News / #paper Tag Research papers 500 articles archived under #paper · RSS Sign in to follow arXiv — Machine Learning research 5d ago Low-rank tensor structure of precipitation and its application to satellite-reference merging arXiv:2610.11000v1 Announce Type: new Abstract: The intermittent and variable nature of precipitation makes its accurate estimation over extended domains difficult, yet its spatiotemporal structure suggests that a low-rank representation may be possible. This work represents… 34 arXiv — Machine Learning research 5d ago Emergent Inverse-Depth Scaling From Nonlinearity In Attention arXiv:2610.11063v1 Announce Type: new Abstract: Scaling laws describe power-law improvements in model performance with dataset size and parameter count, yet their underlying mechanisms are not fully understood. To explain the parameter count scaling, existing theory posits… 12 arXiv — NLP / Computation & Language research 5d ago Measuring and Mitigating Solution Mode Collapse in RLVR arXiv:2610.11064v1 Announce Type: cross Abstract: A language model (LM) can usually answer the same question in more than one way, but reinforcement learning with verifiable rewards (RLVR) is indifferent to which correct answer a model produces. A solution will earn the same… 12 arXiv — Machine Learning research 5d ago CityDeploy-Bench: Benchmarking Physics-Grounded Spatial Set Planning for Multi-Transmitter Network Deployment arXiv:2610.11065v1 Announce Type: new Abstract: Automating city-scale wireless deployment remains challenging under complex urban propagation and network-wide interference. We introduce \textbf{CityDeploy-Bench}, a benchmark that reframes multi-transmitter deployment as… 7 arXiv — Machine Learning research 5d ago Optimally Pacing Budget Spending and Learning arXiv:2610.11074v1 Announce Type: new Abstract: We establish near-optimal regret bounds for budget-constrained online learning against arbitrary classes of budget-pacing experts in the adversarial setting. In particular, given any class of $F$ experts and a candidate budget… 36 arXiv — Machine Learning research 5d ago Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning arXiv:2610.11076v1 Announce Type: new Abstract: Domain-specific continual adaptation of LLMs risks catastrophic forgetting, creating a fundamental tension between acquiring new capabilities and preserving those learned during pretraining. PEFT mitigates this problem by… 31 arXiv — Machine Learning research 5d ago DaCe-DT: Data-Centric Offline Multi-Task Reinforcement Learning via Adaptive Prompts and Trajectory Correction for Heterogeneous Tasks arXiv:2610.11085v1 Announce Type: new Abstract: Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing methods mainly focus on algorithmic optimization, with less emphasis on data-level… 26 arXiv — Machine Learning research 5d ago Cova-PINN: Cross-Domain Conservation Physics-Informed Neural Network for Fluid-Solid Conjugate Heat Transfer in Complex Geometries arXiv:2610.11108v1 Announce Type: new Abstract: Multi-domain physics-informed neural networks (PINNs) flexibly model medium-specific representations to solve fluid--solid conjugate heat transfer (CHT). However, standard multi-domain PINNs enforce governing equations and… 33 arXiv — Machine Learning research 5d ago Dynamics as Code: On Model Compression via Dynamic System arXiv:2610.11115v1 Announce Type: new Abstract: The escalating size of pretrained neural networks has rendered model compression a prerequisite for deployment under stringent memory and compute constraints. With the irrational winding as an example, earlier work introduced a… 26 arXiv — Machine Learning research 5d ago Machine Learning Optimization for Enhanced OS Fingerprinting arXiv:2610.11133v1 Announce Type: new Abstract: Operating System (OS) Fingerprinting is a technique that can be used to identify a network's operating systems by evaluating network traffic in the form of TCP/IP packets. This research will explore the effectiveness of passively… 33 arXiv — Machine Learning research 5d ago QUILT: Rethinking Sparse-Attention Prefill through Shared Query Execution arXiv:2610.11134v1 Announce Type: new Abstract: Sparse attention reduces the cost of long-context attention, but existing kernels typically process queries independently, repeatedly loading and dequantizing KV entries shared across queries. We observe substantial overlap in the… 18 arXiv — NLP / Computation & Language research 5d ago ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis arXiv:2610.11140v1 Announce Type: cross Abstract: Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present ActiveMedAgent, a framework that brings this… 15 arXiv — Machine Learning research 5d ago Ranking Prior Alignment for Credit Risk Modeling: When Do External Priors Matter? arXiv:2610.11146v1 Announce Type: new Abstract: Cold-start credit scoring -- deploying models with scarce labeled data, weak features, or minimal capacity -- is a recurring problem in financial machine learning. When a new lending product launches, labeled default data is… 21 arXiv — Machine Learning research 5d ago Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context Reinforcement Learning arXiv:2610.11152v1 Announce Type: new Abstract: LLM agents increasingly improve at inference time by accumulating experience in context rather than by updating parameters. This process is often described as in-context reinforcement learning (ICRL). Whether in-context learning… 23 arXiv — Machine Learning research 5d ago RideBench: A Large-Scale Exogenous-Aware Benchmark for Ride-Hailing Time Series Forecasting arXiv:2610.11164v1 Announce Type: new Abstract: We release Ride-Hailing, a large-scale ride-hailing time series dataset synthesized from DiDi's marketplace data across 200 spatial areas. Ride-Hailing spans four consecutive years at half-hourly granularity and covers three… 36 arXiv — Machine Learning research 5d ago CARE: A Lightweight Plug-in Gated Correction and Uncertainty-aware Module for Long-term Time Series Forecasting arXiv:2610.11165v1 Announce Type: new Abstract: Multivariate long-horizon forecasting is critical to electricity load scheduling and traffic flow management, and to financial risk control. Existing deterministic backbones output a single trajectory, masking heterogeneous… 32 arXiv — Machine Learning research 5d ago PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation arXiv:2610.11167v1 Announce Type: new Abstract: Vertical-domain few-shot classification remains challenging for small language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy Distillation (OPD) can improve teacher-guided… 11 arXiv — Machine Learning research 5d ago SACQ: Structured Decoding with Memory-Conditioned Refinement for Long-Horizon Forecasting arXiv:2610.11170v1 Announce Type: new Abstract: Long-term time series forecasting (LTSF) models predominantly employ patch-based encoders terminated by a flatten readout head that maps the entire encoded historical memory to all future steps through a single shared projection.… 21 arXiv — Machine Learning research 5d ago Predictive Multiplicity in Cell-Fate Assignment: Label-Free Rashomon Sets and the Limits of Per-Cell Certification arXiv:2610.11185v1 Announce Type: new Abstract: Single-cell trajectory inference maps transcriptomic measurements onto developmental continua, yet configurations that fit the data equally well can assign conflicting cell fates. FateMultiplicity is a label-free framework that… 17 arXiv — Machine Learning research 5d ago Do Flatter Minima Drive Better Generalization? An Algorithmic Separation in Grokking arXiv:2610.11206v1 Announce Type: new Abstract: Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is less established. Grokking provides an unique testbed to understand this… 8 arXiv — Machine Learning research 5d ago Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration arXiv:2610.11214v1 Announce Type: new Abstract: KV-cache quantization and linear attention are two representative approaches to tackling the storage and computational costs of Transformers. KV-cache quantization compresses individual KV entries into discrete codes but retains… 27 arXiv — Machine Learning research 5d ago The Lattice of Transition Laws arXiv:2610.11216v1 Announce Type: new Abstract: Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete tokens. Recent work seeks to combine the… 26 arXiv — Machine Learning research 5d ago Multimodal Graph Retrieval-Augmented Sequential Recommendation via Collaborative Filtering Paths arXiv:2610.11228v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong potential for sequential recommendation through their ability to reason over complex multimodal data. However, existing approaches either rely solely on the target… 19 arXiv — Machine Learning research 5d ago SteerCast: Retrieval-Based Latent Steering for Decoder-Only Time Series Forecasting arXiv:2610.11229v1 Announce Type: new Abstract: Time series forecasting aims to predict future values from historical observations and auxiliary features. We propose \textbf{SteerCast}, a retrieval-based latent steering method that improves decoder-only forecaster at inference… 19 arXiv — Machine Learning research 5d ago Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model arXiv:2610.11236v1 Announce Type: new Abstract: Low-cost sensors enable scalable indoor air quality monitoring but require calibration because of nonlinear distortions, noise, and temporal drift. The conventional strict pairwise calibration setting requires a co-located… 36 arXiv — Machine Learning research 5d ago Read What Matters: Query-Adaptive Quantization for KV Caches arXiv:2610.11245v1 Announce Type: new Abstract: KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch using separate budgets for retained bits and bits fetched per query. ReadKV… 23 arXiv — Machine Learning research 5d ago Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals arXiv:2610.11247v1 Announce Type: new Abstract: On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully understood. Across code generation and mathematical reasoning, OPD with… 21 arXiv — Machine Learning research 5d ago Neuro-Memory Fuzzy Inference System for Mimicking Human-like Car Following Behavior arXiv:2610.11252v1 Announce Type: new Abstract: This study presents the Neuro-Memory Fuzzy Inference System (NeMeFIS), a hierarchical machine learning architecture that asymmetrically models acceleration and deceleration in car following behavior by integrating five human memory… 38 arXiv — Machine Learning research 5d ago Residual spectral instabilities in representation learning arXiv:2610.11257v1 Announce Type: new Abstract: Learned representations can lose latent degrees of freedom successively, suggesting a cascade of transitions whose underlying stability principle remains unclear. Here we formulate dimension-wise posterior collapse in variational… 5 arXiv — Machine Learning research 5d ago How to post-train on a surrogate: Envelope sampling mitigates reward hacking arXiv:2610.11281v1 Announce Type: new Abstract: Large language models (LLMs) are commonly post-trained against LLM judges and other cheap surrogates because the true reward, such as human preference, is too expensive to query at scale. This practice often leads to reward… 27 arXiv — Machine Learning research 5d ago Memorization and Malign Generalization in Conditional Diffusion Models with Random Features arXiv:2610.11288v1 Announce Type: new Abstract: Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions. However, theoretical understanding of their memorization and generalization remains limited, while recent works have… 9 arXiv — Machine Learning research 5d ago From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon arXiv:2610.11309v1 Announce Type: new Abstract: Different optimizers can fit the same training data while selecting classifiers with substantially different geometries, but whether this difference provably affects population performance remains unclear. We show that row-wise… 14 arXiv — Machine Learning research 5d ago NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks arXiv:2610.11313v1 Announce Type: new Abstract: A fundamental question in neural network architecture optimization is whether the minimum hidden-neuron count required to approximate a target function within a prescribed tolerance can be computed efficiently. This paper resolves… 34 arXiv — Machine Learning research 5d ago Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers arXiv:2610.11315v1 Announce Type: new Abstract: In diffusion transformers, low-rank branches can mitigate 4-bit weight--activation (W4A4) post-training quantization (PTQ) loss by decomposing each weight into a low-bit residual and a high-precision low-rank component. Existing… 26 arXiv — Machine Learning research 5d ago Sample-Efficient Generative Conformal Prediction arXiv:2610.11349v1 Announce Type: new Abstract: Generative conformal prediction builds uncertainty sets from samples of a conditional generator, which are efficient only when the samples represent the response distribution well. This can require many samples, each of which can… 25 arXiv — Machine Learning research 5d ago Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data arXiv:2610.11362v1 Announce Type: new Abstract: Binary diffusion models typically require a large number of function evaluations (NFEs) to generate high-quality samples, making practical inference computationally expensive. Reducing NFEs while preserving sample quality without… 35 arXiv — Machine Learning research 5d ago SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces arXiv:2610.11366v1 Announce Type: new Abstract: Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive… 31 arXiv — Machine Learning research 5d ago From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning arXiv:2610.11373v1 Announce Type: new Abstract: Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities. Existing approaches typically address this