2 papers
cs.CL2025
BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes
Baichuan Huang, Ananth Balashankar, Amir Aminifar
Fine-tuning the bias terms of large language models (LLMs) has the potential to achieve unprecedented parameter efficiency while maintaining competitive performance, particularly i…
cs.LG2024
LightFF: Lightweight Inference for Forward-Forward Algorithm
Amin Aminifar, Baichuan Huang, Azra Abtahi +1
The human brain performs tasks with an outstanding energy efficiency, i.e., with approximately 20 Watts. The state-of-the-art Artificial/Deep Neural Networks (ANN/DNN), on the othe…