3/30/2026
PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion
PruneFuse strategy uses pruned networks for efficient data selection and fuses them with original networks to optimize deep neural network training.
3/30/2026
On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks
Complexity analysis of optimal graph rewiring to address oversmoothing and oversquashing in deep graph neural networks.
3/30/2026
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Unified framework for data-centric dynamic training of LLMs with consistent interfaces for data selection and reweighting.
3/30/2026
Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
Study of LLM-based AI scientist agents learning from iterative experimental feedback in cell screening with 800 replicated experiments.
3/30/2026
Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach
Analysis of optimization trade-offs in asynchronous federated learning addressing gradient staleness and client bias.
3/30/2026
Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems
Knowledge distillation approach for deploying Transformer-based reinforcement learning on resource-constrained energy management devices.
3/30/2026
A Formal Framework for Uncertainty Analysis of Text Generation with Large Language Models
Formal framework for measuring uncertainty in LLM text generation accounting for prompting, generation, and interpretation stages.
3/30/2026
Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards
Survey of generative modeling in protein design covering neural representations, conditional generation, and evaluation standards.
3/30/2026
Neuro-Symbolic Process Anomaly Detection
Neuro-symbolic approach combining neural networks and domain knowledge for process anomaly detection from event logs.
3/30/2026
Automatic feature identification in least-squares policy iteration using the Koopman operator framework
Koopman autoencoder-based least-squares policy iteration algorithm enabling automatic feature learning in reinforcement learning.
3/30/2026
Shapley meets Rawls: an integrated framework for measuring and explaining unfairness
Framework using Shapley values to measure and explain unfairness in machine learning models under group fairness criteria with inference methods.
3/30/2026
SPECTRA: An Efficient Spectral-Informed Neural Network for Sensor-Based Activity Recognition
SPECTRA: spectral-informed neural network for sensor-based activity recognition optimized for edge deployment with low latency and privacy.
3/30/2026
EcoFair: Trustworthy and Energy-Aware Routing for Privacy-Preserving Vertically Partitioned Medical Inference
EcoFair: privacy-preserving medical inference framework with lightweight routing for vertically partitioned data and modality-specific embeddings.
3/30/2026
Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory
Theoretical analysis of spectral optimizers like Muon in language model training, studying capacity scaling through linear associative memory framework.
3/30/2026
Machine Unlearning under Retain-Forget Entanglement
Machine unlearning framework addressing retain-forget entanglement where retained samples unintentionally affected by forgetting correlated features.
3/30/2026
Evaluating Interactive 2D Visualization as a Sample Selection Strategy for Biomedical Time-Series Data Annotation
Study comparing sample selection methods (random, farthest-first, interactive visualization) for annotation of biomedical time-series data with real annotators.
3/30/2026
PQuantML: A Tool for End-to-End Hardware-aware Model Compression
PQuantML: open-source hardware-aware neural network compression library for pruning and quantization with unified interface for latency-constrained deployment.
3/30/2026
Hardware-Aware Tensor Networks for Real-Time Quantum-Inspired Anomaly Detection at Particle Colliders
Quantum-inspired anomaly detection using hardware-aware tensor networks for particle collider physics, deployable on classical hardware.
3/30/2026
Benchmarking Tabular Foundation Models for Conditional Density Estimation in Regression
Systematic evaluation of tabular foundation models like TabPFN and TabICL for conditional density estimation in regression tasks with heteroscedasticity.
3/30/2026
Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits
C²MF: context-specific credibility-aware multimodal fusion framework using probabilistic circuits to handle conflicting modalities and situational reliability changes.
3/30/2026
A Judge Agent Closes the Reliability Gap in AI-Generated Scientific Simulation
Judge Agent system using automated mathematical validation to reduce silent failures in LLM-generated scientific simulation code from 42% to 1.5%.
3/30/2026
ExVerus: Verus Proof Repair via Counterexample Reasoning
LLM framework for formal proof repair using counterexample-guided reasoning and behavioral feedback to improve automated verification.
3/30/2026
Doctorina MedBench: End-to-End Evaluation of Agent-Based Medical AI
Comprehensive evaluation framework for agent-based medical AI systems via multi-step clinical dialogue simulation with realistic physician-patient interactions.
3/30/2026
Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned
Real-world evaluation of visual navigation foundation models on robot navigation, testing generalization and providing trajectory quality metrics.
3/30/2026
Collision-Aware Vision-Language Learning for End-to-End Driving with Multimodal Infraction Datasets
Vision-language learning approach for end-to-end autonomous driving using multimodal datasets and collision-aware representation learning.
