跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-15 14:40 — 2026-11-16 14:40(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

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

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,827 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
新论文 · v1arXiv:2611.14003

Spatio-Temporal Calibration of a Vehicle-Mounted Microphone Array for Autonomous Driving

Marvin Seegert, Richard Taupitz, Korbinian Moller, Johannes Betz

原文摘要

Microphones let an autonomous vehicle sense into areas its cameras and LiDAR cannot see, by picking up the sound that other traffic participants emit. Locating those sources and fusing them with the visual perception requires the microphone array to be calibrated and registered relative to the vehicle's other sensors. Existing calibration methods assume small, unobstructed indoor rigs, whereas a vehicle body casts an acoustic shadow that straight-line propagation cannot represent, and to our knowledge no calibration of an array distributed around a vehicle has been reported. We propose a pipeline that uses a balloon burst as a single cross-modal target, which the LiDAR locates in metric coordinates, every microphone hears as a sharp onset and a camera times. Each observation is weighted by its own timing variance, which discounts shadowed arrivals instead of discarding them and needs no model of the vehicle. On a full-size vehicle with eight microphones over a 4.9 m aperture, the held-out range residual of 6.37 cm approaches the 6.07 cm floor set by the onset timing noise, and the calibrated array tracks a moving source to within a few degrees of the vehicle's own LiDAR. A dozen bursts spread around the vehicle suffice, and spreading them matters more than adding more.

cs.SD · eess.AS

新论文 · v1arXiv:2611.13997

Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models

Xingqi Wang, Xiaoyuan Yi, Xing Xie, Jia Jia

原文摘要

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities but raise significant privacy concerns due to their abilities to infer sensitive personal information from images with high precision. While current LVLMs are relatively well aligned to protect universal privacy, e.g., credit card data, we argue that privacy is inherently personalized and context-dependent. This work pivots towards a novel task: can LVLMs achieve Inference-Time Personalized Privacy Protection (ITP$^3$), allowing users to dynamically specify privacy boundaries through language specifications? To this end, we present SPY-Bench, the first systematic assessment of ITP$^3$ ability, which comprises (1) 32,700 unique samples with image-question pairs and personalized privacy instructions across 67 categories and 24 real-world scenarios, and (2) novel metrics grounded in user specifications and context awareness. Benchmarking the ITP$^3$ ability of 21 SOTA LVLMs, we reveal that: (i) most models, even the top-performing o4-mini, perform poorly, with only $\sim$24% compliance accuracy; (ii) they show quite limited contextual privacy understanding capability. Therefore, we implemented initial ITP$^3$ alignment methods, including a novel Noise Contrastive Alignment variant which achieves 96.88% accuracy while maintaining reasonable general performance. These results mark an initial step towards the ethical deployment of more controllable LVLMs. Code and data are available at https://github.com/achernarwang/specify-privacy-yourself

cs.CV · cs.AI · cs.CL · cs.CY · cs.LG

新论文 · v1arXiv:2611.13995

Lipschitz-Controlled Flow Matching for Robust Image Restoration

Sedjro Salomon Hotegni, Konstantin Sonntag, Paul-Christian Bürkner, Sebastian Peitz

原文摘要

Flow-matching models can produce high-quality image restorations, but their learned dynamics may amplify small input perturbations and make reconstructions unstable. We introduce LipsFlower to reduce this amplification. We derive stability bounds for Flow-from-$Y$, which initializes the ordinary differential equation from a noise-perturbed observation, as well as for observation-conditioned posterior sampling, which conditions the velocity field on the observation throughout integration. Based on this analysis, we develop LipHDiT, a Lipschitz-aware hourglass diffusion transformer that serves as the vector-field architecture of LipsFlower. LipHDiT incorporates stabilized approximate spectral normalization, bounded modulation, and convex residual mixing. We also use adversarial finite-radius gain regularization at sampled interpolation states to penalize excessive sensitivity to the state and, for conditional sampling, the observation. We test both formulations on blind face restoration, measuring adversarial robustness and the perceptual quality of the reconstructions. LipsFlower reduces perturbation amplification while keeping restoration quality competitive with the evaluated baselines. These results suggest that Lipschitz-aware flow matching can improve the stability of generative image restoration.

cs.CV

新论文 · v1arXiv:2611.13994

BioXArena-Pro: a research-grade benchmark for autonomous biomedical machine learning agents

Loka Li, Duzhen Zhang, Xingbo Du, Leonard Song, Kun Zhang, Le Song

原文摘要

Coding agents are increasingly proposed as autonomous builders of biomedical models, but existing benchmarks are small, near saturation or open to leaked information. We present BioXArena-Pro, 64 research-level modelling tasks from eight biomedical domains, each rebuilt from a published study; most hold out whole biological units such as species or cohorts. Across 22 agent configurations, the best scores 55.1 of 100, and the scaffold matters almost as much as the model. We re-ran a published method for every task: where the published recipe applies unchanged, the best agent and the methods tie; on rebuilt tasks the methods trail by 8.2 points, suggesting that agents gain by adapting to new data. Pretrained models (including biological foundation models) matter where the strongest agent uses them: forbidding them decreases its score on those tasks by 9 points. Every task was audited in several AI-assisted rounds and a final human review.

cs.LG

新论文 · v1arXiv:2611.13993

Temporal Behavior Trees for Reinforcement Learning: Specifications as Rewards, Curricula, and Diagnostics

Vladimir Krsmanovic, Bernd Finkbeiner

原文摘要

Reinforcement learning from formal specifications often separates task definition, reward shaping, curriculum design, and policy diagnostics into different mathematical objects. This fragmentation requires additional conversion steps and discards structure already present in the specification, such as subtask boundaries, ordering constraints, and quantitative measures. We introduce TBTCL (Temporal Behavior Tree Centric Learning), a framework that uses Temporal Behavior Trees (TBTs) as a unified interface for specification-guided reinforcement learning. A single TBT specifies the task, induces dense robustness-based rewards, defines a curriculum, and supports better understanding of learned policies. By adapting TBT syntax and semantics for specification-guided reinforcement learning, we provide a formalism that is more expressive than popular specification languages such as LTL and inherently hierarchical. We present algorithms to automatically extract a curriculum DAG and derive dense, robustness-based rewards directly from TBT semantics. Furthermore, we utilize TBT trace segmentation to build understandable competence profiles and automatically adapt the reward toward bottlenecks. We evaluate TBTCL on six specifications across discrete and continuous domains and show that Temporal Behavior Trees can serve as a specification, a reward, a curriculum, and a diagnostic.

cs.LG

新论文 · v1arXiv:2611.13992

Pulse or Provenance? What rPPG-Based Deepfake Detectors Learn

Othmane Harraq, Tamer Aldwairi

原文摘要

Remote photoplethysmography (rPPG) has been proposed as a physiological cue for deepfake detection, based on the premise that synthesized faces lack a genuine cardiac signal. We examine what rPPG-style detectors learn on Celeb-DF++ (22 forgery methods) and FaceForensics++ (FF++), using one identically sampled window per real and fake video. On talking-face forgeries, simple chrominance traces reach an AUC of 0.998, exceeding a dedicated rPPG extractor (0.87). Controlled experiments indicate that this signal is not physiological in origin. On fully synthesized forgeries, it is equally discriminative when extracted from background regions or from full frames without face detection, and it is concentrated above the 0.7 to 4 Hz heart-rate band. It is largely removed by shuffling frame order but persists after normalizing resolution, frame rate and encoding, and an independent reimplementation reproduces these findings. Removing high-frequency content makes most synthesized videos appear real, adding it makes real videos appear fake, and injecting a synthetic pulse has little effect. In controlled self-reenactment experiments with two generators, animating a face from a single frame introduces the same high-frequency signal, whereas reconstructing each frame from its own source does not. Face-based chrominance detectors trained on Celeb-DF++ classify over 99% of real FF++ videos as fake, indicating that they largely encode video source rather than manipulation, and a CLIP-based detector exhibits the same behavior. A frozen CLIP backbone matches or exceeds fusions of CLIP with rPPG and frequency features. Finally, we show that the official Celeb-DF and Celeb-DF++ splits share identities and source-video content between training and test, and that custom protocols reusing test videos and identities in training inflate weaker detectors by up to 0.30 AUC.

cs.CV · cs.CR · cs.LG

新论文 · v1arXiv:2611.13991

Universal Approximation Theorem for Metaplectic Neural Operators

Ahmed Abdeljawad, Malek Yacine Rezoug

原文摘要

We prove universal approximation for metaplectic neural operators on nonempty bounded Lipschitz domains. The nonlocal branches are whole-space metaplectic multipliers with zero extension and restriction, associated with any fixed free symplectic matrix. Assuming a smooth, globally Lipschitz, nonpolynomial activation, we obtain compact-uniform approximation of continuous operators from $C^s$ to $C^r$ and from $H^s$ to $H^r$ in the respective output norms, for arbitrary nonnegative integers $s,r$ and finite input and output channel dimensions. In the Sobolev setting, compact input sets must additionally be uniformly bounded in $L^\infty$. One hidden operator layer with one nonlocal branch suffices. A single scalar symbol atom and finitely many positional features are prescribed by the transform and domain independently of the target operator, compact set and accuracy. The proof combines averaging neural operator theory with an exact chirp-conjugated averaging identity and derivative estimates. The result includes Fourier and fixed nondegenerate fractional Fourier multiplier constructions.

cs.LG · math.FA

版本更新 · v2arXiv:2610.17991

DORIS: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration

Wenshuo Zhang, Xiangyue Zhang, Junlin Li, Wenjie Tian, Yubo Zheng, Zhixin Dong, Hongli Xu, Jingyu Ru 等 9 位作者

原文摘要

Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an effective source of complementary physical cues for recovering target radiance under clear-water conditions. However, existing methods have yet to jointly model raw intensity information and polarization cues to enable image restoration driven by an understanding of mixed underwater degradations. To overcome these limitations, we propose DORIS, a unified multimodal language-driven framework that jointly uses polarization and RGB information to generate textual descriptions of degradation types and severity levels through structured semantic instructions and enhances joint restoration representations under the guidance of degradation-aware semantic features to improve restoration robustness under mixed degradations. We further construct a new benchmark named MixPolar, which contains underwater images exhibiting real degradations and the corresponding annotations. It supports systematic evaluation of degradation perception, image restoration, and downstream task performance. Extensive experiments demonstrate that our method effectively integrates polarization and RGB information, achieving competitive performance in degradation perception and image restoration.

cs.CV

新论文 · v1arXiv:2611.13990

On the information rate of phones, syllables and words

Herman Kamper

原文摘要

Which linguistic units minimise the bitrate required to encode speech content: phones, syllables, words, maybe larger units, or something in between? This question has implications for the development of speech and language systems and theories of human language processing. Using a transcribed corpus of 960 hours of English audiobooks, I compare the information rates of phones, syllables, words, multi-word combinations and intermediate tokenisations. While all units are equivalent under a perfect language model, it makes sense to compare these under limited modelling budgets; I use $n$-gram and transformer language models. The lowest bitrates are achieved using words, with slightly longer units sometimes performing best. The results show that, when modelling capacity is limited, units larger than syllables but smaller than long multi-word phrases provide the most efficient representation in terms of information rate.

cs.CL · eess.AS

版本更新 · v5arXiv:2507.01835

Filter-Enhanced Smartphone Hyperspectral Imaging

Daniil Reutsky, Daniil Vladimirov, Yasin Mamedov, Georgy Perevozchikov, Nancy Mehta, Egor Ershov, Radu Timofte

原文摘要

Hyperspectral reconstruction from RGB imagery offers an affordable alternative to costly hyperspectral acquisition devices. However, its accuracy is fundamentally constrained by the limited spectral resolution of standard RGB cameras. In this paper, we propose a new approach that leverages the multi-camera systems integrated into most modern smartphones and enhances their capabilities by modulating their spectral response functions using carefully selected spectral filters, enabling a smartphone to capture richer spectral information. We propose a neural network able to exploit auxiliary RGB images with diverse spectral characteristics, enabling more accurate hyperspectral reconstruction compared to conventional single-image methods. Training is supported by a newly collected dataset, Doomer, which consists of multiple misaligned RGB images alongside corresponding hyperspectral data. We also propose a device-adaptation strategy that conditions the multi-image hyperspectral reconstruction network on camera color correction matrices available in standard DNG metadata, requiring no real images from the target device. We evaluate it on three physical smartphones, two of them unseen during training.

cs.CV

版本更新 · v2arXiv:2606.24324

Prague Dependency Treebank -- Consolidated 2.0: Enriching a Complex Annotation Scheme

Marie Mikulová, Jiří Mírovský, Milan Straka, Pavlína Synková, Jan Štěpánek, Barbora Štěpánková, Jan Hajič

原文摘要

The Prague Dependency Treebank framework is unique in its attempt to systematically include and link different layers of language, including a meaning representation with several types of inter-sentential phenomena, especially coreference and discourse relations. We present its second consolidated version (PDT-C 2.0), which concludes almost 30-years long project of sustained development of the resource to a uniformly and coherently annotated, genre-diversified, almost 4 million token language resource of Czech language, with accompanying fully compatible lexicons. In addition to continuous linguistic research, the richly linguistically annotated corpus is also widely used in international comparisons of the development of traditional and novel NLP tools as well as in conversions into other formalisms. The corpus and the trained parsers are available under the CC BY-NC-SA licence.

cs.CL

新论文 · v1arXiv:2611.13984

Bounded Weighted Edit Distance with Metric Costs

Jihan Wang

原文摘要

We give a deterministic $O(n+k^2)$-time algorithm for bounded weighted edit distance when the input costs form an integer metric on the alphabet extended by a gap symbol. Here $n$ is the total input length and $k$ is the given threshold on the distance. If the distance is at most $k$, the algorithm returns it with an optimal alignment. Otherwise, it reports that the distance exceeds $k$. The running time matches the classical unit-cost bound and is independent of the alphabet size and of the largest cost. The algorithm keeps only the farthest-reaching prefix alignment for each cost and each difference between the total gap costs of the aligned prefixes. For real metrics whose nonzero costs are at least one, scaling and upward rounding give a $(1+\varepsilon)$-approximation for the bounded problem in $\widetilde{O}(n+(k/\varepsilon)^2)$ time. If insertions and deletions have integer costs, the running time improves to $\widetilde{O}(n+k^2/\varepsilon)$.

