Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Jiazhen, Feng, Mingkuan, Chen, Long
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.00395
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917113843679232
author Liu, Jiazhen
Feng, Mingkuan
Chen, Long
author_facet Liu, Jiazhen
Feng, Mingkuan
Chen, Long
contents Integrating segmentation into Multimodal Large Language Models (MLLMs) presents a core trilemma: simultaneously preserving dialogue ability, achieving high segmentation performance, and ensuring fast inference. Prevailing paradigms are forced into a compromise. Embedding prediction methods introduce a conflicting pixel-level objective that degrades the MLLM's general dialogue abilities. The alternative, next-token prediction, reframes segmentation as an autoregressive task, which preserves dialogue but forces a trade-off between poor segmentation performance with sparse outputs or prohibitive inference speeds with rich ones. We resolve this trilemma with all-mask prediction, a novel paradigm that decouples autoregressive dialogue generation from non-autoregressive mask prediction. We present STAMP: Simultaneous Textual All-Mask Prediction, an MLLM that embodies this paradigm. After generating a textual response, STAMP predicts an entire segmentation mask in a single forward pass by treating it as a parallel "fill-in-the-blank" task over image patches. This design maintains the MLLM's dialogue ability by avoiding conflicting objectives, enables high segmentation performance by leveraging rich, bidirectional spatial context for all mask tokens, and achieves exceptional speed. Extensive experiments show that STAMP significantly outperforms state-of-the-art methods across multiple segmentation benchmarks, providing a solution that excels in dialogue, segmentation, and speed without compromise.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
Liu, Jiazhen
Feng, Mingkuan
Chen, Long
Computer Vision and Pattern Recognition
Integrating segmentation into Multimodal Large Language Models (MLLMs) presents a core trilemma: simultaneously preserving dialogue ability, achieving high segmentation performance, and ensuring fast inference. Prevailing paradigms are forced into a compromise. Embedding prediction methods introduce a conflicting pixel-level objective that degrades the MLLM's general dialogue abilities. The alternative, next-token prediction, reframes segmentation as an autoregressive task, which preserves dialogue but forces a trade-off between poor segmentation performance with sparse outputs or prohibitive inference speeds with rich ones. We resolve this trilemma with all-mask prediction, a novel paradigm that decouples autoregressive dialogue generation from non-autoregressive mask prediction. We present STAMP: Simultaneous Textual All-Mask Prediction, an MLLM that embodies this paradigm. After generating a textual response, STAMP predicts an entire segmentation mask in a single forward pass by treating it as a parallel "fill-in-the-blank" task over image patches. This design maintains the MLLM's dialogue ability by avoiding conflicting objectives, enables high segmentation performance by leveraging rich, bidirectional spatial context for all mask tokens, and achieves exceptional speed. Extensive experiments show that STAMP significantly outperforms state-of-the-art methods across multiple segmentation benchmarks, providing a solution that excels in dialogue, segmentation, and speed without compromise.
title Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.00395