Ali Etemad

An Ensemble Semi-Supervised Adaptive Resonance Theory Model With Explanation Capability for Pattern Classification

2023 · IEEE Transactions on Emerging Topics in Computational Intelligence

Most semi-supervised learning (SSL) models entail complex structures and iterative training processes as well as face difficulties in interpreting their predictions to users. To address these issues, this article proposes a new interpretable SSL model …

A Bag of Tricks for Few-Shot Class-Incremental Learning

2024 · arXiv (Cornell University)

We present a bag of tricks framework for few-shot class-incremental learning (FSCIL), which is a challenging form of continual learning that involves continuous adaptation to new tasks with limited samples. FSCIL requires both stability and …

Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference

2024 · arXiv (Cornell University)

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given …