multimodal-interpretability / maia
Official implementation of MAIA, A Multimodal Automated Interpretability Agent
☆78Updated last month
Alternatives and similar repositories for maia:
Users that are interested in maia are comparing it to the libraries listed below
- Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆127Updated 3 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 5 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆162Updated last week
- This repository is maintained to release dataset and models for multimodal puzzle reasoning.☆81Updated 2 months ago
- Holistic evaluation of multimodal foundation models☆47Updated 8 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆65Updated 10 months ago
- ☆31Updated 3 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆70Updated 3 weeks ago
- Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models☆75Updated 7 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆64Updated 3 months ago
- ☆41Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- [ACL 2024 Findings & ICLR 2024 WS] An Evaluator VLM that is open-source, offers reproducible evaluation, and inexpensive to use. Specific…☆67Updated 7 months ago
- ☆96Updated 9 months ago
- ☆26Updated 8 months ago
- [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.☆70Updated 4 months ago
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆63Updated last month
- Official implementation of the paper "MMInA: Benchmarking Multihop Multimodal Internet Agents"☆42Updated last month
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆67Updated last month
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆165Updated 3 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- Official Code Repository for EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents (COLM 2024)☆29Updated 9 months ago
- Official PyTorch Implementation for Task Vectors are Cross-Modal☆22Updated 4 months ago
- ☆140Updated 11 months ago
- Official implementation of FIND (NeurIPS '23) Function Interpretation Benchmark and Automated Interpretability Agents☆49Updated 7 months ago
- Code for Heima☆40Updated this week
- Model Stock: All we need is just a few fine-tuned models☆113Updated 7 months ago
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆48Updated 4 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆47Updated 2 months ago
- ☆48Updated last year