💫 Industrial-strength Natural Language Processing (NLP) in Python

Optimize prompts, code, and more with AI-powered Reflective Optimization

Tools for studying developmental interpretability in neural networks.

Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)

A fast, effective data attribution method for neural networks in PyTorch

Exploration of automated dataset selection approaches at large scales.

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

AI Logging for Interpretability and Explainability🔬

Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

AllenAI's post-training codebase

A framework for few-shot evaluation of language models.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets

Open clone of OpenAI's unreleased WebText dataset scraper. This version uses pushshift.io files instead of the API for speed.

🏡 GitHub Pages template for personal academic homepage

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

Collections of CS PhD Application Fee Waivers of schools in North America

This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"

ViExam is the comprehensive Vietnamese multimodal exam benchmark with 2,548 questions across 7 domains, designed to evaluate Vision-Language Models’ reasoning with integrated text–visual content. I…

Code for the Molmo Vision-Language Model

A curated collection of resources focused on the Mechanistic Interpretability (MI) of Large Multimodal Models (LMMs). This repository aggregates surveys, blog posts, and research papers that explor…

[NAACL 2025 Oral] From redundancy to relevance: Enhancing explainability in multimodal large language models