multimodal-interpretability / maiaLinks
Official implementation of MAIA, A Multimodal Automated Interpretability Agent
☆94Updated 3 weeks ago
Alternatives and similar repositories for maia
Users that are interested in maia are comparing it to the libraries listed below
Sorting:
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆163Updated last month
- PyTorch library for Active Fine-Tuning☆95Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Updated 11 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆141Updated 4 months ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆31Updated 6 months ago
- ☆33Updated 10 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆73Updated 4 months ago
- Holistic evaluation of multimodal foundation models☆47Updated last year
- Decomposing and Editing Predictions by Modeling Model Computation☆138Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆184Updated 7 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆40Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆225Updated last week
- ☆198Updated last year
- [ACL'25 Oral] What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆74Updated 4 months ago
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- Sparse autoencoders for vision☆50Updated this week
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆122Updated last year
- ☆135Updated 2 months ago
- ☆100Updated last year
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆31Updated last year
- ☆32Updated 8 months ago
- ☆144Updated last year
- [ACL2025] Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models☆78Updated 5 months ago
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆192Updated 9 months ago
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆90Updated 3 weeks ago
- ☆88Updated last year
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆180Updated 4 months ago
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆53Updated 11 months ago
- Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurI…☆92Updated last year