EvolvingLMMs-Lab / multimodal-sae
Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
☆106Updated last month
Alternatives and similar repositories for multimodal-sae:
Users that are interested in multimodal-sae are comparing it to the libraries listed below
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆63Updated 9 months ago
- ☆73Updated 6 months ago
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆60Updated last month
- Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models☆74Updated 5 months ago
- [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.☆64Updated 3 months ago
- ☆38Updated 3 months ago
- [ICLR 2025] Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision☆59Updated 7 months ago
- ☆48Updated last week
- [CVPR2025] Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models☆136Updated this week
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆91Updated this week
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆67Updated 2 months ago
- [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"☆130Updated 3 months ago
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆74Updated 6 months ago
- MATH-Vision dataset and code to measure Multimodal Mathematical Reasoning capabilities.☆87Updated this week
- ☆73Updated this week
- Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)☆52Updated this week
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆158Updated 2 months ago
- ☆65Updated last month
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆63Updated this week
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆49Updated 4 months ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆33Updated last month
- [NAACL 2025] Multimodal Needle in a Haystack (MMNeedle): Benchmarking Long-Context Capability of Multimodal Large Language Models☆38Updated 2 weeks ago
- [ICLR2025] DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models☆102Updated last week
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆44Updated last month
- Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 202…☆23Updated this week
- [NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"☆115Updated last year
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆38Updated 2 months ago
- ☆28Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆140Updated 4 months ago
- This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.or…☆116Updated 8 months ago