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

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 19:45各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 21:22 — 2026-11-18 21:22(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:2026-11-18 04:28最近发现新增版本:2026-11-18 19:45库内论文最新更新时间:2026-11-18 08:00

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。

26,870 已收录论文22,374 AI 相关8,156 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 117 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.23196

Nonlinearity-preserving quantum simulation of flows in the early fault-tolerant regime

Hansol Noh, Unam Oh, Sangkyu Baek, Doyeol, Ahn

原文摘要

Ensemble prediction of nonlinear dynamics propagates a probability density whose linear transport equation retains the nonlinear drift, but grid-dependent circuit costs leave end-to-end feasibility in early fault-tolerant quantum computing unresolved. We couple polynomial reduced-order models fitted by sparse identification of nonlinear dynamics to Walsh-synthesized Koopman-von Neumann (KvN) transport and surface-code resource estimation. At fixed model dimension and drift degree, per-step transport rotation counts scale polylogarithmically with cells per reduced coordinate. Balancing model accuracy against circuit costs makes reduced-model polynomial degree a design variable for early fault-tolerant quantum simulation. For a cylinder wake approaching saturation, preparation, propagation and sampling to 1% relative root-mean-square field error against the radial model are estimated to take 1.62 h on about 560,000 physical qubits. Estimated three-coordinate wake runtimes span hours to weeks below one million qubits. IBM hardware experiments demonstrate nonlinear radial KvN transport for this wake, using reference circuits to mitigate noise.

quant-ph · cs.CE · nlin.CD

版本更新 · v2arXiv:2608.27521

Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics

Till Muser, Giovanni Abati, Ivan Dokmanić

原文摘要

Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a regular lat--lon grid causes problems: Cartesian convolutions become distorted at high latitude; 2D FFTs in Fourier neural operators incorrectly assume double periodicity; Cartesian positional encodings in ViTs distort spherical geodesic distances. Recent work moves towards natively spherical primitives, including spherical convolutions (e.g., DeepSphere or DISCO), Spherical Fourier Neural Operators (SFNOs), and geodesic attention. Here we propose Dandelion, a spherical version of Flower---a warp-based neural PDE solver. A Dandelion layer computes a tangent-plane displacement and then transports features along great circles. We obtain a U-Net-like structure by implementing hierarchical pooling entirely in the spherical-harmonic domain. There are thus no convolutions: spatial mixing is achieved only through spherical coordinate changes---or warps. To compare Dandelion with existing spherical architectures, we release an evolving benchmark suite of challenging, natively spherical PDE datasets including a modified Galewsky jet, anomalous chained turbulence, Cahn--Hilliard decomposition, spherical Riemann shocks, Held--Suarez dry atmospheric transport and global ocean dynamics. This new benchmark fills the gap between existing spherical datasets which are either too small and stylized, or much too large (ERA5) for model iteration. Dandelion achieves the best performance on all but one benchmark setting, where the best model is Flower2D, also based on warps. The spherical primitives result in the most physically consistent forecasts.

cs.LG

新论文 · v1arXiv:2611.22494

Fast and Strong Image Protection against Diffusion Personalization

Jiwon Park, Jihye Kang, Namhyuk Ahn

原文摘要

Personalized text-to-image diffusion models can reproduce a person from a handful of photographs. Image protection perturbs each image before publication so that fine-tuning on it fails, but it optimizes every perturbation from scratch, so its cost grows with the number of images. We present the protective diffusion model (PDM), which is trained once and samples the perturbation of a new image over many denoising steps. PDM distills an iterative teacher and is then post-trained with the target residual projection (TRP) loss as a reward, a stronger objective than existing ones. PDM outperforms nine baselines on faces and artworks and nearly matches its teacher at a tenth of the cost.

cs.CV · cs.CR

新论文 · v1arXiv:2611.22486

How Well Is My Artwork Protected? Predicting and Tailoring Protection against Style Mimicry by Personalization

Jihye Kang, Jiwon Park, Sungwoo Hwang, Namhyuk Ahn

原文摘要

Protection tools add an imperceptible perturbation to each artwork so that a model personalized on it fails to imitate its style, and they apply one recipe, a protection method at a fixed strength, to every artwork. We find that the same recipe protects artworks very differently, well beyond the noise of personalization seeds, and that cheap signals predict this protection before any personalization. Because protection rises and falls together across recipes, our method, Patina, predicts the protection of every recipe from one short trial protection and gives each artwork the weakest recipe whose predicted protection reaches a chosen level. At the same level of visibility, Patina lets more artworks pass the protection threshold than any single recipe and warns the artist about artworks for which no recipe is predicted to pass it.

cs.CR

新论文 · v1arXiv:2611.22450

MedImgAnnotator: batch wise medical image annotation and preprocessing tool

Ewunate Assaye Kassaw, Amit Mehndiratta, Peush Sahni, Anup Singh

原文摘要

The curation of large cohort datasets for developing deep learning models demands annotating or editing over the AI-predicted labels. However, openly available annotation tools are time-consuming, as they involve complex navigational steps and do not support batch processing. This study aimed to develop a simple, fast, semiautomated batch-annotation tool named MedImgAnnotator. The tool was created by integrating editing tools, image mask pair matching logic, preprocessing functions, object detection tool, and a plugin management system. Its performance was evaluated in terms of active annotation time and ease of use by the developer and 12 users using open-source MR and CT scans. Additionally, the tool had been used by the MICCAI 2026 CARE Challenge liver segmentation best performance winner to annotate liver masks from 6412 MRI volumes. The evaluation results showed that MedImgAnnotator reduced active annotation time from 206.5+/-32.87 (average active annotation time of openly available tools) seconds to 59 seconds. The Wilcoxon signed-rank test of 12 users evaluation results recorded P values of 0.032 and 0.008 for the active annotation time and higher ease of use rating metrics, respectively, indicating that the current tool significantly reduces annotation time and enhances ease of use. Moreover, the tool utilization for annotating different regions of interest from different modality scans and body regions shows its usability across modalities and areas of interest. MedImgAnnotator, which significantly reduces active annotation time for large imaging cohorts, is available as an executable file and as a Python script. Access link: https://ewunateassaye.github.io/developed-tools/medimgannotator.html

cs.CV · eess.IV

版本更新 · v3arXiv:2506.17247

Recursive Learning-Based Virtual Buffering for Analytical Global Placement

Andrew B. Kahng, Yiting Liu, Zhiang Wang

原文摘要

Due to the skewed scaling of interconnect versus cell delay in modern technology nodes, placement with buffer porosity (i.e., cell density) awareness is essential for timing closure in physical synthesis flows. However, existing approaches face two key challenges: (i) traditional van Ginneken-Lillis-style buffering approaches are computationally expensive during global placement; and (ii) machine learning-based approaches, such as BufFormer, lack a thorough consideration of Electrical Rule Check (ERC) violations and fail to "close the loop" back into the physical design flow. In this work, we propose MLBuf-RePlAce, the first open-source learning-driven virtual buffering-aware analytical global placement framework, built on top of the OpenROAD infrastructure. MLBuf-RePlAce adopts an efficient recursive learning-based generative buffering approach to predict buffer types and locations, addressing ERC violations during global placement. We compare MLBuf-RePlAce against the default virtual buffering-based timing-driven global placer in OpenROAD, using open-source testcases from the TILOS MacroPlacement and OpenROAD-flow-scripts repositories. Without degradation of post-route power, MLBuf-RePlAce achieves (maximum, average) improvements of (56%, 31%) in total negative slack (TNS) within the open-source OpenROAD flow. When evaluated by completion in a commercial flow, MLBuf-RePlAce achieves (maximum, average) improvements of (53%, 28%) in TNS with an average of 0.2% improvement in post-route power.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.05213

StyleComposer: Training-Free Multi-Reference Style Composition

Sanghyeok Lee, Jihye Kang, Namhyuk Ahn

原文摘要

The color, texture, and structure of an image can come from different references, but reference-guided generators transfer each reference as a single style signal. We find that in a diffusion transformer, every pathway that brings in a reference transfers multiple attributes, yet each attribute has one representation in which it is most directly controllable. Guided by this finding, we design StyleComposer to route color through the chromatic coordinates of the latent, texture through the attention keys and values, and structure through the queries, and to limit what else each route admits from its reference. Without training or inversion, StyleComposer follows the references and the prompt together more closely than stylization methods and multi-image generators, and it sets the strength of each attribute separately.

cs.CV

新论文 · v1arXiv:2611.22174

Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation

Daehee Lee, Dongsu Lee, Sanghyun Ahn, Minjong Yoo, Honguk Woo

原文摘要

General-purpose behavior models increasingly internalize broad procedural knowledge during training, making their adaptation to new goals and skill interfaces less a problem of learning entirely new behaviors than of reconfiguring existing competence. We study this capability as reconfigurability, the ability to realize new behaviors by cost-efficiently restructuring existing components and relations under sparse governing information, where task specifications provide high-level goals and procedure specifications expose a limited set of reusable factors, leaving the concrete bindings and compositions required for execution underdetermined. We propose RecPo, a framework that represents skills task-agnostically through multiple procedure views and materializes executable skill sequences by composing stored transitions to realize task-specific changes. RecPo maintains a procedure knowledge base of skill-induced transitions, with each view exposing a reusable factor and preserving local skill connectivity. At deployment, it interprets task specifications through the same views and resolves the resulting compositional queries over the stored relations to bind skills for execution. On long-horizon tasks in an extended Franka Kitchen benchmark, RecPo achieves 91.9% ordered completion with 1.0 ms of task inference per episode across varying procedure support and task-record sparsity. Real-robot studies further demonstrate adaptation through local memory edits without task-specific retraining.

cs.AI

新论文 · v1arXiv:2611.21857

tmol: a GPU-accelerated implementation of the Rosetta energy function for machine learning

