# PRIMA: Multi-Image Vision-Language Models for Reasoning Segmentation

arXiv: https://arxiv.org/abs/2412.15209 · HTML: https://mlsanity.com/paper/2412.15209/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 94 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 12 of 12)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture](https://mlsanity.com/paper/2409.02889/) (2024)
- [LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model](https://mlsanity.com/paper/2312.17240/) (2023)
- [MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models](https://mlsanity.com/paper/2407.17379/) (2024)
- [MMMModal -- Multi-Images Multi-Audio Multi-turn Multi-Modal](https://mlsanity.com/paper/2402.11297/) (2024)

## Built on by (most cited first, 13 of 13)

- [Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs](https://mlsanity.com/paper/2506.21656/) (2025)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [Reasoning Segmentation for Images and Videos: A Survey](https://mlsanity.com/paper/2505.18816/) (2025)
- [Counterfactual Segmentation Reasoning: Diagnosing and Mitigating Pixel-Grounding Hallucination](https://mlsanity.com/paper/2506.21546/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models](https://mlsanity.com/paper/2603.17680/) (2026)
- [EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling](https://mlsanity.com/paper/2604.17087/) (2026)
- [URECA: Unique Region Caption Anything](https://mlsanity.com/paper/2504.05305/) (2025)
- [See-in-Pairs: Reference Image-Guided Comparative Vision-Language Models for Medical Diagnosis](https://mlsanity.com/paper/2506.18140/) (2025)
- [PathMR: Multimodal Visual Reasoning for Interpretable Pathology Diagnosis](https://mlsanity.com/paper/2508.20851/) (2025)
- [DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising](https://mlsanity.com/paper/2603.19216/) (2026)
- [Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning](https://mlsanity.com/paper/2508.00356/) (2025)
- [From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models](https://mlsanity.com/paper/2606.26196/) (2026)

## Abstract (arXiv)

Despite significant advancements in Large Vision-Language Models (LVLMs)' capabilities, existing pixel-grounding models operate in single-image settings, limiting their ability to perform detailed, fine-grained comparisons across multiple images. Conversely, current multi-image understanding models lack pixel-level grounding. Our work addresses this gap by introducing the task of multi-image pixel-grounded reasoning alongside PRIMA, an LVLM that integrates pixel-level grounding with robust multi-image reasoning to produce contextually rich, pixel-grounded explanations. Central to PRIMA is SQuARE, a vision module that injects cross-image relational context into compact query-based visual tokens before fusing them with the language backbone. To support training and evaluation, we curate M4SEG, a new multi-image reasoning segmentation benchmark consisting of ~744K question-answer pairs that require fine-grained visual understanding across multiple images. PRIMA outperforms state-of-the-art baselines with 7.83% and 11.25% improvements in Recall and S-IoU, respectively. Ablation studies further demonstrate the effectiveness of the proposed SQuARE module in capturing cross-image relationships.