collaborators

5 papers

cs.LG2026

LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment

Pascal Ekin, Hyosun Choi, Wei Jie

We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rather than in its weights. Whe…

cs.CL2026

Ensemble Learning for Large Language Models in Text and Code Generation: A Survey

Mari Ashiga, Wei Jie, Fan Wu +5

Generative Pretrained Transformers (GPTs) are foundational Large Language Models (LLMs) for text generation. However, individual LLMs often produce inconsistent outputs and exhibit…

cs.SE2025

Evolving Excellence: Automated Optimization of LLM-based Agents

Paul Brookes, Vardan Voskanyan, Rafail Giavrimis +18

Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software development to customer support. However, LLM a…

cs.SE2025

Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach

Mari Ashiga, Vardan Voskanyan, Fateme Dinmohammadi +7

Recent advancements in Large Language Models (LLMs) for code optimization have enabled industrial platforms to automate software performance engineering at unprecedented scale and…

cs.SE2025

Language Models for Code Optimization: Survey, Challenges and Future Directions

Jingzhi Gong, Vardan Voskanyan, Paul Brookes +7

Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion…