Claude Code Reverse Engineering Itself

[ICLR2025 Spotlight] Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

EvaByte: Efficient Byte-level Language Models at Scale

[ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.

OpenReivew Submission Visualization (ICLR 2024/2025)

GPT4 based personalized ArXiv paper assistant bot

[ICLR 2024] Lemur: Open Foundation Models for Language Agents

Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models

[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild

Paper collection on building and evaluating language model agents via executable language grounding

[EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.

Foundation Architecture for (M)LLMs

An instruction-based benchmark for text improvements.

[ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"

Repo for external large-scale work

Search Engines with Autoregressive Language models

Expanding natural instructions

Collection of advice for prospective and current PhD students

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

MAGMA - a GPT-style multimodal model that can understand any combination of images and language. NOTE: The freely available model from this repo is only a demo. For the latest multimodal and multil…

[EACL'23] MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

Tools for checking ACL paper submissions

(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)

METER: A Multimodal End-to-end TransformER Framework

[ICLR 2022] code for "How Much Can CLIP Benefit Vision-and-Language Tasks?" https://arxiv.org/abs/2107.06383

An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi