📰 Must-read papers and blogs on Speculative Decoding ⚡️

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

Official Implementation of EAGLE-1 (ICML'24) and EAGLE-2 (EMNLP'24)

zkDL, an open source toolkit for zero-knowledge proofs of deep learning powered by CUDA

[ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning

TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

Onboarding guide to Jimmy Lin's research group at the University of Waterloo

FFCV: Fast Forward Computer Vision (and other ML workloads!)

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

Empirical tricks for training robust models (ICLR 2021)

Understanding and Improving Fast Adversarial Training [NeurIPS 2020]

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

A Closer Look at Accuracy vs. Robustness

A pytorch adversarial library for attack and defense methods on images and graphs

[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training

A smaller subset of 10 easily classified classes from Imagenet, and a little more French

Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf

A small course on exploiting and defending neural networks

Github of the FaceForensics dataset

Style Transfer by Relaxed Optimal Transport and Self-Similarity (CVPR 2019)

Code for our nips19 paper: You Only Propagate Once: Accelerating Adversarial Training Via Maximal Principle

Code for FAB-attack

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

A curated list of awesome self-supervised methods