5 papers
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…
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…
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…
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…
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…