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

+479新增论文
+361其中 AI 相关
+63已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-16 01:34 · 全站最近入库:2026-11-16 13:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 21:09 — 2026-11-16 21:09(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:2026-11-16 01:34最近发现新增版本:2026-11-16 13:44库内论文最新更新时间:2026-11-14 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。

23,827 已收录论文19,941 AI 相关6,921 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 17,708 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33(北京时间)
版本更新 · v2arXiv:2604.12407

Tamper-Proofing with Self-Modifying Code

Gregory Morse, Tamás Kozsik

原文摘要

Classical computability theory tells us that self-modifying code (SMC) on a deterministic universal Turing machine can be simulated by non-SMC code on the same model. That abstraction, however, omits the external timing inputs, concurrency, and microarchitectural state that dominate practical execution on modern processors. We argue that once timing, ordering, and self-introspective effects are treated as observables, a practically faithful non-SMC reproduction of timed SMC becomes detectably expensive on commodity systems. We present a tamper-proofing model that combines introspective and polymorphic SMC, reliable clocks, and runtime timing predicates to bind integrity checks to execution behavior. We distinguish static and dynamic SMC generation, characterize the timing semantics needed to avoid catastrophic pipeline clears, and give x86-64 design primitives for checksum-driven self-patching. We also report timer measurements, performance comparisons, and performance-monitoring counter evidence showing that careful engineering - especially loop unrolling and cross-page modification - substantially reduces the overhead of SMC while preserving its tamper-detection value. The paper concludes with an efficiency analysis, a threat model, and deployment guidance for trusted code executing in untrusted environments. The threat model is formalized in Lean 4, relative to an explicit platform contract: the security theorem, the necessity of each assumption and which assumptions each adversary level satisfies or breaks are machine-checked, and the development is registered with the Palomar registry.

cs.CR

新论文 · v1arXiv:2611.15904

HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data

Lingxiao Kong, Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis, Zeyd Boukhers

原文摘要

Cultural heritage sites are increasingly monitored by sensor networks, but querying their data requires database expertise. Large Language Models (LLMs) offer a natural-language interface, yet over raw sensor records they lose track of which sensor, site, and time each value belongs to, and silently miscompute. We present HeriKGQA, a knowledge-graph question-answering method that confines the LLM to interpreting questions and phrasing answers, leaving computation to SPARQL and deterministic code. Questions are parsed into intents constrained by a heritage ontology aligning W3C SOSA/SSN with CIDOC-CRM, compiled into SPARQL, and answered from query results and temporal, spatial, and anomaly facts derived by a grounding layer, with error correction guarding each LLM step. On 500 questions over real data from five heritage sites, HeriKGQA reaches 99.0% accuracy, 18.2 points above the strongest of three baselines using the same LLM and receiving the same anomaly rules and answer conventions, with comparable answer quality while running almost four times faster. Without grounding, accuracy drops by 12.2 points and on anomaly questions from 99% to 66%. We report lessons from development and live deployment.

cs.CL · cs.AI · cs.DB · cs.IR

版本更新 · v2arXiv:2606.05435

DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum

Naima Tasnim, Lalitha Sankar, Oliver Kosut

原文摘要

Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains a significant practical limitation. Adaptive clipping algorithms such as AdaClip shift and scale the gradient prior to clipping and adding noise so that the clipped gradient yields a more informative descent direction. The shift and scaling parameters are selected adaptively based on the empirical mean and variance. However, in existing adaptive clipping algorithms, these empirical estimates have not been also used for momentum to accelerate training itself. On the other hand, DP-Adam is an algorithm that exploits Adam-like momentum updates based on the gradient mean and variance to accelerate training, but does not exploit these estimates for adaptive clipping. In this work, we propose Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum (DP-MacAdam), a novel algorithm that combines these two approaches so as to use the same mean and variance estimates for both clipping and momentum. We perform an analysis showing that DP-MacAdam estimates the gradient variances in a bias-free manner. In addition, we empirically evaluate the privacy and accuracy of DP-MacAdam, demonstrating that it achieves improved model utility compared to DP-SGD, AdaClip, and DP-Adam baselines, without requiring manual tuning of the clipping threshold.

cs.LG · cs.CR

版本更新 · v2arXiv:2610.38520

What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty

Hazel H. Kim, Jakub Binkowski, Ekaterina Fadeeva, Juan David Guerra, Yijie Hao, Zheng Yi Ho, Baixiang Huang, Buyun Liang 等 26 位作者

原文摘要

Hallucination remains one of the most critical challenges in deploying large lan- guage models (LLMs) reliably and safely. Yet the term is used inconsistently across the research community. We argue for a strict definition of hallucinations in LLMs. First, hallucinations should be confident incorrectness, kept separate from expressed uncertainty (UNK). UNK reveals that the model may be wrong, whereas a hallucination does not reveal it and is therefore more dangerous in prac- tice. Conflating the two obscures their distinct behaviors and makes them hard to study. Second, hallucinations should be split by a simple re-elicitation test: does any semantically equivalent prompt recover the correct response? This test probes whether the relevant knowledge is accessible. If none does, the knowledge is likely absent or inaccessible, and the error type is a confabulation (CF) that likely requires external knowledge or retraining; if some does, the knowledge is accessible from the model but applied inconsistently, and the error type is a semantic illusion (SI) that simple prompt or decoding changes can mitigate3. Re-evaluating 14 recent hallucination methods under this taxonomy yields three findings. (1) Mitigation methods are far more effective for SI than for CF. (2) Detection methods flag UNK more often than hallucinated responses (i.e., SI and CF). (3) Latent signals are more informative than output-level signals for CF. An audit of recent hallucination papers shows that most conflate these categories. We recommend reporting CF, SI, and UNK separately, and introduce a practical labeling protocol that needs only a modest number of semantically equivalent prompts.

