Discussion on "Beyond Injectivity: What the ‘Language Models are Injective’ Paper Reveals—and What It Overlooks"

Gerard Sans · 2025-11-04T23:25:52.563Z

If you’ve been anywhere near AI Twitter or arXiv this week, you’ve likely encountered a striking claim: Transformer language models are injective. Different prompts almost surely lead to different hidden states. Not only that, but we can exactly reco...

Discussion on "Beyond Injectivity: What the ‘Language Models are Injective’ Paper Reveals—and What It Overlooks" | Hashnode

Search Hashnode

Beyond Injectivity: What the ‘Language Models are Injective’ Paper Reveals—and What It Overlooks

Responses