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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 06:15 — 2026-11-22 06:15(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:2026-11-21 12:19最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
版本更新 · v2arXiv:2610.24135

Inside the Loop: A Mechanistic Study of Looped Transformers on Permutation Traversal

Magnus Sesodia, Juil Sock, Philip Torr, Christian Schroeder de Witt

原文摘要

Solving algorithmic tasks with many sequential steps typically requires scaling up transformer depth or chain-of-thought length, incurring unfavorable parameter and inference-compute costs, respectively. Looped transformers, which reuse one block of layers across many iterations, are poised to address this, since they scale effective depth without adding parameters or tokens. Yet, it remains unclear what each iteration is actually computing, or whether the loop merely simulates a deeper untied stack. Here, we study directed permutation traversal, in which a model follows H hops from a starting node and reports the node it reaches, so every intermediate hop has a known ground truth. We find that a minimum effective depth is necessary to solve the task, beyond which the degree of weight tying becomes the determining factor. For instance, a looped transformer with a four-layer block iterated eight times solves the task in every seed, while an identically trained untied transformer of the same effective depth never does, succeeding only with a lower learning rate or supervision of its intermediate layers. Probing and intervening on the residual stream, we find that the looped model advances through the intermediate nodes gradually, forming a staircase that adapts to its iteration budget, whereas the untied model, at that lower rate, exposes them only in its final layers. Taken together, our results recast looped transformers as iterative program learners, which allocate their iterations to successive steps of the algorithm and solve tasks that identically trained untied models of the same effective depth do not. Code is available at https://github.com/magnus-sesodia/insidetheloop.

cs.LG · cs.CL

新论文 · v1arXiv:2611.20868

It Depends on the Task: Rethinking Rhetorical Segmentation of Dutch Judicial Decisions

Samyak Sheth, Gerasimos Spanakis, Gijs van Dijck

原文摘要

Classifying the material facts, submissions, judicial reasoning, and the court's decision (rhetorical roles) in case law is a prerequisite for high-quality performance across virtually all NLP-in-law tasks, including legal information retrieval, summarisation, and LLM-based analysis. These rhetorical roles often intertwine and shift sentence by sentence, making reliable classification difficult. This paper introduces the first sentence-level annotated dataset of Dutch judicial decisions, labelled across four legally meaningful categories: material facts, submissions, judicial reasoning, and the court's decision, alongside non-annotated (None) content, and compares several classification strategies, including a staged pipeline that separates None detection from the rhetorical roles, and a Bayesian update that leverages information about the section-header a sentence belongs to. Our results show that no single strategy dominates on both precision and recall: header priors help most when the None sentences are excluded and offer little benefit for None detection itself. These trade-offs matter in practice. For instance, extractive summarisation depends more on recall so it does not miss relevant facts, whereas outcome prediction depends more on precision regarding decision and facts sentences so that the predicted ruling is not contaminated by noise. We use these trade-offs and map the approaches tested in this study onto a set of representative legal NLP use cases.

cs.CL

版本更新 · v2arXiv:2610.36734

CAMR: Compatibility-Aware Memory Replay for Continual Learning in Large Language Models

Jingpu Yang, Tianhao Li, Fengxian Ji, Yufeng Wang, Shuxin Zheng, Xiaoqing Zhang

原文摘要

Continual learning requires large language models to acquire new knowledge and capabilities while retaining what they have learned. Fine-tuning and replay support acquisition and retention, but deciding whether incoming examples need supervision and which historical examples to revisit remains a challenge. We propose Compatibility-Aware Memory Replay (CAMR), an adaptive framework that jointly controls current-example supervision and historical replay. CAMR combines compatibility checks with a learned memory gate to guide an online policy over three actions: learning incoming examples with general replay, jointly reinforcing compatible related examples, and skipping direct supervision of verified mastered duplicates. The policy learns from acquisition, retention, and training-cost feedback under a bounded per-arrival replay budget. We evaluate CAMR with Qwen3-8B-Base on continual factual updating and cross-task and cross-domain learning. On WikiBigEdit, CAMR consistently leads evaluated methods in Original Match from 3K to 100K facts, reaching 93.66% after just 3K facts and surpassing Full-history Replay (LoRA) after 100K facts. It also achieves the highest final scores on all four selected TRACE tasks and maintains or improves earlier-task performance relative to post-acquisition levels in a sequence spanning financial question answering, mathematical reasoning, code generation, and summarization.

cs.CL

版本更新 · v2arXiv:2607.11603

WarpMPC: Large-Batch MPC on GPU via ADMM with Unrolled $LDL^\top$ Factorization

Henrik Hose, Se Hwan Jeon, Charles Khazoom, Sangbae Kim, Sebastian Trimpe

原文摘要

This paper introduces numerical optimizations for maximizing throughput on GPU when solving large batches (10,000 to over 100,000) of sequential quadratic programming (SQP) iterations, where all problems have the same structure. The optimizations are implemented in a toolbox WarpMPC for model-predictive control (MPC) in JAX and Warp. Based on the insight that all MPC problem instances in a batch share the same sparsity in time, cost, and constraints, we propose unrolling sparse linear factorizations and solves, which dominate alternating direction method of multipliers (ADMM) solver runtime. We avoid memory access bottlenecks and wasting computations via optimized memory layout, padding-reducing segmentation of the unrolled factorization, and dependency level scheduled backsolves, additionally accelerating sensitivity computation. We achieve throughputs of 8,000 to 250,000 SQP iterations per second on nonlinear cartpole, quadrotor, and humanoid robot benchmarks, outperforming baselines by 3$\times$ to 25$\times$. We illustrate practical usefulness by synthesizing a dataset and training a neural network approximation of an MPC in under 5 minutes that stabilizes a nano quadrotor in hardware experiments.

cs.RO · eess.SY · math.OC

新论文 · v1arXiv:2611.20864

LiDSeg: Linear DehazeFormer Guidance for Efficient Semantic Segmentation in Adverse Weather Conditions

Yobsan Bayisa Leta, Christos Kyrkou, Maria K. Michael, Theocharis Theocharides

原文摘要

Robust semantic segmentation in adverse weather is essential for safety-critical autonomous systems. Existing restore-then-segment pipelines introduce latency and prioritize pixel-level restoration over semantic discriminability, while domain adaptation methods often face representation bottlenecks and computational complexity. We introduce LiDSeg, a framework that uses reconstruction-informed guidance to improve segmentation under adverse weather. During training, a lightweight guidance encoder is jointly optimized with the segmentation branch using segmentation and auxiliary reconstruction objectives. At inference, the reconstruction decoder is discarded, while the guidance encoder is retained to extract weather-robust features. A lightweight gated fusion module integrates these features into the segmentation branch, preserving clear-weather accuracy while improving adverse-weather robustness. On Foggy Cityscapes, LiDSeg limits the clear-to-dense-fog mIoU degradation to 2.5-2.8 percentage points, reducing the baseline performance drop by more than fivefold. On the official ACDC test server, LiDSeg-PIDNet achieves 75.07% pooled all-condition mIoU, comparable to supervised HRNet-W48 at 75.0%, while remaining substantially smaller. The gains generalize zero-shot to Foggy Driving and Foggy Zurich without training on real-fog images. LiDSeg adds only 1.9-3.1M parameters across several models, with total model sizes of 5.2-39.5M parameters and no inference-time reconstruction overhead. It delivers real-time inference on the NVIDIA Jetson AGX Orin. Code: https://github.com/yobsanb/LiDSeg

cs.CV

新论文 · v1arXiv:2611.20863

Practical Semantic Communication for General-Purpose Networks: Compression of High-Dimensional Embeddings Under Quantization

Leonardo Roque, Louis-Adrien Dufrène, Quentin Lampin, Grégoire Lefebvre, Mohamad Assaad

原文摘要

This paper introduces a practical framework for semantic communication over wireless channels, focusing on the compression of high-dimensional embeddings under quantization and channel errors. Building upon a relaxed Gaussian Information Bottleneck (GIB) model, the approach provides analytical solutions for task-relevant information preservation, even with non-Gaussian targets. The framework relaxes traditional Gaussian assumptions, enabling effective compression for discrete and complex data such as text embeddings. It derives closed-form gradients for optimizing the compression matrix and establishes bounds linking continuous representations to discrete, noisy system performance. Comprehensive experiments on text classification tasks demonstrate that the proposed method outperforms task-agnostic quantization-based compression methods, maintaining high semantic fidelity at low bit budgets per embedding. The approach offers a scalable, interpretable, and resource-efficient solution for deploying semantic communication in general-purpose networks.

cs.IT · cs.LG

版本更新 · v2arXiv:2607.23653

Observer-Assisted Relative-Velocity Compensation with LPV-$H_\infty$ Robust Correction for 3D Trajectory Tracking of Underactuated Non-Minimum-Phase AUVs under Ocean Currents

Mohammad Sabouri

原文摘要

This paper develops an observer-assisted control architecture for 3D trajectory tracking of torpedo-type underactuated AUVs with non-minimum-phase sway/heave dynamics under unknown ocean currents. A three-stage state-current observer provides relative-velocity estimates to a nonlinear feedforward term for dominant current rejection and to an LMI-certified LPV-$\mathcal{H}_\infty$ correction layer. Feedback-linearising cancellation yields a constant input matrix, enabling convex synthesis without pairwise cross terms. A residual-level break-even law shows that the effective surge disturbance depends on current-estimation error, while a singular-perturbation analysis proves local practical uniform ultimate boundedness on the embedded LPV model. REMUS simulations over three trajectories and four current scenarios show 89-96% current-estimation reduction, about 99% translational residual reduction, and RMS tracking-error reduction from 4.04 m to 0.24 m.

eess.SY · cs.RO

版本更新 · v2arXiv:2609.22040

PRIME: Perception Feedback with Situational Memory Embeddings in VLA Models

Erik Deinzer, Naya Baslan, Luca Paparusso, Narunas Vaskevicius, Peter Knott, Luigi Palmieri

原文摘要

Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward inference across the perception--reasoning--planning hierarchy. While modern architectures maintain temporal recurrence within the perceptual module, early perception remains blind to downstream reasoning and navigation goals, processing visual inputs agnostically without prioritizing cues informed by prior decisions. To bridge this gap, this paper introduces PRIME, a learned feedback mechanism that conditions the VLA perceptual queries on a novel Situational Memory. By aggregating latent representations of past perception, reasoning, navigation goals, and predicted behaviors across an L-step window via cross-attention, PRIME enables intent-driven perceptual attention at minimal computational cost, adding only a maximum of 29.7M parameters (0.41% of the 7.3B-parameter base model). Evaluated on the Bench2Drive closed-loop benchmark, PRIME achieves a state-of-the-art Driving Score of 82.47 (+4.73 over ORION) and a Success Rate of 60.00% (+5.38 percentage points), the highest reported Driving Score among published VLAs trained on Think2Drive demonstrations.

cs.CV · cs.RO

版本更新 · v2arXiv:2510.12316

Beating Hateful Narratives on Social Media with Facts: Retrieval-Augmented Counter-Speech Generation

Greta Damo, Elena Cabrio, Serena Villata

原文摘要

Online hate speech threatens social cohesion by amplifying discrimination and harmful narratives against marginalized communities. While counter-speech (CS) - fact-based, respectful responses to hate - offers a constructive alternative to content removal, its large-scale generation remains constrained by factual reliability and the risk of generic responses. We address these challenges with a Retrieval-Augmented Generation (RAG) pipeline grounded in the first large-scale, curated knowledge base built from authoritative international and regional human rights sources, including the United Nations Digital Library, EUR-Lex, and the EU Agency for Fundamental Rights. The framework covers eight groups frequently targeted by online abuse. We systematically evaluate all pipeline components demonstrating that each design choice is empirically motivated, combining automatic metrics, LLM-based judgments, and human evaluation with comparisons against strong baselines. Results show that RAG improves factual grounding, diversity, and perceived effectiveness over No-RAG and performs favorably against existing systems. Our human evaluation further reveals differences between in-group and out-group perceptions of CS, with RAG narrowing but not eliminating this gap. These findings highlight the potential of knowledge grounded CS for scalable social media interventions, while underscoring the need to evaluate such systems with and for the communities they are intended to serve.

cs.CL

新论文 · v1arXiv:2611.20859

Early UAV Detection Using 5G NR LEO Downlinks for Passive ISAC

Mohamed Hamad, Nizar Zorba, Tamer Khattab, Hamid Saeedi, Halim Yanikomeroglu

原文摘要

5G New Radio (NR) low-Earth-orbit (LEO) downlinks enable passive integrated sensing and communication (ISAC) for unmanned aerial vehicle (UAV) detection. Weak echoes require motion-compensated accumulation, but exhaustive searches postpone alerts. We propose a receiver that combines selective Doppler-rate search, early UAV alerts and continued delay-Doppler estimation. Classical, statistical and neural configurations select rates of Doppler change to search, while a shared correlation score determines detection. Simulated echo delay, Doppler and power follow the moving satellite-UAV-receiver geometry, propagation loss, assumed scattering and antenna response. In a line-of-sight scene with acquired beams and UAVs at 5-8 km horizontal distance, all three configurations match exhaustive search at 92.9% correct final detections, with 0.10-0.13% observed false alerts on no-UAV recordings. The neural configuration reduces mean time to the first correct alert by 36.5% versus exhaustive search and 21.9% versus the closest literature baseline, averaging over successfully detected UAVs. These results demonstrate earlier UAV alerts while preserving exhaustive search's final detection accuracy, supporting passive sensing over cellular satellites.

cs.NI · eess.SP

新论文 · v1arXiv:2611.20856

Synapse: Optimizing Natural-Language Agent Skills through Program Repair

Lijuan Li, Zhenpeng Chen, Chenxi Zhang, Yihao Huang, Yang Liu, Chong Wang

原文摘要

Large language model (LLM) agents can improve task performance by optimizing reusable natural-language skills without updating model parameters. Execution feedback reveals failures but does not directly identify which instructions to edit, which related instructions matter, or which tasks an edit may break. We propose Synapse, which casts skill optimization as generate-and-validate repair over a partial program view. A deterministic compiler translates recognized skill constructs into SkIR, a source-linked intermediate representation, while retaining other requirements in the text. Synapse combines execution traces with control-flow and dependence relations to localize faults, propose typed mutations, and select related repair tests, including previously passing ones. Each mutation is written back to its mapped source span and recompiled; validation determines acceptance. Every accepted patch yields a well-formed skill and preserves untargeted instruction spans. Under a one-hop-local execution assumption, selected tests include every test an edit can affect. On DocVQA and LiveMath with three execution models, Synapse improves task success rates over SkillOpt by 3.74-4.54 and 2.40-4.00 percentage points, respectively, and outperforms Trace2Skill and SkillBoost in all six settings. Replacing SkIR-based repair and its test screening with constrained text editing screened only on failing tests lowers DocVQA success rates by 2.40 and 2.67 percentage points for two models. In two recorded repair runs, structural relations add tests for 23 of 37 patches; in one repair, a test added through a control-flow relation exposes a regression missed by coverage of the edited instruction.

cs.SE

新论文 · v1arXiv:2611.20854

When Is the Expensive Method Worth It? A Content-Driven Analysis of Classical Bayer Demosaicing

Taranum Wasu, Harsh Kashyap, HS Pannu

原文摘要

Demosaicing reconstructs a full-colour image from a single-sensor colour-filter-array (CFA) mosaic, where only one colour is measured per pixel. Classical methods make different assumptions about images, from simple averaging to directional edge-aware interpolation, and the directional methods cost markedly more compute. We ask a practical question that a per-image quality ranking does not answer: for a given image, is the expensive directional method worth its cost? Using a controlled simulate-reconstruct pipeline on 80 benchmark images from four public datasets (Kodak, McMaster, BSD100, Urban100), six classical methods, and image-content descriptors fixed before any results were seen, we show that the quality gain of the edge-aware method (Menon 2007) over the best cheap linear method is not constant. It ranges from $-6.6$ to $+6.8$ dB, and on 31% of images it is zero or negative, meaning a cheap method matches or beats the expensive one. The gain is also predictable from content: it correlates with mean image saturation at $r=-0.86$ ($p<10^{-6}$). We then build an interpretable depth-2 decision tree that recommends the best cheap method from image descriptors, beating an always-pick-the-most-common baseline by 20.0 percentage points under leave-one-image-out validation. The analysis uses no deep learning, and every step can be inspected.

cs.CV

新论文 · v1arXiv:2611.20853

Motor Imagery Classification Using Hybrid Cross-Subject Class Mixup and Selective Attention

Jiwon Kim, Chae-Won Lee, Jong-Seok Lee

原文摘要

Motor imagery (MI) enables a brain-computer interface (BCI) to decode movement intentions without overt movement. Hybrid electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) classification combines complementary signals, but inter-subject variability and the design of information exchange between modalities affect generalization to new subjects. We propose a framework that combines Cross-Subject Class Mixup (CSCM) with Selective Attention. CSCM aims to construct new training data to make the model robust against inter-subject variability. It independently selects EEG and fNIRS donor trials from other training subjects within the anchor class and mixes each modality while preserving the original label. Selective Attention provides an effective way to simultaneously model the temporal signal characteristics and fuse the two modalities. It retains causal temporal self-attention for EEG and uses a classification token (CLS) to integrate both modalities, without fNIRS attention updates or direct cross-modal temporal-token attention. Leave-one-subject-out (LOSO) evaluation across 28 subjects on a public EEG-fNIRS dataset yields a mean balanced accuracy (BA) of 76.85% and a macro-averaged F1 score (Macro-F1) of 76.58%. The proposed model achieves the highest mean performance among five reimplemented baselines. We also examine the contributions of CSCM and Selective Attention through modality-specific mixing and donor-policy comparisons, temporal-policy comparisons, interventions on direct cross-modal paths, and component ablations.

cs.LG

新论文 · v1arXiv:2611.20851

artist: A Python package for differentiable ray tracing and gradient-based optimization of solar tower power plant operation

Marlene Busch, Marie Weiel, Kaleb Phipps, Daniel Maldonado Quinto, Max Pargmann, Robert Pitz-Paal, Markus Götz

原文摘要

Solar tower power plants provide dispatchable, renewable energy by concentrating sunlight with thousands of mirrors, called heliostats, onto a central receiver. Efficient operation requires accurate modeling of the optical path from each heliostat to the receiver and compensation for manufacturing imperfections, kinematic misalignment, and material degradation that distort the flux distribution. Conventional ray tracers predict the flux from an assumed plant model but are limited to forward simulation. They cannot recover unknown plant parameters from measured flux nor directly optimize plant operation. We present artist, an open-source, FAIR4RS-compliant Python package implementing a fully differentiable digital twin of solar tower power plants. By making the optical pipeline, comprising heliostat surface representation, kinematics, blocking, and ray tracing, end to end differentiable, artist turns the digital twin from a passive forward model into an active physics-based tool for inverse modeling and data-driven optimization. The resulting gradient-based framework unifies tasks usually handled by separate solutions, such as reconstructing heliostat surfaces and kinematics from operational flux images without costly deflectometry, predicting irradiance at the receiver, and optimizing aim points to realize a desired receiver flux density distribution. Built on PyTorch, artist scales to real plants through GPU acceleration, a structure-of-arrays memory layout, and nested data parallelism. It interfaces with open data sources such as the PAINT database. We describe the software architecture, physical models, and optimization framework, and demonstrate the workflow on representative tasks. By integrating modeling, prediction, and optimization into a single open, interpretable package, artist provides a principled foundation for data-driven research toward autonomous solar tower operation.

cs.LG

新论文 · v1arXiv:2611.20848

MolReps: Taking SELFIES, Making SMILES, Teaching LLMs

Ken Deng, Garrett Morris

原文摘要

The same molecule can be expressed in multiple, syntactically distinct representations, yet it remains unclear whether large language models (LLMs) can recognize and relate these equivalent encodings. We introduce MolReps, a pipeline that generates 9,600 question-answer pairs across ten representations for conversion, normalization, and 2D structure recognition. Post-training on MolReps improves text-only and multimodal models, MolQwen3-4B-Instruct (MQ3-4B-I) and MolQwen3-VL-4B-Instruct (MQ3-VL-4B-I), from $4.01\%$ to $75.13\%$ and from $7.11\%$ to $73.14\%$ (InChIKey match) on the molecule-overlap test set, respectively. On the molecule-disjoint test set, post-training increased validity from $20.35\%$ to $58.12\%$ for MQ3-4B-I and from $17.19\%$ to $59.34\%$ for MQ3-VL-4B-I. However, InChIKey match remained low, decreasing from $3.86\%$ to $3.09\%$ and from $6.44\%$ to $2.29\%$, respectively. Furthermore, the resulting models achieve a relative $27.84\%$ improvement in average over their base model on MolRepBench, a comprehensive benchmark for evaluating molecular property prediction. These results show the effectiveness of targeted post-training for enhancing molecular representation understanding and its potential to improve downstream molecular tasks.

physics.chem-ph · cs.AI · cs.CL

新论文 · v1arXiv:2611.20844

DetourBench: Trajectory-Level Evaluation of Interactive Agents with Exact Minimum-Action Bounds

Hanlin Tian, Sihan Zhu, Zhao Yang, Yuxiang Wang, Zhiquan Hu, Yu Mi, Hongquan Zhu, Qiufei Hu

原文摘要

Benchmarks judge language-model agents mainly by whether they reach the correct final state, not by how they got there. Endpoint scoring cannot separate an agent that retrieved exactly the evidence a decision required from one that read most of the environment, nor an agent that never located the evidence from one that stopped a single action short. Settling this needs a reference cost, and authored solutions establish only that a task is solvable, not that no shorter route exists. We present DetourBench, which constrains the environment until that minimum is computable. Each task is a finite, partially observable transition system with unit-cost accesses whose resources become globally addressable after discovery. Exhaustive search yields the full-information minimum action count $L_0$ with a replayable witness; from graph-recoverable terminal states it also yields exact residual work $R_T$, which separates an episode that stopped one access short from one that wandered, while an irreversible wrong commitment is recorded as having no finite residual distance rather than assigned one. Success, attainment, residual progress, and normalized detour are reported separately. Across 375 scored episodes --- five model endpoints, 25 integrated tasks, three repeats --- success ranges from 58.7% to 96.0% while conditional attainment ranges from 0.803 to 0.890 and orders the models differently. Among recoverable failures, residual work separates near-complete trajectories from costly incompletion and from irreversible commitment. We open-source the instances, oracle witnesses, and evaluation harness at https://github.com/DatagridsAI/DetourBench.

cs.AI · cs.CL

版本更新 · v2arXiv:2607.18506

AI Value Alignment for Evolving Social Norms

Nenad Tomašev, Matija Franklin, Simon Osindero

原文摘要

AI alignment is essential for the safe deployment of advanced AI systems. Given that values and preferences change over time, culture, social roles, and context, we need to develop a better understanding of the possible long-term consequences of AI alignment, in particular considering the likely ubiquitous future use of personalized AI assistants. We introduce a flexible and extensible mathematical modelling framework, rooted in social physics, aimed at answering macro-level questions regarding the evolving social norms in human populations under the assumption of frequent AI use. Our analysis is part-analytical, and part-simulation, enabling us to characterize the long-term dynamical consequences under a diverse set of starting assumptions. We highlight the risk of value lock-in, and normative mode collapse, prominently featured in non-adaptive alignment formulations. Beyond alignment, we advocate for the wider adoption of these kinds of social physics models as an epistemic bridge: enabling rapid, rigorous, and quantitatively-grounded hypothesis testing for sociotechnical foresight in general AI futures, and acting as a tractable precursor to more computationally expensive large-scale agentic evaluations.

cs.CY

新论文 · v1arXiv:2611.20841

Vision-Language Model-Based Phase-OTDR Event Classification

Ahmet Bestami Kose, Mehmet Sergen Catal, Muhammet Cagri Yeke, Kivilcim Yuksel, Abdurrahman Gumus

原文摘要

Phase-sensitive optical time-domain reflectometry (Phase-OTDR) enables distributed vibration sensing, but reliable event classification has traditionally relied on fully supervised models that require extensive annotated data. This study examines the adaptability of a Vision-Language Model (VLM) for Phase-OTDR event recognition through few-shot learning. Raw samples are converted into Short-Time Fourier Transform (STFT) dB-magnitude spectrogram mosaics, color-mapped and resized to RGB images, and processed by a Contrastive Language-Image Pre-training (CLIP) image encoder; few-shot adaptation optimizes only the Tip-Adapter-F cache keys, leaving both encoders unchanged. Under a leakage-controlled protocol (train-side support/validation pool of 512 images per class, fixed held-out test of 120 per class, no test-set access during selection, 20 distinct support-sampling trials), the selected configuration (the ViT-L-14 Vision Transformer encoder with OpenAI weights, 128 shots per class) reaches 96.81 +/- 0.42% accuracy and a macro-averaged F1 score of 96.79 +/- 0.42% on the held-out test set; a label-efficient 16-shot setting, that is, 96 labeled support images at adaptation time across the six classes, already attains 90.17 +/- 0.81%. Tip-Adapter-F clearly outperforms both zero-shot CLIP and the standard training-free Tip-Adapter, and prompt and backbone analyses show that performance is stable across Vision Transformer encoders and insensitive to prompt wording at the selected operating point. Overall, CLIP visual features carry a transferable structure that a lightweight support cache turns into a label-efficient Phase-OTDR event classifier. The code and the corresponding image dataset are made publicly available on GitHub to support further research: https://github.com/miralab-ai/vlm-phase-otdr.

cs.CV · cs.LG

新论文 · v1arXiv:2611.20838

Optimal Dynamic Fees for L2s: A Vault Approach

Ulysse Pavloff, Lin Oshitani

原文摘要

Layer 2 (L2) blockchains incur costs when posting data to Layer 1 (L1) and charge users fees intended to recover those costs. We model this mechanism as a *vault*: user fees increase its balance, L1 posting costs reduce it, and surplus and deficit accumulate over time. Forecast-based fees aim to recover posting costs, but forecast errors accumulate in the vault. Returning the vault balance to a target requires feedback on the accumulated error. Treating the vault as a discrete-time control system, we derive in closed form the optimal trade-off between vault tracking and fee smoothness in an idealized benchmark. The optimal rule retains a fraction of the previous fee and corrects in proportion to the current vault error. This fee-memory fraction is the single parameter tracing the entire trade-off frontier. We compare proportional (P), proportional-integral (PI), and Arbitrum-style controllers against this frontier, both analytically and on historical Ethereum fee data. At the fee movement implied by Arbitrum's current parameters, the optimal rule reduces the benchmark tracking error by about one third. Fee memory improves the tracking-smoothness trade-off.

cs.CR

新论文 · v1arXiv:2611.20835

Hierarchical Regime-Conditioned Dynamics for Spatiotemporal Graphs

Jeremy Baffou, Pascal Frossard, Dorina Thanou

原文摘要

Forecasting the behavior of spatio-temporal systems often requires more than accurate predictions: models should uncover the dynamical modes governing future evolution. Existing temporal graph and latent dynamical models achieve strong forecasting performance, but their latent representations often entangle multiple dynamical patterns, limiting interpretability. Conversely, regime-inference methods explicitly model such modes but typically do not support generative forecasting over graph-structured systems. We introduce HERON, a self-supervised regime-aware generative framework that unifies graph-structured trajectory generation with regime identification. HERON factorizes the latent state into discrete system-level regimes, capturing global dynamical modes, and continuous entity-level dynamics, yielding a modular regime interface compatible with existing spatio-temporal backbones. Crucially, the inferred regime actively conditions system dynamics, enabling regime tracking and controlled simulations under alternative dynamical modes. Without regime annotations, HERON jointly learns forecasts and regime dynamics in a self-supervised manner, recovering meaningful modes across controlled synthetic and real-world datasets while maintaining competitive forecasting performance. These results open a path toward interpretable, controllable generative modeling of spatio-temporal dynamics.

cs.LG · cs.CG

版本更新 · v2arXiv:2611.16736

On the Difficulty of Sequence-Level Supervised Learning for Autoregressive Language Models

Mathieu Blondel, Michaël E. Sander, Germain Vivier-Ardisson, Tianlin Liu, Vincent Roulet

原文摘要

During the supervised learning phase, autoregressive language models are typically trained by minimizing the negative log-likelihood of the training data, which decomposes as a sum of token-level cross-entropies via teacher forcing. This objective is simple and efficient but potentially suffers from so-called exposure bias: a mismatch between the way the model is trained and the way it is used at inference time. Can we instead design sequence-level loss functions that incorporate inference-time decoding procedures, such as greedy decoding or autoregressive sampling? We show that two natural attempts lead to loss functions that are fundamentally flawed: unbounded below. We further show that these two flawed loss functions are intimately connected: using autoregressive Gumbel tricks, the sampling based loss is the expected greedy loss under Gumbel perturbations. Since the pathology stems from the dependence of the decoded sequence on the model parameters, we analyze the update direction obtained by applying a stop gradient on the sampling procedure, leading to a moment matching direction. While it is not the gradient of any loss function, we prove that it defines a valid descent direction in function space for the autoregressive negative log-likelihood. Despite these theoretical insights, the moment matching direction suffers from high variance. We conclude that teacher forcing may well be ``all you need'' for supervised learning of autoregressive models.

cs.LG · stat.ML

版本更新 · v4arXiv:2606.23357

SOAP-Bubbles: Structured Weight Uncertainty for Neural Networks

Adrian Robert Minut, Nico Daheim, Marco Miani, Mohammad Emtiyaz Khan, Wu Lin, Thomas Möllenhoff

原文摘要

Structured weight-uncertainty can improve many aspects of deep learning, but it remains costly to estimate and difficult to implement. Here, we show that these issues can be addressed by adapting the SOAP optimizer. Our key idea is to run IVON, an existing diagonal-covariance variational method, in the eigenspace of SOAP's preconditioner and then use the preconditioner to transform the diagonal estimate into a non-diagonal covariance. The resulting method has costs similar to those of SOAP and requires no drastic changes to training pipelines. We call the posteriors obtained in this way SOAP-Bubbles and our new optimizer Eigenspace-VON (EVON). We show that, for logistic regression, EVON can match the full Gaussian covariance and that, for language model pretraining, it yields significantly better results than existing diagonal-covariance methods. Our work makes it easier to estimate more expressive posterior distributions for deep learning at scale.

