中文
相关论文

相关论文: How Far Are Large Multimodal Models from Human-Lev…

200 篇论文

Large language models (LLMs) have been widely adopted as the core of agent frameworks in various scenarios, such as social simulations and AI companions. However, the extent to which they can replicate human-like motivations remains an…

计算与语言 · 计算机科学 2025-06-17 Xixian Yong , Jianxun Lian , Xiaoyuan Yi , Xiao Zhou , Xing Xie

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

人工智能 · 计算机科学 2025-04-18 Baining Zhao , Ziyou Wang , Jianjie Fang , Chen Gao , Fanhang Man , Jinqiang Cui , Xin Wang , Xinlei Chen , Yong Li , Wenwu Zhu

Multimodal large language models (MLLMs) are proficient in perception and instruction-following, but they still struggle with spatial reasoning: the ability to mentally track and manipulate objects across multiple views and over time.…

人工智能 · 计算机科学 2025-12-30 Ryan Spencer , Roey Yaari , Ritvik Vemavarapu , Joyce Yang , Steven Ngo , Utkarsh Sharma

Scientific reasoning, the process through which humans apply logic, evidence, and critical thinking to explore and interpret scientific phenomena, is essential in advancing knowledge reasoning across diverse fields. However, despite…

计算与语言 · 计算机科学 2026-04-21 Yibo Yan , Shen Wang , Jiahao Huo , Jingheng Ye , Zhendong Chu , Xuming Hu , Philip S. Yu , Carla Gomes , Bart Selman , Qingsong Wen

Exploration and goal-directed navigation in unknown layouts are central to inspection, logistics, and search-and-rescue. We ask whether large language models (LLMs) can function as \emph{text-only} controllers under partial observability --…

人工智能 · 计算机科学 2026-04-14 Stephan Sandfuchs , Maximilian Melchert , Jörg Frochte

Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large…

计算与语言 · 计算机科学 2024-06-05 Chengzu Li , Caiqi Zhang , Han Zhou , Nigel Collier , Anna Korhonen , Ivan Vulić

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal…

Multimodal Large Language Models (MLLMs) are renowned for their superior instruction-following and reasoning capabilities across diverse problem domains. However, existing benchmarks primarily focus on assessing factual and logical…

计算与语言 · 计算机科学 2025-06-10 Aashish Anantha Ramakrishnan , Aadarsh Anantha Ramakrishnan , Dongwon Lee

Recent advancements in Large Language Models (LLMs) have spurred numerous attempts to apply these technologies to embodied tasks, particularly focusing on high-level task planning and task decomposition. To further explore this area, we…

In order to flexibly act in an everyday environment, a robotic agent needs a variety of cognitive capabilities that enable it to reason about plans and perform execution recovery. Large language models (LLMs) have been shown to demonstrate…

机器人学 · 计算机科学 2026-03-04 Shinas Shaji , Fabian Huppertz , Alex Mitrevski , Sebastian Houben

Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on explicit 3D inputs or specialized model architectures, we ask:…

计算机视觉与模式识别 · 计算机科学 2025-11-06 Fangrui Zhu , Hanhui Wang , Yiming Xie , Jing Gu , Tianye Ding , Jianwei Yang , Huaizu Jiang

A navigable agent needs to understand both high-level semantic instructions and precise spatial perceptions. Building navigation agents centered on Multimodal Large Language Models (MLLMs) demonstrates a promising solution due to their…

机器人学 · 计算机科学 2026-02-18 Zerui Li , Hongpei Zheng , Fangguo Zhao , Aidan Chan , Jian Zhou , Sihao Lin , Shijie Li , Qi Wu

While Multimodal Large Language Models (MLLMs) excel at many vision tasks, it is unknown if they exhibit human-like perceptual behaviors. To evaluate this, we introduce HVSBench, the first large-scale benchmark with over 85,000 samples…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Jiaying Lin , Shuquan Ye , Dan Xu , Wanli Ouyang , Rynson W. H. Lau

Multimodal Large Language Models (MLLMs) mimic human perception and reasoning system by integrating powerful Large Language Models (LLMs) with various modality encoders (e.g., vision, audio), positioning LLMs as the "brain" and various…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Jiaxing Huang , Jingyi Zhang

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret…

The planning ability of Large Language Models (LLMs) has garnered increasing attention in recent years due to their remarkable capacity for multi-step reasoning and their ability to generalize across a wide range of domains. While some…

人工智能 · 计算机科学 2025-02-19 Mohamed Aghzal , Erion Plaku , Gregory J. Stein , Ziyu Yao

Embodied decision-making enables agents to translate high-level goals into executable actions through continuous interactions within the physical world, forming a cornerstone of general-purpose embodied intelligence. Large language models…

Our research investigates the capability of modern multimodal reasoning models, powered by Large Language Models (LLMs), to facilitate vision-powered assistants for multi-step daily activities. Such assistants must be able to 1) encode…

计算机视觉与模式识别 · 计算机科学 2024-08-14 Mrinal Verghese , Brian Chen , Hamid Eghbalzadeh , Tushar Nagarajan , Ruta Desai

Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate commonsense reasoning…

机器人学 · 计算机科学 2026-05-01 Teng Wang , Xinxin Zhao , Wenzhe Cai , Changyin Sun

Uncrewed Aerial Vehicles (UAVs) are widely deployed across diverse applications due to their mobility and agility. Recent advances in Large Language Models (LLMs) offer a transformative opportunity to enhance UAV intelligence beyond…

机器人学 · 计算机科学 2026-03-03 Yousef Emami , Hao Zhou , Radha Reddy , Atefeh Hajijamali Arani , Biliang Wang , Kai Li , Luis Almeida , Zhu Han