Andrew Leaver-Fay, Kieran Didi, Jeff Flatten, Alex Ford, Guangfeng Zhou, Nathaniel Corley, Hahnbeom Park, Maxwell W. Kazman 等 15 位作者

原文摘要

Physics-inspired forcefields complement generative machine learning models, showing better generalization beyond the training distribution. However, these forcefields are typically slow to evaluate, and their derivatives are difficult to integrate into ML frameworks. We introduce tmol, a GPU-native PyTorch library implementing the state-of-the-art RosettaGenFF forcefield. tmol supports efficient batched differentiable scoring and whole-structure refinement with up to 362-fold throughput increase (batched). Used as a reward in generative protein design, tmol increases hydrogen bonds and water bridges at designed interfaces.

cs.LG

新论文 · v1arXiv:2611.21777

LLMs as Validators for Cross-Chain Bridges: Evaluating Source-Level and Transaction-Level Attack Detection on Solana

Yasir Rahman, Ishraq Samiha, Shahnewaz Karim Sakib, Anindya Bijoy Das

原文摘要

Cross-chain bridges have suffered substantial asset losses due to vulnerabilities in their on-chain programs. On Solana, missing validation checks can enable exploits even when the underlying blockchain operates correctly. The ability of large language models (LLMs) to diagnose these flaws from source code or transaction records, rather than merely raise alarms, remains insufficiently understood. We implement a native Rust lock-and-mint bridge on a local Solana validator with four exploitable variants: two model flaws from the Cashio and Wormhole incidents, while the other two represent vulnerability classes documented in Solana security audits. Paired vulnerable and secure programs, together with successful attacks, benign sessions, and blocked attempts, allow us to distinguish correct diagnoses from unsupported alarms. We evaluate six configurations of five open-weight models across 16,800 responses, compare source inputs with and without comments, and grade 7,200 answers on vulnerable inputs using two blinded LLM graders. The results reveal substantial differences across conditions: without comments, models diagnose 24% of vulnerable source inputs while frequently flagging the secure bridge. Transaction diagnosis is high for the missing-signer scenario but averages 6% across the other three scenarios. Original comments, some of which describe the flaw, increase source diagnosis to 60%. These findings highlight the importance of distinguishing correct vulnerability diagnoses from unsupported alarms in bridge security review.

cs.CR · cs.AI

版本更新 · v2arXiv:2604.11250

TEMPER: Reducing Attribute Leakage from Face Recognition Embeddings

Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee, Sébastien Marcel

原文摘要

Face recognition embeddings encode soft-biometric attributes such as gender and ethnicity, which can be inferred from templates. This paper proposes TEMPlate Entropy Regularisation (TEMPER), a post-hoc method that removes an attribute. TEMPER learns a linear map of the embedding in a split-latent variational autoencoder. The map is initialised at the principal component analysis (PCA) solution of the embeddings and trained to maximise the predictive entropy of an auxiliary attribute classifier. A relational term keeps the similarities of mated pairs close to the embedding similarities. We evaluate the removal of gender and a four-group ethnicity label from ArcFace embeddings against ten prior post-hoc methods and two label-free controls. Every method is trained on VGGFace2 and tested on IJB-C and RFW at false match rates down to $10^{-4}$. Leakage is the balanced accuracy of the strongest of four attacker families trained on transformed VGGFace2 templates. TEMPER retains the highest IJB-C true match rate at a false match rate of $10^{-3}$ at every leakage threshold for both attributes. TEMPER retains a true match rate of 82.4% at a gender leakage of at most 52.5%, close to chance, against 76.7% for the best prior method. In the ablation, this improvement comes from the PCA initialisation and the relational term.

cs.CV

版本更新 · v2arXiv:2609.10280

Total Simulated Survey Error: Designing and Diagnosing Survey Responses from Large Language Models

Indira Sen, Georg Ahnert, Leah von der Heyde, Jana Lasser, Bernd Weiß, Markus Strohmaier

原文摘要

Large Language models (LLMs), having been trained on vast amounts of human-generated data, may encode the opinions, attitudes, and behaviors of these humans. As such, LLMs show promise in mimicking human-like patterns that facilitate their use in simulating people in a wide variety of contexts. One such context is using LLMs as 'silicon samples', i.e., proxies of people in answering survey questions to establish public opinion, design policies, or use as (social) scientific data. However, several critical questions of social biases, generalization, and technical limitations remain, further complicated by a vast design space open to simulation designers. In addition, LLM-simulated surveys often lean on existing survey infrastructure, e.g., survey questions and samples. These artifacts might not be suitable for LLMs or themselves might have errors that are then inherited by the LLM-powered survey simulations. As a result, we lack a systematic understanding of the design space of LLM-generated surveys as well as how these decisions interplay with inherent LLM limitations. In this article, we aim to systematically identify, trace, and document limitations in LLM-generated survey responses. Building on traditions in the quantitative social sciences, specifically survey methodology and measurement theory, we investigate threats to the validity of LLM-generated survey responses. To do so, we design a framework that enumerates conceptual errors and systematic biases that can occur at different stages of the survey simulation lifecycle. Our framework - called the Total Simulated Survey Error (TS2E) Framework - provides a unified and end-to-end perspective on errors in LLM-generated survey data. We illustrate the framework through a theoretical and empirical case study, which enables survey simulation designers to systematically understand, identify and reflect on errors in LLM-generated surveys.

