English
Related papers

Related papers: How Good are Foundation Models in Step-by-Step Emb…

200 papers

This paper investigates an under-explored but important problem: given a collection of pre-trained neural networks, predicting their performance on each multi-modal task without fine-tuning them, such as image recognition, referring,…

Machine Learning · Computer Science 2023-08-14 Fanqing Meng , Wenqi Shao , Zhanglin Peng , Chonghe Jiang , Kaipeng Zhang , Yu Qiao , Ping Luo

Reasoning has become a defining capability of modern foundation models, yet its development in the audio modality remains limited. Audio poses challenges that are distinct from those of text and vision. It is continuous, temporally dense,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-21 Zhihan Guo , Wenqian Cui , Guan-Ting Lin , Daxin Tan , Jingyao Li , Qiyong Zheng , Dingdong Wang , Jing Xiong , Han Shi , Jiaya Jia , Irwin King

Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recently, process-level reward models (PRMs) were proposed to…

Artificial Intelligence · Computer Science 2025-03-18 Zhaopan Xu , Pengfei Zhou , Jiaxin Ai , Wangbo Zhao , Kai Wang , Xiaojiang Peng , Wenqi Shao , Hongxun Yao , Kaipeng Zhang

We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial,…

Semantic information in embodied AI is inherently multi-source and multi-stage, making it challenging to fully leverage for achieving stable perception-to-action loops in real-world environments. Early studies have combined manual…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Shuai Chen , Hao Chen , Yuanchen Bei , Tianyang Zhao , Zhibo Zhou , Feiran Huang

Large language models (LLMs) have achieved remarkable results on tasks framed as reasoning problems, yet their true ability to perform procedural reasoning, executing multi-step, rule-based computations remains unclear. Unlike algorithmic…

Artificial Intelligence · Computer Science 2025-11-20 Mahdi Samiei , Mahdi Mansouri , Mahdieh Soleymani Baghshah

As Vision-Language Models (VLMs) grow in sophistication, their ability to perform reasoning is coming under increasing supervision. While they excel at many tasks, their grasp of fundamental scientific principles, such as physics, remains…

Machine Learning · Computer Science 2025-09-11 Pranav Pawar , Kavish Shah , Akshat Bhalani , Komal Kasat , Dev Mittal , Hadi Gala , Deepali Patil , Nikita Raichada , Monali Deshmukh

Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's final answer is faithful to the stated reasoning steps. In this…

Computation and Language · Computer Science 2024-10-08 Debjit Paul , Robert West , Antoine Bosselut , Boi Faltings

Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions…

Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural…

Artificial Intelligence · Computer Science 2023-11-21 Gabriel Sarch , Yue Wu , Michael J. Tarr , Katerina Fragkiadaki

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation…

Robotics · Computer Science 2026-04-14 Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and solving mathematical problems, leading to advancements in various fields. We propose an LLM-embodied path planning framework for…

Robotics · Computer Science 2024-07-08 Xiangrui Kong , Wenxiao Zhang , Jin Hong , Thomas Braunl

Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Jun Zhang , Jie Feng , Long Chen , Junhui Wang , Zhicheng Liu , Depeng Jin , Yong Li

Enabling robots to perform novel manipulation tasks from natural language instructions remains a fundamental challenge in robotics, despite significant progress in generalized problem solving with foundational models. Large vision and…

Robotics · Computer Science 2026-05-26 Yinlong Dai , Benjamin A. Christie , Daniel J. Evans , Dylan P. Losey , Simon Stepputtis

Multimodal Large Language Models have demonstrated powerful cross-modal understanding and reasoning capabilities in general domains. However, in the electromagnetic (EM) domain, they still face challenges such as data scarcity and…

Human-AI collaboration requires AI agents to understand human behavior for effective coordination. While advances in foundation models show promising capabilities in understanding and showing human-like behavior, their application in…

Robotics · Computer Science 2026-05-07 Shinas Shaji , Teena Chakkalayil Hassan , Sebastian Houben , Alex Mitrevski

Large language models (LLMs) have undergone significant expansion and have been increasingly integrated across various domains. Notably, in the realm of robot task planning, LLMs harness their advanced reasoning and language comprehension…

Embodied Instruction Following (EIF) studies how autonomous mobile manipulation robots should be controlled to accomplish long-horizon tasks described by natural language instructions. While much research on EIF is conducted in simulators,…

Robotics · Computer Science 2024-03-13 Yuki Inoue , Hiroki Ohashi

Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of using generated videos as scalable supervision for robot learning. However, for embodied manipulation,…

This review explores the potential of foundation models to advance laboratory automation in the materials and chemical sciences. It emphasizes the dual roles of these models: cognitive functions for experimental planning and data analysis,…