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

+1208新增论文
+950其中 AI 相关
+153已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-18 14:10各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 15:41 — 2026-11-18 15:41(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:2026-11-18 04:28最近发现新增版本:2026-11-18 14:10库内论文最新更新时间:2026-11-18 08:00

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

26,057 已收录论文21,704 AI 相关7,828 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 19,291 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
新论文 · v1arXiv:2611.11068

Discrete Diffusion Playground: A 2D Benchmark for Discrete Generative Models

Justin Shao, Sihyun Park, David Ryan Koes, Maria Chikina

原文摘要

Discrete diffusion is a promising framework for categorical generative modeling, but current evaluation protocols often fail to reveal whether models have actually learned the target distribution. We introduce the Discrete Diffusion Playground, a diagnostic benchmark that converts known 2D continuous distributions into binary token sequences through an exact discretized bijection. This creates a rare setting in which models are trained on discrete sequences, but generated samples can be decoded back into 2D and compared directly against a known ground-truth distribution. The benchmark spans smooth Gaussian mixtures and tilted checkerboards with sharp boundaries, disconnected support, and coordinate-dependent structure, allowing it to expose failures that are invisible in standard proxy metrics. It supports exact grid divergences, Wasserstein distances, density visualizations, and nonparametric two-sample tests, providing both quantitative evaluation and interpretable failure diagnosis. Using this testbed, we show that masked diffusion models can learn meaningful adaptive reveal orders but remain less stable than autoregressive baselines on smooth targets and largely fail on tilted checkerboards, where autoregressive models preserve the target geometry. Control experiments with reversed and interleaved token orderings show that autoregressive performance is not explained by favorable bit order alone. The Playground provides a simple but stringent benchmark for stress-testing discrete generative models and for developing evaluation metrics that detect real distributional mismatch rather than proxy performance. Our code is available at https://github.com/shaojus/DiscreteDiffusionPlayground .

cs.LG

新论文 · v1arXiv:2611.11066

Rescene-ESM: an Earth system model built around a frozen AI weather model

Minjong Cheon, Kaoru Kakinuma

原文摘要

Earth system models underpin climate projections, but their cost limits how many scenarios, ensemble members and impact pathways can be explored. Machine-learning weather models forecast as skillfully as physics-based models at a fraction of the cost, yet coupled to an ocean they have produced weak El Nino variability or have learned it from climate-model output, and none carries the climate through rivers to the people exposed to it. Here we present Rescene-ESM, an Earth system model whose coupler, YAHO, yokes a frozen 20.8-million-parameter AI weather model to physically formulated ocean, sea-ice, land, river, carbon and energy components constrained by observations. Adding the couplings one at a time shows what each contributes: over a climatological ocean the AI atmosphere varies from year to year by a third of the observed amount over the oceans, and an interactive mixed layer, an equatorial wave ocean, the residual of the observed sea surface temperature (SST) equation as stochastic forcing and the land's moisture flux raise this step by step and bring El Nino and its teleconnections, leaving the mean climate almost unchanged. The full model simulates about 1,000 years per day on one graphics processing unit, holds the observed climate for a thousand years without drift, reproduces the observed 1979-2022 global warming, carries forced change with a physically based structure around the frozen network (transient climate response 1.60 K), routes runoff to 212 river gauges with a median seasonal-cycle correlation of 0.79 and, driven by emissions, separates the heatwave exposure of an SSP1 and an SSP3 world by a factor of 4.7 in 2081-2100, three-quarters of it through the warmer climate.

physics.ao-ph · cs.LG

版本更新 · v2arXiv:2608.06250

Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification

Alex Buna, Shirley Xiaoqi Liu, Patrick Rebeschini

原文摘要

In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic loss diverges in norm while converging in direction to a max-margin interpolating classifier, whose implicit bias can be statistically suboptimal. In this work, we show that early stopping can overcome this suboptimality: in a Gaussian mixture model with label-flipping noise, GD stopped at an appropriate oracle time achieves minimax-optimal excess zero-one risk for covariance spectra with fast and continuous decay, including polynomial and exponential spectral decays. Our analysis combines a sharp upper bound for the early-stopped iterate with a matching statistical lower bound over arbitrary classifiers, yielding optimal rates that are validated by experiments. A central technical contribution is a new calibration result that converts excess logistic risk into excess zero-one risk; it handles the model misspecification induced by the label-flipping noise, and removes the square-root rate in standard bounds. We also establish a lower bound for linear interpolators, showing that interpolation can require exponentially more samples than early stopping to achieve the same excess risk.

stat.ML · cs.LG

新论文 · v1arXiv:2611.11065

Analysis of the Effect of Doppler on Direct-to-Cell: Real-World Performance and Proposed Improvements

