ResearcharXiv AI / CL
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners

Summary
On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning.
Original Article
Captured source content or English translation, normalized into this reading format.
This story does not yet have captured source text. Open the source link to read it.
Region
Global
Heat Score
81
Category
Research
Language
en
