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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 21:43 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 22:16 — 2026-11-09 22:16（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：2026-11-09 21:43最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 21:40（北京时间）
版本更新 · v3arXiv:2606.04003

A sharp analysis of Root-MUSIC: locations of correct and extraneous roots

Hana Huber, Weilin Li

原文摘要

Root-MUSIC is a spectral estimation algorithm that approximates the unknown signal frequencies by constructing a high-degree polynomial and finding a subset of roots which are closest to the complex unit circle. Previous works found asymptotic expectation formulas for the performance of Root-MUSIC under the implicit assumption that the aforementioned root selection criterion does not select extraneous roots -- those which are unrelated to the correct parameters. This paper removes the need for this assumption by showing all extraneous roots lie outside an annulus of a certain thickness and therefore are not selected by the algorithm. This paper also provides sharp and non-asymptotic error bounds for the correct roots in terms of fundamental model parameters. All results hold under a natural separation condition on the correct signal frequencies and are applicable in both the single- and multi-snapshot models. Numerical simulations confirm our theory. The main mathematical insight of this paper is a geometric property of the Root-MUSIC polynomial: its correct roots are highly stable to noise while its extraneous roots must lie outside of an annulus.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35685

Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews

Hari Sitaula, Manish Sakhakarmy, Pujan Pant, Sagar Newpane

原文摘要

Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and emotionally mixed experiences at living sacred heritage sites. We adapted the LLM-Social Computing (LLM-SC) framework to Pashupatinath Temple, Nepal, by specifying a 12-type entity taxonomy (four original LLM-SC types plus eight sacred-heritage types), four relation types and nine aspect-sentiment dimensions in a GPT-4o extraction prompt, which was applied to a fixed random sample of 2,500 English-language Tripadvisor reviews from a processed corpus of 3,939. The exports contain 11,286 entity, 6,232 aspect-sentiment and 5,590 relation records, covering 2,485, 2,487 and 2,433 reviews, respectively; the eight added sacred-heritage types account for 64.8% of entity records. Against an adjudicated two-annotator reference for 200 reviews, exact normalized surface-and-type matching gave provisional entity scores of 41.0% precision, 21.8% recall and 28.4% micro-F1. Aspect-presence F1 was 53.6% and end-to-end aspect-plus-polarity F1 was 42.6%. Human adjudication supported 153 of 194 first-listed relation candidates (one per review; 78.9%), a candidate-level rate that does not estimate relation recall or whole-graph precision. The contribution is a culturally grounded, domain-specific adaptation with component-wise human evaluation and explicit reproducibility and generalization limitations.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35684HF 社区推荐

OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images

Junyeong Ahn, Geonwoo Kim, Kinam Kim, Gihwi Kim, Hoonjin Jung, Hyojin Jang, Jaegul Choo

原文摘要

Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods condition on a single reference image and must therefore infer the subject's unseen appearance and geometry as the viewpoint changes. To address this limitation, recent methods extend S2V to multiple reference views, providing more information about the subject from different viewpoints. However, they do not explicitly specify the 3D structure that connects these observations. In addition, existing training data do not guarantee that viewpoint changes preserve the same underlying 3D subject. We present OmniShowcase, built on two components: (i) a fully automated data synthesis pipeline that produces training videos along diverse camera trajectories, with viewpoint variation driven by underlying subject geometry, even spanning full 360-degree orbits; and (ii) a geometry-conditioning method that provides the video model with a turntable of surface-normal maps reconstructed from the reference views without requiring temporal alignment with the generated frames. We construct Showcase-4K, a corpus of 3D-asset-based videos covering twelve camera motions across 88 trajectory configurations with reconstruction-derived surface-normal conditioning, and ShowcaseBench, a held-out evaluation set with the source meshes and camera parameters used to render each video. Experiments show state-of-the-art subject identity and 3D consistency while maintaining competitive video quality and motion. Project page: justin4ai.github.io/OmniShowcase

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.30089

ProactEgoMem: Benchmarking Proactive Memory in Streaming Egocentric Video

Ruotong Liao, Meikel Kokowski, Xiaoxiao Sun, Yongqin Xian, Laura Bravo Sánchez, Shiye Su, Federico Tombari, Serena Yeung-Levy 等 9 位作者

