Code generation has emerged as a central capability of large language models, with coding agents now able to produce functionally correct software projects from natural language prompts. However, functional correctness alone does not capture a critical dimension of generation quality: environment specification, defined...
Every text classifier for an African language begins with a budgeting question: how many labelled examples are needed, and can labels from other African languages stand in for them? We answer both questions empirically for 28 language-task pairs, news topic classification in 16 languages (MasakhaNEWS) and tweet sentime...
Bhanu Prakash Vangala, S. Guda, Navya Vangala· 0 citations
Biomedical machine learning papers often compress model performance into one headline number. That number can look like a property of the model even when it depends strongly on how the benchmark was evaluated. We study this problem on the widely used Kermany pediatric chest radiograph dataset using nine image classifie...
Bhanu Prakash Vangala, S. Guda, Latha Peddi et al.· 0 citations
Self-hosting multiple large language models on private or hybrid cloud infrastructure is increasingly appealing for organizations seeking privacy, cost control, and customization, yet no existing system coordinates model selection with model lifecycle management. Serving frameworks such as KServe and Ray Serve deploy m...
Bhanu Prakash Vangala, Tanu Malik· IEEE International Conferenc...· 0 citations
An empirical study of whether complete software artifacts generated by LLM coding agents can be executed in a clean environment using only the code, dependency specifications, and instructions the agent provides suggests that coding-agent evaluation should treat clean-environment executability as a first-class metric a...