cs.CL

版本更新 · v3arXiv:2607.12775

Learning-enabled Acceleration of Scenario-based Model Predictive Control

Trinh Tran, Binh Nguyen, Truong X. Nghiem

原文摘要

Scenario-based model predictive control (SBMPC) is a variant of model predictive control (MPC) that explicitly accounts for uncertainty by optimizing control actions over multiple predicted scenarios. However, its computational complexity increases rapidly with the number of scenarios and prediction horizon, limiting its applicability to real-time planning and control. This paper presents a learning-accelerated Alternating Direction Method of Multipliers (ADMM) algorithm for efficiently solving SBMPC problems by leveraging parallel computing and Moreau envelope learning, while maintaining high solution accuracy. We reformulate the SBMPC problems into consensus forms that can be decomposed via ADMM, separating the scenario-dependent dynamics from non-anticipativity constraints and enabling parallel updates across scenarios and time steps. Building on this decomposition, we utilize a learning-to-optimize scheme that leverages Moreau envelope learning of the cost function to accelerate the primal update in ADMM, thereby reducing computation time. The proposed framework is evaluated on a microgrid energy management problem subject to load and renewable generation uncertainties. Comparisons with IPOPT and MadNLP, two popular and modern nonlinear programming solvers, demonstrate substantial computational speedups while maintaining reliable closed-loop control performance.

math.OC · cs.LG · eess.SY

版本更新 · v2arXiv:2611.06262

SonoDyno: A Sonic Dynamometer for Engine Speed and Load Estimation from Audio

Robin Doerfler, Beat Rossmy

原文摘要

Controllable engine sound synthesis, Active Sound Design and engine order analysis all build on the relationship between the sound of an engine and its momentary operating state: its speed and its load. Recordings of engine sound are abundant in archives, sample packs and online video, yet they rarely carry time-aligned annotations of that state, which limits their applicability to controllable engine sound generation. We present SonoDyno, which estimates the engine speed, the cylinder count and an engine-normalized load intensity from a microphone signal alone, with no tachometer, no bus access and no prior knowledge of the engine configuration. A convolutional scorer of 124,302 parameters reads the energy at the engine orders, the harmonics of half the rotation frequency, in each frame at three time-frequency resolutions to jointly score cylinder count and speed, and a decoder imposes the rotational dynamics of the engine on the speed trajectory. A second head estimates the load intensity, the position of the torque between the engine's drag floor at 0 and its full-load ceiling at 1, from the order levels at the decoded speed. On recordings of engines it has never heard, with microphone position, engine type and cylinder count unknown, SonoDyno places 93 to 97% of the frames within 2% of the true speed, identifies the cylinder count with 80% accuracy and confuses the octave on fewer than 2% of the frames. On an unseen engine of a known type, the load intensity has a mean absolute error of 0.12, and the sign of the torque, driving or braking, is right on 91% of the frames. General pitch trackers fall behind even when the harmonic order of each engine is supplied: on our validation recordings and at a tolerance of 5%, the best of them places 62% of the frames within the tolerance, against 96% for SonoDyno.

cs.SD · eess.AS · eess.SP

新论文 · v1arXiv:2611.15895

Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization

Jason Bohne, Pawel Polak, Gary Kazantsev, David Rosenberg

原文摘要

Bilevel optimization is a core tool in practical machine learning workflows, including hyperparameter tuning, data reweighting, robust learning, reinforcement learning, and imbalanced classification. Hypergradient computation requires the inverse of the inner Hessian, typically estimated via a truncated Neumann series. While existing analyses focus on bias and variance, we show that the product structure of the Neumann series introduces a third source of error: skewness. We identify that, unlike ordinary gradients, whose asymmetry is suppressed by mini-batch averaging, the Neumann estimator amplifies skewness across factors, with the third-moment error growing, under weak contraction, with truncation depth, inner condition number, and per-factor noise asymmetry. This arises in many practical settings such as corrupted labels, outliers, heterogeneous or class-imbalanced datasets. To address this, we introduce the Antithetic Neumann Estimator (ANE), which pairs each Hessian sample with a mirrored counterpart around a reference Hessian and averages the resulting inverse-Hessian estimates. With an exact reference, the antithetic product retains only even-order noise, eliminating all odd-order perturbation terms; with an approximate reference, the residual odd-order contribution is bounded linearly in the reference error. ANE requires only a modification of the Hessian vector step and combines with existing stochastic or variance-reduced bilevel methods. We instantiate ANE-SGD and ANE-VR, the latter adding recursive variance reduction. Across robust regression, data cleaning, offline reinforcement learning, and imbalanced classification, ANE-based methods improve on stochastic and variance-reduced baselines on every task (20 seeds each), lowering loss by 4 to 25% relative to the best baseline; the largest gains, on robust regression, are a 25% lower test loss and a 54% higher test r-squared.

cs.LG · math.OC

新论文 · v1arXiv:2611.15849

Sharp Lower Bounds for Parallel Log-Concave Sampling

Evan Dogariu

原文摘要

How many rounds of parallel queries are needed to sample from a smooth, strongly log-concave distribution on $\mathbb{R}^d$? For every fixed condition number $κ\in (1, \infty)$, we prove that any sampler making polynomially many queries per round requires $Ω_κ(\log d)$ rounds to achieve constant total variation error in the worst case. The lower bound holds even if queries return derivatives of all orders. Together with the first-order parallel Picard algorithm of \cite{zhou2025parallel}, this establishes a depth complexity of $Θ_κ(\log d)$ for parallel log-concave sampling with $\operatorname{poly}(d)$ width. We then study centered Gaussian targets to understand how much width is needed at a given depth. From \cite{chewi2023query,zhou2026complexitygaussiansampling}, it is known that either one round of width $d$ or $\mathcal{O}(\sqrtκ \log d)$ rounds of constant width suffice for first-order Gaussian sampling. At fixed $κ$ we characterize the depth-width tradeoff interpolating between these regimes: when using $ \lceil c \log d\rceil$ rounds, if $0 < c < c_\star(κ)$ then the optimal width at constant TV error is $\widetildeΘ(d^{1-c/c_\star(κ)})$, while if $c \geq c_\star(κ)$ then it is $Θ_κ(1)$. Here, $c_\star(κ)$ is an explicit constant with $c_\star(κ) \sim \sqrtκ / 8$ as $κ\to \infty$.

cs.DS · math.PR

新论文 · v1arXiv:2611.15847

SoK: Design Choices in Tendermint BFT Consensus

Sanaz Taheri-Boshrooyeh, Yahya Hassanzadeh-Nazarabadi

原文摘要

Tendermint is a consensus protocol that tolerates Byzantine faults, implemented first by the Tendermint Core engine and now by CometBFT. Realizing the protocol's separation of agreement from execution, the Application Blockchain Interface (ABCI) of these engines keeps consensus apart from the replicated application, so one engine can serve many independent proof-of-stake chains. A sustained body of research proposes changes that span the protocol's mechanisms, from vote dissemination to block proposal and reward distribution, yet to our knowledge no survey studies the protocol and these works as one family, and broader surveys do not take Tendermint as their subject. We describe the baseline, the protocol as consolidated from its original descriptions, by its design choices. Each is a decision, such as how votes spread or how proposers rotate, through which the baseline provides safety and liveness or another property under its fault and timing model. We classify each work by the design choice it renegotiates, that is, modifies or replaces, by the properties it strengthens or weakens, and by whether its result needs a stronger model. Taking a broader perspective on that classification, we group the surveyed works' solutions into a few threads of concern in the baseline, namely its performance, the accountability of its validators, and the protection of exploitable information. For each thread, we identify the recurring strategies that their approaches follow. Together, these threads and strategies describe the current state of research on the Tendermint family. Where the strategies leave gaps, we pose future directions, each as an open question under an explicit fault and timing model.

cs.DC · cs.CR

新论文 · v1arXiv:2611.15844

Open Vision Banana: A Fully Open Recipe for Generative Visual Perception

Arpit Jadon, Valentinos Pariza, Jona Ruthardt, Ryousuke Yamada, A. Sophia Koepke, Andrei Bursuc, Yuki M. Asano

原文摘要

Recent work suggests that pretrained image generators encode real-world understanding beyond image synthesis. Vision Banana exploits this by framing vision tasks as conditional image editing. However, its data, weights, code, and implementation details are not public. We present Open Vision Banana (OVB), a fully open and reproducible recipe for converting pretrained generators into unified multi-task perception systems. Our analyses identify the design choices that matter most for generalization, including color encoding, prompt design, parameter adaptation, and task balancing. These choices interact, so individually helpful choices can hurt when combined with others. Starting from 4B and 9B parameter open-weight base models and using 2.1M-3.8M training pairs from public datasets, OVB surpasses Vision Banana's reported Cityscapes zero-shot performance (73.9 vs. 69.9 mIoU) and rivals state-of-the-art affine-invariant depth estimators. Its non-zero-shot variants come within five points of Vision Banana on referring and reasoning segmentation but remain further behind on instance segmentation. All models largely retain the base model's image-editing abilities. With legend ensembling, we introduce a test-time scaling method for generator-based perception. It segments an image under several class-color legends and fuses the results by majority vote, correcting unstable color-class bindings and improving mIoU by up to 8.7 points on Cityscapes and 15.0 points on COCO-Object without retraining. We release the dataset construction and processing pipeline, the training and evaluation code, as well as the final, intermediate, and ablation checkpoints. Project website: https://openvisionbanana.github.io

cs.CV

新论文 · v1arXiv:2611.15843

Food Critic: An Agentic Visualization System for Auditable Restaurant-Safety Reasoning

Arleth Salinas, Ishrat Jahan Eliza, Valerio Pascucci

原文摘要

Generative AI agents are increasingly being embedded into visualization systems that can search data, invoke tools, summarize evidence, and produce recommendations. However, when agents rely solely on their own knowledge, the visualization problem is not only whether the agent provides a useful answer, but also whether users can inspect how that answer is grounded. We present Food Critic, an agentic visualization system for diners' restaurant decision support that integrates public health inspection records with crowd review data. The system grounds agents under three conditions: a database-only ReAct agent, a retrieval- augmented agent with access to food-safety regulations, and an ontology-guided agent that produces structured hypotheses and typed evidence. Food Critic externalizes the agent's reasoning within these groundings as inspectable visual evidence. We evaluate LLM models with several use cases under each grounding of our agentic system. Our work positions restaurant choice as a concrete case for studying human-agent collaboration, visual provenance of agent reasoning, and the design of visual interfaces for grounded GenAI decision support.

cs.AI · cs.MA

版本更新 · v3arXiv:2605.07546

Meta-Scaling Laws: On the Invariance and Generality of Neural Scaling

Xing Han, Liu Ziyin, Suchi Saria, Paul Pu Liang

原文摘要

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks. Yet such laws are most needed precisely where they are hardest to obtain: fitting one for a new model and task pair demands expensive sweeps that typically exhaust the very compute budget the law is meant to economize. We study meta-scaling laws: relations that characterize when neural scaling behavior is preserved and predict how it changes under data transformations, enabling forecasts across domains when the shift can be approximated by a compatible transformation. We address this by identifying the right invariants: scaling laws are preserved under bijective (information-preserving) transformations of the data and modified in predictable, information-theoretically grounded ways under non-bijective transformations that lower its information resolution $ρ$: a single axis along which a law fit in one domain can be transported to another. We validate this across language, vision, and speech, and demonstrate two cross-domain applications: predicting scaling for language models trained on electronic health records from laws fit on general text, and predicting time-series classification scaling under varying levels of noise injection, recovering the data-scaling exponents to within $3\%$ error.

cs.LG

新论文 · v1arXiv:2611.15839

k-partite quantum homomorphisms

Amin Karamlou

原文摘要

$k$-partite XOR games and linear binary constraint system (BCS) games arise from systems of linear equations over $\mathbb{Z}_2$, providing distinct quantum relaxations of the same classical constraint satisfaction problem (CSP). Linear BCS games have been generalised to synchronous homomorphism games on arbitrary relational structures, with compositional semantics provided by the quantum monad. We introduce $k$-partite homomorphism games, extending $k$-XOR games from linear systems to arbitrary relational structures. This yields a framework for studying multipartite quantum CSPs and quantum homomorphisms. We characterise perfect strategies in both the tensor-product and commuting-operator models as Kleisli morphisms of suitable state-dependent graded quantum monads on a category of $k$-partite relational structures. We then study quantum advantage in the pseudotelepathic sense: the existence of a perfect quantum strategy without a perfect classical strategy. We show that synchronous and $k$-partite quantum advantage are incomparable at the level of CSP instances. The GHZ instance admits three-player quantum advantage but no synchronous commuting-operator advantage, whereas the magic-square instance admits synchronous quantum advantage but no $k$-partite commuting-operator advantage for any number of players or proper colouring. We also exhibit an explicit six-element template whose CSP is NP-complete and admits two-player quantum advantage. Finally, we prove that no bounded-width CSP template admits $k$-partite quantum advantage, even in the commuting-operator model.

quant-ph · cs.LO

新论文 · v1arXiv:2611.15835

Controlling the Probability of Unknown Unknowns in Pre-Deployment Testing of AI Systems

Rachel Li, Chris Hays, Aaditya Ramdas, Manish Raghavan

原文摘要

In pre-deployment testing of AI systems such as AI agents, a developer can often deal with known failure modes (e.g., leaking API keys, deleting important databases, or installing a malicious package) by implementing fixes or making contingency plans for when the same issue might occur again. What is more challenging are the unknown unknowns: the unseen failure modes that haven't surfaced during testing. The decision to stop testing and deploy therefore faces an inherent tradeoff: continue testing to observe more behaviors, at the cost of time and resources, or stop testing and deploy, at the risk of failure modes remaining undiscovered. How then does the developer decide when they have tested enough? To answer this, we develop an algorithm that certifies when the probability of observing an unseen failure mode is sufficiently small. The algorithm constructs an anytime-valid upper confidence sequence on this quantity, so the developer can repeatedly test a system, inspect the bound, and decide to stop when it falls below a chosen threshold without invalidating the statistical guarantee. Our problem can be interpreted as a sequential variant of the missing-mass estimation problem which gave rise to the classic Good-Turing estimator (Good, 1953). On SWE-Chat, a dataset of real-world coding agent traces (Baumann et al., 2026), we implement our procedure and show that it achieves tighter upper bounds than a simple multiple-testing corrected Good-Turing baseline, and even dominates a fixed-horizon (non-multiple-testing-corrected) Good-Turing upper confidence bound, which is not anytime valid. Additionally, to better match realistic evaluation pipelines, we extend our method to handle sampling from a different task distribution and imperfect automated failure labeling.

cs.AI · cs.CY · math.ST

新论文 · v1arXiv:2611.15829

Training Calibrated Conditional Generative Models with a Sample-Only Coverage Loss

Benjamin Remy, Raphael Rossellini, Chihway Chang, Rebecca Willett

原文摘要

Conditional generative models have become the tool of choice for sampling posteriors in scientific inverse problems, where we seek to sample images or signals conditioned on a set of indirect and noisy measurements. Yet they are often overconfident, which is a critical failure in scientific applications where accurate uncertainty quantification is essential. Existing regularizers fall short in complementary ways: differentiable coverage objectives require the model's density and do not identify the posterior, while strictly proper scoring rules such as the energy score need only samples but do not directly enforce coverage. We close this gap by introducing a differentiable loss function based on the expected coverage probability, estimated from samples alone. It applies to any conditional generative model, with no need for tractable densities or architectural changes. We prove that it is a strict divergence, vanishing if and only if the model equals the true posterior. On simulation-based inference benchmarks, it matches a density-based coverage loss without evaluating the density. On high-dimensional imaging inverse problems, it yields better-calibrated posteriors than scoring-rule regularizers, with little change in the reconstruction quality of point estimates.

cs.LG · stat.ME · stat.ML

版本更新 · v2arXiv:2605.05871

Retain-Neutral Surrogates for Min-Max Unlearning

Junhao Cai, Dohun Kim, Dowon Kim, Sung Il Choi, Chengjun Jin, Juhyun Park, Changhee Joo

原文摘要

Machine unlearning aims to make a model forget designated training data while retaining performance on the rest. In min-max unlearning, an inner adversary perturbs the model to maximize the forget loss, and the model is updated to minimize the retain loss at the resulting surrogate point. When the forget and retain gradients are positively coupled, the standard perturbation also moves toward higher retain loss, and the retain step begins by recovering that loss. We propose Retain-Orthogonal Surrogate Unlearning (ROSU), which redefines the adversary to admit only perturbations orthogonal to the retain gradient. The one that raises the forget loss fastest has a closed form, and ROSU uses it to set the surrogate point and amplifies it into the forgetting step. Under positive coupling the ROSU surrogate avoids the retain cost that coupling induces in the standard surrogate, and the difference shrinks as the gradients approach orthogonality. ROSU has the smallest accuracy gap to retraining in every vision setting (CIFAR-10, CIFAR-100, Tiny-ImageNet) and is competitive with the baselines on language benchmarks (TOFU, WMDP). The redefinition helps most under high positive coupling. Code is available at https://github.com/unlearn-ml/machine-unlearning.

cs.LG

版本更新 · v2arXiv:2510.03857

Optimized Minimal 4D Gaussian Splatting for Efficient Dynamic Scene Representation

Minseo Lee, Byeonghyeon Lee, Lucas Yunkyu Lee, Eunsoo Lee, JunYoung Jeong, Sangmin Kim, Seunghyeon Song, Joo Chan Lee 等 11 位作者

原文摘要

4D Gaussian Splatting has emerged as a new paradigm for dynamic scene representation, enabling real-time rendering of scenes with complex motions. However, it faces a major challenge of storage overhead, as millions of Gaussians are required for high-fidelity reconstruction. Compressing explicit 4D Gaussians is challenging because they exhibit heterogeneous redundancy across static and dynamic regions, and their temporal attributes make direct quantization unstable. In this work, we present OMG4 (Optimized Minimal 4D Gaussian Splatting), a framework that constructs a compact set of salient Gaussians capable of faithfully representing 4D Gaussian models. Our method progressively reduces Gaussians in three stages: (1) Gaussian Sampling to identify primitives critical to reconstruction fidelity, (2) Gaussian Pruning to remove redundancies, and (3) Gaussian Merging to fuse primitives with similar characteristics. In addition, we integrate implicit appearance compression and extend Sub-Vector Quantization (SVQ) to 4D representations with a staged quantization scheme, further reducing storage while preserving quality. Extensive experiments on standard benchmark datasets demonstrate that OMG4 achieves a favorable rate-distortion trade-off over recent state-of-the-art methods, reducing model sizes by over 60% while maintaining reconstruction quality. These results demonstrate the effectiveness of OMG4 as a practical framework for compact and high-fidelity 4D scene representation. Our source code is available at https://minshirley.github.io/OMG4/.

cs.CV

新论文 · v1arXiv:2611.15822

A Faster Scaling Algorithm for Maximum Weight Matroid Intersection

Alina Ene, Huy L. Nguyen

原文摘要

We consider the maximum weight matroid intersection problem. In this problem, we are given two matroids $M_{1}=(E,\mathcal{I}_{1})$ and $M_{2}=(E,\mathcal{I}_{2})$ and integer weights $w(e)$ on the elements $e\in E$, and the goal is to find a maximum-weight common independent set. We give a randomized algorithm that constructs an optimal solution using $\widetilde{O}(nr\log W)$ queries to the independence oracles of the matroids, where $n$ is the size of the ground set $E$, $r$ is the minimum rank of the two matroids, and $W$ is the maximum weight.

cs.DS

版本更新 · v2arXiv:2610.25403

A Faster Strongly Polynomial Time Algorithm for Submodular Function Minimization

Alina Ene, Huy L. Nguyen

原文摘要

We give a strongly polynomial time algorithm for submodular function minimization with overall running time $\widetilde{O}(n^{2}\mathsf{EO}+n^{3})$, where $\mathsf{EO}$ is the running time of a single evaluation of the function. Our algorithm improves upon the previously fastest strongly polynomial algorithms of Lee, Sidford, and Wong (FOCS 2015), Dadush, Végh, and Zambelli (SODA 2018), and Jiang, Lee, Song, and Zhang (SODA 2024) that run in time $\widetilde{O}(n^{3}\mathsf{EO}+n^{4})$. Similarly to prior works, our work combines a cutting plane algorithm with the combinatorial arc-finding framework of Iwata, Fleischer, and Fujishige (JACM 2001). We achieve our faster running time by developing an algorithm that runs the cutting plane method end to end, without restarting after discovering arcs and contracting strongly connected components.

