The paper introduces the Triplet Incremental Training Framework, a non‑intrusive method that adds 3D geometric awareness to general Vision‑Language Models (VLMs) for autonomous driving. By training on automatically generated (image, depth, QA) triplets, the framework uses an auxiliary depth stream to guide the VLM’s visual backbone while a frozen twin stream prevents semantic drift. The depth branch is removed at inference, yielding zero overhead, and the resulting model outperforms state‑of‑the‑art driving VLMs while preserving general reasoning abilities.
By Shengtao Wu, Zichao Dong, Weixuan Qiao, Xiaolu Liu, Xin Zhan, Junbo Chen, Jianke Zhu
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.
By Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang
MV-STRIDE is a Multi‑View hierarchical Spatial Reasoning dataset that models dependencies among perception, scene understanding, and contextual reasoning to support 3D spatial cognition. It introduces a QA generation pipeline that enforces cross‑view constraints, producing multi‑level reasoning tasks with chain‑of‑thought supervision. Experiments show that training on MV‑STRIDE yields state‑of‑the‑art performance on multi‑view spatial benchmarks, enabling MLLMs to reason robustly across diverse viewpoints.
By Jin Xu, Xiaojian Huang, Zhuodong Luo, Zhihong Zhang, Xin Liu, Jiansheng Wei, Xinzhi Wang, Jie Zhao, Xuejin Chen
arXiv:2609.38177v1 Announce Type: cross
Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
By Jaewoo Jung, Hyeonseo Yu, Honggyu An, Jisang Han, Mungyeom Kim, Minkyeong Jeon, Heeseong Shin, Wonjun Moon, Federico Tombari, Daniel Barath, Marc Pollefeys, Seungryong Kim, Sunghwan Hong
arXiv:2506.17545v2 Announce Type: replace
Abstract: Large language models are increasingly being applied to 3D scene understanding. However, existing 3D-aware LLMs largely operate as black boxes: the...
By Junjie Wang, Zhihao Yuan, Shuyi Jiang, Chun-Mei Feng, Yaolun Zhang, Shuguang Cui, Zhen Li, Na Zhao
arXiv:2603. 04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.
By Xiongkun Linghu, Jiangyong Huang, Baoxiong Jia, Siyuan Huang
The paper introduces Vantage, a training‑free, model‑agnostic framework that pairs a vision‑language model with a 3D foundation model to perform Seek‑and‑View reasoning for multi‑view spatial understanding. Vantage first analyzes a question to plan a relevant viewpoint, then augments reasoning with geometry‑grounded visual evidence from that viewpoint. Experiments across six VLMs on five benchmarks show consistent improvements without fine‑tuning, demonstrating that revealing spatial evidence through view‑grounded reasoning reduces reliance on language‑based cross‑view alignment.
By Qixiang Chen, Cheng Zhang, Fucai Ke, Chi-Wing Fu, Jianfei Cai, Jingwen Ye
3D-SceneQ is a new 3D large language model that tackles two key limitations of existing 3D scene understanding pipelines: the inclusion of irrelevant object tokens that add noise, and the exclusive use of point cloud data that lacks rich semantic cues. It introduces a Query‑Guided Adaptive Pruning (QGAP) module that selectively keeps task‑relevant objects based on user instructions, and a Multi‑modal Object‑level Feature Enhancement (MOFE) module that fuses 2D feature embeddings into the 3D representation to enrich semantic information. Experiments show that 3D‑SceneQ surpasses state‑of‑the‑art methods on several benchmarks, achieving significant gains in metrics such as CIDEr and EM@1.
By Yongqi Shan, Lu Zhang, Jiazuo Yu, Yunzhi Zhuge, Huchuan Lu
arXiv:2606. 01215v1 Announce Type: cross Abstract: Current 3D spatial reasoning methods face a fundamental trade-off: neuro-symbolic 3D (NS3D) concept learners achieve interpretable reasoning through compositional programs but are constrained to closed-set concept vocabularies and simple programs; end-to-end 3D multi-modal LLMs (3D MLLMs) could handle complex natural language and open-vocabulary concepts but suffer from black-box reasoning without explicit spatial verification.
By Wentao Mo, Yang Liu
arXiv:2607. 06620v1 Announce Type: cross Abstract: Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry.
By Haida Feng, Hao Wei, Haolin Wang, Shiwei Li, Chade Li, Yihong Wu
arXiv:2610.33558v1 Announce Type: new
Abstract: Video spatial reasoning requires multimodal large language models (MLLMs) to understand how objects are arranged and related across viewpoints. While t...
By Xinglin Li, TingTing Long, Jingzhi Zhou, Jiajing Chen, Jian Yang, Jin Xie
arXiv:2608. 12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning.
By Zile Zhou, Huining Yuan, Weichen Zhang, Xinlei Chen, Xiao-ping Zhang