Samuel Schmidgall

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

High-performance GPU-based simulation platform for reinforcement learning with surgical robot learning

Agent benchmark for medical diagnosis

Code repository for paper: "General surgery vision transformer: A video pre-trained foundation model for general surgery"

A list of papers that I liked.

Papers from the intersection of surgery and data science / machine learning

Produce intelligence by means of natural selection without objective/reward optimization

From Never Ending Reinforcement Learning Workshop ICML 2021

Python implementations of various machine learning algorithms from scratch.

Evolutionary and gradient optimization library for rapid experimentation

Evolutionary Strategies approach toward reward modulated online meta learning with plastic weights

Must-read Papers on LLM Agents.

Papers of ComputerVision x Surgery

Papers from the intersection of deep learning and neuroscience

A list of books I liked

Semester-Project for CS321

Research on Quadrupedal Navigation Spring Semester 2020

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

website for a cool guy

A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

Automated Design of Agentic Systems

No description.

Implementing machine learning algorithms from scratch.

Solved Project Euler Submissions

PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images

Fast and simple implementation of RL algorithms, designed to run fully on GPU.

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

No description.

Utility that enables the comparison of two papers based on semantics to validate or invalidate originality

Selective Hearing -- Final Project in CS484