-
Sungkyunkwan University
- Seoul, South Korea
- https://sites.google.com/view/minjinchoi
Highlights
- Pro
Stars
How to Index Item IDs for Recommendation Foundation Models
[CIKM 2024] Do We Really Need Graph Convolution During Training? Light Post-Training Graph-ODE for Efficient Recommendation
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
Source code for our LBR paper "Closed-Form Models for Collaborative Filtering with Side-Information" published at RecSys 2020.
The official repository for MGFiD (NAACL 2024 Findings)
An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention, AAAI-24
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Learning to Tokenize for Generative Retrieval (NeurIPS 2023)
[WWW 2024] The official repo for paper "Scalable and Effective Generative Information Retrieval".
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
Machine Learning Engineering Open Book
This is the official code for the EMNLP 2023 paper "GLEN: Generative Retrieval via Lexical Index Learning".
Playing Pokemon Red with Reinforcement Learning
Implementation of Nougat Neural Optical Understanding for Academic Documents
Anserini is a Lucene toolkit for reproducible information retrieval research
[CIKM'23] "Toward a Better Understanding of Loss Functions for Collaborative Filtering"
Forgetting-aware Linear Bias for Attentive Knowledge Tracing
언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.
LLM based autonomous agent that conducts in-depth web research on any given topic
The github repository of paper "Understanding Differential Search Index for Text Retrieval" in ACL2023 Findings..
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.
WSDM'22 Best Paper: Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval