Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models

Code and data for ACL'25 paper "TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models"

Official implementation of Arctic-TILT, a sub-billion parameter model for efficient Document Understanding.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Python package to augment multilingual data

Python library for computing bias-variance, ambiguity and bias-variance-diversity decompositions

LLM decomposition; few-shot learning (EMNLP 2024)

Benchmarking LLMs via Uncertainty Quantification

Code of "Model-Based Minimum Bayes Risk Decoding for Text Generation" 2024

A library for minimum Bayes risk (MBR) decoding

"cfg_lexicalizer" can convert s-expressed trees to normalized ones, described in the paper ''Grammar as a Foreign Language.'' by Vinyals et al., In Proc of ICLR2015.

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. …

Code that implements efficient knowledge graph extraction from the textual descriptions

REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).

Code for our paper, "Table and Image Generation for Investigating Knowledge of Entities in Pre-trained Vision and Language Models".

RNN-based language models in pytorch

SLAHAN is an implementation of Kamigaito et al., 2020, "Syntactically Look-A-Head Attention Network for Sentence Compression", In Proc. of AAAI2020.

A Unified Library for Parameter-Efficient and Modular Transfer Learning

A tool that locates, downloads, and extracts machine translation corpora