Pinned Repositories
Unpaired-Image-Generation
Project Repo for Unpaired Image Generation project
forcesight
Given an RGBD image and a text prompt, ForceSight produces visual-force goals for a robot, enabling mobile manipulation in unseen environments with unseen object instances.
visual-force-torque
Estimating the forces and torques applied to a soft robotic gripper using a gripper-mounted camera.
distracted_driver_detection
We use the State Farm Distracted Driver Detection dataset to classify images of drivers as driving safely or performing particular unsafe actions while at the wheel.
fractal_generation
Python scripts which generate fractals from scratch. I wrote these to get some intuition for recursion. Did you know that the B in Benoit B. Mandelbrot stands for Benoit B. Mandelbrot?
gpt4v-screenshot-analyzer
This tool offers an interactive way to analyze and understand your screenshots using OpenAI's GPT-4 Vision API. Capture any part of your screen and engage in a dialogue with ChatGPT to uncover detailed insights, ask follow-up questions, and explore visual data in a user-friendly format.
robot-rlhf
Robot Learning from Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.
sd-video-gen
Video generation using Stable Diffusion.
transformer_from_scratch
Transformer implementation using PyTorch.
vroom
We use visual data alone to learn a control policy for a robotic arm by observing expert video demonstrations. We implement and test several models, accomplishing an 85% success rate for a pick-and-place task.
jeremy-collins's Repositories
jeremy-collins/gpt4v-screenshot-analyzer
This tool offers an interactive way to analyze and understand your screenshots using OpenAI's GPT-4 Vision API. Capture any part of your screen and engage in a dialogue with ChatGPT to uncover detailed insights, ask follow-up questions, and explore visual data in a user-friendly format.
jeremy-collins/robot-rlhf
Robot Learning from Human Feedback. Inspired by advancements in NLP, we train a robot policy via reinforcement learning using a reward function learned exclusively from human preferences.
jeremy-collins/sd-video-gen
Video generation using Stable Diffusion.
jeremy-collins/fractal_generation
Python scripts which generate fractals from scratch. I wrote these to get some intuition for recursion. Did you know that the B in Benoit B. Mandelbrot stands for Benoit B. Mandelbrot?
jeremy-collins/distracted_driver_detection
We use the State Farm Distracted Driver Detection dataset to classify images of drivers as driving safely or performing particular unsafe actions while at the wheel.
jeremy-collins/transformer_from_scratch
Transformer implementation using PyTorch.
jeremy-collins/visual-force-torque
Estimating the forces and torques applied to a soft robotic gripper using a gripper-mounted camera.
jeremy-collins/vroom
We use visual data alone to learn a control policy for a robotic arm by observing expert video demonstrations. We implement and test several models, accomplishing an 85% success rate for a pick-and-place task.
jeremy-collins/CuberBot
A Rubik's Cube solving robot! Two robotic hands with tendon-actuated fingers replicate the movements of a human speedsolver.
jeremy-collins/FundamentalConstantFinder
Can physics be brute forced? We attempt to search through function space in order to find relations between the fundamental constants of the universe.
jeremy-collins/midnight_stretch
A semi-autonomous robotic caregiving system capable of detecting falls among the elderly.
jeremy-collins/pycade
jeremy-collins/SkyTube
Can you stop a skydiver from hitting the ground with a tube full of fluids of increasing density, thus stopping the skydiver with a combination of drag and buoyancy? Only one way to find out!
jeremy-collins/sparse-dictionary-learning
jeremy-collins/classifier-free-guidance-pytorch
Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embedding models
jeremy-collins/IsaacGymEnvs
Isaac Gym Reinforcement Learning Environments
jeremy-collins/Unpaired-Image-Generation
Project Repo for Unpaired Image Generation project