24d ago
Bi-level Heterogeneous Learning for Time Series Foundation Models: A Federated Learning Approach
Federated learning approach for training time series foundation models using bi-level heterogeneous learning to address gradient conflicts.
24d ago
Extraction of linearized models from pre-trained networks via knowledge distillation
Framework for extracting linearized neural network models via knowledge distillation for photonic hardware compatibility.
24d ago
Busemann energy-based attention for emotion analysis in Poincar\'e discs
EmBolic: hyperbolic deep learning architecture for emotion analysis from text using Busemann energy-based attention.
24d ago
The Rhetoric of Machine Learning
Philosophical examination of machine learning through rhetoric lens, arguing ML is inherently rhetorical rather than objective.
24d ago
Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models
Empirical study of Voronoi tessellations in LLM latent spaces, validating scaling laws of expressibility gaps.
24d ago
Instance-Adaptive Parametrization for Amortized Variational Inference
Instance-adaptive variational autoencoder addressing amortization gap in latent variable models through per-instance parametrization.
24d ago
MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
MoBiE: Binarization framework for efficient inference of Mixture-of-Experts LLMs with post-training quantization techniques.
24d ago
OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale
OmniTabBench: Large-scale benchmark comparing GBDTs, neural networks, and foundation models on tabular data with 100+ datasets.
24d ago
STQuant: Spatio-Temporal Adaptive Framework for Optimizer Quantization in Large Multimodal Model Training
STQuant framework for adaptive quantization of optimizer states during large multimodal model training to reduce memory costs.
24d ago
Contraction-Aligned Analysis of Soft Bellman Residual Minimization with Weighted Lp-Norm for Markov Decision Problem
Theoretical analysis of Bellman residual minimization for solving Markov decision processes under linear function approximation.
24d ago
MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems
Neural operator enhancement method for dynamical systems combining Fourier-based operators with diffusion-based high-frequency recovery.
24d ago
VertAX: a differentiable vertex model for learning epithelial tissue mechanics
JAX-based differentiable framework for vertex-modeling epithelial tissue mechanics with automatic differentiation and GPU acceleration.
24d ago
Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems
Decentralized multi-agent RL approach for vehicle-to-infrastructure systems using equivariant neural networks.
24d ago
FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
Efficient scaling technique for diffusion RL post-training using low-precision exploration and higher-precision training.
24d ago
A First Guess is Rarely the Final Answer: Learning to Search in the Travelling Salesperson Problem
Neural method for learning search policies in Traveling Salesperson Problem, training models to iteratively improve solutions.
24d ago
Frailty Estimation in Elderly Oncology Patients Using Multimodal Wearable Data and Multi-Instance Learning
Frailty assessment framework for elderly oncology patients using multimodal wearable data and multi-instance learning.
24d ago
Stress Estimation in Elderly Oncology Patients Using Visual Wearable Representations and Multi-Instance Learning
Wearable-based stress estimation in elderly cancer patients using multimodal smartwatch and ECG data with multi-instance learning.
24d ago
Predictive Representations for Skill Transfer in Reinforcement Learning
Transfer learning formalism using Outcome-Predictive State Representations for knowledge generalization across RL tasks.
24d ago
Learning to Query History: Nonstationary Classification via Learned Retrieval
Nonstationary classification approach using learned retrieval to condition classifiers on historical examples beyond training cutoff.
24d ago
MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale
Study of expert specialization and routing behavior in sparse Mixture-of-Experts architectures for large language models at small scale.
24d ago
AdaBoost Does Not Always Cycle: A Computer-Assisted Counterexample
Computer-assisted proof providing counterexample to open question about AdaBoost convergence to finite cycles.
24d ago
Production-Ready Automated ECU Calibration using Residual Reinforcement Learning
Production application of residual reinforcement learning to automate electronic control unit calibration in vehicles.
24d ago
Epistemic Robust Offline Reinforcement Learning
Offline reinforcement learning approach addressing epistemic uncertainty through ensemble-based conservative value estimation.
24d ago
Mining Electronic Health Records to Investigate Effectiveness of Ensemble Deep Clustering
Evaluation of ensemble deep clustering methods versus traditional approaches for disease subtype detection in electronic health records.
24d ago
Are Stochastic Multi-objective Bandits Harder than Single-objective Bandits?
Theoretical analysis of multi-objective bandits comparing computational complexity to single-objective bandit problems.
24d ago
Selective Neuron Amplification for Training-Free Task Enhancement
Method to enhance LLM task performance by amplifying task-relevant neurons at inference time without parameter modification.
24d ago
Information as Structural Alignment: A Dynamical Theory of Continual Learning
Theoretical framework addressing catastrophic forgetting in continual learning through informational structural alignment rather than external mechanisms.
24d ago
Lumbermark: Resistant Clustering by Chopping Up Mutual Reachability Minimum Spanning Trees
Novel divisive clustering algorithm using mutual reachability minimum spanning trees to detect clusters of varying sizes and densities.
24d ago
Multi-Turn Reasoning LLMs for Task Offloading in Mobile Edge Computing
Research on using multi-turn reasoning LLMs with deep reinforcement learning for task offloading decisions in mobile edge computing systems.
24d ago
SBBTS: A Unified Schr\"odinger-Bass Framework for Synthetic Financial Time Series
Framework for generating synthetic financial time series that model both distributions and temporal dynamics using Schrödinger-Bass Bridge methods.
24d ago
Smart Commander: A Hierarchical Reinforcement Learning Framework for Fleet-Level PHM Decision Optimization
Hierarchical reinforcement learning framework for military aviation maintenance and logistics decisions, addressing fleet-scale decision-making under uncertainty.
24d ago
Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
Research on calibrating uncertainty quantification in LLMs for question-answering through token-level temperature scaling, addressing gaps in existing confidence measures.
24d ago
Mixture Proportion Estimation and Weakly-supervised Kernel Test for Conditional Independence
Mixture proportion estimation from unlabeled data using conditional independence assumptions. Application to PU learning, label noise, and domain adaptation.
24d ago
Diffusion Processes on Implicit Manifolds
SDE-based method for constructing diffusion processes on implicit data manifolds using only point clouds. Data-driven approach without geometric primitives.
24d ago
How Does Machine Learning Manage Complexity?
Computational complexity analysis of ML model expressiveness for complex systems. Studies how ML manages complexity through probability on sampleable distributions.
24d ago
On the Price of Privacy for Language Identification and Generation
Theoretical study of differential privacy cost for language identification and generation. Establishes algorithms and lower bounds quantifying privacy-utility tradeoff.
24d ago
Weaves, Wires, and Morphisms: Formalizing and Implementing the Algebra of Deep Learning
Categorical framework formalizing deep learning model architectures using array broadcasting and morphisms. Mathematical notation for neural network composition.
24d ago
A comparative analysis of machine learning models in SHAP analysis
Comparative analysis of SHAP explainability method applied to different ML models. Reviews interpretability for black-box model predictions.
24d ago
Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions
Training method for Android UI agents improving RL efficiency using single state multiple actions paradigm to reduce sample inefficiency and emulator latency.
24d ago
Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability
Graph neural networks with neural ODEs for thermal-hydraulic forecasting in nuclear reactors under partial observability. Physics-informed surrogate modeling.
24d ago
SL-FAC: A Communication-Efficient Split Learning Framework with Frequency-Aware Compression
Split learning framework with frequency-aware compression reducing communication overhead in distributed neural network training on resource-constrained edge devices.
24d ago
How to sketch a learning algorithm
Data deletion scheme predicting model behavior after training data exclusion. Fast approximation for understanding data influence on learned models.
24d ago
MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis
Multi-agent system using RL for dynamic specialist routing in medical diagnosis. LMM agents route diagnostic queries to appropriate specialists for precision diagnosis.
24d ago
The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
Theoretical analysis explaining why entropy dynamics in LLM internal representations correlate with reasoning correctness. Proposes stepwise informativeness assumption.
24d ago
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
DOVE benchmark evaluates LLM cultural value alignment through open-ended generation. Addresses limitations of discriminative multiple-choice formats and subcultural heterogeneity.
24d ago
Toward Reducing Unproductive Container Moves: Predicting Service Requirements and Dwell Times
ML models predict container service requirements and dwell times at port terminals to reduce unproductive moves. Real-world logistics operations case study.
24d ago
Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
Multi-fidelity optimization framework combining VCG incentive mechanisms with efficient sampling to optimize LLM advertising while managing advertiser strategic behavior.
24d ago
Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
Framework to distill hallucination detection signals into transformer representations during training, enabling inference-time hallucination detection without external verification systems.
24d ago
Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements
Distributed mean estimation with adversarial measurements and asynchronous worker activation. Theoretical convergence rate analysis for parameter-server setup.
24d ago
Adversarial Robustness of Time-Series Classification for Crystal Collimator Alignment
CNN adversarial robustness for particle physics beam-loss monitoring at LHC. Analyzes classifier robustness under adversarial inputs during crystal alignment.