跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 06:41 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 07:35 — 2026-11-22 07:35(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:2026-11-22 06:41最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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

找到 21,490 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 06:39(北京时间)
新论文 · v1arXiv:2611.20377

Halting in Recurrent Sequence Models

Simon Dräger

原文摘要

Recurrent sequence models, such as recurrent neural networks (RNNs) and state space models (SSMs), are often trained to emit an end-of-sequence (EOS) token when their output sequence is complete. During training, EOS is treated as another token without a special loss term or incentive. Although this training paradigm is widely used, it is not understood how models decide to output EOS. We study a minimal version of the EOS halting problem in which networks are trained to emit a given input sequence an instructed number of times, followed by EOS. We train tanh RNNs and linear SSMs on this task, finding that the RNNs encode the number of tokens left to copy in a linear subspace, of which two principal components capture most of the variation. Hidden states with the same remaining count converge to a shared representation regardless of their instructed repeat count. By modulating the hidden state using an affine transformation at the boundary between copied sequences, we shift the RNN's state to the representation shared by states with one fewer copy remaining. The unchanged network emits EOS one copy earlier while reproducing the shortened target sequence in 94.4% of new sequences, revealing that this representation causally determines the stopping time. In the SSMs, the difference between trajectories with different repeat counts is separated across two-dimensional rotation planes whose contributions to the EOS comparison cancel during copying and align near the stopping time. Rotating the planes independently removes most of the intended stopping while preserving the copied content, which shows that the stopping time depends on the planes' relative phases. These results identify two candidate primitives of EOS halting in recurrent models: a shared encoding of the number of remaining tokens in tanh RNNs and phase alignment across fixed rotations in linear SSMs.

cs.LG

版本更新 · v2arXiv:2610.20659

Latent Annealed Posterior Sampling with a Variance-Preserving Local Gaussian Approximation for Sparsely Observed Random Fields

Jiankun Lei, Tian Qi, Xinping Yang, Xiaoting Gan

原文摘要

Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty and controlling conditional sampling costs as spatial resolution increases. We propose latent annealed posterior sampling (LAPS). LAPS first maps the random field into a lower dimensional latent space, while a Branch--Trunk coordinate decoder enables field evaluation at arbitrary spatial locations. Flow matching then learns the latent prior distribution. Based on this learned prior, LAPS performs posterior sampling through multilevel annealing. At each level, prior flow transport generates a reference state, which is combined with Gaussian noise using variance-preserving coefficients to construct a local Gaussian approximation of the conditional prior. This approximation is then combined with the observation likelihood to define a local posterior, from which latent posterior samples are generated using preconditioned MALA. Numerical experiments show that LAPS accurately approximates posterior distributions, preserves distinct posterior modes, and decouples posterior conditioning from output resolution. Across two Gaussian benchmarks, LAPS closely matches exact posterior references, with sliced Wasserstein distances $1.8\%$ and $2.4\%$ higher than those obtained from independent exact posterior samples. In the bimodal posterior benchmark, LAPS reduces the sliced Wasserstein distance from $0.2693$ to $0.1499$ and consistently recovers both modes across all test scenarios. For the two dimensional Navier--Stokes random field, LAPS substantially improves marginal posterior calibration while maintaining nearly constant evaluation time as the output grid is refined from $64^2$ to $192^2$. These results demonstrate that LAPS offers a favorable tradeoff among posterior accuracy, uncertainty calibration, and computational efficiency.

stat.ML · cs.LG

新论文 · v1arXiv:2611.20372

VisDrone-ReID: A Unified Multi-Category Object Re-Identification Benchmark

Asmau Lawal Bilbis, Nathanael L. Baisa, Amudhavel Jayavel

原文摘要

Object re-identification (Re-ID) benchmarks remain predominantly confined to single-category evaluations, limiting the development of unified systems capable of operating across diverse object types. This paper presents VisDrone-ReID, a unified multi-category Re-ID benchmark derived from the VisDrone2019-MOT dataset through a principled conversion pipeline. The pipeline resolves structural incompatibilities between multi-object tracking annotations and Re-ID evaluation requirements, addressing sequence-scoped identity collision, temporal redundancy, and the absence of a principled identity-level train/test split. The resulting benchmark comprises 9,516 identities and 150,016 images across ten object categories - pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor, sourced from 80 unmanned aerial vehicle (UAV) sequences captured across urban environments. A leave-one-out (LOO) evaluation protocol is adopted to provide a comprehensive assessment. Baseline experiments across four representative Re-ID models spanning CNN and transformer architectures establish the first systematic performance reference on this benchmark. Results reveal a consistent Rank-1 to mAP gap across all models, suggesting that VisDrone-ReID presents a genuine retrieval challenge beyond nearest-neighbour matching. Per-category analysis identifies pedestrian as the most challenging category and reveals that vision-language pretraining provides a measurable advantage on semantically distinctive categories. VisDrone-ReID provides a consistent platform for studying multi-category object re-identification under the scale variation, viewpoint challenges, and category diversity characteristic of real-world surveillance scenarios.

cs.CV

新论文 · v1arXiv:2611.20371

Pretty Linear Liars: Unregularized Probes Favor Intervention-Unfaithful Features

Karl Vilhelmsson Emneby, Julian Yocum, Cameron Allen

原文摘要

Linear probing is a common technique in mechanistic interpretability despite the fact that the decodability of a given feature does not necessarily imply the network uses that feature. Intervention faithfulness, not merely decodability, is the appropriate criterion for whether a feature serves a defined active role in the model. Meanwhile, probe regularization has been used for feature discovery, but the impact of regularization on feature causality remains unclear. We study probe regularization systematically, starting with unregularized ordinary least squares (OLS) regression and considering increasing amounts of regularization via ridge regression. We show theoretically that OLS probes amplify low-variance directions in activation space that have spurious correlations with the target feature, whereas regularization reduces influence from these directions. Empirically, we find in a toy transformer and Llama-2-7B that intervention faithfulness increases up to a point, and then decreases again, and that the optimal regularization strength leads to features bearing striking similarity (in both direction and variance) to those learned by optimizing for intervention outcomes directly. Together, these results provide mechanistic justification for regularizing regression probes.

cs.LG · cs.AI

新论文 · v1arXiv:2611.20368

HoloGene: Learning to Lift Sliced Spatial Transcriptomics to Holistic 3D Gene Fields

Yumin Zheng, Qingtian Zhu, Ziyan Zhu, Kailu Song, Yinqiang Zheng, Jun Ding

原文摘要

Spatial transcriptomics (ST) provides spatially resolved gene expression measurements, but most 3D ST datasets are acquired as independently processed 2D sections. Computational approaches span slice registration and integration, explicit or generative interpolation, and coordinate-field modeling. Within the last family, implicit neural representations (INRs) offer a continuous, coordinate-queryable parameterization, but standard isotropic coordinate encodings do not explicitly reflect that serial-section measurements are dense in-plane and sparse along the axial direction. We present HoloGene, an anisotropic conditional INR framework for estimating continuous 3D gene-expression fields from pre-registered ST sections. Its central contribution is an acquisition-aware factorization that couples dense in-plane synthesis with sparse axial evolution using established GAE, FiLM, pseudo-label supervision, and CORAL components. HoloGene compresses high-dimensional expression profiles into a graph-autoencoder latent manifold, uses pseudo-label-derived signature conditioning to provide coarse intra-section context, and applies depth-dependent FiLM modulation to model axial variation. A signature-stratified correlation-alignment regularizer encourages cross-slice covariance alignment in latent features. Using held-out measured sections as cross-sectional references, HoloGene improves reconstruction accuracy and biological preservation metrics compared with general-purpose INRs and adapted spatial-transcriptomics baselines. These results support anisotropic conditional modeling as a practical strategy for estimating 3D expression fields from discontinuous ST sections. Code is available at https://github.com/Szym29/HoloGene.

cs.LG

版本更新 · v4arXiv:2608.09115

Quantum Bicycle LDPC Codes with High $kd^2/n$ from Divisor-Driven Search

Liangdong Lu, Guanmin Guo, Yang Liu, Ruipan Yang

原文摘要

Bicycle (two-block circulant) quantum low-density parity-check (LDPC)codes include some of the best known small quantum codes, yet their design has relied on group-algebra formulations in which the dimension and distance are accessible only through matrix computation. We show that in the cyclic case the construction collapses into the polynomial ring $\F_2[x]/(x^{l}-1)$: self-orthogonality is automatic, the quantum dimension is read off from a polynomial gcd, and the minimum distance is certified exactly through the Calderbank correspondence to additive codes over $\F_4$, turning code search into an algebraically pre-filtered enumeration that reaches parameter regimes poorly covered by existing tables. A computer search based on this framework recovers the short codes $[[42,12,4]]_2$ and $[[62,12,4]]_2$ and produces a family of codes with competitive figure of merit $kd^2/n$, including $[[66,20,7]]_2$ with $kd^2/n=14.85$, above the bivariate bicycle code $[[144,12,12]]_2$ ($kd^2/n=12$) at less than half the block length, together with $[[46,2,8]]_2$, $[[66,2,9]]_2$, $[[66,4,8]]_2$, $[[66,6,8]]_2$ and, at $n=90$, $[[90,16,7]]_2$, $[[90,18,6]]_2$, $[[90,20,6]]_2$. An exhaustive census at $n=48$ delineates the boundary of this picture: we exhibit a $[[48,10,6]]_2$ code from a minimal $48$-element group (the Aydin--Tamo--Barg realization uses $72$ elements), and prove that distance $5$ forces a stabilizer-rank loss, which excludes $[[48,10,5]]_2$ from the weight-$8$ symmetric coset family. The framework thus opens a systematic route to bicycle-type quantum LDPC codes beyond the reach of group-theoretic searches, and identifies exactly where genuinely coset-theoretic phenomena begin.

cs.IT · quant-ph

版本更新 · v3arXiv:2306.00275

A Comprehensive Survey on Orbital Edge Computing: Systems, Applications, and Algorithms

Changhao Wu, Yuanchun Li, Mengwei Xu, Chongbin Guo, Zengshan Yin, Weiwei Gao, Chuanxiu Chi

原文摘要

The number of satellites, especially those operating in low-earth orbit (LEO), is exploding in recent years. Additionally, the use of COTS hardware into those satellites enables a new paradigm of computing: orbital edge computing (OEC). OEC entails more technically advanced steps compared to single-satellite computing. This feature allows for vast design spaces with multiple parameters, rendering several novel approaches feasible. The mobility of LEO satellites in the network and limited resources of communication, computation, and storage make it challenging to design an appropriate scheduling algorithm for specific tasks in comparison to traditional ground-based edge computing. This article comprehensively surveys the significant areas of focus in orbital edge computing, which include protocol optimization, mobility management, and resource allocation. This article provides the first comprehensive survey of OEC. Previous survey papers have only concentrated on ground-based edge computing or the integration of space and ground technologies. This article presents a review of recent research from 2000 to 2023 on orbital edge computing that covers network design, computation offloading, resource allocation, performance analysis, and optimization. Moreover, having discussed several related works, both technological challenges and future directions are highlighted in the field.

cs.DC

版本更新 · v2arXiv:2611.10929

Augur: An Online Learning-based Hardware Data Prefetcher using Reservoir Computing

Satvik Maurya, David Trilla, Swamit Tannu, Alper Buyuktosunoglu

原文摘要

Machine-learning-based hardware prefetchers can learn complex access patterns, but practical deployment demands online adaptation, low-latency inference, and modest hardware cost. We present Augur, a hardware delta prefetcher based on next-generation reservoir computing (NGRC) that meets all three requirements. Augur formulates delta prediction as a history-based regression problem. It constructs a fixed-size reservoir from hashed delta features over a short context window and predicts the next delta using a single dot product. The model is updated online via one-step SGD and requires no offline pre-training, no per-benchmark tuning, and no floating-point arithmetic. Replacing the integer multiplications traditionally used to generate nonlinear reservoir features with bitwise AND operations removes all feature-generation multipliers with no loss in performance. Because Augur regresses a continuous delta, it needs no action set chosen offline for a fixed set of workloads. Augur pairs the reservoir with a simple Markov-based delta predictor for simple delta patterns, and with a selective issuance policy that filters and throttles wasteful prefetches; this policy accounts for about 40% of Augur's advantage and also improves Pythia. Evaluated on 169 traces spanning GAP, Ligra, PARSEC, SPEC CPU 2006, SPEC CPU 2017, and AI workloads, Augur outperforms the state-of-the-art ML-based delta prefetcher by 2.9%, 4.5%, and 5.3% in geomean speedup on 1-, 4-, and 8-core systems, respectively, while achieving ~2x higher prefetch accuracy and 37.8 percentage points fewer overpredictions. Augur is practical to implement at 33 KB storage, 0.32 sq. mm area, and 32.7 mW in 12 nm.

cs.AR

新论文 · v1arXiv:2611.20364

Multi-Library Feature Engineering and Statistically Validated Classification for Power Swing Detection and Stability Assessment

Pallav Kumar Bera, Samita Rani Pani, Ranjeeta Patel

原文摘要

Faults occurring during power swings, and the evolution of a swing into an unstable condition, cause distance-relay maloperation and cascaded outages. This paper identifies faults, faults during power swings, and power swings, and distinguishes stable from unstable swings in a 9-bus WSCC system modeled in PSCAD/EMTDC. Three time-series feature libraries (tsfresh, TSFEL, and tsfeatures) are applied to the 3-phase relay voltages and currents, giving 3286 statistical, temporal, spectral, and fractal descriptors per event window. A two-step feature selection (Boruta all-relevant filtering followed by RFECV- and SHAP-guided minimal-optimal pruning) reduces the feature set to 18 compact, non-redundant features. 14 classifiers spanning linear, kernel/instance-based, probabilistic, neural, and tree-ensemble/boosting families are then benchmarked under repeated stratified cross-validation, with model differences assessed by a Friedman/Nemenyi omnibus-and-post-hoc test and a Nadeau--Bengio corrected paired t-test. Rotation Forest (ROF) identifies the three event types with 99.98% and SVM-RBF distinguishes stable from unstable swings with 97.97% balanced accuracy. The results show that automated, library-driven feature extraction combined with rigorous statistical model comparison achieves near-perfect discrimination while retaining feature-level interpretability through SHAP importance.

eess.SP · cs.LG

新论文 · v1arXiv:2611.20362

Settling the Support Complexity of Correlated Equilibria

Ashkan Soleymani, Patrick Jaillet, Gabriele Farina, Akbar Rafiey

原文摘要

We study the support complexity of approximate correlated equilibria (CE) in two-player games, that is, the minimum number of pure action profiles that must be assigned positive probability to approximate a correlated equilibrium of a two-player matrix game. For $\varepsilon$-approximate coarse correlated equilibria, constant approximation is possible with support $O(\log N/\varepsilon^2)$ in $N\times N$ games. For correlated equilibria, the best known upper bound was $O(\log^2 N/\varepsilon^4)$ [Babichenko et al., 2014, 2017], but whether this bound was tight remained open. We establish a matching lower bound, resolving the open question of Ko and Schvartzman [2017]. Specifically, we show that, already for two-player zero-sum games, for every $1\leq k\leq N^{1/2}$ the worst-case correlated-equilibrium gap achievable by a distribution supported on at most $k$ pure profiles is $$ Θ\left( \min\left\{1,\frac{\sqrt{\log N}}{k^{1/4}}\right\} \right), $$ which implies a $Θ(\log^2 N/\varepsilon^4)$ worst-case support bound. The proof builds on a probabilistic-method construction based on random sign matrices.

cs.GT · cs.LG

新论文 · v1arXiv:2611.20361

Structure-Guided Multi-Granularity Spatiotemporal Transformer for Efficient Monocular 3D Human Pose Estimation

Sheng Xu, Aoduo Li, Rongli He

原文摘要

Existing multi-granularity methods for monocular 3D human pose estimation emphasize spatial joint features while underusing skeletal structure, including global connectivity and temporal continuity. Moreover, modeling entire frame sequences incurs high computational costs. We propose a Structure-Aware Multi-Granularity Spatiotemporal Transformer that integrates structural priors across spatial and temporal representations for accurate and efficient pose estimation. A three-level feature extractor captures human topology at the joint, bone, and limb levels. Gated Adaptive Spatial Attention (GASA) embeds structural constraints into spatial attention, while Multi-Granularity Feature Enhancement (MGFE) uses hierarchical pooling and fusion to strengthen local details and global semantics. Temporal Segment Fusion (TSF) aligns temporal contexts across granularities to capture both short- and long-range motion patterns. Hierarchical Cross-Attention (HCA) promotes spatiotemporal interaction between granularities, and Keyframe Attention (KFA) selects informative motion segments to reduce redundancy and computational cost. Experiments demonstrate improved accuracy and efficiency over conventional Transformer-based approaches, highlighting the effectiveness of structure-aware multi-granularity modeling for monocular 3D human pose estimation.

cs.CV · cs.AI

新论文 · v1arXiv:2611.20352

EPI-SST: Renewal-Structured State-Space Transformers for Epidemic Forecasting

Yiyun Chen, Zewen Liu, Shengpu Tang, Max S. Y. Lau, Wei Jin

原文摘要

Epidemic forecasting supports public health decisions ranging from capacity planning to intervention timing, for which both point accuracy and calibrated uncertainty are essential. Although neural models have advanced point forecasting, producing reliable probabilistic predictions over multiple future horizons remains challenging. Renewal models encode epidemic propagation, while neural forecasters learn flexible multi-horizon representations; integrating these strengths within a probabilistic future rollout remains underexplored. We propose EPI-SST (Epidemic State Space Transformer), a probabilistic forecaster centered on an evidence-driven renewal transition. At each horizon, neural evidence produces a bounded update to an internal multiplier and advances a finite-memory renewal state that generates the future mean trajectory. A separate heteroscedastic Gaussian head controls predictive scale using a validation-selected log-variance penalty. Across four epidemic surveillance benchmarks, EPI-SST achieves the lowest pooled RMSE on every dataset, reducing RMSE by up to 14.2 percent relative to the strongest baseline. It also achieves the lowest continuous ranked probability score (CRPS) at horizons h = 4, 5, 6 on every dataset, with reductions of up to 43 percent relative to the strongest probabilistic baseline. During the abnormal 2019-2020 influenza season, EPI-SST reduces CRPS by 16.9 percent and calibration error by 78.9 percent; a three-seed replication preserves its distributional lead. Ablation studies and frozen-path interventions show that the renewal transition, attention conditioning, horizon coupling, and uncertainty-scale control make complementary contributions to predictive performance.

cs.LG

新论文 · v1arXiv:2611.20348

From Prediction to Action: An Execution-Aware End-to-End Machine Learning Framework for Structured Investment Decision Support

Aditya Bhardwaj, Xingchen Zhang

原文摘要

Financial machine learning is widely used for market prediction, but many existing studies formulate trading as a directional forecasting problem and stop at predicting whether prices will rise or fall. Such predictions are difficult to translate directly into practical trading decisions, which also require execution rules, risk controls, and clearly defined actions. To address this gap, we propose an end-to-end machine learning framework for structured investment decision support. The framework integrates multi-asset market data, execution-aware label construction, feature engineering and refinement, specialist predictive models, and ensemble learning. Rather than defining learning targets solely according to future price direction, the proposed execution-aware formulation considers realised trading outcomes under predefined stop-loss and take-profit rules. Model outputs are subsequently converted into structured trading recommendations comprising trade direction, entry price, stop-loss, take-profit, and risk-reward ratio. The framework is evaluated using time-aware forward testing, with results showing that execution-aware labelling improves risk-adjusted trading performance over conventional directional labelling and that the integrated framework outperforms a simpler single-model baseline across key trading metrics. An automated cloud-based implementation further demonstrates the operational feasibility of the proposed approach. Overall, the findings suggest that closer alignment between predictive modelling, execution logic, and structured decision generation can improve the practical value of machine learning for financial trading.

cs.CE

新论文 · v1arXiv:2611.20339

Response-Threshold Framework for First-Peak Preservation in Noisy Grover Search

Ge Zhong, Charith Jayasekara, Nisal De Silva, Chetan Arora

原文摘要

Grover search is executed only after integer iterations, so noise can alter the stopping decision even when a continuous first peak remains visible. We develop a response-threshold framework separating continuous peak motion, stroboscopic geometry, and the discrete sampled-success argmax. For a Drude-Lorentz environment, linearized HEOM supplies an a priori timing coefficient and sampled-probability differentials. The first-order layer is used as a conservative screen: well-separated points retain the nominal step, whereas near-threshold points escalate to finite-$λ$ evaluation. Across 260 unique HEOM points drawn from five overlapping validation sets, it detects all 15 observed stopping changes with zero regret on the changed subset; its residual errors are 45 one-step-early calls on otherwise stable points; the 245-point stable subset has mean regret $4.42\times10^{-3}$. An empirically validated two-stage workflow escalates every observed change while avoiding 160 of 260 unique full-HEOM propagations. Same-bath NZ2 reduces early calls. A heterogeneous three-qubit circuit exhibits three stopping-transition scales, each replicated across eight marked targets, and finite-shot recovery is 96.18% overall, with failures localized to a near-degenerate boundary at $s=1.5$. A depth-refined transfer test supports the predicted local quadratic timing-to-loss relation.

quant-ph · cs.ET

新论文 · v1arXiv:2611.20336

Spectral Landmarks: Alignment of Landmark Kernel Translates with the Leading Eigenfunctions of a Kernel Operator

Jeanie Schreiber

原文摘要

We study the problem of choosing $m$ landmark points so that the span of the kernel translates is as close as possible to the leading $s$-dimensional eigenspace of a positive-definite kernel. The natural measure is the Hilbert-Schmidt operator discrepancy between the reproducing-kernel-Hilbert-space (RKHS) projectors onto the two subspaces. We give a closed form spectral alignment function in terms of the truncated Mercer kernel and relate it to the classical integrated power function (Nyström trace error) through a two-sided sandwich bound. Minimizing the function by gradient descent on the landmark coordinates produces landmark sets that are evenly spaced. Theoretical results show that optimal configurations are those whose eigenfunction sampling matrix is a scaled isometry. On homogeneous spaces these are exactly the minimal equal-weight cubature rules for products of leading eigenfunctions, and for every $m\ge s$ they are the configurations whose sampled eigenfunctions form a unit-norm tight frame. Experiments on $\mathbb{S}^1$ and $\mathbb{S}^2$ agree with the theory. On the circle, with $s\le2m$ and a moderate bandwidth, every random start converges to equispaced landmarks, and on the sphere the optimizer recovers the regular tetrahedron, octahedron, and icosahedron from random starts. Finally, we analyze the numerical conditioning of the problem.