Yuxi Chen, Muhammad Iqbal Rochman, Kyler McCormack, Jakob Kotz, Monisha Ghosh

原文摘要

Direct-to-cell (DtC) satellites serve unmodified LTE phones today from low Earth orbit, where the satellite's motion creates Doppler shifts of tens of kHz. Since large offsets such as these cannot be compensated adequately by the user equipment (UE), the satellite pre-compensates the Doppler shift of each beam, but it can do so for only one reference point in the beam. A UE elsewhere in the beam still has to compensate a residual offset; previous field studies report residuals of up to 10 kHz, beyond the $\pm$7.5 kHz that the 15 kHz subcarrier spacing can resolve. In this paper we corroborate this effect with our own detailed measurements of Starlink transmissions and further correlate ineffective handover performance to inadequate residual offset compensation. We analyze the Doppler compensation problem with detailed standard-specific simulations and propose a compensation method at the UE, based on the location of the UE with respect to the beam reference point used for the Doppler compensation and the known satellite location, that improves the efficiency of handover. With UE cell-specific pre-compensation, the neighbors are identified, read correctly and handed over to in time rather than lost to radio-link failure.

eess.SP · cs.IT

版本更新 · v2arXiv:2610.03502

Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. Mridha

原文摘要

Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interpretability-verification boundary certifies descriptions of a model: what a circuit computes, or whether it faithfully explains the whole. We instead certify the behavioral effect of an edit: that disabling a circuit removes one skill and provably preserves another, for every input in a region; a feature non-interference guarantee in the information-flow-security sense. We demonstrate such certified edits from toy ReLU networks up to a standard softmax + LayerNorm transformer, proving removal and preservation over continuous embedding-space regions and reaching roughly 9x the input-perturbation dimension an exact solver can handle by switching to sound bound propagation. Furthermore, we prove that no finite deterministic black-box test can certify removal, exhibiting an edit that passes exhaustive testing yet provably fails on a survivor pocket that can be made arbitrarily small. Guarantees hold on small, standard-architecture networks and, like any removal claim, presuppose that the target skill admits a decidable specification, a property which real-world harms may not have.

cs.LG · cs.AI · cs.CR

新论文 · v1arXiv:2611.11064

GARP: Real-Time Generative Agents on Local Hardware in a Game Engine

Piero Molino, Patrick John Chia, Federico Bianchi, Jonathan P. Chen, Paul Szerlip

原文摘要

Generative agents are game characters whose plans, conversations, and memories are written on the fly by a large language model (LLM). The original Generative Agents demonstration used cloud inference in a custom simulation. We present GARP, a platform for real-time generative agents inside Godot, and describe the Character Behavior System used in GARP 2. The complete loop runs on local hardware using a 3B-parameter open-weight model and no cloud service. Alongside the original planning, memory, and reflection, GARP gives each agent an emotion system driven by LLM appraisal, four graded personality axes drawn from the Big Five that set simulation parameters as well as prompt text, six needs whose urgency grows over time, and pairwise relationships updated after every conversation. The system narrows 50+ candidate actions to typically 3-8, constrains model responses with JSON schemas, and surfaces important memories in decision prompts. A layered optimization strategy (an adjustable game clock, decisions taken ahead of need, multi-tier caching, prompt compression, and fully asynchronous execution) keeps the game responsive while the model thinks. In a nine-scenario evaluation, 25 of 27 runs passed log-based checks. Both failures occurred in the birthday party scenario, where one guest omitted the event from their daily plan.

cs.AI · cs.HC · cs.MA

版本更新 · v3arXiv:2606.07642

Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View

Dongdong Wang, Alina Hagen, Isabelle Gatmaitan, Hao Zhou, Yiwen Dong, Shabboo Valipoor, Vivian W. H. Wong, Lingyao Li

原文摘要

Assessing built-environment interaction, such as wheelchair accessibility, is challenging because real-world mobility is shaped by context-dependent and temporary barriers that are difficult to capture at scale. This paper examines whether vision-language models (VLMs) can identify potential accessibility barriers from Google Street View (GSV) imagery. We propose an expert-guided retrieval-augmented framework that combines GSV imagery, ADA-informed guidance, and expert-derived rubrics to evaluate multiple accessibility dimensions. We collect a campus-scale dataset at the University of Florida, linking 407 unique GSV locations with GPS-derived wheelchair dwell behavior as a proxy for potential mobility friction. Results show that VLM ratings are negatively correlated with dwell time and exhibit distributional similarity, with the expert-guided configuration strengthening the correlation from $r=-0.40$ to $r=-0.54$ for the strongest model. Visual cue analysis further shows that features such as curb ramps and crosswalks are associated with higher VLM accessibility scores, while correspondence remains limited for subtle surface conditions, transient obstructions, and viewpoint-dependent barriers. Overall, our findings demonstrate the potential of expert-guided VLMs for scalable preliminary accessibility screening and prioritizing locations for further investigation.

cs.CV · cs.CY

版本更新 · v13arXiv:2602.16291

A Calculus of Inheritance

Bo Yang

原文摘要

Just as the $λ$-calculus is a pure functional programming language built from three primitives (abstraction, application, variable), we present inheritance-calculus, a pure declarative programming language built from three primitives (mixin, definition, reference). We introduce multi-target $\mathtt{this}$ to solve the problem that inheritance conflicts with modularity, and thereby unify object-oriented and configuration constructs: modules, classes, objects, methods, fields, and locals become a single mixin abstraction, and inheritance becomes simply set union, the deep merge of configuration languages. Consequently, composition is commutative, idempotent, and associative, structurally eliminating the multiple-inheritance linearization problem; the inheritance relation has substitutability; every path of every program can be inherited and extended; every subtree can be split into parts that, inherited together, behave as the whole; and programs have no side effects and cover every input. We call these properties modularity by construction. The calculus has no functions, yet it macro-expresses the lazy $λ$-calculus and is more macro-expressive than it in Felleisen's sense. Its semantics is first-order, denotational, and evaluated by tabling, even for cyclic inheritance hierarchies. Inheritance-calculus is distilled from MIXINv2, an implementation in which the same code acts as different function colors and ordinary arithmetic agrees with the relational semantics of logic programming.

