Dravid et al. (2023)

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

• Merullo et al. (2022)concept0.762
  Found a single linear projection sufficient to stitch vision model to LLM for VQA and captioning
• Kornblith et al. (2019)concept0.753
  Introduced CKA and observed that model alignment increases with model scale and dataset size
• Zimmermann et al. (2021)concept0.752
  Showed contrastive learning inverts the data generating process; supports claim that contrastive learners recover statistics of underlying world
• Abrini et al. 2025concept0.745
  Recent ToM in AI work cited as emphasizing inference of others' beliefs, contrasted with this paper's self-focus
• Sorscher et al. (2022)concept0.745
  Showed word embeddings of visual concept names can be isometrically mapped to image embeddings, and developed framework for efficient concept extraction
• Yamins et al. (2014)concept0.744
  Showed that performance-optimized neural networks align with biological brain representations in higher visual cortex
• Baker et al. 2017concept0.731
  Reference for ToM modeled through partially observable inference of others' beliefs
• Abdou et al. (2021)concept0.727
  Discovered that color distances in language representations mirror human perceptual distances; reproduced and extended in this paper