Preprint
Aug 2026
Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
STAMPlus resolves the trilemma beyond single-target prediction, decoupling autoregressive dialogue from non-autoregressive mask prediction and achieves state-of-the-art segmentation performance, preserves general multimodal instruction following, and reduces 12-category latency.
Jia-Zhen Liu, Mingkuan Feng, Long Chen
· 0 citations