[NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
☆72Nov 27, 2025Updated 3 months ago
Alternatives and similar repositories for sae-for-vlm
Users that are interested in sae-for-vlm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12Oct 17, 2024Updated last year
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆101Nov 30, 2025Updated 3 months ago
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆191Sep 26, 2025Updated 5 months ago
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.☆19Jan 28, 2026Updated last month
- Official implementation of CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation☆12Dec 5, 2025Updated 3 months ago
- A framework that allows you to apply Sparse AutoEncoder on any models☆51Jul 11, 2025Updated 8 months ago
- ☆18Jun 20, 2025Updated 9 months ago
- ☆12Aug 8, 2024Updated last year
- Self-supervised adversarial masking for point clouds☆11Jul 12, 2023Updated 2 years ago
- Code repository for "Post-pre-training for Modality Alignment in Vision-Language Foundation Models" (CVPR2025)☆38Jul 25, 2025Updated 7 months ago
- Implementation of "Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning" WACV 2023.☆26Sep 6, 2023Updated 2 years ago
- ☆26Aug 24, 2022Updated 3 years ago
- 🔥 [NeurIPS 2025] Official implementation of "Generate, but Verify: Reducing Visual Hallucination in Vision-Language Models with Retrospe…☆54Jan 22, 2026Updated 2 months ago
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- Official repository for the ICCV 25 paper: QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generati…☆21Jul 29, 2025Updated 7 months ago
- If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions☆17Apr 4, 2024Updated last year
- Metric Adversarial Attacks and Defense☆19Sep 28, 2021Updated 4 years ago
- ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]☆21Aug 21, 2025Updated 7 months ago
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models☆75May 31, 2025Updated 9 months ago
- [CVPR 2025 Highlight] Official Pytorch codebase for paper: "Assessing and Learning Alignment of Unimodal Vision and Language Models"☆58Aug 15, 2025Updated 7 months ago
- TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs☆24Sep 21, 2025Updated 6 months ago
- Official repository for Targeted Unlearning with Single Layer Unlearning Gradient (SLUG), ICML 2025☆15Aug 10, 2025Updated 7 months ago
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆30Jun 5, 2025Updated 9 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆56Sep 22, 2025Updated 6 months ago
- [NeurIPS'25] SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning☆40Oct 14, 2025Updated 5 months ago
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆12Sep 11, 2025Updated 6 months ago
- ✍️ A browser add-on (Firefox, Chrome, Thunderbird) that allows you to autocorrect common text sequences and convert text characters to a …☆12Feb 9, 2026Updated last month
- Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024☆18Mar 25, 2025Updated 11 months ago
- XL-VLMs: General Repository for eXplainable Large Vision Language Models☆47Sep 8, 2025Updated 6 months ago
- ☆13Jan 22, 2025Updated last year
- ☆41Jan 19, 2026Updated 2 months ago
- Jupyter Notebooks from book UNDERSTANDING DEEP LEARNING (Prof Simon Prince) that I could solve.☆12Mar 20, 2024Updated 2 years ago
- PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022☆28May 6, 2023Updated 2 years ago
- Constrained learning using boxes for event-event relation extraction☆12Aug 5, 2022Updated 3 years ago
- MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments☆13Jul 8, 2024Updated last year
- ☆28Feb 27, 2025Updated last year
- ☆157Dec 30, 2025Updated 2 months ago
- Crosslingual Reasoning through Test-Time Scaling☆19May 13, 2025Updated 10 months ago
- [ICLR 2025] See What You Are Told: Visual Attention Sink in Large Multimodal Models☆99Feb 16, 2025Updated last year