OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Official Implementation for NeurIPS'23 paper Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

[TAC 2024] SVFAP: Self-supervised Video Facial Affect Perceiver

Official PyTorch implementation for "Large Language Diffusion Models"

Simple, fast unsupervised word aligner

Official Repo for the Paper "AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text"

A dual-stream transformer-based turn-taking model

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

code for submission https://www.arxiv.org/abs/2502.12317

OSUM: Open Speech Understanding Model, open-sourced by ASLP@NPU.

Code and Results for "Universals of word order reflect optimization of grammars for efficient communication"

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

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

The Zurich Dependency Parser for German

Overview of German Text Simplification Resources, e.g., DEplain corpus, web harvester, alignment methods.

Repository to accompany the SIGDIAL 2024 paper: Elaborative Simplification for German-language Texts

A* CCG Parser with a Supertag and Dependency Factored Model

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

Code for Arehalli, Dillon & Linzen (2022) "Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities"

Unsupervised Sentence Simplification via Dependency Parsing

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.