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

+806新增论文
+644其中 AI 相关
+92已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 11:52 — 2026-11-21 11:52(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58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。

28,961 已收录论文24,030 AI 相关8,912 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 24,030 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.24360

Towards Pose-Robust Few-Shot Vision-Language-Action Models

Wenhao Li, Zhongyi Han, Yuhao Wei, Liang Han, Yilong Yin, Liqiang Nie

原文摘要

Fine-tuning a vision-language-action (VLA) model on a few dozen demonstrations is the standard way to put a manipulation policy on a robot, yet the resulting policy silently assumes that the camera and the robot base stay exactly where they were during data collection: a bumped tripod or a base re-docked a few centimetres away makes it reach for the wrong place. We show that both failures are one phenomenon, a change of the camera-to-base extrinsic that the policy has memorised, and that the robot carries everything needed to undo it. We introduce WACO, a world-anchored canonicalization framework for VLA models: the arm, placed by forward kinematics at the measured joint angles, serves as a metric calibration target, and the static scene serves as the world anchor that tells a moved camera from a moved robot. From a single RGB-D frame, WACO estimates both shifts without ground-truth extrinsics or extra data, canonicalises the image to the calibration viewpoint and the state, action and start pose to the calibration base frame, and fine-tunes the unmodified policy under the artefacts of its own estimator. We also introduce LIBERO-PoseShift, the first benchmark for RGB VLAs with graded camera, base and compound shifts. Across LIBERO-PoseShift, the LIBERO-Plus camera track and four real-world tasks on a UR5e robot, WACO consistently outperforms the standard few-shot recipe and prior viewpoint-robust methods, raising shifted success by 13.2 points in simulation and by 36.7 points on the real robot, recovering 90% of the simulation gap to a ground-truth oracle and 87% of the real-robot gap, and establishing a new state of the art among methods that use no perturbed training data, with no test-time calibration. Project page: https://peacelwh.github.io/WACO/.

cs.RO · cs.AI · cs.CV

版本更新 · v2arXiv:2610.01269

IQS-BO: In-Context Query Selection for Bayesian Optimisation

Luca Geminiani, Nadja Klein

原文摘要

Bayesian Optimisation (BO) is a powerful framework for optimising expensive black-box functions, but typically requires refitting a surrogate and maximising an acquisition function at every evaluation. In-context approaches based on Prior-data Fitted Networks (PFNs) amortise part of this cost by pre-training transformers on functions drawn from synthetic priors. PFNS4BO amortises the surrogate but still relies on a numerically maximised acquisition function, while FIBO performs BO fully in-context by sampling optimiser locations from a learned density, which fixes the decision rule and admits no surrogate. Learned acquisition functions score a finite candidate set with a network, but, lacking a label for the query, learn the score by reinforcement learning. We propose IQS-BO, a PFN that learns the query decision by supervised learning on synthetic priors. In a single forward pass, IQS-BO predicts the probability that each candidate is the best in the set, and we show that training minimises its expected KL divergence to the posterior probability of this event. The model can be pre-trained without a surrogate for fully in-context BO, or take the predictions of a fixed probabilistic surrogate as additional input, amortising only the decision step. Our method proposes queries at a fraction of the cost of acquisition-based methods, while matching or outperforming BO with Gaussian processes (GPs) and available in-context methods in sequential and batch optimisation, in low and high dimensions. Finally, we propose a mixture prior for pre-training PFNs which combines samples from GPs with functions exhibiting warped inputs, narrow optima, or plateaus that are poorly modelled by stationary GP kernels. We show that pre-training on this prior can improve performance and help the network generalise to a broader range of optimisation problems.

cs.LG · stat.ML

版本更新 · v2arXiv:2608.28384

MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places

Jason Armitage, Ioannis Tsochantaridis, Linda Mazzone, Chuqiao Yan, Srini Narayanan, Sarah Ebling

原文摘要

We introduce MAP, the first benchmark to evaluate multimodal AI systems as assistants for users with accessibility requirements when planning visits to places in the real world. In our evaluation, systems are presented with requests to verify or recommend a point of interest meeting an accessibility requirement. MAP contains two novel assessments: Claim verification for accessibility planning assesses if information on places and stated accessibility features is supported and identifies places that satisfy requested accessibility features. Visual evidence retrieval for accessibility planning checks if a multimodal AI system can select visual evidence for the requested place and accessibility feature. Our methodology supports comparison of AI systems in a setting where place information and accessibility information can change over time by evaluating systems and refreshing ground truth data at scheduled times. The benchmark is based on automatic rating and human rating for a proportion of responses.

cs.AI

版本更新 · v3arXiv:2610.15463

MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection

Hexiang Gu, Saihui Hou, Changlan Liu, Min Ren, Huijia Wu, Hongxun Gu, Zhaofeng He

原文摘要

With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex interactions among visual, textual, and contextual cues, making accurate detection challenging. Recent studies have introduced Retrieval-Augmented Generation (RAG) and external knowledge into harmful meme detection. However, existing methods mainly retrieve similar instances or auxiliary information, limiting their ability to capture reusable harmfulness knowledge and underlying reasoning mechanisms, and thus constraining both detection performance and interpretability. To address these challenges, we propose MemeLogos, a knowledge-driven retrieval-augmented reasoning framework for harmful meme detection. MemeLogos abstracts recurring harmfulness patterns and reasoning structures from diverse harmful cases into reusable knowledge units and organizes them into a dedicated star-shaped knowledge graph. By combining structured knowledge retrieval with an explicit multi-stage reasoning process inspired by cognitive mechanisms, MemeLogos leverages retrieved knowledge to guide harmfulness reasoning, improving both detection reliability and interpretability. Extensive experiments show that MemeLogos consistently outperforms existing harmful meme detection methods while generating more coherent and interpretable reasoning, demonstrating the effectiveness of structured harmfulness knowledge for multimodal content understanding.

cs.AI

版本更新 · v2arXiv:2609.32495

Hearsay: Who Can Audit the Record a Deployed Agent Harness Writes?

Jiahong Dai, Zhuochen Yang, Pengyang Shao, Kelvin Ng, Zhongyi Liu, Chengquan Ju, Yuting He, Bo Hu

原文摘要

The record of an agent's run is written by the harness that drives the agent. When the run is later disputed, the auditor was not there and has only this record. We ask whether someone who was not there can check the record, and what decides the answer. It depends on who wrote what a check can rely on: if the harness wrote all of it, the record is only the harness's own word, and we call it hearsay. We build Hearsay, a benchmark that examines the record and not the task: five harnesses run fourteen tasks, model examiners from three vendors and a human panel read the records and answer questions about the runs, and every passage they cite is labelled mechanically by who wrote it. We also audit what is deployed: in all sixteen frameworks, the harness is the only writer. With one writer, readers can name the fault from the record, in up to nine runs in ten, but they cannot check the record. The model examiners claim corroboration for 18 to 55 points more of their evidence than the labels support, a gap we then predicted for runs driven by another vendor's model and found again. And the best of them notices only half of the alterations we make to a record, while the two that name the fault most often cannot tell what a harness left out. With a second writer, the record can be checked. Our sandbox keeps a ledger of what passes between harness and model, and reading the ledger against the record in both directions shows what the record leaves out and what it adds. We test this as an auditor would use it, on one unseen record at a time. On runs driven by a third vendor's model, with every rule committed before the records existed, it reports 64 of 66 alterations and flags none of 84 clean records. On held-out records in five formats it reports 109 of 115. What makes a record evidence is a second writer, not a better reader.

cs.CR · cs.AI · cs.CE · cs.SE

新论文 · v1arXiv:2611.24357

Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents

Guolong Zheng, Chen Hou, Xu Yang, Jianshan Zhang, Tao Huang

原文摘要

Traditional long-horizon LLM agents often hand off context through full-history prompting, retaining all previous action--observation interactions. As execution proceeds, this history keeps growing, increasing inference cost and potentially degrading accuracy. Existing methods control this growth by preserving compact conclusions while removing earlier observations, but doing so can discard evidence that later becomes relevant. We introduce Semantic Context Handoff (SCH), whose central abstraction is state--evidence separation: a compact semantic state carries the agent's current interpretation, while supporting action--observation evidence remains separately addressable and can re-enter context when later execution makes it relevant, without separate summarization or retrieval-model calls. Empirically, SCH improves long-horizon agent performance while substantially reducing context cost. In a controlled 150-task SWE-bench study, SCH's evidence recovery improves Pass@1 from $80.0\%$ to $86.9\%$ at essentially unchanged token use and execution time. In the complete-system comparison, SCH achieves 86.9% Pass@1 while using 43% fewer tokens and 41% less wall-clock time than the strongest baseline by task performance. Across models and benchmarks, SCH consistently reduces token use relative to full-history prompting while remaining competitive with or improving upon the evaluated baselines. Trajectory analysis confirms that SCH recovers evidence from substantially earlier parts of the interaction history rather than merely preserving a recent context window.

cs.AI

新论文 · v1arXiv:2611.24353

When Figures Disagree with Text: Evaluating Autonomous Visual Evidence Verification in Scientific Papers

Guijia Zhang, Hongbo Qiu, Jiajun Zha, Guohao Cai, Hao Zheng, Huihao Jing, Kexu Cheng, Shipeng Luo 等 13 位作者

原文摘要

Scientific figures carry evidence for the claims that cite them, so reviewing a paper means checking that a figure agrees with the text, and not only describing what the figure shows. Benchmarks of figure-text verification typically hand the model the figure, the claim, or the knowledge that an inconsistency exists, which leaves untested whether a model can find the figure worth checking in a complete paper, relate a visual element to the claim it conflicts with, and recognize the conflict. We study this autonomous setting on 31 full manuscripts, each carrying a reviewer-documented figure-text inconsistency from PRISMM-Bench that is hidden from the model. Six multimodal models review each PDF under a neutral prompt, and we then add one input at a time to the same manuscripts. Of 1,445 open-ended reviews, 60.6% mention the flawed figure, yet a grading rubric accepts only 3.3% as diagnosing its contradiction; a blind audit finds the rubric lenient, so we read these as rubric-accepted rates and compare conditions rather than absolute values. In a separate controlled run, naming the figure, without stating that it is flawed, raises rubric-accepted diagnosis from 4.3% to 20.4%, while a consistency instruction and coarse visual cues do not. When the contradiction is visible only in the rendered figure, text-only review yields no accepted diagnosis, while review of the rendered pages with the figure named reaches 15.8%. A baseline that lets the model choose which figures to check, ranked by centrality, stays at 4.8%. Deciding what to verify is thus a large part of the difficulty, and the selection rule we tested does not resolve it. Multimodal document understanding should be evaluated on whether a model can propose what to verify, not only answer questions about a figure it is handed.

cs.AI

新论文 · v1arXiv:2611.24352

OCTR2A: Real-Time RGB-to-BEV Trajectory Projection and Forecasting at Urban Intersections

Emanuele Iacobelli, Simone Teglia, Francesco Pro, Claudia Melis Tonti, Irene Amerini

原文摘要

Trajectory forecasting at urban intersections is often studied assuming that reliable bird's-eye-view (BEV) motion histories are available, which in practice requires costly resources such as LiDAR, aerial views, HD maps, or calibrated infrastructure. We address this upstream perception-to-forecasting problem by reconstructing and predicting agents' BEV trajectories only from paired opposite-corner RGB cameras mounted on existing urban infrastructure at variable heights at inference time. We introduce the Opposite-Corner Trajectory Reconstruction and Anticipation Architecture (OCTR2A), a modular pipeline integrating per-view detection with class refinement, geometric cross-camera matching, transformer-based BEV projection, and egocentric GRU forecasting, trained in cascade and mainly supervised with a soft multi-scale spatial-overlap loss. Since no public benchmark provides this sensing configuration, we introduce R3ST++, a Blender-based synthetic benchmark built from SIND trajectories that provides synchronized opposite-corner views, cross-view correspondences, and BEV ground truth, while also serving as a deployment-support simulator for site-specific fine-tuning. Experiments on these datasets show that, with 12 observed and 12 predicted frames at 10\,Hz, OCTR2A achieves projection~-~forecasting ADE/FDE of 0.144/0.140~-~0.154/0.241~meters in real time on a single consumer GPU. Evaluated on ground-truth BEV histories, the forecasting module improves over the strongest state-of-the-art methods on SIND by 66.7\%/41.7\% ADE/FDE. Transfer experiments on TUMTraf-V2X show that R3ST++ pretraining supports adaptation to real-world roadside domains with different sensing configurations.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.24351

Tell Me How Sure You Are: Communicating Uncertainty in Auxiliary Evidence to Foundation Models

Soumyajit Chatterjee, Baturalp Buyukates, Abhirup Ghosh

原文摘要

In many queries, the context information provided to generative foundation models, such as LLMs and VLMs, is inherently uncertain, including its representations of the physical world. While conventional prompting discards the associated uncertainty, this paper, for the first time in the literature, systematically demonstrates that communicating such uncertainty in context provides useful additional cues for downstream decisions and yields improvements across a wide range of settings. We formulate the decision-making problem as a zero-shot foundation model-assisted image classification task supported by auxiliary text-based characteristics. We choose this due to the availability of well-defined auxiliary properties, associated uncertainty, and unambiguous task correctness. Using five downstream foundation models across three datasets, we extensively evaluate uncertainty arising from both humans and learned models when observing or predicting auxiliary evidence. Across all settings, we find that communicating uncertainty substantially improves downstream LLM classification performance: macro-F1 improves up to $26.18$ percentage points compared to when the uncertainty information is not communicated. We further observe how the foundation models process such uncertainty information and find that auxiliary uncertainty contains predictive information about the correctness of downstream decisions. Together, these results establish uncertainty as useful contextual information and motivate more systematic consideration of uncertainty communication in future foundation-model inference pipelines.

cs.LG

版本更新 · v2arXiv:2609.10193

Are You Learning Biological Signal or Shortcuts? Auditing and Mitigating Bias in Protein-Protein Interaction Datasets

Judith Bernett, Anton Spannagl, Joel Ås, Markus List, David B. Blumenthal

原文摘要

Protein-protein interaction (PPI) databases do not faithfully reflect biological realities. Instead, they are influenced by study and technical biases that distort certain protein and interaction attributes. Machine learning models can exploit these as learning shortcuts if the negative dataset is not constructed with care. So far, the shortcuts introduced during PPI dataset construction have only been examined in isolation. Here, we systematically characterize both reported and, to our knowledge, previously unreported biases in PPI datasets that lead machine learning models to learn shortcuts instead of biological signal. We analyze HIPPIE, IntAct, and STRING, dedicated PPI databases, as well as two datasets derived from 3D-structural information in the Protein Data Bank (PDB). We show that random data splitting introduces strong topological shortcuts. When train-test protein overlap is removed, the resulting datasets still retain usable shortcuts stemming from self-interactions, taxonomic identity, and functional relatedness, whose prevalence interestingly depends on the data source. We further show that sampling negatives from a set of highly replicated non-interactions, an intuitively appealing choice, can amplify the shortcut stemming from functional relatedness. To detect and mitigate these biases, we provide an open Nextflow pipeline that combines similarity-aware, data-loss-minimizing dataset splitting with bias-minimizing negative sampling, both formulated as integer linear programs. Its key concept of quantifying biases to minimize them through optimization-based negative sampling can, in principle, be extended to any machine learning problem where the pool of negative candidates is much larger than the positives and is thus of interest also beyond PPI prediction.

q-bio.MN · cs.LG

新论文 · v1arXiv:2611.24347

automodel: A Skill for Agentic Model Discovery

Marco Virgolin, Harry Desmond, Ester Bergantin, Giorgio Morales, John W. Sheppard, Luigi Romano, Alessandro Lucantonio

原文摘要

The search for better models, whether expressed as analytical equations or neural architectures, has increasingly shifted from manual design toward data-driven automation. While a multitude of algorithms exist, ranging from exhaustive search to AlphaEvolve, recent advances in general-purpose coding agents such as Claude Code and OpenAI Codex raise the question: could providing such systems with a "model discovery recipe" be enough to discover or improve models? We present automodel, an agent skill for general model discovery. With case studies in astrophysics, cardiovascular dynamics, precision agriculture, traffic flow, and vehicle tire dynamics, we show how commercial agents equipped with automodel can successfully identify novel and scientifically-relevant models. Our findings suggest that encoding model-discovery methodology as a portable agent skill can provide a simple, interactive, powerful and broadly applicable alternative to domain-specific automated discovery pipelines. The skill is available at: https://github.com/unlayer-ai/automodel.

cs.AI · astro-ph.CO · astro-ph.GA · cs.NE

版本更新 · v3arXiv:2607.13315

Meta-Learning Preferences for Multilingual LLM Alignment

Jiaying Lin, Seongho Son, Nam Phuong Tran, Long Tran-thanh, Ilija Bogunovic, Debmalya Mandal

原文摘要

Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and meta-policy optimization settings, and empirically demonstrate the effectiveness of our approach on multilingual benchmarks. In an extremely low-resource setting with only 100 target-language preference samples, our approach achieves up to $33.4\%$ win-rate improvements over baseline methods, and consistently outperforms baselines across multiple target languages and model scales. Our approaches retain these advantages across different combinations of meta-training languages and varying linguistic distances from the target languages.

cs.CL

版本更新 · v2arXiv:2610.19520

Spectral World Renderer: Unified 3D Hyperspectral Unmixing

Chia-Ming Lee, Yu-Jou Hsiao, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu

原文摘要

Hyperspectral images (HSI) preserve material evidence lost in RGB, yet 3D material identification from multi-view HSI faces two obstacles. Spectral Gaussian splatting reconstructs spectra accurately but leaves unmixing to per-pixel post-processing, while multi-view hyperspectral capture is costly and real datasets lack pixel-level material labels and sub-pixel proportions. We propose Spectral World Renderer (SWR), a material-aware explicit representation that unifies 3D spectral reconstruction and unmixing: it fits a Gaussian scaffold from RGB and decodes ray-Gaussian intersections into abundances over a shared endmember dictionary. Additionally, appearance guidance prevents spectrally similar materials from merging when intensity absorbs their brightness differences. Moreover, SWR requires no material-label supervision during training. To address the data gap, we further construct the SWR Benchmark (SWR-Bench): a coding-agent pipeline generates eight indoor and outdoor worlds from measured reflectance, aligning HSI with both annotations. SWR achieves the highest mIoU in all eight worlds and the highest mean PSNR on each real dataset. On an 11-class urban world, it trains at least 3.67x faster than unmixing baselines; rendering averages 34.9 joint spectral and label views/s over four worlds on a single RTX 4090.

cs.CV · cs.GR

新论文 · v1arXiv:2611.24342

Exploring Daily Emotional Well-Being through Personalized Data Analysis

Adriana Rodríguez Rodríguez

原文摘要

This project analysed daily emotional well-being from a personalized perspective using records of emotional states and contextual information derived from daily life. It was based on the idea that well-being is not a fixed value, but varies from day to day, and can be better understood in relation to individual context and behaviour. The work is framed within the field of Data Science and focuses on emotional states at an individual level. The project focused on constructing an integrated daily dataset from multiple personal data sources and analysing emotional states. The distributions of emotional variables, their temporal evolution and the differences between users were studied, together with their variability over time. Personality and well-being questionnaires were also incorporated as stable references to better contextualize daily emotional results. A simple personalized recommendation approach was then developed by comparing similar days within each user, exploring how past contextual conditions relate to differences in the user's emotional state. Finally, machine learning techniques were used to evaluate whether daily contextual information contains signals that help distinguish between different types of days relative to a person's usual well-being. The project adopted an applied approach, with an exploratory scope focused on understanding patterns rather than building a fully predictive system. The results showed that emotional well-being is very personal and changes from day to day. General models had limited value, while personalized approaches captured these differences much better, highlighting the importance of analysing each person on their own terms.

cs.HC · cs.LG

新论文 · v1arXiv:2611.24331

OpenGNS: An Open Dataset of the Gradient Noise Scale across Vision, Language, and Diffusion Models

Marcel Aach, Jiangtao Wang, Stefan Kesselheim, Andreas Lintermann

原文摘要

The Gradient Noise Scale (GNS) metric measures the signal-to-noise ratio of gradients in stochastic gradient descent and, as shown by McCandlish et al. (2018), can be used to approximate the Critical Batch Size (CBS) during neural network training. Despite its appearance in technical reports of frontier models, no open dataset of GNS measurements across modern architectures exists, limiting systematic study of the metric. We close this gap by releasing OpenGNS, a dataset of more than 400 GNS measurement trajectories spanning three domains: image classification with ResNets, autoregressive language modeling with Generative Pre-trained Transformers (GPTs), and image synthesis with Diffusion Transformers (DiTs), covering models from 11M to 1B parameters trained under Maximal Update Parameterization (muP) with dense batch-size and learning-rate sweeps. Building on this dataset, we study how the GNS depends on hyperparameters, scale, and training progress, and how it relates to the CBS. We find that the GNS behaves as a consistent "temperature of training", remaining stable across model sizes under muP at equivalent loss, and our results suggest task-dependent biases in its relation to the CBS: a tendency to overestimate the CBS for classification and to underestimate it for generative tasks, consistent in direction across common CBS definitions. The dataset is available at https://huggingface.co/datasets/olympique-marcel/OpenGNS

cs.LG · cs.DC

版本更新 · v3arXiv:2610.26924

DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution

Nan Jia, Wenxuan Shi, Jingqing Ruan, Zhizhao Zeng, Tianyi Zhai, Zhongda Su, Feng Hong, Zhengyu Chen 等 14 位作者

