Abrini et al. 2025

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Dravid et al. (2023)concept0.745
  Found Rosetta Neurons — neurons activated by same patterns across diverse vision models
• Merullo et al. (2022)concept0.740
  Found a single linear projection sufficient to stitch vision model to LLM for VQA and captioning
• Baker et al. 2017concept0.736
  Reference for ToM modeled through partially observable inference of others' beliefs
• Abdou et al. (2021)concept0.736
  Discovered that color distances in language representations mirror human perceptual distances; reproduced and extended in this paper
• Yamins et al. (2014)concept0.731
  Showed that performance-optimized neural networks align with biological brain representations in higher visual cortex
• Zimmermann et al. (2021)concept0.723
  Showed contrastive learning inverts the data generating process; supports claim that contrastive learners recover statistics of underlying world
• Sorscher et al. (2022)concept0.721
  Showed word embeddings of visual concept names can be isometrically mapped to image embeddings, and developed framework for efficient concept extraction
• Kornblith et al. (2019)concept0.720
  Introduced CKA and observed that model alignment increases with model scale and dataset size