# What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models

**Authors:** Tengju Ru, Weitong Lian, Zecong Tang, Zhiheng Liu  
**Lab:** HKU · **Published:** 13 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.23987) · [PDF](https://arxiv.org/pdf/2610.23987) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.23987.html)

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.