Login / Signup

Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3.5's Abilities in Regard to Recognizing and Generating ASCII-Art Are Not Totally Lacking.

David Bayani
Published in: CoRR (2023)
Keyphrases
  • cross modal
  • multi modal
  • text retrieval
  • image understanding