math.NA · cs.LG · math.FA · math.MG

版本更新 · v5arXiv:2607.02764

MorphQuad: Morphable Quadrotor for Superhuman Maneuverability, Manipulation, and Resiliency

Jose Diaz Peon Gonzalez Pacheco, Jiawei Xu, Andrew Zhao, Hongyu Zhou, Atharva Navsalkar, Andrew Scheffer, Amrith Malli Reddi, Sashreek Shankar 等 10 位作者

原文摘要

Infrastructure maintenance, contact-based inspection, and emergency response can benefit from aerial vehicles that act as a flying human hand with extreme maneuverability, manipulation, and resiliency (MMR): maneuverability to fly in arbitrary orientations; manipulation to point sensors, turn valves, and press tools at arbitrary orientations; resiliency to maintain motion accuracy and force application despite disturbances from arbitrary directions, such as wind, ground effects, and friction. Realizing MMR requires more than omnidirectional flight; it also requires (I) vectoring of maximum thrust in any direction, (II) almost-everywhere stability, accounting for kinematic singularities, control singularities, and inter-rotor downwash interference, and (III) miniaturizable structural designs. Existing aerial vehicles satisfy a subset of I--III. We present MorphQuad, a morphable quadrotor that delivers MMR by realizing I--III on a quadrotor structure with independently articulated rotor systems through novel control and thrust allocation algorithms. On hardware, MorphQuad preserves a planar quadrotor structure, and independently articulates each of the four rotor systems, eliminating control singularities and enabling all rotors to align and vector the platform's maximum thrust in any direction; on control and thrust allocation, MorphQuad enjoys a closed-form null-space correction for gimbal lock and downwash interference that maintains almost-everywhere stability via coupling with a generalized geometric controller. With fully-onboard computation, localization, and trajectory execution, MorphQuad demonstrates continuous multi-revolution rotation while translating or hovering (maneuverability); valve turning, perching, and object pressing and pushing with human-wrist strength (manipulation); and push-pull recovery and wind rejection, even when directed to a single rotor (resiliency).

cs.RO

新论文 · v1arXiv:2611.20333

Beyond Service Discovery: Coverage Awareness in LLM-Driven Service Composition

Sepideh Masoudi, Ronja Froelian, Stefan Tai

原文摘要

Large language models increasingly support the automated discovery and composition of services. In federated data ecosystems, this creates new opportunities for reusing existing data products and transformation services when constructing service-based data exchange modeled as data-sharing pipelines. However, finding relevant reusable assets does not imply that the available assets are sufficient to satisfy a consumer request. In this paper, we distinguish reuse discovery, the ability to identify relevant published assets, from reuse coverage, the extent to which the available assets support the transformations required by a request. We further consider coverage awareness, the ability of a composition system to recognize insufficient coverage. We investigate this distinction using PipeFinder, an LLM-driven framework for composing data-sharing pipelines, and evaluate 99 consumer requests against a fixed catalogue of data products and transformation services. Our experiments show that relevant data products can be discovered reliably, while successful composition remains considerably more difficult. More importantly, when required transformation services are missing, the framework typically constructs a pipeline from the available services rather than recognizing that the request cannot be satisfied. Explicitly incorporating coverage checking into the planning procedure substantially improves recognition of such cases. These results suggest that coverage awareness should be treated as an explicit concern in LLM-driven service composition and cannot be assumed to follow from improved discovery or model capability.

cs.DC

新论文 · v1arXiv:2611.20331

LENS: Replacing LayerNorm and Softmax in Transformers with Learnable Normalization States

Yuhao Liu, Salim Ullah, Akash Kumar

原文摘要

LayerNorm and attention Softmax are critical operations in Transformers. However, they cannot be efficiently mapped to General Matrix Multiplication (GEMM) computations on hardware. Therefore, modern hardware accelerator designs, such as NPUs on ASIC/FPGA, consume a large amount of hardware resources or chip area to implement their specific arithmetic units. Building on previous work about LayerNorm, Softmax, and their alternatives, we introduce Learnable Normalization States (LENS), a framework that reformulates LayerNorm as tiny MLPs by abstracting a common structure from related methods and extends this method to Softmax, which moves more of the computation in Transformers to GEMM as a hardware-friendly architecture. We evaluate LENS on image classification with Vision Transformers (ViT) and autoregressive language modeling with Pythia models, including generalization tests on WikiText and LAMBADA. Across these tasks, LENS matches or exceeds baseline performance in several vision settings and retains most of the baseline performance in the remaining vision and language experiments. These findings may suggest that hand-designed normalization and attention functions are not the only choice as alternatives to LayerNorm and Softmax. LENS also provides a basis for exploring Transformer architectures for resource-limited accelerators.

cs.LG · cs.AI · cs.AR

新论文 · v1arXiv:2611.20330

Sidewalk Stewards: A Visual Analytics Approach for Interactive Topology Repair of Sidewalk Networks

Stefan Cobeli, Leonardo Ferreira, Logan Loch, Luiza Melo, Peyman Baghershahi, Claudio D. G. Linhares, Nivan Ferreira, Sourav Medya 等 10 位作者