cs.PL · cs.SE

版本更新 · v2arXiv:2505.10877

Graph and Simplicial Complex Prediction Gaussian Process via the Hodgelet Representations

Mathieu Alain, So Takao, Xiaowen Dong, Bastian Rieck, Emmanuel Noutahi

原文摘要

Predicting labels for graph-structured data is crucial in many scientific applications. Recently, Gaussian processes with graph-level inputs have been proposed as flexible non-parametric models for classification tasks. In this work, we extend this framework to regression tasks and to simplicial complexes, enabling the modelling of attributes defined on edges and higher-order simplices. Drawing on Hodge theory, we construct representations based on the Hodge decomposition, allowing the model to distinguish between exact, co-exact, and harmonic signal components. We introduce Hodgelet representations as rich, learnable topological descriptors of simplicial complexes and show that our framework improves predictive performance across a range of applications. Our work broadens the applicability of Gaussian processes to prediction tasks at the graph and simplicial-complex levels.

cs.LG · cs.AI

版本更新 · v4arXiv:2606.13898

HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing Model Serving

Haoran You, Yotam Nitzan, Lingzhi Zhang, Yifan Gong, Mang-Tik Chiu, Connelly Barnes, Yan Kang, Yuqian Zhou 等 11 位作者

原文摘要

Creative image editing tools, such as Adobe Photoshop's Remove and Generative Fill buttons, are central to everyday customer use and account for a major share of traffic. However, current generative AI models face significant latency challenges, which become even more pronounced as the field transitions from convolution-based U-Nets to Diffusion Transformers (DiTs). In our evaluation on hundreds of representative image editing samples spanning a wide range of mask ratios, the DiT module alone accounts for an average of 73% of the total model latency, even after being distilled from 50 timesteps down to 8 timesteps. To tackle this challenge, we propose $\textbf{HiLo-Token}$, an input-adaptive token compression framework that allocates a larger token budget to high-frequency, rich-context regions while assigning fewer tokens to low-frequency areas. Specifically, for the editing region specified by the user mask, we retain all tokens within a dilated mask to preserve strong locality and contextual relevance. Outside the editing region, we introduce a simple yet effective high-frequency token selection strategy based on spatial frequency to capture important local details, while using tokens from a heavily downsampled image to represent low-frequency components and preserve the coarse global structure. Extensive experiments on production-level evaluation data validate the effectiveness of the proposed method, which achieves 3.13$\times$, 2.59$\times$, and 1.67$\times$ DiT speedups on A100-80GB for image editing tasks across small, medium, and large mask ratio categories with average ratios of 6.38%, 15.92%, and 35.36%, respectively, without any regression in generation quality. In production, where the editing pipeline is served as disaggregated, independently autoscaled GPU workers, these per-request savings translate into a 33% reduction in the GPUs required to serve the models.

cs.CV · cs.AI

新论文 · v1arXiv:2611.11063

Target Recoverability under Selective Labels: A Failure Mode in ECG-Based Acute Coronary Syndrome Prediction

Alexander Schubert, Anton Håkansson, Ziad Obermeyer

原文摘要

Medical machine learning models often learn from diagnoses observed only in patients clinicians chose to test. The biases of such selective labels are well known, but less understood is what happens when a diagnosis includes cases the model's inputs cannot detect. Because testing decisions draw on information the model does not see, these cases can appear predictable among tested patients, producing relationships that fail, and can even reverse, among the untested. We formalize this mechanism and show in simulations that it worsens as testing becomes more selective or undetectable cases more common, while models trained only on detectable cases remain informative. We empirically study electrocardiogram (ECG)-based prediction of acute coronary syndrome (ACS), which is confirmed only by invasive testing and whose subtypes differ in how clearly they appear on the ECG. Three ECG foundation models fine-tuned on revascularization, our ACS proxy, performed well among catheterized patients (AUROC 0.740-0.770) but worse than chance for 30-day major adverse cardiovascular events among untested patients (AUROC 0.381-0.478). Models trained on ECG-visible subtypes retained discrimination (AUROC 0.680-0.709), whereas a model trained on unstable angina, which can occur without ECG changes, was inversely related to risk (AUROC 0.310). Under selective labels, effective learning therefore requires prediction targets that can be inferred from the model's inputs and evaluation in the intended deployment population, which often extends beyond the patients who were tested.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11062

What Does Multiple Choice Actually Measure? Disentangling Video Understanding from Option Exploitation

