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

+0新增论文
+0其中 AI 相关
+0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：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 07:12 — 2026-11-16 07:12（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：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 23,348 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:2611.15488

FloCOS: Predicting Compact Forward Occupancy Sets of Surrounding Vehicles via Conditional Flow Matching

Chuansheng Dong, Yinxiao Zhan, Zongdian Li, Peng Hou, Jin Wang, Jiayu Fan

原文摘要

Existing methods for predicting surrounding vehicles' forward occupancy may under-approximate the ground-truth occupancy, exposing the ego vehicle to collision risk, or produce overly conservative regions that unnecessarily restrict feasible space and cause planning failures. To address these issues, we propose FloCOS, a conditional flow-matching framework that predicts compact forward occupancy sets with high occupancy coverage. FloCOS represents the forward occupancy set as a time-varying union of half-space convex polygons parameterized by temporal basis coefficients. Conditional flow matching captures the conditional distribution of these coefficients to govern the temporal evolution of the convex components, trained under coverage and union-area losses that penalize missed occupancy and excess area. For downstream trajectory optimization, the predicted nonconvex union is directly incorporated into hyperplane-based collision-avoidance constraints. Evaluations on the Waymo Open Motion Dataset show that FloCOS generates compact forward occupancy sets with high coverage and achieves a higher interaction completion rate than evaluated baselines. Real-world vehicle experiments further confirm its ability to support collision-free planning in interactive scenarios.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.29458

Precise Convergence Speed of Clipped SGD

David A. R. Robin

原文摘要

We present a tightened convergence analysis of clipped gradient descent on $(L_0, L_1)$-smooth functions, with quantitative constants. Building on the ideas of Koloskova et al (2023), we refactor several case disjunctions to reveal the central role of a control of the bias derived from fundamental properties of $\ell_2$-projection, simplifying proofs. We also extend the domain of validity from $η\leq 1 / (9 β)$ to $η< 1 /β$ where $β= L_0 + c L_1$ for clipping constant $c$, which matches the more traditional analysis of smooth functions. We strengthen the convergence criterion from $\left( \min_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ to $\left( \frac{1}{T} \sum_{t < T} \mathbb{E}[\lVert \nabla f(x_t) \rVert_2] \right)$ with matching speed, and lower the final achievable floor from $\mathcal{O}(\min(σ^2/c, σ))$ to the more precise $6 \min(σ^2 /c, 3 σ)$.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2106.07501

Improved Streaming Algorithm for Balanced Hypergraph Partitioning

Zhicheng Guo

原文摘要

Balanced hypergraph partitioning is an essential task for massive hypergraph analysis in distributed computing. Existing methods usually use the entire hypergraph to obtain structural information before the assignment process. However, many applications require online partitioning, motivating the development of streaming algorithms. In the streaming order, vertices are assigned in real time and their ownership does not change. Therefore, partitioning the streamed vertices under the balance constraint is challenging. In this paper, we propose a method for balanced hypergraph partitioning in the streaming mode. By defining a modularity function under the Erdos-Renyi random hypergraph model, we build the Erdos-Renyi Hypergraph Modularity Greedy. We approximate the hypergraph as a uniform hypergraph and optimize the modularity function with lower computational complexity. Compared with other modularity functions, our modularity function is more suitable for streaming algorithms. Finally, we design a data structure to reduce the execution time for finding the block with minimum capacity. Overall, our method achieves the state-of-the-art performance when evaluated with the cut-net metric.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.03501

STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data

Yi Zhang, Farhad Nooralahzadeh, Jonathan Fürst, Fabio Scherrer, Claude Lehmann, Antonis Bezes, Vassiliki Kotroni, Kurt Stockinger

原文摘要

Copernicus, the European Union's Earth observation program, produces petabytes of Earth observation and climate data, offering immense potential for research, policy, and applications. However, access to these datasets requires advanced programming skills and familiarity with domain-specific formats such as NetCDF or GRIB. Moreover, general-purpose Text-to-SQL systems fail when applied naively to the meteorological domain due to a profound ``Symbolic-to-Numeric'' gap. To overcome these limitations, we present an end-to-end Text-to-SQL framework specifically engineered for real-world, scalable meteorological data exploration. Our system intercepts natural language to resolve spatial and semantic ambiguities \textit{before} SQL generation. We design STRATOS, a Spatio-Temporal Resolution Agent for Text-to-SQL to dynamically bridge the symbolic-to-numeric gap by mapping fuzzy concepts to a localized ontology and resolving spatial entities via external knowledge bases. Further, our complexity-aware query rewriter rewrites expensive spatial predicates, reducing execution times from hours to seconds. Last, we introduce the STRATOS Evaluation Workload, comprising 7,520 complex query pairs explicitly designed by domain experts to test scalability and symbolic-to-numeric translation across challenging spatio-temporal dimensions previously unexplored by Text-to-SQL systems.

cs.DB · cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12479

Brief introduction to post-quantum cryptography in industrial applications

Mateusz Żarski, Jarosław Miszczak, Ilias Cherkaoui, Cédric Crettaz, Indrakshi Dey, Adela Georgescu, Deepak V. Katkoria, Ruxandra F. Olimid 等 12 位作者

原文摘要

The development of Post-Quantum Cryptography (PQC) is directly motivated by the necessity to secure information in the face of the quantum threat. This paper provides an overview of recent developments relevant to PQC adoption across several industrial applications, including IoT, healthcare, civil and infrastructure engineering, and defense. We present a brief, self-contained overview of PQC and its market positioning. We perform implementation experiments on selected quantum-safe methods and quantify several aspects, such as the quantum resources required to break common cryptographic schemes, as well as the performance of the most well-known PQC algorithms. We also discuss the resistance of different PQC classes to quantum attacks and the status of PQC implementations in different programming languages. Finally, we present benchmark results on KEMs and signature algorithms to help select the appropriate algorithm for a specific application based on criteria such as algorithm performance, data lifetime, and level of data sensitivity.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15481

SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution

Haojun Tang, Wenda Zhao, Xiang Zhou, Qiwei Lin, Lida Huang, Yan Wang

原文摘要

Recently developed remote sensing (RS) agents execute real-world tasks with complex workflows through multi-step tool invocation. These agents, however, typically rely on predefined expertise or parameter updates. They thus require updating expert knowledge or retraining models whenever new tools, tasks, or execution patterns emerge, limiting their continual adaptability in dynamic Earth environments. In this work, we seek to equip general-purpose agents with RS tool-call knowledge that can be automatically extracted from demonstrated trajectories without expert intervention or parameter updates. Specifically, we propose SkillEarth, a self-evolving skill extraction method that externalizes RS tool-call knowledge as reusable, retrievable, and evolvable skill files and refines them through observation-grounded evolution. Unlike existing automatic skill extraction methods that rely on outcome-based reflection to refine skills holistically, SkillEarth grounds skill evolution in real tool-chain execution and combines dual-judge feedback with a grounded observation routing graph for precise component-level refinement. The resulting skills are generalizable, reliable, and transferable: they improve overall RS tool-call performance across three frontier LLMs and four open-source LLMs, are refined through real tool execution feedback, and support cross-model reuse without retraining. Experiments on OpenEarth-Bench and Earth-Bench demonstrate that SkillEarth achieves better tool selection, argument correctness, execution-order consistency, and task completion than existing RS agents and skill extraction methods.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15479

DETER: Suppression During Pretraining for Tamper Resistance

Maria Ios Glarou, Martin Jaggi

原文摘要

Open-weight language models can acquire knowledge that could enable biological, chemical, or cyber misuse. Any attempt to limit such knowledge must remain effective after the model weights are released and can be fine-tuned. Unlearning applied after pretraining can be rapidly undone, whereas filtering the pretraining corpus offers greater resistance. We ask whether actively suppressing knowledge during pretraining can further increase the fine-tuning required to acquire it. Even simple gradient ascent interleaved with standard pretraining on the filtered corpus makes medical knowledge harder to acquire through adversarial fine-tuning than filtering alone or post-hoc unlearning. At 1B parameters, reaching the held-out PubMed loss of an unfiltered model requires over 20$\times$ as many PubMed fine-tuning tokens as after filtering alone. Retained knowledge is evaluated using both held-out data and downstream tasks. Across model sizes, varying suppression strength reveals an increasingly favorable trade-off between fine-tuning difficulty and held-out loss on retained pretraining data. These results point to pretraining as an effective stage for making unwanted capabilities harder to acquire through subsequent fine-tuning. Code is available at \href{https://github.com/MEGlr/DETER}{\texttt{github.com/MEGlr/DETER}}.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.01750

Deep Heteroskedastic Regression: Post-Hoc Variance Estimation from Latent Representations

Mikkel Jordahn, Jonas Vestergaard Jensen, James Harrison, Michael Riis Andersen, Mikkel N. Schmidt

