综述性论文,梳理联邦学习的研究进展并系统列出开放问题与挑战。

cs.LG · cs.CR · stat.ML

查看原文摘要

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

版本更新 · v2arXiv:1811.03604Google Research

面向移动键盘预测的联邦学习

Federated Learning for Mobile Keyboard Prediction

Andrew Hard, Kanishka Rao, Rajiv Mathews, Swaroop Ramaswamy, Françoise Beaufays, Sean Augenstein, Hubert Eichner, Chloé Kiddon 等 9 位作者

AI 速读 基于摘要

作者在智能手机虚拟键盘的下一词预测任务上,用联邦平均算法在客户端设备上训练循环神经网络语言模型,并与服务器端随机梯度下降训练进行比较,报告联邦方法取得更好的预测召回率。

cs.CL

查看原文摘要

We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual keyboard for smartphones. Server-based training using stochastic gradient descent is compared with training on client devices using the Federated Averaging algorithm. The federated algorithm, which enables training on a higher-quality dataset for this use case, is shown to achieve better prediction recall. This work demonstrates the feasibility and benefit of training language models on client devices without exporting sensitive user data to servers. The federated learning environment gives users greater control over the use of their data and simplifies the task of incorporating privacy by default with distributed training and aggregation across a population of client devices.