English
Related papers

Related papers: RoboStream: Weaving Spatio-Temporal Reasoning with…

200 papers

Humans perceive and understand real-world spaces through a stream of visual observations. Therefore, the ability to streamingly maintain and update spatial evidence from potentially unbounded video streams is essential for spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Fangfu Liu , Diankun Wu , Jiawei Chi , Yimo Cai , Yi-Hsin Hung , Xumin Yu , Hao Li , Han Hu , Yongming Rao , Yueqi Duan

Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential challenge. However, existing spatio-temporal reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Jinho Park , Youbin Kim , Hogun Park , Eunbyung Park

Humans are born with vision-based 4D spatial-temporal intelligence, which enables us to perceive and reason about the evolution of 3D space over time from purely visual inputs. Despite its importance, this capability remains a significant…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Xingyilang Yin , Chengzhengxu Li , Jiahao Chang , Chi-Man Pun , Xiaodong Cun

Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…

Machine Learning · Computer Science 2024-10-01 Shu Ishida

We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zhenyu Pan , Han Liu

World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in…

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced cross-modal understanding and reasoning by incorporating Chain-of-Thought (CoT) reasoning in the semantic space. Building upon this, recent studies…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Chengzhi Liu , Yuzhe Yang , Yue Fan , Qingyue Wei , Sheng Liu , Xin Eric Wang

Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effectively plan and act in dynamic, multi-room 3D environments.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Wenbo Hu , Yining Hong , Yanjun Wang , Leison Gao , Zibu Wei , Xingcheng Yao , Nanyun Peng , Yonatan Bitton , Idan Szpektor , Kai-Wei Chang

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Machine Learning · Computer Science 2026-04-24 Zhixin Zhang , Shabo Zhang , Chengcan Wu , Zeming Wei , Meng Sun

Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions, even when they are occluded. This ability is crucial for tasks such as vision-language navigation and autonomous…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Zhenyang Liu , Yikai Wang , Sixiao Zheng , Tongying Pan , Longfei Liang , Yanwei Fu , Xiangyang Xue

Spatial understanding is fundamental for embodied agents, yet most spatial VLMs and benchmarks remain offline-evaluating post-hoc QA over pre-recorded inputs and overlooking two crucial deployment-critical requirements: long-horizon…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Yuxi Wei , Wei Huang , Qirui Chen , Lu Hou , Xiaojuan Qi

How can we imbue robots with the ability to manipulate objects precisely but also to reason about them in terms of abstract concepts? Recent works in manipulation have shown that end-to-end networks can learn dexterous skills that require…

Robotics · Computer Science 2021-09-27 Mohit Shridhar , Lucas Manuelli , Dieter Fox

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Joowon Kim , Seungho Shin , Joonhyung Park , Eunho Yang

The convergence of embodied agents and large language models (LLMs) has brought significant advancements to embodied instruction following. Particularly, the strong reasoning capabilities of LLMs make it possible for robots to perform…

Long video understanding is still challenging for recent Large Video-Language Models (LVLMs) due to the conflict between long-form temporal understanding and detailed spatial perception. LVLMs with a uniform frame sampling mechanism, which…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Shenghao Fu , Qize Yang , Yuan-Ming Li , Xihan Wei , Xiaohua Xie , Wei-Shi Zheng

Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routing foveal focus toward task-relevant details while maintaining peripheral awareness of the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Brown Ebouky , Gabriele Carrino , Niccolo Avogaro , Christoph Studer , Andrea Bartezzaghi , Mattia Rigotti

In recent years, video question answering based on multimodal large language models (MLLM) has garnered considerable attention, due to the benefits from the substantial advancements in LLMs. However, these models have a notable deficiency…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Jinglei Zhang , Yuanfan Guo , Rolandos Alexandros Potamias , Jiankang Deng , Hang Xu , Chao Ma

While Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to…

Robotics · Computer Science 2025-11-13 Mobin Habibpour , Fatemeh Afghah

Spatiotemporal reasoning is a fundamental capability for artificial intelligence (AI) in soft tissue surgery, paving the way for intelligent assistive systems and autonomous robotics. While 2D vision-language models show increasing promise…

Recent advancements in Multimodal Large Language Models (MLLMs) have shown remarkable capabilities across various multimodal contexts. However, their application in robotic scenarios, particularly for long-horizon manipulation tasks,…