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

+1200新增论文
+951其中 AI 相关
+132已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 16:53各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 17:46 — 2026-11-20 17:46(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:2026-11-20 08:48最近发现新增版本:2026-11-20 16:53库内论文最新更新时间:2026-11-20 02:59

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

28,609 已收录论文23,738 AI 相关8,785 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 5,242 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.26459

Bayesian optimization on amortized search space

Tristan Fauvel, Federico Pavone, Titouan Guillou, Pau Redon Muñoz, Chloé Geoffroy

原文摘要

In real-world black-box optimization problems, a mechanistic simulator is often available that approximately predicts the behavior of the system as a function of the parameters being optimized. Here, we show how an amortized inverse map of such a simulator can be used in Bayesian optimization to restrict the search space while using a Gaussian process kernel that is aware of the original problem geometry. This allows for efficiently leveraging the low intrinsic dimensionality of the optimization problem. We characterize its approximation bias and information gain, and derive an intrinsic-dimension-dependent regret rate under additional geometric and Gaussian Process assumptions. We illustrate the method with an application to drug dosing personalization in Parkinson's disease. We use, as a simulator, a pharmacokinetic/pharmacodynamic (PK/PD) model of a drug, a mechanistic model calibrated on population data with quantified parameter uncertainty. A dosing neural network is trained offline against the model, amortizing the map from patient PK/PD parameters to the regimen predicted to be optimal, and online Bayesian optimization then searches over this learned, low-dimensional representation rather than over raw dosages. Numerical simulations demonstrate the improved performance of our method in this application, as well as under simulator misspecification.

stat.ML · cs.LG

版本更新 · v3arXiv:2609.33496

Chameleon: Dynamic Format Adapter for Efficient Diffusion

Arnab Sanyal, Sandeep Chinchali

原文摘要

Post-training quantization (PTQ) is the standard way to run modern diffusion models on memory-constrained accelerators, yet every existing diffusion PTQ scheme fixes the $\mathit{number\ format}$ in advance and only tunes the scale, zero point, or per-layer bit-width. At a fixed bit-width the best format depends on the distribution being encoded, and that distribution differs across weight channels, across layers, and along the diffusion timestep, where activation distributions slide from heavy-tailed and noise-dominated to tightly clustered and structured. We propose Chameleon, a PTQ framework that holds the bit-width fixed and treats the format itself as a discrete variable, chosen per weight channel and per activation layer, optionally refined per timestep bucket. Activation formats come from {INT8, FP8 E4M3, FP8 E5M2, MXFP8, MXINT8}, selected ahead of time from two cheap statistics (empirical kurtosis and the closed-form diffusion SNR) and stored in a lookup table; weight formats come from {INT8, MXINT8} at 8 bits or {INT4, NF4, FP4 E2M1, MXINT4, MXFP4} at 4 bits, selected offline by reconstruction error. An architectural fork adapts the same selection layer to multi-step UNets, single-step distilled models, and Diffusion Transformers. Most of the gain comes from the per-layer choice; the timestep refinement helps mainly at 6-bit activations. Across SDXL, SDXL-Turbo, and PixArt-$α$ on COCO-2014, Chameleon achieves the best FID in all six backbone $\times$ bit-width settings, with CLIP within 0.24 of the FP16 reference and the best of all quantized methods at $W_{4}A_{8}$. On PixArt-$α$, a real mixed-format kernel runs 1.09$\times$ faster than FP16 end-to-end with 3$\times$ smaller weights.

cs.LG · cs.AI · cs.CV

新论文 · v1arXiv:2611.26447

Scaling classical hardware for accurate real-time quantum error correction

Chenyang Jin, Susanne F. Yelin, Andi Gu

原文摘要

Fault-tolerant quantum computation requires a classical decoder fast enough to process syndrome measurements at the rate at which they are generated, and to return its decisions with low latency. This is most demanding for superconducting processors, whose fast syndrome cycles force a trade-off between decoding speed and accuracy. Decoders fast enough to keep up sacrifice accuracy, which must be compensated for with larger codes and thus additional physical qubits. Here we introduce Rapids, a streaming neural decoder that is both fast and accurate. We achieve this by co-designing the decoder with a field-programmable gate array (FPGA): the network is built from operations that map cheaply onto the device and trained in its integer arithmetic. For the distance-19 surface code, Rapids decodes each round of syndromes in under a microsecond on a single FPGA, fast enough for superconducting processors, and returns its decisions with the low latency that fault-tolerant algorithms require. Its logical error rate is 240 times lower than that of existing real-time hardware decoders. The same design extends to the color code and the [[144,12,12]] bivariate-bicycle code, on which our decoder is 16 times more accurate than the real-time Relay decoder. We further show that the decoder scales: spread over several FPGAs or hardened into custom silicon, it becomes faster, more accurate, or able to decode larger codes. Classical hardware thus becomes a further resource, alongside qubits, that can be scaled to improve fault-tolerant quantum computers.

quant-ph · cs.AR · cs.LG

版本更新 · v3arXiv:2609.19153

Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data

Gregory M. Dickinson

原文摘要

Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study rather than a means to prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single word ablation that measures the effect of a preprocessing step directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~0.68) and constitutional versus non-constitutional law type (~0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of about 18,500 candidate words in turn, and a task-specific stoplist is built from the measurements. Common generic stoplists fall below the no-removal baseline in all twelve held-out tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and supplemental analysis finds that word-level statistics predict removal effects poorly, because true removal effects differ by less than the measurement can register, leaving little to predict. The method generalizes to any inherited preprocessing default; the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.

cs.CL · cs.CY · cs.IR · cs.LG

新论文 · v1arXiv:2611.26441

Should Belgians Install an Advanced Energy Management System in Their Electrified Dwelling ?

Julian Ruddick, Cedric De Cauwer, Thierry Coosemans, Maarten Messagie

原文摘要

As dwellings electrify and more complex electricity pricing spreads in Belgium, the question arises: What are the potential benefits of installing an advanced energy management systems in an electrified Belgian dwelling ? To answer this question, we simulate 500 representative Belgian dwellings in which fossil systems are replaced by controllable electric technologies: space heating via air-to-air heat pumps, domestic hot water via electric boilers, and private transport via electric vehicles with home chargers. Photovoltaic systems are assigned according to current adoption rates. We evaluate two advanced energy management systems (EMS): model predictive control (MPC) and TreeC, a machine learning method using decision trees to model the EMS strategy. These are compared to a rule-based controller (RBC) that mimics default operation and an MPC with perfect forecasts (MPC P) as an upper bound. Performance for these EMSs is assessed for 2023 under a real contract with hourly prices and a monthly peak tariff. Average annual savings versus RBC are 82.5 EUR, 116.6 EUR, and 177.4 EUR for TreeC, MPC, and MPC P, respectively. All EMSs deliver similar thermal comfort (26-31 Kh). MPC saves more, while TreeC achieves higher EV charge completion (93.3% vs 88.8% for MPC, with a max charge of 95%) and a smoother aggregate load across the 500 dwellings. Savings remain modest relative to EMS purchase (280-680 EUR) and subscription (0-360 EUR/year) costs which is not favourable towards widespread adoption. The data and code to reproduce this study are available at https://github.com/EVERGi/should_belgians_install_advanced_ems_paper.

eess.SY · cs.LG

版本更新 · v2arXiv:2611.19597

Synthetic Neurosymbolic Task Generation with Controlled Constraint Complexity

Mykhailo Buleshnyi, Zsolt Zombori, Michael Benedikt

原文摘要

We introduce NeSySy, a synthetic generator for neurosymbolic learning tasks that jointly produces logical constraints and consistent datasets. Unlike existing benchmarks, NeSySy provides fine-grained control over key properties such as constraint structure, tightness, input dependence, and data generation and alignment strategies. In particular, it allows the use of rich constraints over infinite domains, and uses solvers to ensure that the constraints are meaningful and that generated samples satisfy the constraints. We design NeSySy to support both learning with declarative constraints and learning from distant supervision. Across a range of constraint families, we provide evidence that its parameters induce systematic and largely independent effects on task difficulty. Using NeSySy, we study constraint-aware learning methods, identifying regimes where explicit constraint enforcement is beneficial and where expressive unconstrained models can instead learn constraint structure directly from data. Our results establish NeSySy as a controlled testbed for analysing the interaction between learning and logical structure. NeSySy is built around a pipeline that incorporates solvers. Satisfiability checkers (CNFgen and Z3) generate and certify constraints. Constrained optimizers (RC2 for MaxSAT, Z3 for OMT) compute optimal repairs that guarantee every generated sample is consistent.

cs.LG · cs.AI · cs.LO · cs.NE · cs.SC

新论文 · v1arXiv:2611.26426

Exact Bayesian layers via characteristic functions

William H. W. Thompson, Guillaume St-Onge, Laurent Hébert-Dufresne, Jean-Gabriel Young

原文摘要

Bayesian neural networks provide principled uncertainty estimates, but training them with Monte Carlo sampling can be expensive. Sampling-free variational inference algorithms make training Bayesian neural networks feasible, but existing approaches assume a Gaussian output distribution, which can be inaccurate in applied problems. Here, we introduce CF-Prop, an uncertainty propagation method that uses characteristic functions to compute the exact output distribution of a Bayesian ReLU layer, without any sampling, even in non-Gaussian settings. Because CF-Prop propagates characteristic functions, the evidence lower bound---the objective of variational training---can be computed in closed form for a broad class of likelihoods, including the Gaussian, Poisson, and Gamma. This allows to implement an efficient resulting variational inference algorithm, CF-VI. On CIFAR-100, CF-VI achieves the lowest calibration error of any tested method, improving on the next best method by about 35%. On a heavy-tailed insurance claim dataset, CF-VI accurately captures tail uncertainty that is severely underestimated by both other sampling-free methods and Monte Carlo methods.

stat.ML · cs.LG · stat.CO

新论文 · v1arXiv:2611.26419

FEA solver integration of a composite World Model with a Spiking Neural Network memory Block for computationally efficient modelling of defects and variabilities

Bassam El Said, Adam Sobey

原文摘要

Each fibre-reinforced composite structure has a unique material architecture. The manufacturing methods used and the presence of defects lead to local variations which require material-scale models that can resolve the response in real time at every location in the structure. Concurrent multi-scale schemes provide this capability, but at a prohibitive computational cost for large structures as the number of integration points and time increments scales with size. Surrogates have been studied extensively as replacements for material-scale models to mitigate these computational limitations. A surrogate must represent an arbitrary local architecture including defects, track the irreversible material state over an unknown number of increments, remain stable when driven recursively by its own predictions, and fit within the memory available at every integration point. Here, a Composites World Model based on a Multi-Modal Spiking Transformer architecture is designed to meet these requirements. The proposed architecture combines a material encoder, a Spiking Neural Network memory block that tracks the long-term internal state of the material, and transformer blocks that learn the short-term applied strain state. The system is trained in three stages: material architecture encoding, base training on short time windows, and recursive fine-tuning with scheduled sampling to suppress cumulative error drift. The trained model is disassembled at inference and coupled to a non-linear FE solver, enabling structural scale simulation of composites containing embedded defects. Benchmarks against experimental results for IM7/8552 laminates under tension, compression and transverse shear, for pristine and wrinkled composites, show that the SNN memory block successfully tracks the material internal state and results in prediction errors between 0.4% and 4.8%.

cs.LG

新论文 · v1arXiv:2611.26413

Sequential Anytime Valid Tests for Efficient Inference-Time Alignment

Vishesh Kumar Singh, Sayak Ray Chowdhury

原文摘要

Inference-time alignment methods, such as Best-of-N (BoN), improve language model outputs by generating multiple candidates per prompt and selecting among them using a reward model. Much of this cost is wasted: a fixed budget is applied to every prompt, although the computation required by prompts varies widely. Adaptive methods halt once sampled answers appear settled, but their thresholds are tuned heuristics with no statistical control over early-stopping errors. We instead seek an anytime-valid stopping rule that takes an error tolerance $α$ as input and halts only once an answer is certified to hold a majority ($θ_a > 1/2$) under the generator's distribution. We aggregate candidates by final answer with a reward-weighted self-consistency (RWSC) score and treat stopping as a sequential test over the resulting clusters. Applying Wald's sequential probability ratio test to these clusters yields SPRT-RWSC, which performs well empirically, but its guarantee fails because the leading answer shifts during sampling, and the run is continuously monitored. Our main contribution, e-RWSC, replaces Wald's test with a betting supermartingale (an e-process) for every answer the policy produces, bounding the probability of ever certifying a non-dominant answer by $α$, uniformly over time and across all answers. The RWSC scores drive the bets, so they affect only how quickly a dominant answer $a^\star$ is certified, not validity; certification takes $O(\log(1/α)/d_{\mathrm{KL}}(θ_{a^\star}\|1/2))$ samples. Experiments across several language models, datasets, and reward models confirm the predicted $1/d_{\mathrm{KL}}$ scaling of cost and show that accuracy improves over baselines at substantially lower token cost.

cs.LG

新论文 · v1arXiv:2611.26412

How to Effectively Manage the Energy in Residential Systems: Development and Comparison of Methods

Julian Ruddick

原文摘要

The transition from fossil fuels presents significant challenges in energy management. To ensure a sustainable energy future, it is crucial to reduce energy consumption when possible and to synchronize electricity consumption and storage with the production from sources with low greenhouse gas emissions. This thesis explores a variety of energy management methods used to manage batteries, heat pumps, and other energy-related systems. The thesis presents three simulation cases alongside one real-world experiment to compare energy management done through simple rules, optimization, and machine learning methods. Furthermore, this thesis introduces TreeC, a novel machine learning-based method that learns understandable yet efficient energy management strategies, applicable to many cases. The three key contributions of this thesis can be summarized as follows: 1) The developed TreeC method demonstrates competitive performance compared to a variety of energy management approaches, such as model predictive control and reinforcement learning, across a diverse set of energy management problems. The understandability of TreeC's energy management strategies greatly improves the transparency and trustworthiness of machine learning-based energy management. 2) The real-world experiment highlights the need to validate energy management methods on actual hardware and not solely on simulations. Both TreeC and model predictive control performed worse than in simulations, due to, respectively, insufficiently representative training data and the real-time input data not being reliable enough. 3) Energy management algorithms reduce costs in electrified Belgian dwellings, particularly in poorly insulated dwellings, electric vehicle chargers, and photovoltaic installations. However, on average, these cost savings do not yet outweigh the current costs and effort required to implement such algorithms.

eess.SY · cs.LG · cs.NE

版本更新 · v3arXiv:2610.09186

The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning

Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari

原文摘要

We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum. A large language model (LLM) learns to reason step-by-step when data is structured such that the next token depends on a small amount of preceding context. Inference in LLMs resembles pattern recognition when the next token depends on a large amount of preceding context. If the next token depends on only the $c$ most recent tokens, reasoning traces are paths on a de Bruijn graph whose nodes are $c$-length contexts and edges are next-token transitions between contexts. The set of reasoning traces of a task forms a directed acyclic subgraph of the de Bruijn graph. An LLM that has learned all edges of this subgraph can compose them to solve longer, unseen tasks, i.e., it reasons step-by-step. We prove that the number of edges is vanishingly small compared to the number of reasoning traces. We also prove and show empirically that the number of training samples a transformer needs is a linear in the number of edges, so learning to reason step-by-step is sample efficient. We can induce de Bruijn structure in any task by maintaining a ``state'' that makes future reasoning independent of the past. The frequency of states in the reasoning trace determines $c$. We show, by fine-tuning Qwen2.5-1.5B-Instruct to solve equations and answer questions about stories, that frequent states (small $c$) result in higher accuracy but greater fragility to perturbations at test time. LLMs trained with a large $c$ are only as good as models that perform pattern recognition without reasoning. A moderate density of states balances accuracy and robustness. Real-world data has de Bruijn structure: Qwen3-14B and Qwen3-32B retain over 75\% of their accuracy on GSM8K, MATH-500 and GPQA-Diamond when attention is restricted to a sliding window less than 15\% as long as the full reasoning trace.

cs.LG · cond-mat.dis-nn

新论文 · v1arXiv:2611.26410

Statistical Inference with Ill-Conditioned Random Weight Neural Network Sieves

Giovanni Ballarin, Lyudmila Grigoryeva, Lukas Gonon

原文摘要

Random weight neural networks (RWNNs) are shallow networks whose hidden-layer parameters are randomly generated and then kept fixed, while only the output coefficients are estimated. Conditional on the sampled parameters, RWNN regression is a linear sieve problem with random approximation space. We show that such random sieves cannot remain uniformly well-conditioned as their dimension grows. For parametrized feature families satisfying polynomial covering and Lipschitz conditions, the eigenvalues of the population covariance matrix are proven to have polynomial upper bounds determined by the covering geometry of the parameter space, leading to a vanishing smallest eigenvalue. We develop approximation, estimation, and inference theory that explicitly treats the ill-conditioning. Under a $β$-Hölder source condition, we obtain both faster-than-Monte-Carlo $L^2$ approximation rates and new $L^\infty$ approximation bounds based on stratified sampling. We then derive improved consistency guarantees for ridge-regularized least squares driven by ridge effective dimension, spectral, and leverage-based stability conditions. For inference, we establish asymptotic linearity and Gaussian limits for linear functional directions while allowing the smallest eigenvalue of the population covariance matrix to vanish. Nondegeneracy is directional: we characterize it with a ridge-normalized Rayleigh quotient and extend it to smooth functionals via Riesz representation. Consistency of ridge-adjusted variance estimators is proved, yielding feasible studentized inference. Numerical experiments illustrate the deterioration of random-feature conditioning and the finite-sample behavior of the resulting estimation and inference procedures.

stat.ME · cs.LG · econ.EM · stat.ML

新论文 · v1arXiv:2611.26407

Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

Yuchen Zhou, Lili Zheng, Yuxin Chen, Gen Li

原文摘要

Flow matching is a versatile framework for generative modeling that transports a source distribution to a target data distribution. A key advantage is its flexibility in the choice of source distribution, such as heavy-tailed and multimodal sources. Yet finite-step sampling guarantees for non-Gaussian sources remain limited. We establish a nonasymptotic convergence theory for Euler discretization of flow matching with linear interpolation. Suppose the source distribution on $\mathbb{R}^d$ has an everywhere positive, continuously differentiable density, finite total variance $\mathsf{TotVar}_{\mathsf{base}}$, and an $L$-Lipschitz score. Using the population velocity field and a suitable time grid, this sampler achieves total variation error at most $\varepsilon$ in $\widetilde{O}(Ld\mathsf{TotVar}_{\mathsf{base}}/\varepsilon)$ iterations, provided the target distribution satisfies a mild second-moment condition. These assumptions cover, among many examples, source distributions such as multivariate Student's $t$ distributions with more than two degrees of freedom and finite Gaussian mixtures with shared covariance, while accommodating target distributions with neither a smooth density nor bounded support.

stat.ML · cs.AI · cs.IT · cs.LG

版本更新 · v4arXiv:2608.30044

Balance of Benchmarks: Evidence Retention and Multiplicity-Aware Model Comparison

Jhen-Ke Lin, Hong-Yun Lin

原文摘要

Benchmark aggregation requires decisions about how much evidence to use and how much influence each benchmark receives. Curated suites control influence through selection, which can exclude informative observations. A broader pool can retain those observations. With equal weighting, repeated or closely related benchmarks gain influence as their number grows. We introduce Balance of Benchmarks (BoB) to retain eligible observations and control their influence separately. We fit benchmark-specific response curves to place different difficulty ranges on a shared ability scale and use description similarity to downweight benchmarks in crowded neighborhoods. We test retention and density weighting in separate interventions on WildScores, a sparse collection of 148 developer-reported benchmarks, using 14 Artificial Analysis benchmarks as a controlled reference. With the model population fixed and entire source-lineage families held out, suite expansion improves held-out prediction under BoB and equal-weight equating on both WildScores and BIG-bench. Under substantial reporting overlap, density weighting improves robustness to multiplicity. Complete re-listings yield smaller mean rank displacement under BoB (0.63 versus 1.95 for equal-weight equating), with benefits also in paraphrased re-listings and supported affine fits. The benefit can reverse if models report different benchmarks, because a single weight per column gives models that report only part of a group less than its intended share. We therefore compute each model's weights from the benchmarks it reports. This rule removes the reversal in controlled re-listings and keeps held-out prediction close to that of equal weighting. These comparisons separate evidence retention, benchmark influence, and reporting coverage and show why repeated entries need to be handled per model.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.26391

Simulation-pretrained autoencoders versus PCA for compressing multimode fibre transmission matrices

Callum J. Wilson, Terry Wright, Qing Yang, Zhong Wen, Michael P. Pound, George S. D. Gordon

原文摘要

Multimode optical fibres can image through a thin, flexible probe once their transmission matrix (TM) has been measured, but a TM is large and must be re-measured whenever the fibre moves. A compact model of feasible TMs would make storing and re-estimating them cheaper, so we ask how compactly TMs can be represented, and from how few measured TMs. Here we benchmark a permutation-equivariant autoencoder, pretrained on simulated fibres and adapted to measured TMs, against principal component analysis (PCA). At 62x compression, adapting the pretrained autoencoder with just two measured TMs reconstructs the TM of a 50um fibre well enough to focus light at 98% of the ideal enhancement, and it stays accurate when the TMs are shifted by 25 pixels or zoomed by 10%, which quickly degrades a linear basis. It is not, however, a better compressor: PCA is about ten times more accurate when fitted on all 163 real TMs (1.1% against 11.9% error on held-out TMs) and is already more accurate from ten. The autoencoder's value is as a prior when few or no real TMs exist: with none it reaches 29% error, against 91% for PCA fitted on the same simulation. Transfer to a different fibre is only partial. The most important extension, not yet tested, is to recover pixel-basis TMs from fewer measurements than a full TM, which would turn the pretrained prior from a compressor into a measurement-saving tool.

physics.optics · cs.LG

新论文 · v1arXiv:2611.26383

Evidence from a Multi-Regime Causal Discovery Benchmark: UCMT Algorithms, Comparative Performance, and Controlled Ablation Studies

Mahyar Eslami

原文摘要

We present an internal, pre-registered evaluation of the UCMT causal discovery algorithm family alongside established alternatives across heterogeneous benchmark regimes, complemented by a separately pre-registered, controlled study of UCMT v2 Global components. The contribution is both empirical and methodological: a family-stratified comparison of three actively developed algorithm configurations and targeted evidence about which internal stages affect their outcomes. In the main benchmark, UCMT v2 Global has higher directed F1 than NOTEARS and DAGMA in selected real, semi-synthetic and Gaussian-network comparisons at the paired-run level, while trailing leading permutation-search methods in other settings. The BOSS-based UCMT v4 produces a CSuite-specific directed-F1 improvement over BOSS (mean paired difference +0.279; pair-level Holm p < 0.001), but the dataset-level adjusted result is not significant (p = 0.188). In a separate fixed-skeleton ablation, UCMT v2 Global exceeds an adapted R^2-SortnRegress orientation baseline on standardized iSCM data (directed F1 0.537 vs 0.468, dataset-level Holm p = 0.031); absolute orientation accuracy is 0.563 and there is no established broad advantage over RESIT, ANM or DirectLiNGAM. Controlled ablations show that sparsity and BIC-based refinement materially affect some outcomes, whereas the examined arbitration and automatic regime-selection mechanisms do not yield confirmed general improvements. We report performance shortcomings, multiple-testing correction, runtime costs, evaluation limitations and reproducibility checks. The results support UCMT as an implemented and empirically investigated algorithm family, not a claim of overall superiority, independent validation or demonstrated commercial impact.

cs.LG

版本更新 · v2arXiv:2605.17170

TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks

Hanzhang Shen, Haoran Wu, Yiren Zhao, Robert Mullins

原文摘要

Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image tokens, and semantic role such as user queries, tool calls, observations, or reasoning. These axes capture distinct token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bit-widths under a fixed memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache capacity and achieving 30% higher end-to-end throughput, when running on real GPU systems.

cs.LG

版本更新 · v4arXiv:2609.02986

Two Principles for Autoregressive Language Modeling

Runlin Shi, Bojian Yin, Guoqi Li

原文摘要

We investigate the functional differentiation learned by RoPE Transformers to derive principles for autoregressive language modeling. We introduce two intervention-based metrics: RoPE Frequency Importance Score (RFIS) measures how removing a frequency contribution changes a head's full attention distribution, and RoPE Positional Dependence (RPD) isolates the effect of rotary modulation. In Qwen3 and Llama3.1, these metrics distinguish retrieval from positional modeling, while individual heads can exhibit both functions. A mid-low-frequency Global Positional Band (GPBand) separates their frequency dependencies and tracks the training sequence length in controlled experiments, suggesting that global positional fitting can hinder zero-shot length extrapolation. These findings motivate two principles. (1) Functional Organization: retrieval and positional functions should be assigned separately and mixed within layers with layer-specific allocation; and (2) Positional Dependence: positional modeling should operate only locally, while global access should rely on position-independent retrieval. Matched pretraining from scratch and targeted architectural ablations at 380M and 1.4B parameters support both principles and highlight the importance of mechanism choice in realizing each function. Together, these findings suggest a promising route toward architectural innovation grounded in the functional requirements of autoregressive language modeling.

cs.LG

版本更新 · v2arXiv:2610.05332

Compact set-valued deep ensembling in multi-class classification

Kim-Dung Tran, Dang-Man Nguyen, Vu-Linh Nguyen, Xuan-Truong Hoang, Sébastien Destercke, Van-Nam Huynh