原文摘要

Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks. In heteroskedastic regression, where the uncertainty of the target depends on the input, a common approach is to train a neural network that parametrises the mean and the variance of the predictive distribution. Yet to this day, training deep heteroskedastic regression models poses severe practical challenges in the trade-off between uncertainty quantification and mean prediction, such as variance overfitting, optimization difficulties and representation collapse. In this work, we identify and discuss the core issues and propose a simple and efficient procedure that addresses these jointly by post-hoc fitting a variance model across the intermediate layers of a pretrained network on a hold-out dataset. We demonstrate that this method is competitive with end-to-end trained mean-variance networks in heteroskedastic UQ on several data modalities. The method retains mean prediction accuracy, is cheap at both train and prediction time, and requires no additional data compared to existing methods. Finally, we show this method works on large scale foundation models for chemistry, paving the way for cheap heteroskedastic UQ in large scale neural networks without having to retrain such models end-to-end.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15475

Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models

Eric So, Alex Imas

原文摘要

We show that AI models exhibit loyalty capture, a form of structural sycophancy in which reporting relationships influence models' recommendations to serve the personal interests of their supervisors, without any explicit instruction, user feedback, or adversarial prompting. Specifically, models reporting to a CEO are significantly more likely to recommend cutting investment spending when the CEO's bonus depends on raising current period earnings. This effect is predictably absent from a metric-irrelevant placebo. The behavior appears consistent with loyalty-based motivated reasoning: models identify the bonus target, calculate how their recommendation helps achieve the target, and dismiss considerations of long-term value, often presenting their recommendations without treating the incentive as a conflict of interest. Prompt-based interventions help whereas generic conflict disclosures or stakeholder bargaining fail to eliminate it. Taken together, our findings indicate that AI models deployed within reporting relationships can act in favor of their supervisor's incentives at the expense of the organizations they are meant to serve.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.16543

The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation

Jiaheng Zhang, Daqiang Zhang

原文摘要

The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation.

cs.IR · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15472

What You See Is (Not) What You Got: The Human Factor in PDF Signature Verification

Jakob Heher, Emanuel Pichler, Stefan More

原文摘要

Signed PDF documents have legally binding value under frameworks such as the EU's eIDAS regulation. In this work, we present Genuine PDF Forgeries, a novel attack class that focuses on human factors in signature validation. Our attacks target the disconnect between cryptographically verifiable signer certificates and human-visible signature blocks embedded in documents. We analyze our attacks against 23 PDF viewers and validation tools across desktop platforms and the web. We find that nine of the 13 viewers that automatically report signature validity hide authenticated signer information behind additional user interaction. We then evaluate the attack in twin deception-based online studies with 584 EU-based participants. To further validate the impact, we perform a highly tailored real-world attack study with six trials within two privacy-sensitive organizations. Five of six organizational trials accepted requests authenticated using the forged visual identity. In the online studies (total n=584), the most effective attack variant deceives 71.9% of eligible participants on first impression, and 57.3% continue to be deceived even after we prompt for additional introspection. We derive viewer-side countermeasures and prototype a safeguard that overlays the untrusted signature block with signer information obtained from the validated certificate. Our results show that boolean validity indicators, not associated with the authenticated signer identity, are insufficient in practice.

cs.CR · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15469

HARE: Fast Read Disturbance Threshold Profiling in Modern DRAM Chips via Reduced Timing Constraints

F. Nisa Bostanci, Ismail E. Yuksel, Ataberk Olgun, Harsh Songara, Andreas Kosmas Kakolyris, Haocong Luo, Konstantinos Marios Sgouras, Onur Mutlu

原文摘要

Modern DRAM chips are vulnerable to read disturbance, which manifests as bitflips in a victim row physically near an aggressor row that is repeatedly activated. State-of-the-art mitigations rely on accurate and exhaustive profiling of the read disturbance threshold (RDT), i.e., the minimum number of aggressor row activations needed to induce the first bitflip. However, RDT changes significantly and unpredictably over time, motivating online profilers that dynamically adjust a mitigation's RDT configuration. RDT profiling is costly for online profilers (e.g., hundreds of seconds for a 16-bank DDR4 module) because 1) measuring a single DRAM row's RDT requires many activations and 2) each DRAM row can have a different RDT, requiring many rows to be profiled. We introduce HARE, an online RDT profiling technique that intentionally exacerbates read disturbance to quickly profile a DRAM module. HARE's key idea is to reduce the timing constraints between consecutive DRAM commands during profiling. Doing so significantly reduces profiling time by 1) directly reducing the execution time of the profiling command sequence and 2) exacerbating read disturbance such that the first bitflip occurs at a smaller activation count than with the conventional RowHammer sequence. From our characterization of 180 real DDR4 DRAM chips from four major DRAM manufacturers, we make three observations. First, HARE measures a DRAM row's RDT 31.2% faster than the RowHammer profiler and a DRAM module's minimum RDT with an average reduction of 21.7%. Second, HARE flips more than 95% of the cells that the RowHammer pattern flips. Third, HARE preserves the RDT ranking of rows well enough such that it can exhaustively reprofile a small set of rows to improve its minimum RDT estimation. Our end-to-end evaluations show that HARE enables significant system performance improvements and outperforms the RowHammer profiler.

