Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding

Improving Efficiency and Reliability of Computer Vision Models in Real-World Deployment with MX Quantization

Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization

MILEAM: Modeling Input-Aware Logic Errors of Approximate Multipliers using Machine Learning

Beyond Sampling: Classwise Loss Optimization for Imbalanced Deep Learning Recommendation Systems

Revisiting Lottery Ticket Hypothesis: Toward Efficient and Robust Deep Neural Networks

HDFlow: A Multi-layer Design and Evaluation Framework for Hyperdimensional Computing

Neuro-Symbolic AI vs. Vector Symbolic Architectures: Learning, Architecture and Reasoning

Proof-of-Useful-Work Blockchain for Trustworthy Biomedical Hyperdimensional Computing

A Comparative Study of Structured and Narrative EHR Data for 30-Day Readmission Risk Assessment