Elliott Piercy, Justin Chan, Sepand Dyanatkar

原文摘要

Video understanding evaluations are intended to measure a model's proficiency in video perception and task solving. However, current VideoQA benchmarks struggle to isolate these capabilities due to their reliance on multiple-choice (MC) answer guidance, language priors, and fragile scoring pipelines. Disentangling these confounding factors reveals how much of a model's score is supplied by the evaluation context rather than earned through faithful perception. Across six VideoQA benchmarks of varying length, we find that accuracy is significantly above chance without any visual input. This is caused by shortcutting and option-prior reliance. We express these effects in the language of faithfulness: option-exploitation and answer-conditioned reasoning traces are unfaithful even when they are correct. Together, our results show that a VideoQA score is jointly determined by language priors, option timing, and how outputs and labels are converted into correctness. We produce a novel Option-Delayed Replay (ODR) mechanism that discloses options at controlled stages of an open-ended (OE) trajectory, to obtain objective MC scores from faithful option-free inference. Our work demonstrates that agentic methods with ODR and faithful inference can match option-exploiting performance. Finally, we formalize our diagnostic collection and ODR as a reproducible evaluation protocol, and we release a human-relabelled edition of LVBench (correcting $20.5\%$ of keys) to remove annotation noise as a confounding variable.

cs.CV

新论文 · v1arXiv:2611.11061

Symplectic Normal Coordinates Flow for Generative Modeling of Hamiltonian Systems

Christopher M. Pierce

原文摘要

In conditioned generative models of physical systems, the densities at different values of the conditioning parameters are often related through symplectic transformations. For stable linear Hamiltonian systems, there exists a symplectic transformation to "normal coordinates" such that the dynamics is reduced to rotations in each phase-space plane. This picture extends to the nonlinear case where, away from resonances, the Birkhoff normal form again consists of rotations in phase space, now with amplitude dependence. In this work, we introduce an invertible symplectic flow layer consisting of amplitude-dependent rotations in learned normal coordinates. We derive the condition under which the nonlinear rotation layer is symplectic and detail an architecture that guarantees it. Experiments are carried out on three conditional generative modeling problems: a synthetic chain of coupled nonlinear oscillators and two problems from accelerator physics. We show empirically that normalizing flows with the new layers achieve competitive or superior negative log-likelihoods compared to baseline flows, with gains that grow with the strength of the nonlinearity on the synthetic system.

physics.acc-ph · cs.LG

新论文 · v1arXiv:2611.11057

Symbolic Synthesis with Token-Level LLM Guidance

Derek Egolf, Stavros Tripakis

原文摘要

We propose a synergistic combination of classical program synthesis techniques and contemporary large language models (LLMs) to solve the problem of recursive program synthesis from first-order logic specifications. Our approach leverages the strengths of both paradigms: we use LLMs as a source of statistical bias to guide the search for a correct program. At the same time we use techniques from classical synthesis to short-circuit on semantically incorrect prefixes and to avoid sampling semantically equivalent responses. The statistical bias is derived from the next-token distribution of an LLM, which is highly context-dependent. We operate with the understanding that (1) there is some class of synthesis instances that can be discharged by small models and symbolic tools, and (2) every other instance can be decomposed into these instances. Therefore, our intention is to expand the reach of small, open-weight LLMs and symbolic synthesis techniques, not to compete with proprietary frontier models on every possible instance. These are different tools for different jobs. In our experimental evaluation, we find that our method solves more benchmarks than either small LLMs or classical synthesis techniques alone. Our method solves 30/32 benchmarks using only a Qwen2.5 model with 32 billion parameters. Qwen2.5 solves 0 benchmarks on its own, and only solves a few additional benchmarks when combined with traditional constrained decoding techniques.

cs.PL

版本更新 · v2arXiv:2604.10290

AI Organizations are More Effective but Less Aligned than Individual Agents

Judy Hanwen Shen, Daniel Zhu, Siddarth Srinivasan, Henry Sleight, Lawrence T. Wagner, Morgan Jane Matthews, Erik Jones, Jascha Sohl-Dickstein

原文摘要

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business goals, but less aligned, than individual AI agents. We examine 12 tasks across two practical settings: an AI consultancy providing solutions to business problems and an AI software team developing software products. Across all settings, AI Organizations composed of aligned models produce solutions with higher utility but greater misalignment compared to a single aligned model. Our work demonstrates the importance of considering interacting systems of AI agents when doing both capabilities and safety research.

cs.AI

版本更新 · v2arXiv:2610.05516

Distributed Learning of $α$-Potential Functions in Strategic Multi-agent Systems

Yifei Chen, Chinmay Maheshwari

原文摘要

We study the problem of computing the tightest \(α\)-potential approximation of a general-sum game over continuous action spaces, within a prescribed class of potential functions and when each player has access only to its own utility function. The difficulty is twofold: the approximation error involves a worst-case search over an infinite set of unilateral deviations, and the required utility information is distributed across players. For a linear-in-parameters potential class, we use an exact finite-tuple reformulation that separates the problem into a global outer search over deviation tuples and distributed convex inner problems. We develop a primal--dual inner oracle tailored to this structure and establish a uniform one-sided accuracy guarantee. This oracle can be combined with global outer search to obtain an end-to-end guarantee on the outer optimization error. We also develop a projected zeroth-order outer method as a computationally lighter alternative for higher-dimensional problems. Numerical experiments illustrate the accuracy--computation tradeoff between the two outer-search methods and show that the proposed optimization framework can improve upon analytical \(α\)-potential constructions.

