Skip to content
arXiv cs.CV · Papers

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

arXiv:2608.02791v1 Announce Type: new Abstract: MLLM-based segmentation faces a core segmentation trilemma: high segmentation performance, preserved dialogue ability, and fast inference. Embedding-prediction methods may disrupt language modeling through pixel-level objectives, whereas next-token generation is inefficie