跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 00:56 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 01:12 — 2026-11-08 01:12（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 00:56最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 00:54（北京时间）
新论文 · v1arXiv:2611.05711

Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses

Zhengtao Gao, Francesco Bombassei De Bona, Leonardo Alchieri, Ivana Kiprijanovska, Simon Stankoski, Bojan Sofronievski, Hristijan Gjoreski, Marc Langheinrich 等 9 位作者

原文摘要

Facial Expression Recognition (FER) on optomyographic (OMG) smart glasses such as OCOsense enables privacy-preserving, camera-free affect sensing for health and well-being. Most FER systems are fully supervised, i.e., they rely either on hand-crafted expert features with classical machine learning, or on end-to-end deep models trained from labelled data. Both depend on large quantities of labelled expressions, which are costly to collect and limit deployment in real-world, personalized settings. We investigate Self-Supervised Learning (SSL) as a route to label-efficient FER on these glasses. We pretrain a Vision Transformer with a masked-autoencoder objective on unlabelled OCOsense recordings and finetune it for five-class FER under person-independent cross-validation. Across label budgets from 5% to 100%, pretraining consistently improves performance; with only 5% of the labels, the pretrained model outperforms the from-scratch model trained with all labels. Our results show that SSL pretraining is a practical way to reduce labelling cost for smart eyewear FER, and we discuss the implications for future personalization and continual adaptation.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05709

Agents, Think Only When it Helps

Min-Seon Kim, Seungdong Yoa, Sanghyu Yoon, Ye Seul Sim, Suhee Yoon, Dongmin Kim, Jung-Eun Kim

原文摘要

LLM agent distillation transfers agentic capabilities to student models by training on complete teacher trajectories that typically interleave thoughts and actions. We question how critical thought supervision is for agents' ultimate action performance. To answer this, we disentangle their impacts by independently perturbing teacher thoughts and actions during distillation. On widely adopted agent benchmarks across model scales, altering or discarding thoughts has little effect on student performance. We find, however, that thought supervision becomes important when information about the thought is not disclosed in the corresponding action during training. By identifying such discrepant cases, our findings challenge the common practice of distilling entire teacher trajectories for LLM agents, and offer a new insight that thought supervision can be a discernible choice for efficiency depending on whether the information of thought is disclosed in the action.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05706

Neural networks and games

Philip R. Neary

原文摘要

Hopfield neural networks and noncooperative games provide seemingly different approaches to understanding how collective outcomes emerge from local interactions. In a neural network, individual units adjust their states according to local signals; in a game, players choose actions to maximise individual payoffs. I establish an exact equivalence between symmetric binary Hopfield networks and binary-action games that admit a quadratic potential. The equivalence identifies stable network configurations with pure-strategy Nash equilibria, and asynchronous neural updating with best-response dynamics. More broadly, the storage and retrieval of memories in neural networks correspond, respectively, to the design and selection of equilibria in games.

cs.NE · cs.GT · cs.LG · econ.TH

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05705

Iterated Elimination of Dominated Mixed Strategies

Federico Echenique, Amanda Friedenberg

原文摘要

This note compares two iterated dominance procedures, one based on eliminating mixed strategies and one based on eliminating pure strategies. It shows that, in compact and continuous games, the mixed-strategy procedure can trail the pure-strategy procedure by at most one round: If the pure-strategy procedure terminates at round $M$, the mixed-strategy procedure terminates at either $M$ or $M+1$, and this bound is tight. It also provides two characterizations of the mixed-strategy procedure that are round-for-round equivalent to it and that require checking for improvements only against opponents' pure strategies.

econ.TH · cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05704

Memory-Access Profiling for Early Multicore Interference Awareness in Embedded Systems

Jean-Baptiste Lefoul, Ahmad Shahnejat Bushehri, Alaric Chan Lock, Felipe Gohring de Magalhaes, Gabriela Nicolescu

原文摘要

Applications executing on different multicore processors may interfere through shared resources. Such interference can introduce execution-time variability and complicate system integration, especially when applications that behave predictably in isolation are co-scheduled. This paper presents a profiling framework for early multicore interference awareness. The proposed approach captures source-level memory-operation traces from C applications with limited source-code modification and combines them with architectural parameters of the target platform. The framework maps memory accesses to cache sets and memory blocks, generates cache-occupancy profiles and heatmaps, and evaluates pairwise interference risks through a progressive three-stage analysis. First, a coarse-grained screening step classifies applications according to their non-stack memory-access behavior. Second, a static multicore cache-profiling step identifies cache sets whose combined footprint exceeds or approaches the hardware associativity. Third, a temporal footprint analysis tracks intervening unique blocks between consecutive accesses to the same memory block and computes Contention Potential Growth to identify execution windows vulnerable to cache eviction. The framework is evaluated using four benchmark pairings executed on a dual-core platform, with hardware performance counters measuring L2 cache misses used as validation references. The results show that the proposed analysis is consistent with the observed high- and low-risk cases and provides conservative warnings for near-capacity configurations. In particular, different applications pairs might produces up to 213.09% increase in L2 cache misses. These results demonstrate that memory-access profiling can provide practical and interpretable early indicators of cache-related multicore interference before exhaustive hardware testing.

