CMU Locus Lab

TCN

Sequence modeling benchmarks and temporal convolutional networks

convmixer

Implementation of ConvMixer for "Patches Are All You Need? 🤷"

mpc.pytorch

A fast and differentiable model predictive control (MPC) solver for PyTorch.

deq

[NeurIPS'19] Deep Equilibrium Models

qpth

A fast and differentiable QP solver for PyTorch.

wanda

A simple and effective LLM pruning approach.

fast_adversarial

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

SATNet

Bridging deep learning and logical reasoning using a differentiable satisfiability solver.

convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

differentiable-mpc

deq-flow

[CVPR 2022] Deep Equilibrium Optical Flow Estimation

ect

Consistency Models Made Easy

cfd-gcn

massive-activations

Code accompanying the paper "Massive Activations in Large Language Models"

FLYP

Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models

tofu

Landing Page for TOFU

torchdeq

Modern Fixed Point Systems using Pytorch

chatllm-vscode

deq-ddim

scaling_laws_data_filtering

convmixer-cifar10

Simple CIFAR-10 classification with ConvMixer

tta_conjugate

Test-Time Adaptation via Conjugate Pseudo-Labels

T-MARS

Code for T-MARS data filtering

robust_union

[ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.

acr-memorization

diffusion-model-hallucination

get

Generative Equilibrium Transformer

smoothinv

Single Image Backdoor Inversion via Robust Smoothed Classifiers

MonotoneDBM

convcov