Name: Christopher Agia
Type: User
Company: @googlers, @rvl-lab-utoronto
Bio: PhD candidate in Computer Science at Stanford University focusing on Robotics, Learning and Vision. Intern at NASA JPL.
Twitter: agiachris
Location: St. George Campus, Toronto
Blog: https://www.chrisagia.com/
Christopher Agia's Projects
The data skeleton from "3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera" http://3dscenegraph.stanford.edu
AER201 Autonomous Packing Robot - Interface and Machine Code
Visit academic site
Batched operations for PyTorch autograd
Anomaly Detection System using Gaussian Mixture Models
CLIPort: What and Where Pathways for Robotic Manipulation
An implementation of a Gomoku AI Engine
Connect, secure, control, and observe services.
Program that compresses the size of image files without compromising image quality to optimize memory usage
Implementation for the Neural Logic Machines (NLM).
Contains several implementations for numerical integration and root finding algorithms
Convert a PDDL domain into an OpenAI Gym environment.
PDDL planner interface for PDDLGym.
WebAssembly for Proxies (Rust SDK)
Contains implementations of several common machine learning models and optimization techniques used for regression and classification problems.
APS360 Final Project - Rotation Invariant 3D Shape Completion Network
Code accompanying "Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks"
A functorch-accelerated framework for efficient neural network uncertainty quantification with SCOD
Intelligent system that approximates the semantic similarity of any two pair of words by parsing data from large novels and computing cosine similarities and Euclidean spaces between vector descriptors of each word
Pytorch version of SfmLearner from Tinghui Zhou et al.
SfMLearner applied to the Canadian Planetary Emulation Terrain Energy-Aware Rover Navigation Dataset
Simulator that ranks the performance of any Solar Array CAD model and predicts the instantaneous energy generation based on the vehicle’s global position, the relative angle to the sun, and shading due to the vehicle’s design
Official repository for "STAP: Sequencing Task-Agnostic Policies," presented at ICRA 2023.
WebAssembly for Proxies (test framework)
Query UCSF Truth Tobacco Industry Documents Archive
Standalone JIT-style runtime for WebAssembly, using Cranelift