Using open source LLMs to build synthetic datasets for direct preference optimization

The code of several works on oimo.io/works

Generative Agents: Interactive Simulacra of Human Behavior

🐥 Code and Dataset for our EMNLP 2022 paper - "ProsocialDialog: A Prosocial Backbone for Conversational Agents"

Code and Data for ACL 2019 "Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention"

Tutorials for reinforcement learning in PyTorch and Gym by implementing a few of the popular algorithms. [IN PROGRESS]

데이터 분석가와 개발자를 위한 오픈소스 플랫폼으로 뉴스데이터와 타 분야 데이터를 융합할 수 있는 분석 및 개발 환경을 제공합니다. _Open source platform for data analysts and developers, Providing an analysis and development environment that can fuse news…

Code for the paper "Language Models are Unsupervised Multitask Learners"

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

Flickr-Faces-HQ Dataset (FFHQ)

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

task-oriented dialogue system, especially for LLM, contain subtask: (1) intent-detection (2) slot filling (3) dialogue state tracking

Official repository for "SimpleTOD: A Simple Language Model for Task-Oriented Dialogue"

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…

Data augmentation for NLP

A toolkit for Spoken Language Understanding Evaluation (SLUE) benchmark. Refer paper https://arxiv.org/abs/2111.10367 for more details. Official website: https://asappresearch.github.io/slue-toolkit/

Simple text to phones converter for multiple languages

Converts English text to IPA notation

Data and code for the paper "End-to-End Slot Alignment and Recognition for Cross-Lingual NLU" (Accepted to EMNLP 2020)

An evolving list of electronic media data sets used to model mental-health status.

Training and evaluation of the OLISIA cascade system for Dialogue State Tracking (DST) on the MultiWoz dataset which ranked first in the "Speech Aware Dialog Systems Technology Challenge" track of …

code for EXPLORING THE VIABILITY OF SYNTHETIC AUDIO DATA FOR AUDIO-BASED DIALOGUE STATE TRACKING

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

This is the Pytorch implementation of our work: BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking, ACL 2023.

AAAI 2021: "UBAR: Towards Fully End-to-End Task-Oriented Dialog System with GPT-2"