原文摘要

Accurate pedestrian network data is foundational to urban accessibility, routing, and infrastructure planning, yet such data remains scarce and difficult to produce at scale. Automated extraction pipelines have made significant strides by leveraging computer vision to derive sidewalk networks from aerial imagery, and have seen real-world adoption by municipalities seeking cost-effective inventory solutions. Yet, these pipelines consistently produce topological errors (e.g., disconnected components, dangling edges, missed connections, malformed intersections) that undermine the utility of the extracted networks for routing and accessibility analysis. Correcting these errors requires situated human judgment that global automated repair strategies cannot replicate, yet practitioners currently lack dedicated tools to support this work efficiently. We present Sidewalk Stewards, a visual analytics system that bridges the gap between automated extraction and a deployment-ready pedestrian network. Sidewalk Stewards detects candidate topology errors, supports interactive user-guided correction through coordinated spatial views, and provides real-time quality feedback as edits are applied. We evaluate Sidewalk Stewards through a comparative user study, case studies across cities, and a quantitative evaluation. Compared with conventional workflows, the system facilitates error identification and enables faster and more complete correction. The case studies illustrate the workflow across different urban contexts, and the quantitative evaluation shows that a small number of user corrections can enhance multiple sidewalk quality metrics. Sidewalk Stewards is available at urbantk.org/sidewalk.

cs.HC · cs.CV · cs.CY

版本更新 · v4arXiv:2607.27924

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

Dongxiu Liu, Haoyi Niu, Peng Cheng, Yuan Gao, Xirui Kang, Sangli Teng, Koushil Sreenath, Xianyuan Zhan

原文摘要

In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world. We introduce Physical-Time Flow (PT-Flow), a novel approach that learns a continuous latent velocity field operating in physical time. Crucially, the underlying dynamics of sequential data are parameterized by an ordinary differential equation (ODE) embedded in a well-structured representation space. Under this paradigm, the prediction of future can be recast as temporal integration via an ODE solver in the compressed latent space. Building upon PT-Flow, we construct ODEWorld, a continuous-time latent world model that is both efficient and versatile. By extracting time-variant features and enforcing ODE properties on both the dynamical representation space and the latent velocity field, ODEWorld effectively addresses the long-standing representation collapse issue in latent world model literature. This also enables high-quality image reconstruction even after long-horizon prediction. Moreover, its continuous nature allows for arbitrary temporal resolution and even backward prediction, which is impossible for most discrete-time models. Lastly, ODEWorld can provide rich planning-oriented information to facilitate downstream policy learning. Comprehensive experiments demonstrate that ODEWorld successfully reconciles planning-conducive dynamics abstraction with visual realism, excelling in both video generation and robotic control. Project page: https://dstate.github.io/odeworld_website/.

cs.LG · cs.CV · cs.RO

版本更新 · v2arXiv:2605.17671

PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment

Michael Arbel, Basile Terver, Jean Ponce

原文摘要

Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its stability: non-collapsed stable equilibria align with leading nonlinear canonical correlation subspaces, while collapsed equilibria may also be stable attractors. Motivated by this result, we introduce PEIRA, a non-contrastive SSL method with an explicit objective defined through the trace of the optimal linear regressor. We show that its only stable equilibria are nontrivial global minimizers and recover the same canonical correlation subspaces, with regularization selecting the effective dimension. Experiments on ImageNet-1K and CIFAR-10 show PEIRA is competitive with VICReg and LeJEPA baselines, and qualitative empirical results support the theory. Project page: https://peira-ssl.github.io. Code: https://github.com/MichaelArbel/peira-loss (loss implementation), https://github.com/Basile-Terv/PEIRA (experiment reproduction).

cs.LG · cs.AI

新论文 · v1arXiv:2611.20326

Simulating access to alcohol screening, brief intervention, referral to and receipt of specialty treatment for alcohol use disorder in California and Texas: A study protocol for an agent-based modeling study (AUDTxSim)

Rainer Hilscher, Andy Kawabata, Nick Kruskamp, William Dowd, Nina Mulia, Carolina Barbosa, Georgiy Bobashev, Jessica Duncan Cance 等 11 位作者

原文摘要

Alcohol use disorder (AUD) affects millions of US adults. Primary care-based screening, brief intervention, and referral to treatment (SBIRT) is a leading strategy for identifying heavy drinking early, but access to primary care, screening, and specialty treatment differs markedly across subgroups. Whether scaling SBIRT and expanding treatment capacity narrows or widens these differences is unknown and cannot feasibly be tested in a randomized trial. We present AUDTxSim (AUD Treatment Simulation), a stochastic, spatially explicit, individual-based model of alcohol use, AUD, SBIRT, and specialty treatment for the adult populations of California and Texas. Agents represent every adult in synthetic populations of the two states (28.0 and 19.3 million adults), each geo-located to a Census tract and linked to nearby treatment facilities. In daily time steps, the model simulates: (1) annual transitions among eight alcohol use and AUD states; (2) healthcare visits, screening, brief intervention, and referral; (3) treatment seeking, standalone medication for AUD, mutual help, and requests for hospitalization, residential, or outpatient care; (4) a treatment manager that allocates individuals to facilities by preference, geography, and capacity, with telehealth substitution and waitlists; and (5) treatment progression, stepdown between levels of care, and post-treatment mutual help. It is implemented in Python with Repast4Py to run in parallel on a computing cluster. Once calibrated to state, rural-urban, and demographic targets for healthcare visits, heavy drinking and AUD prevalence, and mortality, AUDTxSim will project population-level and subgroup-specific effects of alternative SBIRT reach and treatment capacity scenarios on AUD prevalence, treatment receipt, and mortality. We report the model structure, decision logic, data sources, and calibration plan.

cs.CY

版本更新 · v4arXiv:2510.18218

DualHash: Stochastic Primal-Dual Algorithms for W-Type Regularized Deep Hashing

Luxuan Li, Xiao Wang, Chunfeng Cui

原文摘要

Deep hashing encodes high-dimensional image features into compact binary codes, enabling efficient similarity search in large-scale content-based image retrieval, a problem akin to semantic-preserving lossy compression under extreme bit-rate constraints. A fundamental challenge in deep hashing stems from the discrete nature of quantization in generating the codes. W-type regularizations, such as $z\mapsto\||z|-1\|_1$, are widely adopted and empirically effective at pushing network outputs toward binary values. However, existing methods often directly optimize these regularizations without convergence guarantees. While proximal gradient methods offer a promising solution, the coupling between W-type regularizers and neural network outputs results in composite forms that generally lack closed-form proximal solutions. In this paper, using Fenchel duality, we reformulate the nonconvex W-type regularization term through its convex conjugate, yielding a min-max problem with tractable proximal updates. We show that this min-max problem captures the stationarity of the original deep hashing objective up to the quantization error. Building on this problem, we present a stochastic primal-dual hashing algorithm, referred to as DualHash, with oracle complexity guarantees. We derive two algorithm instances: a momentum-based version with $O(\varepsilon^{-4})$ oracle complexity and an improved $O(\varepsilon^{-3})$ version using variance reduction, both for $\varepsilon$-KKT points of the min-max problem, which yield near-stationarity guarantees for the original objective. Experiments on three standard datasets demonstrate competitive retrieval accuracy and reduced quantization error, validating the practical value of DualHash for image retrieval problems. Our implementation of DualHash is available at https://github.com/RailLee/DualHash.

math.OC · cs.CV

版本更新 · v3arXiv:2509.26305

Feedback Forensics: A Toolkit to Measure AI Personality

Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier, Robert Mullins

原文摘要

Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional benchmarks based on automatic checks struggle to measure such traits. Evaluation methods using human feedback such as Chatbot Arena have emerged as a popular alternative. These methods infer "better" personality and other desirable traits implicitly by ranking multiple model responses relative to each other. Recent issues with model releases highlight limitations of these existing opaque evaluation approaches: goblin-obsessed, sycophantic and generally over-the-top personalities have resulted in model rollbacks and extensive media coverage. Despite these known issues, limited public tooling exists to explicitly evaluate model personality. We introduce Feedback Forensics: an open-source toolkit to track AI personality and related behavioural traits, both those encouraged by human (or AI) feedback, and those exhibited across AI models trained and evaluated on such feedback. Feedback Forensics is adaptive and can automatically find new traits appearing in models. We demonstrate the toolkit's usefulness in two steps: (A) first we analyse the personality traits encouraged in popular human feedback datasets including MultiPref, PRISM and data from Chatbot Arena; and (B) then use our toolkit to analyse how much popular models exhibit such traits. We release (1) our Feedback Forensics toolkit alongside (2) a web app tracking AI personality in popular models and feedback datasets and (3) the underlying annotation data, see https://github.com/rdnfn/feedback-forensics.

cs.CL · cs.AI

版本更新 · v4arXiv:2610.01425

Why Does Train-Validation Separation Emerge? Gradient-Allocation Dynamics in Pretrained Fine-Tuning

Yuchen Li, Zongqi Fan, Ken-Tye Yong, Nguyen H. Tran

原文摘要

During fine-tuning, training accuracy often keeps rising after validation accuracy has levelled off. We explain this growing train-validation gap with a support-transfer account: early updates use structure shared by many examples, whereas later fitting relies increasingly on narrow structure whose benefit transfers less to held-out data, so per-example gradient allocations differentiate as the gap grows. We measure this with two readouts computed from fixed training probes alone, the pooled dispersion $D_{\mathrm{den}}$ of normalized gradient magnitudes and its within-class part $D_{\mathrm{within}}^{\mathrm{wt}}$, and derive sufficient conditions under which allocation dispersion, cross-entropy separation, and the accuracy gap grow together. In a constructed feature hierarchy, raising the sample-private feature share from .3 to .7 raises the final accuracy gap from .185 to .527, and homogenizing per-example gradient magnitudes reduces the gap mainly after substantial fitting (median full-dose changes of -4.91 to -11.79 percentage points when it starts at the three later training stages). In 90 fine-tuning runs of three language backbones on six tasks, both readouts are positively associated with the accuracy gap in every run, and $D_{\mathrm{den}}$ remains positive in 89 of 90 runs after linear detrending; 20 vision runs show the same association.

cs.LG

新论文 · v1arXiv:2611.20324

High-Speed Forward and Reverse Tractor-Trailer Driving with Learned Vehicle Dynamics

Aaron Chen, David Shen, Taekyung Kim, Kaleb Ben Naveed, Dimitra Panagou

原文摘要

Tractor-trailer systems are difficult to control, especially unstable during reverse motion, and their dynamics depend on difficult-to-measure factors, including road friction and suspension coefficients. We introduce a learned dynamics model for tractor-trailer control and compare it with a reduced-order dynamics model with Fiala tire forces as an analytic baseline. Specifically, we compare a model predictive path integral (MPPI) controller that uses the learned dynamics model to an MPPI controller that uses the analytic model, as well as to three additional baseline controllers. In the main closed-loop tracking experiments across four simulated environments, MPPI with learned dynamics achieves mean speeds closer to the target magnitudes and lower root-mean-square (RMS) hitch angles than MPPI with the analytic model at every tested setpoint, with higher completion rates in seven of eight reverse configurations.

cs.RO · eess.SY

新论文 · v1arXiv:2611.20321

Unreasonable Confidence from Simulator Misspecification: Directional Robustness on the SPEED+ Sim-to-Real Benchmark

