Stars
A framework for few-shot evaluation of language models.
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
Robust recipes to align language models with human and AI preferences
ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.
Course resources and notes for the ESSLLI 2023 course on neural symbolic methods.
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
A high-throughput and memory-efficient inference and serving engine for LLMs
MiniWoB++: a web interaction benchmark for reinforcement learning
Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
A prize for finding tasks that cause large language models to show inverse scaling
Google Research
Code for the paper: Evaluating Relaxations of Logic for Neural Networks: A Comprehensive Study (IJCAI 2021)
Probabilistic Circuits from the Juice library
Graph4nlp is the library for the easy use of Graph Neural Networks for NLP. Welcome to visit our DLG4NLP website (https://dlg4nlp.github.io/index.html) for various learning resources!
Accurately generate all possible forms of an English word e.g "election" --> "elect", "electoral", "electorate" etc.
Implementation of our ACL 2020 paper: Structured Tuning for Semantic Role Labeling
UnQovering Stereotyping Biases via Underspecified Questions - EMNLP 2020 (Findings)
VerbNet semantic parser and related utilities
Latex code for making neural networks diagrams
Materials from the ACL 2018 tutorial on neural semantic parsing