collaborators

6 papers

eess.SY2026

A flexible language model-assisted electronic design automation framework

Cristian Sestito, Panagiota Kontou, Pratibha Verma +5

Large language models (LLMs) are transforming electronic design automation (EDA) by enhancing design stages such as schematic design, simulation, netlist synthesis, and place-and-r…

cs.LG2026

GatedFWA: Linear Flash Windowed Attention with Gated Associative Memory

Jiaxu Liu, Yuhe Bai, Xiangyu Yin +1

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves li…

cs.AR2025

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition

Keran Zheng, Yinting Huang, Zhewen Yu +1

Recent advancements in Large Language Models (LLMs) have demonstrated impressive capabilities as their scale expands to billions of parameters. Deploying these large-scale models o…

cs.AR2025

ATHEENA: A Toolflow for Hardware Early-Exit Network Automation

Benjamin Biggs, Christos-Savvas Bouganis, George A. Constantinides

The continued need for improvements in accuracy, throughput, and efficiency of Deep Neural Networks has resulted in a multitude of methods that make the most of custom architecture…

cs.LG2025

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It

Guoxuan Xia, Olivier Laurent, Gianni Franchi +1

Label smoothing (LS) is a popular regularisation method for training neural networks as it is effective in improving test accuracy and is simple to implement. ``Hard'' one-hot labe…

cs.CV2025

Cached Multi-Lora Composition for Multi-Concept Image Generation

Xiandong Zou, Mingzhu Shen, Christos-Savvas Bouganis +1

Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and style…