Nikolay Dolgov

原文摘要

Vision-based navigation systems for orbit must be trained almost entirely on synthetic imagery, because real labelled images of a given spacecraft in flight rarely exist. Benchmarks like SPEED+ are built for that situation: the training set comes from a simulator, and the test sets are real images of a satellite mockup under two kinds of lighting. That simulator approximates how light reflects off mylar and aluminium, and like every scientific simulator it is misspecified. Its error is radiometric, since it misses the specular highlights, hard shadows and sensor saturation common in real images. We probe the resulting synthetic-to-real gap, the central risk for such systems, with a deliberately simple monocular pose estimator. In a 2x2 study of backbone adaptation and photometric augmentation, trained on synthetic images and tested on both real hardware-in-the-loop domains, we find three things. (1) The model does not know it is failing: regions conformally calibrated to 90% on synthetic data cover only 9-15% of rotation errors on sunlamp and 21-38% on lightbox, so a wrong pose carries the confidence of a correct one. (2) Transfer is asymmetric: scaling data and features improved synthetic rotation error from 1.65 to 1.03 rad but moved the harshly lit sunlamp domain by only 0.05 rad, under twice its seed s.d., whereas adapting the backbone's last stage carried 63-83% of its extra synthetic gain to both real domains. (3) Once the backbone adapts, augmentation helps only in the direction it models: our photometric stack improved the diffusely lit lightbox domain from 1.17 to 0.99 rad on every seed but moved sunlamp no more than seed-to-seed variation, while with the backbone frozen it helped sunlamp more. Every post-review experiment was pre-registered, and the code, per-image predictions and pre-registration record are at https://github.com/lokindoo/spacecraft-pose-estimation.

cs.CV · cs.AI · cs.LG

版本更新 · v11arXiv:2606.11171

Bellman-sufficient Information Complexity

Yunbei Xu

原文摘要

We introduce Bellman-sufficient information complexity for minimax analysis of sequential decision problems. A Bellman-sufficient state retains the history needed for the controlled recursion; an index $Y=χ(Ω)$ specifies which information the bounds charge. A log-penalized Bellman program gives the upper bound, and a Bellman--Fano comparison with an algorithm-dependent reference trajectory gives the lower bound. When admissibility, calibration, and growth conditions hold and the bounds match at a common localization scale, they yield an information-risk sandwich. UCB bounds the immediate decision loss through calibration and optimism, while AMS/EBO gives a robust relaxation of the AIR Bellman program. Our main application gives a negative answer to a widely studied form of the GP--UCB minimax-optimality question. For every $0<α<1/4$, we construct a fixed bounded continuous kernel with minimax regret $Θ(T^{1-α})$ along an infinite sequence of horizons. At those horizons, two globally calibrated GP--UCB rules incur linear regret under one fixed truth. A policy that applies action-index AMS to a predetermined finite set in each epoch attains the minimax order; EBO gives a dual interpretation. Many low-value directions inflate the global exploration multiplier even though ignoring them is inexpensive. Through the canonical RKHS feature map, the same construction gives a finite-horizon polynomial minimax gap for the specified maximal-information-calibrated LinUCB rule. A numerical experiment illustrates the mechanism.

cs.LG · cond-mat.stat-mech · cs.IT · math.OC · math.ST

新论文 · v1arXiv:2611.20319

How did data sharing evolve in the decade since the FAIR Principles?

Sheeba Samuel, Daniel Mietchen

原文摘要

A decade after the publication of the FAIR Guiding Principles, what have we learned about data sharing, and what do data availability statements (DAS) and other materials accrued over that period tell us about how data-sharing practices, attitudes, and infrastructures evolved? Here, we present a large-scale longitudinal analysis of over 6.8 million biomedical articles from the PMC Open Access Subset, spanning 2011 to 2025. Using an automated pipeline, we extracted and classified DAS, repository links, accession numbers, and supplementary materials, assigning each article a data-sharing score and independently FAIR-assessing a subset of cited dataset URLs. We find that explicit DAS adoption rose from ~2% in 2011 to 68% in 2025, while "available on request" statements grew in parallel from near zero to over 19%. The corpus growth amplifies both patterns: articles with a DAS containing an explicit repository mention rose from 132 in 2011 to 94,697 in 2025, while "available on request" articles rose from 77 to 173,474 over this span. Structural biology and genomics consistently achieved the highest data-sharing scores, while clinical research and public health ranked lowest. Gold Open Access journals showed a small advantage over subscription journals, while Diamond Open Access journals outperformed both. Internationally collaborative articles scored higher than domestic ones. A gender gap emerged: female first-authored articles' scores declined more than male first-authored ones. The analysis further covered additional dimensions, from compliance with funder/journal mandates and JATS XML tagging standards to computational reproducibility signals and the co-occurrence of DAS with ethics statements. A decade on, the gap between declaring data availability and actually sharing machine-readable, reusable data persists across fields, infrastructures and demographics.

cs.IR · cs.DL

新论文 · v1arXiv:2611.20318

Near-Optimal Methods for Generalized Lipschitz Convex Optimization

Dmitry Kovalev, Grigory Malinovsky

原文摘要

In this paper, we consider a convex optimization problem, where the upper bound on the subgradient norm depends on the objective function. We establish a lower bound on the number of iterations required by any first-order method to find an approximate solution to the problem. Furthermore, we present two near-optimal algorithms that can match the lower bound up to logarithmic factors. The first algorithm is a projected GD with a carefully designed stepsize schedule which incorporates warm-up and decay phases. The second algorithm is scalar-stepsize clipped AdamW which extends the near-optimal guarantees to the stochastic setting, where only a noisy unbiased estimator of the subgradient is available.

math.OC · cs.LG