cs.MA · cs.GT · eess.SY · math.OC

新论文 · v1arXiv:2611.11055

But It Was True When I Checked: Compiling SHOP-Style Method Preconditions into Partially-Ordered HTN Planning

Harrison Oates

原文摘要

Method preconditions specify when a method may be applied in hierarchical task network (HTN) planning, but their meaning differs under two established semantics. The SHOP planners, like the classical HTN formalism of Erol, Hendler and Nau, require the precondition to hold immediately before the method's first action. HDDL, the input language of the International Planning Competition's HTN track, instead introduces an auxiliary action to check it; under partial order, unrelated actions may invalidate the precondition before the method starts. HDDL's designers adopted this weaker semantics because the first-action reading could not easily be compiled. Subsequent work has repeatedly identified its compilation under partial order as an open question, with existing transformations limited to total order. We give a compilation of the first-action semantics into standard partially ordered HTN planning without method preconditions using only two additional facts, thereby resolving a longstanding question in the HTN planning community.

cs.AI

版本更新 · v2arXiv:2609.14802

From matrix inversion to constraints: provably tighter confidence regions for importance weights in label shift

Mushan Li, Kihyun Han, Yanyuan Ma

原文摘要

Importance weights are essential in domain adaptation under label shift, yet their utility is often undermined by the finite sample uncertainty associated with their estimation. Existing methods typically analyze this uncertainty through Gaussian elimination on interval-valued linear systems, which leads to overly conservative confidence regions and inefficient downstream applications. We propose a paradigm shift from inversion-based inference to a direct matrix constraint framework. We use this framework to define a joint confidence region and extract marginal intervals via linear programming, deriving provably tighter bounds for importance weights while maintaining exact finite-sample validity. Furthermore, we analyze the confidence region's geometry and provide the theoretical results for its diameter bounds. Evaluated across text, image, multimodal benchmarks, including AGNews, MNIST, CIFAR-10, N24News, and a real-world autonomous driving dataset, nuImages, our approach consistently yields shorter confidence intervals and smaller prediction sets than inversion-based methods.

stat.ML · cs.LG

版本更新 · v3arXiv:2602.14320

Catalytic Tree Evaluation From Matching Vectors

Alexandra Henzinger, Edward Pyne, Seyoon Ragavan

原文摘要

We give new algorithms for tree evaluation (S. Cook et al. TOCT 2012) in the catalytic-computing model (Buhrman et al. STOC 2014). Two existing approaches aim to solve tree evaluation (TreeEval) in low space: on the one hand, J. Cook and Mertz (STOC 2024) give an algorithm for TreeEval running in super-logarithmic space $O(\log n\log\log n)$ and super-polynomial time $n^{O(\log\log n)}$. On the other hand, an earlier algorithm of J. Cook and Mertz (STOC 2020), run on a catalytic tape, solves TreeEval in logarithmic $O(\log n)$ free space and polynomial time, but with polynomial $O(\sqrt{n})$ catalytic space. We show that the latter result can be improved. We give a catalytic algorithm for TreeEval with logarithmic $O(\log n)$ free space, polynomial runtime, and subpolynomial $2^{O(\log^εn)}$ catalytic space (for any $ε> 0$). Our result also implies an improved simulation of time by catalytic space, via the reduction of Williams (STOC 2025). Our TreeEval algorithm comes from a framework, inspired by private information retrieval, that generically reduces tree evaluation to two combinatorial objects: matching-vector families and decoders (a new object we define that closely resembles decoding polynomials). These ingredients' parameters directly govern an algorithm's resources: the vectors' dimension determines its catalytic space, and the decoder's sparsity determines its free space and runtime. In addition to enabling our new algorithm, this framework explains existing tradeoffs, for example why the Cook-Mertz algorithm needs super-logarithmic space but no catalytic tape. It also lets better matching-vector families or decoders plug in directly to give better algorithms.

cs.DS

新论文 · v1arXiv:2611.11050

Floquet-Parameterized Koopman-MPC for Tracking Periodic Orbits

Kartik A. Pant, Vishnu Vijay, Yufei Zhu, Xintong Deng, Taewoo Nam, Inseok Hwang

原文摘要

Designing real-time control for nonlinear systems to track periodic orbits can be challenging, especially for complex and coupled dynamical systems (e.g., tethered kites), where the true model parameters are hard to obtain. To address this, we propose a physics-informed Koopman learning approach that incorporates periodic-orbit stability directly into the learned linear predictor. The approach combines the underlying periodic structure of the dynamics along with periodic state-input trajectory data to learn physically consistent linear predictors (in lifted/observable space). We leverage Floquet theory, which studies the stability of periodic orbits in nonlinear systems, to obtain the periodic stability information of a given orbit via a monodromy matrix (i.e., the state transition matrix over an entire period). Subsequently, we impose open-loop monodromy constraints to learn Floquet-parameterized linear predictors using a least-squares Extended Dynamic Mode Decomposition (EDMD) formulation, thereby constraining the search space and aiding in Koopman learning. We then utilize these linear predictors to design a model predictive control (MPC) law for tracking periodic references. Finally, we evaluate the designed framework on a cartpole system under periodic forcing and compare it against a purely data-driven baseline.