原文摘要

This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and robustness of cautious (set-valued) predictions targeting multiple utilities, which may involve reward-sensitivity. To mitigate the training and storage burdens, we propose to employ compact ensembles, such as Bayesian Neural Networks and Convolutional Neural Networks with the Monte-Carlo dropout prediction option, to produce probabilistic predictions. For each query instance, these probabilistic predictions are then used to define a representative distribution optimizing some statistical distance. The representative distribution is then employed to define the Bayes-optimal prediction (BOP) of any utility. To address the potential unrobustness of singleton prediction making, we propose a family of set-utilities satisfying some desirable properties and whose set-valued BOPs can be found efficiently. Empirical evidence is then given to illustrate the potential (dis)advantages of the proposed ensemble learning framework.

cs.LG

新论文 · v1arXiv:2611.26355

Mamba Flow Matching Neural Processes: Linear-Time Inference for Irregularly Observed Spatial Fields

Cosmo Santoni, Giovanni Charles, Timothy James Hitge, Oliver Watson, Elizaveta Semenova

原文摘要

Interpolating a spatial field, such as daily maximum temperature, from sparse, irregularly located observations recurs across the environmental and health sciences. Standard Gaussian-process kriging refits hyperparameters and solves an $O(N^3)$ system for every new field. When many related fields are observed, such as daily maps from one sensor network, neural processes (NPs) instead learn the interpolation map from past fields and predict a new field in one forward pass. Joint-predictive variants, which sample whole fields rather than independent per-location values, typically use self-attention over context and query points, costing $O(K^2)$ in the combined point count $K$ and limiting practical use to a few thousand points. State-space models offer a linear-time alternative, but a direct state-space adaptation compresses the context into one hidden state before reading queries, reducing what the decoder sees. We propose MambaFlowNP, a linear-compute joint-predictive NP trained with conditional flow matching. A multi-directional Mamba-2 scan reads context and query tokens in one shared sequence, so each query's velocity is read from its own scan position rather than a compressed context summary, and because queries only read the scan state, predictions are consistent across query sets. MambaFlowNP is competitive with the strongest attention-based joint-predictive baselines on synthetic Matérn Gaussian-process benchmarks, and on regional to continental-scale NOAA temperature interpolation it attains the lowest RMSE and CRPS and near-nominal coverage on every tier, while running 114--784$\times$ faster than the strongest joint-predictive baseline. A single forward pass scales to $10^6$ points on one NVIDIA L40S GPU in under a second. This makes joint prediction feasible for continental-scale, irregularly sampled sensor networks; predictive quality is evaluated up to $K=5{,}580$.

cs.LG

新论文 · v1arXiv:2611.26351

TRCF: Temporal-Reference Complementary Forecasting for Irregular Multivariate Time Series

Xudong Zuo, Shusen Ma, Qirui Chen, Bing Fan, Yun-Bo Zhao

原文摘要

Irregular multivariate time series forecasting supports healthcare monitoring, environmental analysis, and activity recognition. Channel-independent (CI) approaches capture each variable's temporal patterns but do not explicitly use observations from other variables. Channel-dependent (CD) modeling exploits relationships among variables, yet asynchronous measurements make these relationships difficult to learn. Incorporating cross-variable information while preserving each variable's irregular history therefore remains a key challenge. We propose Temporal-Reference Complementary Forecasting (TRCF), a framework that augments a compact CI forecaster with a complementary CD branch. ANCHOR aggregates observed values and timestamps at shared temporal locations, retaining observation support to form compact CI features. BRIDGE constructs complementary features through history completion. It first estimates each variable's historical values from its own observations, then uses differences between other variables' observed and estimated values at nearby times to correct missing entries. The completed history preserves observed values and is encoded to supply context alongside the direct CI representation. Finally, the two representations are fused, combined with the query-time embedding, and passed to a shallow multilayer perceptron for forecasting. Experiments on four real-world datasets show that TRCF achieves the lowest mean squared error and mean absolute error in the main benchmark comparison, while reducing measured peak inference memory by 17.28% to 87.98% relative to APN.

cs.LG

新论文 · v1arXiv:2611.26333

OceanCoder: A Verification-Guided Large Language Model for Automated Simulation Modelling in Ocean Engineering

Can Xue, Changhong He, Ziyi Sun, Anliang Ge, Shimin Yu, Bingchen Liang

原文摘要

Numerical simulation is important in ocean engineering, but model construction requires expert knowledge. Large language models support automated modelling, but code syntax and successful execution alone do not establish whether generated models and results meet engineering requirements. We present OceanCoder, a Qwen3-8B-based large language model for automated simulation modelling in ocean engineering. To address specialised programming requirements and scarce training data, we develop an extensible data construction pipeline producing 12,000 verified supervised fine-tuning (SFT) examples across 12 engineering task categories. A three-layer verification framework checks model inputs against engineering parameters and task constraints, verifies completion of required simulation analyses, and assesses the engineering plausibility of computed outputs. Its outcomes provide graded rewards for group relative policy optimisation (GRPO), guiding the model towards engineering task completion. We also construct the first benchmark for automated modelling in ocean engineering, covering out-of-distribution tasks and real-world engineering cases. Experiments and ablation studies demonstrate the effectiveness of the data pipeline, verification framework and reward design. OceanCoder outperforms both base models and the closed-source comparison, with Pass@1 increasing from 0% for the base model to 46.77% after SFT and 51.43% after GRPO. These results support engineering verification as a training signal for automated simulation modelling.

cs.LG · cs.SE

新论文 · v1arXiv:2611.26328

Conformal Selection for Hierarchical Streaming Data

Zhenyuan Sun, Chengyao Yu, Ruixing Ming, Bingyi Jing

原文摘要

Many real-world tasks involve making sequential decisions about whether to select candidates before their responses of interest are revealed. In this work, we address the online selection problem in the context of hierarchical data, where candidates arrive sequentially from different populations. This extends existing online conformal selection frameworks beyond the standard i.i.d./exchangeable data assumption. The primary challenge lies in constructing valid statistics for each candidate sequentially under the hierarchical data structure. To this end, we first develop Online Hierarchical Selection (OHS), a distribution-free method that enables principled candidate selection for hierarchical data streams. Specifically, we introduce methods to construct rank-based e-values for both between-group and within-group samples, and apply averaged e-values to the online e-BH procedure. We then develop OHS with feedback (OHSF), which boosts the power of OHS by leveraging potential response feedback. Theoretically, the proposed methods achieve false discovery rate control under mild hierarchical exchangeability and data arrival assumptions at any time. We also generalize methods to broader settings, such as data with covariate shift and selection under effect-related responses. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness of the proposed methods.

stat.ML · cs.LG

新论文 · v1arXiv:2611.26323

Predicting Surface Displacement Fields of Laser Powder Bed Fusion Parts Using STL-Derived Graphs and Part-Level Descriptors

Saima Ahmed Suhi, Lang Yuan, Md Habibor Rahman

原文摘要

Predicting part distortion before fabrication remains challenging in laser powder bed fusion (LPBF), while thermomechanical simulation is computationally expensive for repeated design evaluations. This study presents a two-branch graph attention network (GAT) to predict three-dimensional surface displacement directly from STL-derived graphs. The first branch learns geometric relationships among connected vertices of a densified STL surface mesh, while the second incorporates 12 part-level descriptors of mass distribution, build-plate contact, overhang, size, and shape. Displacement labels from ANSYS Additive Print simulations are mapped onto STL vertices using Gaussian-kernel weighted averaging. Evaluated on 117 parts using five-fold cross-validation split by part, the model achieves an R^2 of 0.946 and a mean absolute error of 0.0178 mm for displacement magnitude. Relative to a node-wise multilayer perceptron, GAT improves R^2 from 0.913 to 0.946; for build-direction displacement, R^2 increases from 0.903 to 0.939. GAT also outperforms GraphSAGE (R^2 = 0.936) and a graph convolutional network (R^2 = 0.934) across all five folds. Ablation experiments show that removing mass-distribution descriptors reduces magnitude R^2 to 0.900, while removing build-plate contact and overhang descriptors reduces it to 0.920. These results demonstrate the value of combining local mesh connectivity with global geometric descriptors to predict LPBF distortion, enabling faster design iteration and earlier identification of distortion-prone geometries.

cs.LG

新论文 · v1arXiv:2611.26319

A Control-Theoretic Approximation to Predictive Coding Dynamics

Ryan Fayyazi, Kyle Daruwalla, Mitra Javadzadeh

原文摘要

Backpropagation remains the dominant method for training deep neural networks, but its reliance on non-local computations has motivated the search for biologically plausible alternatives. Two prominent frameworks, predictive coding (PC) and deep feedback control (DFC), offer distinct approaches to local learning, yet their relationship remains unclear. Here, we show that DFC arises as a local approximation to predictive coding dynamics near fixed points, with exact equivalence in shallow linear networks and systematic deviations arising with depth, nonlinearity, and distance from equilibrium. We characterize how this approximation, which we call Approx PC, deviates from PC in its activity dynamics, and show that these deviations can be mitigated by relinearizing the feedback controller and approaching the output target through a sequence of intermediate nudges. In networks trained on MNIST and FashionMNIST, Approx PC reaches task performance comparable to PC trained with the same nudges, and weights learned with it transfer directly to PC inference. Our results unify energy-based and control-theoretic perspectives on learning and open the door to applying tools from control theory to the training of predictive coding networks.

cs.LG · cs.AI · q-bio.NC

版本更新 · v3arXiv:2606.00384

VESTA: Visual Exploration with Statistical Tool Agents

William Rudman, Abhishek Divekar, Kanishk Jain, Sebastian Joseph, Stella S. R. Offner, Matthew Lease, Kyle Mahowald, Greg Durrett 等 9 位作者

原文摘要

Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to propose statistical models, but these systems struggle on challenging modeling tasks. To address these limitations, we introduce VESTA (Visual Exploration with Statistical Tool Agents), a framework that equips VLMs with a dynamically growing toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA explores data before and during refinement by selecting or creating reusable diagnostic tools. We evaluate VESTA using three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers that culminates in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. VESTA's dynamic tool creation outperforms prior agentic pipelines for statistical analysis and visual tool creation, with the largest gains on complex and domain-specific tasks. Against strong agentic coding harnesses (Claude Code, Codex, and OpenCode), VESTA is better on all time series tasks and on complex distribution fitting tasks, though the harnesses achieve better fits on simpler distributions. Further, dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VESTA VLM critic can reason over directly.

cs.AI · cs.CL · cs.CV · cs.LG · stat.CO

新论文 · v1arXiv:2611.26307

Scalable fault vulnerability analysis for ReRAM-based process-in-memory CNN accelerators