challenge by… 30 arXiv — Machine Learning research 5d ago CoPoE: Multimodal Fusion via Decomposable Disease-Coordinate Product-of-Experts for Missing-Modality Alzheimer's Diagnosis arXiv:2610.11394v1 Announce Type: new Abstract: Multimodal Alzheimer's disease (AD) diagnosis benefits from integrating heterogeneous clinical, imaging, genomic, and biomarker evidence, but clinical cohorts frequently suffer from irregular modality missingness. Existing fusion… 34 arXiv — Machine Learning research 5d ago Learning from Hetero Density for Cryo-EM Protein Reconstruction arXiv:2610.11403v1 Announce Type: new Abstract: Reconstructing protein structures from cryo-electron microscopy (cryo-EM) maps is essential for understanding macromolecular assemblies. Although learning-based methods have improved protein reconstruction, information from hetero… 6 arXiv — Machine Learning research 5d ago MC-TRCM: Observation-Aware Recursive Fusion for Incomplete Mobile and Wearable Mental-Health Feature Views arXiv:2610.11408v1 Announce Type: new Abstract: Public mobile and wearable mental-health datasets often provide summarized feature tables rather than synchronized raw sensor streams. In these releases, each anchor corresponds to a survey or label time and may combine phone or… 34 arXiv — Machine Learning research 5d ago Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation arXiv:2610.11423v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by aligning its policy with a teacher model on trajectories generated by the student model itself. Through this process, the student policy moves toward the teacher on the prompts… 38 arXiv — Machine Learning research 5d ago MotiveMob: Motivation as Semantic Action for Closed-Loop Human Mobility Generation arXiv:2610.11442v1 Announce Type: new Abstract: Human mobility generation, an important task in urban research, synthesizes trajectory data for urban planning and transportation management. Human mobility can be characterized as a "why-where-when" decision process: people form… 22 arXiv — Machine Learning research 5d ago Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains arXiv:2610.11454v1 Announce Type: new Abstract: Unified atomistic modeling has the potential to accelerate discovery in chemistry, materials science, and biology by bridging data-rich chemical domains and data-scarce biological contexts. However, existing generative approaches… 5 arXiv — Machine Learning research 5d ago Generative Adversarial Loops arXiv:2610.11458v1 Announce Type: new Abstract: AI research progress can be viewed as the interaction between two processes: benchmark creation and method discovery. Historically, both were driven by human intelligence. However, recent advances in AI have accelerated automated… 27 arXiv — Machine Learning research 5d ago Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD arXiv:2610.11475v1 Announce Type: new Abstract: Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining. We show that it can mispredict finite-batch stochastic gradient descent (SGD) qualitatively, and we trace the… 32 arXiv — Machine Learning research 5d ago Compactness and Consistency: A Conjoint Framework for Deep Graph Clustering arXiv:2610.11506v1 Announce Type: new Abstract: Graph clustering is a fundamental task in data analysis, aiming at grouping nodes with similar characteristics in the graph into clusters. This problem has been widely explored using graph neural networks (GNNs) due to their… 10 arXiv — Machine Learning research 5d ago When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning arXiv:2610.11523v1 Announce Type: new Abstract: Federated reinforcement learning (FRL) enables distributed agents to collaboratively train decision-making policies, but its decentralized training process also exposes global policy learning to Byzantine manipulation. Existing… 23 arXiv — NLP / Computation & Language research 5d ago Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models arXiv:2610.10550v1 Announce Type: new Abstract: Personalizing text-to-image diffusion models from a few reference images requires preserving subject identity while following prompts that describe new contexts. Full-model fine-tuning is parameter-intensive, whereas low-rank… 22 arXiv — NLP / Computation & Language research 5d ago Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch arXiv:2610.10592v1 Announce Type: new Abstract: Historical Polish is well documented as a language but annotated in machine-readable form only to about a million words for the period this paper covers; the rest sits behind optical character recognition of variable quality. We… 6 Page 6 of 10 · 500 articles ← Newer Older →
