Brandon Amos

Differentiable Optimization-Based Modeling for Machine Learning

No description.

Differentiable convex optimization layers

Image Completion with Deep Learning in TensorFlow

A PyTorch implementation of DenseNet.

Website for personal collection and previewing of LaTeX templates. Presented with Python/Jinja2.

An intelligent block matrix library for numpy, PyTorch, and beyond.

Plot your .zsh_history.

♥ Linux, xmonad, emacs, vim, zsh, tmux

Short and fun Python scripts.

My reading list.

No description.

An unofficial mirror of the core PARSEC 3.0 benchmark suite with patches to run on x86_64 Arch Linux and generalize builds.

Small Python library to automatically set CUDA_VISIBLE_DEVICES to the least loaded device on multi-GPU systems.

Website for personal collection and previewing of Beamer and TikZ snippets. Presented with Python/Jinja2.

Minimal-maintenance conference tracker.

Check your GitHub READMEs for broken links.

The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.

No description.

Haskell-driven, small-scale web analytics with minimal configuration.

Unofficial Torch ECOS bindings to solve linear programs (LPs) and second-order cone programs (SOCPs).

Unofficial Gurobi Torch bindings.

Miscellaneous short shell scripts.

Lecture materials for Cornell CS5785 Applied Machine Learning (Fall 2024)

Ensure all links in a Github Wiki point to valid locations within the Wiki.

Build LLVM, Polly, and PoCL in an Ubuntu 12.04 Docker container.

Instructions and files to set up a server mirroring the entire Android project.

No description.

No description.

An ongoing repository of data on coronavirus cases and deaths in the U.S.

A Python-embedded modeling language for convex optimization problems.

[ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Optimal Transport tools implemented with the JAX framework, to get auto-diff, parallel and jit-able computations.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

A version of verl to support diverse tool use

Official Implementation of paper accepted by ICLR2025-MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

Prompts for our Grok chat assistant and the `@grok` bot on X.

An Introduction to Deep Generative Modeling: Examples

[ICLR 2022] Path integral sampler

No description.

functorch is JAX-like composable function transforms for PyTorch.

Datasets, Transforms and Models specific to Computer Vision

Python interface for OSQP

Proto-RL: Reinforcement Learning with Prototypical Representations

Differentiation through cone programs.

Notes for ICML 2019

Source code for lecture notes

Python interface for SCS

C package that solves convex cone problems via operator splitting