steve's repositories
adahessian
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
ASTRA
Self-training with Weak Supervision (NAACL 2021)
bolt
10x faster matrix and vector operations
byteps
A high performance and generic framework for distributed DNN training
CHMM-ALT
Code for "BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition"
CLSR
The official implementation of "Disentangling Long and Short-Term Interests for Recommendation" (WWW '22)
DEFUSE
code of our WWW 2022 paper Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction
DensePhrases
ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too
diplomacy_cicero
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
dpro
Analysis for the traces from byteprofile
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
fairseq-apollo
FairSeq repo with Apollo optimizer
fast-transformers
Pytorch library for fast transformer implementations
flash-attention
Fast and memory-efficient exact attention
frnet
The Source Code of FRNet
gdfm_nips22
code of Generalized Delayed Feedback Model with Post-Click Information in Recommender Systems, NeurIPS 2022
keras-io
Keras documentation, hosted live at keras.io
KnowledgeablePromptTuning
kpt code
p4app-switchML
Switch ML Application
pretraining-with-human-feedback
Code accompanying the paper Pretraining Language Models with Human Preferences
ps-lite
A lightweight parameter server interface
robust-aggregate-lfs
Source code of our ACL 2022 paper 'Learning to robustly aggregate labeling functions for semi-supervised data programming'
SCM4LLMs
Self-Controlled Memory System for LLMs
skweak
skweak: A software toolkit for weak supervision applied to NLP tasks
t-few
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"
tart
Code and model release for the paper "Task-aware Retrieval with Instructions" by Asai et al.
wrench
WRENCH: Weak supeRvision bENCHmark
WWW-22-DIHN
[WWW'22] Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation