# CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark

arXiv: https://arxiv.org/abs/2605.18621 · HTML: https://mlsanity.com/paper/2605.18621/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 28 of 28)

- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Ferret: Refer and Ground Anything Anywhere at Any Granularity](https://mlsanity.com/paper/2310.07704/) (2023)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Osprey: Pixel Understanding with Visual Instruction Tuning](https://mlsanity.com/paper/2312.10032/) (2023)
- [Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors](https://mlsanity.com/paper/2505.24625/) (2025)
- [HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation](https://mlsanity.com/paper/2502.09838/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM](https://mlsanity.com/paper/2501.00599/) (2024)
- [EgoHumans: An Egocentric 3D Multi-Human Benchmark](https://mlsanity.com/paper/2305.16487/) (2023)
- [BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation](https://mlsanity.com/paper/2203.02533/) (2022)
- [Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception](https://mlsanity.com/paper/2403.02969/) (2024)
- [MMPTRACK: Large-scale Densely Annotated Multi-camera Multiple People Tracking Benchmark](https://mlsanity.com/paper/2111.15157/) (2021)
- [ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives](https://mlsanity.com/paper/2411.19083/) (2024)
- [PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity](https://mlsanity.com/paper/2510.23603/) (2025)
- [Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels](https://mlsanity.com/paper/2304.10539/) (2023)
- [Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2501.04670/) (2025)
- [MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation](https://mlsanity.com/paper/2503.18135/) (2025)
- [MessyTable: Instance Association in Multiple Camera Views](https://mlsanity.com/paper/2007.14878/) (2020)
- [IDMR: Towards Instance-Driven Precise Visual Correspondence in Multimodal Retrieval](https://mlsanity.com/paper/2504.00954/) (2025)
- [Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset](https://mlsanity.com/paper/2508.11058/) (2025)
- [LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation](https://mlsanity.com/paper/2604.11789/) (2026)
- [VICI: VLM-Instructed Cross-view Image-localisation](https://mlsanity.com/paper/2507.04107/) (2025)

## Built on by (most cited first, 3 of 3)

- [InstructSAM: Segment Any Instance with Any Instructions](https://mlsanity.com/paper/2605.26102/) (2026)
- [HumanPhys: A Human-Centric Physical-World Perception Benchmark for Real-World Visual Reasoning](https://mlsanity.com/paper/2610.14679/) (2026)
- [Frame Evidence:A Benchmark for Reference Frames and Visual Evidence in Multi-Image Spatial Reasoning](https://mlsanity.com/paper/2610.19564/) (2026)

## Abstract (arXiv)

Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in cross-view reasoning remains limited by three major gaps: the scarcity of large-scale well-annotated training data, the lack of comprehensive benchmarks for systematic evaluation, and the absence of explicit alignment mechanisms that establish object-level consistency across views. To address these gaps, we thoroughly develop CrossView Suite across three coordinated components: CrossViewSet, CrossViewBench, and CrossViewer. Firstly, we introduce a multi-agent data engine to meticulously curate a large-scale, high-quality cross-view instruction dataset, termed CrossViewSet, covering 17 fine-grained task types with 1.6M samples. Second, we meticulously create a scene-disjoint CrossViewBench to comprehensively assess the cross-view spatial understanding capability of an MLLM, evaluating it across various aspects. Finally, we propose CrossViewer, a progressive three-stage framework for cross-view spatial reasoning in MLLMs, following a Perception -> Alignment -> Reasoning paradigm. Our method equips an adaptive spatial region tokenizer to capture fine-grained object representations, and then aligns the multi-view objects explicitly, and thus fuses aligned features for boosting the cross-view inference capacity for MLLMs. Extensive experiments and analyses show that large-scale training data, systematic evaluation, and explicit cross-view alignment are all critical for advancing MLLMs from single-view perception toward real-world spatial intelligence. The project page is available at https://github.com/Thinkirin/Crossview-Suite.