Spatial Cognition and Navigation

Derniers papiers

• Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents

  Gabriel Turinici · 2 octobre 2026

  Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial comprehension through an architecture combining geometrical tools with a LLM serving as a high-level orchestrator in grid-world…

• KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs

  Aravindh Mahendran, Michael King, Matthew Koichi Grimes, Antoine Yang, Tyler Zhu, Joseph Heyward, Tengda Han, Shiry Ginosar, Chen Sun, Dima Damen, Simon Osindero, Noah Snavely, Simon Lynen, Jo\~ao Carreira, Viorica P\u{a}tr\u{a}ucean · 1 octobre 2026

  We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introduce the first benchmark that probes geographical layout understanding from real-world videos, spanning up to 1km distances. Inspired by the cognitive science literature, we evaluate models against the…

• Uruqi: Learning Spatial Cognition from Visual Experience

  Shichao Li, Meiqi Wang, Fei Su, Zhicheng Zhao · 1 octobre 2026

  Spatial intelligence requires maintaining a coherent understanding of the world as the embodied agent moves. Like humans, the agent must use its own motion to interpret changes across observations and update object locations and spatial relations accordingly. Despite spatial post-training having sub…

• Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

  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 · 1 octobre 2026

  Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evidence across viewpoints into a coherent 3D understanding. A growing body of work …

• SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models

  Rafi Ibn Sultan, Xiangyu Zhou, Md. Sajid Alam Chowdhury, Chengyin Li, Prashant Khanduri, Marco Brocanelli, Dongxiao Zhu · 1 octobre 2026

  Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions that require reasoning over visual space. Recent spatial-reasoning methods incorporate generated grounding, where models pr…

• VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience

  Siqi Zhang, Meng Wei, Chenyang Wan, Shaohao Zhu, Shufan Shen, Xihui Liu, Zhihua Wei, Tai Wang, Jiangmiao Pang · 29 septembre 2026

  Spatial reasoning is fundamental to embodied agents, yet it remains unclear whether spatial understanding can be carried forward to guide sequential interactions. Existing spatial-reasoning benchmarks typically terminate at offline predictions, while navigation benchmarks evaluate spatial reasoning …

• Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation

  Xun Huang, Shijia Zhao, Rongsheng Qu, Jiayuan Li, Xin Lu, Weixin Li, Chenglu Wen, Cheng Wang · 25 septembre 2026

  Does progress on spatial reasoning benchmarks translate into better navigation? Existing benchmarks test isolated inferences from images or videos, with little connection to downstream navigation. Our analysis reveals a gap between benchmark-oriented spatial specialization and navigation performance…

• EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models

  Yang Zhao, Zhuo Chen, Xubo Yang · 16 septembre 2026

  Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, placing joint demands on the integrated spatial intelligence of today's foundation VLMs. Existing spa…

• SceneBench: A Hierarchical Benchmark for Vision-Language Understanding of 3D Scenes

  Anubhav Khanal, Prabigya Acharya, Roshni Poudel, Sujan Kapali, Bigyan Bhatta, Pramish Paudel, Francois Rameau, Danda Pani Paudel · 16 septembre 2026

  Vision-language models excel at 2D image understanding but remain limited in 3D spatial reasoning. Progress is hindered by limitations in current benchmarks. First, 3D datasets often rely on point clouds that capture geometry but discard rich visual features like texture, text, and materials. Second…

• MindTopo: Can Foundation Models Reason in Topological Space?

  Yunfei Ge, Anbang Liu, Qineng Wang, Johnalbert Garnica, Jianwen Lyu, Zihan Wang, Reuben Tan, Jianfeng Gao, Ruohan Zhang, Yining Hong, Jiajun Wu, Manling Li · 11 septembre 2026

  Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on topological relations that remain invariant under continuous deformation. Cognitive science identifies these relations as foundational to spatial understanding, yet foundation-model evaluations la…

• MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling

  Jin Xu, Xiaojian Huang, Zhuodong Luo, Zhihong Zhang, Xin Liu, Jiansheng Wei, Xinzhi Wang, Jie Zhao, Xuejin Chen · 9 septembre 2026

  Despite the rapid progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, robust multi-view spatial reasoning remains a fundamental bottleneck due to the lack of structured 3D cognitive pathways in existing datasets. To address this, we introduce MV-STRIDE, a Multi-View hie…

• SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

  Soohyun Ryu, Sohee Kim, Eunho Yang · 9 septembre 2026

  Large Vision-Language Models (LVLMs) have achieved strong performance on diverse visual tasks, yet their ability to reconstruct and reason about the 3D structure of the scene depicted in 2D images -- referred to as spatial intelligence -- remains limited. Existing approaches attempt to address this …

• Geometry-Aware Test-Time Learning for Quantitative Spatial Reasoning

  Gege Zhang, Shuaicheng Niu, Gang Dai, Lei Sun, Shuangping Huang · 9 septembre 2026

  Quantitative spatial reasoning in visual-language models (VLMs) aims to infer spatial distances and directional relationships among objects in 3D space from a 2D image and a natural language query. Despite recent progress, VLM spatial reasoning remains brittle under distribution shifts, largely due …

• GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene Graphs

  Junqing Du, Fernando Ropero, Erkin Turkoz, Yanfeng Zhang, Lu Liu · 4 septembre 2026

  3D spatial reasoning underpins understanding and acting in the physical world, yet it remains unreliable in current multimodal large language models (MLLMs). These models falter at precise geometric measurement, at transforming between egocentric and allocentric viewpoints, and at grounding fine-gra…

• SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation

  Ziyun Qian, Zizhi Chen, Yizhou Liu, Mingyang Sun, Dingkang Yang, Lihua Zhang · 2 septembre 2026

  Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Existing prompt-driven or layout-conditioned methods improve controllability, but often lack an optimizable and verifiable spatial intermediary before …

• Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models

  Ashwin Nedungadi, Stefan Oehmcke, Stefan L\"udtke · 2 septembre 2026

  Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translate spatial descriptions into code. We introduce Autor…

• ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence

  Xiaohan Zhang, Feng Gu, Xudong Rao, Xuhao Pan, Tao Wei, Zhou Pan, Kun Zhan · 18 août 2026

  Spatial intelligence requires foundation models to maintain coherent spatial state across interactions with the physical world. However, existing data-centric approaches typically treat spatial reasoning as independent question-answer instances, enabling shortcut-based answering and providing limite…

• Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models

  Hunter Schofield, Mohammed Elmahgiubi, Mohammad Mahdavian, Richard Shi, Jinjun Shan, Amir Rasouli, Dongfeng Bai · 12 août 2026

  Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent vision-language models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, state-of-the-art app…

• Explore, Map, Remember, Decide: Are Embodied VLMs Ready for Safety-Critical Scenarios?

  Gabriele La Malfa, Nitay Alon, Emanuele La Malfa, Reuth Mirsky, Stefan Sarkadi · 11 août 2026

  Theory of Space framework (ToS) assesses the spatial understanding of curiosity-driven Vision-Language Models (VLMs) under partial observability. As AI techniques are increasingly applied to safety-critical scenarios, it is crucial to understand whether VLMs possess robust spatial memory and make re…

• Self-Evolving Neuro-Symbolic Skills for Tool-Augmented Spatial Reasoning

  Shi-Yu Tian, Zhuo-Xia Wang, Xuan-Yi Zhu, Zhi Zhou, Xinwei Yang, Kun-Yang Yu, Ming Yang, Yang Chen, Yu-Feng Li · 11 août 2026

  Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that demand both precise spatial perception and fine-grained geometric computation beyond end-to-end generation. Tool augmentation offers a natural solution…

• MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents

  Gengyang Xu, Dongwei Xiao, Yiteng Peng, Shuai Wang · 11 août 2026

  An embodied agent is an intelligent entity that interacts with its environment through a physical body. Currently, the evaluation of embodied agents primarily relies on two paradigms: (1) manually annotated Visual Question Answering (VQA) pairs and (2) high-level task completion metrics, such as suc…

• Disentangling 3D Modeling from Spatial Reasoning

  Haoze Sun, Jiequan Cui, Qingshan Xu, Richang Hong · 7 août 2026

  In this work, we explore an alternative paradigm for spatial reasoning by explicitly disentangling 3D perception from reasoning, rather than jointly acquiring implicit 3D perception and reasoning through large-scale training. Our key observation is that modern perception models excel at estimating c…

• Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests

  Patrick Rim, Tom Long, Ekta Prashnani, Ruth Rosenholtz, Ben Boudaoud, Peter Xenopoulos, Alex Wong, Joohwan Kim, Jae-Hyun Jung · 28 juillet 2026

  Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performance: when a model fails a spatia…

• Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation Model Spatial Understanding

  Zhiwei Wei, Yonghe Sun, Zhenjia Liu, Wenjia Xu, Chao He, Weihua Dong, Chunbo Liu, Hua Liao · 21 juillet 2026

  Spatial understanding is crucial for foundation models (FMs), and maps have long helped humans organize and reason about geographic information. This study examines whether choropleth maps remain useful for machine spatial understanding when models can directly process structured geodata. We introdu…

• MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors

  Lubin Bai, Mengyu Cao, Sixue Wang, Zhongwei Wan, Yue Pan, Jiale Hou, Xiang Li, Xiuyuan Zhang · 17 juin 2026

  Large language model agents are increasingly integrated into map services. Since map services are embedded in everyday-life scenarios rather than professional task settings, users often express their needs informally, resulting in underspecified queries with many unspoken needs, namely, implicit dec…