cs.DS

版本更新 · v2arXiv:2602.02212

3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds

Zheyuan Zhou, Liang Du, Zixun Sun, Xiaoyu Zhou, Ruimin Ye, Qihao Chen, Yinda Chen, Lemiao Qiu

原文摘要

Despite advances in vision-language-action (VLA) models, they remain limited in highly dynamic game settings such as 3D open worlds and competitive player versus player (PvP) settings, where agents must efficiently extract sparse, actionable signals from dense visual input while integrating multimodal cues to track off-screen high-value targets in real time. To address this, we introduce 3A-VLA (Abstraction-Aligned Action VLA), a framework that grounds action learning in explicit intention and environment abstractions rather than superficial pattern matching. We introduce dual task-agnostic abstractions: the intention abstraction (IA), which condenses verbose instructions and reasoning into explicit semantic primitives, and the environment semantics abstraction (ESA), which structures dense visual streams into a spatial-functional affordance representation to guide grounded actions. We further propose an abstraction alignment reweighting (AAR) module that adaptively reweights the action imitation loss. A continuous intention-environment alignment signal is used to emphasize reliable action supervision when abstractions agree and reduce the influence of ambiguous demonstrations when they diverge, thereby learning a policy that balances fine-grained control and high-level reasoning without the need for manual rules. Extensive experiments show that 3A-VLA performs competitively among the evaluated baselines in both open-world (Minecraft) and competitive PvP (Game for Peace) settings. It also demonstrates zero-shot combat transfer from Game for Peace to high-fidelity games, including Valorant, CS2, GTA V, Elden Ring, and Mount & Blade.

cs.CV

版本更新 · v3arXiv:2605.22715

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim

原文摘要

As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inertial signals are highly dependent on the sensing setup, including body location, mounting position, sensor orientation, device hardware, and sampling protocol. This setup dependence makes it difficult to learn motion representations that transfer across devices and datasets, and limits the broader use of wearable IMUs beyond closed-set recognition. We introduce AnyMo, a geometry-aware framework for setup-agnostic human motion modeling. AnyMo uses physics-grounded IMU simulation over dense body-surface placements to generate diverse and plausible synthetic signals, pre-trains a graph encoder from paired synthetic placement views and masked partial observations, tokenizes multi-position IMU into full-body motion tokens, and aligns these tokens with an LLM for motion-language understanding. We evaluate AnyMo on three complementary tasks: zero-shot activity recognition across 14 unseen downstream datasets, cross-modal retrieval, and wearable IMU motion captioning, where it improves average Accuracy/F1/R@2 by 11.7\%/11.6\%/22.6\% on HAR, increases zero-shot IMU-to-text and text-to-IMU retrieval MRR by 15.9\% and 28.6\%, respectively, and improves zero-shot captioning BERT-F1 by 7.5\%. These results support AnyMo as a generalist model for wearable motion understanding in the wild. Project page: https://anymo-project.github.io.

cs.CV · cs.AI · cs.CL · cs.HC

新论文 · v1arXiv:2611.13983

Optimization-Based Path Planning for Industrial Manipulators: Experimental Validation in Additive Manufacturing

Shiva Ganesh Murali, Valentin Bhend, Deepak Ingole, Gabriele Fadini, Alisa Rupenyan

原文摘要

Robotic additive manufacturing requires joint paths that reconcile robot feasibility with process-specific geometry. We develop an offline optimization-based path planner that combines joint-path regularity and self-collision penalties with process costs and constraints, so that a new process enters through its own reference, residuals, and tolerances. Full-path and boundary-coupled chunked optimization handle references of different lengths. Iterative Weight Tuning (IWT) determines the cost weights from the gaps between Key Performance Indicators (KPIs) and their targets. In carbon-fiber winding and robotic 3D printing, the planned paths meet the geometric tolerances and all KPI targets, and both paths are executed on a UR10e, without extrusion for printing, with joint-level tracking recorded during execution.

