SeGDeP introduces a decoupled prompt system that separates semantic identification from spatial grounding in reasoning segmentation. It uses a semantic prompt branch and an independent geometric projection path to produce semantic features and a DETR‑predicted box, which jointly condition a SAM mask decoder. The model achieves high cIoU and gIoU scores while adapting only a small fraction of Qwen3‑VL parameters via LoRA.
arXiv:2606. 17539v1 Announce Type: cross Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging.
arXiv:2609.37283v1 Announce Type: new Abstract: Medical multimodal large language models (MLLMs) are increasingly expected not only to answer clinical questions, but also to localize the visual evide...
arXiv:2606. 03564v2 Announce Type: replace-cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
arXiv:2606. 03564v1 Announce Type: cross Abstract: Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning.
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.
arXiv:2605.17630v3 Announce Type: replace Abstract: Frozen segmentation foundation models often fail when the target class appears in a form that is weakly represented during pretraining. To address...
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
arXiv:2608. 07299v1 Announce Type: cross Abstract: Radiology reports describe clinical observations but do not specify executable segmentation targets.
arXiv:2606. 12830v1 Announce Type: cross Abstract: While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidence acquisition and multi-step visual interaction.
arXiv:2608. 09818v1 Announce Type: cross Abstract: Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding.
The paper introduces MedREAL, a unified framework that aligns linguistic reasoning with spatial grounding for medical visual question answering and segmentation. MedREAL employs Seg Anchored Reasoning Pooling (SARP) to extract semantic evidence from segmentation tokens and a Reasoning-to-Visual (R2V) fusion mechanism to integrate these features into a segmentation pipeline. Using the newly created MedRAVS-13K dataset, MedREAL achieves superior performance, reporting 68.49% gIoU and 70.47% cIoU, and generates evidence masks that consistently match textual diagnoses.
arXiv:2607. 05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception to interleaved visual-language reasoning, often referred to as ``thinking with images''.