As Software Engineering enters its new era (SE 3.0), AI coding agents increasingly automate software development workflows. However, it remains unclear how exac...
Automated Program Repair (APR) aims to automatically generate correct patches for buggy programs. Recent approaches leveraging large language models (LLMs) have...
LLM-based software engineering is influencing modern software development. In addition to correctness, prior studies have also examined the performance of softw...
Fully automated verification of large-scale software and hardware systems is arguably the holy grail of formal methods. Large language models (LLMs) have recent...
Large language models (LLMs) have achieved remarkable progress in code generation, largely driven by the availability of high-quality code datasets for effectiv...
Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the u...
We present a genetic programming approach to automatically discover convergence acceleration methods for discrete ordinates solutions of neutron transport probl...
As LLMs and foundation models scale, checkpoint/restore has become a critical pattern for training and inference. With 3D parallelism (tensor, pipeline, data), ...
Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and t...
The real estate sector remains highly dependent on manual document handling and verification, making processes inefficient and prone to fraud. This work present...
Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context infer...
Live video analytics (LVA) runs continuously across massive camera fleets, but inference cost with modern vision models remains high. To address this, dynamic m...