cs.RO · math.OC

版本更新 · v3arXiv:2610.30468

SplatLab: Autonomous Scientific Discovery for 3DGS Research

Seemandhar Jain, Manmohan Chandraker

原文摘要

Scientific discovery requires more than generating hypotheses: ideas must be grounded in prior work, translated into executable methods, experimentally validated, challenged by counterevidence, and communicated through reproducible findings. Despite recent advances in autonomous research agents, closing this entire loop remains challenging in rapidly evolving computer-vision fields with complex training pipelines and expensive evaluations. We introduce SplatLab, an autonomous scientific discovery system for 3D Gaussian Splatting (3DGS) that integrates literature understanding, hypothesis generation, implementation, experimental refinement, falsification, and manuscript writing into a unified research pipeline. Given a research prompt, a target-paper URL, or no input at all, SplatLab identifies research opportunities, proposes novel methods, trains and ablates candidates across Mip-NeRF 360 and LLFF, and produces manuscripts grounded in verifiable experimental evidence. Unlike prior systems, SplatLab performs discovery over verified baseline implementations using domain-aligned modification scaffolds. A cascade-weighted Elo tournament evolves candidate methods using measured GPU performance and verbal-gradient feedback, while a standing falsifier incorporates adversarial stress testing directly into selection. An integrity audit binds reported claims to logged experiments, and reviewer-driven feedback can initiate further experimentation rather than merely revising text. SplatLab discovers methods achieving PSNR improvements of +0.18 to +3.78 dB over matched baselines, including +3.78 dB on astrophotographic nebula rendering, a previously unexplored setting for 3DGS. By closing the loop between scientific reasoning, executable experimentation, and evidence-backed communication, SplatLab compresses months of researcher effort into days of mostly autonomous compute.

cs.CV · cs.AI

版本更新 · v2arXiv:2606.24366

MorfFlex: Handling Rich Morphology

Jaroslava Hlaváčová, Marie Mikulová, Barbora Štěpánková, Milan Straka, Jan Hajič

原文摘要

We present MorfFlex, a morphological dictionary architecture suitable for languages with extensive regularity in both inflection and derivation. As the primary example of MorfFlex in use we introduce MorfFlex CZ, a morphological dictionary of Czech. It is distributed as a simple, unstructured list of <wordform, lemma, tag> triplets, however, its manually maintained, unpublished source files and conversion scripts encode a sophisticated system of inflectional and derivational patterns. These patterns dramatically reduce the otherwise enormous size of the dictionary, which currently contains over 100 million wordforms and more than 1 million lemmas. The MorfFlex CZ dictionary serves as an essential resource for ensuring the consistency of manual morphological annotation in the Prague Dependency Treebanks and underpins state-of-the-art automatic tools such as MorphoDiTa. In this paper, we focus on: (i) presenting an effective method for managing the rich morphological system within the dictionary, and (ii) demonstrating the utility of such a language resource for maintaining annotation consistency in corpora and supporting the development of advanced NLP applications.

cs.CL

版本更新 · v2arXiv:2405.20057

A General Automata Model for First-Order Temporal Logics (Extended Version)

Luca Geatti, Alessandro Gianola, Nicola Gigante

原文摘要

First-order linear temporal logic (FO-LTL) is a flexible and expressive formalism capable of naturally describing complex behaviors and properties. Although the logic is in general highly undecidable, the idea of using it as a specification language for the verification of complex infinite-state systems is appealing. However, a missing piece, which has proved to be an invaluable tool in dealing with other temporal logics, is an automaton model capable of capturing the logic. In this paper we address this issue, by defining and studying such a model, which we call first-order automaton. We define this very general class of automata, and the corresponding notion of regular first-order language (of finite words), showing their closure under most language-theoretic operations. We show how they can capture any FO-LTL formula over finite words, over any signature and theory, and provide sufficient conditions for the semi-decidability of their non-emptiness problem. Then, to show the usefulness of the formalism, we prove the decidability of monodic FO-LTL, a classic result known in the literature, with a simpler and direct proof.

cs.LO

版本更新 · v2arXiv:2611.10693

Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception?

Liwei Liu, Jun Tao, Xingyuan Li, Xuenan Xu, Chen Zhang, Junyi Wang, Boya Zhang, Xiaoyu Yang 等 11 位作者

原文摘要

Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope remains largely human-centric, focusing on what humans can directly see or hear. This progress raises the prospect of perception beyond human limits, such as extending hearing to sounds that are inaudible to humans. More broadly, the physical world is full of waves, vibrations, and oscillations, only a small fraction of which are directly audible to humans. This invites the extension of multimodal LLMs toward a broader form of machine hearing, which remains largely underexplored. To investigate this direction, we introduce the Machine Hearing Benchmark (MHB), comprising 6,128 instances across 13 tasks and seven domains. MHB spans highly heterogeneous input regimes, with sampling rates from approximately $10^{-5}$ to $10^6$ Hz, sequence lengths from $10^1$ to $10^6$ samples, and both single- and multi-channel inputs. Evaluations of current open-source and proprietary Audio LLMs (ALLMs) reveal limited zero-shot transfer to machine hearing. Supervised adaptation on machine-hearing data alone does not close this gap, suggesting that the challenge extends beyond data exposure to a systematic mismatch between existing audio front ends and machine-hearing inputs. To address this mismatch, we introduce MachEar, a lightweight encoder extension that complements the pretrained Audio LLM for machine-hearing inputs. The results show that MachEar equips a pretrained Audio LLM with stronger machine-hearing capabilities while largely preserving its existing audio understanding performance.

cs.SD · cs.CL

版本更新 · v3arXiv:2610.15146

Compute-Optimal Scaling Laws for Spiking Language Models

Dan Saunders, Benjamin Ren, Catherine He

原文摘要

Spiking neural networks target energy-efficient language modeling through sparse, binary activations, but the efficiency-accuracy tradeoff of spiking language models is uncharacterized at scale. We present the first Chinchilla-style IsoFLOP scaling study of a spiking language model, sweeping SpikeGPT-family models (RWKV backbone) from width 384 to 1536 across compute budgets from $3\times10^{17}$ to $10^{19}$ FLOPs on FineWeb-EDU. We report two findings. First, the compute-optimal frontier is $N_{opt} \propto C^{0.56}$, close to the 0.50 that Hoffmann et al. report for dense Transformers, so spiking does not change how parameters and data should be traded off under a compute budget. Second, against non-spiking RWKV and Transformer baselines trained the same way, the loss gap splits into a backbone cost of about 0.16 nats that does not change with compute and a spiking cost that falls steadily with compute, from 0.34 to 0.23 nats over our range. These results give the first compute-optimal recipe for spiking language models and quantify the accuracy cost of their sparsity.

cs.LG · cs.CL · cs.NE

版本更新 · v8arXiv:2503.06223

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion

Ruofan Wang, Xingjun Ma

原文摘要

Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is critical. However, existing evaluations remain largely instruction-centric, focusing on explicit malicious queries while overlooking a more realistic and underexplored risk: whether safety alignment remains robust under harmful contextual exposure. This limitation is particularly important for multimodal systems, where visual inputs can substantially steer model behavior and render text-only auditing insufficient. In this work, we study multimodal safety auditing under harmful contextual exposure, asking whether VLMs can maintain safe behavior when partial toxic text is paired with visual context. To enable systematic auditing, we propose RedDiffuser (RedDiff), a reinforcement-based framework that leverages diffusion models to generate semantically coherent visual inputs for black-box safety testing. By combining greedy prompt search with reinforcement optimization, RedDiffuser uncovers high-risk multimodal inputs that expose latent safety failures. Extensive experiments on both open-source and commercial VLMs show that such context-conditioned failures are widespread. On LLaVA, RedDiffuser increases unsafe response rates by up to 10.69% on the original set and 8.91% on a hold-out set, with strong transferability to Gemini and LLaMA-Vision. These vulnerabilities persist even under external safety guardrails, suggesting that current system-level safety mechanisms remain insufficient for realistic multimodal risks. Our findings reveal a critical blind spot in existing safety evaluations and establish context-aware multimodal auditing as an essential paradigm for diagnosing hidden vulnerabilities in modern VLM systems.

cs.CV

版本更新 · v2arXiv:2608.20394

A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer

Wonsup Shin, Jingu Kim

原文摘要

Industry pipelines that turn speech into supervised fine-tuning (SFT) data via multi-stage refinement are increasingly adopted but, to our knowledge, have not been publicly ablated stage-by-stage, leaving each stage's marginal value unknown. We design a production-ready speech-to-SFT pipeline in which transcript refinement (Phase 0) and SFT data quality refinement (Phase 2) are independently toggleable, yielding a 2x2 factorial design. For each condition, we generate QA-form SFT data from Korean medical and finance conference recordings and fine-tune 9 models (5 LLM families, 2.4B-70B); we evaluate with four cross-provider LLM judges, a blind six-expert human evaluation, and three downstream MCQA benchmarks. Our central finding is that, under a fixed, standard SFT recipe, improvements in QA data quality do not transfer uniformly into downstream MCQA gains. 4-judge quality rises consistently, yet the cross-model mean MCQA gain is not significant; positive transfer concentrates on family-domain aligned pairs. All six human raters report higher full-pipeline quality, confirming the LLM-judge direction. An STT-engine swap to Whisper-medium confirms pipeline robustness. An LLM-difficulty audit shows the two frontier LLMs admit unknown on approximately 8% of QA on average; we release samples, prompts, code, and all SFT checkpoints.

cs.SD · cs.CL

新论文 · v1arXiv:2611.13980

What to Predict for Efficient Scheduling on Parallel Machines

Evripidis Bampis, Bruno Escoffier, Dimitris Fotakis, Giorgos Mitropoulos, Michalis Xefteris

原文摘要

We study learning-augmented algorithms for scheduling on multiple parallel machines under the objectives of minimizing the makespan or the total weighted completion time. We assume that the algorithm has access to noisy information (the prediction) about an optimal solution, expressed through a solution encoding that implicitly quantifies both the amount of information provided and the nature of noise (errors in the prediction). Our central question is to determine the maximum level of noise that still allows for efficiently recovering this optimal solution. We observe that information guiding greedy scheduling to optimality or revealing the optimal assignment of tasks to machines is very sensitive to noise, and prove that recovering an optimal solution from solution encodings capturing either is computationally hard, even for a small (non-constant) number of errors. On the positive side, we show that an order-based encoding, which leads to errors that are dispersed locally, is robust to noise. We present a dynamic programming framework that utilizes this encoding and solves optimally several classical scheduling problems, including makespan and total weighted completion time minimization on identical or unrelated machines.

cs.DS

新论文 · v1arXiv:2611.14599

StructRL: Model-Free Reinforcement Learning with Replay Graphs

Ivo Nowak

原文摘要

StructRL turns the experience collected during reinforcement learning into an explicit replay graph. Once the graph contains a path to the task goal, dynamic programming selects actions on the observed part of the state space; these actions form a graph policy that is defined only where the required transitions have been observed. StructRL transfers these actions to model-free learners: as action preferences for a DQN Q-model and as target directions along shortest observed paths for a SAC actor. For DQN on three sparse-reward MiniGrid tasks, final success rises from 0.10 to 0.90 (DoorKey), 0.10 to 0.80 (KeyCorridor) and 0 to 0.50 (ObstructedMaze); plain DQN does not catch up with three times the budget. For SAC on continuous PointMaze, graph-derived direction labels raise final success from 0.17 to 1.0 on seven matched runs that reached the goal. Distilling the graph policy into a fresh Q-model gives a DoorKey 6x6 controller that reaches the goal from 91% of reachable states, against 38% for plain DQN. Scaling experiments identify three bottlenecks: incomplete graph support, structural aliasing, and loss of graph information in high-dimensional inputs.

cs.LG

新论文 · v1arXiv:2611.13978

WINIC: An Automatic Cycle-Accurate Multi-Platform Microbenchmarking Tool for Instruction Performance Metrics

Tobias Rühl, Jan Laukemann, Georg Hager, Gerhard Wellein

原文摘要

Performance models allow developers to gain important insights into the interaction of their code with the hardware that executes it, and enable them to apply target-specific optimizations. To create in-core performance models for out-of-order processors, architecture-specific performance metrics like latency, throughput, and port binding of individual instructions are indispensable. For x86 microarchitectures, there already exist tools to automatically obtain those values; however, the extension of performance modeling tools like the Open Source Architecture Code Analyzer (OSACA) to support further architectures like RISC-V emphasizes the need for a multi-platform microbenchmarking tool. We present WINIC (What I Need Is Cycles), an automatic cross-platform microbenchmarking tool. Unlike previous tools, it can obtain throughput and operand-based latency metrics for most supported instructions of any 64-bit x86, AArch64, and RISC-V microarchitecture without the need for root permissions or extended system control levels. We cover the methodology of microbenchmarking and the approach of WINIC to collect cycle-accurate performance data for assembly instructions. We show that WINIC can be used to automatically obtain a vast number of accurate results and demonstrate for four target microarchitectures that our results match between 71% and 99% of the performance data of instructions obtained by similar tools and documentation. Furthermore, we investigate how operand-based metrics measured by WINIC can be used to improve the in-core performance predictions on selected micro-kernels, exemplarily for the Neoverse V2 microarchitecture.

cs.PF

版本更新 · v2arXiv:2509.01642

REVELIO: Universal Multimodal Task Load Estimation for Cross-Domain Generalization

Maximilian P. Oppelt, Andreas Foltyn, Nadine R. Lang-Richter, Bjoern M. Eskofier

原文摘要

Adaptive interactive systems that respond to user mental state require task load estimation that stays reliable outside its training context. Models built in one setting rarely transfer, limiting real-world use. This work presents Robust Estimation Via End-to-End Learning of Multimodal Observations (REVELIO), a unified framework, dataset and evaluation protocol for cross-domain task load estimation. Cardiac, electrodermal, muscle, respiration, skin temperature, eye tracking and facial signals were recorded in 96 sessions, spanning a laboratory working memory task, a driving simulator and two games under consistent hardware and annotation. Multimodal fusion reached up to 0.87 area under the receiver operating characteristic curve, above single input eye tracking (0.83), facial action units (0.74) and biosignals (0.62). Multi-domain training stayed calibrated on domains seen in training, whereas removing the target domain caused the classifier to collapse in some applications. REVELIO provides a standardized foundation for measuring modality contributions and cross-domain generalization toward deployable workload-aware systems.

cs.LG

新论文 · v1arXiv:2611.13976

Gradient Inversion through Linear and Affine Subspace Constraints

Konstantinos Bouros, Athanasios P. Liavas

原文摘要

Federated learning enables multiple clients to collaboratively train a machine-learning model without directly sharing their local datasets. However, as prior works have shown, the gradients exchanged during training may reveal sensitive information about client data. Most existing attacks usually optimize dummy inputs to match the true client gradients (Gradient Inversion Attacks), while some attempt to reconstruct them based on the observation that aggregate gradients from a fully connected (FC) layer are a linear combination of its inputs. In this work, we extend this observation by showing that aggregate gradients from an FC layer with the correct scaling are actually an affine combination of its inputs. We evaluate a gradient inversion attack that leverages either known linear-subspace information or its affine-subspace counterpart at each FC layer to improve reconstruction accuracy. Our results show that subspace-based methods can substantially improve reconstruction quality over the chosen baselines in certain settings. We further demonstrate that moderate overestimation of the batch size can generally improve or preserve reconstruction quality, even when the true batch size is unknown. We additionally examine reconstruction under gradient perturbations introduced by a differential privacy (DP) mechanism, providing insight into the effectiveness of the considered formulations under noisy conditions.

cs.CR · cs.LG

版本更新 · v2arXiv:2605.18760

DOTRAG: Retrieval-Time Reasoning Along Paths

Larnell Moore, Naihao Deng, Rada Mihalcea, Farnaz Jahanbakhsh

原文摘要

Graph Retrieval-Augmented Generation (GraphRAG) faces significant challenges in complex relational retrieval tasks, particularly in densely connected knowledge graphs where the number of possible paths grows rapidly with reasoning depth. Existing GraphRAG retrieval algorithms either rely on rigid, predefined heuristics to identify relevant graph context or employ costly LLM-based reasoning to guide graph traversal. To address these limitations, we propose DotRAG, a lightweight, training-free GraphRAG retrieval algorithm that uses large language model (LLM) reasoning to narrow the search space and recover task-relevant relational paths. During indexing, DotRAG constructs an entity-relation knowledge graph, generates a graph-wide overview summarizing its contents, and leverages graph reachability indexing to avoid expensive online graph traversals. At query time, the LLM uses this overview to identify promising graph regions and hypothesizes relationship sequences connecting graph information to the query. The LLM then performs targeted relational searches, using graph constraints to restrict the candidate pool progressively. On MetaQA 2-hop queries, DotRAG achieves 97.78% retrieval recall and 51.27% F1, compared to the best baseline scores of 34.74% and 6.33%, respectively. On STaRK-MAG, DotRAG achieves 85.07% recall on 2-hop queries while demonstrating greater computational efficiency than reasoning-based GraphRAG baselines, with 12.2x lower retrieval latency than HopRAG.

cs.IR · cs.AI

新论文 · v1arXiv:2611.13975

Understanding Mixture-of-Experts Language Models Beyond Expert Boundaries

Zhenhong Zhou, Mao Zheng, Mingyang Song, Qiankun Li, Kun Wang, Junfeng Fang

原文摘要

In Mixture-of-Experts (MoE) models, the nature of expert specialization remains controversial. Reports of domain-associated expert preferences contrast with analyses attributing routing primarily to token identity or syntactic patterns. To clarify these differing accounts, we look beyond expert-level routing to investigate the neuron-level organization of domain-specialized computation using Routing-Aware Magnitude Profiling (RAMP), a measure developed for this analysis. Using mixed-domain calibration data, we identify domain-specialized neuron sets with 58-74% overlap across multi-source samples of the same domain, compared with 15-24% across domains. To understand how this organization evolves during training, we trace neuron importance throughout pre-training and post-training across three fully open MoE families. Neuron importance continues to reorganize between pre-training checkpoints despite comparatively stable expert-level importance rankings, while post-training largely preserves neuron rankings. Building on these neuron-level perspectives, we further introduce RAMP-based Pruning (RAMPr) to select neurons across experts for balanced multi-domain capability preservation. At 75% neuron retention, RAMPr preserves average 91-98% of original full performance across six models. At 50% retention, our pruning method can reduce resident GPU memory by 36-43% and improves batched prefill throughput by 17-39% effectively. Our code is available at https://github.com/ydyjya/Neuron-Level-Specialization-in-MoE

cs.AI · cs.CL

新论文 · v1arXiv:2611.13973

On the Spectral Estimation of VARMA Processes

Bin Zhu, Mattia Zorzi

原文摘要

We consider the problem of estimating the power spectral density of a Vector-valued Autoregressive Moving-Average (VARMA) process. A well-established approach to accomplishing this task consists of formulating a moment problem that selects the spectral density maximizing an entropy-like index while matching certain moments of the underlying process. However, existing methods assume that the moving-average (MA) component is either fixed or scalar, thereby reducing the class of ARMA models over which the optimal spectral density is sought. In this paper, we propose a new moment problem, based on the notion of transportation entropy, for learning the spectral density of a VARMA process without fixing the MA component or restricting it to be scalar.

stat.ML · cs.LG · math.OC