跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 17:39 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 17:40 — 2026-11-08 17:40（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-08 17:39最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 17:37（北京时间）
新论文 · v1arXiv:2611.02121

Conditional Calibration Contracts under Coupled Load: A Branch-Aware Audit of Switched Inference

Juan S. Santillana

原文摘要

Bursty serving changes both queue states and the population selected for each model. We study conditional calibration contracts as a specification to be validated, rather than a certified property of an existing router. CA-MHD combines load-coupled distillation, closed-loop replay and a cost-informed Schmitt router in a discrete-event simulator with a hardware service table. Across 40 cells (ten training seeds and four content-load coupling levels), we distinguish the original teacher, frozen wide heads on an adapted trunk, and the narrow student. A common teacher-trajectory audit has median absolute student-teacher deficit 0.06 percentage points, but does not certify the student-selected deployment support. Historical results use a kernel correctness gap, not the published SmoothECE; we separately prove selected-branch composition for a residual functional at a common fixed scale. The deployed wide branch has lower ordinal accuracy than the original teacher in all 40 cells. Same-checkpoint student-only serving has lower historical ordinal gap in 27/40 cells; routing also exposes violation tails up to 17.5 percent. Student p99 latency remains above the 1.5 ms target. Retrospective temporal recalibration improves the ordinal gap in 39/40 cells, but causal delayed-label availability is unverified and no incremental per-mode benefit is detected after multiplicity adjustment. An in-sample CUSUM detects 30/40 checkpoint changes at five historical false alarms, with no prospective false-alarm guarantee. These findings support a branch-aware audit and a scoped negative result, not demonstrated routing superiority. Independent budgets, selected-support validation and net utility under a satisfied SLA remain open.

cs.LG · cs.CL · cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.27144

Learning Risk Scores Robust to Unobserved Confounders

Ryan Edmonds, Yingxiao Ye, Sina Aghaei, Andrés Gómez, Çağıl Koçyiğit, Phebe Vayanos

原文摘要

We consider the problem of learning risk scores to prioritize individuals for scarce resources or interventions, from historical observational data affected by unobserved confounding. Decisions about who receives scarce resources are often guided by risk scores based on recorded characteristics, such as responses to a survey. These risk scores are increasingly being learned directly from observational data: historical records of individuals' characteristics, allocation decisions, and outcomes. Standard methods such as inverse propensity weighting (IPW), which corrects for the bias introduced by the historical allocation policy, can be used to learn accurate risk scores if the historical decision process is fully explained by the recorded characteristics. In practice, however, historical decisions often depend on unrecorded information, causing learned risk scores to systematically under-prioritize exactly the individuals whose unrecorded circumstances drove past prioritization. We propose a method for learning risk scores that are robust to this kind of unobserved confounding, building on IPW. Since propensity weights cannot be reliably estimated under unobserved confounding, we instead treat them as belonging to an uncertainty set determined by the observable data and domain-informed estimates of the degree of confounding, combining sensitivity analysis from causal inference with Wasserstein distributionally robust optimization. The resulting robust risk score learning problem admits a sample-based approximation that we reformulate as an exponential cone program compatible with off-the-shelf solvers. We demonstrate the effectiveness of our approach on semi-synthetic data derived from datasets in the UCI Machine Learning Repository. Our method improves calibration by up to 29.2% over traditional benchmarks and up to 11.1% over the state of the art, without compromising other metrics.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02114

CNN-Based Retinal OCT Classification: Research Gap Analysis and a From-Scratch Baseline, ED126-A

Shkelqim Sherifi

原文摘要

Automated classification of retinal pathologies from Optical Coherence Tomography (OCT) images remains challenging because diagnostically relevant morphological patterns may exhibit substantial inter-class similarity. Although high classification accuracies have been reported on benchmark OCT datasets, cross-study comparison is limited by heterogeneous evaluation protocols and by the limited characterization of compact convolutional neural network (CNN) baselines trained from random initialization. This study addresses this gap through two contributions. First, it provides a focused review of CNN-based retinal OCT classification and identifies methodological considerations relevant to controlled benchmarking. Second, it presents ED126-A, a purpose-built four-class CNN baseline trained from scratch under a documented experimental protocol on the Kermany labeled OCT dataset. The model contains 1,241,380 total parameters, including 1,239,460 trainable parameters, and is evaluated using training-dynamics analysis, class-wise performance metrics, confusion-matrix analysis, confidence analysis, t-SNE representation-space visualization, Grad-CAM, hierarchical feature-map analysis, and one-vs-rest ROC/Precision-Recall analysis. On the image-level held-out test set, ED126-A achieved 95.03% accuracy, with a macro-F1 of 0.9205 and a weighted-F1 of 0.9521. The principal class-conditional limitation occurred for Drusen, which attained a recall of 0.9605 but a precision of 0.7493 and an F1-score of 0.8419. The confusion matrix identified Normal to Drusen and CNV to Drusen as major error channels. These results support the use of ED126-A as a documented from-scratch reference baseline and provide an empirical basis for controlled evaluation of transfer learning, increased depth, attention, multi-scale feature fusion, and calibration in subsequent studies.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02112

Order-Only On-Policy Distillation

Guangzeng Han, Yu Wu, Xiaolei Huang

原文摘要

On-policy distillation (OPD) trains a student on its own generations by matching the teacher's token probabilities. These probabilities entangle two kinds of information: which tokens the teacher prefers, and how confident it is. The latter reflects the teacher's own capacity and calibration, which a smaller student may be unable to reproduce. Because the teacher temperature changes these values without changing the ordering, OPD is also sensitive to the temperature choice. We ask whether the teacher's ordering of candidate tokens is enough, and propose Order-Only On-Policy Distillation (O$^{3}$PD). At each student-generated prefix, O$^{3}$PD trains the student to reproduce the order of the teacher's top-$K$ tokens, without fitting their probability values. The objective is therefore invariant to the teacher temperature and needs no temperature tuning. Across six teacher--student pairs, O$^{3}$PD outperforms OPD on the average over HMMT25, AIME24, and AIME25 in every pair, by up to 2.9 points, with gains of up to 5.6 points on AIME25. Other ranking losses yield similar gains, so the benefit comes from ordinal supervision itself. Analysis shows that O$^{3}$PD departs further from the teacher's probabilities than OPD, yet reproduces its ranking more faithfully and yields a stronger student. The ranking, not the probability values, thus carries the knowledge that on-policy distillation needs to transfer.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.02626

Learning Better Certified Models from Empirically-Robust Teachers

Alessandro De Palma

原文摘要

Adversarial training attains strong empirical robustness to specific adversarial attacks by training on concrete adversarial perturbations, but it produces neural networks that are not amenable to strong robustness certificates through neural network verification. On the other hand, earlier certified training schemes directly train on bounds from network relaxations to obtain models that are certifiably robust, but display sub-par standard performance. Recent work has shown that state-of-the-art trade-offs between certified robustness and standard performance can be obtained through a family of losses combining adversarial outputs and neural network bounds. Nevertheless, differently from empirical robustness, verifiability still comes at a significant cost in standard performance. In this work, we propose to leverage empirically-robust teachers to improve the performance of certifiably-robust models through knowledge distillation. Using versatile feature-space distillation objectives, we show that distillation from adversarially-trained teachers can significantly improve the performance of state-of-the-art certified training algorithms for ReLU networks on robust computer vision benchmarks.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02109

Wideband Microwave Linear Analog Computer (MiLAC) for Frequency-Flat and Frequency-Selective Processing

Juan Vidal Alegría, Matteo Nerini, Bruno Clerckx

原文摘要

Microwave linear analog computer (MiLAC) has been proposed as an analog processing architecture to perform efficient computation in the microwave domain. Consisting of reconfigurable impedance networks, a MiLAC can extract many of the gains of large multi-antenna systems without costly digital processing, e.g., achieving capacity in narrowband multiple-input single-output (MISO). However, the behavior of wideband MiLAC, required to support high data-rate transmissions, is widely unknown. The impedance components of MiLACs have non-trivial frequency-dependent response, requiring specific implementations to characterize it. In this work, we consider MiLAC implementations based on LC resonators with tunable capacitance, which allow synthesizing near-arbitrary passive lossless impedance matrices at individual frequencies using inductors and varactors. We characterize the mapping between optimal MISO precoding at a reference frequency, and the vector of capacitances configuring the MiLAC. We derive the degrees of freedom (DoFs) remaining after fixing such optimum precoding at the reference frequency, and show that these DoFs can be exploited to tune the frequency response of the MiLAC. We propose two techniques to exploit these DoFs: a closed-form approach for frequency-flat MiLAC processing, and a numerical approach for multi-frequency MiLAC processing, optimizing processing at frequencies other than the reference one. The frequency-flat approach shows satisfactory performance in a simulated frequency-flat millimeter-wave scenario, approaching the performance of digital processing. The multi-frequency approach can adapt to the frequency-selectivity of a simulated sub-6GHz scenario, attaining gains over frequency-flat digital processing. This constitutes the first demonstration that realistic MiLAC implementations can be configured to perform independent computations at different frequencies.

cs.IT · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.17439

InTAct: Interval-based Task Activation Consolidation for Continual Learning

Patryk Krukowski, Jan Miksa, Piotr Helm, Jacek Tabor, Paweł Wawrzyński, Przemysław Spurek

原文摘要

Continual learning seeks to acquire new knowledge while preserving previously learned representations. Despite the success of prompt-based methods, they remain fragile in domain-incremental learning scenarios, where shifts in the input distribution cause representation drift in shared layers and lead to forgetting. We introduce InTAct, a method that preserves functional behavior in shared representations without freezing parameters or retaining past data. InTAct constrains updates within activation regions associated with prior domains, while allowing flexible adaptation elsewhere, thereby stabilizing neuron functionality rather than directly restricting parameter values. The approach is architecture-agnostic, integrates seamlessly with existing prompt-based frameworks, and matches or outperforms state-of-the-art methods on domain-incremental benchmarks.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02108

Capable but Not Scalable: Requirements and Interaction Costs of Building Multi-View CAD Datasets for Design Research

Danyal Sarfraz, SeEun Lee, Ulugbek Vahobjon Ugli Ismatullaev, JoungHyun Kim, Abdurakhimov Donierbek, KwanMyung Kim

原文摘要

Transforming CAD models into consistent multi-view image datasets is increasingly important for AI-driven product design research, yet existing workflows can impose substantial burdens on researchers without programming expertise. We examine this challenge from a human-computer interaction (HCI) perspective by analyzing ten reported rendering practices and deriving fourteen requirements spanning dataset quality, visual consistency, and user interaction. We then assess eleven development- and design-oriented tools against an illustrative task involving STEP models, interpreting potential interaction costs through the cognitive dimensions framework. Our analysis reveals a gap between technical capability and practical scalability: programming-based frameworks offer flexible automation but require coding expertise, while graphical design tools provide accessible functionality yet retain repetitive per-product operations. No assessed workflow combines a low programming threshold, low repetition viscosity, and flexible protocol configuration. Based on these findings, we propose design directions including reusable rendering presets, collection-wide previews and corrections, mixed-initiative orientation assignment, and automatic provenance recording. This work reframes CAD dataset generation as an end-user interaction design problem and establishes requirements for more accessible, scalable dataset creation tools.

cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02107

ZT-DAC: ML-Driven Dynamic Access Control Policy for Zero Trust in DER Networks

Arun B. Chandrasekaran, Damilola Popoola, Souradeep Bhattacharya, Manimaran Govindarasu

原文摘要

The increasing penetration of Distributed Energy Resources (DERs) in the smart grid has significantly expanded the cyber-attack surface. Traditionally, DER networks rely on static role-based access control (RBAC) mechanisms that assume persistent trust after authentication. This limitation enables adversaries to maintain unauthorized privileges and move laterally across DER systems, disrupting grid operations. Although attribute-based access control (ABAC) enables fine-grained and context-aware access decisions, it does not fully eliminate implicit trust. Zero Trust (ZT) principles can be incorporated to enhance ABAC policies. This paper proposes a dynamic access control framework for implementing ZT in DER networks (ZT-DAC). The proposed solution employs a two-stage verification process and integrates an Open Policy Agent (OPA)-based RBAC with a machine learning (ML)-based ABAC to enforce continuous and adaptive trust score assessment. To support realistic DER operations, a DER-specific access control model is developed and used to generate a domain-informed dataset of access requests incorporating both legitimate and adversarial behaviors. Experimental results on the dataset show that the OPA-based decision layer achieves \(91.92\%\) accuracy, with a False Positive Rate of \(14.45\%\), while the ML model achieves a Mean Absolute Error of \(2.074\) and an \(R^2\) of \(0.891\) in trust-score prediction. The ABAC layer achieves \(93.27\%\) accuracy, with a FPR of \(3.88\%\), validating its practical feasibility within realistic DER environments.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02105

Faster Semi-Streaming and Dynamic Approximate Maximum Weight Matchings in General Graphs: A Unified Framework

Jiale Chen

原文摘要

We study the $(1-\varepsilon)$-approximate maximum weight matching problem in general graphs with $n$ vertices and integer edge weights in $[1,W]$. For $W=n^{O(1)}$, we obtain faster algorithms in the semi-streaming and dynamic settings: (1) Semi-streaming: Deterministic $O(\varepsilon^{-2})$-pass and $O(\varepsilon^{-2}\log(1/\varepsilon))$-pass algorithms for unweighted and weighted matching. (2) Incremental: A deterministic algorithm for weighted matching processing $m$ edge insertions in total time $O((m\varepsilon^{-3}+n\varepsilon^{-6})\log^3 n)$. (3) Decremental: A randomized algorithm for weighted matching processing all edge deletions from an $m$-edge graph in total time $O((m\varepsilon^{-8}+n\varepsilon^{-47})\log^{O(1)}n)$ with high probability. (4) Fully dynamic: A deterministic reduction from weighted matching in general graphs to unweighted matching in bipartite graphs incurring $O(\varepsilon^{-4}\log^{O(1)}(1/\varepsilon))$ multiplicative update-time overhead, independent of $n$. Underlying these results is a unified framework that reduces the problem to repeatedly solving two simpler matching subproblems: a $(1-\varepsilon)$-approximate maximum weight matching on a sparse subgraph with $O(n/\varepsilon)$ edges, and a constant approximation on the remaining edges. The framework builds on dual entropy regularization, a smoothing technique underlying efficient solvers for packing linear programs. To handle the exponentially many odd-set constraints, we adapt the smoothing technique to regularize only the vertex duals and develop a new cut partition that preserves odd-set feasibility during optimization.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21253

Theoretical guidelines for annealed Langevin dynamics in compositional simulation-based inference