cs.DS

版本更新 · v2arXiv:2611.11632

Characterizing Scanpath Decoding Pipelines with Perturbation Profiles

Saleh Mozaffari, Abolfazl Nadi

原文摘要

When a scanpath descriptor supports a classification, it is rarely clear what the classification rests on. We propose perturbation profiles. Five transformations each target one stated property of every scanpath (fixation order, the coupling of durations to positions, the duration distribution, orientation and handedness, and fine spatial structure) while preserving a listed set of invariants. The classifier is refit, and the change in participant-held-out AUC is the pipeline's sensitivity to that property. Intervals come from a participant bootstrap that refits the classifier; in simulations they were conservative (99.7% coverage; standard errors about 1.8 times the empirical spread). We profiled nine descriptors on thirteen binary problems from three public datasets, with a within-fold AUC and class-balanced folds and a stated rule for which sensitivities to interpret. Of 565 intervals, 95 excluded zero; 80 were robust to the pooled AUC, 20 fold partitions and longer runs (36 of them within +/-0.05 AUC), and 45 also held with boosted trees. Most came from GazeBase (322 participants). Permuting fixation order raised the AUC of a descriptor based on mean saccade amplitude, because permuted amplitude has as its expectation the mean pairwise distance, a measure of spread. A "comprehension" contrast pooled over two programs was a contrast between their layouts: it vanished among trials of the same program, and synthetic gaze drawn from the layout alone reproduced the program contrast beneath it. For native versus non-native readers, spatial jitter at the scale of text lines reduced recurrence's discrimination. A Python package is released.

cs.AI

新论文 · v1arXiv:2611.15814

Large Payments Model

Natraj Raman, Abhenandhan Manoharan, Vishwasreddy Thuniki, Dhvani Kansara, Anirudh Som, Hassan Firouzi, Kostis Gourgoulias, Laukik Hoshing 等 15 位作者

原文摘要

Payment applications such as fraud detection, authorization prediction, and payment optimization draw on overlapping transaction information. This motivates a reusable payments intelligence layer that shares learned representations and predictive signals, rather than developing predictive models independently for each task. Realizing this shared capability requires handling heterogeneous transaction fields, high-cardinality identifiers, lifecycle-dependent attributes, long histories, and rare outcomes while meeting latency and cost constraints. We present Large Payments Model (LPM), a domain-specific foundation model designed for operational use and trained from scratch on large-scale structured transaction data to learn reusable representations for payment prediction tasks. LPM employs field-specific encodings and lifecycle-aware self-supervision in two complementary architectures: the Independent variant uses hybrid masking and supports efficient per-transaction inference, while the Sequence variant incorporates entity-linked histories through compact latent representations for richer temporal context. Optional distillation enables resource-constrained deployment. We pretrain LPM on up to 400 billion tokens and study scaling, downstream performance, and representation reuse. LPM improves over strong task-specific baselines across multiple prediction tasks in Merchant and Treasury Services, demonstrating applicability in distinct payment domains. Its representations also facilitate adaptation to a target not observed during pretraining through compact task-specific components. Together with production deployment, these results position LPM as a practical basis for reusable payments intelligence.

cs.LG · cs.AI · cs.CE

新论文 · v1arXiv:2611.15810

Sparse PCA with Overlapping Supports: NP-Hardness and an FPTAS

Alberto Del Pia, Dekun Zhou

原文摘要

In sparse principal component analysis (SPCA) with several components, each must be sparse and all must be pairwise orthogonal. When the supports of the components overlap, these two requirements interact. For a covariance matrix of fixed rank, polynomial-time algorithms with optimality or approximation guarantees are known for one component, and for several components with disjoint supports or with a common support. We study the general model, with individual sparsity constants and arbitrary support overlaps. We are given a rational $n\times r$ matrix $R$ and $d$ sparsity constants $s_i \le n$, and the goal is to find an $n\times d$ matrix $X$ with orthonormal columns that maximizes $\|R^\top X\|_F^2$, such that column $i$ has at most $s_i$ non-zero entries. Here $RR^\top$ plays the role of the covariance matrix and has rank at most $r$. We show that SPCA is NP-hard even when $r = d = 2$, but admits a fully polynomial-time approximation scheme (FPTAS) when $r$ and $d$ are fixed. The returned solution has exactly orthonormal columns, and its entries are real algebraic numbers in an exact representation. For fixed $ε$, the number of steps of the algorithm is linear in $n$ up to a polylogarithmic factor. Our approach reduces SPCA to a sparse version of the orthogonal Procrustes problem, that is, to maximizing a linear function over the feasible region of SPCA. We show that this problem is NP-hard even for $d = 2$, and we give an FPTAS for it when $d$ is fixed. This FPTAS combines approximate dynamic programming over the rows, two-column updates that restore exact orthogonality, and an exact computation of the few variables for which these updates are not available.

cs.LG · math.OC

新论文 · v1arXiv:2611.15809

Fine-Grained Generative Hallucination Detection and Correction for Aerial Image Captioning

Debolena Basak, Somsubhra De, Maunendra Sankar Desarkar

原文摘要

Aerial imagery captured by unmanned aerial vehicles (UAVs) plays a vital role in applications such as surveillance, disaster response, and large-scale environmental monitoring. Automatic generation of textual descriptions for such imagery is essential for reducing manual inspection overhead and enabling better downstream decision-making. However, Multimodal Large Language Models (MLLMs), despite their impressive captioning capabilities, are prone to hallucination, producing descriptions that are inconsistent with the visual input. This problem is significantly amplified in aerial imagery due to its unique challenges such as extreme viewpoint variation, small objects, class imbalance, and ambiguous visual entities. Existing hallucination detection approaches either rely on computationally expensive large external models such as GPT-4, which perform poorly on aerial domains, or treat the problem as a rigid binary classification task, ignoring the inherent uncertainty in ambiguous cases. To address these limitations, we propose a lightweight, reference-free framework for hallucination detection and correction in free-form aerial image captioning. Our method leverages state-of-the-art MLLMs, specifically InternVL3 and Qwen2.5-VL, to detect hallucinated content in generated captions with minimal computational overhead. Detected hallucinations are corrected through a dedicated refinement module that improves the factual consistency of the original captions. Extensive experiments on the Labelled Illusion Dataset (LID) demonstrate that our framework significantly reduces hallucination rates while remaining practical for real-time deployment in resource-constrained environments. Code is available at: https://github.com/Debolena7/Hal_Detect.

cs.CV · cs.AI · cs.CL

新论文 · v1arXiv:2611.15804

Computational Explanations of Semantic Universals

Shane Steinert-Threlkeld, Jakub Szymanik

原文摘要

Despite their differences, the languages of the world share many deep features when it comes to how they express meaning. These semantic universals are likely to reflect shared aspects of human cognitive, communicative, and social structure. Recent advances in cross-linguistic semantics and computational linguistics allow us to develop explanations of the sources of such properties. This Element presents a body of work doing just that: we explicate a framework for providing computational explanations of semantic universals and then describe several such explanations using principles of ease of learning and efficient communication. Empirical domains include quantifiers, color terms, modals, and indefinites. After providing these explanations, we provide a discussion of future directions for advancing the explanatory power of computational methods in semantic typology.

cs.CL

新论文 · v1arXiv:2611.15803

Statistical-to-computational gaps in central limit theorems for high-dimensional tensors

Debsurya De, Dmitriy Kunisky

原文摘要

We study high-dimensional central limit theorems (CLTs) as hypothesis testing problems, comparing the number of summands needed for statistical and computational indistinguishability of the normalized sum from the limiting Gaussian distribution as the dimension and number of summands grow together. For the off-diagonal entries of sums of i.i.d. rank-one tensors formed from standard Gaussian vectors (equivalently, the problem of distinguishing Wigner from Wishart tensors), we prove total variation bounds sharpening previous estimates of Mikulincer (2020) and give matching polynomial-time tests. This shows that the statistical and computational thresholds coincide for this CLT, contrary to a proposal by Kunisky, Moore, and Wein (2024). On the other hand, we also show that, for tensors of order at least three, sufficient Gaussian dilution of the summands by adding independent Gaussian noise and rescaling gives a CLT model with a statistical-to-computational gap (in the above setting and ones with more general rank-one summand distributions). To the best of our knowledge, such a phenomenon has not been observed before in any high-dimensional CLT. In particular, in the relevant parameter regimes, we show that a brute-force search achieves strong detection, while polynomials of degree up to $n^{Ω(1)}$ cannot achieve strong separation. The latter lower bounds control low-degree $χ^2$-divergences by a novel method based on cumulant generating functions, and we further illustrate the use of these tools by applying them to masked tensor CLT models where only a prescribed subset of tensor entries is revealed.

math.ST · cs.CC · math.PR

版本更新 · v3arXiv:2609.13630

Minimum central circles: an effective characterization of the global asymptotic constant

Maurizio Falconi

原文摘要

Let $R^\ast(n)$ be the minimum radius of a central circle externally tangent to nonoverlapping circles of radii $1,\ldots,n$. We prove that $R^\ast(n)=C_\ast n^2+o(n^2)$ and give finite linear programs that enclose $C_\ast$ with prescribed error. An exact angular comparison reduces the problem to marked points on a line with separation at least the geometric mean of each pair of marks. Concatenation with bounded joining cost and reassignment to the prescribed normalized radii prove existence of the limit. Balanced finite-word programs give a bracket of width $(1/k+1/r)/π$, before directed arithmetic error, using $k$ types and words of length $r$. We also obtain explicit geometric bounds. For the upper bound, we recover finite and countable reflected-block constructions by actual permutations, retaining all pair constraints. A coupled terminal-subset argument gives an explicit lower bound strictly above $1/8$. Together these give $C_{\rm term}+η_{\rm width}\le C_\ast\le U_4$. The lower endpoint comes from the terminal-subset argument, and the upper endpoint from the four-block construction; neither is asserted sharp. The finite-word scheme establishes computability; efficient high-precision evaluation and the structure of global optimizers remain open.

math.MG · cs.CG

版本更新 · v4arXiv:2607.28654

Minimum central circles: chain order, seam obstructions, and exact finite certification

Maurizio Falconi

原文摘要

We minimize the radius of a central circle externally tangent to pairwise non-overlapping circles of radii $1,2,\ldots,n$. We first study the adjacent-chain relaxation, which imposes only the constraints between consecutive circles. Its angular kernel has strict anti-Monge structure, so Supnick's classical theorem supplies a fixed minimizing cyclic order at every central radius. A monotonicity argument transfers this order to the chain-radius problem. Full geometric feasibility requires every pairwise angular constraint. We give a self-contained criterion for feasibility of the canonical Supnick necklace on $\{k,\ldots,n\}$ at its chain root, expressed by one seam deficit. For every fixed $k$ the seam eventually fails and its failure persists. We prove the complete classifications for $k=1,2,3$, whose first failures occur at $n=8,13,17$, respectively. For the global infimum, we certify rational brackets $L_n<R^*(n)\le U_n$ of exact width $10^{-11}$ for every $3\le n\le14$. The lower proof combines independently enclosed angles, integer dynamic programming, and complete cyclic-order coverage; the upper proof uses exact rational Cartesian witnesses. The certificate does not depend on floating-point pruning in the numerical search. We distinguish these finite brackets and fixed-order theorems from numerical descriptions of floating circles and from unresolved claims about all optimal placements.

cs.CG

新论文 · v1arXiv:2611.15802

RUMI: A Robotiq-Matched Universal Manipulation Interface for Robot Learning with Augmented Reality and Haptic Feedback

Kevin Avdiu, Seongjin Bien, Yannik Blei, Philine Meister, Johannes Hechtl, Philipp Schmitt, Kai Wurm, Georg von Wichert 等 9 位作者

原文摘要

Many manipulation tasks require carefully controlled contact forces for successful execution, yet large-scale, force-aware datasets remain scarce. Handheld interfaces can help by transmitting interaction forces directly through the operator's arm, but most existing designs are tailored to simple linear grippers and do not match the nonlinear mechanics of widely used robotic grippers. We present RUMI, a handheld universal manipulation interface matched to the Robotiq 2F-85 with exchangeable fingertip sensors that preserves the target gripper geometry while enabling natural input before contact and force measurement after contact. By integrating the tracking system into a virtual reality headset, our method provides real-time augmented reality feedback about the kinematic feasibility of motion on the target robot platform. We further introduce a haptic feedback mechanism that supports force-aware teleoperation for simulated and real robots. A user study shows fewer episodes containing joint-limit violations with live robot visualization and pose initialization (3/50) than without augmented reality (16/50). We additionally train imitation policies from demonstrations, collected using two different fingertip modalities enabled by the gripper-matched hardware, and assess the haptic interface's capability for collecting force-aware teleoperation datasets in simulation.

cs.RO · cs.AI

版本更新 · v2arXiv:2606.02879

Direct Informed Sampling on Riemannian Manifolds via Loewner Order Lower Bounds

Phone Thiha Kyaw, Jonathan Kelly

原文摘要

Informed sampling techniques accelerate sampling-based motion planners by focusing the search on promising regions of the state space, yet most existing methods rely on Euclidean heuristics that become inadmissible under configuration-dependent Riemannian metrics. While scalar eigenvalue bounds restore admissibility by uniformly scaling the Euclidean distance, they discard the directional structure of the metric, producing overly conservative informed sets. We propose a matrix-valued admissible heuristic that exploits the Loewner order on symmetric positive definite matrices to compute the tightest constant lower bound on the metric tensor while preserving its full directional structure. The Cholesky factorization of this bound defines a linear map to an isotropic Euclidean space in which the Riemannian informed set reduces to a standard prolate hyperspheroid, enabling direct, rejection-free sampling using existing algorithms. Experiments on manipulation tasks with a 6-DoF UR5, 7-DoF Franka, and 14-DoF PR2 under three distinct Riemannian metrics show that our heuristic produces consistently tighter informed sets than both the Euclidean and scalar eigenvalue bounds, accelerating convergence across multiple state-of-the-art asymptotically optimal planners.

cs.RO

版本更新 · v3arXiv:2610.04792

Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness

Songyuan Sui, Zhen Tan, Mohan Zhang, Rana Muhammad Shahroz Khan, Xia Hu, Tianlong Chen

原文摘要

Missing modality remains a longstanding challenge in multimodal learning. Existing methods typically address this issue through modality recovery or adaptive strategies. However, they overlook models' internal cross-modal dependencies formed during multimodal training, which later impair robustness. We systematically characterize a counterintuitive deployment-time failure mode: models trained on full modalities can underperform unimodal models when one modality is missing at inference time. This pattern appears across diverse architectures, such as fusion models, CLIP-style two-tower models, and vision-language models. We show that such degradation is closely associated with learned cross-modal dependencies in the principal parameter subspaces. Multimodal training induces structured rotations of these subspaces, particularly in cross-modal interaction layers. These rotations are associated with reduced task-aligned margins and larger task-aware representation harm under missing-modality inputs. We propose Geodesic Unlearning (GU), a lightweight parameter-editing method that leverages Grassmannian subspace geometry for structured subspace correction to improve missing-modality robustness. It rotates the principal input subspace toward a unimodal reference along a geodesic path. We prove that this correction minimizes the distance to the reference within a fixed subspace-distance budget. Experiments across architectures and datasets show that GU improves performance under missing-modality inference while preserving full-modality accuracy, outperforming strong missing-modality robustness baselines. These findings support a geometric view of deployment-time missing-modality degradation and suggest localized subspace editing as a practical route for robustness correction.

cs.AI · cs.CV