Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

arXiv:2607.24651 · cs.CV, cs.CL, cs.IR · Submitted 2026-07-27 · Read on arXiv

cs.CV, cs.CL, cs.IR

Submitted: 2026-07-27

Updated: 2026-11-17

Code: https://github.com/hiyouga/EasyR1

Terminology

Sources

Related papers