collaborators

5 papers

cs.LG2026

ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?

Ayush Nangia, Shikhar Mishra, Aman Gokrani +1

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the…

cs.CL2026

Making Large Language Models Speak Tulu: Structured Prompting for an Extremely Low-Resource Language

Prathamesh Devadiga, Paras Chopra

Can large language models converse in languages virtually absent from their training data? We investigate this question through a case study on Tulu, a Dravidian language with over…

cs.LG2026

Language Models Entangle Language and Culture

Shourya Jain, Paras Chopra

Users should not be systemically disadvantaged by the language they use for interacting with LLMs; i.e. users across languages should get responses of similar quality irrespective…

cs.LG2026

METIS: Mentoring Engine for Thoughtful Inquiry & Solutions

Abhinav Rajeev Kumar, Dhruv Trehan, Paras Chopra

Many students lack access to expert research mentorship. We ask whether an AI mentor can move undergraduates from an idea to a paper. We build METIS, a tool-augmented, stage-aware…

cs.LG2026

Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts

Dhruv Trehan, Paras Chopra

We report a case study of four end-to-end attempts to autonomously generate ML research papers using a pipeline of six LLM agents mapped to stages of the scientific workflow. Of th…