Camille Touron, Gabriel V. Cardoso, Julyan Arbel, Pedro L. C. Rodrigues

原文摘要

Compositional score-based approaches to simulation-based inference (SBI) approximate the posterior over a shared parameter given $n$ independent observations by aggregating individually learned posterior scores: currently, there are two main propositions of such methods (Geffner et al. (2023), Linhart et al. (2026)). As the resulting composite score does not correspond to the score of any distribution along the forward diffusion path of the true multi-observation posterior, sampling from it via a reverse SDE leads to an irreducible bias. Annealed Langevin dynamics provides a principled alternative: it treats the composite score as the genuine score of a sequence of tractable bridging densities and samples from them in succession. When properly tuned, it could lead to a controllable bias. However, its hyperparameters, namely step sizes, the number of steps per level, and the number of annealing levels, have so far been chosen empirically. We derive Wasserstein bounds for annealed Langevin with approximate scores and translate them into explicit decision rules for these hyperparameters that guarantee a prescribed sampling accuracy, while highlighting different theoretical aspects of each composite score formulation. In the Gaussian setting, we obtain closed-form expressions for all relevant quantities and prove that the bridging densities of Linhart et al. (2026) consistently admit larger step sizes and require fewer total Langevin steps than those of Geffner et al. (2023). Furthermore, we show empirically that the tuning obtained in the Gaussian setting generalizes to more complex problems, thus providing a well-understood and theoretically grounded starting point for practitioners using compositional score-based approaches.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.05268

Is the Geometry Doing the Work? An Operating-Point Audit of Hierarchy in Hyperbolic Vision-Language Models

Jaeyoung Kim, EunSeok Kim, Dongsuk Jang

原文摘要

Hyperbolic vision-language models are designed to encode abstraction geometrically: general concepts near the origin, specific ones farther out, and entailment cones representing directed order. We ask whether trained MERU, HyCoCLIP, and PHyCLIP models actually use these mechanisms. We audit seven released checkpoints and matched from-scratch interventions. All audited converged checkpoints remain near-Euclidean in the dimensionless radius $u=\sqrt{c}ρ$: the largest observed image-side value is $0.37$ -- well below $u\approx0.84$, where local metric distortion reaches $10\%$. Releasing the curvature floor changes curvature and norms but not this regime, with mixed, generally modest downstream shifts. Trained entailment cones are saturated or nearly saturated, so low violation rates can arise from trivially wide cones rather than learned order. Preregistered semantic traversal detects weak within-branch order but no operative full-hierarchy readout. Shuffle-controlled tests detect no pair-specific radial ordering in released checkpoints, and no positive result is consistent across all three matched ViT-B seeds. This non-detection is sensitivity-bounded: the diagnostic reaches $80\%$ power only at $\approx13.5$ pp of shuffle-controlled excess, while the largest released gap is $\approx5$ pp. We trace this to a low-curvature shortcut: lowering curvature widens entailment cones and suppresses violations without learning order. In the probed trajectories, gradient decomposition identifies entailment as the dominant curvature-lowering pressure during collapse. Yet curvature contracts even when entailment is removed, so the shortcut is not the sole cause. Under our diagnostics, the audited formulations do not demonstrate an operative radial or cone-based hierarchy. We distill the audit into a five-number geometry report for evaluating future hierarchy claims.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.26350

OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents

Kaicheng Zhang, Wen Ge, Lei Jiang, Weixin Yang, Jordan Langham-Lopez, Jialin Yu, Lukasz Szpruch, Hao Ni

原文摘要

Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial relevance of benchmark tasks is often overlooked. Yet financial workflows are inherently multi-stage, spanning interdependent tasks such as forecasting, strategy construction, risk management, and trading. Existing platforms typically focus on a single task, and can therefore overstate agent competence and fail to reveal weaknesses in generalization, real-market interaction, and financially meaningful decision-making. We introduce OpenFinGym, a unified gym environment for quantitative-finance agent development that covers forecasting, market generation, real-time trading, and fraud detection under a single execution and verification interface. OpenFinGym additionally provides an automated task-construction pipeline that turns quantitative finance publications into executable task packages; a containerised runtime with a host-side verifier service that supports scalable agent rollouts and prevents runtime train-test leakage; a paper trading engine with a low-latency data-stream design; deferred-resolution support for long-horizon and event-market forecasts; and integration for SFT and RL post-training.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02104

Consolidating Reasoning with Test-Time Training

Haotian Wu, Zeming Chen, Hao Zhao, Antoine Bosselut

原文摘要

Effective multi-agent collaboration requires finalizing solutions from reasoning that is distributed across the individual attempts of many agents. However, useful intermediate reasoning can remain unexploited when collaboration is limited to voting on conclusions reached among individual agents, or aggregating long, noisy collections of reasoning trajectories in context. In this work, we propose TTT-Consolidate, a framework that uses multi-agent reasoning trajectories as adaptation data to improve a model's subsequent reasoning. TTT-Consolidate jointly consolidates trajectories into parametric representations through test-time training, then generates a new solution by conditioning on the consolidated information. We meta-learn how to consolidate using bi-level optimization at training time, where an inner loop encodes reasoning trajectories into a lightweight LoRA adapter, and an outer loop learns meta-parameters for the inner loop such that the consolidation is helpful for the model to synthesize a final solution. As no large-scale corpus of diverse reasoning trajectories exists for training aggregation methods, we construct the OpenParallelThinking corpus composed of 12,810 math problems paired with a mixture of trajectories from six LLMs. Evaluated on challenging math and STEM benchmarks, TTT-Consolidate outperforms the best aggregation baselines by up to 20 percentage points, even under matched compute and runtime settings, with the gap widening at larger model scales. TTT-Consolidate also recovers from unsuccessful individual trajectories more robustly, an ability that improves as the number of available (even incorrect) trajectories increases. Finally, we demonstrate that TTT-Consolidate benefits from both SFT and RL-based outer loop objectives. We will release TTT-Consolidate and OpenParallelThinking for use in future work on reasoning aggregation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.00557

NeuroVolve: Evolving personalized visual stimuli toward user-defined brain response targets

Haomiao Chen, Keith W Jamison, Daniel Chong, Yunrui Zhang, Mert R. Sabuncu, Amy Kuceyeski

原文摘要

A central question in neuroscience is what visual features drive brain responses across regions. Classic approaches rely on handcrafted stimuli to test specific hypotheses, limiting discovery to features defined before experiments. Here we introduce NeuroVolve, a data-driven generative framework for synthesizing images that achieve flexible, user-defined patterns of brain activation in individuals. NeuroVolve recovers established selectivity across visual cortical regions and, paired with subject-specific brain encoding models, generates personalized stimuli reflecting individual differences in neural preference. Beyond single-region selectivity, NeuroVolve uncovers multi-region response selectivity, characterizing how regions jointly represent visual content during naturalistic perception. We further demonstrate generalization beyond visual cortex: in a prospective fMRI experiment, NeuroVolve-generated stimuli targeting the amygdala, a classically non-sensory region, drove measured activation consistent with predictions in novel participants. Together, these results establish NeuroVolve as a less constrained, data-driven tool for probing individual-level neural selectivity across the brain.

cs.CV · q-bio.NC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38847

Local Quantum Fault Tolerance Without Expansion

David Ponarovsky

原文摘要

We study fault-tolerant quantum computation using a fixed, local error-correction rule and a geometrically simple code: the cubical $(d,d')$-Toric code with $d',d-d'\geq 2$, including the 4D Toric code. Under sufficiently weak local-stochastic Pauli noise, our construction uses noiseless, bounded-depth classical processing per physical time step. Its correction cycle acts only on the current syndrome, has constant depth, and is repeated unchanged during idle logical computation; it requires neither multiscale decoder states nor scale-dependent communication delays. Our proof treats errors and syndromes as chains in a cubical complex, combining geometric shrinking under the sweep rule with a space--time explanation-tree argument inspired by Toom's theorem. It does not rely on expansion. We establish three results: 1.Explicit higher-dimensional sweep rule. We give a local algorithm for choosing sweep corrections on cubical $(d,d')$-Toric complexes, resolving the local-existence question of Kubica and Preskill. 2. Fault-tolerant computation. We prove a circuit-level threshold theorem for noisy sweep cycles interleaved with logical gates. In particular, the 4D Toric code admits a fixed, constant-depth syndrome-based correction cycle without a multiscale decoder or expansion-based encoding. We do not claim constant total-depth overhead. 3. Ideal decoding under local-stochastic noise. For an initial local-stochastic Pauli error of rate $p$ below threshold, $n^{d+1}$ noiseless sweep cycles recover the encoded state on a side-length-$n$ $(d,d')$-Toric code with probability at least $1-O(\operatorname{poly}(n))p^{Ω(n)}$, extending earlier guarantees for independent errors.

quant-ph · cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02101

When Delay Meets Drift: Physical Safety of Robot Foundation Models Is a Cross-Layer Problem

Liangkai Liu, Bimal Thapa Magar

原文摘要

Robot foundation models now act in a closed loop, yet their safety is evaluated one variation at a time: robustness benchmarks perturb the scene while assuming instantaneous inference, and real-time execution methods study inference delay in nominal scenes. We argue that physical safety is not a property of the model alone, but emerges from how variations in the physical environment, the model, the computing platform, and execution interact in closed loop. We formalize this as cross-layer variation propagation across these system layers and use an interaction contrast to measure when joint variation creates more risk than the sum of its parts. In 4,000 paired closed-loop episodes of the pi0.5 vision-language-action model on LIBERO, a 400 ms inference delay raises the safety-violation rate by 3.5 percentage points under the training viewpoint but by 37 percentage points under a 60-degree camera shift: 33.5 percentage points (95% CI: 25-43) more than the two effects combined. We close with a research agenda toward predictable physical intelligence: predicting when variation becomes risk, and adapting compute, power, and control accordingly.

cs.RO · cs.CV · cs.ET

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.22516

SALE: Source-Aware Dynamic Pricing with Strategic Buyers

Jinjiang Zou, Yang Li, Zemin Zheng

原文摘要

In modern commerce, firms and platforms typically use customer features from different sources to personalize prices: some features are verified using seller records or third-party data, while others are self-reported and may be strategically manipulated by buyers seeking lower prices. In this paper, we study the problem of source-aware dynamic pricing with strategic buyers, where the buyer's valuation is a sparse linear function of her high-dimensional features plus market noise with an unknown distribution. We develop the Source-Aware Localized exploration and calibrated Exploitation (SALE) policy, which personalizes exploration using past learning and verified features, and corrects for strategic manipulation using verified and reported features during exploitation. Our novel personalized design aims to narrow the range of prices explored, reducing unnecessary exploration at excessively high or low prices. To support learning under this design, we derive a new population equation that enables sparse valuation parameter estimation and, in turn, nonparametric estimation of the unknown noise distribution, even when buyer features are dependent over time. By uncovering the intrinsic sparse structure, our analysis establishes estimation guarantees for both learning tasks using the same exploration data. With these guarantees, we show that SALE achieves a sublinear expected regret bound, explicitly quantifying the benefit of using verified features to narrow exploration intervals. Several numerical studies further demonstrate the appealing performance of SALE.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02096

EarthJev: Calibrated, Non-Generative Answers to Natural-Language Questions about Sentinel-2 Land Cover

Domenico Benfenati, Antonio Maria Rinaldi, Cristian Tommasino

原文摘要

Vision-language models for remote sensing answer questions about satellite images by generating text: every answer costs a decoding loop, has to be parsed back to an option, and comes without a usable probability. We present EarthJev, a 0.8B-parameter model that answers typed questions about multispectral Sentinel-2 patches without generating any token. All 12 bands enter the vision encoder of Qwen3.5-0.8B through a widened input layer initialised from the RGB kernels, and, following the open OneJev recipe, the answer is read from the logits of the option letters at a single position and trained with cross-entropy plus Brier score. Under a pre-specified analysis plan, we compare it with the same backbone fine-tuned to generate the answer and with three multimodal language models fine-tuned with LoRA, all trained on the same 70,890 questions from 5% of BigEarthNet v2.0 and timed in one job on the same GPU; VQA models that classify over a fixed answer vocabulary are reported as a reference for the cost of answering only the questions seen in training. EarthJev answers a question in 19.9 ms, 4.3 to 8.7 times faster than the multimodal language models and 6.8 times faster than its own backbone used generatively; when all the questions about an image are asked together, it answers them in 42.8 ms, 3.7 to 10.1 times faster than the batched generative models. On 36,028 test questions it reaches 86.0% accuracy (three seeds), 0.6 and 1.2 points below the two 2B multimodal models and 3.5 points below the remote-sensing EarthDial-4B, with answers that are valid by construction and calibrated probabilities (ECE 0.006). Replacing the nine non-RGB bands with their mean costs 4.5 points, so the model uses the multispectral input, and in an ablation training the whole vision encoder raises accuracy to 88.4% at the same cost. Code and model: https://github.com/CosmoIknosLab/EarthJev

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02093

Bernoulli On-Policy Distillation: Don't Ignore High-Confidence Student Tokens

Mingyu Cao, Yaokai Jin, Shiwei Liu, Lu Yin

原文摘要

On-policy distillation (OPD) trains a student language model on its own trajectories using token-level supervision from a stronger teacher. We show that standard sampled reverse-KL OPD systematically suppresses updates to high-confidence tokens, such that their weak gradient contribution does not necessarily imply weak or uninformative teacher supervision. We introduce Bernoulli On-Policy Distillation (Bernoulli OPD), which directly matches the teacher and student probabilities for that token. This yields a bounded probability space correction that preserves teacher-student disagreement while avoiding the additional confidence-dependent suppression induced by vanilla OPD. Fixed-rollout analyses show that Bernoulli OPD substantially restores optimization signal to high-confidence tokens while remaining sensitive to teacher-student disagreement. We further analyze the resulting model behavior through confidence distributions, answer calibration, policy movement, and training dynamics, showing that Bernoulli OPD's gains cannot be explained simply by longer reasoning, larger optimization steps, or more uniform imitation of the teacher. Code is available at https://github.com/duterscmy/Bernoulli-OPD.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2604.10669

A Linear Temporal Logic of Frequencies on Series of Events

Melissa Antonelli, Alessandro Giuseppe Buda, Leonardo Ceragioli, Ferdinando Fugazza Calda, Giuseppe Primiero

原文摘要

This paper introduces LTLFS, a linear temporal logic for reasoning about frequencies in finite series of probabilistic events. The logic conservatively extends linear temporal logic over finite traces with measure-sensitive operators that compare the empirical distribution observed at any point in a series with an independently specified target distribution. Its semantics integrates the actual sequence of events, the probability distribution governing individual outcomes, and the set of finite assignments compatible with the target frequency. This supports two complementary tasks: verifying whether an observed partial distribution is compatible with the benchmark, and predicting whether and with what probability the completed series can still satisfy it. The language can express observed and attainable frequencies, the probability of realizing a desired final distribution, and conditional probabilities for subsequent outcomes under the assumption that the benchmark is met. We establish formal properties of the operators and characterize their interaction with the temporal structure. A running example concerning representational fairness in sequential outputs from a generative AI system illustrates how the framework can distinguish temporary deviations from irrecoverable violations and support early, logically interpretable intervention. LTLFS thereby provides a symbolic foundation for runtime monitoring of evolving quantitative requirements, with applications to explainable and responsible AI.

cs.LO · math.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02091

HQNN-CL: Regime-Aware Hybrid Quantum Neural Network with Continual Learning for Financial Forecasting

Muhammad Atif Saeed, Akhtar Jamil, Subhan Ullah

原文摘要

Financial time-series forecasting is still difficult owing to the non-stationary nature of the market, regime changes, and catastrophic forgetting, which makes conventional deep learning models hard to adapt in the long term. To achieve uncertainty-aware robust financial forecasting in the face of changing market conditions, this study proposes a Hybrid Quantum-Classical Neural Network with Continual Learning (HQNN-CL). The proposed framework combines Gaussian Hidden Markov Model (HMM) based regime detection, BiLSTM temporal encoding, adaptive-depth parameterized quantum circuits, Elastic Weight Consolidation (EWC), experience replay, and probabilistic forecasting in a single architecture. The framework was tested on four real-time stock datasets: Microsoft, Systems Limited, Teradata and Tata Consultancy Services, and compared with seven state-of-the-art forecasting models, including recurrent and Transformer-based models. The experimental results show that HQNN-CL has outperformed other methods on the Systems Limited (RMSE = 3.0149) and Teradata (RMSE = 0.8909) datasets and is within 0.32% and 0.40% of the best baseline method for Microsoft and Tata Consultancy Services, respectively. The proposed framework also generates well-calibrated probabilistic forecasts within the range of 89.5% to 96.5% empirical coverage rate, has zero catastrophic forgetting (BWT = 0.0000) for all sequential learning tasks, and consistently shows positive forward transfer. Ablation and statistical significance analyses also validate the performance of adaptive quantum feature learning and continual adaptation under heterogeneous market conditions, regime-wise.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.17541

FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation

Qijian Tian, Jiayu Ying, Xuhong Wang, Yuan Xie, Lizhuang Ma, Xin Tan

原文摘要

We present FLEG, a feed-forward network that reconstructs language-embedded 3D Gaussians from multi-view images. Previous feed-forward language-embedded Gaussian reconstruction methods are restricted to a fixed number of input views and typically attach a language-aligned semantic embedding to each Gaussian, resulting in impractical input settings and semantic redundancy. In contrast, we introduce a geometry-semantic dual-branch distillation framework that supports a variable number of uncalibrated and unposed multi-view images as input. We also propose a novel-view-based distillation strategy during training that mitigates overfitting to input views. In addition, we observe that semantic representations are significantly sparser than geometric ones, and per-Gaussian language embedding is unnecessary. To exploit this sparsity, we design a decoupled language embedding strategy that represents language information with a sparse set of semantic Gaussians, rather than attaching embeddings to every Gaussian. Compared with dense pixel-aligned per-Gaussian embedding schemes, our method uses only 5% of the language embeddings while maintaining comparable semantic fidelity, effectively reducing storage costs. Extensive experiments demonstrate that FLEG outperforms state-of-the-art feed-forward reconstruction and language-embedded Gaussian methods in both reconstruction quality and language-aligned semantic representation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.20258

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Sangwoo Park, Woongyeong Yeo, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh 等 9 位作者

原文摘要

Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment.

cs.LG · cs.AI · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2609.36279

Proofs Without Nominals: Gödel's Ontological Argument, its Shallow Embedding, and the Open Questions of the Monatshefte Notes

Christoph Benzmüller

原文摘要

The shallow embedding of higher-order modal logic in classical higher-order logic, used in Benzmüller and Scott's Notes on Gödel's and Scott's variants of the ontological argument, reaches beyond the modal object language: its quantifiers range over domains containing the nominals and satisfaction operators of hybrid logic. A proof using one proves a theorem of the embedding, not necessarily of the modal logic. Whether a result is one of the modal logic can be settled by replaying it in an explicit calculus, or, more cheaply and for all results at once, by analysing what the embedding's proofs substitute. Every statement the Notes prove has a proof in the embedding substituting nothing outside the object language, 294 of them explicit. The Notes' own proofs substitute none either; what it flags are terms a prover introduced. A soundness theorem over general models closed under the object language, and a sentence of that language the embedding proves but which fails in such a model, fix what the certificate says. The Notes' three open questions are settled too, without nominals, but by the empty instance of the conjunction axiom, too cheaply to convince. Generalised to Gödel's "any number of summands", the axiom covers the empty conjunction and the singleton. This article restricts it to at least two different conjuncts, a non-degenerate reading of Gödel's footnote, and settles them again without nominals. In effect only the empty conjunction is excluded; the singleton comes back with the other axioms. In one variant the restriction refutes the possible existence of a God-like being; the answers return, with no side condition, once the Notes' non-emptiness clause is confined to Gödel's essence. Every theorem here is verified in Isabelle/HOL and independently in Lean 4, the separating model in its propositional part; the countermodels are Nitpick's, checked by the build.

cs.LO · cs.AI · math.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02090

Local Solution Repair for Multi-Agent Pickup and Delivery

Ethan Schneider, Jingkai Chen, Seth Hutchinson, Sonia Chernova

原文摘要

Multi-robot systems in automated warehouses must efficiently attend to a constant stream of pickup-and-delivery tasks while avoiding collisions. Existing Multi-Agent Pickup-and-Delivery (MAPD) solutions generate plans that are globally feasible but often locally inefficient. In large-scale, long-horizon deployments, these inefficiencies, such as robots backtracking from target goal locations and idling in congested areas, accumulate over time and degrade performance. This paper contributes Local Solution Repair (LSR), a goal replanning approach that detects suboptimal behaviors at run-time and locally improves plans to reduce conflict between agents. We demonstrate the utility of our approach by repairing solutions generated by state-of-the-art MAPD baselines, M2M and LNS-PBS. Our results in long-horizon warehouse simulations over three environments show upwards of 5.9% improvement in task throughput over current state-of-the-art methods by reducing the number of suboptimal instances by ~36k or by 14.6% with minor additional computation time.

cs.RO · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.10747

Pneuma-Seeker: Relational Reification of Information Needs for Agentic Data Discovery and Preparation

Muhammad Imam Luthfi Balaka, John Hillesland, Kemal Badur, Raul Castro Fernandez

原文摘要

When faced with data problems, many data workers cannot articulate their information need precisely enough for software to help. Although LLMs interpret natural-language requests, they behave brittly when intent is under-specified, e.g., hallucinating fields, assuming join paths, or producing ungrounded answers. We present Pneuma-Seeker, a system built around a central idea: relational reification. Pneuma-Seeker represents a user's evolving information need as a relational schema: a concrete, analysis-ready data model shared between user and system. Rather than answering prompts directly, Pneuma-Seeker iteratively refines this schema, then discovers and prepares relevant sources to construct a relation and executable program that compute the answer. Pneuma-Seeker employs an LLM-powered agentic architecture with conductor-style planning and macro- and micro-level context management to operate effectively over heterogeneous relational corpora.

cs.DB

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.02088

Measuring "Success" In the Transition from Pre- to Post-LLM Conversational Agents through the Lens of Interaction & Explanations for Older Adults

Tamara Zubatiy, Niharika Mathur, Reina Chan, Srijan Pokharel, Rosemarie Santa González, Agata Rozga, Xiang Zhi Tan, Elizabeth D. Mynatt

原文摘要

Conversational agents (CAs) for older adults have moved through at least two distinct eras, split by the emergence of large language models (LLMs) at the end of 2022. The first era was defined by commercial smart speakers such as the original Google Home and Amazon Alexa, built on rigid, rule-based dialogue. Interactions were single-turn, user-initiated and "successful" if and only if a command matched one of a finite set of pre-templated intents. The current era is marked by LLM-powered systems capable of open-ended, multi-turn conversation, with capacity for personalization and foundations for more proactive interaction. This shift has not only transformed what CAs can do for users, but also changed what researchers can measure when it comes to understanding "success" of user interactions with CAs. In this case study, we reflect on over 8 years of research spanning more than 100 participants across multiple field sites to trace how our own working definitions of "success" have evolved. We reflect on two completed bodies of work with pre-LLM CAs and an in-progress study with a post-LLM CA. We discuss how our definition and measurement of success have evolved during this transition and also ask open questions to the community about how to optimally measure "success" in the post-LLM CA era. This research is deeply applied and subject to the messiness of real-world deployments. Our intended contributions are deliberately practical, a combination of methodological considerations and reflection questions to support researchers engaging with this new wave of technologies.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.08839

Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing

Dominick Reilly, Qiyu Wu, Hiromi Wakaki, Srijan Das, Yuki Mitsufuji

原文摘要

Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to leverage them effectively, as they treat modalities as interchangeable inputs rather than sources of complementary supervision. We propose Mixture of Probes (MoP), a novel framework that disentangles modality-specific and modality-general signals within the MLLM, allowing the model to preserve modality-dependent structure while learning transferable representations across modalities. At its core, MoP achieves this through a structured probing mechanism that extracts and organizes information from intermediate representations of a shared modality encoder, rather than relying only on final-layer alignment as done in existing MLLMs. To support this disentanglement, we further introduce MoP Cross-modal Training (MoP-X), a training strategy for MoP centered around a probe disentanglement loss that prevents probe collapse and encourages cross-modal learning. We evaluate MoP across two domains spanning eight tasks and four modalities under a comprehensive evaluation protocol tailored to the privileged modality setting, where each modality is independently treated as the sole input at inference time. MoP consistently outperforms strong MLLM baselines, achieving up to 65% relative improvement, demonstrating that auxiliary modalities, even when unavailable at inference, can provide substantial gains when effectively leveraged during training. Code, model checkpoints, and evaluation protocols will be made available at https://github.com/Sony/MoP.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.38960

Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation

Yi Wang, Tianzi Wang, Peter Bell

原文摘要

Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence. Omni-modal agents, which autonomously orchestrate perception tools to actively collect evidence, achieve strong performance, but it remains unclear whether active perception from both audio and visual modalities depends on broad specialized toolsets, especially audio or visual modality-specific tools. Such systems may also introduce long execution trajectories and substantial inference cost. We investigate whether comparable performance can be retained with a compact workflow exposing only essential perceptual capabilities. Starting from the specialized-tool OmniAgent, we conduct staged controlled experiments that prune the toolset and progressively consolidate modality-specific tools into omni-modal tools, motivating a two-tool agent comprising only Omni-modal captioning and Omni-modal QA. Across three widely used AVQA benchmarks, our compact agent achieves comparable or better accuracy than the specialized-tool agent while reducing inference cost by around 70%.

cs.AI · cs.CL · eess.AS

查看论文
arXiv ↗PDF ↗