News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 4d ago FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding arXiv:2608.23849v1 Announce Type: new Abstract: Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives are diverse but easy, whereas hard-negative miners… 15 arXiv — Machine Learning research 4d ago UHI-Bench: Benchmarking Dual-Source Urban Heat Island Modeling Across Cities in Diverse Climate Regimes arXiv:2608.23857v1 Announce Type: new Abstract: Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface temperature UHI (LST-UHI) and near-surface air temperature UHI (AirT-UHI), capture… 21 arXiv — Machine Learning research 4d ago Revelation Control arXiv:2608.23860v1 Announce Type: new Abstract: Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision, while accounting separately for any useful progress created… 30 arXiv — Machine Learning research 4d ago Every Layer Counts: An Exponential $L_2$ Depth Hierarchy for ReLU Networks arXiv:2608.23877v1 Announce Type: new Abstract: We prove a depth hierarchy for ReLU neural networks in which every additional ReLU layer can save exponentially many neurons. For every $\ell\geq 3$, a globally $[0,1]$-valued, $1$-Lipschitz function is realized by a depth-$\ell$… 15 arXiv — Machine Learning research 4d ago Partial Optimal Transport on the Circle for All Transported Masses in O(N log N) arXiv:2608.23910v1 Announce Type: new Abstract: Partial optimal transport compares two measures while leaving part of the mass unmatched, which is what makes it robust to outliers, occlusion, and clutter. The quantity of interest is usually the whole profile - the optimal cost… 29 arXiv — Machine Learning research 4d ago The Loss Floor of Denoising Score Matching: Fisher Geometry from Schr\"odinger Bridges arXiv:2608.23916v1 Announce Type: new Abstract: Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. The two objectives share the same population minimizer, but the conditional target… 6 arXiv — Machine Learning research 4d ago GATNextHop: A GAT for Shortest Path Routing with Cross-Topology Generalization arXiv:2608.23917v1 Announce Type: new Abstract: Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topology, limiting scalability in dynamic or large-scale networks. This paper… 7 arXiv — Machine Learning research 4d ago MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences arXiv:2608.23936v1 Announce Type: new Abstract: We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public and available-by-permission… 25 arXiv — Machine Learning research 4d ago CoDrift: Compositional Drifting for Offline Reinforcement Learning arXiv:2608.23939v1 Announce Type: new Abstract: Offline reinforcement learning is intrinsically multi-objective: a policy must remain compatible with the behavioral support of a fixed dataset while preferentially selecting high-value actions. We recast these objectives in a… 18 arXiv — Machine Learning research 4d ago Low-Latency Activation-Regularized Sparse Neural Operators with Distillation Assistance Towards Real-Time Edge-Deployable Virtual Sensing arXiv:2608.23987v1 Announce Type: new Abstract: Virtual sensing enables digital twins and safety-critical systems to reconstruct and forecast spatial-temporal physics in real time. However, conventional computational and data-driven methods often face challenges in… 14 arXiv — Machine Learning research 4d ago Revenge of Monosemanticity: Specialized Neurons Improve Data Efficiency in MLPs arXiv:2608.24007v1 Announce Type: new Abstract: Understanding how neural networks learn and organize features is central to understanding their behavior. Much existing theory of feature learning has focused on the emergence of a global low-dimensional predictive geometry. We… 10 arXiv — Machine Learning research 4d ago ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning arXiv:2608.24033v1 Announce Type: new Abstract: Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still… 28 arXiv — Machine Learning research 4d ago PinSieve: Production Selective VLM Serving and a Governed Memory Flywheel for Enterprise Content-Quality Triage arXiv:2608.24040v1 Announce Type: new Abstract: Enterprise AI agents in production often need to be bounded, stateful, observable, and governable rather than fully autonomous. We present PinSieve, a production case study in a large-scale content-quality pipeline. Its deployed… 21 arXiv — Machine Learning research 4d ago XP-JEPA: Cross-Predictive Physics Grounding for Forecastable Latent Dynamics arXiv:2608.24044v1 Announce Type: new Abstract: Latent world models plan by predicting how candidate actions transform learned representations. In self-predictive models, however, the encoder and predictor are optimized jointly and can co-adapt to latent transitions that are… 7 arXiv — Machine Learning research 4d ago Physics-Integrated Operator Learning via Gaussian Splatting Representations arXiv:2608.24049v1 Announce Type: new Abstract: Neural operators provide efficient surrogates for spatiotemporal PDE systems, but purely data-driven formulations often accumulate substantial errors during long-horizon autoregressive prediction and may fail to exploit available… 38 arXiv — Machine Learning research 4d ago ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport arXiv:2608.24051v1 Announce Type: new Abstract: Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses temporal history into stable complex… 18 arXiv — Machine Learning research 4d ago PhysicsBench: A Unified Leaderboard for Generative and Predictive Models in Engineering Design and Simulation arXiv:2608.24056v1 Announce Type: new Abstract: Generative and predictive artificial intelligence models are increasingly used to generate geometry and to predict physical fields and scalar quantities in engineering design and simulation. Yet these models are typically evaluated… 7 arXiv — Machine Learning research 4d ago Mechanistic Circuit Identification for