跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

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

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 20:39 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 20:56 — 2026-11-09 20:56（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：2026-11-09 20:39最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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

找到 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 20:38（北京时间）
版本更新 · v2arXiv:2606.16888

LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations

Johannes Heidersberger, Shail Jadav, Dongheui Lee

原文摘要

Learning from Demonstration (LfD) enables intuitive robot skill acquisition by allowing robots to learn directly from human task demonstrations. However, current methods often fail to address the fact that due to suboptimal and inconsistent human behavior, the quality of the demonstration can vary within each demonstration. Therefore, we introduce LOPAL (LOcal Performance-aware Active Learning), an active learning approach that leverages this local demonstration quality information. Our approach consists of two synergistic components. First, a local performance-driven LfD method uses a Gaussian Mixture Model (GMM) to encode both the demonstrated trajectories and their associated local quality assessments. This enables the generation of trajectories that outperform the imperfect demonstrations by utilizing complementary local data of high performance. Second, active data acquisition allows to improve beyond the imperfect demonstrations by collecting additional informative samples. In areas missing good data, the user is actively requested to provide corrections through a shared autonomy (SA) mechanism, while the robot autonomously executes the learned behavior. The efficacy of LOPAL was validated in both a simulation and a real-world experiment. The results from a real-world pipe inspection task showed that the proposed approach can achieve up to 27.31 % improvement in task performance while also reducing the effort required to collect the demonstrations.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.17738

Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC

Ho Fung Tsoi, Dylan Rankin

原文摘要

Many self-supervised methods for training foundation models at the Large Hadron Collider (LHC) rely on data augmentations to encourage the model to embed events into a representation space invariant to certain physical or detector symmetries. A common challenge arises from the large freedom in choosing a proper set of augmentations on which downstream performance depends. The implementation of augmentations involves either modifying existing events, potentially breaking the event fidelity, or simulating more event variants, which is computationally intensive. In this work, we present a data-driven method of pairing events by their similarity via the energy mover's distance (EMD), which measures how similar two events are in terms of the work required to transform one into the other. With this approach, distinct events are sampled and matched by their similarity to serve as views for learning invariance, keeping the physics content of each event intact without handcrafted distortions. We demonstrate this augmentation-free pairing method by pre-training on QCD jets via self-distillation and show that it can yield semantic jet embeddings with downstream discrimination power comparable to or better than an augmentation-based baseline.

hep-ex · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.17726

Self-Supervised Learning for Robust Resonance Mass Regression in Cascade Decays

Ho Fung Tsoi, Alex Yang, Luis Felipe Gutierrez Zagazeta, Shion Chen, Dylan Rankin

原文摘要

Reconstructing the mass of a heavy resonance from its decay products with missing energy is one of the central tasks that directly determine the sensitivity in new physics searches at collider experiments. Supervised learning approaches to this problem often struggle to generalize well due to the presence of various systematic uncertainties and distribution shifts. Exhausting all possible variations in the labeled data can be very compute-intensive, while a failure of the model to generalize can corrupt the reconstructed resonance widths that are critical in peak-hunting analyses. In this work, following the foundation model paradigm, we use a self-supervised approach to pre-train a transformer encoder with VICReg to learn an embedding invariant to various corruptions, then fine-tune it for mass regression on a heavy resonance with masses ranging from 2.5 to 6.5 TeV and a SUSY-like cascade decay into an eleven-body final state. We show that the pre-trained model reconstructs sharper resonance peaks and has a more stable performance under various realistic corruptions, compared to a supervised model of the same architecture trained on the same augmented data from scratch.

hep-ex · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.06615

Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions

Kaichen Shen, Wei Zhu

原文摘要

Score-based generative models commonly employ linear forward diffusions with Gaussian reference distributions, limiting their ability to directly incorporate structural information into the noising dynamics. We introduce latent nonlinear denoising score matching (LNDSM), which combines nonlinear, structure-informed latent diffusions with the variational autoencoder (VAE) training framework. In our construction, the forward diffusion is designed to admit a prescribed reference distribution, such as a Gaussian mixture model, that reflects qualitative features of the latent data distribution. We derive a computable approximation to a cross-entropy upper bound in the VAE objective using Euler-Maruyama discretization and the resulting Gaussian conditional transitions. To stabilize training, we remove two zero-mean control variates whose variances become large for small time steps. The resulting objective enables joint training of the encoder, decoder, and latent score network. Numerical experiments on benchmark image datasets demonstrate the effectiveness of LNDSM in learning structured distributions, outperforming conventional latent score-based generative modeling in sample quality and mode balance across several settings, while achieving improved training efficiency. These results highlight the potential of nonlinear, structure-informed latent diffusions for generative modeling.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36312

