multimodal-interpretability / maiaLinks
Official implementation of MAIA, A Multimodal Automated Interpretability Agent
☆86Updated 2 months 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.☆148Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- PyTorch library for Active Fine-Tuning☆89Updated 6 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 9 months ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆30Updated 3 months ago
- Holistic evaluation of multimodal foundation models☆48Updated last year
- ☆34Updated 7 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆179Updated 2 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Decomposing and Editing Predictions by Modeling Model Computation☆138Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆53Updated last year
- Sparse autoencoders for vision☆39Updated last week
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆70Updated 2 months ago
- ☆142Updated last year
- ☆41Updated last year
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆28Updated 4 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆177Updated 4 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆91Updated 9 months ago
- [ACL2025] Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models☆77Updated 2 months ago
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆118Updated last year
- ☆133Updated last year
- ☆100Updated last year
- Official Code Repository for EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents (COLM 2024)☆35Updated last year
- Model Stock: All we need is just a few fine-tuned models☆122Updated 2 weeks ago
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory☆72Updated 3 months ago
- Tree prompting: easy-to-use scikit-learn interface for improved prompting.☆40Updated last year
- ☆85Updated last year
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- [ACL'25 Oral] What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆71Updated 2 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆177Updated 11 months ago