cs.LG

新论文 · v1arXiv:2611.20826

Conversing with a Conversational Agent: A Real Conversation, Not a Simulated One

Christophe Denis

原文摘要

The claim that interactions with artificial conversational agents merely simulate human conversation rests on a philosophical distinction between reproducing the observable features of an activity and actually performing it. Although this distinction is appropriate for certain physical phenomena, its application to linguistic and symbolic activities is far less straightforward. This article argues that conversations with large language model (LLM)-based agents are genuine conversational activities rather than mere simulations, without thereby attributing consciousness, subjective understanding, or human intentionality to artificial systems. Drawing on the distinction between subjective and objective simulation, the article first examines the limitations of defining conversation exclusively through the intrinsic properties of its participants. It then develops a relational and semiotic account of conversational activity, informed by linguistic pragmatics, Lacan's Conversing with a Conversational Agent theory of the mirror, Baudrillard's concept of the simulacrum, Simondon's philosophy of individuation, and Peirce's semiotics. These perspectives make it possible to distinguish the reality of conversational interaction from the appearance of artificial subjectivity and from the epistemic validity of the meanings produced. The argument culminates in the concept of Hybrid Semiotic Fabrication, which characterizes meaning-making as a distributed process involving human participants, artificial intelligence, corpora, and technical arrangements. Recognizing the reality of human-AI conversation therefore entails neither anthropomorphizing artificial agents nor granting their outputs epistemic authority. Rather, it requires a more precise account of the relational, semiotic, and normative conditions under which conversational meaning is produced and justified.

cs.AI

新论文 · v1arXiv:2611.20824

Network-Native DNN Architecture Synthesis for Distributed Inference

Fan Yang, Xiaolong Wu, Qi Cao, Fen Hou, Yulin Shao

原文摘要

Distributed deep neural network (DNN) inference typically follows a model-first paradigm, in which a predefined DNN is partitioned and deployed over a physical network. On irregular communication-computation topologies, however, this approach can create transmission bottlenecks and leave distributed resources underutilized. This paper reverses this perspective and asks: given a physical network, what kind of DNN can it naturally support? To answer this question, we propose a network-native DNN architecture synthesis paradigm in which the physical network topology directly defines inter-node neural dependencies. Neural computation is allocated across nodes under communication, computation, storage, synchronization, and latency constraints. We establish structural properties of the synthesis problem and develop linear programming (LP)-based Architecture Synthesis (LPAS), an efficient topology-guided algorithm that produces a feasible architecture with a computable bound on suboptimality. Experiments on physical networks of different sizes show that LPAS achieves relative gaps below 0.6% to the LP-derived upper bound, with substantially lower runtime than direct mixed-integer LP optimization on larger networks. Under matched network deadlines, the network-native architectures activate more compute nodes and utilize a larger proportion of available model-storage capacity than the model-first baseline. After training, the network-native models achieve higher classification accuracy across all evaluated dataset-precision settings, with the average gain of up to 10.69%. This network-native design paradigm thus turns the physical network from a deployment constraint into an architecture design primitive.

cs.IT · cs.DC

新论文 · v1arXiv:2611.20823

Medical question answering collapses in Hausa: a pre-registered pilot on three small open models

Abbas Sani

原文摘要

A system that reads nothing and always answers the most frequent letter scores \BaselineP{} on our Hausa medical multiple-choice set. \NBelowBaseline{} of the \NModels{} small open models we evaluate do not beat it. We lead with that because the usual summary of a multilingual result -- a percentage-point drop from English -- does not say whether what survives the drop is performance at all. On a paired English--Hausa set of \NEval{} MedMCQA items, three instruction-tuned models of 3--4B parameters lose between \GapMedGemma{} and \GapQwen{} points of accuracy, every gap significant after Holm correction. Back-translating the Hausa items into English recovers between half and two-thirds of the gap for the two general-purpose models but not demonstrably for the medically adapted one, so the deficit is substantially, though not wholly, a matter of the language of presentation. Answers are also far less stable: agreement across three option orderings falls from \ConsEnQwen{} to \ConsHaQwen{} in the worst case. An exploratory error analysis of \ENRows{} discordant items attributes most of the damage to medical vocabulary lost in translation (\ETerm{}, 95\% CI \ETermLo{}--\ETermHi{}), usually in the question stem. A fourth registered hypothesis proposed closing the gap with self-generated preference pairs. Its pilot gate found nothing to train on: asked to reason in Hausa rather than to pick a letter, the model echoes the prompt back, switches into Swahili, or simply stops without answering; only \GateParse{} of chains are parseable. We report that intervention as not run, which is itself the sharper result -- a forced-choice benchmark cannot see a model that has no generative command of the language at all. All hypotheses, thresholds and decision rules were registered before any model was run, and all deviations are logged.

cs.CL

新论文 · v1arXiv:2611.20822

No-Shot Text-to-Speech: Limitations of Zero-Shot TTS and its Evaluation Methods in Representing Queer and Transgender Voices

Juliana Francis, Robin Netzorg, Joakim Gustafson, Éva Székely

原文摘要

Gender expansive voices remain underrepresented in speech datasets, which could cause challenges with generalizability in zero-shot Text-To-Speech (TTS) systems. We evaluate six zero-shot TTS models on two datasets: one containing non gender expansive voices (N-GE) and one with gender expansive (GE) voices from self-identified speakers. Human ratings found that 2 of the 6 models synthesize less similar GE voices compared to N-GE voices, and 3 have improved performance for GE voices. Automated evaluations yield conflicting results, with speaker similarity and automated mean opinion score predictors rating performance of GE voices inconsistently between models and human ratings. This highlights a potential blind spot in evaluation pipelines, emphasizing a need for more representative data and metrics that better capture human perceptual judgments. Our findings stress the need to include transgender, queer, and minority communities in creation of better datasets and model training.

cs.SD

版本更新 · v2arXiv:2603.04760

Designing and Validating a Self-Aligning Tool Changer for Modular Reconfigurable Manipulation Robots