cs.AR · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15467

AutoOntic: Automatic Ontology Induction from Text for Knowledge Graph Construction

Alla Chepurova, Aydar Bulatov, Mikhail Burtsev, Yuri Kuratov

原文摘要

Graph-based retrieval-augmented generation depends on the quality of the knowledge graph (KG) it retrieves over, yet schema-free LLM-based extraction pipelines typically produce flat graphs: deduplicated entities and relations with no type hierarchy and no domain/range constraints. We present AutoOntic, a pipeline that automatically constructs an ontology from text by canonicalizing open-vocabulary entity types and relations, inducing a hierarchy over the canonicalized types, and mining relation-level domain and range constraints. Its hierarchy induction procedure prioritizes types using corpus-derived relation-argument profiles and places them through local, LLM-adjudicated parent/child checks, allowing newly inserted types to trigger reassignment of existing parent-child links. The resulting hierarchy constrains entity deduplication and supports the induction of relation-level domain/range constraints. For intrinsic evaluation, we introduce a reference-based protocol that classifies induced ontology types as exact, broader, narrower, or unrelated to reference domain and range classes. On the Wikidata-TekGen and DBpedia-WebNLG subsets of Text2KGBench, over 90% of AutoOntic's induced endpoint types are semantically aligned with the reference classes across two LLM backbones: about half match exactly, while most remaining differences concern granularity. On MINE, knowledge graphs organized using an ontology built by AutoOntic achieve 88% retrieval accuracy. AutoOntic is available at https://github.com/screemix/AutoOntic.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15465

On-Edge Acoustic Continual Anomaly Detection: A Cross-Platform Comparative Study

Rami Zewail, Yehia Ehab, Karim Ali, Ahmed Mahrous, Mohamed Awad, Bassem Mokhtar

原文摘要

Acoustic Anomaly Detection (AAD) serves as a non-contact approach for machine condition monitoring, yet much of the existing research is evaluated offline and rarely addresses embedded hardware constraints or microphone variations under operational drift. This paper presents a comparative evaluation of on-edge continual AAD across two embedded platforms the ESP32-S3 (with an external I2S digital microphone) and the Arduino Nicla Vision (with an onboard Pulse Density Modulation (PDM) microphone) using a shared detection model. The model utilizes a lightweight ShallowNet encoder and contrastive prototype learning to map spectrograms into a 32-dimensional embedding space. Both boards run an identical TensorFlow Lite for Microcontrollers (TFLM) encoder, performing on-device prototype learning updated via an exponential moving average. A cloud pipeline orchestrated through Firebase and MQTT enables remote data collection and retraining. Evaluated via a controlled speaker-replay protocol using standardized Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge Task 2 machine sounds, the ESP32-S3 achieved 82.35% to 95.00% accuracy across five machine types, while the Nicla Vision achieved 79.41% to 95.00%. The two platforms demonstrated comparable performance, confirming that the lightweight prototypical architecture transfers reliably across distinct hardware and sensor tiers.

cs.SD · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15464

RSE-TTS: Compact Text-to-Speech through Shared Text-Aware Reference Encoding and Generation

Ming Ma, Mingjie Chen, Yuanzhong Zheng, Hengyao Bao, Hailin Yu, Shijing Yu, Hao Qiu, Gongfan Cao 等 11 位作者

原文摘要

Can a speech generator also serve as an effective voice encoder? We show that a pretrained autoregressive text-to-speech (TTS) backbone can be repurposed for reference compression, improving speaker similarity in subsequent synthesis. Jointly encoding reference speech and its transcript further strengthens this capability. Controlled ablations and activation interventions trace the text benefit through intermediate acoustic representations into the compressed vectors that condition generation. Building on these findings, we introduce RSE-TTS, whose Reconstructive Speaker Encoder (RSE) shares the generation backbone and compresses paired reference text and speech into eight continuous vectors. Sharing reduces encoder-generator parameters by 48% relative to independent pretrained encoding. Large-scale English training yields a 118M-parameter generator that improves both word error rate and speaker similarity over the corresponding official MOSS-TTS-Nano cloning modes on all three English benchmarks. Combined with acoustic continuation, RSE-TTS approaches the speaker similarity of substantially larger systems while achieving lower WER than the evaluated CosyVoice 3 and MOSS-TTS-Local models. Audio samples are available at https://voxnexusai.github.io/RSE-TTS/.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15463

