RewardBench: the first evaluation tool for reward models.

The Universe of Evaluation. All about the evaluation for LLMs.

The Universe of Data. All about data, data science, and data engineering

[ACMMM 2021] PyTorch implementation for "Mining Latent Structures for Multimedia Recommendation"

Generate textbook-quality synthetic LLM pretraining data

A high-throughput and memory-efficient inference and serving engine for LLMs

코딩 테스트 스터디

This repository provides a reference implementation of gOCCF: Graph-Theoretic One-Class Collaborative Filtering Based on Uninteresting Items (AAAI 2018).

This repository provides a reference implementation of ASiNE: Adversarial Signed Network Embedding (SIGIR 2020).

HMLET (Hybrid-Method-of-Linear-and-non-linEar-collaborative-filTering-method)