Mahfudz Maskur, Takuya Kiyokawa, Kensuke Harada

原文摘要

Modular reconfigurable robots require reliable mechanisms for automated tool exchange, but conventional rigid active couplings often fail due to inevitable positioning and orientational errors. To address this, we propose a misalignment-tolerant tool changer. The tool changer consists of an insert part on the robot side, which contains a servo-driven cam and lock-pin, and a receptacle part on the tool side, which has an isosceles triangular lead-in guide and chamfered walls. During insertion, these geometries generate angled contact forces that passively align the two parts, so the tool changer compensates for angular and lateral misalignments without force sensors. A motor-driven rotating tool exchange station stores the tools and rotates to bring the selected tool to the exchange position. Experiments confirmed that, with the current guide and chamfer geometry, the tool changer tolerates rotational offsets of $ \pm$ 20 degrees and lateral offsets of up to 7 mm.

cs.RO

新论文 · v1arXiv:2611.20819

Surprise-Gated Memory for Live Speaker Diarization

Louis Mouchon, Alexis Lainault

原文摘要

We transpose the Surprise-Gated Memory recipe, a frozen encoder plus a calibrated novelty signal that gates a one-shot episodic store consolidated by periodic replay, from continual visual learning to live speaker diarization. The moment-to-moment question a streaming diarizer must answer, whether an arriving voice belongs to an already-heard speaker or a new one, is a known-versus-novel decision, exactly the decision the surprise gate is built for. On a frozen fine-tuned DiariZen backbone, our online system SGM-Diar recovers 4.8 of the 9.2 diarization-error points separating a naive online baseline from the offline oracle on AMI-SDM (52%) and 1.9 of 2.3 points on VoxConverse (82%), in the end-of-meeting revisable mode, with calibration frozen on development data and transferred cross-domain without adjustment. These are single-seed runs on three AMI meetings and five VoxConverse sessions, so the ordering of conditions rather than the absolute rates is the result. Beyond error rate, we measure the gate's behaviour directly and find a coherent memory-like profile: one-shot speaker recall at 0.857, a novelty response that habituates as speakers become familiar, re-identification that is invariant to the length of intervening silence, and a false-novelty rate of 0.001. Two ablations reproduce, now on audio, the central prediction of the visual SGM work: a sliding replay window is worse than no replay at all. The memory is strictly intra-meeting and is wiped at the end, and no gradient touches the run-time system. We report SGM-Diar as a proof-of-concept and state its limitations explicitly.

cs.SD · cs.AI

版本更新 · v2arXiv:2608.15390

The Quick and the Dead: Estimating Sparse-Matrix Permanents with Adaptive Work Filtering

Deniz Elbek, Yiğit Manafi, Zeynep Gürdal, Sinan Yıldırım, Kamer Kaya

原文摘要

Rasmussen's permanent estimator is a simple and unbiased estimator for the permanent of a binary matrix, but its practical performance can be limited by trajectories that terminate before completing a perfect matching. These failed trajectories, together with dispersion among the surviving weights, can substantially reduce the effective sample size. Although the literature leverages techniques such as doubly-stochastic matrix scaling to improve proposal balance and support filtering to remove structurally infeasible choices, using these at every step can substantially increase the trajectory cost. Furthermore, these techniques do not directly address the choice of the next vertex whose residual neighborhood is used for the proposal. This paper uses the classical minimum-degree ordering in sparse matrix algorithms to select the next vertex with $\mathcal{O}(n + m)$ total bucket-maintenance work per trajectory, where $n$ is the number of rows/columns in the matrix and $m$ is the number of nonzeros. The proposed estimator uses adaptive schedules to invoke the more expensive scaling and filtering operations only when needed. The experiments show favorable empirical accuracy under fixed time budgets on the tested matrices.

cs.DS

新论文 · v1arXiv:2611.20815

ForeSay: Tell the Future in Words, Branch the Details in Noise for Precipitation Nowcasting

Xudong Ling, Wenjie Luo, Chaorong Li, Tianxi Huang, Tao He, Guiduo Duan

原文摘要

Precipitation nowcasting involves two distinct scales of uncertainty: macroscopic storm evolution and fine-scale local convective variations. Current generative ensemble methods entangle both scales within independent random noise draws. This coupling causes two practical limitations: every ensemble member must execute the full sampling trajectory from scratch, so an N-member ensemble costs N times a single forecast; moreover, divergent trajectories spatially misalign heavy-rain echoes across members, causing standard pixel-wise averaging to blur critical high-intensity extremes. We present ForeSay, a generative nowcasting framework that decouples macroscopic evolution prediction from local stochastic detail generation. Given historical radar frames, a vision-language model first predicts a textual scenario of future storm dynamics to condition a Rectified Flow generator. Guided by this shared macroscopic prior, ensemble members share early trunk sampling steps to establish the storm trajectory and branch with fresh noise only in later steps to explore local convective details. Because members then differ mainly in local details, self-anchored support-consensus decoding replaces pixel averaging with discrete support voting to preserve sharp heavy-rain cores. Across six datasets, ForeSay achieves the best CSI at the highest precipitation thresholds, with relative improvements over the strongest baseline on each dataset ranging from over 10% to 84%. Our 8-member ensemble retains the forecasting skill and diversity of eight independently sampled runs while reducing computational cost from 8x to 5.2x that of a single forecast.

cs.AI