3/17/2026
From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning
Proposes Kalman World Models, a method for training state-space models using recursive Bayesian filtering instead of backpropagation for online learning.
3/17/2026
Self-Flow-Matching assisted Full Waveform Inversion
Flow matching-based approach for full-waveform inversion with generative priors to improve seismic imaging robustness.
3/17/2026
Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference
Outcome-Aware Tool Selection method for semantic routers in LLM inference, reducing latency by offline interpolation without GPU cost.
3/17/2026
CHIMERA-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design
Standardized benchmark dataset and evaluation framework for computational antibody design methods with unified metrics.
3/17/2026
Modality-free Graph In-context Alignment
Framework for in-context learning on graphs without modality-specific encoders, enabling cross-domain adaptation for graph foundation models.
3/17/2026
Improving Channel Estimation via Multimodal Diffusion Models with Flow Matching
Multimodal diffusion model using flow matching for channel estimation, fusing LiDAR, camera, and location data.
3/17/2026
Scalable Machines with Intrinsic Higher Mental-State Dynamics
Theoretical work on implementing higher-order mental-state dynamics in Transformers via triadic modulation for information pre-selection.
3/17/2026
Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding
Framework reconciling in-context and in-weight learning in Transformers through dual representation space encoding to reduce conflict.
3/17/2026
Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization
Probabilistic Gaussian Homotopy framework for nonconvex optimization using Boltzmann-weighted gradient aggregation.
3/17/2026
Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy
Analysis of complex singularities in softmax cross-entropy loss that limit safe step sizes during optimization training.
3/17/2026
Scalable Classification of Course Information Sheets Using Large Language Models: A Reusable Institutional Method for Academic Quality Assurance
End-to-end LLM method for auditing course information sheets at scale to identify GenAI vulnerabilities in academic assessments.
3/17/2026
Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
Survey of privacy-preserving machine learning for IoT devices, covering federated learning, differential privacy, and resource constraints.
3/17/2026
Volumetric Radar Echo Motion Estimation Using Physics-Informed Deep Learning: A Case Study Over Slovakia
Physics-informed CNN for precipitation nowcasting using volumetric radar data to estimate multi-altitude motion fields.
3/17/2026
Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE
Federated learning approach for fraud detection in payment systems using NVIDIA FLARE, preserving privacy across institutions with non-IID data.
3/17/2026
BERTology of Molecular Property Prediction
Systematic study of chemical language models for molecular property prediction, analyzing performance inconsistencies across benchmarks through controlled experiments.
3/17/2026
SemRep: Generative Code Representation Learning with Code Transformations
SemRep: generative code representation learning using code transformations for semantic reasoning in software development.
3/17/2026
PLUME: Building a Network-Native Foundation Model for Wireless Traces via Protocol-Aware Tokenization
PLUME: 140M-parameter foundation model for wireless packet traces using protocol-aware tokenization.
3/17/2026
PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers
PDE-SSM: state-space block replacing attention in diffusion transformers using learnable convection-diffusion-reaction equations.
3/17/2026
Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
Dynamic curriculum learning approach using gradient-based difficulty estimation for adaptive example ordering.
3/17/2026
Greedy Information Projection for LLM Data Selection
GIP framework for selecting training examples for LLM fine-tuning by maximizing mutual information with task-specific signals.
3/17/2026
IGU-LoRA: Adaptive Rank Allocation via Integrated Gradients and Uncertainty-Aware Scoring
IGU-LoRA: adaptive rank allocation for parameter-efficient fine-tuning of LLMs using integrated gradients and uncertainty scoring.
3/17/2026
Node Role-Guided LLMs for Dynamic Graph Clustering
LLM-guided approach for interpretable dynamic graph clustering with semantic explanations of cluster formation and evolution.
3/17/2026
On Interpolation Formulas Describing Neural Network Generalization
Theoretical analysis extending Domingos interpolation formula to stochastic gradient descent, characterizing neural network generalization as kernel machines.
3/17/2026
Scribe Verification in Chinese manuscripts using Siamese, Triplet, and Vision Transformer Neural Networks
Deep metric learning approach (Siamese, Triplet, Vision Transformer) for identifying scribes in Chinese manuscript calligraphy datasets.
3/17/2026
UVLM: A Universal Vision-Language Model Loader for Reproducible Multimodal Benchmarking
UVLM: unified framework for loading and benchmarking multiple vision-language models with standardized interface in Colab environment.
3/17/2026
Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels
Self-training framework with label correction for handling noisy data in neural network training using bilevel optimization techniques.
3/17/2026
FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data
FedPBS: federated learning algorithm addressing statistical heterogeneity and non-IID data for distributed ML training with privacy preservation.
3/17/2026
Close to Reality: Interpretable and Feasible Data Augmentation for Imbalanced Learning
Interpretable data augmentation for imbalanced learning that generates realistic, feasible samples with transparent procedures and adjustability.
3/17/2026
True 4-Bit Quantized Convolutional Neural Network Training on CPU: Achieving Full-Precision Parity
Method for training 4-bit quantized CNNs on standard CPUs with PyTorch achieving full-precision accuracy parity for cost-effective deep learning.
3/17/2026
Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications
CONSERVAttack method for testing high energy physics ML applications against physically motivated systematic uncertainties and adversarial robustness.
3/17/2026
Chunk-Guided Q-Learning
Chunk-Guided Q-Learning algorithm for offline reinforcement learning balancing bootstrapping error and policy flexibility over long horizons.
3/17/2026
Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning
Aumann-SHAP framework for interaction-aware counterfactual explanations decomposing model transitions using cooperative game theory.
3/17/2026
Benchmarking Open-Source PPG Foundation Models for Biological Age Prediction
Benchmarking open-source PPG foundation models for biological age prediction, comparing task-specific vs general-purpose models across populations.
3/17/2026
Gated Graph Attention Networks for Predicting Duration of Large Scale Power Outages Induced by Natural Disasters
Gated graph attention networks for predicting duration of large-scale power outages induced by natural disasters.
3/17/2026
Understanding the Emergence of Seemingly Useless Features in Next-Token Predictors
Analysis of redundant features emerging in Transformer next-token predictors, identifying gradient components responsible for seemingly useless feature computation.
3/17/2026
Not All Latent Spaces Are Flat: Hyperbolic Concept Control
Hyperbolic control mechanism using parallel transport to steer text-to-image models away from unsafe content generation.
3/17/2026
SVD Contextual Sparsity Predictors for Fast LLM Inference
Framework for accelerating LLM inference using contextual sparsity predictors for ReGLU-based feed-forward networks with minimal accuracy loss.
3/17/2026
Align Forward, Adapt Backward: Closing the Discretization Gap in Logic Gate Networks
Analysis of training-inference mismatch in neural networks with soft vs hard selection, using logic gate networks as test case.
3/17/2026
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
TACTIC method for tabular anomaly detection using in-context learning with foundation models, advancing unsupervised learning for anomaly detection tasks.
3/17/2026
Hybrid Intent-Aware Personalization with Machine Learning and RAG-Enabled Large Language Models for Financial Services Marketing
Hybrid architecture combining classical ML for customer segmentation with RAG-enabled LLMs for personalized financial services marketing content generation.
3/17/2026
Balancing Multimodal Domain Generalization via Gradient Modulation and Projection
Gradient modulation and projection techniques balance optimization across modalities in multimodal domain generalization tasks.
3/17/2026
Artificial intelligence-enabled single-lead ECG for non-invasive hyperkalemia detection: development, multicenter validation, and proof-of-concept deployment
Pocket-K AI-ECG system using ECGFounder foundation model for non-invasive hyperkalemia detection with handheld deployment.
3/17/2026
Interleaved Resampling and Refitting: Data and Compute-Efficient Evaluation of Black-Box Predictors
Efficient procedure for evaluating excess risk of empirical risk minimization using black-box access with minimal data and compute.
3/17/2026
Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys
Self-Indexing KVCache predicts sparse attention from compressed keys to reduce KV cache bottleneck in long-context LLM inference.
3/17/2026
Domain-Skewed Federated Learning with Feature Decoupling and Calibration
Addresses domain skew in federated learning through feature decoupling and calibration across distributed clients with diverse data.
3/17/2026
GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies
GoldenStart improves flow-matching RL policies via Q-guided priors and entropy control for faster inference and better exploration.
3/17/2026
Sampling Boltzmann distributions via normalizing flow approximation of transport maps
Mathematical foundation for sampling Boltzmann distributions via normalizing flows, proving existence of transport map approximations.
3/17/2026
Learning in Function Spaces: An Unified Functional Analytic View of Supervised and Unsupervised Learning
Unified functional analytic framework interpreting supervised and unsupervised learning as variational optimization over function spaces.
3/17/2026
High-Fidelity Compression of Seismic Velocity Models via SIREN Auto-Decoders
SIREN auto-decoder framework for high-fidelity compression of seismic velocity models using implicit neural representations.
3/17/2026
Enhancing LLM Training via Spectral Clipping
Spectral clipping optimization technique for LLM training that addresses spectral norm instability and gradient noise issues in standard optimizers.