SG^2SLAM: Spatial Geometry-Informed 3D Gaussian Splatting SLAM for Monocular Outdoor Navigation

Ziang Guo, Didar Seyidov, Yixiao Zhou, Xuefeng Zhang, Ali Alridha Abdulkarim, Chen Min, Zufeng Zhang, Dzmitry Tsetserukou

原文摘要

Monocular outdoor navigation requires robust camera motion estimation and a dense, navigable map, where 3D Gaussian Splatting SLAM serves this task through an explicit differentiable parameterization and closed-form projection. However, typically, the geometry is recovered by associating 2D pixels with 3D points, so a modular SLAM system absorbs tracking error into the map, leading to cascading degradation. To address these gaps, we present SG^2SLAM, which couples streaming spatial geometry with a ray-conditioned 3DGS kernel. Streaming spatial geometry replaces the per- frame cross-dimensional correspondence with a chunk-level metric prior that supervises tracking and mapping from one source. A ray-conditioned kernel extends each primitive with a viewing-direction subspace that senses the monocular camera viewpoints. The joint optimization over spatial geometry and poses ensures a globally consistent map and trajectory outcome. Experiments on the KITTI and Waymo Open datasets show that our SG^2SLAM surpasses the per-frame association baselines in the monocular outdoor navigation task. Code will be made publicly available upon acceptance.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36311

Confidence Is Not a Promise: A Reference Audit of Typed Decision Models

Pedro Carvalho Brom

原文摘要

Typed decision models return a probability distribution over options supplied by the caller, and software tends to act on that number as if it were a guarantee. We measure what it licenses, comparing the open-weight Laya, in five checkpoints, with Jev 1.13, available only through an API. A probability licenses a statement about groups of decisions, not about one decision, and a gate that promises an accuracy among the cases it decides alone keeps that promise only with a lower bound checked on data like its traffic. Across 190 exchangeable evaluations, a threshold chosen by point estimate breaks the promise in 147, Learn then Test keeps it in all of them, and a Beta lower-bound rule decides more items on average than Learn then Test in 128 and fewer in none, without its guarantee. Calibrated in English, Jev keeps a promise of 95% in 8 of 51 locales. Ordinary typing noise breaks a promise calibrated on clean text, and, in exploratory runs, training with noise raises the noisy accuracy with no loss on clean text. In four further domains, a fine-tuned Laya needs from 250 to 8,000 labels to be non-inferior to Jev, and does not get there on LIAR2. Under drift, the preregistered claim for a Bayesian retraining loop is not supported: the loop avoids needless retraining where the change does not degrade the model, at a cost equivalent to recalibration alone, and re-qualifying the threshold in every window keeps the promise more often where it does. On the monthly series of M3, neither decider predicts the direction of the next value better than a constant answer. Confidence separates right from wrong answers with an AUROC from 0.80 to 0.96, but it does not select faithful explanations, and exact coalition games of single decisions show what an explanation can still say through an API that rounds to two decimals. We release the frozen answers with a datasheet, a promise check and the code.

cs.LG · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36309

Bridging Exploration and Loss of Plasticity in On-Policy Reinforcement Learning

Andrea Vasco Grieco, Evelyn D'Elia, Edoardo Caldarelli, Raffaello Camoriano

原文摘要

Deep reinforcement learning (RL) algorithms have been observed to lose the ability to adaptively learn from new data, a phenomenon termed Loss of Plasticity (LoP). While many metrics have been shown to correlate with it, the causal mechanisms and the geometric conditions from which it can arise have not been clearly identified. We analyze LoP in Proximal Policy Optimization with isotropic Gaussian policies, the state-of-the-art formulation for many continuous action spaces in RL. We report multiple metrics which characterize the effect that the policy standard deviation $σ$ has on LoP, and we also suggest related explanations for the effectiveness of widely adopted LoP mitigation techniques. We observe a significant effect of $σ$ on the extent of LoP, and accompany this with both theoretical and experimental supporting arguments. Our experimental validation consists of LoP benchmark evaluations against standard baselines as well as real-world policy deployment on a 7-DoF robotic arm.

cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36308

When Retrieval Is Not Enough: Obsolete Facts in Agent Memory

Oleeviya Babu Poikarayil, Tony Basil Babu, Abdulrahman Nahhas, Het Darshan Mehta, Jawid Ahmad Baktash, Ernesto William De Luca, Klaus Turowski

原文摘要

Memory-agent benchmarks often collapse retrieval and answer generation into one score, making it hard to tell whether a failure comes from missing an update or from not using an update that was already retrieved. We examine this distinction on the single-hop FactConsolidation task of MemoryAgentBench. With Qwen2.5-7B-Instruct on 6K-history BM25 accuracy drops from 45% to 32% when the retrieved evidence budget grows from 64 to 512 tokens, even though a gold-assisted post-hoc audit finds the newest statement in every retrieved set. Most of the errors occur on questions that also contain an obsolete statement version. Under a frozen prompt and equal four-statement evidence size, replacing one unrelated statement with the obsolete competing statement reduces accuracy from 100% to 44.6% for Qwen2.5 and from 100% to 87.8% for Qwen3-14B, with all 50 harmful paired flips classified as stale. A 32K-history replication likewise favors BM25-64 over BM25-512 (69% versus 58%). These results suggest that retrieving the correct fact is not enough. An obsolete competing statement can be more harmful than an unrelated piece of evidence of the same size.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36306

How Learning Selects Equilibria and When It Leads to Collusion

Hanzhang Wang, Manxi Wu

原文摘要

We study how learning algorithm design shapes equilibrium selection in infinite-horizon discounted Markov games with finite states and actions. Each episode, players choose smooth best responses to beliefs about opponents' policies, test them using noisy observations, and resample rejected beliefs or explore at rates determined by increasing transformations of their discounted values. We show that stochastically stable states induce approximate stationary Nash equilibria maximizing the minimum transformed discounted value across players, with transformations governing which players selection favors. In repeated games with bounded recall of noisy public signals, longer recall weakly increases the selected minimum transformed value. In repeated Cournot games, every stochastically stable state induces an approximate public perfect equilibrium whose minimum discounted profit across firms exceeds the Cournot-Nash benchmark. Collusion is therefore inevitable under these conditions and learning dynamics. For symmetric firms, selected profits can approach the monopoly benchmark arbitrarily closely. These results offer a novel equilibrium-selection perspective on algorithmic collusion.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37710

zkDuel: Characterizing SumCheck Prover Kernels across GPU Programming Models

Samarth Narang, Alhad Daftardar, Brandon Reagen

原文摘要

SumCheck is a central prover primitive in zero-knowledge proofs, exposing table-parallel work that maps naturally to GPUs but becomes increasingly arithmetic-intensive as finite fields widen. We study how this shift affects the cost of programming SumCheck in Triton rather than CUDA. Our benchmark, zkDuel, provides matched implementations of 25 zkPHIRE-derived constraints alongside diagnostic polynomials, covering 32-, 64-, 128-, and 256-bit prime fields, with independent CPU-reference validation and cross-backend checksum gating. Of 800 configurations attempted on an NVIDIA H100, 758 complete with matching checksums. CUDA's median advantage over Triton falls from 3.5x at 32 bits to 1.4x at 256 bits, and Triton is faster on 19 large-table configurations; the same convergence appears on an A100, where the gap falls from 4.4x to 1.6x. Profiling shows that the small-field gap largely reflects host launch overhead and redundant modular additions in Triton's original block reduction, whose relative costs diminish as multi-limb Montgomery work grows. Replacing that reduction with tl.reduce brings Triton's median kernel time within 8% of CUDA on both GPUs, while specialized point interpolation improves 256-bit evaluation kernels by 1.55-1.75x. At cryptographic widths, these results show that a Python-embedded DSL can approach CUDA performance, although the largest fully unrolled constraints still expose compiler-scalability limits.

cs.AR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36303

Deep Learning Volumetric Segmentation for Prediction of Cavity Geometry in Underground Jet Boring Mining

Giovanni Zingaro, Yuan Wang, Deepak Meena, Peter Cheng, Russell Buchanan, John Quilty, Robert Gracie

原文摘要

The Jet Boring System (JBS) is a proprietary technology developed by Cameco Corporation to extract high-grade uranium ore at the Cigar Lake Mine in Northern Saskatchewan, Canada. The JBS remotely excavates ore using a high-pressure water jet that cuts cavities within an artificially frozen ore body. This study outlines a Deep Learning (DL)-based workflow that formulates the cavity prediction problem as a volumetric binary semantic segmentation task. A preprocessing pipeline assembles drilling and jetting records, cavity scans, and a mine-wide geology block model onto a common voxel grid, where each voxel in the prediction is labelled as consumed or non-consumed during jetting. A three-dimensional U-Net with a backfill residual branch is trained on historical field cavities. The model is benchmarked against a baseline consisting of a cylindrical cavity centered along the pilot hole, with a diameter defined by domain experts. The proposed workflow achieves an IoU of 0.601 $\pm$ 0.088 and an F$_1$-Score of 0.747 $\pm$ 0.077 on a held-out test set, improving on the cylindrical baseline currently used in cavity planning by 22.4% and 14.7%, respectively. An eXplainable Artificial Intelligence (XAI) feature attribution approach is applied to identify the most influential input driving the predicted cavity geometry. The accuracy of the proposed model demonstrates its potential to support mine planning.

