4 papers
ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localization
Shahd Seddik, Fahd Seddik, Amirrezza Esmaeili +2
Automated program repair at repository scale requires an agent to locate a fault among thousands of files and synthesize a correct patch. Existing graph-based agents represent how…
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Fahd Seddik, Fatemeh Fard
We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream benchmark scores and reveal represe…
Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra
Fahd Seddik, Abdulrahman Elbedewy, Gaser Sami +2
Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to c…
Analysis of AdvFusion: Adapter-based Multilingual Learning for Code Large Language Models
Amirreza Esmaeili, Fahd Seddik, Yongyi Ji +2
Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code…