Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.

A comprehensive benchmarking framework for evaluating and optimizing CPU-centric agentic AI systems across multiple workloads, reproducing results from the research paper: "A CPU-Centric Perspectiv…

LLM Dynamic Planner - Combining LLM with PDDL Planners to solve an embodied task

Code release for ReaLM accepted by DAC 25

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

Repository to host and maintain SCALE-Sim code

HISIM introduces a suite of analytical models at the system level to speed up performance prediction for AI models, covering logic-on-logic architectures across 2D, 2.5D, 3D and 3.5D integration

21 Lessons, Get Started Building with Generative AI

CIM test time adaptation estimation framework.

AI and Memory Wall

Machine Learning Systems

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

The source code of "Agents of Autonomy: A Systematic Study of Robotics on Modern Hardware" paper

Code for "Learning to Model the World with Language." ICML 2024 Oral.

A pytorch model profiler with information about macs, energy and e.t.c

Simulator + benchmark suite for Micro Aerial Vehicle design.

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Benchmarking suite to evaluate 🤖 robotics computing performance. Vendor-neutral. ⚪Grey-box and ⚫Black-box approaches.

GoldenEye is a functional simulator with fault injection capabilities for common and emerging numerical formats, implemented for the PyTorch deep learning framework.

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

Sniffy Bug: A fully autonomous swarm of gas-seeking nano quadcopters in cluttered environments

Simple and easily configurable grid world environments for reinforcement learning

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Implementation of robust quantization, weight clipping and random bit error training to improve robustness against bit errors in quantized weights.