3/30/2026
Globalized Adversarial Regret Optimization: Robust Decisions with Uncalibrated Predictions
Optimization framework for robust decisions when predictions lack calibrated error bounds, combining robust and regret formulations.
3/30/2026
Asymptotic Optimism for Tensor Regression Models with Applications to Neural Network Compression
Theoretical analysis of rank selection for low-rank tensor regression with applications to neural network compression and model optimization.
3/30/2026
A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning
Decoupled audio transformer architecture inspired by human cognition for efficient self-supervised learning on resource-constrained devices.
3/30/2026
Finding Distributed Object-Centric Properties in Self-Supervised Transformers
Analysis of object discovery in self-supervised Vision Transformers, showing how [CLS] token attention maps contain spurious activations affecting localization.
3/30/2026
Dual-Stage Invariant Continual Learning under Extreme Visual Sparsity
Continual learning method for object detection under extreme visual sparsity conditions using dual-stage invariant learning.
3/30/2026
On associative neural networks for sparse patterns with huge capacities
Higher-order associative memory models combining exponential interactions with sparse pattern storage for improved storage capacity.
3/30/2026
Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms
Analysis of privacy-accuracy trade-offs in high-dimensional sparse linear regression using differential privacy mechanisms and approximate message passing.
3/30/2026
Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR
Method for compressing conversational audio context in LLM-based speech recognition systems, studying multimodal context from prior turns for improved ASR.
3/30/2026
Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
Approach for merging multiple LoRA modules while preserving subspace coverage and addressing directional anisotropy to maintain task representation in general-purpose systems.
3/30/2026
SALMUBench: A Benchmark for Sensitive Association-Level Multimodal Unlearning
Benchmark for evaluating machine unlearning in multimodal models like CLIP, introducing SALMUBench with 60K persona-attribute associations for fine-grained forgetting evaluation.
3/30/2026
Label-Free Cross-Task LoRA Merging with Null-Space Compression
Method for merging independently fine-tuned LoRA adapters across heterogeneous tasks using null-space compression, addressing classification-regression task combinations.
3/30/2026
Making Multi-Axis Models Robust to Multiplicative Noise: How, and Why?
Graph-learning algorithm (MED-MAGMA) for fitting Kronecker-sum-structured models with multiplicative noise in genomics applications.
3/30/2026
Generative Score Inference for Multimodal Data
Generative approach for uncertainty quantification in multimodal supervised learning combining images and text data.
3/30/2026
Kantorovich--Kernel Neural Operators: Approximation Theory, Asymptotics, and Neural Network Interpretation
Theoretical analysis of Kantorovich-kernel neural network operators with density results, convergence estimates, and Korovkin theorems.
3/30/2026
Meta-Learned Adaptive Optimization for Robust Human Mesh Recovery with Uncertainty-Aware Parameter Updates
Meta-learning framework for human mesh recovery from images using optimization-friendly initializations and uncertainty-aware updates.
3/30/2026
UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models
UNIFERENCE: discrete-event simulation framework for developing and benchmarking distributed AI inference algorithms across heterogeneous devices and networks.
3/30/2026
AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese
AMALIA: fully open source LLM trained on high-quality European Portuguese data with native evaluation benchmark and improved pt-PT representation.
3/30/2026
ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs
ALBA: linguistically grounded benchmark for evaluating LLM performance on European Portuguese, addressing underrepresentation in existing benchmarks.
3/30/2026
Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence
Experimental pipeline profiling energy consumption, latency, and quality trade-offs for deploying LLMs on edge devices with hardware constraints.
3/30/2026
Machine Learning Transferability for Malware Detection
Study evaluating ML feature compatibility and transferability across malware detection datasets under distribution shifts.
3/30/2026
Complexity-Aware Deep Symbolic Regression with Robust Risk-Seeking Policy Gradients
Deep symbolic regression using policy gradients with complexity awareness for interpretable data-driven mathematical expression discovery.
3/30/2026
How iteration order influences convergence and stability in deep learning
Theoretical analysis of how iteration order affects convergence and stability in deep neural network training without learning rate schedules.
3/30/2026
Robust Predictive Modeling Under Unseen Data Distribution Shifts: A Methodological Commentary
Methodological commentary on robust predictive modeling under distribution shifts in real-world deployment scenarios.
3/30/2026
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
Task Tokens method adapts behavior foundation models to specific tasks via learnable tokens while preserving zero-shot generalization capabilities.
3/30/2026
FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
FastCache accelerates Diffusion Transformer inference through learnable linear approximation and spatial-aware token selection for hidden-state caching.