English
Related papers

Related papers: SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot …

200 papers

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Guangfu Guo , Xiaoqian Lu , Yue Feng , Mingming Sun

Intuitive learning is crucial for developing deep conceptual understanding, especially in STEM education, where students often struggle with abstract and interconnected concepts. Automatic question generation has become an effective…

Artificial Intelligence · Computer Science 2026-01-13 Nicholas X. Wang , Neel V. Parpia , Aaryan D. Parikh , Aggelos K. Katsaggelos

Recent advancements in Vision-Language Models (VLMs) have demonstrated strong potential for autonomous driving tasks. However, their spatial understanding and reasoning-key capabilities for autonomous driving-still exhibit significant…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Kexin Tian , Jingrui Mao , Yunlong Zhang , Jiwan Jiang , Yang Zhou , Zhengzhong Tu

3D visual grounding aims to locate objects based on natural language descriptions in 3D scenes. Existing methods rely on a pre-defined Object Lookup Table (OLT) to query Visual Language Models (VLMs) for reasoning about object locations,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Wenyuan Huang , Zhao Wang , Zhou Wei , Ting Huang , Fang Zhao , Jian Yang , Zhenyu Zhang

Large Language Models (LLMs) represent formidable tools for sequence modeling, boasting an innate capacity for general pattern recognition. Nevertheless, their broader spatial reasoning capabilities, especially applied to numerical…

Robotics · Computer Science 2023-12-05 Manasi Sharma

Open-Vocabulary Mobile Manipulation (OVMM) is a crucial capability for autonomous robots, especially when faced with the challenges posed by unknown and dynamic environments. This task requires robots to explore and build a semantic…

Robotics · Computer Science 2024-06-27 Dicong Qiu , Wenzong Ma , Zhenfu Pan , Hui Xiong , Junwei Liang

Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…

Robotics · Computer Science 2026-03-31 Qiming Zhu , Zhirui Fang , Tianming Zhang , Chuanxiu Liu , Xiaoke Jiang , Lei Zhang

Long-horizon egocentric video presents significant challenges for visual navigation due to viewpoint drift and the absence of persistent geometric context. Although recent vision-language models perform well on image and short-video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 James Tribble , Hao Wang , Si-En Hong , Chaoyi Zhou , Ashish Bastola , Siyu Huang , Abolfazl Razi

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Jiahua Chen , Qihong Tang , Weinong Wang , Qi Fan

Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Michael Ogezi , Freda Shi

Spatial tracing, as a fundamental embodied interaction ability for robots, is inherently challenging as it requires multi-step metric-grounded reasoning compounded with complex spatial referring and real-world metric measurement. However,…

Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding. Recent studies have sought to enhance the reasoning capabilities of remote sensing MLLMs, typically through cold-start…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Di Wang , Shunyu Liu , Wentao Jiang , Fengxiang Wang , Yi Liu , Xiaolei Qin , Zhiming Luo , Chaoyang Zhou , Haonan Guo , Jing Zhang , Bo Du , Dacheng Tao , Liangpei Zhang

Prompt learning is an effective way to exploit the potential of large-scale pre-trained foundational models. Continuous prompts parameterize context tokens in prompts by turning them into differentiable vectors. Deep continuous prompts…

Machine Learning · Computer Science 2025-01-03 Zhenhan Huang , Tejaswini Pedapati , Pin-Yu Chen , Jianxi Gao

Spatial world models, representations that support flexible reasoning about spatial relations, are central to developing computational models that could operate in the physical world, but their precise mechanistic underpinnings are nuanced…

Neurons and Cognition · Quantitative Biology 2025-10-27 Dezhi Luo , Qingying Gao , Hokin Deng

Prompt engineering is a powerful tool used to enhance the performance of pre-trained models on downstream tasks. For example, providing the prompt "Let's think step by step" improved GPT-3's reasoning accuracy to 63% on MutiArith while…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Cheng Shi , Sibei Yang

Our brain has an inner global positioning system which enables us to sense and navigate 3D spaces in real time. Can mobile robots replicate such a biological feat in a dynamic environment? We introduce the first spatial reasoning framework…

Robotics · Computer Science 2025-05-20 Pengdi Huang , Mingyang Wang , Huan Tian , Minglun Gong , Hao Zhang , Hui Huang

MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Yuheng Shi , Xiaohuan Pei , Linfeng Wen , Minjing Dong , Chang Xu

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

Recently, various methods have been proposed to create open-domain conversational agents with Large Language Models (LLMs). These models are able to answer user queries, but in a one-way Q&A format rather than a true conversation.…

Computation and Language · Computer Science 2024-07-02 Ahmed Njifenjou , Virgile Sucal , Bassam Jabaian , Fabrice Lefèvre

Grounding large language models (LLMs) in domain-specific tasks like post-hoc dash-cam driving video analysis is challenging due to their general-purpose training and lack of structured inductive biases. As vision is often the sole modality…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Manyi Yao , Bingbing Zhuang , Sparsh Garg , Amit Roy-Chowdhury , Christian Shelton , Manmohan Chandraker , Abhishek Aich