Saurabh Misra work spans machine learning, large-scale systems, and software performance, with a consistent focus on building faster, more efficient, and more sustainable technology.

NVIDIA’s Nemotron 3 Nano 30B features a 1M token context and 3B-active design, helping you build faster workflows and test tools locally.

Your browser does not support the audio element. TL;DR: Caching bit shifts looks smart but makes code up to 6× slower. Modern CPUs and compilers make direct ...

What if the key to unlocking the full potential of your AI-powered workflows lies not in adding more tools but in optimizing the ones you already have? For developers and teams using Claude Code, the ...

This repository is supplementary to our paper, CompilerDream: Learning a Compiler World Model for General Code Optimization [Arxiv]. We provide the code of our ...

This workshop on Engineering Design Optimization using MATLAB® and Python™ addresses the shape optimization of mechanical components for strength. Python ...

Abstract: The herein proposed Python package pflacco provides a set of numerical features to characterize single-objective continuous and constrained optimization problems. Thereby, pflacco addresses ...

Abstract: Optimizing Python code is essential for enhancing performance and efficiency. This project investigates the use of large pre-trained language models, specifically GPT (Generative Pre-trained ...

ProcessOptimizer is a Python package designed to provide easy access to advanced machine learning techniques, specifically Bayesian optimization using, e.g., Gaussian processes. Aimed at ...

Software development has benefited greatly from using Large Language Models (LLMs) to produce high-quality source code, mainly because coding tasks now take less time and money to complete. However, ...