2/17/2026
Multi-dimensional Persistent Sheaf Laplacians for Image Analysis
Multi-dimensional persistent sheaf Laplacian framework for image analysis addressing dimensionality reduction sensitivity.
2/17/2026
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
Theoretical analysis of temperature scaling properties for classifier calibration and LLM stochasticity control.
2/17/2026
Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
Drift-diffusion matching framework embedding asymmetric RNN dynamics in latent manifolds for biological neural computation.
2/17/2026
Adjoint-based Shape Optimization, Machine Learning based Surrogate Models, Conditional Variational Autoencoder (CVAE), Voith Schneider propulsion (VSP), Self-propelled Ship, Propulsion Model, Hull Optimization
Adjoint-based ship hull optimization using ML surrogate models and CVAEs for complex propulsion systems.
2/17/2026
Activation-Space Uncertainty Quantification for Pretrained Networks
GAPA: post-hoc Gaussian Process method for uncertainty quantification in pretrained networks via activation-space modeling.
2/17/2026
Fault Detection in Electrical Distribution System using Autoencoders
Autoencoder-based fault detection in electrical power distribution systems using probabilistic decision methods.
2/17/2026
Gradient Networks for Universal Magnetic Modeling of Synchronous Machines
Physics-informed neural networks with gradient networks for dynamic modeling of synchronous electrical machines.
2/17/2026
ThermEval: A Structured Benchmark for Evaluation of Vision-Language Models on Thermal Imagery
ThermEval benchmark for evaluating vision-language model generalization on thermal imagery across surveillance and medical applications.
2/17/2026
Distributed Quantum Gaussian Processes for Multi-Agent Systems
Quantum-enhanced Gaussian processes with distributed training for multi-agent systems using quantum kernel embeddings.
2/17/2026
BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames
BPP method for robot imitation learning attending to relevant historical frames via key frame selection in long-context tasks.
2/17/2026
Cold-Start Personalization via Training-Free Priors from Structured World Models
Cold-start personalization using structured world models and RL for efficient user preference inference with limited interaction budget.
2/17/2026
Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI
Neural network transfer learning from low-resolution LAMOST to medium-resolution DESI stellar spectra for parameter estimation.
2/17/2026
Learning with Subset Stacking
Regression algorithm using subset stacking for heterogeneous data with local predictors trained on random input-space subsets.
2/17/2026
When is Offline Policy Selection Sample Efficient for Reinforcement Learning?
Analysis of sample efficiency in offline policy selection for reinforcement learning via off-policy evaluation and Bellman error.
2/17/2026
Permutation-based Inference for Variational Learning of Directed Acyclic Graphs
PIVID method for inferring Bayesian network structure from observational data using permutation-based variational inference.
2/17/2026
Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
Memory-efficient zeroth-order optimizer (MeZO) for LLM fine-tuning using only forward passes, with sparse parameter improvements.
2/17/2026
Optimal Design for Human Preference Elicitation
Optimal design methods for efficient human preference elicitation to reduce annotation costs in preference learning models.
2/17/2026
Exact Solution to Data-Driven Inverse Optimization of MILPs in Finite Time via Gradient-Based Methods
Gradient-based methods for solving data-driven inverse optimization problems with mixed integer linear programs.
2/17/2026
Synergizing Foundation Models and Federated Learning: A Survey
Survey of federated learning combined with foundation models for privacy-preserving distributed training.
2/17/2026
GraphFM: A generalist graph transformer that learns transferable representations across diverse domains
Multi-graph pretraining approach enabling graph transformers to learn transferable representations across diverse domains.
2/17/2026
Benchmarking AI-based data assimilation to advance data-driven global weather forecasting
Benchmark for evaluating AI-based data assimilation methods using real-world observations for weather forecasting.
2/17/2026
MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameters
Lightweight multivariate time series forecasting model with 0.1K parameters for resource-constrained settings.
2/17/2026
Online Posterior Sampling with a Diffusion Prior
Posterior sampling algorithms for contextual bandits using diffusion model priors.
2/17/2026
Model-based Large Language Model Customization as Service
Privacy-preserving LLM customization service using differentially private synthesis for domain-specific fine-tuning.
2/17/2026
Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality
Theoretical analysis showing denoising diffusion models adapt optimally to unknown low-dimensional data.
2/17/2026
VCDF: A Validated Consensus-Driven Framework for Time Series Causal Discovery
Consensus-driven framework improving robustness of time series causal discovery methods.
2/17/2026
Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection
Dynamic batch-aware expert selection for efficient Mixture-of-Expert model inference during serving.
2/17/2026
Cautious Optimizers: Improving Training with One Line of Code
One-line modification to momentum-based optimizers improving stability and speed for transformer pretraining.
2/17/2026
Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces
Bayesian flow networks for out-of-distribution molecular generation in drug design.
2/17/2026
Regularized Top-$k$: A Bayesian Framework for Gradient Sparsification
Bayesian framework for gradient sparsification in distributed training using error accumulation.
2/17/2026
Adaptive Width Neural Networks
Technique to learn unbounded neural network layer width during training without manual hyperparameter selection.
2/17/2026
SWIFT: Mapping Sub-series with Wavelet Decomposition Improves Time Series Forecasting
Lightweight time series forecasting model using wavelet decomposition for resource-constrained environments.
2/17/2026
Faster Adaptive Optimization via Expected Gradient Outer Product Reparameterization
Studies rotational equivariance in adaptive optimizers and proposes reparameterization for improved convergence.
2/17/2026
Fast Graph Generation via Autoregressive Noisy Filtration Modeling
Autoregressive framework for fast graph generation using topological data analysis concepts.
2/17/2026
LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference
Block clustered quantization technique for 4-bit weight and activation LLM inference without quantization-aware training.
2/17/2026
Fenchel-Young Variational Learning
Introduces Fenchel-Young losses as generalizations of KL divergence for variational learning methods.
2/17/2026
Less is More: Improving LLM Alignment via Preference Data Selection
Novel data selection approach for Direct Preference Optimization to improve LLM alignment by addressing parameter shrinkage from noisy preference data.
2/17/2026
Contextual Quantum Neural Networks for Stock Price Prediction
Contextual quantum neural networks for stock price prediction using quantum superposition and new training techniques.
2/17/2026
Robust Multi-Objective Controlled Decoding of Large Language Models
RMOD inference algorithm aligns LLMs to multiple objectives via robust maximin game formulation achieving Nash equilibrium.
2/17/2026
Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
Learning rate annealing schedules improve robustness to hyperparameter tuning in stochastic gradient optimization.
2/17/2026
Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction
Knowledge distillation of GNN teachers into MLP students for graph link prediction using heuristic methods.
2/17/2026
Riemannian Denoising Diffusion Probabilistic Models
Riemannian Denoising Diffusion Probabilistic Models for learning distributions on submanifolds without requiring explicit geodesic information.
2/17/2026
Sparse Latent Factor Forecaster (SLFF) with Iterative Inference for Transparent Multi-Horizon Commodity Futures Prediction
Sparse Latent Factor Forecaster with iterative inference for commodity futures prediction addressing amortized inference deployment gap.
2/17/2026
A Generalized Hierarchical Federated Learning Framework with Theoretical Guarantees
Multi-layer hierarchical federated learning framework generalizing to arbitrary network architectures with nested aggregation.
2/17/2026
RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours
Deep learning model for 8-hour probabilistic precipitation forecasting integrating radar, satellite, and NWP data.
2/17/2026
Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning
Heterogeneity-aware client sampling for federated learning with diverse communication and computational capabilities.
2/17/2026
Residual Feature Integration is Sufficient to Prevent Negative Transfer
Residual feature integration prevents negative transfer in transfer learning through simple architectural modifications.
2/17/2026
MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
MoESD applies speculative decoding to accelerate Mixture of Experts LLM inference without accuracy loss.
2/17/2026
On the Relation between Rectified Flows and Optimal Transport
Theoretical analysis of connections between rectified flows, flow matching, and optimal transport with invariance properties.
2/17/2026
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
Difficulty-targeted online data selection and rollout replay techniques improve data efficiency in LLM reinforcement learning fine-tuning.