25d ago
AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
Analytic federated learning (AFL) paradigm enabling closed-form solutions for federated learning with pre-trained models in single-round training.
25d ago
SleepNet and DreamNet: Enriching and Reconstructing Representations for Consolidated Visual Classification
SleepNet and DreamNet: deep learning models for visual classification via feature enrichment and reconstruction with pre-trained encoders.
25d ago
Matrix Profile for Anomaly Detection on Multidimensional Time Series
Matrix Profile extension for anomaly detection in multidimensional time series from real-world applications like sensor monitoring.
25d ago
DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning
DROP: distributional reinforcement learning framework with asymmetric learning rates modeling optimistic/pessimistic dopamine neuron behavior.
25d ago
Pseudo-Probability Unlearning: Efficient and Privacy-Preserving Machine Unlearning
Pseudo-probability unlearning method for efficient privacy-preserving machine unlearning with reduced computational overhead and residual information.
25d ago
SSPINNpose: A Self-Supervised PINN for Inertial Pose and Dynamics Estimation
Self-supervised physics-informed neural network for real-time human pose and dynamics estimation from sparse IMU sensor configurations.
25d ago
Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
Inference-time scaling method for discrete diffusion language models via trajectory refinement without retraining for reward optimization.
25d ago
Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
Negative Binomial VAE extension with discrete count-based latents for improved biological plausibility over continuous VAE representations.
25d ago
Quantitative Estimation of Target Task Performance from Unsupervised Pretext Task in Semi/Self-Supervised Learning
Method for quantitatively estimating target task performance from unsupervised pretext tasks in semi/self-supervised learning before full training.
25d ago
LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks
LNN-PINN: physics-informed neural network framework with liquid residual gating for improved predictive accuracy on complex PDE problems.
25d ago
In-Context Decision Making for Optimizing Complex AutoML Pipelines
In-context learning approach for AutoML pipeline optimization beyond hyperparameter tuning, incorporating fine-tuning and ensembling techniques.
25d ago
Physics-Informed Spectral Modeling for Hyperspectral Imaging
PhISM: physics-informed deep learning architecture for unsupervised hyperspectral imaging using continuous basis functions for interpretable latent representations.
25d ago
LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
LoFT method for long-tailed semi-supervised learning using foundation models with parameter-efficient fine-tuning to improve pseudo-label quality.
25d ago
MDP modeling for multi-stage stochastic programs
MDP modeling framework extending policy graphs for multi-stage stochastic programs with decision-dependent uncertainty and statistical learning.
25d ago
Entropy After </Think> for reasoning model early exiting
Technique for detecting when reasoning LLMs overthink by analyzing entropy after chain-of-thought to enable early exiting.
25d ago
Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing
Bayesian machine learning potentials for molecular simulations with uncertainty quantification using equivariant message passing.
25d ago
ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks
Method for efficiently computing Lipschitz constant estimates for neural networks using local information to improve robustness certification.
25d ago
Approximate Replicability in Learning
Approximate replicability framework for machine learning algorithms that remain stable under input resampling.
25d ago
Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints
Spectral clustering alternatives to Laplacian with group fairness constraints for equitable cluster representation.
25d ago
GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
GIFT unifies GRPO, DPO, and UNA in reinforcement learning framework for LLM alignment combining group-relative sampling with implicit preference learning.
25d ago
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
LoRA-DA provides data-aware initialization for low-rank adaptation via theoretical framework and asymptotic analysis for parameter-efficient fine-tuning.
25d ago
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
Nirvana specialized generalist model with task-aware memory mechanism for domain adaptation while preserving broad LLM capabilities.
25d ago
Tensor-Efficient High-Dimensional Q-learning
Tensor-based Q-learning approach to handle high-dimensional reinforcement learning by exploiting problem structure without neural networks.
25d ago
Adaptive Symmetrization of the KL Divergence
Adaptive symmetrization of KL divergence for learning probability distributions with normalizing flows and energy-based models.
25d ago
SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization
SpecQuant framework for ultra-low-bit LLM quantization using spectral decomposition and adaptive truncation for efficient device deployment.
25d ago
TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
TREASURE foundation model for payment transaction understanding and analysis with applications to anomaly detection.
25d ago
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
CHiQPM provides global and local interpretability for image classification in safety-critical domains with hierarchical explanations.
25d ago
Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
Adaptive Replay Buffer (ARB) dynamically prioritizes data sampling in offline-to-online reinforcement learning to balance stability and asymptotic performance.
25d ago
Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
First empirical study of machine unlearning in hybrid quantum-classical neural networks and variational quantum circuits.
25d ago
Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning
Reinforcement learning framework to learn weather/climate model parametrization schemes as state-dependent functions online instead of using fixed coefficients.
25d ago
Low-Rank Key Value Attention
Low-Rank Key-Value (LRKV) attention reduces transformer KV cache memory by exploiting redundancy across attention heads with low-rank residuals.
25d ago
BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack
BadImplant introduces multi-targeted backdoor attacks against graph neural networks with injection-based mechanisms.
25d ago
Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems
Explainable AI methods to improve ML reliability and prevent unexpected behavior in industrial cyber-physical systems.
25d ago
SPICE: Submodular Penalized Information-Conflict Selection for Efficient Large Language Model Training
SPICE uses submodular optimization and Fisher information to select training data for efficient LLM instruction tuning while addressing gradient conflicts.
25d ago
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
Infusion framework uses influence functions to craft training data perturbations that induce targeted model behavior changes, evaluated on vision and language tasks.
25d ago
Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials
Open-source foundation model for 3D molecular and materials modeling with both generative and predictive capabilities.
25d ago
Interventional Time Series Priors for Causal Foundation Models
Interventional time series data generator for training causal foundation models on time series, extending prior-data fitted networks to temporal domains.
25d ago
EvoFlows: Evolutionary Edit-Based Flow-Matching for Protein Engineering
EvoFlows: variable-length protein sequence model using flow matching for protein engineering with native support for insertions, deletions, and mutations.
25d ago
Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications
CONSERVAttack method for identifying vulnerabilities and systematic uncertainties in ML models applied to high-energy physics data analysis.
25d ago
CRPS-Optimal Binning for Univariate Conformal Regression
Non-parametric conformal regression method using optimal binning with CRPS loss for conditional distribution estimation.
25d ago
MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations
MR-CDM: multi-resolution conditional diffusion framework for variable-length time series forecasting with hierarchical decomposition and adaptive embeddings.
25d ago
Toward Personalized Darts Training: A Data-Driven Framework Based on Skeleton-Based Biomechanical Analysis and Motion Modeling
Data-driven sports training framework using skeleton-based biomechanical analysis and motion modeling for personalized dart coaching.
25d ago
Matrix Profile for Time-Series Anomaly Detection: A Reproducible Open-Source Benchmark on TSB-AD
Open-source benchmark and reproducible implementation of Matrix Profile methods for univariate and multivariate time-series anomaly detection.
25d ago
Self-Distilled RLVR
On-policy self-distillation approach for LLM training combining dense teacher signals with sparse verifiable rewards from environment feedback.
25d ago
NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure
NativeTernary: binary encoding format for ternary neural network weights achieving 2 bits per weight, 1.31x compression over GGUF for BitNet models.
25d ago
k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
Proposes k-maximum inner product attention mechanism for graph transformers to reduce computational complexity while maintaining expressive power.
25d ago
A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs
Deep learning approach for clinical risk prediction from incomplete multimodal EHR data using point cloud paradigm to handle irregular sampling and missing modalities.
25d ago
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
Empirical robustness analysis of TabPFN's attention mechanisms for tabular in-context learning, examining noise immunity across heterogeneous datasets.
25d ago
Active Statistical Inference
Active inference methodology for ML-assisted data collection, using models to identify which points merit labeling under budget constraints for efficient learning.
25d ago
Resistance Distance and Linearized Optimal Transport on Graphs
Studies linearization of discrete transportation distance on graphs, connecting optimal transport to graph structure and providing nonasymptotic analysis.