cs.RO · eess.SY

版本更新 · v3arXiv:2606.17342

Learning a Maximum Entropy Model for Visual Textures using Diffusion

Xinyuan Zhao, Eero P. Simoncelli

原文摘要

Visual textures -- spatially homogeneous image regions containing repeated elements (e.g. a field of grass, the bark of a tree) -- are ubiquitous in visual scenes and provide important cues for recognizing and analyzing materials, surface geometry and objects. A number of existing texture models extract essential statistics from a single texture image, and can then generate high-quality samples that are visually similar to the original by matching these statistics. However, their statistics are either hand-designed or based on a network pretrained for another purpose (e.g., object recognition). Here, we develop the first principled method for unsupervised learning of a set of statistics that are used to constrain a maximum entropy probability model for texture. We leverage methods developed for generative diffusion models to derive training and sampling procedures, and compare these to the traditional method of sampling via matching the statistics. Despite the compactness of our trained model (512 statistics), it generates texture images whose quality is as good as or better than the current state-of-the-art model (~177k statistics), both visually and by quantitative perceptual scoring using DreamSim. Finally, we show that images generated from parameters lying along a line between the parameter vectors corresponding to two different reference textures are homogeneous textures with features that smoothly transition between those of the two references.

cs.CV

版本更新 · v6arXiv:2507.21183

MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge

Guangchen Lan, Sipeng Zhang, Tianle Wang, Yuwei Zhang, Daoan Zhang, Xinpeng Wei, Xiaoman Pan, Hongming Zhang 等 10 位作者

原文摘要

As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori Preference Optimization (MaPPO), a methodology for learning from preferences that explicitly incorporates prior reward knowledge into the optimization objective. Building on the paradigm employed by Direct Preference Optimization (DPO) and its variants of treating preference learning as a Maximum Likelihood Estimation (MLE) problem, MaPPO integrates prior reward estimates into a principled Maximum a Posteriori (MaP) objective. This not only generalizes DPO and its variants, but also enhances alignment by mitigating the oversimplified binary classification of responses. Additionally, MaPPO introduces no additional hyperparameters, and supports preference optimization in both offline and online settings. In addition, MaPPO can be used as a plugin for DPO variants, including widely used SimPO, IPO, and CPO, and produce consistent improvements. Extensive empirical evaluations of different model sizes and model series on three standard benchmarks (MT-Bench, AlpacaEval 2.0, and Arena-Hard) demonstrate consistent improvements in alignment performance without sacrificing computational efficiency.

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.11045

Agents Propose, Code Verifies, Humans Decide: Verified Agentic Ingestion of Heterogeneous Scientific Tables into Relational Databases

Bharatha Rankothge, Suzanne Hodgkins, Virginia Rich, Michael Kirby

原文摘要

Public scientific datasets rarely arrive analysis-ready. They arrive as messy folders of wide matrices, long tables, spreadsheets, and per-cohort files whose keys and encodings differ, and every reanalysis must reconnect them first. A coding agent can automate this, but its mistakes can look plausible, and without an audit trail, a mistake that corrupts data can go uncaught. We present an AI-assisted ingestion pipeline built on one rule: LLM agents propose, deterministic code verifies, and humans decide. Narrow agents see compact, citable evidence about the files, never the data, and return typed proposals. A verifier with 39 check types tests each proposal against that evidence in two loops, one for the schema's structure and one for its meaning, and a human reviewer approves the schema and the load. Code compiles PostgreSQL DDL, reshapes the data, quarantines rows it cannot place, records provenance, and reconciles every staged row against the database. On four public biomedical datasets, one held out from development, 9 of 20 first proposals failed a check and every failure was caught: the loops repaired eight, and a one-line reviewer edit fixed the ninth. All 45.1 million values loaded with zero reconciliation gap. Discovering a dataset's structure took 4-7 LLM calls and preparing its data at most one more, costing under $0.50 per dataset. In a separate test, each of nine planted data errors was quarantined with a reason or recorded in an audit log.

cs.DB · cs.AI · q-bio.QM

版本更新 · v5arXiv:2511.15974

Knowledge and Reasoning Augmented Learning for Language Model Assisted Antimicrobial Decision Support

Zhe Li, Yehan Qiu, Yuntian Huang, Xin Ding, Yujie Chen, Jing Sun, Min Yan, Lei Chen 等 18 位作者

