[NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
☆64Nov 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
Sorting:
- [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"☆95Nov 30, 2025Updated 3 months ago
- [NeurIPS'25] SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning☆40Oct 14, 2025Updated 4 months ago
- The official implementation of Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion [AAAI'2…☆15Feb 2, 2026Updated last month
- TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs☆23Sep 21, 2025Updated 5 months ago
- Official repository for Targeted Unlearning with Single Layer Unlearning Gradient (SLUG), ICML 2025☆15Aug 10, 2025Updated 6 months ago
- Self-supervised adversarial masking for point clouds☆11Jul 12, 2023Updated 2 years ago
- ☆12Oct 17, 2024Updated last year
- [ICCV 2025] Auto Interpretation Pipeline and many other functionalities for Multimodal SAE Analysis.☆183Sep 26, 2025Updated 5 months ago
- MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments☆13Jul 8, 2024Updated last year
- ☆13Jan 22, 2025Updated last year
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆12Sep 11, 2025Updated 5 months ago
- Code and dataset for the ICLR 2024 paper "Thought Propagation: An analogical Approach to Complex Reasoning with Large Language Models."☆17Mar 4, 2024Updated last year
- [NeurIPS 2024] CoSy is an automatic evaluation framework for textual explanations of neurons.☆19Jan 28, 2026Updated last month
- ☆16May 13, 2025Updated 9 months ago
- Self-training LLaVA for medical☆16Nov 3, 2024Updated last year
- ☆41Jun 9, 2025Updated 8 months ago
- ☆18Jun 20, 2025Updated 8 months ago
- [ECCV 2024 Oral] Official implementation of the paper "PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers"☆18Jul 3, 2025Updated 7 months ago
- XL-VLMs: General Repository for eXplainable Large Vision Language Models☆46Sep 8, 2025Updated 5 months ago
- ☆18Nov 8, 2024Updated last year
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆17Mar 31, 2025Updated 11 months ago
- official implementation of "CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusi…☆18Sep 5, 2024Updated last year
- [NeurIPS 2025] More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models☆75May 31, 2025Updated 9 months ago
- ☆14Jul 25, 2020Updated 5 years ago
- Crosslingual Reasoning through Test-Time Scaling☆19May 13, 2025Updated 9 months ago
- Code for "Preference Tuning For Toxicity Mitigation Generalizes Across Languages." Paper accepted at Findings of EMNLP 2024☆18Mar 25, 2025Updated 11 months ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆42Nov 15, 2024Updated last year
- If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions☆17Apr 4, 2024Updated last year
- ABC: Achieving Better Control of Multimodal Embeddings using VLMs [TMLR2025]☆20Aug 21, 2025Updated 6 months ago
- 🔥 [NeurIPS 2025] Official implementation of "Generate, but Verify: Reducing Visual Hallucination in Vision-Language Models with Retrospe…☆52Jan 22, 2026Updated last month
- Implementation of "Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning" WACV 2023.☆26Sep 6, 2023Updated 2 years ago
- Implementation of PatchSAE as presented in "Sparse autoencoders reveal selective remapping of visual concepts during adaptation"☆30Oct 31, 2025Updated 4 months ago
- Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…☆22Nov 8, 2023Updated 2 years ago
- Metric Adversarial Attacks and Defense☆19Sep 28, 2021Updated 4 years ago
- Code repository for "Post-pre-training for Modality Alignment in Vision-Language Foundation Models" (CVPR2025)☆38Jul 25, 2025Updated 7 months ago
- [CVPR 2025] Offical implementation of the paper "Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters The…☆31Feb 27, 2025Updated last year
- E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models☆39Jan 5, 2026Updated last month
- Modality Gap–Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models☆51Feb 23, 2026Updated last week
- [NeurIPS 24] A new training and evaluation framework for learning interpretable deep vision models and benchmarking different interpretab…☆29Jun 5, 2025Updated 8 months ago