cs.PF

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05703

From Type to Token: Petri Nets, Individual Token Philosophy, and Individualized Causal Effects

Fernando Delbianco, Fernando Tohmé, Gustavo Bodanza

原文摘要

Structural Causal Models and Bayesian Networks are the dominant framework for representing causal relations. They are fundamentally type-level formalisms since their estimands, Average Treatment Effects and Conditional Average Treatment Effects, are properties of distributions over populations, not of individual units. When treatment effects exhibit unbounded heterogeneity, these estimands collapse. What persists is the structural, token-level core of causation. We argue that Petri Nets under the Individual Token Philosophy are the natural representation of these token-level causal structures. We develop a formal translation from Bayesian Networks to Petri Nets, providing a two-layer account of individualized causality. The PN layer provides a structural representation of causal mechanisms that does not rest on distributional assumptions. In turn, a conformal prediction layer quantifies causal effects with finite-sample coverage guarantees. Together they constitute a complete account of individual causal effects.

cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.02325

Coalitions, Stability, and Majority Jackpots: Frameworks for Unifying Majoritarian and Proportional Allocation in Multiwinner Elections

Kit Scriven, Nitin Kohli

原文摘要

Social choice literature on multiwinner elections tends to focus on characterizing two distinct tasks: majoritarian representation and proportional representation. However, many real world systems can be viewed as operating between these two extremes, such as majority jackpot systems used in several countries throughout history. Towards the goal of better understanding these systems from a social choice perspective, we introduce two frameworks that encompass existing desiderata for majoritarian and proportional settings: coalitions, which encompasses properties such as fixed majority and solid coalitions; and stability, which encompasses various generalizations of Condorcet's criterion for single-winner elections, such as Gehrlein stability and local stability, among others. We develop theory and tools that characterize the mathematical and computational aspects of both frameworks across a wide array of preference structures (such as the unrestricted domain over candidates and the restricted domain of party lists). Building on this foundation, we shed new light on majority jackpot electoral systems, which to date have received limited mathematical analysis in the social choice literature.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05702

TACT: A Pragmatic Approach to Qualitative Analysis with an AI Council

Rudrajit Choudhuri, Christian Bird, Carmen Badea, Anita Sarma

原文摘要

Qualitative data can tell software teams what their stakeholders need, yet rigorously analyzing thousands of qualitative responses takes expert time that few teams can afford or justify. Teams therefore often face a false choice: leave the responses unanalyzed, or hand them to a large language model and accept its interpretation and judgment. In this paper, we take a pragmatic approach to AI-assisted qualitative analysis and present TACT (Traceable AI Council for Thematic analysis), a procedure that enables such analysis at scale while keeping teams in control of interpretation and judgment. TACT comes in two variants: TACT-Lite, the core AI council procedure, and TACT-Full, which adds adversaries (models from other model families that critique each model's output) and a decision model that surfaces high-uncertainty code assignments. We evaluated TACT on an independent dataset of 256 Stack Overflow threads qualitatively coded by other researchers. Against their labels, TACT's candidate codebook achieved an F1 of 0.75-0.77 and its final coding an F1 of 0.71-0.72. On a held-out sample, agreement between our own manual coding and TACT's coding was Cohen's $κ$ of 0.79-0.85. TACT is also economical: model calls cost \$13.77 (TACT-Lite) to \$33.59 (TACT-Full) per 100 threads. Finally, drawing on our experience building and validating TACT, we identify pitfalls in AI-assisted qualitative analysis, describe safeguards to address them, and offer guidance for teams and researchers applying TACT in practice.

cs.SE · cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05697

GeoDIVE: Geospatial Descent Informed by Value Estimation

Hamza Iqbal, Dan Cher, Eric Xing, Pranavi Kolouju, Abby Stylianou, Robert Pless, Nathan Jacobs

原文摘要

Finding specific objects, structures, and spatial patterns supports critical work in agriculture, infrastructure planning, environmental monitoring, and disaster response. These features, however, are often dispersed across very large regions and span dramatically different spatial scales, which defines a search space that is costly to embed, maintain, and search naively. We introduce GeoDIVE, a model that treats a multiresolution satellite image gallery as a forest and uses best-first traversal to determine which tiles to encode. At each visited node, a lightweight model then predicts an optimistic estimate of the best query similarity hidden among its descendants using the query and subtree representations. In evaluations with image and open-vocabulary text queries, GeoDIVE matches exhaustive search at 10% of the encoding cost for image queries and leads all tested baselines at every budget in both modalities. To support future evaluation of multiscale geospatial search, we also release object-level image and text queries for Git-10M, constructed from Microsoft building footprints and OpenStreetMap polygons with VLM-generated captions. Source code and models will be made publicly available.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.35316

Reliability Engineering for AI Systems: Challenges, Methods, and Directions

Rong Pan, Yili Hong, Min Xie

原文摘要

AI reliability concerns whether an AI system performs its intended function dependably over a stated period and under stated operating conditions, with clear evidence. As these systems become more autonomous, this function should include more than only a correct output. Retrieval, memory, tool use, permissions, human oversight, and interactions among systems must operate consistently and safely, and, for a generative AI, so must the reasoning process that produces the output. Average benchmark accuracy only measures system capability; it does not quantify this broader reliability claim. This paper adapts established reliability engineering methods, from failure definitions and operational envelopes to FMEA, accelerated testing, field monitoring, and reliability growth, to AI systems. A four-level diagnostic framework classifies failures as component, operational-loop, agentic-conduct, or network and governance failures. Test, evaluation, verification, and validation (TEVV), sequential monitoring, and FRACAS create and refresh evidence. The SMART framework provides statistical guidance for measurement, analysis, assessment, and test planning, and the NIST's AI risk management framework provides organizational guidance for governance, evaluation, monitoring, and mitigation. Three cases are discussed to illustrate these programs. It is shown that while the established reliability engineering principles can still provide a usable foundation, new measurements and safety guardrails are urgently needed as these systems are self-evolving at a fast pace.

cs.AI · stat.AP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.04273

Scalable Neural Video Representation Compression

Tianhao Peng, Ho Man Kwan, Fan Zhang, Shan Liu, David Bull

原文摘要

Scalable video coding (SVC) encodes a video into a layered bitstream of a base layer and one or more enhancement layers, enabling decoding at different bitrate/quality/resolution operating points for diverse devices and network conditions. SVC has been incorporated into major video coding standards and has recently attracted growing interest for both scene-agnostic and scene-adaptive neural video codecs. Among the latter, implicit neural representation (INR) based codecs overfit a compact neural network to an individual video, offering fast decoding and competitive coding efficiency. However, research on scalable INR-based compression remains in its infancy: existing methods introduce additional network layers, which couple the bitrate with the decoding complexity and cannot match strong scalable/non-scalable codecs. This paper proposes S-NVRC, a scalable INR-based video codec that jointly supports fine-grained bitrate and decoding complexity scalability from a single embedded bitstream. It adopts a coarse-to-fine prefix for feature grids and a nested prefix for network layers, which scale bitrate and decoding complexity, respectively. With a single encoding, S-NVRC spans a wide range of bitrate and decoding complexity and outperforms SHM-12.4 and the multi-layer VTM-20.0 by 43.7% and 5.6% in BD-rate on the UVG dataset.

eess.IV · cs.CV · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05695

Demystifying Information Flow Downgrading using the Real--Ideal Paradigm

Suraaj Kanniwadi, Andrew C. Myers

原文摘要

The real--ideal paradigm, an approach to security specification developed in the cryptography community, has the benefit that it can express sophisticated confidentiality and integrity requirements, even for decentralized systems. We show that this paradigm is the basis for a powerful and intuitive new semantic framework for language-based security. Our new framework cleanly and extensionally captures existing security definitions, including not only noninterference but also less understood information flow properties that involve downgrading, such as robust declassification and nonmalleable information flow. Past semantics for these properties have relied on intensional downgrading events. Further, we show that all of these properties can be enforced by a practical information-flow type system for a while-language that supports downgrading. Surprisingly, correctness of this type system is also characterized as a real--ideal simulation, with an important implication: the security of heterogeneous, decentralized systems with a strong (real) attacker can be understood by reasoning about a weak (ideal) attacker whose power is restricted to interaction with downgrading. This result explains the usefulness of nonmalleable information flow and related security properties. The results are fully formalized using the Rocq prover and are publicly available.

cs.PL · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.05152

Polynomial and Pseudopolynomial Algorithms for Two Classes of Bin Packing Instances

Renan Fernando Franco da Silva, Vinícius Loti de Lima, Rafael C. S. Schouery, Jean-François Côté, Manuel Iori

原文摘要

The Bin Packing Problem (BPP) and Cutting Stock Problem (CSP) are classical combinatorial optimization problems extensively studied since the 1960s. State-of-the-art exact algorithms are based on set-cover and arc-flow models whose linear relaxation, rounded up, matches the integer optimum for most benchmark instances, a condition known as the Integer Round-up Property (IRUP). In 2016, Delorme et al. showed that most existing instances could be solved within ten minutes by approaches exploiting this property. This motivated them to introduce two new classes of instances, Augmented IRUP (AI) and Augmented Non-IRUP (ANI), designed to challenge the exact algorithms available at the time. Although these classes have motivated significant advances over the past decade, 13 out of 500 AI and ANI instances remain unsolved within standard time limits in the literature. In this paper, we show that while AI and ANI are particularly hard for mixed-integer programming methods, the BPP restricted to these classes is not strongly NP-hard. We present polynomial-time algorithms for the AI class and pseudopolynomial-time algorithms for the ANI class, which solve all such instances orders of magnitude faster than previous approaches. They are also straightforward to adapt to the Skiving Stock Problem, the dual counterpart of the CSP. In addition, they can be used as preprocessing routines in exact methods, as their runtime is independent of the instance class, although they are guaranteed to return an optimality status only for instances belonging to the class for which they were designed.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00290

Quantifying Local and Global Fidelity of Nonlinear Embeddings

Henry Han

原文摘要

Dimension reduction rests on a claim: t-SNE and UMAP preserve local structure, PCA global structure. Our DLP curve is the share of each point's k nearest neighbors a map keeps. Corrected for chance, it gives L at k=10 and G over 30 to 50% of the data, local and global fidelity. At the midpoint the curve is provably a rank correlation of distances. The LG reversal test decides, with a stated error rate, which of two maps is local and which global. On twelve datasets of up to 1.38 million points, G agrees with established global scores at 0.84 and 0.93, and the area under R_NX at 0.22 and 0.30. The entity fidelity E, read at each point's entity size, predicts which entities a map loses beyond L and G where entity sizes differ. In an agent memory of one million passages, t-SNE and PCA cross at 150,000 passages (p=2.6e-5).

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05693

Anchored Slice Propagation with Boundary Transport for 3D CT Segmentation from Three Orthogonal Annotated Slices

Tushar Kataria, Md Rakibul Haque, Shireen Y. Elhabian

原文摘要

Sli2Vol propagates a binary mask through affinities between adjacent slices, but an error can persist because each prediction becomes the input to the next step. Three orthogonal annotations reduce dependence on any one chain, yet they offer more than three starting masks: where a chain crosses another annotated plane, the correct label is already known. Those labels could correct drift during propagation and indicate how much to trust each chain at fusion. Between annotated planes, the information carried by the chain may matter as well. A binary mask records foreground membership but discards distance to the boundary, a cue that could help follow gradual shape changes between slices.We address these two sources of error with a fixed pretrained affinity backbone. We anchor each chain by correcting its prediction where it crosses another annotated plane, then use its agreement with those labels to weight fusion. We compare this anchored mask with two ways of transporting boundary geometry: a truncated signed-distance field (SDF) propagated by dense affinity averaging, and a contour whose vertices follow motion cues from the same affinity. The contour tracker starts from a hand-crafted rule and learns a motion correction from supervoxel pseudo-objects in 506 CT volumes, without manual organ labels. On 2,091 held-out structure instances from approximately 403 CT scans spanning 17 abdominal structures, anchoring raises mean Dice from 0.737 with orthogonal mask propagation to 0.769 and improves every structure. Beyond the anchored mask, learned contour tracking improves Dice by 5.7\% for the esophagus and 5.9\% for the postcava, while SDF transport improves right-adrenal Dice by 2.8\%. The anchored methods have similar mean Dice (0.769--0.772); contour tracking performs worse on the kidneys, stomach, and hepatic vessel tree.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05690

Turbocharging PiPNN for Proximity and $k$-NN Graph Building

Tobias Rubel, Richard Wen, Guy Blelloch, Laxman Dhulipala, Lars Gottesbüren, Jakub Łącki, Vahab Mirrokni

原文摘要

Graph-based Approximate Nearest Neighbor Search (ANNS) indexes such as HNSW and Vamana deliver state-of-the-art query performance at the cost of large indexing times. The recently introduced PiPNN method drastically accelerated index construction by way of a partitioning-based algorithm leveraging dense matrix multiplication and top-$K$ aggregation kernels. In this paper, we unlock the full potential of PiPNN's hardware-friendly algorithm design. We introduce PiPNN II, which optimizes multiple steps of the PiPNN recipe, giving up to $8\times$ speedups for graph-based ANNS index construction. In addition, we present GPiPNN, a GPU implementation which builds comparable ANNS indices up to $43.7\times$ faster than Jasper and up to $50\times$ faster than CAGRA. We also extend PiPNN II and GPiPNN to compute high-quality $k$-NN graphs directly, which unlocks massive speedups over methods used in many existing systems for clustering, anomaly detection, and more. For 10-NN graph building at $90\%$ recall, we obtain up to a $13\times$ speedup on CPUs and $6.6\times$ on GPUs as compared to the prior best methods. PiPNN II can build a billion-scale 10-NN graph in under 16 minutes. Common to both PiPNN II and GPiPNN is the use of quantization to reduce memory traffic and leverage fast low-precision matrix operations. Top-$K$ emerges as a new bottleneck, which we optimize with specialized code for specific $K$, and by fusing with the matrix kernel to avoid materializing the distance matrix to memory. On CPUs, we demonstrate further performance improvements by leveraging our matrix kernels in the RobustPrune procedure proposed in Vamana and used in PiPNN. On GPUs, we flatten recursive partitioning into segmented batches, use one fused top-$K$ abstraction for partitioning and leaf scoring, and prune with already-witnessed direct edges rather than new candidate-to-candidate scoring passes.

cs.DB · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05689

TRUST-Stereo: Teacher-Assisted Robust Uncertainty-Guided Search and Transfer for Fast Stereo Matching

Pouya Sohrabipour, Yihong Feng, Chaitanya Kumar Reddy Pallerla, Tuan Dang, Ngan Le, Dongyi Wang

原文摘要

Coarse-to-fine stereo matching enables efficient disparity estimation but remains sensitive to errors in propagated disparity, which may place ground-truth correspondences outside subsequent local search ranges. We propose TRUST-Stereo (Teacher-Assisted Robust Uncertainty-Guided Search and Transfer for Fast Stereo Matching), which addresses this limitation through an Uncertainty-Guided Residual Search Module (UGRSM). UGRSM estimates the reliability of propagated disparity and predicts residual offsets to adaptively relocate local cost-volume centers. Additionally, we introduce a two-stage Senior-Junior Teacher Assistant knowledge distillation strategy to transfer rich monocular representations from a large foundation model to a lightweight backbone to achieve fast stereo matching performance. Experiments on KITTI 2012, KITTI 2015, ETH3D, and Middlebury demonstrate strong zero-shot generalization. Using only 1.4M synthetic stereo pairs, TRUST-Stereo achieves state-of-the-art results on several benchmark metrics, outperforming competing efficient methods trained with substantially larger datasets, including real-world pseudo-labeled samples. Specifically, it achieves a KITTI 2015 EPE of 0.93, ETH3D Bad 1.0 of 2.13% and Middlebury Bad 2.0 of 6.79% while maintaining inference at approximately 50 ms per stereo pair.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.12702

Product Monte Carlo: Expectation Under a Product of Densities

Pietro Carlotti, Sifan Liu, Yuling Yao

原文摘要

Aggregating independently computed sub-sample inferences is a well-known challenge in large-scale Bayesian computation, federated learning, and opinion pooling. The core problem is to approximate a distribution whose density is proportional to a product of individual densities. We propose Product Monte Carlo (PMC), an algorithm for computing arbitrary expectations under a product of densities using only Monte Carlo draws from individual densities. We turn the intractable product expectation into a regression problem by expressing it through a family of computable conditional expectations. Besides the point estimate, our fully Bayesian regression formulation provides coherent uncertainty quantification and principled diagnostics. We establish theoretical guarantees on consistency and characterize convergence rates for the PMC estimator. Across simulated and real-data experiments varying the number, dimensionality, and heterogeneity of the component distributions, PMC achieves higher estimation accuracy, better-calibrated uncertainty coverage, and improved scalability at a lower computational cost than existing methods. In addition, PMC requires no density evaluation, making it applicable to simulation-based inference, as we demonstrate in an application with protein images.

stat.ME · cs.LG · stat.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.28315

Pairwise Reflection Symmetry in Frequency Rectangles

Enrico Iurlano, Günther R. Raidl

原文摘要

Many combinatorial designs ask for equal distribution of given symbols across the entries of a matrix. The paramount examples are Latin squares, where each symbol from $\{1,\dots,n\}$ appears once per row and column of an $n\times n$ matrix. Frequency rectangles extend this to $λn \times μn$ matrices with repeated symbols under controlled column and row frequencies. In this more general setting, we examine structural properties of pairwise reflection-symmetry, which requires that, on every pair of columns, each ordered symbol pair $(p,q)$ occurs as often as its reversal $(q,p)$. This order-balance is precisely what makes head-to-head comparisons unbiased, i.e., no symbol gains a systematic advantage from the position it occupies relative to another, a fairness demand arising for instance when scheduling tournaments or laying out comparative trials. Existence of such objects for odd $λ$ turns out to be remarkably more subtle than for even $λ$. After showing that existence holds also for sufficiently large odd $λ$, we initiate the search for the smallest possible value of $λ$ in this setting. We obtain the insight that a per-column multiplicity of $λ=1$ can be achieved if and only if $n$ is a power of two. We complement the existence results with a direct product construction and add several further observations on the property. Finally, we propose and evaluate a quadratically constrained integer program to computationally search for these objects. The resulting experiments reveal that many of them possess an underlying group-theoretic structure which, as we conjecture, may even be unavoidable in certain settings.

cs.DM · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.14381

NodeSyn: Socially Aligned Synthetic Data for AI Evaluation

Qazi Mamunur Rashid, Xuan Yang, Zhengzhe Yang, Yanzhou Pan, Erin van Liemt, Darlene Neal, Kshitij Pancholi

原文摘要

Recent advancements in generative AI facilitate large-scale synthetic data genera- tion for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSyn, an evidence-grounded methodology that generates socially relevant syn- thetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs, NodeSyn elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.09788

POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction

Brandon Smock, Libin Liang, Maxim Sokolov, Amrit Ramesh, Valerie Faucon-Morin, Tayyibah Khanam, Maury Courtland

原文摘要

Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving $\textrm{GriTS}_\textrm{Con}$ of 0.964 while running over 130$\times$ faster at 300$\times$ lower cost. Further, POTATR's output is spatially grounded: every recognized element has a bounding box, enabling visual verification and geometric text assignment. As a result, POTATR performs unified page-level TE while composing with other models, enabling extension to scanned documents via external OCR and to full-document TE via techniques like cross-page merging. Code and models are available at https://github.com/kensho-technologies/POTATR.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.14191

Attention to Mamba: A Recipe for Cross-Architecture Distillation

Abhinav Moudgil, Ningyuan Huang, Eeshan Gunesh Dhekane, Pau Rodríguez, Luca Zappella, Federico Danieli

原文摘要

State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand, the community has built up a considerable body of knowledge on how to train Transformers, and many pretrained Transformer models are readily available. To facilitate the adoption of SSMs while leveraging existing pretrained Transformers, we aim to identify an effective recipe to distill an Attention-based model into a Mamba-like architecture. In prior work on cross-architecture distillation, however, it has been shown that a naïve distillation procedure from Transformers to Mamba fails to preserve the original teacher performance, a limitation often overcome with hybrid solutions combining Attention and SSM blocks. The key argument from our work is that, by equipping Mamba with a principled initialization, we can recover an overall better recipe for cross-architectural distillation. To this end, we propose a principled two-stage approach: first, we distill knowledge from a traditional Transformer into a linearized version of Attention, using an adaptation of the kernel trick. Then, we distill the linearized version into an adapted Mamba model that does not use any Attention block. Overall, the distilled Mamba model retains most of the original Pythia-1B Transformer performance, reaching a perplexity of 14.01 close to the teacher's 13.86. This largely carries over to downstream tasks, although some gaps appear on tasks relying more on in-context recall. To show the efficacy of our recipe, we conduct thorough ablations at 1B scale with 10B tokens varying sequence mixer architecture, scaling analysis on model sizes and total distillation tokens, and a sensitivity analysis on tokens allocation between stages.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.26421

Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting

Cristiana Diaconu, Jonas Scholz, Aliaksandra Shysheya, Stratis Markou, Payel Mukhopadhyay, Miles Cranmer, Richard E. Turner

原文摘要

State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restricts usage for under-resourced groups and severely limits fast model iteration. Here we develop Otter Weather, a highly efficient spatiotemporal forecasting model designed to democratise high-performance weather prediction with AI. Evaluated on ERA5 reanalysis data at 1.5° resolution using standard WeatherBench protocols, the Otter family significantly advances the skill-compute Pareto frontier. The deterministic version outperforms the best NWP baseline by 9.6% at a 24-hour lead time while requiring fewer than 3.5 A100-days for training. It provides a 2x efficiency gain over lightweight AI models and a 100-fold reduction in compute compared to resource-intensive frontier architectures. We extend these efficiency gains into probabilistic forecasting by training via the Continuous Ranked Probability Score (CRPS). Scaling to a larger architecture, Otter-XL achieves a 9.7% CRPS improvement over the IFS ENS baseline. This yields an almost two-fold increase in predictive skill over comparable lightweight models at similar compute budgets. Otter-XL also outperforms frontier architectures like GenCast by over 2%, while using an order of magnitude less compute. Finally, Otter is applied out-of-the-box to a complex acoustic scattering PDE task where it outperforms a state-of-the-art foundation modelling approach, suggesting that the advances made here might apply across a range of scientific domains.

cs.LG · cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05680

Toward an Optimal Configuration for Tree Species Classification from Bark Images: A Leakage-Safe Ablation Study