Right Answers, Inconsistent Evidence: Source-Level Counterfactual Auditing of Large Audio-Language Models

Yi Zhang, Yi Li, Hongwei Du

原文摘要

A large audio-language model (LALM) can answer "is a cat present?" about a mixture correctly, and its confidence can drop when the cat is removed, yet this does not show that it can tell the cat's presence from its absence. We introduce TRACE. It deletes the queried source and each rival in turn and asks whether every view still containing that sound outscores the view with it removed. Across 8 LALMs and 3,456 controlled mixtures, 6.3% of correct answers fail this ordering: the target-absent view scores at or above some target-present view, a conflict no shared threshold repairs. A target-only score check misses 42.5% of them. The share rises from 4.9% to 8.4% as target SNR falls from +5 to -5 dB, even on units correct at every level, and survives loudness and re-pairing controls. Accuracy certifies the answer; TRACE audits whether it orders presence above absence. Code and data: https://github.com/yikise/TRACE.

cs.SD · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15462

Chinese Whispers About Vulnerabilities

Jukka Ruohonen

原文摘要

The dissemination of information about known software vulnerabilities occurs online in various ways. Everything from email and development systems to social media are used. Given this variety and a dataset of about 382 thousand online references for about 55 thousand vulnerabilities, the paper demonstrates that the referenced online information sources tend to be mostly dissimilar statistically. The mean cosine similarity between them is only 0.22. Interestingly, the amounts of online references neither increase nor decrease similarity between the online information sources. In contrast, vulnerabilities primarily associated with GitHub and programming language ecosystems tend to have more dissimilar online references than other vulnerabilities. Also vulnerability reports, whether in bug tracking systems or bug bounty platforms, tend to increase dissimilarity. With these empirical results, the paper contributes to the efforts to narrow an enduring knowledge gap related to the online tracking and associated traceability of software vulnerabilities.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12144

DisasterVLG: Vision-Language Grounding and Evidence-Based Reasoning for Disaster Scene Understanding

Ali Diba, Aisha Al-Mohannadi, Yin Yang, Muhammad Imran, Ferda Ofli

原文摘要

General-purpose vision-language models struggle with crisis imagery due to its inherent noise, ambiguity, and high variability across disaster events - yet timely, accurate scene understanding is critical for humanitarian response. To address this, we introduce DisasterVLG, a large-scale multi-task dataset containing 1.24 million disaster images from 142 countries paired with 33 million structured annotations spanning dense captioning with localization, incident assessment, relational scene descriptions, and crisis-grounded visual question answering (VQA) across diverse hazard types and scene contexts worldwide. Unlike prior disaster benchmarks that focus narrowly on classification, DisasterVLG unifies recognition, grounded reasoning, and uncertainty-aware interpretation. A distinguishing feature is its evidence-grounded annotation design: each VQA instance includes supporting evidence text that links visual observations to answers, alongside positive and negative question pairs, multiple answer formats, and difficulty labels. Visual grounding layer links caption phrases to image regions and relationship statements to subject-object boxes, with explicit labels for visual supports and clues. To support rigorous evaluation, we construct a human-verified test set of 38K images (1.15M annotations) spanning broad geographic regions and disaster types. Experiments with domain-adapted vision-language models demonstrate strong performance across disaster captioning, incident recognition, and grounded VQA, while also exposing the limitations of general-purpose models in crisis-specific reasoning. DisasterVLG establishes a scalable, reproducible benchmark for vision-language models that must reason reliably under real-world uncertainty. We will publicly release the dataset, trained models, and code.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15460

Read and Ignore: What Self-Directed LLM Agents Do in Public Service Scenarios

Diana Kozachek, Kinjalk Srivastava

原文摘要

Underspecified instructions leave LLM agents to decide what to do. In public services, staff write these instructions, but the agent's decisions affect residents, patients, and students. We build four expert-validated public-service scenarios with records and decision levers that can be checked in the files, collect $2{,}400$ trajectories from ten LLMs under four prompt conditions, and compare them with $1{,}000$ runs in a context-free sandbox. Agents read the records in $96.9\%$ of open-ended runs and produce an artifact or a self-chosen task in $18.7\%$; with an explicit task, $86.0\%$ produce. Domain context does not change how many runs produce ($18.7\%$ vs.\ $16.0\%$), and the production ranking of the models largely carries over (Spearman $0.79$), while the ranking by whether a model reads the records does not ($0.19$). Context cuts boundary-probing turns per run by $60\%$, and some artifacts contradict the records. We contribute a test that a public-service institution can run on its own records before procurement; its rule-based taxonomy needs no labeled data, and scenarios, code, and trajectories are released.