cs.CE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36300

Building Mathematical Software -- Lessons from the Development of GAP

Alexander Hulpke

原文摘要

Mathematical software has particular needs that are not all covered by the existing literature on software engineering or algorithm design. This paper looks at some of these aspects, in the concrete context of the computer algebra system GAP. It also studies the potential impact AI systems could have on the development process for mathematical software.

math.HO · cs.MS · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36298

Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks

Ayana Moshruba, Maryam Parsa

原文摘要

Machine learning models deployed behind query interfaces expose more than their predictions, because an adversary can use those predictions to rebuild the model itself. Model stealing attacks (MSAs) exploit this exposure by training a surrogate model that replicates the decision behavior of a target through black-box queries alone, without access to its parameters or training data. These attacks are well characterized for conventional artificial neural networks (ANNs), yet spiking neural networks (SNNs) process information in a fundamentally different way. SNNs communicate through sparse, discrete spikes, and their outputs depend on membrane potentials that evolve over time rather than on a static mapping from input to output. This temporal mode of computation suggests that the decision behavior of an SNN may be harder to reconstruct from its responses. This work tests that possibility by benchmarking four representative MSAs, namely the Papernot, Tramèr, T-RND, and color perturbation attacks, against SNNs and their ANN counterparts on MNIST, Fashion-MNIST, and CIFAR-10. Across every attack and dataset, SNNs prove consistently more difficult to steal. Surrogates of SNNs achieve 10% to 20% lower agreement with the target model and 15% to 25% lower adversarial transferability than surrogates of ANNs. We attribute this resistance to the way SNNs compute, as their spike-based and time-dependent dynamics yield decision boundaries that ANN-based surrogates struggle to approximate, even under large query budgets. These findings extend the known resilience of SNNs beyond attacks on training data to the replication of model functionality, strengthening the case for neuromorphic architectures in security-sensitive applications.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36295

Detecting and Mitigating Query-Based System Prompt Leakage Attacks

Tushar Nayan, Pratik Poudel, Qian Lou, Yuede Ji, Jason Liu, Ruimin Sun

原文摘要

Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions. Existing defenses often assess queries independently, missing malicious behavior that emerges across interactions. We present AdvGuard, a model-agnostic framework for detecting and mitigating system prompt leakage. AdvGuard models cross-query relationships using a bounded semantic interaction graph, statistically filters candidate components, and converts them into line graphs for graph convolutional network (GCN) classification. This approach captures multi-hop patterns in query similarity that distinguish coordinated extraction from benign workflows. A lightweight prompt-level detector provides protection before sufficient interaction history accumulates, and the framework supports black-box LLM deployments. In mixed-query evaluations, AdvGuard improves recall by up to 36% over the strongest baseline while maintaining a false positive rate of at most 3.4%. In multi-turn workloads, it achieves 97.23%-99.1% F1 with 100% recall. Leave-one-attack-family-out tests yield 99.98% mean recall and 99.99% mean F1, with no observed false positives. Integrated into the adaptive PLeak and LeakAgent attack loops, AdvGuard limits exact-match leakage to 0.00-0.01 and substring-match leakage to 0.01-0.09 across evaluated victim models. These results demonstrate robust detection of unseen attack families and substantially reduced prompt reconstruction.

cs.CR · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.12273

Learning to Control: The iUzawa-Net for Nonsmooth Optimal Control of Linear PDEs

Yongcun Song, Xiaoming Yuan, Hangrui Yue, Tianyou Zeng

原文摘要

We propose an optimization-informed deep neural network approach, named iUzawa-Net, aiming for the first solver that enables real-time solutions for a class of nonsmooth optimal control problems of linear partial differential equations (PDEs). The iUzawa-Net unrolls an inexact Uzawa method for saddle point problems, replacing classical preconditioners and PDE solvers with specifically designed learnable neural networks. We prove universal approximation properties and establish the asymptotic $\varepsilon$-optimality for the iUzawa-Net, and validate its promising numerical efficiency through nonsmooth elliptic and parabolic optimal control problems. Our techniques offer a versatile framework for designing and analyzing various optimization-informed deep learning approaches to optimal control and other PDE-constrained optimization problems. The proposed learning-to-control approach synergizes model-based optimization algorithms and data-driven deep learning techniques, inheriting the merits of both methodologies.

math.OC · cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.07063

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training

Pingbang Hu, Xueshen Liu, Z. Morley Mao, Jiaqi W. Ma

原文摘要

Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant but imperfectly aligned general training data. In this work, we move beyond the data-selection framing and introduce Dr. Post-Training (Data-Regularized Post-Training), a novel framework that reconceptualizes general training data as a data-induced regularizer that prevents overfitting to the scarce target objective, rather than serving as a pool for selection. Specifically, our framework proposes that, at each training step, we construct a feasible set of model update directions using the general training data, and project the model update direction specified by the scarce target data onto that feasible set. Standard training and existing data selection methods arise as special cases with different choices of the data-induced regularizer, and these methods correspond to different points on a bias-variance spectrum with different regularization strengths. Building on this view, we propose a family of methods offering a richer design space and more flexible bias-variance tradeoffs. For practical LLM-scale use, we introduce careful system optimizations that realize these methods with minimal overhead. Extensive experiments across SFT, RLHF, and RLVR show that our methods outperform standard training and state-of-the-art data selection baselines, with the largest gains where the general and target data are most misaligned, and system benchmarks confirm their efficiency.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.08488

NN-OpInf: an operator inference approach using structure-preserving composable neural networks

Eric Parish, Anthony Gruber, Patrick Blonigan, Irina Tezaur

原文摘要

We propose neural network operator inference (NN-OpInf): a structure-preserving, composable, and minimally restrictive operator inference framework for the non-intrusive reduced-order modeling of dynamical systems. The approach learns latent dynamics from snapshot data, enforcing local operator structure such as skew-symmetry, (semi-)positive definiteness, and gradient preservation, while also reflecting complex dynamics by supporting additive compositions of heterogeneous operators. We present practical training strategies and analyze computational costs relative to linear and quadratic polynomial OpInf (P-OpInf). Numerical experiments across several nonlinear and parametric problems demonstrate improved accuracy, stability, and robustness over P-OpInf and prior NN-ROM formulations, particularly when the dynamics are not well represented by polynomial models. These results suggest that NN-OpInf can serve as an effective drop-in replacement for P-OpInf when the dynamics to be modeled contain non-polynomial nonlinearities, offering potential gains in accuracy and out-of-distribution performance at the expense of higher training computational costs and a more difficult, non-convex learning problem.

cs.LG · math.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36289

Compatibility and future-proof testing for multi-agent systems

Yueshan Li, Lorenzo Fiaschi, Andrea Censi, Emilio Frazzoli

原文摘要

Independently developed autonomous agents, such as autonomous vehicles, must guarantee joint compatibility, such as safety and task-completion requirements, when they operate in a shared environment. Existing methods require a centrally designed specification, or interaction mechanism before any agent is deployed. However, such centralized design is unrealistic when agent designs are confidential to their developers, and it is not flexible enough to accommodate future agent designs. We study a bi-level structure in which a regulator coordinates developers by publishing seed agents, and each developer independently tests its agent to ensure that it is compatible with every seed-compatible agent, a property we call future-proofness. Under this structure, joint compatibility is guaranteed for any agents that are designed and tested independently, without any coordination with each other. In this work, we first formulate compatibility for general multi-agent systems and show why it is not trivially implied by seed-compatibility. We then characterize the future-proof agents as the closure of the seed and show that this closure is monotone in the seed. Finally, we study a class of executable tests that involve interaction with the seed alone, and we ask to what extent such tests can distinguish the future-proof agents.

cs.MA · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36288

BUSTA: Teaching Small Language Models to Reason About Binary Execution

Ritika Poddar, Aidan Fennelly, Deirdre Murphy, Eric Wolos, Corre L. Steele, Michael Doyle

原文摘要

Large Language Models (LLM) are increasingly applied to Reverse Engineering (RE) workflows. RE, however, differs from common LLM coding tasks as it requires models to reason about low-level program behavior. Furthermore, the deployment of tooling in resource-constrained sandboxed RE environments limits the ability to use frontier-scale solutions. We examine whether a targeted LLM training approach can transfer distinct RE skills to open models via inverse basic-block execution: given an x86-64 basic block and a desired output register state, the model predicts the input register values that produce it. Fine-tuning \texttt{Qwen3-1.7B} and \texttt{Nemotron-3-Nano} with Group Relative Policy Optimization (GRPO) raises knowable-register prediction accuracy from 73.2\% to 85.3\% and from 63.3\% to 95.2\%, respectively. Frontier models still score highest (up to 99.2\%), but our fine-tuned \texttt{Nemotron-3-Nano} comes within four points at a fraction of the parameter count. We release both fine-tuned models and the training dataset.

cs.CR · cs.AI · cs.LG · cs.PL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36287

A Smart Instant Book Filter Model based on Dual-Objective Optimization

Yi Hou, Li Fan, Huizhong Duan

原文摘要

Hospitality service in online marketplaces has become increasingly popular over the past few years, not only because it helps people easily rent short-term lodging but also because it empowers travelers to connect with locals and feel belonging. A typical pattern of these industries is a central platform mediating the economic interactions between guests and hosts, where a successful booking experience is the key to user satisfaction. However, one of the biggest challenges is the possible delay of response and chance of rejection when guests try to book a request-to-book listing. Previously, we enabled the instant book feature to allow hosts to instantly accept qualified guests and guests to confirm bookings immediately. Yet the symptom has not been alleviated given mixed request-to-book and instant book listing supply in search results. One possible solution is to promote all instant book listings in search results; however, booking rate will be damaged due to some improperly promoted low quality listings. In this paper, we present a novel smart instant book filter system that applies the instant book filter intelligently and shifts request-to-book to instant book without hurting booking rate. Compared with traditional two-sided markets research that targets finding strategies to maximize a single overall social welfare goal, our proposed system aims to maximize the instant book rate with the constraint that booking rate should not decrease, forming a dual-objective optimization problem. We show A/B testing results for our system exposed to global users, demonstrating that our model performs better than previous human-expert-tuned models in terms of both instant book rate and overall booking rate. We also achieved improved metrics such as the host instant book adoption rate. The proposed system has been deployed to production and is serving millions of users every day.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36285

ASPEN: Adaptive Semantic Reasoning via Command Persistence Prediction for Efficient Navigation VLAs

Vieri N. Akustia, Bin Hu

原文摘要

Navigation vision-language-action (VLA) policies repeatedly invoke costly semantic reasoning even when the next command remains unchanged. Command reuse can reduce computation but risks missing instruction-dependent turns or stops. We introduce ASPEN, an event-triggered scheduler based on command persistence prediction: estimating whether the frozen base policy would reissue its previous command. A lightweight multimodal predictor combines temporal observations, language instructions, execution history, and cached VLA confidence. At eligible command boundaries, sufficient predicted persistence permits command reuse. Otherwise, ASPEN triggers fresh semantic reasoning from the VLA. Evaluated with frozen NaVILA on cross-dataset RxR-CE val-unseen, ASPEN reduces VLA calls by 9.5% and estimated inference time by 8.1%, including scheduling overhead. It maintains comparable navigation performance and preserves identical baseline action sequences on 92.1% of episodes.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.30749

From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation

Ying Yuan, Xinyu Liu, Sriram Krishna, David Held

原文摘要

Large-scale dexterous grasp datasets encode rich priors over hand-object interaction, but their use has largely been confined to grasp generation and pick-and-place manipulation. We study whether such data can instead support functional dexterity in articulated tool use, where a robot must acquire a tool, maintain contact, and operate its functional moving parts. We adapt a hierarchical imitation learning framework that combines high-level hand sub-goal prediction with a low-level goal-conditioned controller. We construct a 355k-trajectory grasp-pretraining dataset from large-scale dexterous grasp annotations and use it to pretrain the low-level controller. The controller is then fine-tuned on downstream task demonstrations. To evaluate this setting, we introduce DexCraft, a simulation benchmark with six articulated tool-use tasks requiring coordinated finger motion. Across simulation and real-world experiments, our approach outperforms end-to-end diffusion policy baselines and hierarchical policies trained from scratch. In the real world, it improves full-task success by 33.3 percentage points over DP3. These results show that grasp datasets can serve not only as resources for grasp synthesis, but also as scalable pretraining data for contact-rich dexterous manipulation. Videos are shown on https://yingyuan0414.github.io/grasp2dexterity/ .

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2608.07578

Demodalising Gödel's God? Ultrafilters, Rigidity and Modal Collapse Revisited

Christoph Benzmüller

原文摘要

Gödel's ontological argument is modal by design. Possibility and necessity are among its central concerns, and connected interpretation decisions -- extensions or intensions for the positive properties, constant or varying quantifier domains, the choice of modal logic, etc. -- subtly shape the argument and, in particular, whether the modal collapse is implied or not. It is tempting to abstract the modality away and to read the positive properties as merely forming an ultrafilter -- which, however, may replace Gödel's argument with a perhaps more manageable alternative that may have little to do with Gödel's original intention. In this spirit, Odifreddi and Gomes argue that modal collapse is an intrinsic structural feature of any theory that characterises positive properties as an ultrafilter and identifies God as its principal generator. This comment shows that the structural claim is false. There is an explicit S5 model, with constant domains, in which positivity is at every world a modal ultrafilter principally generated by a unique and necessarily existing Godlike individual, and in which the modal collapse nevertheless fails -- already for an atomic formula. What drives the collapse is not the ultrafilter structure but the rigidity of positivity -- itself a thoroughly modal condition: given only that positivity is a modal ultrafilter, modal collapse and rigidity are equivalent. Rigidity is thus exactly what the collapse adds to the ultrafilter structure, and the disagreement is whether it is to be counted part of that structure at all. Two further claims of Odifreddi and Gomes are clarified: one on the derivability of Gödel's Theorem IV, one on the extensionality of positivity. All results are machine-checked in Isabelle/HOL, which distinguishes kernel-checked proofs from model-finder output.

math.LO · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.18202

Locally invariant manifolds and foliations

Lachlan Ewen MacDonald

原文摘要

Invariant manifolds and foliations associated to invariant pseudo-hyperbolic reference geometries have been well-studied in the context of dynamics implemented by a diffeomorphism. In this paper, we provide sufficient conditions for the existence of maximally smooth, \emph{locally} invariant manifolds and foliations containing a given \emph{locally} invariant, pseudo-hyperbolic reference geometry, in the context of dynamics implemented by a smooth map which need not be invertible. The theory is motivated by applications to the developing theory of large-step optimisation.

math.DS · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.38829

Diversity Combining for Multi-Path LLM Reasoning

Guangsheng Yu, Litianyi Zhang, Qin Wang, Xu Wang, Mingyuan Li, Shaoxiong Ji, Ren Ping Liu, Massimo Piccardi

原文摘要

Multi-path reasoning methods such as self-consistency (SC) sample $K$ reasoning paths and choose the most frequent answer. However, their gains quickly plateau as $K$ increases, and locating this saturation point currently requires fitting a scaling model to accuracies measured at several values of $K$ or stopping online per query. We formalize multi-path LLM reasoning as a diversity combining problem from wireless communications: each path is a noisy channel observation, and the pairwise correlation of path correctness caps the design-effect effective sample size of the vote at a finite ceiling. Generalized least squares (GLS) analysis shows that, for paths with equal gains, the optimal linear combiner of latent embeddings is uniform exactly when every row of the path covariance has the same sum, as under exchangeability, supporting majority vote as the natural default in standard SC while leaving room for weighting or pruning under heterogeneous prompt-template branches. Across 5 models and 12 benchmarks, prompt-template diversity reduces path correlation in $55$ of $60$ model-benchmark cells, with a mean relative reduction of $16\%$ and reductions in every task domain. We derive an Adaptive-K rule that uses a four-path pilot to select $K^*$, retaining $96$--$103\%$ of MV@$K{=}32$ accuracy across Math, QA, and NLU.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36281

Privately Clipping Heavy-Tailed Data

Matthew Joseph, Alex Kulesza

原文摘要

Summing vectors is a basic task in differentially private data analysis. Standard private sum algorithms clip vectors to some bound, sum them, and add noise scaled to the bound. The differential privacy literature has developed a deep library of noise addition mechanisms, but it offers few tools for privately choosing a clipping bound based on the data. We introduce a method that privately chooses a clipping bound by optimizing residual coherence, the directional alignment of vectors exceeding the bound, against the variance cost of additional noise. We prove a close relationship between residual coherence and bias for a general class of heavy-tailed data regimes and show empirically that, across several datasets, our method outperforms existing baselines.

cs.CR · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.36280

EVA-Flow: Learning Shared Chemistry for Unified Environment-Aware Molecular Conformation Generation

Bing Yan, Anuroop Sriram, Zachary Ward Ulissi, Kyunghyun Cho, Ricky T. Q. Chen, Benjamin Kurt Miller

原文摘要

Molecular 3D structures underpin simulations of thermodynamics, kinetics, crystallization, and nucleation, making their accurate prediction central to drug discovery and materials design. However, molecular geometry can change dramatically across environments. Existing models either ignore environmental effects or train separate models for each environment. We hypothesize that transfer learning across contexts is possible for conformer generation and that a general model will perform better when training data are limited, as in ligand binding and crystallization. We introduce EVA-Flow, a unified framework for environment-aware molecular conformation generation that learns shared chemical structure and adapts it through environment-conditioned generative modeling. Across vacuum, protein-ligand docking, solvation, and crystal packing, pretraining and cross-environment finetuning provide their largest gains in the three data-scarce settings. Evaluation against multiple reference conformations shows that EVA-Flow covers a broad range of solvation conformations. Analyses of molecules shared across environments support its ability to generate different conformations for the same molecule in different environments.

cs.LG · cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2403.12357

Unifying Sparse Estimation of Precision and Covariance Matrices

Aramayis Dallakyan, Mohsen Pourahmadi

原文摘要

Penalized maximum likelihood is a widely used approach to estimate a sparse precision or a sparse covariance matrix. A zero in the precision matrix encodes a conditional independence and a zero in the covariance matrix a marginal independence, and the two estimators have been developed separately, each with its own algorithm. We show that these two problems can be unified via a single reparametrization of the last column of either matrix. This reparametrization decouples the likelihood function for each problem to a one-dimensional minimization followed by a penalized multiple regression. Our approach applies to any penalty that is separable in the off-diagonal entries and linear on the diagonal. When the penalty is the $\ell_1$ norm, it unifies the graphical Lasso and the covariance graphical Lasso algorithms.

stat.CO · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37709

Towards Myocardial Infarction Diagnosis: An Investigation into Machine Learning and Deep Learning Algorithms using ECG Data

Rafid Ahnaf, Husne Mubarak, Fahim Ahsan, G. M. Refatul Islam, Rafeed Rahman, Nabuat Zaman Nahim

原文摘要

Myocardial Infarction (MI) is a severe and potentially fatal cardiac condition caused by myocardial injury due to ischemia, and timely detection can substantially reduce its mortality. Electrocardiography (ECG) is the primary diagnostic modality for MI, but manual interpretation is susceptible to human error. In this work, we propose Visionary V2, a multi-step, adaptive filtration method for ECG signal normalization, and use it to study machine learning (ML) and deep learning (DL) approaches to MI detection on the PTB Diagnostic ECG Database using all 15 available leads. On statistical features extracted from the filtered signals, such as the R-R interval, a Bagging ensemble of decision trees reaches 96.6% accuracy, compared with 87.7% when the signals are processed with BioSPPy. We further generate an image dataset from the filtered signals, on which a custom ResNet-50 misclassifies only 1 of 7,000 validation images and a custom CNN reaches an F1 score of about 98.7%. Finally, we apply LIME, Grad-CAM and Integrated Gradients to verify that the image models attend to the ECG waveform rather than the background. These results indicate that careful signal normalization combined with ML and DL models can support fast and accurate automated MI screening.

eess.IV · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.21975

Machine learning and digital pragmatics: Which word category influences emoji use most?

Mohammed Q. Shormani, Lamia Alhassoun, Yehia A. AlSohbani

原文摘要

This study examines the performance of the state-of-the-art MARBERT model in identifying the lexical/pragmatic category associated with emoji use on X within a digital pragmatics approach (DPA). A net corpus of 15856 Colloquial Arabic (CA) posts containing emojis was collected from X using Python. The texts were tokenized and normalized into 4 lexical categories, namely noun_norm, verb_norm, adj_norm, and adverb_norm, and 2 pragmatic/structural categories, question_norm and exclamation_norm. MARBERT was finetuned and optimized to identify which category scores standard metrics more, hence associated with emoji use, while binary logistic regression was used to examine which category is statistically associated with emoji occurrence. Findings unveil that nouns dominate the corpus in normalized frequency (M = 0.675, SD = 0.161), followed by verbs (M = 0.083, SD = 0.100). However, verbs have the strongest influence of emoji use indicated by verb density (\b{eta} = 0.821, p = .001, 95% CI [0.332, 1.309]). Findings further show that MARBERT performs comparatively well for verbs (precision = .74, recall = .99, F1 = .85) and nouns (precision = .88, recall = .44, F1 = .59), and substantially weaker for the less frequent categories. The study concludes that in digital pragmatics of CA on X, emoji use association with lexical/pragmatic category can be explained by a hybrid approach of computational, statistical, and pragmatic methods, reflecting the interaction among machine learning, linguistic/lexical features, contextual representation, and digital communication.

cs.CL

查看论文
arXiv ↗PDF ↗