原文摘要

Today's multimodal assistants are typically prompted to interpret the visual evidence presented to them. To offload the cognitive burden of remembering across long horizons, wearable assistants should instead proactively acquire and maintain useful memory as the user's surroundings evolve. Doing so on the user's behalf requires identifying what matters, understanding the scene in real time, and initiating memory maintenance in the background while the user stays focused on their activities. We introduce ProactEgoMem, a benchmark that evaluates proactive memory in streaming egocentric video. Three tasks ground the evaluation in ambient environmental needs: Information Capture (IC) preserves transient yet dense visual information, State Tracking (ST) follows changing object states, and Location Tracking (LT) records object movements. The benchmark defines its protocol at two levels of proactiveness: the Notification Level asks for a single timely notification that satisfies the user's intent, while the deeper Intervention Level asks the agent to maintain memory on the user's behalf through an active start-to-stop tool lifecycle. Parallel ProactEgoMem-Daily and ProactEgoMem-Sci tracks contain 300/100 clips covering daily and scientific use cases, paired with 1000/500 questions in ProactEgoMem-QA, which measures the quality of the proactively acquired memory. Across proprietary, open-source, video-language, and streaming baselines, even the strongest models fail to capture memory both timely and accurately. ProactEgoMem provides a rigorous evaluation foundation for proactive multimodal assistance and for video agents that co-exist with their users.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35682

Printed and Scanned: Exposing the Fragility of Single-Image Morphing Attack Detectors under Print-Scan Degradation

Diogo J. Paulo, Hugo Proença, João C. Neves

原文摘要

Face morphing attacks, in which the biometric traits of two or more identities are blended into a single face image, pose a severe threat to identity document issuance and automated border control. Consequently, a large body of work has proposed Single-image Morphing Attack Detection (S-MAD) algorithms and benchmarked them on datasets such as SYN-MAD22. However, the majority of these benchmarks operate exclusively in the digital domain, which contrasts with the real-world passport issuance pipeline in some countries, which still requires an applicant-supplied photograph to be printed and subsequently re-scanned before it is embedded in the identity document or fed into an automated verification system. This print-scan step introduces halftoning, resampling, color-space, and sensor noise that are absent from digital pipelines, and may mask the high-frequency artifacts that S-MAD models rely on. In this work, we introduce a print-scan version of the SYN-MAD22 dataset, obtained by printing and re-scanning all bona fide and morphed images at 300 and 600 DPI, and we use it to evaluate eight state-of-the-art S-MAD models trained exclusively on digital data. We additionally repeat the acquisition with a second scanner to assess cross-device robustness. Our results show that detectors that achieve near state-of-the-art performance in the digital domain suffer a more than threefold increase in average equal error rate, with the same qualitative degradation observed across both scanning devices, exposing a critical, previously under-reported gap between digital-benchmark performance and robustness to print-scan degradation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.25692

Homomorphic Quantum Error Correction

Kornikar Sen, Miguel A. Martin-Delgado

原文摘要

We study the algebraic compatibility between quantum homomorphic encryption and stabilizer quantum error correction in an honest-but-curious model, restricting the encryption to the transversal block-Pauli mask $(X^aZ^b)^{\otimes n}$ controlled by two secret key bits $a$ and $b$. We prove a necessary and sufficient criterion for an $[[n,1,d]]$ stabilizer code to remain compatible with this mask, namely that the transversal $X$ and $Z$ operators commute with every stabilizer generator, and we specialize it to a classical-code criterion for Calderbank--Shor--Steane codes. Combining code-space preservation with the logical action of the mask, every stabilizer code falls, with respect to each of the two transversal mask operators, into exactly one of three classes: incompatible, compatible but trivially acting, or compatible with a nontrivial logical Pauli action; the two operators need not fall into the same class. We verify this classification by exact symplectic computation for rotated and planar surface codes, toric codes, triangular and toric color codes, the $[[15,1,3]]$ code and several small codes, and find that the class is fixed by the lattice size and the boundary presentation rather than by the topological phase: the surface-code family realizes all three classes, whereas color codes realize only the two compatible ones. For encrypted computation we show that the Shor code does not implement the logical $T$ gate by a transversal $T^{\otimes 9}$, whereas suitable triorthogonal codes do so up to a Clifford correction. We formulate logical-Pauli masking as a code-independent algebraic template. Syndrome extraction and recovery are key-independent whenever the mask preserves the code space, so that the client only needs the block size and the class of the code to decrypt.

quant-ph · cs.CR · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35680

Verse: Semantics and Verification of Hybrid Multi-Agent Scenarios

Yangge Li, Katherine Braught, Alex Yuan, Sayan Mitra

原文摘要

Verifying cyber-physical systems with many interacting agents remains difficult because interactions are mediated by sensors, individual decisions are constrained by environment (map) structure, and the resulting mode space scales combinatorially. We present Verse, a framework for writing agents, maps, and sensors in a familiar programming language syntax, with a formal semantics for the resulting scenarios. A compiler translates each scenario to a hybrid automaton whose executions correspond exactly to the runs of the scenario. Reachability analysis on this automaton builds an execution tree from two post operators, one for continuous flow over a time step and one for a single agent's mode change, and checks safety assertions at every vertex. The tree expands only the modes that are reached, without enumerating the global mode space. Experiments highlight expressive modeling across cars and drones, 2D/3D maps (including OpenDRIVE imports), noisy sensors, and multiple simultaneous safety assertions. Verse verifies a scenario with 7 agents and 37 modes in 90 seconds on a standard laptop; it is competitive with CORA and JuliaReach on ARCH benchmarks, and on multi-agent scenarios is an order of magnitude faster than JuliaReach at the cost of looser reachable sets.

cs.FL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.18377

Theory and interpretability of Quantum Extreme Learning Machines: a Pauli transfer matrix approach

Markus Gross, Hans-Martin Rieser

原文摘要

Quantum reservoir computers (QRCs) have emerged as a promising approach to quantum machine learning, since they utilize the natural dynamics of quantum systems for data processing and are simple to train. Here, we consider $n$-qubit quantum extreme learning machines (QELMs) with initial-state encoding and continuous-time reservoir dynamics. Applying the Pauli transfer matrix (PTM) formalism reveals the encoding-generated features and their linear transformation by quantum channels, and thereby provides a nonlinear vector autoregression model as an interpretable classical representation of a QELM. We show that the nonlinear information processing capacity of a QELM factorizes into the ability of the encoding to represent a given target function and the decodability of the relevant Pauli features after the effective PTM. Comparing geometric and statistical decodability reveals features that are algebraically hidden yet recoverable through data correlations. We relate the decodability of Pauli features to the spreading of measurement operators under Heisenberg evolution (Krylov growth). Focusing on the unitary channel, we discuss how structured Hamiltonians, when paired with certain observables, can impair model performance, as reflected in a low rank of the readout and the effective PTMs. We trace this effect to Hamiltonian symmetries and derive asymptotic rank estimates for symmetry-resolved observable families. Our decodability analysis disentangles the contributions of encoding, reservoir dynamics, and measurement observables, and thus provides interpretable diagnostics that can inform the design of QELMs and reduce reliance on exhaustive hyperparameter search. As a specific application, we consider forecasting nonlinear dynamical systems and show that the readout of a trained QELM closely matches the expression of the underlying flow map at leading orders.

quant-ph · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35679

CounterFlow: Target-Conditioned Flow Matching for Visual Counterfactuals

Paul Sevellec, Elisa Fromont, Romaric Gaudel, Laurence Roze, Paul Viallard, Laetitia Houeix

原文摘要

In eXplainable AI, counterfactual explanations have gained significant traction by offering users direct, intuitive, and actionable insights into model decisions. We introduce CounterFlow, a novel framework based on Conditional Flow Matching that generates visual counterfactual explanations by directly steering a source image toward a user-specified target class. By leveraging target-conditioned vector fields, CounterFlow identifies highly realistic semantic modifications while requiring substantially lower computational overhead than traditional GAN- or diffusion-based architectures. Empirical evaluations on standard benchmarks demonstrate that CounterFlow achieves state-of-the-art performance in both visual realism and target class switching. By working directly in the raw pixel space, CounterFlow offers a more practical solution for real-world deployment.

cs.LG · cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2503.16089

Query-Efficient Fixpoints of $\ell_p$-Contractions

Sebastian Haslebacher, Jonas Lill, Patrick Schnider, Simon Weber

原文摘要

We prove that an $ε$-approximate fixpoint of a map $f:[0,1]^d\rightarrow [0,1]^d$ can be found with $\mathcal{O}(d^2(\log\frac{1}ε + \log\frac{1}{1-λ}))$ queries to $f$ if $f$ is $λ$-contracting with respect to an $\ell_p$-metric for some $p\in [1,\infty)\cup\{\infty\}$. This generalizes a recent result of Chen, Li, and Yannakakis [STOC'24] from the $\ell_\infty$-case to all $\ell_p$-metrics. Previously, all query upper bounds for $p\in [1,\infty) \setminus \{2\}$ were either exponential in $d$, $\log\frac{1}ε$, or $\log\frac{1}{1-λ}$. Chen, Li, and Yannakakis also show how to ensure that all queries to $f$ lie on a discrete grid of limited granularity in the $\ell_\infty$-case. We provide such a rounding for the $\ell_1$-case, placing an appropriately defined version of the $\ell_1$-case in $\textsf{FP}^{dt}$. To prove our results, we introduce the notion of $\ell_p$-halfspaces and generalize the classical centerpoint theorem from discrete geometry: for any $p \in [1, \infty) \cup \{\infty\}$ and any mass distribution (or point set), we prove that there exists a centerpoint $c$ such that every $\ell_p$-halfspace defined by $c$ and a normal vector contains at least a $\frac{1}{d+1}$-fraction of the mass (or points).

cs.CC · cs.CG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36009

DuplexTune: Coupled-State Replay for Memory-Efficient Mixture-of-Experts Adaptation

