Alternatives and similar repositories for sae-for-vlm:

Users that are interested in sae-for-vlm are comparing it to the libraries listed below

• ethanlshen / HierNet
  Code for "Are “Hierarchical” Visual Representations Hierarchical?" in NeurIPS Workshop for Symmetry and Geometry in Neural Representation…
  ☆20Updated last year
• jiaangli / VLCA
  Do Vision and Language Models Share Concepts? A Vector Space Alignment Study
  ☆14Updated 5 months ago
• kdariina / CLIP-not-BoW-unimodally
  Code for "CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally"
  ☆11Updated 2 months ago
• lapisrocks / DiscreteAdversarialDistillation
  [NeurIPS 2023] Official repository for "Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models"
  ☆12Updated 10 months ago
• brendel-group / clip-ood
  Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)
  ☆11Updated 8 months ago
• amitakamath / vl_text_encoders_are_bottlenecks
  Code and datasets for "Text encoders are performance bottlenecks in contrastive vision-language models". Coming soon!
  ☆11Updated last year
• Stanford-AIMI / RaVL
  [NeurIPS 2024] RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
  ☆20Updated 5 months ago
• hammoudhasan / DiffCLIP
  Official Implementation of DiffCLIP: Differential Attention Meets CLIP
  ☆26Updated last month
• princeton-pli / VLM_S2H
  Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
  ☆13Updated 3 months ago
• d-ailin / CLIP-Guided-Decoding
  ☆17Updated 9 months ago
• BatsResearch / ex2
  If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
  ☆16Updated last year
• james-oldfield / muMoE
  [NeurIPS'24] Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  ☆30Updated 7 months ago
• Vinoground / Vinoground
  ☆10Updated 6 months ago
• ExplainableML / fomo_in_flux
  Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]
  ☆54Updated 4 months ago
• yossigandelsman / second_order_lens
  Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"
  ☆39Updated 5 months ago
• SprocketLab / roboshot
  ☆22Updated 11 months ago
• tianyi-lab / R2-T2
  Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"
  ☆15Updated last month
• fredzzhang / atlas
  Official PyTorch implementation for NeurIPS'24 paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"
  ☆19Updated 2 months ago
• ivonajdenkoska / tulip
  [ICLR 2025] Official code repository for "TULIP: Token-length Upgraded CLIP"
  ☆25Updated 2 months ago
• jonkahana / CLIPPR
  An official PyTorch implementation for CLIPPR
  ☆29Updated last year
• ilkerkesen / ViLMA
  ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models (ICLR 2024, Official Implementation)
  ☆16Updated last year
• yuhui-zh15 / C3
  Official implementation of "Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data" (ICLR 2024)
  ☆30Updated 6 months ago
• kaist-ami / BEAF
  [ECCV’24] Official repository for "BEAF: Observing Before-AFter Changes to Evaluate Hallucination in Vision-language Models"
  ☆19Updated last month
• uclaml / PDE
  Official repo of Progressive Data Expansion: data, code and evaluation
  ☆28Updated last year
• MeganTj / multimodal_alignment
  ☆11Updated last month
• visipedia / ssw60
  Sapsucker Woods 60 Audiovisual Dataset
  ☆15Updated 2 years ago
• locuslab / llava-token-compression
  ☆41Updated 5 months ago
• locuslab / T-MARS
  Code for T-MARS data filtering
  ☆35Updated last year
• ytaek-oh / fsc-clip
  [EMNLP 2024] Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
  ☆16Updated 6 months ago
• SriramB-98 / vit-decompose
  ☆22Updated 3 months ago