PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models

Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlight).

GPT4 based personalized ArXiv paper assistant bot

Codes and data for EMNLP 2022 paper: Analogical Math Word Problems Solving with Enhanced Problem-Solution Association

A guidance language for controlling large language models.

800,000 step-level correctness labels on LLM solutions to MATH problems

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)

An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of Human Behavior

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Real or Fake Text? Evaluation criteria for human-written and computer-generated text through the gamification of annotation. Published in EMNLP 2020.

Thesis proposal document

This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Can Be Injected in Language Models."

The newly improved planner (and more) in the cloud.

Repository that lets you run an automated planner as a service on heroku.

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

Extensions to torch distributions

A benchmark for understanding and evaluating rationales: http:https://www.eraserbenchmark.com/

High-accuracy NLP parser with models for 11 languages.

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

Examples of how to create colorful, annotated equations in Latex using Tikz.

程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).

Collection of NLP model explanations and accompanying analysis tools

Code for Evaluating Explanations for Reading Comprehension with Realistic Counterfactuals.

A curated list of pretrained sentence and word embedding models

replication code for EMNLP 2021 paper

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.