Controllable Data Generation arXiv:2608.24065v1 Announce Type: new Abstract: While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still rely on heuristic prompt-based control. This black-box paradigm provides limited insight into how individual samples… 15 arXiv — Machine Learning research 4d ago A Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps: Scaling a MEDLINE Atlas to 1.05 Million Neurons on a Single Consumer GPU arXiv:2608.24067v1 Announce Type: new Abstract: A self-organising map turns a large corpus into a browsable two-dimensional atlas, but building one at MEDLINE scale has been impractical: the best-matching-unit (BMU) search that dominates training is bound by the bandwidth needed… 26 arXiv — Machine Learning research 4d ago Knowing When to Ask for Help: Bayesian Self-Escalation in Hierarchical LLM Agents arXiv:2608.24087v1 Announce Type: new Abstract: Current LLM agent systems decide delegation before reasoning begins (a router picks a model) or after a response is complete (a verifier scores it and may retry). We study a third regime: an agent that recognises, during its own… 30 arXiv — Machine Learning research 4d ago The Sharp Tail of Uniform Stability arXiv:2608.24098v1 Announce Type: new Abstract: Uniform stability controls how much one training example can change the loss at any test point. A new logarithmic-free upper bound shows that a $\gamma$-uniformly stable algorithm with loss in $[0,L]$ has generalization gap at most… 6 arXiv — Machine Learning research 4d ago Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection arXiv:2608.24113v1 Announce Type: new Abstract: Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring temporal structure, such as shifted periodicity or localized oscillatory fluctuations. However, existing LLM-based time-series… 23 arXiv — Machine Learning research 4d ago A mesh-free multiresolution deep energy method with phase-field modeling of brittle fracture arXiv:2608.24126v1 Announce Type: new Abstract: Phase-field modeling of brittle fracture removes the need to track cracks explicitly by recasting their evolution as the minimization of an energy functional. In return it requires a discretization dense enough to resolve a… 25 arXiv — Machine Learning research 4d ago From Gradient-Boosted Trees to Deep Recommenders: Practical Lessons from Migrating a Production Customer Support Recommender arXiv:2608.24132v1 Announce Type: new Abstract: Product catalogs in fast-moving service businesses are shifting from static, independently priced SKUs toward dynamically bundled, discount-coupled offerings--a shift that strains the tree-based classifiers traditionally preferred… 18 arXiv — Machine Learning research 4d ago Steering Recurrent Reasoners at Inference Time with Readout Feedback arXiv:2608.24136v1 Announce Type: new Abstract: Recurrent models, which repeatedly update latent states with shared computation blocks, have emerged as powerful architectures for solving complex reasoning tasks. Existing inference-time methods scale computation by running more… 12 arXiv — Machine Learning research 4d ago Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation arXiv:2608.24146v1 Announce Type: new Abstract: In reinforcement learning policy evaluation, classic on-policy methods often suffer from high variance when estimating policy performance. To mitigate this issue, behavior policy search has been proposed to learn data-collecting… 12 arXiv — Machine Learning research 4d ago From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits arXiv:2608.24167v1 Announce Type: new Abstract: Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial observability even determining the indifference subsidy at a single belief requires solving an infinite-horizon belief-state problem… 37 arXiv — Machine Learning research 4d ago PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization arXiv:2608.24207v1 Announce Type: new Abstract: Semantic identifiers (SIDs) represent entities as hierarchical token sequences for generative retrieval and recommendation. Residual-quantization tokenizers construct these sequences by selecting a codeword at each level and… 17 arXiv — Machine Learning research 4d ago A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm arXiv:2608.24210v1 Announce Type: new Abstract: Training neural networks requires balancing the trade-off between fitting the training data and achieving robust performance on unseen inputs. This ability, commonly referred to as generalizability, is determined by the gap between… 22 arXiv — Machine Learning research 4d ago Contrastive Branch Policy Optimization arXiv:2608.24300v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are… 27 arXiv — Machine Learning research 4d ago Causal Analysis for Time Series Foundation Models arXiv:2608.24303v1 Announce Type: new Abstract: Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially… 18 arXiv — Machine Learning research 4d ago A Structural FHMM for Interpretable Disease Trajectories in T2DM arXiv:2608.24328v1 Announce Type: new Abstract: In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Type 2 diabetes mellitus (T2DM). The model represents a patient's latent health… 38 arXiv — Machine Learning research 4d ago When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data arXiv:2608.24381v1 Announce Type: new Abstract: Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missingness remains under-explored. In this paper, we evaluate a mask-and-recover SSL… 24 arXiv — Machine Learning research 4d ago Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning arXiv:2608.24386v1 Announce Type: new Abstract: Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification (UQ) for such outputs remains an open challenge. While E(3)-equivariant neural networks excel at point estimates, they lack rigorous… 36 arXiv — Machine Learning research 4d ago Joint Distribution Alignment for Universal Domain Adaptation arXiv:2608.24429v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditional UDA learning usually assumes that the label spaces of the source and target… 17 arXiv — Machine Learning research 4d ago Evaluating Deep Multivariate Imputation Models on Wearable Device Data arXiv:2608.24436v1 Announce Type: new Abstract: Wearable device data enables continuous health monitoring, but suffers from structured missingness: features sharing a physical sensor drop out together. Deep imputation methods such as BRITS and SAITS have seen limited evaluation… 33 arXiv — Machine Learning research 4d ago WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation arXiv:2608.24479v1 Announce Type: new Abstract: Massively parallel simulation changes the data regime in which off-policy reinforcement learning (RL) is trained, challenging stabilizers designed for data-limited replay. Through controlled experiments across eight benchmark… 35 arXiv — Machine Learning research 4d ago Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning arXiv:2608.24482v1 Announce Type: new Abstract: Mechanistic Localization bridges mechanistic interpretability and post-training optimization by isolating critical parameters via interpretative approaches and then guiding parameter-efficient Supervised Fine-Tuning (SFT) in a… 38 arXiv — Machine Learning research 4d ago Where Entropy Is Measured Matters: Policy Geometry in Bounded Continuous-Control PPO arXiv:2608.24488v1 Announce Type: new Abstract: Many continuous-control policies are optimized as unbounded Gaussians and then mapped into bounded actions. We show that where entropy is measured changes the policy geometry learned by proximal policy optimization (PPO). In an… 29 arXiv — Machine Learning research 4d ago When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study arXiv:2608.24492v1 Announce Type: new Abstract: Uncertainty quantification (UQ) methods are widely used for hallucination detection in large language models (LLMs) in closed-book settings where ground-truth evidence is unavailable at inference time. Prior work has proposed… 17 arXiv — Machine Learning research 4d ago It depends: Incorporating correlations for joint aleatoric and epistemic uncertainties of high-dimensional output spaces arXiv:2608.24518v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) plays a vital role in enhancing the reliability of deep learning model predictions, especially in scenarios with high-dimensional output spaces. This paper addresses the dual nature of uncertainty --… 8 arXiv — Machine Learning research 4d ago From Numerical Simulators of PDEs to Neural Emulators and Back arXiv:2608.24547v1 Announce Type: new Abstract: Simulation is central to modern engineering and science, but the cost of numerical solvers for partial differential equations (PDEs) remains a bottleneck whenever fast or many-query evaluations are required. Neural emulators… 28 arXiv — Machine Learning research 4d ago Persistent Cross Entropy arXiv:2608.24549v1 Announce Type: new Abstract: Persistent entropy is the Shannon entropy of a persistence-based probability measure defined on a persistence diagram. However, its cross-entropy version is not naturally defined because two persistence diagrams generally have… 4 arXiv — Machine Learning research 4d ago FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk Assessment arXiv:2608.24551v1 Announce Type: new Abstract: Machine learning models are widely used in financial fraud and credit-risk detection, yet their adversarial robustness remains difficult to evaluate because financial tabular data involve domain-specific constraints, severe class… 25 arXiv — Machine Learning research 4d ago SeisMamba: Low-Latency Single-Station Seismic Magnitude Estimation for Spatially Distributed Earthquake Early Warning arXiv:2608.24561v1 Announce Type: new Abstract: Rapid earthquake magnitude estimation is central to earthquake early warning, yet many operational systems depend on dense regional seismic networks and region-specific calibration. This creates a spatial coverage barrier for… 11 arXiv — Machine Learning research 4d ago Across the Loss Landscape with Progressive Growth arXiv:2608.24568v1 Announce Type: new Abstract: Deep neural networks generalize well despite their highly nonconvex, overparameterized loss landscapes, a phenomenon often associated with the geometry of the minima found by stochastic optimization. We study how incremental… 8 arXiv — Machine Learning research 4d ago IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents arXiv:2608.24588v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools. In these settings, relevant task information often unfolds over time rather than being fully… 5 arXiv — Machine Learning research 4d ago Delayed Optimizer-State Transport Shapes Short-Horizon Training Decisions arXiv:2608.24593v1 Announce Type: new Abstract: Adaptive optimizers retain gradient history in moment variables, allowing a local change in loss weighting to alter later updates. We examine whether this delayed transport is large enough to change prospective short-horizon… 21 arXiv — Machine Learning research 4d ago Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks arXiv:2608.24597v1 Announce Type: new Abstract: Electroencephalography (EEG) is a widely used window into human brain function, but most EEG models remain tied to a one-dataset-one-model supervised paradigm. Recent EEG foundation models offer a route toward reusable… 16 arXiv — Machine Learning research 4d ago Conditional GraphGANFed: Optimizing Graph-Structured Molecule Generation in Federated Generative Adversarial Networks arXiv:2608.24610v1 Announce Type: new Abstract: Generative adversarial networks (GANs) have garnered considerable attention in molecular discovery for their ability to generate novel and high-quality molecules. To efficiently train a GAN model while preserving data privacy,… 18 Page 9 of 10 · 500 articles ← Newer Older →
