ykwon0407

WeightedSHAP

WeightedSHAP: analyzing and improving Shapley based feature attributions (NeurIPS 2022)

DataInf

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)

beta_shapley

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)

wdro_local_perturbation

Principled learning method for Wasserstein distributionally robust optimization with local perturbations (ICML 2020)

fast_dist_shapley

Efficient Computation and Analysis of Distributional Shapley Values (AISTATS 2021)

dataoob

Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value (ICML 2023)

data_purchase_in_comp

Competition over data: how does data purchase affect users? (TMLR)

STAT5206_Fall_2022

Statistical Computing and Introduction to Data Science @ Columbia Stats

STAT5206_Spring_2023

Statistical Computing and Introduction to Data Science @ Columbia Stats

ykwon0407.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

incontext_influences

Official repository for "In-context Example Selection with Influences"

influence_analysis_papers

Influence Analysis and Estimation - Survey, Papers, and Taxonomy

Intro_to_ML_Safety

introduction-to-github

Get started using GitHub in less than an hour.

leewtai.github.io

Github Pages

LLMDataHub

A quick guide (especially) for trending instruction finetuning datasets

LoRA-MPT

A repo for finetuning MPT using LoRA. It is currently configured to work with the Alpaca dataset from Stanford but can easily be adapted to use another.

Modality-Gap

Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning

open_lth

A repository in preparation for open-sourcing lottery ticket hypothesis code.

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

sanity_checks_saliency

sktime

A unified framework for machine learning with time series

STAT5206_Fall_2023

STAT5206_Summer_2023

Statistical Computing and Introduction to Data Science @ Columbia Stats

STAT5206_Summer_2024

Statistical Computing and Introduction to Data Science @ Columbia Stats

TART

TART: A plug-and-play Transformer module for task-agnostic reasoning

the-algorithm

Source code for Twitter's Recommendation Algorithm

the-pile

tree_influence

Influence Estimation for Gradient-Boosted Decision Trees

won-j.github.io

my home page