原文摘要

General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliable evidence. Training these capabilities requires diverse and challenging tasks. However, generating tasks directly from raw data often overlooks deeper questions that emerge through analysis and provides limited evidence for verification. To address these limitations, we introduce DataPraxis, an analytics task synthesis framework based on verified workspace evolution. The framework progressively enriches workspaces with validated findings and artifacts, then inherits and combines these workspaces to uncover deeper questions. It constructs tasks from accumulated findings and their dependencies, verifying analytical results both during evolution and after task assembly. Using this framework, we construct DataPraxis-5K, a dataset of 5,000 verified trajectories spanning diverse domains and output formats, to train DataPraxis-27B and DataPraxis-35B-A3B. DataPraxis-27B achieves 55.11 on DABStep and 51.9 on JobBench, matching or surpassing frontier models such as GLM-5.2. DataPraxis-5K is available at huggingface.co/datasets/stargazerhust/DataPraxis-5k

cs.AI

新论文 · v1arXiv:2611.24330

Can Weight-Space Programming Alter Learned Ethical Priorities?

Kai Yi Ji

原文摘要

We investigate whether a weight edit can alter how a model trades off honoring a commitment against benefiting more people. In a concept-supervised text model, we alter fitted choice weights so that the benefit required to override a formal pledge is larger than for an ordinary promise. Across six independently trained text readers, the edit selects the larger group in both orders on 100% of targeted ordinary conflicts and 83.3% of targeted formal conflicts. It preserves the source model's success rates on smaller conflicts and its factual accuracy. The remaining formal-conflict failures coincide with errors reading a beneficiary number. A separate classifier demonstrates why this distinction matters: reusing a factual answer passes an unconditional choice test but fails to preserve small-gap promises. In a YOLO11n pilot on COCO128, a bias edit increased small-target matches from 3/43 to 9/43, and an equivalent score calibration reproduced the retained detections. These exploratory results show a way to test selective changes to learned priorities in a model with an exposed trade-off mechanism. Whether the method can discover such changes in less structured language models remains open.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.24329

Distribution-Free Uncertainty Quantification for Weather Forecasting: Conformal Prediction Under Spatiotemporal Dependence

Mariya

原文摘要

Conformal prediction gives finite-sample, distribution-free marginal coverage and has begun to be applied to gridded weather forecasts. Marginal coverage concerns the long-run fraction of covered points at a location, not how coverage behaves jointly across space and time on a given day. I benchmark eight interval-construction procedures (Gaussian, pooled and per-cell split conformal, per-season, adaptive conformal inference and rolling windows) for gridded 2 m temperature forecasts at eight lead times from 6 hours to 10 days, using ERA5 at 5.625 degree resolution, a deliberately modest convolutional forecaster and ECMWF's operational HRES, with calibration in 2017-2018 and testing in 2019-2021. Alongside coverage, width and interval score, I report dependence diagnostics: a spatial overdispersion index, quantiles of daily spatial coverage and miss persistence relative to a shuffled-days null. Per-cell methods reach near-nominal marginal coverage, yet the day-to-day variance of the fraction of cells covered is roughly 3 to 10 times what independent cells would give, and misses cluster in time; both effects grow with lead time for the CNN, also appear for HRES, and are shared by all methods. An oracle that divides each day's normalised errors by that day's mean removes 81 to 92 percent of the excess dispersion for the CNN and 93 to 98 percent for HRES, so days of large errors across much of the grid account for most of it. A day-scale predicted from seasonal terms and already-verified errors lowers the overdispersion index without widening intervals but improves interval score by at most 0.6 percent; on HRES from 12 hours to 3 days it has the lowest overdispersion index while ACI or season-conditional calibration has the best interval score, so no method is best on both. The study covers one variable, one coarse grid, a reanalysis target and two forecasters.

cs.LG

版本更新 · v2arXiv:2606.10592

Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting

Xingyu Zhang, Jingyao Wang, Xin Yu, Zeen Song, Jianqi Zhang, Changwen Zheng, Wenwen Qiang

原文摘要

Time series forecasting often suffers from over-smoothing, especially when future dynamics are multi-modal. Forecasts may follow the coarse trend of the observed future, but fail to preserve sharp changes, oscillations, turning points, and regime transitions that define plausible dynamic evolution. In this work, we revisit over-smoothing from the perspective of latent dynamical mode compression: under partial observation and single-realization supervision, multiple plausible future modes can be weakened, merged, or averaged during forecasting. Based on this view, we propose Dirichlet-Guided Group Forecasting (DGF), a mode-preserving forecasting framework that explicitly models multiple mode-conditioned predictive distributions and uncertainty over their selection probabilities. DGF uses a Dirichlet-guided hierarchical sampling mechanism and reward-based optimization to encourage forecasts that are accurate, dynamically consistent, and mode-distinct. Extensive experiments on real-world forecasting benchmarks show that DGF reduces over-smoothing while improving forecasting accuracy, diversity, and dynamical consistency. Our code is publicly available at https://github.com/Zh-XY22/DGF

cs.LG

新论文 · v1arXiv:2611.24327

Pixel2Perspective: A Benchmark for Multi-Modal and Multi-View Generalization in Vision-Language Models

Aditya Gandhamal, Aniruddh Sikdar, Arya Kishor, Suresh Sundaram

原文摘要

Embodied AI systems, such as drones and autonomous vehicles, improve navigation by enhancing perception in environments containing unseen objects. While Visual Language Models (VLMs) offer strong image understanding, their real-world application is underexplored. For effective deployment, open-vocabulary semantic segmentation (OVSS) models, leveraging models like CLIP to assign pixel-level labels from text, must be robust to outdoor conditions, adverse weather, and varying viewpoints. Despite their potential, these models encounter significant challenges in cross-domain generalization, hindering their practical use in embodied AI applications. In this work, we present Pixel2Perspective, a benchmark for multi-angle object localization and open-vocabulary segmentation across both aerial and ground perspectives. This benchmark supports thorough evaluation across different viewpoints and sensor modalities. We assess foundational models like CLIP and advanced OVSS models using a curated dataset that spans varied outdoor conditions, sim-to-real scenarios, and multiple sensors, including infrared, to support the development of robust and generalizable perception systems. We also present a novel framework, Multi-Source RGB-IR Uncertainty Quantification (MSRIQ), which jointly models aleatoric and epistemic uncertainties across RGB and infrared imagery. This approach supports robust evaluation of open-vocabulary segmentation models across diverse environmental conditions. Our work sets a robustness-driven benchmark, providing key insights and laying the foundation for future research in open-world embodied AI perception. The benchmark and project page are available at https://aniruddhsikdar1.github.io/publications/pixel2perspective/

cs.CV

新论文 · v1arXiv:2611.24325

Structure-Preserving Neural Approximation of Convex, Semiconvex, and Quasiconvex Functions

Yeachan Park, Yeoneung Kim

原文摘要

Input convex neural networks provide a natural way to enforce convexity globally through architectural constraints. We study how this structure-preserving approximation framework extends to semiconvex, quasiconvex, and convex transformable functions. For $C^{1,1}$ convex functions on compact convex domains, we establish the sharp $W^{1,p}$ minimax rate $m^{-1/d}$ under max-affine approximation with $m$ affine pieces, and show that every max-affine function admits an exact bounded-width ICNN representation with complexity linear in $m$. The same $W^{1,p}$ approximation rate extends to semiconvex functions through quadratic lifting and to convex transformable functions through monotone composition. For general Lipschitz quasiconvex functions, we develop a quantitative finite-probe approximation theory based on monotone responses to affine projections and obtain a structure-preserving IqCNN with an $L^\infty$ approximation guarantee. We further show that these approximation results extend to ReLU-transferable smooth activations, including Softplus and ELU. Numerical experiments on PDE-based approximation problems compare the proposed architectures with parameter-matched MLPs and validation-tuned shape penalties, demonstrating global structural validity without penalty tuning while maintaining competitive approximation accuracy. Overall, the results identify recoverable convex latent structure as the key mechanism enabling gradient-level structure-preserving approximation beyond convexity.

cs.LG · math.OC

新论文 · v1arXiv:2611.24324

Reducing Inference Cost of Coding Agents with Timeout Cascades

Boxi Zhou, German Sviridov, Dmitrii Ustiugov, Haris Javaid

原文摘要

AI coding agents have become one of the most popular applications of large language models. Yet, agentic AI comes at the cost of a tremendous amount of GPU compute resources, which limits its profitability and its viability at scale. In this paper, we investigate whether smaller, cheaper models can cut this cost without sacrificing accuracy. We evaluate 36 popular large and small open-weight models released since 2024 on a software engineering benchmark, and find that recent small models are closing the accuracy gap compared to their large counterparts. We investigate the structure of this gap and find that the gap is highly concentrated around hard tasks that small language models fail to solve while achieving remarkably good accuracy for easy and medium complexity tasks. Following this observation, we show that by utilizing a hybrid inference strategy that tries a small model first and escalates to a large one only when needed, we can achieve up to 33% reduction in total GPU-hour costs and 16.4% on all tasks from SWE-bench Verified, without sacrificing accuracy. Strikingly, this simple cascade nearly matches an oracle-style task router, highlighting a practical path for deploying cost-aware coding agents in production without complex learned task routers and with minimal engineering complexity.

cs.AI · cs.SE

新论文 · v1arXiv:2611.24323

RespCCT and FreqCCT: Compact, Explainable and Cost-Aware Convolutional Transformers for Multi-Class Respiratory Disease Classification

Auntor Chakma, Mst. Farhana Akter, Abu Henaf Rashid Ahmad Mufti, Asmana Yasmin

原文摘要

Chest auscultation depends on the listener, and software that classifies lung sounds could give a second reading where trained listeners are scarce. The most accurate published classifiers fine-tune large pretrained networks, and their accuracy is rarely reported with running cost or paired statistics. This study makes three contributions. (i) It proposes RespCCT and FreqCCT, two compact convolutional transformers of 173,187 and 124,999 parameters that learn from random initialization on mel, constant-Q and cepstral images of 5 s frames from three public databases, ICBHI, KAUH and RD@TR, with 1,665 audio files in seven classes. (ii) It compares both models with five ImageNet-pretrained networks and larger distilled variants on one test set, using paired bootstrap intervals. (iii) It measures the cost of every pipeline stage on one CPU thread, tests whether attribution maps depend on the trained weights, and probes whether the learned features reveal the recording source. On the test fold, RespCCT reaches an accuracy of 98.13% and a macro F1 of 0.970, and FreqCCT reaches 97.58% and 0.951. Over five folds, RespCCT with three seeds reaches 97.65% and 0.959, and FreqCCT with one seed reaches 96.95% and 0.941. The two strongest pretrained networks reach a macro F1 of 0.984, whereas RespCCT needs 2.0 to 64.6 times less weight storage. Computing the three input images takes longer than running either model, and a linear probe identifies the source database with 0.958 accuracy. A team can weigh accuracy against storage and time before device testing.

cs.SD · cs.LG

新论文 · v1arXiv:2611.24321

Benchmarking LLM abilities on postdoc-level natural science problems

Alina Avanesyan, Alexey Boldyrev, Liqun Deng, Denis Derkach, Mary Godunova, Mikhail Hushchyn, Dmitry Ilvovsky, Irina Knyazeva 等 13 位作者

原文摘要

Scientific problems have no answer key, so evaluating an agent means deciding what counts as a better solution before any agent is run. Existing benchmarks either match a symbolic answer against a key or, where they require executable work, score it by unit tests, by a rubric, or by position on a competition leaderboard. None of these is the criterion by which a field decides that one published method beats another. STEMBench adopts that criterion directly. Each of its twelve research problems in high-energy physics, astrophysics and neuroscience is scored by its own field's figure of merit, and each comes with two measured anchors: a submission that uses no domain knowledge, and an expert reference reproducing a published method, both obtained by running code shipped with the benchmark. The interval between them states how much of a problem is crossed by scientific insight rather than by engineering. Across eight frontier models, task-level wins and domain-level leadership dissociate: a model that wins five of the twelve tasks leads no domain mean. In the high-effort cross-model comparison, at least one model's mean score exceeds the expert anchor on seven of twelve tasks. The remaining five span uncertainty estimation, latent and causal inference, and cross-site clinical classification. Numerical scores and official-submission validity capture different aspects of performance and are reported separately. We release the tasks, graders, anchors and harness.

cs.AI · physics.data-an

版本更新 · v2arXiv:2611.23048

Wall-to-wall maps of canopy height and aboveground carbon across the Atlantic Forest

Matheus Pinheiro Ferreira, Thiago Carmuega Rabaçal, Giulio Brossi Santoro, Giovanna de Andrade Ferreira, Rodrigo Costa Pinto, Danilo R. A. de Almeida, Paulo Guilherme Molin, Catherine Torres de Almeida 等 18 位作者

原文摘要

Global canopy height maps are increasingly used to estimate forest carbon, yet their regional accuracy is rarely tested. We present wall-to-wall maps of canopy height (10 m) and aboveground carbon density (30 m) for the Brazilian Atlantic Forest in 2024. Height was predicted by a deep learning network fusing Sentinel-2 reflectance, Sentinel-1 and ALOS PALSAR backscatter and ALOS elevation, trained on 7,179 and tested on 1,793 patches (58,800 km$^2$) from a statewide airborne LiDAR campaign over São Paulo state, Brazil. On held-out test patches, the mean absolute error is 2.26 m at 10 m and 1.90 m at 30 m, and the model was validated at two LiDAR sites outside São Paulo. Over the same pixels, the Meta and World Resources Institute global product has more than twice this error. A power law fitted to 124 inventory plots converted canopy height to above ground carbon density. The remaining forest holds 1,944 TgC over 28.3 Mha. Global products therefore need local validation before use in carbon accounting.

cs.CV

新论文 · v1arXiv:2611.24316

Fuse to Recognize the Unseen: Class-Relative Infrared-Visible Fusion for Open-Vocabulary Semantic Segmentation

Zehao Gao, Jie Feng, Wenda Zhao, Junpeng Zhang, Ronghua Shang, Weisheng Dong

原文摘要

Visible-infrared image fusion leverages complementary thermal cues to enhance visual perception, particularly under challenging illumination. However, such perceptual complementarity does not readily translate into semantic gains in open-vocabulary semantic segmentation (OVSS), where CLIP-based models are predominantly pretrained on RGB imagery. Directly introducing IR information may instead disrupt RGB-language alignment, turning promising thermal cues into semantic interference that undermines unseen-class recognition. Our pixel-level RGB-IR semantic analysis reveals that class-relevant thermal cues can correct certain RGB misclassifications while preserving reliable RGB predictions, motivating RGB-anchored, class-relative thermal cue selection. Based on this insight, we propose EmergeFuse, an infrared-visible fusion framework for OVSS that selectively converts complementary thermal evidence into unseen-class semantic corrections. Specifically, class-relative cue selection evaluates RGB-IR semantic responses and calibrated thermal evidence relative to RGB predictions, generating class-relative correction requests through competitive selection. Text-contrast image rectification then translates these selected requests into semantic rectification directions through text contrasts, guiding evidence-gated feature updates to realize complementary thermal evidence for unseen-class recognition. Experiments on three benchmarks demonstrate gains of up to 4.755% in unseen-class mIoU and 15.730% in strict complementary conversion rate over existing fusion methods, while maintaining competitive fusion quality.

cs.CV · cs.AI

新论文 · v1arXiv:2611.24314

Supervised Hebbian Class Networks: Learning Without Backpropagation

John Loverich

原文摘要

This paper introduces Supervised Hebbian Class Networks as a method for training multi- layer perceptrons and convolutional networks without gradient calculations or backpropa- gation. Each neuron in a learned layer is assigned a class, while connections follow the usual fully connected or convolutional pattern. The method combines a class-based supervision rule shared across layers with a Lion optimizer adapted to Hebbian activity products. All layers train together throughout the run, and their activities provide class predictions di- rectly, without a separately trained classifier. The experiments test the method on MNIST with a multilayer perceptron and on CIFAR-10 with a convolutional networ

cs.LG

版本更新 · v2arXiv:2601.07783

Affordable Data Collection System for UAVs Taxi Vibration Testing

Chaoyi Lin Yang, Gabriele Dessena, Oscar E. Bonilla-Manrique

原文摘要

Structural vibration testing plays a key role in aerospace engineering for evaluating dynamic behaviour, ensuring reliability and verifying structural integrity. These tests rely on accurate and robust data acquisition systems (DAQ) to capture high-quality acceleration data. However, commercial DAQs that provide the required performance and features are often expensive and complex, limiting their accessibility for small-scale research and experimental applications. This work presents the design and experimental validation of an affordable and in-house-developed acceleration DAQ, tested on a small fixed-wing UAV through several Taxi Vibration Test (TVT) runs and ambient vibration measurements. The proposed system integrates several OrangePi 3 LTS single-board computers with multiple LSM6DS3TR-C MEMS inertial measurement units operating simultaneously via an Inter-Integrated Circuit (I2C) communication interface, managed under a Python-based master/slave architecture. Data is acquired at a stable sampling rate of approximately 208 Hz and post-processed using Welch's method to estimate their Power Spectral Density (PSD). Results confirm the system ability to provide consistent multi-sensor acceleration data and repeatable PSD profiles under the same test conditions; thus, demonstrating its reliability. With a total hardware cost below 600 EUR (approximately 690 USD), the developed DAQ offers a compact, scalable and cost-effective alternative for aerospace vibration analysis and structural testing.

eess.SY · cs.RO · eess.SP

新论文 · v1arXiv:2611.24313

AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents

Stavros Damianakis, Konstantinos Psounis

原文摘要

Prompt injection is the dominant unsolved security risk for LLM agents, and the community now agrees that robustness must be measured against adaptive attackers rather than fixed benchmark injections. Many adaptive red teamers exist, and most are built to maximize attack success rate (ASR). Yet ASR counts how often a target breaks, not in how many different ways. A red teamer can achieve a high ASR by reusing a few techniques that work, leaving the others untested and absent from the attacks used to harden models. We present AutoPI, an adaptive red teamer designed to find many different ways to break a target, not just to break it often. AutoPI uses PIAtlas, a taxonomy of prompt-injection techniques, both to guide its search and to measure coverage. For each scenario, an attacker LLM writes an injection for every sub-technique in the taxonomy and then reworks the ones that fail using feedback from an LLM judge. The method is black-box and training-free, it plugs into existing benchmarks in place of their fixed attack templates, and it stays up to date as the taxonomy evolves. We evaluate AutoPI on AgentDojo and IPI Arena against open-weight and proprietary target models. Alongside ASR, we report technique coverage, the fraction of taxonomy classes, techniques, and sub-techniques that yield at least one successful injection. On AgentDojo, AutoPI finds a successful injection against Qwen3.6-35B in all six classes of the taxonomy and for more than 90% of its techniques. Against Claude Haiku 5.5, the most robust target we evaluate, it achieves between 20% and 50% higher ASR and between 25% and 400% higher class-level coverage than recent state-of-the-art adaptive red teamers, while requiring no training. We release our code and the generated attacks to support reproducible, coverage-aware evaluation.

cs.CR · cs.AI · cs.LG

版本更新 · v3arXiv:2608.06618

Beyond Co-Movement: Locality by Exposures Enables a Joint Factor-Graph Framework for Portfolio Diversification

Sara Chehab, Giorgos Iacovides, Parisa Yazdanparast, Danilo Mandic

原文摘要

Current portfolio construction methods are either agnostic to the effects of idiosyncratic shocks (standard factor models) or to the latent data structure driving systematic returns (recent graph-based approaches). This presents an opportunity to combine the complementary market aspects captured by the factor and graph domains, allowing asset allocations to operate directly on the underlying market structure, rather than on its observed co-movement or its finite-sample artefacts. In this work, we introduce the Mutually-INformed Graph-Locality and Exposures framework (MINGLE), which mutually regularises the factor and graph domains by redefining graph locality through systematic factor exposure profiles, rather than via observed co-movements. This is formalised through a unified Alternating Direction Method of Multipliers (ADMM) framework that jointly learns a latent factor representation and its induced graph topology directly from market returns. The resulting exposure-similarity graph aligns more closely with established economic sectors than conventional correlation-based graphs. Portfolios constructed from this representation are shown to consistently outperform their correlation-based counterparts across a range of volatility regimes and transaction cost levels. For rigour, paired statistical testing confirms that these gains stem from the reconciliation of the graph and factor domains.

q-fin.PM · cs.LG · q-fin.ST