2/18/2026
Out of Distribution Detection for Efficient Continual Learning in Quality Prediction for Arc Welding
Out-of-distribution detection for continual learning in arc welding quality prediction using VQ-VAE Transformer architecture.
2/18/2026
Morephy-Net: An Evolutionary Multi-objective Optimization for Replica-Exchange-based Physics-informed Neural Operator Learning Networks
Morephy-Net uses multi-objective evolutionary optimization for physics-informed neural operators on parametric PDEs in noisy regimes.
2/18/2026
Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective
Analyzes signal propagation and weight randomness in physics-informed neural networks using spectral/statistical properties.
2/18/2026
GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
GenFacts generates valid counterfactual explanations for multivariate time series using class-discriminative VAE.
2/18/2026
Learning Admissible Heuristics for A*: Theory and Practice
Learns admissible heuristics for A* search algorithms using constrained optimization to guarantee solution optimality.
2/18/2026
Flock: A Knowledge Graph Foundation Model via Learning on Random Walks
Flock: knowledge graph foundation model using random walk learning for zero-shot link prediction on novel entities and relations.
2/18/2026
TabImpute: Universal Zero-Shot Imputation for Tabular Data
TabImpute: zero-shot universal imputation for tabular data with missing values using language model approach.
2/18/2026
General Exploratory Bonus for Optimistic Exploration in RLHF
General exploratory bonus method for optimistic exploration in RLHF that avoids bias toward reference model high-probability regions.
2/18/2026
Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability
Transformer models learn permuted congruential generator sequences via in-context prediction with curriculum learning and interpretability analysis.
2/18/2026
Terminal Velocity Matching
Terminal Velocity Matching generalizes flow matching for one/few-step generative modeling with Wasserstein distance bounds.
2/18/2026
Syndrome-Flow Consistency Model Achieves One-step Denoising Error Correction Codes
Applies consistency models to error correction codes for one-step neural decoding in low-latency communication settings.
2/18/2026
BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
BEP algorithm trains binary neural networks with constrained weights/activations via error propagation for resource-constrained deployment.
2/18/2026
Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study
Improves VAE and autoencoder training using random Fourier transformation with frequency principle analysis for aviation safety anomaly detection.
2/18/2026
ARGUS: Adaptive Rotation-Invariant Geometric Unsupervised System
ARGUS detects distributional drift in high-dimensional data streams using local statistics over fixed spatial partitions of data manifold.
2/18/2026
Stratified Hazard Sampling: Minimal-Variance Event Scheduling for CTMC/DTMC Discrete Diffusion and Flow Models
Stratified hazard sampling reduces variance in discrete diffusion/flow models by optimizing event scheduling in CTMC/DTMC processes.
2/18/2026
PROMA: Projected Microbatch Accumulation for Reference-Free Proximal Policy Updates
PROMA: reference-free proximal policy method for LLM training that controls KL divergence via gradient projection without reference model.
2/18/2026
GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance
GenDA reconstructs high-resolution urban wind fields from sparse sensor data using graph-based diffusion and classifier-free guidance.
2/18/2026
Orthogonalized Policy Optimization:Decoupling Sampling Geometry from Optimization Geometry in RLHF
OPO: theoretical framework for LLM alignment using constrained proximal policy optimization with work-dissipation principle and chi-square geometry.
2/18/2026
Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
Instant Retrospect Action algorithm improves policy exploitation in online RL through Q-network representation learning.
2/18/2026
Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting
Green-NAS multi-objective neural architecture search optimizes weather forecasting models for efficiency and carbon footprint.
2/18/2026
Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based Models
MinPV Principle minimizes path variance in score-based models to improve accuracy and stability.
2/18/2026
On the Role of Iterative Computation in Reinforcement Learning
Analyzes role of iterative computation in RL, showing policies benefit from additional compute beyond fixed parameters.
2/18/2026
Achieving Optimal Static and Dynamic Regret Simultaneously in Bandits with Deterministic Losses
Algorithm achieving simultaneous optimal static and dynamic regret in adversarial multi-armed bandits.
2/18/2026
Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models
Horizon Imagination improves efficiency of diffusion-based world models for RL by denoising multiple future observations.
2/18/2026
How Well Do Large-Scale Chemical Language Models Transfer to Downstream Tasks?
Systematic evaluation of chemical language model scaling on molecular property prediction downstream tasks.
2/18/2026
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
Recovery-based shielding framework integrates Gaussian process models with RL for provably safe control in continuous systems.
2/18/2026
Online GPU Energy Optimization with Switching-Aware Bandits
Online GPU energy optimization using bandit algorithms to reduce power consumption in HPC systems.
2/18/2026
Linear Bandits beyond Inner Product Spaces, the case of Bandit Optimal Transport
Extends linear bandits theory beyond inner product spaces using optimal transport for recommendation and clinical systems.
2/18/2026
Can Multimodal LLMs Perform Time Series Anomaly Detection?
Evaluates multimodal LLMs and vision-language models for time series anomaly detection in systems monitoring.
2/18/2026
Curved representational Bregman divergences and their applications
Mathematical analysis of curved Bregman divergences and their applications in statistical learning.
2/18/2026
Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications
MINT framework aligns LLMs with biomedical knowledge using preference optimization on multimodal data.
2/18/2026
MMS-VPR: Multimodal Street-Level Visual Place Recognition Dataset and Benchmark
MMS-VPR introduces a large-scale multimodal dataset for street-level visual place recognition in pedestrian environments.
2/18/2026
cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
Cadrille uses reinforcement learning for multi-modal CAD reconstruction from point clouds, images, and text inputs.
2/18/2026
TQml Simulator: optimized simulation of quantum machine learning
TQml Simulator benchmarks numerical simulation techniques for quantum machine learning circuits to accelerate research.
2/18/2026
Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs
AI agent framework integrating LLMs with Lean formal proof assistant for automated theorem proving.
2/18/2026
A LoD of Gaussians: Unified Training and Rendering for Ultra-Large Scale Reconstruction with External Memory
Gaussian splatting technique with external memory for large-scale 3D reconstruction rendering.
2/18/2026
Token-Based Audio Inpainting via Discrete Diffusion
Discrete diffusion method for audio inpainting using pre-trained tokenized representations.
2/18/2026
Hybrid Reward-Driven Reinforcement Learning for Efficient Quantum Circuit Synthesis
Reinforcement learning approach for quantum circuit synthesis optimization using Q-learning.
2/18/2026
Counterfactual Survival Q-learning via Buckley-James Boosting, with Applications to ACTG 175 and CALGB 8923
Reinforcement learning framework for dynamic treatment regime estimation from censored survival data.
2/18/2026
XAI-Driven Spectral Analysis of Cough Sounds for Respiratory Disease Characterization
Explainable AI methodology for cough sound spectral analysis to characterize respiratory diseases.
2/18/2026
NPG-Muse: Scaling Long Chain-of-Thought Reasoning with NP-Hard Graph Problems
Scaling long chain-of-thought reasoning in LLMs using NP-hard graph problems for cost-effective training.
2/18/2026
Agents of Discovery
Autonomous AI agents for physics data analysis using machine learning in particle physics research.
2/18/2026
Learning depth-3 circuits via quantum agnostic boosting
Quantum machine learning method for learning phase states via agnostic boosting.
2/18/2026
Improving User Interface Generation Models from Designer Feedback
RLHF approaches for improving LLM-based UI generation using designer feedback and rationale.
2/18/2026
VLCE: A Knowledge-Enhanced Framework for Image Description in Disaster Assessment
Vision-language model enhancement framework for improved disaster assessment image descriptions.
2/18/2026
FlowDrive: moderated flow matching with data balancing for trajectory planning
Flow matching trajectory planning for autonomous driving with data balancing strategies.
2/18/2026
Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
Safety vulnerability analysis of diffusion language models and mitigation strategies for jailbreak attacks.
2/18/2026
Generalized Parallel Scaling with Interdependent Generations
Method for scaling parallel LLM inference by enabling interdependent token generation across multiple responses.
2/18/2026
mini-vec2vec: Scaling Universal Geometry Alignment with Linear Transformations
Efficient linear transformation method for aligning text embedding spaces without parallel data.
2/18/2026
Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
Convergence analysis of regret matching in zero-sum games bridging theoretical and practical game-solving methods.