Maeve Côté

原文摘要

Background: The automatic identification of tree species from bark photographs is of practical interest for forestry inventory and the wood-processing industry, yet the design choices that govern the accuracy of deep-learning approaches have not been studied systematically, and some prior results may be inflated by leakage of images of the same trunk across training and test partitions. Methods: A systematic ablation study is conducted on the public BarkNet 1.0 dataset (20 species) under the established tree-level, leakage-safe partitioning scheme. Using ConvNeXt-V2 backbones, the following factors are varied in turn and evaluated by five-fold cross-validation: patch size, the strategy by which per-patch predictions are aggregated into an image-level decision, the training regime (single- versus two-stage), backbone capacity, the whole-image baseline, and the number of patches available at inference. Results: Per-patch accuracy rises monotonically with patch size (from 75.6% at 160 px to 89.6% at 512 px), and image-level accuracy rises in step, plateauing near 94.9% around 512 px. Learned aggregation exceeds majority voting by at most 0.7 pp, an advantage that shrinks as patches grow and attention becomes near-uniform. Backbone capacity (pico to tiny) alters accuracy by less than a point, and two-stage training offers no advantage over one-stage. Whole-image classification (91.9%) trails patch-based aggregation, since it admits no bag to average over; accuracy increases with the number of patches at inference, saturating around 64. Conclusions: The study yields a simple recommended configuration: patches as large as possible while leaving enough to average over (around 512 px here), with a nano backbone. It also quantifies the second-order role of learned aggregation and model capacity, providing a reproducible reference point for practitioners and future research

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05675

Quadratic reset bounds for finite maximal prefix codes

Samrath Singh Chadha

原文摘要

Let $C$ be a finite maximal prefix code of maximum codeword length $k\ge2$. We prove that, whenever the literal decoder of $C$ is synchronizing, it has a reset word of length at most $(k-1)(4k-5)$. The bound is independent of the alphabet and the number of decoder states. Its main ingredient is a short-detection theorem: a linear observation of the decoder, with terminal weight constant on states of depth $k-1$, is either identically zero or nonzero on a word of length at most $2k-3$. The proof uses a first-return decomposition in noncommuting variables and cancellation of a highest-degree coefficient. For codes whose codeword lengths are $k-1$ and $k$, we prove the sharper bound $2(k-1)^2-1$ and characterize equality. The binary code with the single short word $a^{k-1}$ attains this bound for every $k\ge2$; an age representation and a potential on circular arcs give the matching lower bound. Both upper bounds yield polynomial-time constructions in the explicit code size. The mathematical results and the algorithms are formalized in Lean, with polynomial work bounds in a specified binary cost model.

cs.FL

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2608.00932

Gaokerena: A Small Persian Medical Language Model Family

Mehrdad Ghassabi, Hamidreza Baradaran Kashani, Pedram Rostami, Sadra Hakim, Zahra Kazemi, Amirhossein Poursina, Milad Tavakoli, Audrina Ebrahimi

原文摘要

Persian medical natural language processing remains limited by the scarcity of domain-specific resources and insufficient public characterization of their coverage and quality. We present Gaokerena, an openly released suite of Persian medical resources comprising an 85.5-million-word corpus of 101,954 web articles; MF3QA, a 24,000-pair patient-doctor question-answering dataset; 1,878 Iranian medical examination questions (KOPP); 1,089 manually translated medical MMLU questions (FA_MED_MMLU); and approximately 18,000 machine-translated MedMCQA training items filtered by two language-model evaluators. We characterize the resources' composition, orthographic variation, redundancy, topical coverage, privacy indicators, answer-key balance, extraction artefacts, and translation limitations. As application case studies, we adapt Aya-Expanse-8B into Gaokerena-V, trained on the corpus and MF3QA, and Gaokerena-R, developed through preference-based reasoning distillation. On translated medical MMLU, Gaokerena-V achieves 49.31% accuracy under direct prompting, compared with 46.65% for Aya-Expanse-8B; the paired exact McNemar test is statistically inconclusive (p = 0.0502). Gaokerena-R reaches 52.80% using five-sample self-consistency and a verifier, but this higher-compute setting is not directly comparable. Under matched five-sample chain-of-thought self-consistency without a verifier, Gaokerena-R scores 48.58%, versus 46.92% for Aya-Expanse-8B, a non-significant difference (p = 0.190). English evaluation also reveals a substantial performance gap relative to Persian. To our knowledge, Gaokerena provides the first openly released and systematically characterized suite of Persian medical resources alongside generative models built on them. These protocol-specific results do not establish an isolated training advantage or clinical readiness.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05671

How Do Artificial Agents Make Decisions in Light of Visual Data?

Keyty Loza, Shayan Monadjemi

原文摘要

Vision-language models (VLMs) have demonstrated significant advances in reasoning with visual data, which is particularly important given that much of human knowledge is encoded visually in scientific articles and other sources. However, a gap remains in understanding how artificial agents, powered by VLMs, perceive and navigate decision-making under uncertainty in the presence of visual data. This study explores this gap by evaluating and analyzing autonomous decision-making processes. Building upon prior work in visualization literacy and decision theory, we conducted two complementary studies: one examining how agents perceive and quantify uncertainty encoded in visualizations, and another investigating how artificial agents make decisions based on visual data in the form of images. We analyzed perception accuracy and decision performance across models and visualization types. Our results show that GPT-4o demonstrates the highest accuracy in perceiving uncertainty in pie and bar charts among the tested models. For decision-making, autonomous agents showed the best alignment with rational decision theory when uncertainty was represented through circle charts, icon arrays, or text.

cs.AI · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05670

Inferring Factor Importance with Explainable AI Model for Macrophage Immune Cell Polarization

Joseph Pateras, Gurseerat Kaur, D. Joshua Cohen, Barbara D. Boyan, Zvi Schwartz, Preetam Ghosh

原文摘要

Macrophages are highly plastic immune cells that dynamically shift between pro- and anti-inflammatory phenotypes in response to cytokines, transcriptional regulators, metabolic cues, and local microenvironment. Yet macrophage polarization is governed by nonlinear regulatory networks that are difficult to study experimentally. Here, we integrate mechanistic simulation, surrogate neural networks, and explainable machine learning to identify key regulatory drivers of polarization. We generated simulation data with a COPASI-based macrophage polarization model and used them to train an LSTM surrogate capable of reconstructing temporal macrophage marker dynamics across diverse macrophage activation states. SHAP, Individual Conditional Expectation, and Partial Dependence Plot analyses quantified feature importance, identified nonlinear response regimes, and characterized higher-order interactions among cytokines, transcription factors, and polarization markers. The model identified oxygen availability and IL10 as dominant anti-inflammatory regulators, consistently promoting M2-associated outputs such as ARG1 and VEGF. Conversely, IFN-γ, TNFα, IL12, iNOS, CXCL9, and mCXCL10 reinforced M1-associated inflammatory programs. STAT1-centered analyses identified iNOS, TNFα, and mCXCL10 levels as strong contributors to STAT1 outcomes, consistent with amplification of the IFN- γ/JAK/STAT1 inflammatory axis. VEGF negatively contributed to predicted STAT1 output, suggesting antagonism between M2 markers and M1 activation. SHAP, ICE, and PDP analyses also showed that STAT1 regulation is nonlinear and threshold-like: pro-inflammatory signals must accumulate before STAT1 rises sharply. Together, it demonstrates that the LSTM explainability framework can identify polarization drivers, uncover nonlinear regulatory thresholds, and prioritize pathways for experimental validation.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05669

The Harmonic Online $k$-Server Algorithm Is Poly(k)-Competitive

Yichen Huang

原文摘要

The online $k$-server problem is one of the most fundamental problems in online algorithms. In this problem, $k$ servers are located in a metric space and serve a sequence of requests at points in the metric space by moving a server there. The Harmonic algorithm is a very natural algorithm: it chooses a server with probability inversely proportional to its distance from the request. It is also highly efficient, being memoryless and answering each request in $O(k)$ time. However, its competitive ratio has remained unsettled between the $O(2^k \log k)$ upper bound (Bartal and Grove, JACM 2000) and the $k(k+1)/2$ lower bound (Raghavan and Snir, 1994, IBM J. Res. Dev.). We prove that Harmonic is $2k^4$-competitive on every metric space against adaptive online adversaries. Our analysis uses a potential combining corrected electrical energy with the distances of online servers to their assigned adversary locations.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05668

Sundance: A Simple SMT Solver for Program Verification

Amar Shah, Benjamin F. Jones, Can Cebeci, Jason Z. S. Hu, Lee A. Barnett, Rémi Delmas, Marijn Heule, Bryan Parno 等 9 位作者

原文摘要

We present Sundance, an SMT solver for program verification written in about 13,600 lines of Rust. Sundance combines the Cadical SAT solver with congruence closure, linear arithmetic, algebraic datatypes, and pattern-based quantifier instantiation. Sundance produces eDRAT proofs for every unsat answer. On 21,531 queries from Verus, Dafny, and F*, Sundance is comparable to existing solvers, with 26--38 times fewer lines of code than Z3 and cvc5. We further show that its components can be swapped for Z3's arithmetic solver, MiniSat, and the Semper e-graph. We have open sourced Sundance.

cs.LO

查看论文
arXiv ↗PDF ↗