Official style files for papers submitted to venues of the Association for Computational Linguistics

NaturalProofs: Mathematical Theorem Proving in Natural Language (NeurIPS 2021 Datasets & Benchmarks)

AANN project by (KM)^2

Open Source Neural Machine Translation and (Large) Language Models in PyTorch

Anki's shared backend and web components, and the Qt frontend

Dataset of of Social Artifacts from Different Indian Geographical Subcultures

Code for Preventing Language Models From Hiding Their Reasoning, which evaluates defenses against LLM steganography.

The boundary of neural network trainability is fractal

CMU Wilderness Multilingual Speech Dataset

Cerberus is an app that reduces the annotation burden of linguists

Materials for "Prompting is not a substitute for probability measurements in large language models" (EMNLP 2023)

Code and data for "A fine-grained comparison of pragmatic language understanding in humans and language models"

Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems, SIGMORPHON 2021

A natural language interface for computers

This repository accompanies the paper "Revisiting the Optimality of Work Lengths"

The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit

2025 AI/ML internship & new graduate job list updated daily

DSPy: The framework for programming—not prompting—language models

Hack Together: RAG Hack | Register, Learn, Hack

A Latex style and template for paper preprints (based on NIPS style)

Course website for CMU 11737 multilingual natural language processing 2023 fall

MIS is a new mathematical object

This repository contains resources for technical coding interviews.

Automated Design of Agentic Systems

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Auto_Jobs_Applier_AI_Agent aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in an tailored way.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…