原文摘要

Background: Antimicrobial decision support requires both clinical knowledge and patient-specific reasoning. We developed Knowledge and Reasoning Augmented Learning (KRAL) to improve language model performance on antimicrobial decision-making tasks. Methods: In this retrospective technical study, a 27-billion-parameter student model underwent guideline-grounded supervised fine-tuning followed by Multi-turn Agentic GRPO using clinical reasoning trajectories. Six configurations were evaluated on 123 clinician-validated clinical antimicrobial treatment cases from Peking Union Medical College Hospital (PUMCH) and 100 JAMA Clinical Challenge cases. A language model judge scored responses, and paired tests compared configurations. Component ablations assessed benchmark performance and training stability. Results: On the PUMCH benchmark, KRAL achieved the highest composite score (0.895 on a 0-1 scale), outperforming all five controls (all P<0.001). On JAMA, KRAL scored 0.600 and exceeded the base model with and without retrieval (P = 0.0048 and 0.0499, respectively). Reinforcement learning ablation experiments demonstrate that the reward smoothing can significantly improve the performance and training stability of vanilla GRPO. Conclusions: KRAL improved performance on a single-center clinical antimicrobial benchmark and publicly available JAMA clinical challenge cases by combining guideline-grounded learning with Multi-turn Agentic GRPO. Further external clinical validation is needed to evaluate the practical utility and effectiveness of KRAL.

cs.AI

新论文 · v1arXiv:2611.11043

GARDEN: Efficient GPU-Accelerated Billion-Scale GNN Training via Caching-Sampling-Batching Co-Design

Qingrui Zhu, Lei Liu, Yushu Cai, Kai Sheng, Zhiwen Chen, Xin He

原文摘要

Graph Neural Networks (GNNs) have shown impressive performance in diverse tasks such as social network analysis and recommendation systems. However, scaling their training to billion-edge graphs is hindered by the memory wall: GPU memory capacity falls short of the massive storage requirements for node features and topology. Sampling-based GNN training frameworks mitigate this by streaming subgraphs from CPU to GPU, but they incur prohibitive PCIe data transfers and non-coalesced memory accesses, resulting in bandwidth underutilization and low compute efficiency. We propose GARDEN, a GPU-accelerated sampling-based system that co-designs caching, sampling, and batching to eliminate these bottlenecks. GARDEN introduces three key innovations: (1) an Adaptive High-Fidelity Cache Allocator (AHFCA) that combines offline reuse profiling and online hotness tracking to dynamically cache features and adjacency lists within a fixed GPU memory budget, avoiding static allocation waste; (2) a Grouping-based Parallel Sampler that reorders stochastic neighborhood accesses(GPS) to maximize warp occupancy and hide latency on power-law graphs; and (3) a Super-batch Degree Classifier(SDC) that fuses mini-batches into degree-homogeneous groups, enabling cache-friendly coalesced transfers and high GPU utilization. Evaluations on real-world billion-scale graphs demonstrate that GARDEN achieves 4.54x, 1.27x, and 2.97x end-to-end training speedups over DGL-UVA, DUCATI, and FastGL, respectively, while maintaining model convergence and accuracy.

cs.DC

新论文 · v1arXiv:2611.11040

Advancements in Cloud-Native Systems: A Systematic Mapping Study of Reliability and Scalability across Cloud-Native, Edge-Native and AI-Enabled Systems

Shrinivass Arunachalam Balasubramanian

原文摘要

Cloud-native systems now extend to the network edge and host artificial-intelligence (AI) workloads, including AI agents, but evidence on their reliability and scalability is scattered and uneven. We report a PRISMA 2020 systematic mapping study with an evidence-graded synthesis. Five logged OpenAlex searches on 11 October 2026 covered cloud-native systems, edge AI, agentic AI for operations, reliability of agentic applications and physical AI; 189 records from an earlier exploratory search were added separately. After 301 duplicate removals and an automated peer-review venue rule, 4,611 records were screened against written criteria and a five-level relevance scale. The review includes 1,794 primary studies from 2017-2026 and 95 secondary studies, with every decision released in Dataset S1. Each primary study was assigned to a 13-category taxonomy and graded as simulation, prototype or testbed, production data, production deployment, or not determinable from the abstract. Of 1,003 studies with a determinable level, 66.2% used prototypes or testbeds, 18.0% simulations and 15.8% production data or deployments. A 93-study synthesis core, appraised from indexed abstracts, shows production deployments of cascading-failure prevention, trace- and graph-based root-cause analysis and predictive autoscaling, and production-trace evaluations of cold-start mitigation. Edge reliability and physical AI rely mainly on simulations and testbeds. AI-agent reliability uses tool-grounded diagnosis, explicit safety properties, trace-driven repair and workload-aware scheduling, while empirical studies show that agent frameworks remain fragile. Conclusions are limited to the documented corpus. The principal gaps are production evidence for edge-native systems, shared resilience benchmarks and dependable agentic operations.

cs.SE · cs.AI · cs.MA · cs.NI · cs.PF

版本更新 · v3arXiv:2610.14423

Scaling Laws for Multimodal Data Mixtures

Aditi Khandelwal, Ayush K. Tarun, Yixuan Xu, Imanol Schlag, Golnoosh Farnadi, Siva Reddy, Luke Zettlemoyer, Antoine Bosselut

原文摘要

Frontier AI systems are increasingly natively multimodal, jointly pretrained on multiple modalities, such as text, vision, and audio. However, the scientific understanding of the multimodal data mixtures used to pretrain these systems --- how much of each modality to mix, and at what potential interference cost to the others --- is largely absent or gatekept. In this work, we derive data mixing scaling laws for three modalities: text, vision, and audio. Multimodal Large Language Models (MLLMs) increasingly adopt Mixture-of-Experts (MoE) architectures, as MoEs scale efficiently and partially limit cross-modal interference. We therefore use MoEs to conduct 268 experiments ranging from 457M to 8.3B parameters, on up to 150 billion tokens. Our work leads to multiple actionable insights into multimodal data mixing for training MLLMs. First, compute optima are modality-specific: audio modality is model-heavy, favoring scaling parameters over tokens, while text and vision require balanced scaling of model size and data. Second, repeating vision or audio data beyond 2x yields negligible benefits. Finally, cross-modal interactions are highly asymmetric: vision strongly interferes with audio, whereas audio's interference with learning text and vision is negligible. Overall, we provide a principled foundation for understanding the multimodal data mixtures needed to train frontier MLLMs.

cs.CL · cs.LG

版本更新 · v2arXiv:2601.09865

Advancing Model Refinement: Muon-Optimized Distillation and Quantization for LLM Deployment

Jacob Sander, Brian Jalaian, Venkat R. Dasari

原文摘要

Correction notice (v2). Two implementation issues affect these experiments. All LoRA training ran under DeepSpeed, which replaced the optimizer passed to the Trainer with AdamW at a constant learning rate, so the Muon and Adam arms used the same optimizer. The cross-entropy term was computed without the next-token shift, so the preference for alpha = 1 reflects that objective rather than the value of the teacher. Each comparison also uses a single GPTQ quantization, and repeated quantizations differ by up to several points. The findings on Muon's quantization robustness, the distillation weight and accuracy relative to GPTQ alone should not be relied on. See the notice on page 1. Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and energy demands. Optimizing these models requires addressing three key challenges: acquiring task-specific data, fine-tuning for performance, and compressing models to accelerate inference while reducing resource demands. We propose an integrated framework combining GPTQ-based quantization, low-rank adaptation (LoRA), and a specialized data distillation process to significantly reduce model size and complexity while preserving or enhancing task-specific performance. By leveraging data distillation, knowledge distillation via Kullback-Leibler divergence, Bayesian hyperparameter optimization, and the Muon optimizer, our pipeline achieves up to 2x memory compression (e.g., reducing a 6GB model to 3GB) and enables efficient inference for specialized tasks. Empirical results demonstrate superior performance on standard LLM benchmarks compared to GPTQ quantization alone, with the Muon optimizer notably enhancing fine-tuned models' resistance to accuracy decay during quantization.

cs.LG · cs.AI

新论文 · v1arXiv:2611.11038

Iterative Interference Cancellation for Near-Field XL-MIMO Networks with LoS Channels

Nayyab Haider, Rodrigo C. de Lamare

原文摘要

In extra-large multiple-input multiple-output (XL-MIMO) systems, near-field users experience spherical wavefront propagation, offering higher spatial resolution than far-field plane-wave models, but complicating signal detection and interference cancellation. Under line-of-sight conditions, we propose a weighted-rate successive interference cancellation (WR-SIC) scheme whose ordering metric exploits the enhanced spatial degrees of freedom of near-field propagation to prioritize users with stronger channels. An iterative detection and decoding (IDD) scheme with LDPC coding is then developed. Simulations in hybrid near- and far-field deployments show that the proposed WR-SIC and IDD schemes improve bit-error and sum rates over existing schemes

cs.IT

版本更新 · v4arXiv:2603.14869

A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems

Haoyu He, Yu Duan, Wenzhen Liu, Hanyuan Hang, Boyu Qin, Qiantu Tuo, Xiaoke Yang, Rui Li

原文摘要

Reliable photovoltaic (PV) power generation requires timely detection of module defects that may reduce energy yield, accelerate degradation, and increase lifecycle operation and maintenance costs during field operation. Electroluminescence imaging is therefore widely adopted for PV module inspection; however, automated defect detection in real operational environments remains challenging due to heterogeneous module geometries, low-resolution imaging conditions, subtle defect morphology, long-tailed defect distributions, and persistent data and label-space shifts from evolving inspection and labeling processes. These factors limit the robustness and long-term maintainability of conventional deep-learning inspection pipelines. To address these challenges, this paper proposes SEPDD, a Self-Evolving Photovoltaic Defect Detection framework designed for evolving industrial PV inspection scenarios. SEPDD integrates automated pipeline optimization with a trigger-driven evolution mechanism that re-optimizes the whole training/evaluation pipeline when deployment indicators (retraining failure, label evolution, environmental change, periodic maintenance) fire, enabling deployment-time adaptation to distribution shifts and newly emerging defect patterns. Experiments on a public PV defect benchmark and a private industrial dataset, both exhibiting severe class imbalance and significant domain shift, demonstrate SEPDD's effectiveness: it attains mAP50 of 91.5% on the public dataset and 49.5% on the private dataset, surpassing the autonomous baseline by 14.9% and human experts by 4.8% on the public dataset, and by 4.9% and 2.5%, respectively, on the private dataset; comparisons are limited to the two evaluated datasets and the studied baselines. By improving the robustness and adaptability of automated PV inspection, the proposed framework supports more reliable maintenance of distributed PV systems.

cs.AI