5LLMs can reduce their bias in multi-turn conversations (opens in new tab)(b-score.github.io)5taesiri10mo ago0
6Understanding Generative AI Capabilities in Everyday Image Editing Tasks (opens in new tab)(arxiv.org)5taesiri10mo ago1
7Hot prompting boosts LLM accuracy with fact highlights (opens in new tab)(twitter.com)4taesiri1y ago0
8Hot: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs (opens in new tab)(arxiv.org)4taesiri1y ago1
9ZeroBench: An Impossible Visual Benchmark for Contemporary LMMs (opens in new tab)(arxiv.org)9taesiri1y ago3
14Planaritify – My iOS game about planar graphs, made in one day (opens in new tab)(itunes.apple.com)6taesiri8y ago1