cs.AI · cs.HC · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15459

Fear of Memorizing Objects: End-to-End Zero-Shot Model-Based Object Detection

Leon Greiner, Wout Boerdijk, Junwen Huang, Benjamin Busam, Rudolph Triebel, Maximilian Durner

原文摘要

This paper presents FOMO (Fear of Memorizing Objects), an end-to-end trainable transformer-based architecture for zero-shot model-based object detection. Existing approaches typically follow a proposal-and-match pipeline: target-agnostic mask proposals are generated and then matched to template features in a set of loosely coupled stages, making them susceptible to fragmented proposals in clutter and degraded matching under occlusions. FOMO elegantly replaces this paradigm by injecting object template information early in the detection pipeline: Bidirectional attention between learnable latent tokens, multi-view CAD templates, and query image features produces object-aware image features and conditioned queries which are subsequently decoded into bounding-box and confidence predictions. We train FOMO on Clutter6D, a novel large-scale synthetic dataset with over 500k images featuring more than 10k diverse object models rendered in highly cluttered scenes with multiple instances and varying occlusion levels, which addresses the limited object diversity and lack of realistic dense clutter in existing datasets for training zero-shot multi-instance algorithms. In true zero-shot fashion, FOMO achieves 54.2 mAP on BOP-Classic-Core at 0.23 s per image, ranking second overall with 3.8 pp difference to the top method while being more than 7x faster. Throughout comprehensive ablation studies we investigate and verify architectural design choices.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2511.00125

DAISY: Fault-Guided Assertion Inference for Dafny

Álvaro Silva, Alexandra Mendes, Ruben Martins

原文摘要

Formal verification with Dafny provides strong correctness guarantees, but verification failures often require users to determine where helper assertions are needed and to manually write the assertions necessary for verification to succeed. This proof-engineering burden is difficult, time-consuming, and a barrier to the adoption of verification-aware languages. We present DAISY (Dafny Assertion Inference SYstem), a tool for fault-guided assertion inference in Dafny. Given a Dafny program and a target method, DAISY localizes likely assertion sites using verifier diagnostics, LLM-based localization, or their combination. It then annotates the program with assertion placeholders, retrieves relevant in-context examples, generates candidate assertions with an LLM, and validates candidates by running the Dafny verifier. To evaluate DAISY, we extend DafnyBench with verification-failing variants created by removing helper assertions from verified programs. The resulting benchmark distinguishes between programs with one missing assertion, two missing assertions, and all assertions removed, allowing us to evaluate DAISY on increasingly difficult proof failures. On this benchmark, DAISY verifies 86\% of programs with a single missing assertion and 36\% of programs with two missing assertions. These results show that fault-guided LLM assertion inference can repair many Dafny verification failures. They also show that successful repairs often differ from the original assertions, reducing proof-engineering effort without reconstructing the original proof.

cs.SE · cs.AI · cs.LO · cs.PL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.10304

Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages

Vladimir Dobrovolskii, Ibragim Badertdinov, Alexander Golubev

原文摘要

Challenging repository-level benchmarks remain limited for many programming language ecosystems, where filtering scarce candidates with ambiguous descriptions or defective tests can discard valuable engineering problems. We introduce Longtail-SWE, a benchmark of 202 issue-resolution tasks across 13 languages with limited coverage in existing repository-level benchmarks: Clojure, Dart, Elixir, Erlang, F#, Haskell, Julia, Kotlin, Lua, OCaml, R, Scala, and Swift. Its construction uses a solver-judge-repairer pipeline: a solver attempts each candidate task, and a judge reviews the task together with the solver's trajectory and test results to guide revisions to tests and task descriptions. These revisions aim to correct tests that reject valid alternative implementations or accept incorrect solutions while retaining challenging tasks and preserving their intended requirements. We evaluate nine model configurations, including frontier models, and analyze task-solving performance, consistency across repeated attempts, and resource usage. We release all benchmark instances, executable environments, complete construction and evaluation tooling, and agent trajectories, together with an additional set of easier tasks to support evaluation of smaller models.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15457

WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration

Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser, Muzammil Behzad

原文摘要

Underwater image restoration remains challenging because color distortion, scattering, and detail loss affect low- and high-frequency image components differently. Recent diffusion-based methods have shown strong restoration quality, but often rely on multi-stage pipelines and costly iterative refinement. We present WaveFlow-UIE, a single-pipeline wavelet-domain flow model that directly learns to transform degraded underwater wavelet representations into clean ones. Our method applies a discrete wavelet transform, estimates lightweight physics-inspired degradation cues including transmission and ambient light, and conditions a velocity network trained with flow matching in wavelet space. The training objective combines flow-matching, frequency-weighted reconstruction, perceptual, color-consistency, and physics-consistency losses. Across UIEB, LSUI, UFO-120, and EUVP, WaveFlow-UIE achieves a strong quality-efficiency tradeoff, with especially competitive results on perceptual metrics. Relative to a strong wavelet-based diffusion baseline, the proposed model substantially reduces inference cost while maintaining or improving restoration quality on several paired benchmarks. We show that reducing the inference process from five flow steps to a single step preserves nearly all of the restoration quality while providing an additional speedup of about $4\times$ on UIEB at $256\times256$ resolution. This single-step result suggests that a single-pass wavelet-domain model is an effective alternative to heavier diffusion-style refinement.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15456

Bet Imaginatively, not Historically in Independent-Data Sequential Testing

Nathaniel Xu, Feng Liu, Danica J. Sutherland

原文摘要

Sequential testing avoids some of the many controversies and drawbacks related to traditional batch testing with p-values. In particular, the testing by betting paradigm has developed rapidly in recent years; it frames the level of evidence against the null as the wealth of a player in a betting game. Naturally, how much a player should bet is a key consideration, and should reflect their confidence in what they know about the next observed data point. Much current work uses standard betting strategies developed for adversarial problems. In the stochastic setting, where the observed data is independent and stationary, these approaches may be suboptimal. We propose a simple betting strategy, follow the leave-one-out e-power (FLOE), that exploits the i.i.d. nature of a data stream to estimate the e-power of our current test on the underlying distribution. We average not over the historical evidence collected so far, as generic online learning-based methods do, but instead over the equally-likely possible data sequences we might have seen based on shuffling the data. With an additional principled regularization technique, this simple drop-in method yields substantial improvements in testing performance on a variety of kernel two-sample and independence testing problems.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2409.07563

MPPI-Generic: A CUDA Library for Stochastic Trajectory Optimization

Bogdan Vlahov, Jason Gibson, Manan Gandhi, Evangelos A. Theodorou

原文摘要

This paper introduces a new C++/CUDA library for GPU-accelerated stochastic optimization called MPPI-Generic. It provides implementations of Model Predictive Path Integral control, Tube-Model Predictive Path Integral Control, and Robust Model Predictive Path Integral Control, and allows for these algorithms to be used across many pre-existing dynamics models and cost functions. Furthermore, researchers can create their own dynamics models or cost functions following our API definitions without needing to change the actual Model Predictive Path Integral Control code. Finally, we compare computational performance to other popular implementations of Model Predictive Path Integral Control over a variety of GPUs to show the real-time capabilities our library can allow for. Library code can be found at: https://acdslab.github.io/mppi-generic-website/ .

cs.MS · cs.DC · cs.RO · eess.SY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.11513

Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics

Zhongyang Hu, Naijie Gu, Xiangzhi Tao, Tianhui Gu, Yibing Zhou

原文摘要

A key subtask in lexical substitution is ranking the given candidate words. A common approach is to replace the target word with a candidate in the original sentence and feed the modified sentence into a model to capture semantic differences before and after substitution. However, effectively modeling the bidirectional influence of candidate substitution on both the target word and its context remains challenging. Existing methods often focus solely on semantic changes at the target position or rely on parameter tuning over multiple evaluation metrics, making it difficult to accurately characterize semantic variation. To address this, we investigate two approaches: one based on attention weights and another leveraging the more interpretable integrated gradients method, both designed to measure the influence of context tokens on the target token and to rank candidates by incorporating semantic similarity between the original and substituted sentences. Experiments on the LS07 and SWORDS datasets demonstrate that both approaches improve ranking performance.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15449

Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning

Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim

原文摘要

Text-aware image super-resolution (TAISR) aims to recover high-resolution images from low-resolution inputs while preserving textual content. Existing methods treat this as a visual restoration problem, yet severely degraded text often cannot be read from local visual evidence alone. Humans instead read it by reasoning over image context, logical patterns, and prior knowledge. This raises a fundamental question: Does TAISR need reasoning? To answer this, we introduce two diagnostic tools. The first, ReasonText, is a human-curated benchmark that separates reasoning-required text from locally recoverable text. The second, Ground-Truth Text-Crop Accuracy (GTTCA), is a recognition-based metric that measures text restoration quality without text detection errors. Evaluating twelve recent super-resolution (SR) models, we find a consistent and substantial performance drop on reasoning-required text, revealing a systematic blind spot. Two observations point to a remedy. One is that text-conditioned SR models restore text substantially better when given ground-truth text. The other is that multimodal large language models (MLLMs) can read degraded text in low-resolution images through reasoning. We therefore propose Reasoning Transfer via Captioning (RTC), a training-free plug-in that uses an external MLLM to infer the degraded text and feeds the resulting caption to a text-conditioned SR model. RTC consistently improves all six text-conditioned SR models we evaluate, especially on reasoning-required text. Surprisingly, a real-world SR model with RTC can even outperform the TAISR model with RTC, suggesting that reasoning should be a core design axis for future TAISR.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15448

Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models

Nikola Đukić, Tim Lebailly, Tinne Tuytelaars

原文摘要

In computer vision, vision-language and self-supervised encoders are two unique paradigms characterized by global language alignment and high-quality vision-only patch representations, respectively. Multimodal large language models (MLLMs) often use the former because of language alignment, despite the recent rise in vision-centric tasks resembling traditional dense vision tasks that would likely benefit from the high-quality patch representations, raising the question whether self-supervised models could aid MLLMs in vision-centric tasks. To investigate this, we define semantic (in)consistency of patch tokens from language-aligned encoders and identify two sets of tokens, semantically consistent (SCTs) and semantically inconsistent (SITs). Through systematic probing via the removal of SCTs or SITs from the input of modern MLLMs, we show higher reliance on SCTs than SITs, as removal of the former induces larger performance drops. This demonstrates that MLLMs benefit from semantic consistency of vision tokens. With this in mind, we devise a simple yet effective extension of the MLLM training objective that combines traditional language modeling with semantic guidance via minimization of semantic inconsistency. This strategy, named Semantically-Guided Training (SGT), combines the signals of both loss terms to push the vision encoder towards providing semantically consistent tokens, while preserving language alignment. Extensive evaluation shows that SGT outperforms all baselines and MLLMs with specialized vision encoders on vision-centric benchmarks while keeping strong scores on text-centric benchmarks, thus setting state of the art on average across all tasks. Our results highlight the importance of combining language alignment and semantic consistency through the lens of MLLMs rather than independently from them and pave the way towards the design of better MLLM vision encoders.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.15447

Escaping the Curse of Dimensionality in One-Step Flow-Based Generative Models

Konstantin Yakovlev

原文摘要

Flow and diffusion-based generative models achieve state-of-the-art quality, but require multiple forward passes at inference time, making them computationally costly. Consistency models overcome this by learning a flow map directly, enabling few-step generation and dramatically reducing the computation needed at test time. However, formal statistical guarantees for such one-step generators are scarce. Existing results either suffer from the curse of dimensionality or rely on impractical loss functions. We investigate whether one-step flow-based models can escape the curse of dimensionality under the assumption that the data distribution is generated by a low-dimensional surface perturbed with Gaussian noise. In this setup, we derive approximation and generalization error bounds for the flow map estimate that circumvent the curse of dimensionality. Our findings provide the first principled explanation for practical success of one-step flow-based generative models.

math.ST · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.25096

Toward Agentic Retrieval-Augmented Generation for Enterprise Retail Workflows over Heterogeneous Data Sources

Jeonghwan Choi, Jibin Hwang, Hayoon Park, Hyeonjae Cheon, Hwanjun Song

原文摘要

Enterprise retail workflows require agents to chain evidence across heterogeneous sources, from structured product and order records to unstructured inquiries and reviews, yet existing agentic RAG benchmarks rarely capture this challenge. To enable controlled evaluation of such workflows, we introduce RetailBridge, a compositional retail benchmark built from persona-driven simulations. Its questions are constructed by linking entities and intermediate answers across heterogeneous sources, requiring agents to identify the relevant sources, carry evidence between them, and produce a grounded answer. To systematically evaluate LLMs on these retail workflows, we develop RetailRAG, a retail-aware framework equipped with auto-schema briefing, source-routed plan chaining, and diagnostic plan revision. RetailRAG consistently outperforms existing agentic RAG baselines across all evaluation axes, serving as a strong reference system for assessing LLM agents on retail workflows. On RetailBridge, evaluating ten LLM backbones with RetailRAG reveals multi-source chaining as the dominant bottleneck across providers and model scales, suggesting that reliable retail agents require explicit cross-source orchestration rather than scaling alone. Code and data are publicly available at https://github.com/DISL-Lab/RetailBridge.

cs.AI · cs.IR

查看论文
arXiv ↗PDF ↗