Aniseh Dorostkar, Hamed Farbeh, Hamid R. Zarandi, Meysam Sharifzadeh

原文摘要

Resistive random-access memory (ReRAM)-based processing-in-memory (PIM) accelerators offer a highly efficient platform for parallel matrix-vector multiplications (VMM) in neural networks, leveraging analog computation, high density, low leakage, and non-volatility. However, their susceptibility to permanent faults, such as stuck-at-high (\textit{SaH}) and stuck-at-low (\textit{SaL}) resistance states, permanently corrupts the convolutional neural networks (CNNs) weights mapped onto ReRAM cell conductance values, thereby degrading inference accuracy and leading to system unreliability in safety-critical applications. Fault injection is a commonly used technique to assess the vulnerability of neural networks by systematically injecting faults into individual parameters and measuring the resulting accuracy degradation. Although this method is accurate, it is prohibitively time-consuming and computationally expensive, especially for large-scale CNNs. In this paper, we propose a fast, scalable, and analytical framework to quantify the fault vulnerability of convolutional neural networks deployed on ReRAM-based PIM accelerators. This method quantifies vulnerability at different granularities, including weights, kernels, and layers, without the need for exhaustive simulation, enabling the design of fault-tolerant accelerators for edge and safety-critical applications. The comparison between the results of the proposed vulnerability score (VS) metrics with performance metric of CNNs captured with fault injection simulations confirms the effectiveness of our proposed method. Unlike exhaustive fault injection, which requires days or weeks, whereas the proposed approach achieves a speedup of about $10^4\times-10^5\times$, enabling fast and accurate vulnerability analysis for large-scale CNNs within only a few minutes or hours.

cs.AR · cs.LG

版本更新 · v3arXiv:2606.19230

A human-in-the-loop Bayesian optimization framework for constraint-aware bioprocess development

Samuel Stricker, Claus Wirnsperger, Alessandro Butté, Laura Marie Helleckes, Gonzalo Guillén Gosálbez, Antonio del Rio Chanona, Mehmet Mercangöz

原文摘要

We present Pareto Front Guided Sampling (PFGS), a human-in-the-loop (HiL) Bayesian Optimization (BO) framework that reformulates surrogate-model predictions as a multi-objective optimization problem, allowing domain knowledge to beadded intuitively to any BO problem. PFGS addresses constrained optimization by treating the posterior probability of constraint satisfaction as an explicit Pareto objective, and robust optimization via a Monte Carlo estimate of expected lower-confidence performance under input perturbations, capturing likely degradation. The multi-dimensional Pareto front makes trade-offs between predicted performance, model uncertainty, constraint satisfaction, and robustness visible through pairwise two-dimensional projections on an interactive dashboard, allowing selection criteria to be refined as the model and objectives evolve. The framework is showcased on a eight-dimensional in-silico fed-batch Chinese Hamster Ovary cell culture case study. We showed improved performance over BO when the expert has perfect domain knowledge; however, PFGS is not designed to outperform BO, but rather to present a HiL acquisition function framework.

cs.LG · cs.HC · stat.ML

新论文 · v1arXiv:2611.26291

Who Moved My $Z$ Boson? Revealing Resonance Features Inside a Neural Network

Kevin Alberto Urquía Calderón, Midori Kato, Inar Timiryasov, Oleg Ruchayskiy

原文摘要

Methods used in mechanistic interpretability have revealed human-aligned concepts inside language and image models. In this paper, we search for physics concepts inside a neural a generative collider physics model trained on real LHC data (ShellFlow). We discover features inside ShellFlow that represent resonances, such as the $Z$, $J/ψ$, and $Υ$. The network was never told which muons come from a resonance, it was only trained to generate the kinematics of the final-state particles. We use these features to alter aspects of the $Z$ boson: we change its mass between $\sim80$ and $105$ GeV, and removing such a feature from the neural network produces a broader $Z$ peak. In both cases the rest of the invariant mass spectrum remains mostly unchanged. The feature was built from the gradients of the neural network, and its selectivity was built using pattern recognition methods. A generative particle physics model trained on unlabeled data can be modified internally to change a physical quantity.

hep-ph · cs.LG · hep-ex · physics.data-an

版本更新 · v3arXiv:2609.39632

Towards Better Exploration in Sequential Test-Time Scaling

Joseph Rance, Fabio Pizzati, Juil Sock, Woody Bayliss, Marc Górriz Blanch, Philip Torr, Adel Bibi

原文摘要

Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over long timescales. Parallel methods repeatedly sample independent answers from the model, scaling poorly on problems the model is unlikely to solve in a single attempt. In contrast, sequential methods build on previous answers to access new ideas, yet so far have not been shown to reach answers beyond those found by parallel scaling. First, we show that sequential scaling often stops improving because it becomes prematurely trapped in an attractor: a set of answers that prevents exploration of different answers once entered. Across 27 combinations of scaling methods, models, and benchmarks, we find that 53.8% of sequential scaling trajectories enter an attractor within four iterations. Second, we show that a simple model-mixing intervention helps escape attractors. This reduces the attractor hit rate by 21.2 percentage points on average, expands solution coverage beyond a compute-matched parallel baseline, and improves accuracy of recursive self-aggregation by at least 2.2 percentage points. Our results motivate refocusing long-horizon test-time scaling from parallel methods to sequential methods that improve previous answers.

cs.LG