mlsanityData to 14 Oct 2026

NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation

arXiv 2511.06651 ↗First posted 10 Nov 2025cs.CVcited by 0

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

In this study, we propose NOVO (NO text, Visual-Only prompts), a novel framework that bridges vision-language models (VLMs) and segmentation models through visual-only prompts. Unlike prior approaches that feed text-derived SEG token embeddings into segmentation models, NOVO instead generates a coarse mask and point prompts from the VLM output. These visual prompts are compatible with the Segment Anything Model (SAM), preserving alignment with its pretrained capabilities. To further enhance boundary quality and enable instance-level segmentation, we introduce a training-free refinement module that reduces visual artifacts and improves the quality of segmentation masks. We also present RISeg, a new benchmark comprising 918 images, 2,533 instance-level masks, and diverse reasoning queries to evaluate this task. Experiments demonstrate that NOVO achieves state-of-the-art performance across multiple metrics and model sizes, demonstrating its effectiveness and scalability in reasoning segmentation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 4 of its 33 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

4 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought4 Jun
  2. 2023LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model28 Dec

Other references · 2

  1. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  2. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation
  2. 2026Reason Twice: Segmentation via Candidate Discovery and Comparative Reasoning
  3. 2026SeGDeP: Semantic- and Geometric-Aware Decoupled Prompts for Reasoning Segmentation
  4. 2025Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
  5. 2024PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation
  6. 2026DR2Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models
  7. 2025LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation
  8. 2024LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning