Makesh Sreedhar

Makesh Sreedhar is an applied scientist in the NVIDIA Dialog Research group where he focuses on model alignment and guardrails for language models. While working on his master’s degree at the University of Wisconsin-Madison, Makesh worked on efficient techniques for machine translation and multi-hop question answering. Makesh likes reading about recent advancements in NLP and applying them to address industry challenges.
Makesh Sreedhar

Posts by Makesh Sreedhar

Generative AI / LLMs

Announcing NVIDIA SteerLM: A Simple and Practical Technique to Customize LLMs During Inference

With the advent of large language models (LLMs) such as GPT-3, Megatron-Turing, Chinchilla, PaLM-2, Falcon, and Llama 2, remarkable progress in natural language... 10 MIN READ