Paul Raj, Simon Caldwell, Daniel Whitmore, Mutlu Mete

原文摘要

Sparse expert execution does not remove the stored states needed to adapt a mixture-of-experts language model. We present DuplexTune, a framework for replaying coupled hidden states through pretrained attention and expert modules. Trainable width bridges connect two residual streams to the backbone. Bridge warm-up precedes backbone adaptation, with router weights kept frozen. We analyze the implicit state-recovery equation and identify the convergence and replay conditions needed for reconstruction. On Qwen1.5-MoE-A2.7B, the single-H800 evaluation reports 38.8 GB peak memory, versus 64.8 GB for supervised fine-tuning with checkpointing, and throughput of 25.1 versus 19.9 samples/s. DuplexTune achieves 67.2% MMLU, 75.6% GSM8K, and 7.69 MT-Bench, with a weaker multilingual score than the checkpointed baseline. The results characterize a configuration-dependent tradeoff among state storage, throughput, and adaptation quality.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.14386

CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents

Maxime Heuillet, Sharadind Peddiraju

原文摘要

Enterprise data science and analytics spans closed-ended information extraction with verifiable answers and open-ended insight discovery. Agents are evaluated on one or the other, so there is no evidence on whether one system can serve both. We present \texttt{CIPHER}, a data science agent built on a Decoupled Exploration--Selection (DES) framework that applies test-time scaling at the plan level: generating $N$ candidate analysis plans, selecting $M{<}N$ for parallel execution, and aggregating the results. We evaluate $48$ distinct design choices for the DES framework (spanning generation, selection, budget and aggregator capacity) jointly on $357$ tasks from Infi-DA-Bench (closed-ended) and InsightBench (open-ended), on a proprietary and an open-weights base model. A single zero-tuning configuration is competitive against purpose-built specialist baselines under matched models, within $1.2$pp of \texttt{DataWise} and $1.3$pp of \texttt{Agent-Poirot}. The joint sweep exposes that generation and aggregation are the most influential performance levers, while random selection --- the only strategy with zero overhead --- matches its tuned alternatives. These results offer new insights on the design of test-time scaling strategies, and on how a fixed inference budget is best allocated across them, for agents deployed on enterprise analytics workloads.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31489

An Improved Bound for Testing $k$-Colorability

Bangjie Xu

原文摘要

We study the sample complexity of testing $k$-colorability in the dense graph model. A graph is $\varepsilon$-far from being $k$-colorable if at least $\varepsilon n^2$ edge deletions are required to make it $k$-colorable. We prove that a uniformly random induced subgraph on $O(k\log k/\varepsilon)$ vertices is non-$k$-colorable with probability at least $2/3$ whenever the original graph is $\varepsilon$-far from $k$-colorable. The proof combines a palette-based coloring process with a container-style encoding-and-reconstruction argument. This yields $O(k\log k/\varepsilon)$, which is no worse than the previous state of the art $O(k\log (1/\varepsilon)/\varepsilon)$ throughout the nonvacuous parameter range, and is an improvement when $\log k=o(\log(1/\varepsilon))$. For each fixed $k$, combining this upper bound with the known $Ω(\log k/\varepsilon)$ lower bound gives $Θ(1/\varepsilon)$ dependence on $\varepsilon$.

cs.DM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35671HF 社区推荐

Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks

Yao Huang, Zhiyuan Zeng, Yu Wang, Zhitong Zhu, Dingcheng Duan, Hao Li, Shangzhi Xu, Yifan Wang 等 17 位作者

原文摘要

As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are routinely accompanied by comprehensive system cards, open-weight models receive less scrutiny regarding frontier risks. To address this gap, we present an independent safety evaluation of DeepSeek V4.1 Flash-1017, the latest version of V4.1 Flash that departs from V4 with a new architecture, scaled-up training, and strong agentic capabilities. Drawing on the EU General-Purpose AI Code of Practice, we evaluate the model across 34 benchmarks, including 5 in-house suites, spanning evaluation integrity, loss of control, and harmful manipulation. Conforming to the AEF-1 standard, we compare V4.1 Flash-1017 against V4.1 Flash, earlier DeepSeek V4 models, and leading closed-source systems (GPT-6 Astra, GPT-5.6 Sol, and Gemini 3.8 Flash). Overall, V4.1 Flash-1017 shows substantial safety improvements over the V4 generation and approaches or matches leading closed-source baselines on several dimensions, while still exhibiting notable behaviors that warrant continued attention. Building on our findings, we highlight three key observations and recommendations. First, because safety can shift and even regress across minor updates, developers should integrate safety evaluation into incremental releases. Second, as final-turn outputs and end-state checks alone cannot reliably detect loss-of-control behaviors, deployments require process-level observability across both reasoning traces and action logs. Third, because public benchmarks elicit strong evaluation awareness and face data contamination risks, developing private benchmarks is essential for trustworthy frontier evaluation.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35670

Continuous-Time Safe Planning and Control for Agile Quadrupeds

Gage MacLin, Mason Peterson, Camilla Tabasso, Venanzio Cichella, Joshua Migdal, Tye Brady, Taskin Padir

原文摘要

Agile quadruped navigation in dynamic environments demands trajectories that are both dynamically feasible and provably collision-free. Most real-time planners achieve tractability through a convex reduction that requires simplified kinematic models, discarding motion that the robot can readily execute, and certify safety only at discretization points, leaving open possible inter-sample collisions with moving obstacles. We present a real-time motion planning framework that retains the fully-actuated $SE(2)$ model of a quadruped, with its anisotropic, heading-coupled velocity bounds, and accepts the resulting nonconvexity. By parameterizing trajectories as composite Bernstein polynomials, we exploit the convex hull property to certify collision avoidance and the input bounds over the entirety of each planning horizon. Solved at online replanning rates, the optimization runs in closed loop, commanding body velocities to the locomotion controller. We validate the approach in simulation against ablations and external baselines, and in hardware experiments on a quadruped navigating among unknown moving obstacles, recovering both lateral and heading-coupled motion that simplified models exclude.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.04325

On the Architectural Complexity of Neural Networks

Nicholas J. Cooper, François G. Meyer, Michael L. Roberts, Carlos Zapata-Carratalá, Lijun Chen, Danna Gurari

原文摘要

We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.

cs.LG · cs.DM · math.CO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36008

Practice Makes Perfect: Tacit Knowledge, Generative AI, and Returns to Schooling and Experience

Eduardo Levy Yeyati, Darío Judzik, Juan Ignacio Barbiero

原文摘要

Generative AI changes the scarcity of different forms of human capital. It makes codified knowledge cheaply available at the point of production, while judgment acquired through practice remains tied more closely to the worker. We ask what this does to two familiar prices in the wage structure: the return to schooling and the return to experience. In a short-run framework, machine-supplied codified knowledge substitutes directly for the codified component of worker human capital, lowering the schooling gradient. If codified and practice-based knowledge are complements, the return to experience rises where learning through practice is fastest; technology-specific experience can also become obsolete, rotating the experience profile rather than shifting it uniformly. Using US Current Population Survey earnings data from 2018 through June 2026, we compare occupations in the top and bottom quartiles of the pre-ChatGPT Felten-Raj-Seamans exposure index. After the public release of ChatGPT, the return to a year of schooling falls by 0.55 log points in exposed occupations. The return to a year of experience rises by 0.26 log points at three years of potential experience, is unchanged at fifteen, and falls by 0.12 log points at twenty-five; under the baseline quadratic, the effect crosses zero at 18.1 years. These breaks appear with the release, disappear under a pandemic placebo, survive a common censoring rule across the full sample, and remain when each occupation is allowed its own pre-shock schooling and experience gradients. The pattern is a repricing of human capital inside exposed occupations: codifiable knowledge becomes less scarce, while the value of experience depends increasingly on whether it transfers to the new technology.

econ.GN · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35663

SCAFFOLD under Hessian Similarity: Sharp Convergence Rates

Zhirayr Tovmasyan, Slavomír Hanzely, Egor Shulgin, Peter Richtárik, Sebastian U. Stich

原文摘要

One of the main challenges of federated learning is heterogeneous data split among the clients, leading to biased local updates called client drift. The SCAFFOLD algorithm (Karimireddy et al., 2020) corrects client drift with control variates, but its relation to the similarity of client data is not yet fully understood: the original similarity-based guarantees cover only quadratics with a stronger second-order similarity assumption, and a follow-up weakly convex analysis (Luo et al., 2025) obtains a $\sqrt{Lδ}$ dependence for $L$-smooth losses with averaged Hessian similarity $δ$. We analyze SCAFFOLD with minibatch-based control variates and establish linear dependence on Hessian similarity beyond quadratics, for both convex and nonconvex objectives. In particular, for convex objectives with exact gradients, $R$ SCAFFOLD rounds with $K$ local steps lead to an objective gap of order $(L/K+δ)D_0^2/R$, where $D_0$ is the initial distance to a minimizer. When $K=Θ(L/δ)$, it improves the minibatch SGD rate by a factor $Θ(L/δ)$. For nonconvex objectives, we prove an analogous stationarity guarantee under uniform Hessian similarity for a client-selection variant. In both settings, we extend these guarantees to stochastic gradients and prove matching lower bounds for the analyzed methods with constant local stepsizes. We also show that, under partial participation, even identical clients need not obtain the full communication benefit of additional local steps.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36006

MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine

Simon A. Lee, Jiahang Sha, Moonseong Jeong, Yunbei Pan, Jeffrey N. Chiang

原文摘要

System One decision models such as Jev answer structured questions in a single forward pass without generating text, offering fast and computationally efficient clinical decision support. We evaluate MedJev, an open System One model that runs locally on a laptop, across ten medical benchmarks spanning medical knowledge, diagnosis, and patient level prediction using MIMIC IV and MIMIC IV ED. We compare MedJev against zero shot LLM baselines, published GPT results, and supervised models. MedJev achieves accuracies of 72.5 percent on MedQA, 75.4 percent on USMLE, and 80.1 percent on NEJM, approaching published GPT 4 performance while maintaining well calibrated confidence estimates (ECE 0.028 to 0.063). On patient level tasks, MedJev achieves an AUROC of 0.926 for In Hospital Mortality, exceeding XGBoost (0.902), but underperforms supervised models on operational outcomes such as ED Triage Admission (0.745 vs. 0.809). Patient level predictions also exhibit substantial miscalibration (In Hospital Mortality ECE 0.286). We introduce a lightweight, two parameter recalibration method that adapts predictions to local patient populations using 50 to 200 labeled examples, reducing ECE to 0.007. Our findings establish open System One models as a promising zero shot baseline for medical AI, combining competitive predictive performance with low computational cost and efficient local calibration. We release our code and evaluation harness to support future research.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2410.11389

The Qualitative Collapse of Concurrent Games (Extended Version)

Pierre Clairambault

原文摘要

In this paper, we construct an interpretation-preserving functor from a category of concurrent games to the category of Scott domains and Scott-continuous functions. We give a concrete description of this functor, extending earlier results on the relational collapse of game semantics. The crux is an intricate combinatorial lemma allowing us to synchronize states of strategies which reach the same resources, but with different multiplicity. Putting this together with the previously established relational collapse, this provides a new proof of the qualitative-quantitative correspondence first established by Ehrhard in his celebrated extensional collapse theorem. Whereas Ehrhard's proof is indirect and rests on an abstract realizability construction, our result gives a concrete, combinatorial description of the extraction of quantitative information from a qualitative model.

cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35659

Environment Edits as a Corrective Signal for Reward Learning

Isaac Ngui, Courtney McBeth, Nancy M. Amato

原文摘要

Robot corrections allow people to adjust a robot's behavior, but a single correction changes many features. Also, preferences about object attributes and relationships between objects cannot be expressed by moving the robot. We propose environment edits as a complementary form of feedback. The robot's motion is held constant as the human edits the scene, so the only explanation for the edit is the moved object. We introduce Feature Learning from Environmental and Robot-Relational Edit Traces (FERRET), which learns preferences from both robot and environment corrections. We show that environment edits are able to disambiguate features and learn preferences that robot corrections alone cannot.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.35744

FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents

Hoyoung Lee, Suyeol Yun, Jack Haverty, Yunju Cho, Meesong Kim, Daekyung Park, Sumin Kim, Jihoon Kwon 等 20 位作者

原文摘要

Evaluating finance research agents requires rubrics that reflect expert standards and fix the values correct as of an information cutoff. Expert-reviewed finance benchmarks rely on fixed, per-item rubrics, which are costly to extend and cannot encode each institution's own standard. In FinAutoRubric, experts specify reusable evaluation guidance, while agents and code carry out query-specific rubric generation, review, and validation. This expert guidance governs every agent, as prompts and as rules that code enforces, and a Task Bank of reusable criteria carries it across tasks. In long-horizon loops that follow the expert guidance, a writer agent researches every expected value and a reviewer agent verifies it, and failures escalate to a human. On three expert-authored finance benchmarks, its rubrics track expert scoring as closely as the strongest evaluated generator while stating the expert rubric's expected value for more criteria, their scores agree with human grading, and in-house analysts prefer them in a blind review. The released 100-query FinAutoRubric Benchmark, built from in-house analysts' key questions across 78 tasks and eight asset classes, shows that rubrics from an earlier model generation still leave headroom for a later one.

cs.AI · q-fin.CP

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35656

Provably Efficient Q-learning for Robust Reinforcement Learning

Yuchen Jiao, Gen Li

原文摘要

Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on robust MDPs (RMDPs) have been proposed, for ensuring that agents can perform reliably to unpredictable conditions in real-world environments. Despite of the rich literature, \revision{an efficient model-free method is still lacking} for robust RL, particularly for Markovian data, which is more relevant in practical applications. In this work, we take a step towards settling this problem by proposing a sample efficient (asynchronous Q-learning) algorithm for robust RL. In particular, consider a $γ$-discounted infinite-horizon RMDP with state space $\mathcal{S}$ and action space $\mathcal{A}$, where the uncertainty set is specified by the total variation (TV) distance with uncertainty level $σ$. Assuming access to a single trajectory of Markovian samples induced by a behavior policy and the nominal transition kernel, the sample complexity of the proposed Q-learning algorithm --- to achieve an entrywise $\varepsilon$-approximation of the optimal Q-function --- is bounded by $$ \frac{1}{μ_{\mathsf{min}}\varepsilon^2(1-γ)^3\max\{1-γ,σ\}} + \frac{t_{\mathsf{mix}}}{μ_{\mathsf{min}}(1-γ)} $$ up to logarithmic factors. Here, $t_{\mathsf{mix}}$ and $μ_{\mathsf{min}}$ denote the mixing time and the minimum state-action occupancy probability of the sample trajectory, respectively. This result is nearly minimax optimal, with an additional factor of $\frac{1}{1-γ}$. Moreover, it achieves a significant improvement over existing bounds.

stat.ML · cs.AI · cs.LG · math.ST

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30913

Prompt PerturbAItions: Mechanisms of LLM Response Inconsistencies

Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar, Joshua Chen, Yian Wang, Navin Kumar, Hari Sundaram, Eshwar Chandrasekharan 等 9 位作者

原文摘要

Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic, yet less is known about whether such lexical variation in otherwise semantically equivalent prompts can degrade factual reliability. We study how lexical and tone-based prompt perturbations affect the factual reliability of LLMs. Using controlled prompt variations spanning polite, random, and increasingly toxic levels, we evaluate seven LLMs on ARC-Easy, GSM8K, and MMLU. We find that lexical perturbations reduce factual accuracy and increase predictive uncertainty in most models. Interestingly, increasing toxicity results in decreasing accuracy. To examine whether these answer inconsistencies correspond to internal changes, we conduct attribution-graph analyses of model activations and influences. We find that perturbations amplify perturbation-sensitive variant nodes relative to core reasoning nodes. We also observed a monotonic trend with increasing toxicity score and increasing activation and influence in Variant nodes. These findings position prompt wording and tone as a critical dimension of LLM reliability and provide behavioral and mechanistic evidence that surface-level lexical variation can alter factual outputs and internal computation.

cs.CL · cs.AI · cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35652

Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel

Jayoung Ryu, Kyunghyun Cho, Romain Lopez

原文摘要

Many high-throughput scientific experiments produce distributional outputs, requiring conditional generative models to interpret the data, and to predict outcomes at new inputs. Acquiring experimental data at new conditions (e.g., for a new antigen or a new cell type) is often expensive, motivating the need for automated experimental design methods. However, existing active learning frameworks are limited as they assume scalar or vector-valued outputs. We first show that the Wasserstein test risk of a conditional generative task decomposes into a mean term and a shape term, demonstrating why mean-based active learning is blind to distributional shape. To capture both, we propose the transport Neural Tangent Kernel (tNTK), a tractable kernel that measures how sensitive a generative model's predicted distribution is with respect to its parameters. The tNTK recovers the standard NTK in the deterministic limit and upper-bounds the posterior Fréchet variance of the prediction under small parameter perturbations. It admits a closed-form expression for affine Gaussian transport and tractable Monte Carlo estimators otherwise. Treating the tNTK as the covariance function of a Gaussian process, we greedily select inputs that minimize the total GP posterior variance across the pool, yielding a distribution-aware active learning strategy. We evaluate this strategy across four classes of conditional generative models, including conditional flow matching and conditional Monge gap, on synthetic distributions, intent-labeled sentences, and single-cell perturbation responses. In these experiments, the tNTK outperforms the baseline NTK computed from the conditional mean, demonstrating the value of distribution-aware active learning for generative-modeling tasks.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35650

FLOWSTEP: A Framework for Learning to Predict GitHub Actions Workflow STEPs

Jiangnan Huang, Bin Lin, Yutaro Kashiwa

原文摘要

Continuous Integration and Delivery (CI/CD) are fundamental to modern software development, yet configuring pipelines such as GitHub Actions (GHA) workflows remains complex and error-prone. Recent work has explored Transformer-based models for GHA workflow recommendation, but existing approaches typically model workflow steps as a single homogeneous generation task. This formulation overlooks a key distinction: reusable Actions are structured, ecosystem-level components, whereas project-specific Scripts encode local build, test, and deployment semantics. Consequently, current models struggle to capture the different forms of knowledge required for accurate workflow completion. In this work, we present FLOWSTEP, a framework for GHA workflow step completion that explicitly distinguishes between Action and Script generation. FLOWSTEP combines large language models (LLMs) with contrastive learning to better capture semantic relationships among workflow contexts, Actions, and Scripts. Evaluated on established benchmarks, FLOWSTEP improves end-to-end workflow step prediction accuracy from 38.23% to 51.09%. Beyond prediction accuracy, we further study whether LLM-as-a-judge can provide a more semantic evaluation of generated workflow steps. By comparing LLM-based assessments with human annotations, we find that the best-performing model configuration reaches substantial agreement with human ground truth (Krippendorff's alpha = 0.701), suggesting that LLM-as-a-judge can serve as a scalable complement to manual evaluation.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.06542

Recovering topological information of light by topological learning

Benquan Wang, Trishita Das, Yuhan Peng, Tatjana Kleine, Shanshan Chang, Jinhui Chen, Nilo Mata-Cervera, Chunyu Li 等 11 位作者

原文摘要

The evolution of modern-day communication networks towards enhanced capacity and robustness is driving interest in topological light wave as a next-generation information carrier. However, harnessing its potential is hindered by the lack of an effective topological reader, particularly when strong disorder renders conventional readout intractable. Here we address this by introducing TOPO$^{2}$, an artificial intelligence framework that leverages on topological learning to recover topological information from light. We demonstrate it on highly distorted optical fields with embedded Skyrmion topologies, showing that we can extract the topological numbers in a single shot with just a conventional camera. We showcase its capability in a TOPO$^{2}$-based communication scheme, sending and recovering information encoded in a topological alphabet, confirming that it outperforms conventional approaches. Our connection of topological photonics with topological AI as a powerful paradigm for robust high-capacity information encoding and processing opens a new path towards topological information optics.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.08424

Generalized Wasserstein Flow Matching: Nested Couplings for Point Cloud Generation

Moritz Piening, Richard Duong, Gabriele Steidl

原文摘要

We formulate flow matching on probability measures over probability measures. Directly from the Wasserstein-on-Wasserstein (WoW) continuity equation, we show that admissible nested outer and inner couplings induce a valid metameasure flow and non-local velocity field. Validity requires neither optimal plans nor a smooth manifold. Practically, this opens up the design space of multisample flow matching: exact Wasserstein plans are distinguished by energy and straightness, while sliced and lazy linear plans yield scalable alternatives. Point-cloud experiments, including controlled Bures-Wasserstein and Euclidean minibatch baselines, demonstrate the resulting geometry-cost trade-off.

cs.LG · math.OC · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35649

RLNC vs Reed-Solomon in Satellite Channels: Crossover Analysis and the Bridging Property

Angeline Szczepanski, Vipindev Adat Vasudevan

原文摘要

Satellite communication systems are increasingly relied upon for connectivity in remote areas and are expected to play a pivotal role in 6G networks, operating under high round-trip times and packet loss where forward error correction is essential. This work evaluates Reed-Solomon (RS) coding, Random Linear Network Coding (RLNC), and a combined RS+RLNC hybrid over a three-hop satellite channel whose loss statistics are derived from orbital geometry and link-budget calculations rather than assumed, comparing RS and RLNC at matched code rates of 0.800. The central finding is the \emph{bridging property} of RLNC: every RS code rate collapses above a crossover threshold $p^*$, while RLNC operates continuously through all failure regions with overhead growing as $1/(1-p)$. At rate~0.800, $p^* \approx 0.21$. Under the derived satcom channel with mean burst duration 166~minutes, RS$(255,204)$ is impractical despite an average loss rate of 1%, while RLNC requires 15.5~Mbit to recover all 1000 packets. An RS+RLNC hybrid reduces overhead by 19% relative to pure RLNC at BER$=10^{-3}$. To the authors' knowledge, this is the first analytical derivation of the rate-normalised crossover $p^*$ between RS and RLNC and the first experimental confirmation of the bridging property under a physically derived satellite channel model.

cs.NI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.15465

Building a Dataset for Music Sample Identification

R. Oguz Araz, Xavier Lizarraga, Xavier Serra, Dmitry Bogdanov

原文摘要

Sample identification (SI) is the task of matching an element of a musical work to its musically transformed versions used to create new works. The task has received little attention and lacks large-scale publicly available data. In this work, we mine sampling annotations from a music database and split them for training and evaluation. The resulting dataset is nearly three orders of magnitude larger than the existing SI benchmarks, with training, validation, and test sets of 114 k, 6 k, and 10 k tracks. We find that naively splitting the annotations places the same tracks in different sets. To avoid this, we construct a graph from the annotations and split it over connected components. We further find that a single mega-component contains half of the annotations, making component-wise splitting incompatible with balanced splits; we trim it, yielding a leakage-aware pipeline. We share the dataset for non-commercial scientific research purposes only and make the data-analysis and splitting code publicly available. We hope that our work fosters research on SI.

cs.SD

查看论文
arXiv ↗PDF ↗