About
I am Rishabh, currently part of the research group at Cartesia, working on post-training.
Previously, I was a Research Scientist at ServiceNow, where I worked on post-training through data curation, fine-tuning, reinforcement learning, and model evaluations. Some of my work includes the Apriel-15B model series, research on multilingual alignment and benchmarking, curriculum learning for preference modeling, and improving agentic capabilities.
Before that, I was an AI Resident at Meta AI (FAIR), working on text detection and multimodal vision-and-language understanding.
Prior to that, I completed my Master's at IIIT Hyderabad, focusing on adversarial robustness of language models.
Research
Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs
Findings of ACL 2025
Improving Selective Visual Question Answering by Learning from Your Peers
AI Residency at Meta AI, FAIR | CVPR 2023
