news
Jun 2, 2025 | We are organizing the second version of Emergent Visual Abilities and Limits of Foundation Models (EVAL FoMo 2) at CVPR 2025. |
---|---|
Jun 2, 2025 | We are organizing the Mechanistic Interpretability for Vision workshop at CVPR 2025. |
Jun 1, 2025 | We have done some digging into how multimodal LLMs process visual information. Check out our workshop paper at CVPR 2025 Mechnasitic Interpretability for Vision workshop and our paper at CVPR 2025 XAI4CV. |
Jun 1, 2025 | Check out our ICML 2025 paper on making interpretable sparse wide neurl networks possible leveraging sparsity and mixture-of-experts tricks. |
Jun 1, 2025 | Check out our ICML 2025 paper on concept erasure for diffusion and flow models. |
Jun 1, 2025 | We have a scalable concept erasure solution based on model merging and model arithmetic for diffusion models (which we will present at ICCV 2025). |
Apr 20, 2025 | We have a clever trick to identify (and remove) important neurons for a concept through time steps in duffion models, which we present in ICLR 2025 Scope workshop. |
Sep 28, 2024 | Check out our ECCV 2024 workshop: Emergent Visual Abilities and Limits of Foundation Models. |
Sep 27, 2024 | We have a paper in NeurIPS 24 on evaluating abstract shape recognition in vision-language models. |
Sep 12, 2024 | Was awarded a grant by the Google Gemma 2 Academic Program to do research on GemmaScope |
Aug 12, 2024 | We have a perspective paper on the cognitive revolution in interpreting neural networks. |
Jul 4, 2024 | Check out our ECCV 2024 paper on safe text to image generation. |
Jun 6, 2024 | Check out our paper on guiding the attention of vision transformers. |
Apr 25, 2024 | Invited speaker at Trustworthy Multimodal Learning with Foundation Models at British Machine Vision Assosication. Talk title: Understanding Foundation Models through Interpretation and Evaluation. |