English
Related papers

Related papers: MosaicThinker: On-Device Visual Spatial Reasoning …

200 papers

Recent advancements in reinforcement learning with verifiable rewards have pushed the boundaries of the visual reasoning capabilities in large vision-language models (LVLMs). However, training LVLMs with reinforcement fine-tuning (RFT) is…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zilin Xiao , Jaywon Koo , Siru Ouyang , Jefferson Hernandez , Yu Meng , Vicente Ordonez

As textual reasoning with large language models (LLMs) has advanced significantly, there has been growing interest in enhancing the multimodal reasoning capabilities of large vision-language models (LVLMs). However, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Junfei Wu , Jian Guan , Kaituo Feng , Qiang Liu , Shu Wu , Liang Wang , Wei Wu , Tieniu Tan

Egocentric video reasoning centers on an unobservable agent behind the camera who dynamically shapes the environment, requiring inference of hidden intentions and recognition of fine-grained interactions. This core challenge limits current…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Baoqi Pei , Yifei Huang , Jilan Xu , Yuping He , Guo Chen , Fei Wu , Yu Qiao , Jiangmiao Pang

Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathematical and coding tasks. However, their effectiveness in embodied domains which require continuous interaction with environments through…

Computation and Language · Computer Science 2025-05-15 Wenqi Zhang , Mengna Wang , Gangao Liu , Xu Huixin , Yiwei Jiang , Yongliang Shen , Guiyang Hou , Zhe Zheng , Hang Zhang , Xin Li , Weiming Lu , Peng Li , Yueting Zhuang

Large vision-language models (VLMs) show strong multimodal understanding but still struggle with 3D spatial reasoning, such as distance estimation, size comparison, and cross-view consistency. Existing 3D-aware methods either depend on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Ruosen Zhao , Zhikang Zhang , Jialei Xu , Jiahao Chang , Dong Chen , Lingyun Li , Weijian Sun , Zizhuang Wei

3D Visual Grounding (3DVG) focuses on locating objects in 3D scenes based on natural language descriptions, serving as a fundamental task for embodied AI and robotics. Recent advances in Multi-modal Large Language Models (MLLMs) have…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Beining Xu , Siting Zhu , Zhao Jin , Junxian Li , Hesheng Wang

Current multimodal large language models (MLLMs) still face significant challenges in complex visual tasks (e.g., spatial understanding, fine-grained perception). Prior methods have tried to incorporate visual reasoning, however, they fail…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Zhangquan Chen , Ruihui Zhao , Chuwei Luo , Mingze Sun , Xinlei Yu , Yangyang Kang , Ruqi Huang

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Rui Yang , Ziyu Zhu , Yanwei Li , Jingjia Huang , Shen Yan , Siyuan Zhou , Zhe Liu , Xiangtai Li , Shuangye Li , Wenqian Wang , Yi Lin , Hengshuang Zhao

Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Kelly Cui , Nikhil Prakash , Ayush Raina , David Bau , Antonio Torralba , Tamar Rott Shaham

Next-generation AI companions must go beyond general video understanding to resolve spatial and temporal references in dynamic, real-world environments. Existing Video Large Language Models (Video LLMs), while capable of coarse-level…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Honglu Zhou , Xiangyu Peng , Shrikant Kendre , Michael S. Ryoo , Silvio Savarese , Caiming Xiong , Juan Carlos Niebles

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Wanyue Zhang , Wenxiang Wu , Wang Xu , Jiaxin Luo , Helu Zhi , Yibin Huang , Shuo Ren , Zitao Liu , Jiajun Zhang

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Yang Liu , Ming Ma , Xiaomin Yu , Pengxiang Ding , Han Zhao , Mingyang Sun , Siteng Huang , Donglin Wang

We introduce Thinking with Spatial Code, a framework that transforms RGB video into explicit, temporally coherent 3D representations for physical-world visual question answering. We highlight the empirical finding that our proposed spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jieneng Chen , Wenxin Ma , Ruisheng Yuan , Yunzhi Zhang , Jiajun Wu , Alan Yuille

An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Sahithya Ravi , Gabriel Sarch , Vibhav Vineet , Andrew D. Wilson , Balasaravanan Thoravi Kumaravel

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Yifan Liu , Fangneng Zhan , Kaichen Zhou , Yilun Du , Paul Pu Liang , Hanspeter Pfister

While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (VLA) models for end-to-end robot control, few studies…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Ganlin Yang , Tianyi Zhang , Haoran Hao , Weiyun Wang , Yibin Liu , Dehui Wang , Guanzhou Chen , Zijian Cai , Junting Chen , Weijie Su , Wengang Zhou , Yu Qiao , Jifeng Dai , Jiangmiao Pang , Gen Luo , Wenhai Wang , Yao Mu , Zhi Hou

Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric benchmark targeting low-level spatial intelligence in embodied 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiyao Zhang , Mingxu Zhang , Yitong Peng , Haoxuan Liu , Chenshuo Wang , Yuxing Long , Haoyang Huang , Dongjiang Li , Nan Duan , Hui Shen , Hao Dong

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Byungwoo Jeon , Yoonwoo Jeong , Hyunseok Lee , Minsu Cho , Jinwoo Shin

Spatial reasoning, which requires ability to perceive and manipulate spatial relationships in the 3D world, is a fundamental aspect of human intelligence, yet remains a persistent challenge for Multimodal large language models (MLLMs).…

Artificial Intelligence · Computer Science 2025-11-21 Weichen Liu , Qiyao Xue , Haoming Wang , Xiangyu Yin , Boyuan Yang , Wei Gao

Visual Spatial Reasoning (VSR) is a core human cognitive ability and a critical requirement for advancing embodied intelligence and autonomous systems. Despite recent progress in Vision-Language Models (VLMs), achieving human-level VSR…