EvolvingLMMs-Lab / multimodal-sae
Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.
☆124Updated 2 months ago
Alternatives and similar repositories for multimodal-sae:
Users that are interested in multimodal-sae are comparing it to the libraries listed below
- [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"☆131Updated 4 months ago
- Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models☆75Updated 6 months ago
- [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.☆70Updated 4 months ago
- [ICLR 2025] Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision☆59Updated 8 months ago
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension.☆65Updated 10 months ago
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆63Updated 3 weeks ago
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆69Updated 3 months ago
- Holistic evaluation of multimodal foundation models☆45Updated 7 months ago
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆46Updated 2 months ago
- ☆74Updated 7 months ago
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆161Updated 3 months ago
- Official implementation of "Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation" (CVPR 202…☆25Updated 2 weeks ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆24Updated 4 months ago
- This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.or…☆115Updated 8 months ago
- OpenVLThinker: An Early Exploration to Vision-Language Reasoning via Iterative Self-Improvement☆50Updated last week
- Official PyTorch Implementation for Task Vectors are Cross-Modal☆22Updated 3 months ago
- An open source implementation of CLIP (With TULIP Support)☆113Updated last week
- What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆63Updated last month
- [ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation☆47Updated 3 months ago
- [NAACL 2025 Oral] Multimodal Needle in a Haystack (MMNeedle): Benchmarking Long-Context Capability of Multimodal Large Language Models☆40Updated 3 weeks ago
- ☆49Updated last year
- Codes for Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models☆180Updated 5 months ago
- ☆31Updated 2 months ago
- Official implementation of MAIA, A Multimodal Automated Interpretability Agent☆76Updated 3 weeks ago
- Matryoshka Multimodal Models☆98Updated 2 months ago
- ☆87Updated 6 months ago
- ☆85Updated 3 weeks ago
- official code for "BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning"☆33Updated 2 months ago
- ☆48Updated 4 months ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆65Updated last month