LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning

ICLR 2026 Conference Submission15582 Authors

Keywords: Vision-Language Model, 3D Scene Understanding, 3D Vision-Language Learning, Post-training

TL;DR: We propose LEO-VL, a 3D VLM equipped with an efficient scene representation to unlock scalability of 3D-VL learning, and propose a novel post-training objective SceneDPO

Abstract: Developing vision-language models (VLMs) capable of understanding 3D scenes has been a longstanding goal in the 3D-VL community. Despite recent progress, 3D VLMs still fall short of their 2D counterparts in capability and robustness. A key bottleneck is that current scene representations struggle to balance performance and efficiency: competitive performance comes at the cost of heavy token overhead, which in turn hampers the scalability of 3D-VL learning. To address this, we propose the condensed feature grid (CFG), an efficient scene representation featuring significantly reduced token overhead and strong perception capability. Building on CFG, we introduce LEO-VL, a 3D VLM trained on 700k 3D-VL data spanning four real-world indoor domains and five tasks such as captioning and dialogue. To enhance the robustness of 3D VLM, we further propose SceneDPO for post-training, which involves contrasts across answers and scenes. LEO-VL achieves state-of-the-art performance on various 3D QA benchmarks, including SQA3D, MSQA, and Beacon3D. Our extensive experiments highlight the efficiency of our representation, the benefit of task and scene diversity, consistent scaling effects, and the advantages of SceneDPO compared to SFT and GRPO. We hope our findings advance the efficiency, scalability, and robustness of future 3D VLMs.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 15582