跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订,在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+1085新增论文
+884其中 AI 相关
+130已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 11:32 — 2026-11-19 11:32(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59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。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v6arXiv:2508.05597

确定性通信复杂度的NP困难性与加性不可近似性

NP-Hardness and Additive Inapproximability of Deterministic Communication Complexity

Serge Gaspers, Tao Zixu He, Simon Mackenzie

AI 速读 基于摘要

作者报告:给定布尔函数完整真值表,确定两方计算该函数所需最小最坏情况通信比特数是NP困难的,且在任何固定加性误差下不可近似。

cs.CC · cs.DS · math.CO

查看原文摘要

Given the full truth table of a Boolean function whose input is split between two players, we study the complexity of determining the minimum worst-case number of bits they must communicate to compute it. This is a basic meta-complexity question, posed by Yao in 1979. We prove NP-hardness of approximation within every fixed additive error for deterministic communication complexity, under deterministic polynomial-time reductions. The result holds both in the standard model and in Yao's original model, where the players alternate after every bit and only the receiver of the last bit must determine the answer. In particular, it resolves the exact computation question under Yao's original conventions. Earlier versions of this same paper established exact NP-hardness for the standard model, independently and concurrently with Hirahara, Ilango, and Loff. In both models, a polynomial-time estimator with any fixed additive error would yield a polynomial-time $3$-SAT algorithm, deterministic or bounded-error randomized according to the estimator. For the standard model, we also give quantitative implications for errors that grow with the number $T$ of table entries. A bounded-error randomized polynomial-time estimator with additive error $c\log T/\log\log T$, for any fixed $0\le c<1/8$, yields a bounded-error randomized $3$-SAT algorithm on $N$ variables and $O(N)$ clauses running in time $2^{O(N^α)}$ for every fixed $8c<α<1$. A deterministic polynomial-time estimator with additive error $c_*\log\log T$, for an effective absolute constant $c_*>0$, yields a deterministic algorithm running in time $2^{O((\log N)^2)}$ on such formulas.

版本更新 · v2arXiv:2607.00861

TrajLoc:面向多目标运动控制的轨迹注意力定位

TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control

Omer Sela, Inbar Huberman-Spiegelglas, Michael Rotman, Sagie Benaim, Avi Ben-Cohen

AI 速读 基于摘要

TrajLoc 通过在注意力层中为每个对象 token 注入以目标位置为中心的高斯热图,实现图像到视频生成中多对象轨迹的独立空间约束。

cs.CV · cs.GR

查看原文摘要

Controlling the motion of multiple objects in image-to-video (I2V) generation requires preserving object identities while enforcing adherence to distinct target trajectories. This becomes particularly challenging as the number of objects increases and their paths intersect or occlude one another. Existing approaches entangle multiple trajectories within a shared, dense conditioning signal, making object-level correspondence difficult to preserve in crowded scenes. We depart from this paradigm and enforce a strict, per object spatial constraint that isolates instances independently. Our method, TrajLoc, achieves this directly within the attention layers by substituting the cross-attention weights of each object token with a Gaussian heatmap centered on its target location at every frame. The same per object token interface carries trajectory and depth through a learned embedding and preserves identity by encoding first frame appearance in place of an object token. Evaluations across six datasets, featuring up to 20 simultaneously controlled objects and out of distribution real world scenes, demonstrate that our method consistently improves both visual fidelity and trajectory adherence. Applied to two architecturally distinct backbones (CogVideoX 5B and WaN 2.1 14B), our approach achieves average gains of +4.3 dB PSNR and a 51% reduction in trajectory end point error compared to the strongest baselines. Project page: https://sela-omer.github.io/traj-loc/

版本更新 · v2arXiv:2610.32024

BARC-Bench:良性请求,风险后果

BARC-Bench: Benign Asks, Risky Consequences

Kangkang Li, Kelvin Luu, Lily Ma, Tu Trinh, Ying Liu, Mohamed Elfeki

AI 速读 基于摘要

作者提出 BARC-Bench 基准,用 110 个表面良性但暗含安全边界的任务,评估智能体在欠指定指令下是否会越界。

cs.AI

查看原文摘要

Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce BARC-Bench, a collection of 110 tasks across nine simulated workspace environments where benign requests leave openings for unsafe actions. In this benchmark, we evaluate agent behavior against safety boundaries established by workspace records, implicit environmental context, and unstated social norms. For example, an agent asked to schedule off-boarding discussions must arrange the meeting without prematurely revealing an employee's resignation through a shared calendar invitation. Evaluating four frontier model configurations across five attempts per task reveals that models are not consistently safe: the share of tasks completed safely on all five attempts ranges from 9.1% to 72.7%, with even the strongest configuration producing a safety violation on 27.3% of tasks. These results highlight an asymmetric operational risk: while models frequently complete complex workflows, their inability to consistently respect unstated boundaries presents a substantial barrier to safe autonomous delegation.

版本更新 · v4arXiv:2608.04228

拓扑计算路径:表示不变性与可观测商

Topological Computational Paths: Presentation Invariance and Observable Quotients

Arthur Freitas Ramos, Ruy J. G. B. de Queiroz, Anjolina Grisi de Oliveira, Tiago M. L. de Veras

AI 速读 基于摘要

研究有限计算路径的连续表示,比较保留完整带符号轨迹的拓扑与仅记录端点、长度和精确路径实现的可观测拓扑,并分析二者在表示不变性下的差异。

cs.LO · math.AT

查看原文摘要

A computational path records the steps used to establish an equality. Topologies on computational equality witnesses can depend on the chosen generators and execution schedule, even when their algebraic and homotopical meanings agree. We study continuous presentations of finite computational paths whose declared rewrites are realized by endpoint-fixed homotopies. We compare a topology retaining the full signed trace with an observable topology recording endpoints, length, and exact path realization. Continuous finite-word interpretations that are inverse up to scoped rewriting preserve trace-sensitive quotient arrows and their final composable-pair spaces. Observable quotients behave differently. Over a point with a nonempty primitive alphabet, we classify their topology: it records length parity when all named relations preserve parity, and is otherwise indiscrete. Adjoining a conservative abbreviation can therefore turn a discrete two-element quotient into an indiscrete space, even though ordinary multiplication remains continuous. A circle presentation also gives nonhomeomorphic quotients under binary and equal-slot timing. Geometric completeness alone does not identify the trace-sensitive and observable topologies. Multiplication is continuous on the quotient of composable representatives. We characterize when this topology agrees with the ordinary pullback topology and give an open-projection criterion. Universal presentations recover classical fundamental-groupoid topology. Normal forms, primitive interchange, and a Cayley covering prove completeness for circle, torus, product, and rose presentations. A literal-word correspondence relates the semantics to the reflexivity, symmetry, and transitivity fragment of equality derivations. Selected results are formalized in Lean, with the realization models and proof coverage stated explicitly.

版本更新 · v2arXiv:2611.02174

超越单位圆特征值:稳定状态空间动力学的不变基

Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics

Jiaqian Zhu, Yang Zhang, Junhua Ding, Xiaowei Yu

AI 速读 基于摘要

作者提出对角递推的守恒量具有分层结构,并通过Kronecker-Cayley变换按构造强制满足各层条件,以在训练前固定守恒量。

cs.LG

查看原文摘要

Diagonal state space models process long sequences at linear cost, yet the same transition is applied at every step of a rollout, so an unconstrained recurrence holds no quantity fixed and the state decays or grows without bound. Current designs constrain one quantity, and preserving one does not guarantee preservation of the others, so a model can hold its norm to machine precision while momentum drifts by hundreds of percent. We claim that the conserved quantities of a diagonal recurrence are layered, that each layer requires a strictly stronger condition on the operator, and that a unit-modulus spectrum reaches only the outermost. Acting on the claim, we enforce the conditions required for every layer by construction. The generator of the Kronecker-Cayley transition (KC) is a graph Laplacian over object subspaces, $\mathbf{H}=\mathbf{L}\otimes I_m$, advanced by a Cayley transform, and the step stays diagonal at $O(N^3+N^2m)$ cost. The conserved set is exactly a $2m^2$-dimensional family of quadratic forms, held at every parameter value, so the quantities and the dynamics the construction reaches are fixed before training. On four conservation benchmarks, KC holds total mass at or near the reference floor while every diagonal baseline loses it by orders of magnitude. We further compare against mass correction and find that two correctors fail once the underlying prediction diverges, which shows that assembly rather than correction is necessary for a guarantee that holds across the rollout. A free modal basis trained under a conservation penalty conserves only by freezing its spectrum, whereas the assembled operator conserves with every mode but one free to rotate. Beyond these benchmarks, KC holds the linear momentum of three $N$-body systems and, at the operator level, the conserved quantity in molecular dynamics, chemical kinetics, pharmacokinetics and power-grid swing dynamics.

版本更新 · v2arXiv:2610.32670

任意范数下凸体追逐问题的线性下界

A Linear Lower Bound for Convex Body Chasing in Every Norm

Nicolas Christianson

AI 速读 基于摘要

作者证明在任意范数下,ℝ^d 中凸体追逐的竞争比存在 Ω(d) 下界,从而说明 Sellke 的 O(d) 算法渐近最优。

cs.DS · cs.CG · math.MG

查看原文摘要

We establish an $Ω(d)$ lower bound on the competitive ratio of convex body chasing in $\mathbb{R}^d$ with movement costs measured in any norm. Previously, the best known lower bound valid across all norms was $Ω(d^{1/6})$, established by Papazov (2023); stronger lower bounds were known for $\ell_p$ norms, where Bubeck, Klartag, Lee, Li, and Sellke (2019) had established a lower bound of $Ω(\max\{\sqrt{d}, d^{1-1/p}\})$. In particular, a linear lower bound was known only for the $\ell_\infty$ norm, realized by the standard construction of chasing faces of a hypercube. Our lower bound strictly improves on the prior universal and $\ell_p$ lower bounds for $p < \infty$ and shows that the functional Steiner point algorithm of Sellke (2023) - which has competitive ratio $O(d)$ - is asymptotically optimal for every norm. Our approach is based on the recursive construction of Bubeck, Coester, and Rabani (2023) for metrical service systems, which gives a lower bound of $Ω(r^2)$ for requests of size $O(r)$. We show that requests in their construction, each comprising a set of discrete points in a graph metric, can be mapped to the vertices of convex requests in a $(2r+1)$-dimensional $\ell_p$ vector space while approximately preserving movement costs up to a factor of $O(r)$; the general result then follows via Milman's (1985) quotient-of-a-subspace theorem.

版本更新 · v2arXiv:2611.02335

基于归因的单细胞基础模型诊断

Attribution-based diagnostics for single-cell foundation models

Farnoush Rezaei Jafari, Tristan Lazard, Kenza Bouzid, Shruthi Bannur, Jeremiah Wander, Ashley Mae Conard, Stephanie Hyland, Lorin Crawford 等 9 位作者

AI 速读 基于摘要

该研究系统评估了事后归因方法在单细胞基础模型下游预测诊断中的价值与陷阱。

cs.LG · q-bio.QM

查看原文摘要

Single-cell RNA foundation models (scFMs) are increasingly used for in-silico biological discovery, yet predictive performance alone does not reveal whether their decisions rely on biologically meaningful signals or model-specific shortcuts. We systematically investigate post-hoc attribution of downstream predictions across two tasks: cell-type annotation using pretrained Cell2Sentence and scGPT models, and perturbation prediction using scGPT+STATE in a controlled setting. For cell annotation, we use attribution to assess whether predictions rely on established marker genes and how their relevance varies with model architecture, expression rank, and the surrounding cellular context. For perturbation prediction, we compare attribution patterns with known regulatory ground-truth in a synthetic setting to assess what they reveal about the model's learned computations. Across these tasks, attribution reveals biological feature use, contextual interactions, contributions from different input pathways, learning progression, associations with prediction quality, and potential pitfalls that are not fully captured by standard performance metrics. Experiments with complete and limited regulatory knowledge further demonstrate that conclusions drawn from attribution depend strongly on the choice of biological reference, baseline, and null model. Together, these findings highlight the value of attribution as a flexible post-hoc diagnostic for understanding model behavior, identifying potential issues, and informing the development of scFMs.

版本更新 · v2arXiv:2610.37863

DropFENO:面向混合润湿图案表面液滴平衡的无数据、基于物理的算子学习框架

DropFENO: A Data-Free, Physics-Based Operator-Learning Framework for Droplet Equilibria on Mixed-Wettability Patterned Surfaces

Ganesh Sahadeo Meshram, Partha Pratim Chakrabarti, Suman Chakraborty

AI 速读 基于摘要

作者提出仅从自由能出发、无需解数据的神经算子框架 DropFENO,用于学习化学图案壁面上液滴的平衡态与毛细力。

cs.CE

查看原文摘要

We study whether the equilibrium of a drop on a chemically patterned wall, and the capillary forces that the pattern exerts on it, can be learned from the free energy alone, without solution data. We introduce DropFENO (Droplet Free-Energy Neural Operator), in which Fourier (FNO), tensor-factorised Fourier (TFNO) and wavelet (WNO) neural operators are trained in two and three dimensions on the diffuse-interface free energy of the drop, with its volume and centroid constraints imposed as penalties. The predictions are tested with the virtual-work (Hellmann--Feynman) theorem: the force exerted by the pattern on a held drop is a wall integral of the equilibrium field which, for a drop straddling a wettability step, reduces identically to the contact-line law $F=σΔ\cosθ\,L$. DropFENO reproduces this law and the energy landscape of a drop crossing a step, and reproduces the pinning of the receding contact line less accurately. The residual error lies in the soft modes of the capillary energy (small displacements of the interface and the contact line). This explains why the energy is predicted accurately while contact-line positions are not, and why on striped walls the operators return Cassie-like states instead of the edge-pinned states whose anisotropic apparent angles the reference minimiser shares with lattice Boltzmann simulations. On held-out patterned walls the median energy of the predictions lies $\NdEmedRandFnoTwo$ of the free-drop energy above the best known minimum (FNO, two dimensions), at about one hundredth of the cost of a per-instance minimisation, and a refinement by a classical solver started from the prediction returns the reference state in almost all cases.

版本更新 · v2arXiv:2604.14993

服务具有大内存足迹的链式结构作业:面向大型基础模型服务

Serving Chain-structured Jobs with Large Memory Footprints with Application to Large Foundation Model Serving

Tingyang Sun, Ting He, I-Hong Hou

AI 速读 基于摘要

针对大内存足迹的链式结构作业服务,提出“服务器链组合”问题,通过块放置与缓存分配建模流水线并行下的大模型服务,并给出可扩展且具性能保证的算法。

cs.DC · cs.PF

查看原文摘要

As a current trend in Artificial Intelligence (AI), large foundation models are increasingly employed as the core of AI services. However, even after training, serving such models at scale remains a challenging task due to their heavy resource footprints, particularly in terms of GPU memory. While recent works revealed unique characteristics of systems serving foundation models that distinguish them from traditional distributed computing systems, there is still a lack of fundamental understanding of the underlying system management problems. This work aims at addressing this gap by extracting a novel problem of "server chain composition" via block placement and cache allocation for serving chainstructured jobs with large memory footprints, which models a fundamental problem in serving large foundation models through pipeline parallelism. After showing the NP-hardness of the optimal solution, the focus is turned to developing scalable algorithms with guaranteed performance under state-of-the-art load balancing. Application of the proposed solution to a distributed large language model (LLM) serving system shows significant reduction of response times compared to state-of-the-art solutions.

版本更新 · v2arXiv:2606.01643

手语生成中的条件坍缩:一项诊断与覆盖度论证

Conditional Collapse in Sign Language Production: A Diagnostic and a Coverage Argument

Rui Hong, Jana Košecká

AI 速读 基于摘要

作者提出用三个独立层级诊断手语生成模型的条件坍缩问题,并论证目标忠实度取决于训练句对测试条件的覆盖密度而非语料规模。

cs.CV

查看原文摘要

The goal of Sign Language Production (SLP) is to translate natural language text into corresponding sign language movements performed by a virtual avatar. The quality of the generated motion is typically evaluated by a motion-space Frechet distance (FID) and back-translation BLEU score on benchmarks such as How2Sign. The existing approaches can improve both metrics substantially while the underlying generator fails to represent the input sentence, a failure we call conditional collapse. In this work we propose to evaluate the generated motion at three independent levels: (tau1) initial-pose conditioning, (tau2) output diversity, and (tau3) target faithfulness. We compute these as pairwise-distance ratios using latent representations of a frozen motion autoencoder (MoAE), judged against each dataset's own GT-vs-GT reference. We evaluate diffusion and regression SLP models on How2Sign, including a re-implemented Neural Sign Actors, and show that tau3 faithfulness is never attained, while FID varies by nearly two orders of magnitude and is uncorrelated with faithfulness. We then apply the same models and diagnostic to Phoenix-2014T, CSL-Daily, and gloss-level ASL3DWord and show that faithfulness varies proportionally to how densely the training sentences cover the test conditions (conditioning coverage) and not corpus size. The smaller but densely covered Phoenix-2014T and ASL3DWord datasets generate faithful sign motion, while CSL-Daily follows the input text yet falls short of sign language faithfulness. Using the largest, open-domain How2Sign dataset, the models collapse at every scale. We introduce two measurements of the text data that rank the corpora in the order of how densely the training sentences fill the embedding space, and how close each test sentence lies to its nearest training sentence.

版本更新 · v3arXiv:2601.23268

TCBench:全球尺度热带气旋路径与强度预报基准

TCBench: A Benchmark for Tropical Cyclone Track and Intensity Forecasting at the Global Scale

Milton Gomez, Marie McGraw, Saranya Ganesh S., Frederick Iat-Hin Tam, Ilia Azizi, Samuel Darmon, Monika Feldmann, Stella Bourdin 等 16 位作者

AI 速读 基于摘要

作者提出 TCBench,一个基于 IBTrACS 的全球热带气旋路径与强度 1–5 天预报基准,用于公平、与模型无关地比较物理模式与 AI 天气模型。

cs.CE

查看原文摘要

TCBench is a benchmark for evaluating global, short to medium-range (1-5 days) forecasts of tropical cyclone (TC) track and intensity. To allow a fair and model-agnostic comparison, TCBench builds on the IBTrACS observational dataset and formulates TC forecasting as predicting the time evolution of an existing tropical system conditioned on its initial position and intensity. TCBench includes state-of-the-art physics-based (TIGGE) and Artificial Intelligence Weather Prediction (AIWP) models (AIFS, Pangu-Weather, FourCastNetV2, GenCast, FNV3P2). If not readily available, TC tracks are consistently derived from model outputs using the TempestExtremes library. TCBench provides deterministic and probabilistic storm-following metrics. On 2023 test cases, AIWP models skillfully forecast TC tracks, while realistic intensity forecasts require additional steps such as post-processing or task-specific training. Designed for accessibility, TCBench helps AI practitioners tackle domain-relevant TC challenges and equips tropical meteorologists with data-driven tools and workflows to improve prediction and TC process understanding. By lowering barriers to reproducible, process-aware evaluation of extreme events, TCBench aims to democratize data-driven TC forecasting.

版本更新 · v2arXiv:2609.11836

自由概率状态演化与随机矩阵差异

Free-Probabilistic State Evolution and Random Matrix Discrepancy

August Y. Chen, Ahmed El Alaoui

AI 速读 基于摘要

作者为作用于独立高斯随机矩阵线性组合的近似消息传递迭代建立了自由概率意义下的状态演化,并将其用于构造算子范数更小的随机矩阵差异二元向量。

math.PR · cs.DS

查看原文摘要

Let $A_1,\ldots,A_n$ be independent $d \times d$ real symmetric Gaussian random matrices, and consider the linear operator $A(x) = n^{-1/2}\sum_{i=1}^n x_iA_i$, $x\in \mathbb R^n$. We construct an iterative algorithm in the Approximate Message Passing family which iterates over $A$ and its adjoint $A^*$, and establish a state evolution result which characterizes its behavior in the limit $d\to \infty, 2n/d^2 \to α$ in terms of a correlated Gaussian-semicircular process in a free probability space, in the sense of strong convergence of operators. We then apply this iteration to the random matrix discrepancy problem which asks for a binary vector $x \in \{-1,+1\}^n$ such that $A(x)$ has a small operator norm. Our algorithm achieves an operator norm $2σ(α)$, for a standard deviation $σ(α)<1$ for all $α>0$, and $σ(α) = O(1/\sqrt{α\log α})$ for large $α$. This resolves the algorithmic question of Kunisky-Zhang (2023) and Maillard (2025).

版本更新 · v2arXiv:2605.04029

随时间保持对齐:通过情境反思与隐私保护行为数据实现纵向人-LLM对齐

Stayin' Aligned Over Time: Towards Longitudinal Human-LLM Alignment via Contextual Reflection and Privacy-Preserving Behavioral Data

Simret Araya Gebreegziabher, Allison E Sproul, Yinuo Yang, Chaoran Chen, Diego Gómez-Zará, Toby Jia-Jun Li

AI 速读 基于摘要

作者提出从单次交互后的即时偏好采集转向纵向、情境化的对齐测量框架,并实现浏览器系统BITE进行两周部署研究。

cs.HC

查看原文摘要

Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implicitly treats preference as static, even though many LLM-mediated decisions unfold over time and may be re-evaluated differently after real-world consequences and observed outcomes. Therefore, we argue for a methodological shift from single-moment preference elicitation to longitudinal, context-situated alignment measurement. We present a methodological framework for collecting temporally grounded alignment signals by combining (1) in-situ preference capture, (2) context-triggered follow-up preference reflection, and (3) privacy-preserving behavioral traces that help interpret preference change. As an instantiation of this methodology, we introduce BITE, a browser-based system that detects consequential LLM interactions, prompts reflection across later decision points, and supports progressive, user-controlled consent for sharing behavioral data. Through a two week longitudinal deployment study with 8 participants, our approach surfaced differences between immediate and later user preferences in accuracy, relevance and other dimensions of the LLM output. Our findings highlight the limitations of single-moment preference datasets and underscore the importance of longitudinal methods for alignment evaluation in everyday use.

版本更新 · v2arXiv:2609.18772

手语手形的零样本跨语言识别

Zero-Shot Cross-Lingual Recognition of Sign Language Handshapes

Marcel Granero-Moya, Carolina del Corral Farrarós, Gloria Haro, Coloma Ballester, Ricardo Marques

AI 速读 基于摘要

作者提出首个手形零样本跨语言框架,将 ASL 模型迁移到加泰罗尼亚手语(LSC),并借助共享的音系特征分解实现无目标语言训练标签的识别。

cs.CL · cs.CV

查看原文摘要

Sign language processing advances rapidly for high-resource languages such as American Sign Language (ASL), yet most of the world's sign languages lack the phonological annotations new methods require. We present the first zero-shot cross-lingual framework for handshape recognition, transferring from ASL to Catalan Sign Language (LSC). Our approach leverages the decomposition of handshapes into five phonological features -- selected fingers, flexion, spread, thumb position, and thumb contact -- shared across both languages, to decode LSC handshapes from predicted features via a composite phonological distance metric. We evaluate three architectures (MLP, SL-GCN, SHuBERT) trained on two ASL corpora (PopSign, Sem-Lex) against a 37-handshape, single-signer LSC benchmark. Zero-shot transfer proves viable once recording-format disparities are harmonized, reaching 80.0% phonological feature accuracy and 54.5% expected handshape accuracy. Phonological decomposition thus offers a bridge for extending sign language technologies to low-resource languages without any target-language video training labels.

版本更新 · v2arXiv:2609.01800

利用大型深度神经网络改进合成孔径声呐图像中的自动目标识别

Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural Networks

C. J. Moore, Alex Hurt, Jordan Malof

AI 速读 基于摘要

该研究探讨在合成孔径声呐自动目标识别中使用高容量深度神经网络,并在小数据集上系统评估多种正则化策略的影响。

cs.CV

查看原文摘要

Automatic Target Recognition (ATR) in Synthetic Aperture Sonar (SAS) is often underpinned by deep neural networks (DNNs). Recent research has focused on relatively low-capacity DNNs (i.e., relatively fewer trainable parameters) to avoid overfitting on the small training datasets that are typically available for SAS. However, recent research has found that increasing DNN capacity often improves performance, even when training data is scarce. Motivated by this emerging finding - termed the double descent phenomenon - this work investigates the use of especially high-capacity DNNs for SAS-ATR. We evaluate the performance of several state-of-the-art DNN architectures as we increase their model capacity. We examine performance in a realistic leave-one-geo-location-out cross-validation scheme. We find that increasing model capacity often increases performance substantially, and is never harmful. All of our large models significantly outperform two baseline models from recent publications. Training high-capacity models on small dataset however requires careful regularization, and we also perform systematic experiments showing the impact of several regularization strategies: pretraining on other imaging modalities, data augmentation (including some new to SAS), DropPath, and weight decay. We show that each of these strategies independently improves the performance of the large models.

版本更新 · v5arXiv:2507.22017

Cyst-X:用于胰腺囊肿风险分层与跨机构AI的多中心MRI基准

Cyst-X: A Multicenter MRI Benchmark for Pancreatic Cyst Risk Stratification and Cross-Institutional AI

Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Ziliang Hong, Zhixiang Wang, Elif KelesDeniz Seyithanoglu, Zheyuan Zhang, Alpay Medetalibeyoglu 等 30 位作者

AI 速读 基于摘要

作者构建了覆盖七中心、764例患者的胰腺囊肿MRI公开基准,并提供分割与IPMN风险预测的参考AI模型及联邦学习模拟结果。

eess.IV · cs.CV

查看原文摘要

Intraductal papillary mucinous neoplasms (IPMNs) are pancreatic cancer precursors, and guideline-based risk stratification both over-treats indolent lesions and misses progression. We present Cyst-X, a public benchmark of 1,461 T1-weighted (T1W) and T2-weighted (T2W) MRI volumes from 764 patients at seven centers, with expert pancreas masks, risk labels, splits and reference AI risk-prediction models. PanSegNet segmented the pancreas with Dice of 86.34% (T1W) and 89.26% (T2W) on held-out centers. For the primary task, high-risk versus low-risk IPMN, a 3D DenseNet-121 achieved cross-validated AUCs of 74.59% and 73.45%; complementary broad binary and three-class tasks reached 78.67--81.28% and 73.47--75.76%. Because patient images often cannot be pooled across institutions, we also simulated federated learning across the seven centers. On T2W MRI, FedProx was similar to centralized training in center-averaged external AUC (71.00% versus 71.18%) but not in pooled AUC (62.35% versus 77.49%). Radiologist comparisons showed cohort-dependent sensitivity--specificity tradeoffs. Cyst-X supports reproducible method development and identifies within-IPMN risk discrimination and cross-center score comparability as open challenges.

版本更新 · v2arXiv:2604.25076

面向稀疏奖励任务与多样奖励塑形的零样本协调

Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings

Keenan Powell, Peihong Yu, Pratap Tokekar

AI 速读 基于摘要

作者提出用随机奖励塑形训练方法集成,以提升智能体与采用不同奖励塑形但稀疏目标相同的未知伙伴在稀疏奖励任务中的零样本协调表现。

cs.LG

查看原文摘要

Many Multi-Agent Reinforcement Learning (MARL) agents fail to adapt properly to cooperating with agents trained with the same objectives but different seeds, algorithms, or other training differences. This is the problem of Zero-Shot Coordination (ZSC), which focuses on training agents to cooperate well with unknown agents. ZSC has been studied for a variety of tabular cases and simple games such as Hanabi, achieving excellent results. However, existing solutions to ZSC only consider identical rewards for your trained agents and all future partners. This is not realistic for the trained agents, as they do not consider the problem of cooperating with agents that have identical sparse objectives but shape the rewards for those objectives in different manner. To address this issue, we show how to train an ensemble of methods using randomized reward shapings chosen using 4 selection algorithms. Experiments done on the Overcooked environment demonstrate consistent improvements of 62.2%-119.2% in sparse reward over baseline ZSC algorithms when playing with agents that have identical sparse rewards but different reward shapings.

版本更新 · v3arXiv:2312.03399

Connected Dominating Sets in Triangulations

Prosenjit Bose, Vida Dujmović, Hussein Houdrouge, Pat Morin, Saeed Odak

原文摘要

A dominating set of a graph $G$ is \emph{connected} if it induces a connected graph in $G$. For planar triangulations, it has been known since 1990 that every $n$-vertex triangulation with $n\ge4$ admits a connected dominating set of size at most $n/2 - 1$, and no improvement to this bound was known for over three decades. We break this longstanding barrier by showing that every $n$-vertex triangulation has a connected dominating set of size at most $10n/21$. Equivalently, every triangulation admits a spanning tree with at least $11n/21$ leaves. This result has graph drawing applications, establishing a bound for one-bend free sets and improving the known bound for simultaneous planar embeddings. The connected dominating set results extend readily to show that an $n$-vertex triangulation of a surface of Euler genus $g$ has a connected dominating set of size at most $10n/21+O(\sqrt{gn})$.

math.CO · cs.DM

版本更新 · v3arXiv:2601.16882

Explaining Group Recommendations via Counterfactuals

Maria Stratigi, Nikos Bikakis, Kostas Stefanidis

原文摘要

Group recommender systems help users make collective choices but often lack transparency, leaving group members uncertain about why items are suggested. Existing explanation methods focus on individuals, offering limited support for groups where multiple preferences interact. In this work, we introduce and formalize the problem of finding counterfactual explanations for group recommendations. We introduce a comprehensive set of item- and explanation-level metrics that capture different aspects, such as relevance, popularity, explanation utility, interpretability, and fairness. We design five algorithms that employ techniques such as search-space pruning, greedy selection, early stopping, and incremental refinement to reduce computational cost and the number of recommender calls while producing high-quality explanations. The algorithms consider different trade-offs; for example, some prioritize computational efficiency at the expense of explanation quality, while others focus on improving explanation quality at a higher computational cost. Experiments on real-world datasets analyze these trade-offs in terms of explanation size, computational cost, utility, and fairness.

cs.IR · cs.AI

版本更新 · v3arXiv:2608.29057

Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems

Aidan Li, Uday Kiran Reddy Tadipatri, Mahan Fathi, Sarath Chandar, Ross Goroshin

原文摘要

Koopman autoencoders (KAEs) seek a higher-dimensional latent representation in which nonlinear dynamics evolve linearly. However, many interesting systems have multiple basins of attraction, and both theoretical and empirical work has shown these multibasin systems cannot generally admit a single finite-dimensional global Koopman embedding under standard assumptions. We posit that encoders with a sparsity-inducing objective encouraging few active latent coefficients will provide latent supports as an inspectable basin-modeling principle for Koopman autoencoders. We use these encoders producing sparse latents in training Sparse Koopman Autoencoders (SKAEs) without basin labels or other regime annotations, and treat the learned latent supports as model-produced regime variables after training. Across a range of procedurally generated multibasin systems and chaotic flows, we show that SKAEs have superior forecasting performance compared to dense-latent KAEs. We also perform a mechanistic study that shows latent supports produced by SKAEs are both essential for the quality of the representation and useful for identifying basins on basin-interior states, whereas dense-latent KAEs collapse to an uninformative single support family. These results identify sparse latents and their corresponding supports as label-free, interpretable regime variables for Koopman learning in nonlinear systems with multiple local dynamical laws.

cs.LG · math.DS

版本更新 · v2arXiv:2610.41994

DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention

Zhangchi Feng, Harry Jiang, Yangyifei Luo, Ray Zhang, Richong Zhang

原文摘要

Linear attention scales linearly with sequence length, but its finite-state memory can limit long-context retrieval. In gated linear recurrences, memory retention depends on state decay, which is shaped jointly by gate parameters A_log and dt_bias and by input activations. In controlled Gated DeltaNet (GDN) experiments, both parameters remain highly correlated with their initial values after training, highlighting the importance of initialization. Therefore, we introduce Dual-Axis Memory Initialization (DAMI), which jointly configures these parameters before training. DAMI assigns geometric timescales across heads for varied retrieval distances and a low-high-low input-sensitivity profile across layers. A small activation sample calibrates the GDN-family implementation to match both behavioral targets without adding trainable parameters. Across GDN, KDA, GDN2, Mamba-2, and RWKV-7, DAMI improves average RULER-style retrieval accuracy by 5.29 to 16.71 percentage points over the corresponding random-initialization baselines. Performance on language modeling, commonsense reasoning, and 2K real-world retrieval remains broadly comparable to those baselines. Our code is available at https://speedai.com/research/dami.

cs.AI · cs.CL

版本更新 · v3arXiv:2603.14147

An Alternative Trajectory for Generative AI

Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha

原文摘要

The generative artificial intelligence (AI) ecosystem is undergoing rapid transformations that threaten its sustainability. As models transition from research prototypes to high-traffic products, the energetic burden has shifted from one-time training to recurring, unbounded inference. This is exacerbated by reasoning models that inflate compute costs by orders of magnitude per query. The prevailing pursuit of artificial general intelligence through scaling of monolithic models is colliding with hard physical constraints: grid failures, water consumption, and diminishing returns on data scaling. This trajectory yields models with impressive factual recall but struggles in domains requiring in-depth reasoning, possibly due to insufficient abstractions in training data. Current large language models (LLMs) exhibit genuine reasoning depth only in domains like mathematics and coding, where rigorous, pre-existing abstractions provide structural grounding. In other fields, the current approach fails to generalize well. We propose an alternative trajectory based on domain-specific superintelligence (DSS). We argue for first constructing explicit symbolic abstractions (knowledge graphs, ontologies, and formal logic) to underpin synthetic curricula enabling small language models to master domain-specific reasoning without the model collapse problem typical of LLM-based synthetic data methods. Rather than a single generalist giant model, we envision "societies of DSS models": dynamic ecosystems where orchestration agents route tasks to distinct DSS back-ends. This paradigm shift decouples capability from size, enabling intelligence to migrate from energy-intensive data centers to secure, on-device experts. By aligning algorithmic progress with physical constraints, DSS societies move generative AI from an environmental liability to a sustainable force for economic empowerment.

cs.AI · cs.LG

版本更新 · v2arXiv:2611.01449

CONFIRM: Governing Scientific Reporting for Trustworthy Agentic Neuroimaging

Yuxiang Wei, Lijing Zhu, Qizhen Lan, Yanteng Zhang, Vince D. Calhoun

原文摘要

Large language model (LLM) agents can autonomously run neuroimaging analyses from research questions to reported findings. Existing agentic systems use tools to check that code runs and reported values match its output, but rely on LLM judgment to decide which results warrant scientific reporting. We show that LLM judges endorse site-confounded findings even when the confound is presented as evidence. We present \textbf{CONFIRM}, a framework that separates running an analysis from deciding which findings to report. CONFIRM encodes each hypothesis as a machine-readable, pre-specified analysis plan that fixes the claim and its pass criteria before computing results. It then filters results through five deterministic gates (search history and multiplicity, confounds, power, analytic stability, and replication) under three configurable reporting standards, from least to most demanding: \textit{Screen}, \textit{Replicate}, and \textit{Full}. Failed claims receive diagnoses that guide follow-up analyses. To evaluate reporting decisions at the claim level, we introduce \textbf{NeuroClaimBench}, comprising 489 executable neuroimaging claims with frozen data, including literature-supported findings and 150 controls designed to violate individual methodological requirements. On NeuroClaimBench, CONFIRM falsely supports at most 3\% of controls, compared with 23--38\% for the baselines, while recovering up to 61\% of literature-supported claims. When auditing an existing agent, CONFIRM reduces false support on controls from 23\% to 0\% while retaining the agent's literature-supported claims. Its diagnostic feedback also produces more supported revisions than Self-Refine with fewer LLM calls. Together, CONFIRM and NeuroClaimBench show that basing reporting decisions on pre-specified analysis plans and deterministic gates is essential for trustworthy autonomous scientific discovery.

cs.AI · cs.MA

版本更新 · v2arXiv:2611.03533

CoLa3D: Composable Latent 3D Decomposition

Xudong Cai, Yongcai Wang, Deying Li, Chuanxia Zheng

原文摘要

We introduce CoLa3D, a simple and effective model for composable 3D scene decomposition that, given a single whole-scene latent from either a single image or an existing scene mesh as input, directly outputs a set of object meshes with consistent spatial layout that can be assembled back into a coherent scene. CoLa3D introduces a novel paradigm for 3D scene decomposition within a shared whole-scene latent, unlike alternatives that perform per-object generation in canonical spaces and then glue the objects back together with fragile pose and scale estimation. The network is a lightweight, flexible, and scalable query-based transformer that accepts various types of queries, including 2D masks, 3D points, and learnable queries, and learns to decompose the scene into objects in a compact latent space. On both synthetic and real-world datasets, CoLa3D achieves state-of-the-art performance on composable 3D scene decomposition, substantially improving global scene-level consistency and object-level quality while running 2 times faster and using less than 1% of SAM 3D's training data. Visible depth on par with MoGe2 further confirms that latent decomposition preserves accurate visible scene geometry while producing physically complete, decomposable object meshes.

cs.CV

版本更新 · v3arXiv:2303.12212

Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering

Łukasz Brzozowski, Grzegorz Siudem, Marek Gagolewski

原文摘要

Community detection is a significant challenge in analysing real graphs, including social, citation, biological, and many other networks. This article proposes three new, general, hierarchical frameworks to deal with this task. The introduced approach supports various linkage-based clustering algorithms, vertex proximity matrices, and graph representation learning models. We compare 364 module combinations on Stochastic Block Model graphs and real-life datasets. We observe that our best pipelines (Wasserman-Faust and the mutual information-based PPMI proximity, as well as the deep learning-based DNGR representations) perform competitively with the state-of-the-art Leiden and Louvain algorithms. At the same time, unlike the latter, they remain hierarchical. Thus, they output a series of nested partitions of all possible cardinalities which are compatible with each other. This feature is crucial when the number of correct partitions is unknown in advance, and we show that it is obtained at near-zero practical cost in terms of partition quality. On graphs composed of many small communities, our pipelines are more accurate than the reference solutions. Nevertheless, the downside of our approach is its time complexity, which confines the framework to networks of some 10000 vertices on personal machines.

cs.SI · cs.LG

版本更新 · v2arXiv:2610.13202

S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding

Yuhang He, Hongyu Ge, Zihan Lin, Siyi Liu, Yongqi Zhang

原文摘要

Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the response groups used for policy optimization. In our profiled RLVR workloads, attention accounts for 72--76\% of autoregressive decoding kernel time. Sparse attention reduces these reads, but sampling directly from a sparse policy changes the response groups used for learning. For group-relative optimization, we show that even exact response-wise reweighting does not generally recover the expected dense-policy update because the advantage of each response depends on the rewards of other group members. We propose Self-Sparse Speculative Rollouts (S$^3$R). It uses sparse attention to propose tokens, then generates responses through full-attention verification and exact speculative sampling. Drafting and verification share the same policy parameter, eliminating the need to train or update a separate drafter. The resulting response groups follow the dense-policy distribution. Under S$^3$R, we characterize speedup conditions and the costs of drafting and verification. We found that dense verification still requires the complete historical KV cache. A KV-aware scheduler therefore limits KV-cache repeated offloading and restoration while maintaining rollout parallelism. % OR thrashing In a matched ablation with an aggressive sparse drafting budget, S$^3$R maintains stable training while direct sparse sampling with training-side correction becomes unstable. On long-context mathematical reasoning, S$^3$R achieves $1.39\times~1.35\times$ the end-to-end training throughput of autoregressive rollouts on Qwen3 model, with comparable task performance.

cs.LG · cs.CL

版本更新 · v3arXiv:2610.32660

WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport

Chunchun Yang, Yang Cao, Zhitang Chen

原文摘要

Continual Wi-Fi sensing must learn new rooms or users (plasticity) while keeping earlier ones (stability), yet sensing nodes often cannot retain channel state information (CSI) for privacy and storage reasons. We propose WiMoT (Wi-Fi Moment Transport), which stores the per-class feature mean and covariance of every earlier domain instead of samples. Stored statistics become stale when the representation changes, so WiMoT restricts the change to an affine map on a frozen feature basis and applies the same map to the statistics, which then stay valid without old samples. Supervised contrastive learning learns the new domain, a closed-form loss on the stored statistics keeps earlier classes separable, and a Gaussian discriminant classifier refitted from the transported statistics predicts without domain identity. On 3DO, WiMANS, and Widar3.0, WiMoT reaches average final accuracies of 94.02%, 89.61%, and 95.16% with at most 0.58 percentage points (pp) of forgetting. On 3DO and Widar3.0 it is 3.77 and 13.11 pp ahead of the strongest of 21 baselines, which uses replay; on WiMANS it matches the strongest replay baseline in accuracy while reducing forgetting from 2.78 to 0.00 pp. Rank-32 covariance factors shrink the moment memory to 6.4% at a cost of at most 0.49 pp.

cs.AI

版本更新 · v3arXiv:2610.31900

Distributed Swarm Morphogenesis with Neural Cellular Automata

Ray Verma, Anthony Tzes, Eliseo Ferrante

原文摘要

Swarm morphogenesis requires robots to assemble desired shapes through local interactions. We present a modular framework integrating neural cellular automata (NCA) with existing site assignment and collision-aware control. Within this framework, we introduce a decentralized attachment-site discovery mechanism. Robots already in the formation update and share local NCA states to identify new attachment sites, enabling progressive growth without a predefined list of sites during deployment. To bridge the mismatch between conventional NCA growth and gradual physical assembly, we additionally propose offline sparse-retention fine-tuning that simulates partial attachment, together with a false-positive loss that penalizes invalid site activations. Simulations demonstrate formation of diverse lattice morphologies, scaling to several hundred robots, and substantial improvements in morphology accuracy from the proposed fine-tuning. Experiments with Crazyflie quadrotors validate the integrated execution pipeline using robot-relative observations reconstructed from external tracking.

cs.RO · cs.MA

版本更新 · v3arXiv:2602.09994

ORCHID: Fairness-Aware Orchestration in Mission-Critical Air-Ground Integrated Networks

Chuan-Chi Lai, Chi Jai Choy

原文摘要

Uncrewed Aerial Vehicles (UAVs) provide on-demand wireless coverage for mission-critical Air-Ground Integrated Networks (AGINs). However, DRL-based orchestration faces challenges from multi-agent non-stationarity and the trade-off between energy efficiency (EE) and service fairness. To address these issues, we propose ORCHID (Orchestration of Resilient Coverage via Hybrid Intelligent Deployment), a stability-enhanced two-stage learning framework. First, GBS-aware topology partitioning provides a topology-informed warm start for UAV deployment. Second, a Reset-and-Finetune (R\&F) mechanism is integrated into Multi-Agent Proximal Policy Optimization (MAPPO) to support stable late-stage policy refinement through event-triggered rollback and learning-rate adaptation. To study the efficiency-fairness trade-off, ORCHID employs a Max-Min Fairness (MMF)-oriented bandwidth allocation based on a closed-form Egalitarian Bargaining Game (EBG) solution and is compared with Proportional Fairness (PF). Experiments show stronger served-user bottleneck-rate protection under MMF, together with competitive coverage and user-rate fairness and favorable energy-efficiency and UAV-load-balancing performance under zero-shot scalability and mobility tests. Overall, ORCHID provides an effective balance among user-level service protection, energy efficiency, and policy stability for resilient mission-critical UAV networks.

cs.NI

版本更新 · v2arXiv:2605.29290

A Two-Count Baseline for Change Detection on Dynamic Networks

Izhar Ali

原文摘要

Change-point detectors for dynamic networks aim to find changes in how a network is connected. They are evaluated on real networks with labelled events, but many of these events also change how active the network is: how many vertices take part and how many edges are present. A detector can therefore score well by responding to activity alone, without detecting any change in structure. We test whether detectors from the literature beat a simple baseline that tracks only the number of active vertices and the number of edges in each snapshot, a baseline that we motivate with a standard statistical test for a change in activity. On ten datasets, four of them from the papers of published detectors, none of thirteen detectors ranks the labelled events significantly better than the baseline when the results are pooled (AUC $0.75$, or $0.73$ with scales taken from early snapshots only, against $0.66$ for the best detector). The baseline is best on only two datasets, however, and on the four datasets with the most events three detectors that track individual vertices score higher. When we rewire networks while keeping the degree of every vertex fixed, most detectors that ignore vertex identities barely respond, but several that track individual vertices do. New detectors should be compared with this baseline and tested at fixed degree.

cs.CG