Automated Evaluation of RAG Systems

HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels

Supercharge Your LLM Application Evaluations 🚀

a gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini

A curated list of Large Language Model with RAG

Forward-Looking Active REtrieval-augmented generation (FLARE)

Evaluation and Tracking for LLM Experiments

Doing simple retrieval from LLM models at various context lengths to measure accuracy

OpenAI + LINE + Vercel = GPT AI Assistant

It will detect the damage done to the car and classify into MINOR, MODERATE and SEVERE

Stable Diffusion web UI

The UI design language and React library for Conversational UI

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

A curated list of resources for Document Understanding (DU) topic

Domain-Generalized Face Anti-Spoofing with Unknown Attacks. ICIP, 2023

MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKU

MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning

Low rank adaptation for Vision Transformer

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

Online Coreset Selection for Rehearsal-based Continual Learning, ICLR 2022

[MIDL 2023] Official Imeplementation of "Making Your First Choice: To Address Cold Start Problem in Vision Active Learning"

Reproducing experimental results of LL4AL [Yoo et al. 2019 CVPR]

Cross-model active contrastive coding

[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"

Background Subtraction based on Decomposition into Low-Rank and Sparse Matrices