Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation

• 类型：arxiv
• 标识：2608.02791
• 链接：https://arxiv.org/abs/2608.02791
• 主分类：rag
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：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.
• 待LLM分类：否
• 标题中文：更优、更强、更快、更广：面向基于 MLLM 分割的结构化全 Mask 预测
• TLDR中文：STAMPlus 解决了超出单目标预测的三难问题，解耦自回归对话与非自回归 mask 预测，取得 SOTA 分割性能，同时保持通用多模态指令遵循能力，并降低 12 类别延迟。
• 来源文件：
• /inbox/tom/_candidates/2026-08-05-agent-rag-longcontext-candidates.json
• [S2 enrich]