Uber Research

deep-neuroevolution

Deep Neuroevolution

PPLM

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

go-explore

Code for Go-Explore: a New Approach for Hard-Exploration Problems

PyTorch-NEAT

LaneGCN

[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting

DeepPruner

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch (ICCV 2019)

parallax

Tool for interactive embeddings visualization

jpeg2dct

poet

Paired Open-Ended Trailblazer (POET) and Enhanced POET

CoordConv

EvoGrad

go

The Go programming language. This fork was created for pprof++, a Go profiler with hardware performance monitoring. Read through the link for more detail: https://eng.uber.com/pprof-go-profiler/

TuRBO

permute-quantize-finetune

Using ideas from product quantization for state-of-the-art neural network compression.

deconstructing-lottery-tickets

CRISP

metropolis-hastings-gans

loss-change-allocation

MARVIN

Uber's Multi-Agent Routing Value Iteration Network

GOCC

Map-Elites-Evolutionary

Map-Elites based on Evolution Strategies

vargp

Variational Auto-Regressive Gaussian Processes for Continual Learning

brezel

dispatch-optim

Constrainted based optimization

rl-controller-verification

Quadcopter Verification

go-context-propagate

last-diff-analyzer

A multi-language tool for checking semantic equivalence for code

tailr

TAILR

xplane-bazel-docker

Bazel Xplane

alpacas

Alpacas