Heidelberg-NLP / CC-SHAP-VLMLinks
Official code implementation for the paper "Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?"
☆12Updated 5 months ago
Alternatives and similar repositories for CC-SHAP-VLM
Users that are interested in CC-SHAP-VLM are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models☆35Updated 5 months ago
- Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations" (ICLR '25)☆84Updated 3 months ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆39Updated 10 months ago
- Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".☆60Updated last year
- What do we learn from inverting CLIP models?☆55Updated last year
- Do Vision and Language Models Share Concepts? A Vector Space Alignment Study☆16Updated 9 months ago
- Sparse autoencoders for vision☆44Updated this week
- If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions☆17Updated last year
- ☆68Updated 10 months ago
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"☆53Updated last year
- Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."☆46Updated 11 months ago
- Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)☆33Updated last year
- [Arxiv] Aligning Modalities in Vision Large Language Models via Preference Fine-tuning☆88Updated last year
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Models☆80Updated last year
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 10 months ago
- Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…☆58Updated 2 years ago
- [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks☆13Updated 4 months ago
- Code for 'Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality', EMNLP 2022☆30Updated 2 years ago
- Holistic evaluation of multimodal foundation models☆48Updated last year
- [NeurIPS 2023] A faithful benchmark for vision-language compositionality☆84Updated last year
- [NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image feat…☆46Updated last year
- Code for "Enhancing In-context Learning via Linear Probe Calibration"☆36Updated last year
- PyTorch codes for the paper "An Empirical Study of Multimodal Model Merging"☆37Updated last year
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆28Updated last year
- ☆39Updated last year
- Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)☆10Updated last year
- Public code repo for EMNLP 2024 Findings paper "MACAROON: Training Vision-Language Models To Be Your Engaged Partners"☆14Updated 11 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆42Updated last year
- ☆100Updated 5 months ago
- Code for "CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally"☆15Updated 7 months ago