cs.LG — recent papers

215 papers recorded in this category. Newest first.

• Embedding Models Measure in Peculiar Ways
  Embedding spaces define notions of semantic similarity and distance. We study whether those embeddings reflect physical measurements of mass, distance, time and volume, which admit…
  2026-09-17
• How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?
  Pretraining a neural PDE surrogate can reduce the amount of new CFD data needed when geometry or modeled physics changes. However, it remains unclear how different components of di…
  2026-09-17
• Score Centering Stabilizes Off-policy Reinforcement Learning
  Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inferen…
  2026-09-17
• PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
  Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reco…
  2026-09-17
• Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols
  Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Altho…
  2026-09-17
• Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control
  World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world states and robot actions, enabling the policy to learn physical dynami…
  2026-09-17
• OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
  As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important across physical AI domains such as autonomous driving. End-to-end dr…
  2026-09-17
• dQwen3.5: Hybrid-Attention Diffusion Language Models
  Adapting a pretrained autoregressive (AR) model is a cost-efficient route to a diffusion language model (DLM). While nearly all such adaptations start from a full-attention transfo…
  2026-09-17
• MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
  Reinforcement learning constitutes a promising approach owing to its potential for superhuman performance and self-learned policies. However, its application to real-world autonomo…
  2026-09-17
• Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
  Video diffusion models repeatedly process long spatiotemporal token sequences during denoising, making attention a major computational bottleneck. Linear attention offers an appeal…
  2026-09-17
• Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates
  We study efficient algorithms for realizing the first-order oracle complexity of optimization of $G$-Lipschitz convex functions with respect to the $\ell_{q}$-norm over an $\ell_{p…
  2026-09-17
• TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
  Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transitions and traditionally is gui…
  2026-09-17
• The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings
  We study first-order black-box convex optimization over an $\ell_p$-ball for objectives Lipschitz in the $\ell_q$-norm, solving in the affirmative the nonsmooth version of the COLT…
  2026-09-17
• RISC-V and machine learning: a survey
  The intersection of open-source processor architectures and machine learning is driving the demand for customizable, efficient, and accessible hardware. This survey examines the st…
  2026-09-17
• Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging
  Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on hist…
  2026-09-16
• How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents
  Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pr…
  2026-09-16
• Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
  As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes h…
  2026-09-16
• Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory
  Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally int…
  2026-09-16
• A General Kernel Framework for Non-CND Distance Measures Using |D|-Dimensional Sparse Landmark Embeddings
  Kernel methods, and Gaussian Processes (GPs) in particular, require a Hilbertian distance measure---one whose square is conditionally negative definite (CND)---to guarantee positiv…
  2026-09-16
• Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
  In particle collider experiments, event reconstruction is the task of inferring the kinematics of short-lived particles produced in the hard scatter from the stable final states re…
  2026-09-16
• Fast Learning Rates for Physics-Informed Kernel Methods
  In physics-informed machine learning, a target function $u^*$ is learned from noisy value observations $y_i=u^*(x_i)+ \varepsilon_i$, together with differential information, given …
  2026-09-16
• Learning Lyapunov Operators for Nonlinear Systems
  Constructing Lyapunov functions for nonlinear dynamical systems is a central problem in stability analysis, yet remains challenging. Lyapunov functions are commonly characterized a…
  2026-09-16
• Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data
  Large Language Models (LLMs) are now routinely trained using synthetic data, since high-quality human data has been exhausted by the ever increasing needs of larger and larger mode…
  2026-09-16
• Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
  Reliable prediction of crystallographic texture in laser powder bed fusion is critical for linking process conditions with anisotropic response and for qualification. However, blac…
  2026-09-16
• Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data
  The scaling laws hold that a language model grows more capable with more parameters and more training data, and Mixture-of-Experts (MoE) architectures have ridden these laws to rem…
  2026-09-16
• Interpretable Multi-Instance Learning Enables Early Prediction of Key Molecular Alterations from Routine Flow Cytometry in Acute Myeloid Leukemia
  Background: Molecular testing for NPM1 and FLT3-ITD mutations guides critical early treatment decisions in acute myeloid leukemia (AML), but results can take weeks, long after thes…
  2026-09-16
• FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection
  Unauthorized hardware replacement can preserve a wireless device's logical identity while altering its physical implementation, posing a challenge to hardware integrity verificatio…
  2026-09-15
• Bridging the Gap Between Homogeneous and Heterogeneous Asynchronous Optimization Is Surprisingly Difficult
  Modern large-scale machine learning tasks often require multiple workers, devices, CPUs, or GPUs to compute stochastic gradients in parallel and asynchronously to train model weigh…
  2026-09-15
• Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
  The absolute capacity of dense associative memory has mainly been analyzed for unbiased patterns. Here we examine the effect of bias in centered binary patterns under the Krotov-Ho…
  2026-09-15
• Tables Decoded: DELTA for Structure, TARQA for Understanding
  Table understanding is a core task in document intelligence, encompassing two key subtasks: table reconstruction and table visual question answering (TabVQA). While recent approach…
  2026-09-15
• Reduced-Space Multi-Fidelity Bayesian Optimization of Process Simulation Models
  Optimizing industrial process flowsheets is often computationally prohibitive due to the high cost of rigorous simulations and the curse of dimensionality inherent in complex desig…
  2026-09-15
• Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
  Test-time prompt tuning (TPT) enables adaptation on a single test instance, achieving improved accuracy but often sacrificing calibration performance. Most existing calibration met…
  2026-09-15
• OPEN-1B: A Fully Auditable Training Run
  Open-source language models have a reproducibility problem. Despite releasing weights, training data, and recipes, none of them are provably reproducible due to the non-associativi…
  2026-09-15
• Large Language Models Develop Belief State Geometry In-Context
  Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly underst…
  2026-09-15
• Hybrid Variational Quantum Circuits for Multivariate Regression and High-Dimensional Data Reconstruction
  Variational quantum circuits (VQCs) are parameterized quantum circuits optimized classically. We propose a hybrid variational quantum circuit (HVQC) extending VQCs with a classical…
  2026-09-15
• Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
  Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. D…
  2026-09-15
• Quantum-Inspired Trainable and Parameter-Efficient Tensor Networks for Image Inpainting
  This work introduces quantum-inspired tensor-network circuits as trainable transforms for image inpainting. Among the proposed architectures, the diagonal quantum Fourier transform…
  2026-09-15
• Goal-oriented probabilistic forecasting for dynamic PRB allocation in 5G networks
  Efficient physical resource block (PRB) allocation in 5G networks requires accurate demand forecasting. Conventional methods minimize symmetric error metrics (MAE, RMSE), ignoring …
  2026-09-15
• Conformal Policy Learning with Distribution-Free Safety Guarantees
  Policy learning aims to determine who should be treated based on individual characteristics. In high-stakes settings such as medicine and public policy where safety is a central co…
  2026-09-15
• Same Flow, Different Paths: Variance Reduction in Flow Matching
  In flow matching (FM), a velocity model $v_θ$ is trained using a predefined path $g_t$ that connects data and noise samples (e.g., $g_t(x_0, x_1) = (1 - t) x_0 + t x_1$). In this w…
  2026-09-15
• Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation
  Statistical heterogeneity limits federated learning when a single global classifier cannot represent client-specific label distributions. In this work, we propose Personalized Fede…
  2026-09-15
• Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record
  An agent that learns from rewards has to trust whatever reports those rewards. When the reports suddenly change, either the world changed or the reporter broke. From the reports al…
  2026-09-15
• Memorisation bias in medical AI
  Medical AI models hold immense potential to improve patient outcomes, but they are also known to unintentionally memorise individual records from their training datasets. While suc…
  2026-09-15
• Bellman Policy Optimization
  Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs). We introduce Bellman Policy Optimization (BPO), a critic-…
  2026-09-14
• A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models
  When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the latter: the correct motion rem…
  2026-09-14
• Disentangling Representation Evolution in Transformers through Directional Decomposition
  Transformer representations evolve through learned additive transformations that either preserve their current direction or redirect it. We study this evolution as a functional geo…
  2026-09-14
• Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
  As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training …
  2026-09-14
• Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication
  Record-level differential privacy exposes a structural misalignment in personalized federated learning when client-specific variation is low-dimensional while training repeatedly r…
  2026-09-14
• Safe Meta-Reinforcement Learning via Information Space Reachability
  Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL in real-world tasks is hinder…
  2026-09-14
• Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
  Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps typically requires distilling …
  2026-09-14
• Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning
  The last decade has seen the development of powerful methods for learning complex structure from high-dimensional data. These advances have brought to the foreground fundamental co…
  2026-09-14
• Quenched Ensemble Sampling
  Some of the sharpest challenges in sampling from the energy functions of physical systems arise at phase transitions, where the density of states changes abruptly and many sampling…
  2026-09-14
• Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold start
  We show that logconcave probability measures along the Gaussian cooling path have thin-shell stability, generalizing the thin-shell theorem. This result leads to improved complexit…
  2026-09-14
• Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations
  This paper establishes a perfect-reconstruction (PR) interpretation of AddUNet and its full-rate realization, and introduces a Residual Full-Rate PR architecture for task-directed …
  2026-09-14
• Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence
  This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-triggered inference in a cooperative…
  2026-09-14
• A Ranking Approach for Measuring Calibration
  When providing forecasted probabilities with a predictive model, the ideal model offers perfect calibration: the true probability of the outcome (i.e., the probability that $Y=1$) …
  2026-09-11
• CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
  Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement …
  2026-09-11
• Benign Loss Landscapes Can Coexist with Worst-Case Hardness
  Deep neural networks are expressive enough to contain worst-case targets that can be evaluated in polynomial time but cannot be learned in polynomial time by gradient descent. For …
  2026-09-11
• A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning
  Regularization-based methods have become a standard approach for training Deep Reinforcement Learning policies against adversarial input perturbations. In this paper, we unify thes…
  2026-09-11
• MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling
  Efficient microservice scheduling is crucial for maintaining load balance across nodes in data centers and ensuring high quality of service. However, achieving this in practice rem…
  2026-09-11
• Robust Policy Optimization via Adversarial Importance Sampling
  Significant progress has been made in safeguarding deep reinforcement learning (DRL) policies against input perturbations. Developing robust DRL involves three main stages: algorit…
  2026-09-11
• Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent
  We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motivated by minimum-loss-based S…
  2026-09-11
• Transfer Learning for Evolving Domains
  Transfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets). Typically, tra…
  2026-09-11
• Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions
  Optimal transport (OT) compares distributions and aligns datasets in machine learning, yet unregularized discrete OT requires a linear program with quadratically many transport var…
  2026-09-11
• A Large-Scale AIS Dataset from Finnish Water
  This research paper contributes to the maritime research community by introducing a comprehensive AIS dataset from Finnish waters, specifically the Baltic Sea region. AIS data, ini…
  2026-09-11
• Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
  A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The problem is not that the counter is…
  2026-09-11
• Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
  As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activat…
  2026-09-10
• From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good
  Artificial Intelligence does more than create a governance problem. It can also reveal where institutions have already failed to provide responsiveness, belonging, care, and accoun…
  2026-09-10
• TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
  Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussi…
  2026-09-10
• CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
  Causal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its evaluation relies heavily on str…
  2026-09-10
• 3D Point Splatting for mmWave Radar Novel View Synthesis
  Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior metho…
  2026-09-10
• CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search
  Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework com…
  2026-09-10
• Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting
  Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-serie…
  2026-09-10
• AdamX: Cosine similarity meets gradient descent
  We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-a…
  2026-09-10
• Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead
  We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $\ell$ actions before decidi…
  2026-09-10
• Dynamic language model representations for multi-objective reaction optimisation
  Optimising chemical reactions across multiple objectives, such as yield, selectivity, and safety, is central to chemical synthesis, and model-driven approaches depend critically on…
  2026-09-10
• Predicting Privacy Leakage from Weight Spectral Density
  Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art attacks require training compu…
  2026-09-10
• Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology
  Clinical electroencephalography (EEG) data are valuable for healthcare research and for developing artificial intelligence (AI)-based clinical decision-support systems, but EEG rec…
  2026-09-10
• Likelihood-free inference with nuisance parameters through normalizing flows
  We present a simple decomposition of a neural-network-based normalizing flow that naturally uncovers a pivotal statistic (or something close) in the presence of nuisance parameters…
  2026-09-09
• A positive resolution of the gap-entropy conjecture
  We prove the gap-entropy conjecture for fixed-confidence best-arm identification with independent unit-variance Gaussian arms, means in $[0,1]$, and a unique optimal arm. For each …
  2026-09-09