Propietario

ExplainableML

4 repositorios indexados · Ver en GitHub

• sae-for-vlm

  [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

  Python · 96 estrellas

• EgoCVR

  [ECCV 2024] EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

  Python · 41 estrellas

• SOTAlign

  [ICML 2026] SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport

  Python · 11 estrellas

• SAE-TM

  [ICML 2026] Sparse Autoencoders are Topic Models

  Jupyter Notebook · 10 estrellas