MehdiHmidi523/DeepRL-Navigation
M.Sc Thesis: Robotic Navigation under Partial Observability with Actor-Critic Methods DDPG, SAC, PPO. Environment, Lidar, and Kinematic Models provided.
M.Sc Thesis: Robotic Navigation under Partial Observability with Actor-Critic Methods DDPG, SAC, PPO. Environment, Lidar, and Kinematic Models provided.
Generate and auto-execute Python scripts in the cli
Make text LLMs listen and speak
Slides, code and data for SLEAP tutorial at MIT on July 9, 2020.
An invoice generator app built using Next.js, Typescript, and Shadcn
YAS: Yet Another Shop, a sample microservices project in Java
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
AI wearables
Cutting stock problem: A Genetic Algorithm to solve the One dimensional multiple stock size cutting stock problem (MSSCSP) using Mutation vs Mutation and Recombination.
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Python call graph visualization for recursive functions.
A simple Progressive Web App skeleton project
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way.
Longterm Memory for Autonomous Agents.
A framework for orchestrating AI agents using a mermaid graph
We write your reusable computer vision tools. 💜
Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Collection of useful C++ classes
⚡ Edgen: Local, private GenAI server alternative to OpenAI. No GPU required. Run AI models locally: LLMs (Llama2, Mistral, Mixtral...), Speech-to-text (whisper) and many others.
📈 Web tribute to the Tron: Legacy Boardroom Scene
A real-time 3D digital map of Tokyo's public transport system
A framework to enable multimodal models to operate a computer.
Code for Cross-Task Neural Architecture Search for EEG Signals
Exploration of diffuison-based generative model to sychronizing brain dynamics from semantic language input.
Implementation of Domain Specific Denoising Diffusion Probabilistic Models for Brain Dynamics/EEG Signals
Exploration on introducing discrete codex and raw wave decoding to realize Brain-to-Text translation.