multimodal-interpretability / maiaLinks
Official implementation of MAIA, A Multimodal Automated Interpretability Agent
☆83Updated last month
Alternatives and similar repositories for maia
Users that are interested in maia are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆112Updated last month
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆146Updated 3 weeks ago
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆29Updated 3 months ago
- PyTorch library for Active Fine-Tuning☆87Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- Holistic evaluation of multimodal foundation models☆48Updated 11 months ago
- ☆34Updated 7 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 9 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆70Updated last month
- ☆41Updated last year
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆91Updated 8 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆178Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- Decomposing and Editing Predictions by Modeling Model Computation☆138Updated last year
- ☆142Updated last year
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- [ACL2025] Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models☆77Updated 2 months ago
- ☆83Updated 11 months ago
- Model Stock: All we need is just a few fine-tuned models☆119Updated 10 months ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆53Updated last year
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆113Updated 10 months ago
- Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Ref…☆63Updated 5 months ago
- Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind☆177Updated 10 months ago
- Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurI…☆90Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated 11 months ago
- ☆185Updated last year
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆116Updated last year
- ☆99Updated last year
- X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains☆47Updated 3 months ago
- This is the official repository for the paper "Flora: Low-Rank Adapters Are Secretly Gradient Compressors" in ICML 2024.☆104Updated last year