Hyesu Lim
  • Home
  • Publications
  • Contact
  • CV
  • Writing
    • Welcome to My New Site
  • Publications
    • VisualScratchpad: Grounding Visual Concepts in Large Vision Language Models
    • ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
    • CytoSAE: Interpretable Cell Embeddings for Hematology
    • Sparse Autoencoders Reveal Selective Remapping of Visual Concepts During Adaptation
    • Towards Calibrated Robust Fine-Tuning of Vision-Language Models
    • TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
    • AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain

Sparse Autoencoders Reveal Selective Remapping of Visual Concepts During Adaptation

April 1, 2025·
Hyesu Lim
,
Jinho Choi
,
Jaegul Choo
,
Steffen Schneider
· 0 min read
PDF patchsae fastsae (generalized) Project poster, slides & video
projects interpretability
Last updated on April 1, 2025
Sparse Autoencoders Domain Adaptation Vision Models
← CytoSAE: Interpretable Cell Embeddings for Hematology October 1, 2025
Towards Calibrated Robust Fine-Tuning of Vision-Language Models December 1, 2024 →

Made with Hugo Blox. Duplicate this template →