Pinned Loading

1. Digital-Dermatology/SelfClean Digital-Dermatology/SelfClean Public

   [NeurIPS 2024] 🧼🔎 A holistic self-supervised data cleaning strategy to detect irrelevant samples, near duplicates and label errors.

   Python 36 2

2. Digital-Dermatology/SelfClean-Revised-Benchmarks Digital-Dermatology/SelfClean-Revised-Benchmarks Public

   [ML4H 2023] 🧼🔎 SelfClean revised versions of benchmark datasets for more reliable performance estimation.

   9

3. mlbio-epfl/STRUCTURE mlbio-epfl/STRUCTURE Public

   [NeurIPS 2025] TL;DR: Aligning pretrained unimodal models with the proposed framework using limited paired data yields ~52% gains in cross-modality zero-shot classification and ~92% in retrieval.

   Python 10 1

4. mlbio-epfl/Aristotelian mlbio-epfl/Aristotelian Public

   We revisit the Platonic Representation Hypothesis using calibrated representational similarity metrics with statistical guarantees.

   Python 11 1