cs.CY

新论文 · v1arXiv:2611.20382

Signs of Wear: Evaluating Intelligent Speed Assistance Under Synthetic Adverse Conditions

Johannes Fabian Hahn, Mao Shan, Julie Stephany Berrio Pere

原文摘要

Intelligent Speed Assistance (ISA) systems rely on cameras to recognize speed-limit signs, yet existing benchmarks underrepresent the weathered, dirty, and overgrown signs commonly encountered on rural roads. We use generative image editing to introduce different forms of wear into real street-level images of speed-limit signs. The resulting ISA-Wear dataset contains paired original and edited images. Guided by text instructions, a multimodal image-editing model adds snow, rust, vegetation, faded paint, or mud to the speed-limit sign in a street-level frame at three severity levels. Where appropriate, the surrounding scene is adapted as well, and the viewpoint is kept. Every edited frame has an unedited counterpart, and we only evaluate frames whose original is recognized correctly, so any failure can be attributed to the wear. Since the model alters the sign's geometry in 21\% of the edits, all edits are filtered by a geometric check and a manual review. Severity is measured as the LPIPS distance between the original and the edited sign plate. On 716 worn frames, we find that in detect-then-read pipelines, wear breaks detection before it breaks reading. The detector finds only 62\% of the worn signs, even though it finds every one of them in the original frames. Missed detections account for 78--87\% of failed reads, a pattern that a zero-shot detector shares. Given the annotated sign box, as in the crop-based benchmarks, a classifier still reads 78\% of the worn signs, but only 56\% when it has to rely on the detector

cs.CV · eess.IV

版本更新 · v3arXiv:2509.17707

Automatic Intermodal Loading Unit Identification using Computer Vision: A Scoping Review

Emre Gülsoylu, Alhassan Abdelhalim, Derya Kara Boztas, Ole Grasse, Carlos Jahn, Simone Frintrop, Janick Edinger

原文摘要

Background: The standardisation of Intermodal Loading Units (ILUs), including containers, semi-trailers, and swap bodies, has transformed global trade, yet efficient and robust identification remains an operational bottleneck in ports and terminals. Objective: To map Computer Vision (CV) methods for ILU identification, clarify terminology, summarise the evolution of proposed approaches, and highlight research gaps, future directions and their potential effects on terminal operations. Methods: Following PRISMA-ScR, we searched Google Scholar, dblp and OpenAlex for English-language studies with quantitative results and charted the included studies across methods, datasets, failure modes, and evaluation metrics. Results: We reviewed 95 studies published between 1990 and 2026. A shift from static (e.g., OCR-gates) to vehicle-mounted camera setups is observed. Only 26 studies report an end-to-end accuracy (median 94.5%, range 19-100%). Eight datasets are publicly available, yet none is commonly used as a benchmark, and six studies describe a deployed system and seven a field test. Conclusions: We propose the term ILU identification for this broader task, which includes finding the unit and its code and covers semi-trailers and swap bodies. The literature still reflects its origin at the gate: challenges typical of moving cameras receive the least attention, and no study reports separate results for semi-trailers or swap bodies. Evaluation requires public benchmarks that cover these conditions and all ILU types, with end-to-end accuracy results. Promising directions are synthetic data, unified end-to-end models, recognisers built for codes without linguistic context, and mission planning with automatic coverage path planning for vehicle-mounted cameras. Addressing these challenges could reduce human errors, turnaround times and operational costs and increase resilience against disruptions.

cs.CV

版本更新 · v3arXiv:2607.25967

Quasi-SVD: Learning a Lie-constrained matrix factorisation for real-time imaging

Christopher Hahne

原文摘要

Singular Value Decomposition (SVD) underlies matrix factorisation tasks across many fields, with imaging applications demanding cost-efficient processing. Yet SVD algorithms are inherently sequential, constraining GPU throughput and limiting online deployment in imaging pipelines. This study introduces a fully parallelized matrix factorization framework for GPUs by enforcing matrix orthogonality on left singular vectors via Lie-parametrised algebra and recovering the remaining components through soft constraints. This asymmetric constraint design enables an efficient parallel decomposition with an orthogonal left factor, achieves high reconstruction fidelity and substantially accelerates computation relative to the exact SVD, with high throughput exceeding standard video frame rates. Performance is evaluated on multiple imaging tasks spanning complementary computational regimes: (1) an MNIST denoising benchmark at an intermediate scale with known ground truth, (2) Mueller matrix polarimetry for neurosurgical tissue characterisation, requiring massive batch processing of small matrices, and (3) spatio-temporal background subtraction for ultrasound localisation microscopy, requiring high-dimensional matrix separation. Across regimes and instruments, the proposed framework demonstrates robust domain transfer at various matrix scales and 2.6--67$\times$ speed-ups over the exact GPU SVD, and, unlike randomised SVD, accelerates large batches of small full-rank matrices. By prioritising downstream reconstruction fidelity over exact spectral recovery, the proposed SVD framework enables GPU-friendly matrix factorisation.

cs.CV · cs.LG · math.NA

版本更新 · v3arXiv:2609.38840

scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning

Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim 等 12 位作者

原文摘要

Single-cell RNA-seq representation learning is fundamentally label-free: cell identities, states, and contexts are not fixed training targets, so what constitutes signal or nuisance is analysis-dependent. A single representation must therefore preserve biological identity and state, remain robust to nuisance context, and retain the gene-level variation needed for expression analysis, three demands we call the representation trilemma. To tackle this problem, we introduce scTrilemma, a latent-bottleneck VAE that routes expression-derived variation to the embedding, the decoder, or the prior rather than forcing all of it through one embedding. It gates gene tokens by expression, routes the cell representation through the decoder, and conditions the prior on unlabeled pseudo-bulk context, under a single reconstruction objective and without target annotations or auxiliary representation losses. In release-based zero-shot evaluation on successive CZ CELLxGENE Census releases, scTrilemma leads all three demands at once and preserves biological-state, differential-expression, and pathway structure across multiple disease settings. Latent interventions further show that context can be removed at almost no cost to the other demands, leaving identity against fidelity as the remaining tension. Code is publicly available at https://github.com/yunhak0/scTrilemma.

cs.LG · cs.AI

新论文 · v1arXiv:2611.19810

Developing JEEVHITAA: Designing and Evaluating a Human-Centered AI Ecosystem for Collective Care

Shyama Sastha Krishnamoorthy Srinivasan, Harsh Pala, Shahnawaz, Mohan Kumar, Pushpendra Singh

原文摘要

Health management is often a collective activity, involving family members and close relations in monitoring, interpreting, and coordinating care. Yet, most digital health technologies remain individual-centric, offering limited support for the distributed responsibilities and negotiated information sharing that characterize collective care. We present JEEVHITAA, a human-centered AI ecosystem designed to address this gap. Drawing on existing literature on collective health practices, we identify key requirements and translate them into a canonical ontology and a versioned data schema that underpin a mobile ecosystem integrating wearable data, role-aware sharing, granular access controls, auditable histories, and AI-assisted health summarization and verification. We first evaluated core system primitives using 1,000 ontology-driven synthetic care circles to test data visibility and information-processing workflows. We then conducted a controlled lab study with 13 subject--care-actor dyads (26 participants), combining task-based interactions, semi-structured interviews, the System Usability Scale, and component-level usability assessments. Findings indicate positive perceptions of usability and highlight the value of granular sharing and transparent information provenance. They also expose tensions between reciprocal transparency and surveillance, and between AI-mediated assistance and potentially intrusive notifications. We discuss implications for designing accountable, context-sensitive technologies that support collective care.

cs.HC · cs.ET

新论文 · v1arXiv:2611.17720

Ego2Flow: Benchmarking the Traffic-System Impact of Autonomous Driving on Maps Distilled from Real-World Roads

Yu Dong, Weiying Shen, Hangyu Li, Shu Han, Hong Li, Xiangbo Gao, Keshu Wu, Zhengzhong Tu 等 11 位作者

原文摘要

End-to-end autonomous driving is predominantly evaluated through ego-vehicle safety and task completion. Its deployment in urban traffic, however, creates sustained interactions among vehicles whose collective effects remain insufficiently evaluated. We introduce Ego2Flow, a closed-loop benchmark for assessing the traffic-system impact of autonomous driving on maps distilled from real-world cities. To construct realistic 3D urban environments for sustained closed-loop traffic simulation, we develop an agent-guided map distillation framework that integrates real-world maps and observations with complementary geographic information. Through an iterative feedback mechanism and a traffic information graph that jointly guide scene generation, the framework preserves lane topology, critical road geometry and decision-relevant visual conditions while simplifying nonessential details and completing unobserved regions. Using our proposed framework, we generate and publicly release six CARLA maps from the Argoverse 2 dataset, covering the corresponding real-world regions and enabling paired comparisons of driving behavior under real and simulated observations. On these maps, Ego2Flow evaluates how autonomous driving policies affect traffic efficiency, safety, stability and energy consumption across diverse road structures. Compared with existing construction methods, our framework achieves the lowest average displacement error between planning outputs from paired real and simulated observations. We further benchmark representative driving policies to characterize their system-level impact on urban traffic. Project Page: https://github.com/Fisher-007/Ego2Flow.

cs.RO · cs.CV

新论文 · v1arXiv:2611.17686

What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning?

Kevin Krahn, Eric Fosler-Lussier

原文摘要

Self-supervised speech models (S3Ms) have been scaled up to thousands of languages and millions of hours of audio, yet little is known about how these models structure semantic knowledge across languages. In this work, we probe sentence-level semantics in massively multilingual S3Ms across 76 languages, using linear maps from frozen speech representations into a frozen text embedding space, evaluated by cross-modal retrieval. Sentence meaning is linearly accessible but highly uneven across languages and resource tiers. Cross-lingual probes can match language-specific probes on languages never seen in probe training, but per-model monolingual decodability does not predict transfer. Within the OmniASR wav2vec family, scaling from 300M--7B disproportionately benefits high-resource languages, and ASR tuning sharply improves semantic decodability while making representations more language-specific. However, semantic content is entangled with acoustics, inflating apparent performance on single-speaker corpora.

cs.CL

新论文 · v1arXiv:2611.16335

From More to Better: Causal Inference and Digital Experimentation in the Age of AI

Winston Chou, Mårten Schultzberg, Lo-Hua Yuan, Wenjing Zheng, Avi Feller, David Holtz, Widad Machmouchi, Sven Schmit 等 21 位作者

原文摘要

Artificial intelligence (AI) is quickly expanding the capacity of organizations to produce and analyze data. We argue that this expansion shifts the leverage of data scientists from performing individual analyses to assessing the credibility and importance of findings and determining when evidence generalizes across contexts. Drawing on a roundtable of academic researchers and industry practitioners, we examine three ways in which data scientists who work on causal inference and experimentation can help organizations turn more analytical capacity into better decisions: preserving and accumulating the learning value of experimentation beyond individual tests; choosing and combining experimental, observational, and synthetic evidence; and ensuring evaluation keeps pace with AI as its capabilities and uses evolve. In each area, we distinguish established practice from open questions. We conclude with implications for the training and practice of data science and for organizations.

cs.AI · stat.AP

版本更新 · v2arXiv:2609.24687

Discrete Isoperimetric Inequalities via Curvature

Zejia Chen, Zongchen Chen, Xinyuan Zhang

原文摘要

Isoperimetric inequalities on the Boolean hypercube play a fundamental role in the analysis of Boolean functions. These inequalities have been established primarily for the uniform measure and for biased product measures, often through Fourier-analytic or inductive arguments. We develop a curvature-based semigroup framework to establish isoperimetric inequalities for measures with weakly dependent coordinates. In particular, we show that a Dobrushin-type condition, together with marginal boundedness of the distribution, implies the local Bobkov inequality, Talagrand's $L^1$--$L^2$ and variance--surface-area inequalities, the Kahn--Kalai--Linial inequality, and the Eldan--Gross inequality. Our results apply to zero-field Ising models with interaction matrix $J$ throughout the Dobrushin uniqueness regime $\|J\|_1<1$. The framework builds on discrete Bakry--Émery theory and gradient estimates and can also be extended to measures on Hamming slices or hypergrids.

math.PR · cs.DM

新论文 · v1arXiv:2611.16293

Rasoi: Visual Diffs for Evaluating Structural Changes Made by Coding Agents

Riya Sahni, Aryan Kaul, Anushka Bhatnagar, Xuanming Zhang, Vivian Liu, Reya Vir, Lydia B. Chilton

原文摘要

Coding agents let developers modify software rapidly through natural language. However, as agents take on larger changes, developers can lose track of how the codebase is evolving. These edits may look correct on the surface while restructuring the system in unexpected ways: duplicating logic, changing modules outside the requested scope, removing functionality developers meant to keep, or introducing architectural drift. We investigate how visual diffs can help developers understand and evaluate the structural changes that coding agents make. We present Rasoi, a design probe that maps how a codebase's architecture evolves after each agent-made edit, letting developers inspect which architectural elements and relationships were added, modified, or removed across multiple levels of abstraction. We deployed Rasoi in a week-long study with 12 developers working on their own codebases across varied technical domains. We found that visual diffs helped developers see whether changes stayed within scope, notice unexpected restructuring, and understand how modified parts related to the system as a whole. Our findings suggest that the value of oversight tools for coding agents lies less in making developers trust the agent and more in helping developers feel confident in their own evaluation of agent-made changes. We discuss implications for visual tools that support code comprehension and human oversight in AI-assisted software development.

cs.SE · cs.HC

新论文 · v1arXiv:2611.16076

An EPTAS for Max-Cut on Interval Graphs

Hani Ahmadzadeh, Morteza Alimi

原文摘要

Max-Cut was shown NP-hard on interval graphs by Adhikary, Bose, Mukherjee, and Roy (SoCG 2021). The best previously known approximation ratio for this class, due to Ahn, DeHaan, Kim, and Lee (APPROX 2025), exceeded the Goemans--Williamson ratio of about $0.878$ by only $10^{-34}$. We give a deterministic efficient polynomial-time approximation scheme (EPTAS): for every $\varepsilon\in(0,1)$, a $(1-\varepsilon)$-approximate cut of an unweighted $n$-vertex interval graph can be found in time $2^{O(\varepsilon^{-2}\log^3(2/\varepsilon))}n^2$. The same guarantee and running time hold for Max-Bisection. An FPTAS is impossible unless $\mathrm{P}=\mathrm{NP}$. Our algorithm rests on a structural theorem: every interval graph with $m$ edges can be turned into an interval graph of clique-width $O(\varepsilon^{-2}\log^2(2/\varepsilon))$ by deleting at most $\varepsilon m$ edges. The construction combines endpoint-rank coordinates, length-dependent rounding, and a shifted dyadic hierarchy. Intervals intersecting cell boundaries at their own scales are isolated at small total edge cost; the interactions of remaining long intervals with smaller subproblems can be summarized by counts. The structural theorem also yields a randomized EPTAS via Lampis's scheme for bounded clique-width; our direct dynamic program is deterministic and handles Max-Bisection. Finally, for every $\varepsilon>0$, it is NP-hard to approximate Max-Cut within $84/85+\varepsilon$ on unweighted chordal graphs, which contain interval graphs. Thus an approximation scheme for Max-Cut on chordal graphs would imply $\mathrm{P}=\mathrm{NP}$.

cs.DS

版本更新 · v2arXiv:2611.05556

AGORA: Reliability-Aware Aggregation of LLM Judges on Small Evaluation Sets

Junhyung Ahn

原文摘要

LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer. In this regime the per-item mean weights weak judges as heavily as strong ones, and confusion-table models such as Dawid-Skene must estimate a per-judge error table from too few items. We propose AGORA (Aggregation Of Reliability-weighted Assessments), an item-response-theory aggregator that places every item on one latent quality scale and describes each judge by a sensitivity parameter and ordered rating thresholds, so judge reliability is learned from all items jointly and without human labels. Across three benchmarks, AGORA matches or exceeds Dawid-Skene on large evaluation sets, and its advantage widens as the set shrinks toward a few hundred items. It remains accurate as pools grow more uneven, a label-free dispersion statistic indicates in advance when trust weighting helps, and its learned trust weights track per-judge human validity. Code is available at https://github.com/JunhyungAhn/llm-as-judge-irt.

cs.AI · cs.CL

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

版本更新 · v5arXiv:2511.05963

Next-Latent Prediction Transformers Learn Compact World Models

Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward S. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam 等 10 位作者

原文摘要

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with consistent transition rules. This often leads to learning solutions that generalize poorly. We introduce Next-Latent Prediction (NextLat), which extends standard next-token training with self-supervised predictions in the latent space. Specifically, NextLat trains a transformer to learn latent representations that are predictive of its next latent state given the next token. Theoretically, we show that these latents converge towards belief states, compressed information about the history necessary to predict the future. This simple auxiliary objective injects a recurrent inductive bias into transformers while leaving their architecture, parallel training efficiency, and inference unchanged. NextLat effectively encourages transformers to form compact internal world models with coherent belief states and transition dynamics -- crucial properties not guaranteed by standard next-token prediction alone. Empirically, across benchmarks in world modeling, reasoning, planning, and language modeling, NextLat demonstrates significant gains over standard next-token prediction and other baselines in downstream accuracy, representation compression, and lookahead planning. Furthermore, NextLat enables variable-length self-speculative decoding, accelerating inference by up to 3.3x in language modeling. NextLat offers a simple yet effective paradigm for learning compact, predictive representations in transformers that generalize better. Our code is available at https://github.com/JaydenTeoh/NextLat.

cs.LG

新论文 · v1arXiv:2611.15046

Prototypes of the Mind: A Unified Framework for Probing the Visual Brain

Shi Chen, Seoyoung Ahn, Doris Tsao

原文摘要

Deep learning has driven substantial progress in modeling fMRI responses, yet most existing approaches are optimized for a single objective---such as neural encoding, stimulus decoding, or post hoc interpretation---making it difficult to obtain a coherent account of neural representations. We introduce a unified framework that connects vision foundation models to brain activity while supporting neural analysis from multiple complementary perspectives. Our approach replaces black-box features with a sparse, interpretable representation composed of visual prototypes, and links these prototypes to voxel responses through a linear readout. This design makes the model transparent at both levels: prototype activations expose the visual concepts present in the stimulus, while the learned linear weights characterize each voxel's selectivity. Using this interface, we identify which visual concepts drive neural responses and where they appear in the image, reveal cortical organization through voxel tuning in prototype space, and perform controlled stimulus synthesis to probe cortical selectivity through targeted interventions. Together, these results establish prototype-based representations as a unified and interpretable foundation for studying visual representations in the human brain.

q-bio.NC · cs.AI

版本更新 · v3arXiv:2610.29873

HAWK: Heterogeneity-Aware KV Cache Transfer for Efficient GPU-NPU Phase-Disaggregated LLM Inference

Junhyeok Park, Jungeun Yoon, Kyungmin Kim, Hunsoon Lee, Shinyoung Ahn, Kangho Kim

原文摘要

Large language model (LLM) inference exhibits distinct computational characteristics across its two phases: prefill is compute-intensive, whereas decode is more memory-bound. As a result, AI accelerators achieve varying levels of efficiency across the two phases. GPUs are well suited to prefill, but are often underutilized during decode. By contrast, NPUs can utilize their compute resources more effectively during decode. Motivated by this observation, we explore a heterogeneous architecture that integrates GPUs and NPUs, mapping prefill to GPUs and decode to NPUs to achieve high performance and efficiency. However, realizing such heterogeneous integration is challenging because LLM phase disaggregation requires KV cache transfer from prefill to decode (that is, from GPUs to NPUs), which is complicated by differences in inter-device communication mechanisms and KV cache tensor layouts. To address this, we propose HAWK, a transfer mechanism that enables rapid KV cache transfer across heterogeneous devices. HAWK establishes a remote direct memory access (RDMA) path for direct cross-device transfers while handling inter-device tensor layout discrepancies as part of the transfer process. In particular, HAWK allocates tensor-layout-aware RDMA buffers on the NPU side to match the target tensor layout. Leveraging these buffers, HAWK orchestrates data transfer from a conventional contiguous GPU RDMA buffer to the corresponding NPU buffers, allowing transferred tensors to be consumed directly without additional data rearrangement while maintaining transfer efficiency. We implement and evaluate HAWK on a system built with commercially available GPUs and NPUs, demonstrating performance within 7.88% of a GPU-only system under the same SLO constraints while achieving up to 1.26$\times$ higher power efficiency and 1.72$\times$ higher cost efficiency.

cs.AR · cs.DC

版本更新 · v2arXiv:2606.20467

智能体符号搜索:超越手工表达式、网格与神经网络的偏微分方程近似求解

Agentic Symbolic Search: Approximating Solutions of PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks

Zongmin Yu, Jun Zhai, Liu Yang

AI 速读 基于摘要

提出 Agentic Symbolic Search(ASYS),让编码智能体结合进化搜索与梯度拟合,从已知 PDE 和数学知识出发构造并改进显式符号近似。

cs.LG · math.NA · physics.comp-ph

查看原文摘要

Numerical methods and neural networks have transformed our understanding of nonlinear partial differential equations (PDEs), yet discovering mathematical representations that explain their dynamics remains largely an expert task. We introduce Agentic Symbolic Search (ASYS), in which coding agents construct and refine explicit approximations from a known PDE and supplied mathematical knowledge. ASYS couples evolutionary search over differentiable symbolic programs with gradient-based fitting, using the governing equation to evaluate candidates and guide their revision. For a singular generalized Constantin-Lax-Majda profile, ASYS infers a missing decay term that sets how fast the field approaches its singular-time limit, and builds a basis that fits the profile to a median error of $3.90\times10^{-5}\%$. For Fujita blow-up, separating diffusion from reaction and deriving a local response lowers the supplied formula's error from 55.5% to 0.0879%. For Allen-Cahn interfaces, a 14-parameter construction yields a mode-coupling law confirmed by independent simulations. These studies show how agentic search develops mathematical starting points into accurate, analyzable approximations.

版本更新 · v2arXiv:2508.08807

面向节点与超边的高效属性超图嵌入

Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges

Yiran Li, Gongyao Guo, Chen Feng, Jieming Shi

AI 速读 基于摘要

提出 SAHE,统一学习属性超图中节点与超边的嵌入,并通过高阶相似度与近似优化兼顾质量与效率。

cs.SI

查看原文摘要

An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes and hyperedges to compact vectors for use in important tasks such as node classification, hyperedge link prediction, and hyperedge classification. Generating high-quality embeddings is challenging due to the complexity of attributed hypergraphs and the need to embed both nodes and hyperedges, especially in large-scale data. Existing solutions often fall short by focusing only on nodes or lacking native support for attributed hypergraphs, leading to inferior quality, and struggle with scalability on large attributed hypergraphs. We propose SAHE, an efficient and effective approach that unifies node and hyperedge embeddings for AHNEE computation, advancing the state of the art via comprehensive embedding formulations and algorithmic designs. First, we introduce two higher-order similarity measures, HMS-N and HMS-E, to capture similarities between node pairs and hyperedge pairs, respectively. These measures consider multi-hop connections and global topology within an extended hypergraph that incorporates attribute-based hyperedges. SAHE formulates the AHNEE objective to jointly preserve all-pair HMS-N and HMS-N similarities. Direct optimization is computationally expensive, so we analyze and unify core approximations of all-pair HMS-N and HMS-N to solve them simultaneously. To enhance efficiency, we design several non-trivial optimizations that avoid iteratively materializing large dense matrices while maintaining high-quality results. Extensive experiments on diverse attributed hypergraphs and 3 downstream tasks, compared against 11 baselines, show that SAHE consistently outperforms existing methods in embedding quality and is up to orders of magnitude faster.