Papers with constrained projection

1 papers
Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding (2026.acl-long)

Copied to clipboard

Challenge: Large Vision–Language Models (LVLMs) integrate visual perception with language understanding, but how vision information contributes to the model’s decoding process remains under-explored.
Approach: They propose a simple training-free decoding method that guides text generation in Large Vision–Language Models by Referencing Vision Tokens.
Outcome: The proposed method leverages the semantic information embedded within vision tokens by projecting it into the text token distribution.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations