English
Related papers

Related papers: ESCAPE: Episodic Spatial Memory and Adaptive Execu…

200 papers

Achieving generalizable and precise robotic manipulation across diverse environments remains a critical challenge, largely due to limitations in spatial perception. While prior imitation-learning approaches have made progress, their…

Robotics · Computer Science 2025-05-28 Yiqi Huang , Travis Davies , Jiahuan Yan , Jiankai Sun , Xiang Chen , Luhui Hu

Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…

Artificial Intelligence · Computer Science 2026-03-10 Shaobin Ling , Yun Wang , Chenyou Fan , Tin Lun Lam , Junjie Hu

Autonomous exploration in unknown environments is key for mobile robots, helping them perceive, map, and make decisions in complex areas. However, current methods often rely on frequent global optimization, suffering from high computational…

Robotics · Computer Science 2026-02-27 Kai Li , Shengtao Zheng , Linkun Xiu , Yuze Sheng , Xiao-Ping Zhang , Dongyue Huang , Xinlei Chen

Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…

Artificial Intelligence · Computer Science 2025-05-27 Ye Ye

We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value…

Machine Learning · Computer Science 2020-10-26 Sean R. Sinclair , Tianyu Wang , Gauri Jain , Siddhartha Banerjee , Christina Lee Yu

Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans…

Robotics · Computer Science 2023-11-08 Priyam Parashar , Vidhi Jain , Xiaohan Zhang , Jay Vakil , Sam Powers , Yonatan Bisk , Chris Paxton

Manipulation in confined and cluttered environments remains a significant challenge due to partial observability and complex configuration spaces. Effective manipulation in such environments requires an intelligent exploration strategy to…

Robotics · Computer Science 2026-05-20 Qixuan Li , Chen Le , Dongyue Huang , Jincheng Yu , Xinlei Chen

Modern perception models, particularly those designed for multisensory egocentric tasks, have achieved remarkable performance but often come with substantial computational costs. These high demands pose challenges for real-world deployment,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Sanjoy Chowdhury , Subrata Biswas , Sayan Nag , Tushar Nagarajan , Calvin Murdock , Ishwarya Ananthabhotla , Yijun Qian , Vamsi Krishna Ithapu , Dinesh Manocha , Ruohan Gao

The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate only a small portion of parameters during inference,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-31 Zixu Shen , Kexin Chu , Yifan Zhang , Dawei Xiang , Runxin Wu , Wei Zhang

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Machine Learning · Computer Science 2026-05-12 Riccardo Ali , Alessio Borgi , Christopher Irwin , Mario Severino , Pietro Liò

Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…

Hardware Architecture · Computer Science 2026-04-10 Fabrizio Pittorino , Manuel Roveri

Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that…

Machine Learning · Computer Science 2018-12-27 Sirui Xie , Junning Huang , Lanxin Lei , Chunxiao Liu , Zheng Ma , Wei Zhang , Liang Lin

In cooperative multi-agent reinforcement learning (MARL), agents aim to achieve a common goal, such as defeating enemies or scoring a goal. Existing MARL algorithms are effective but still require significant learning time and often get…

Machine Learning · Computer Science 2024-03-08 Hyungho Na , Yunkyeong Seo , Il-chul Moon

We address key challenges in long-horizon embodied exploration and navigation by proposing a new object transport task and a novel modular framework for temporally extended navigation. Our first contribution is the design of a novel…

Computer Vision and Pattern Recognition · Computer Science 2022-10-31 Sriram Narayanan , Dinesh Jayaraman , Manmohan Chandraker

Spatial-temporal reasoning is a challenging task in Artificial Intelligence (AI) due to its demanding but unique nature: a theoretic requirement on representing and reasoning based on spatial-temporal knowledge in mind, and an applied…

Artificial Intelligence · Computer Science 2021-05-17 Chi Zhang , Baoxiong Jia , Song-Chun Zhu , Yixin Zhu

Recent research in robot exploration and mapping has focused on sampling environmental hotspot fields. This exploration task is formalized by Low, Dolan, and Khosla (2008) in a sequential decision-theoretic planning under uncertainty…

Machine Learning · Computer Science 2013-05-28 Kian Hsiang Low , John M. Dolan , Pradeep Khosla

Long-horizon agentic reasoning requires large language models to act over long interaction histories containing thoughts, tool calls, observations, and partial conclusions. The challenge is not merely that these histories grow long, but…

Artificial Intelligence · Computer Science 2026-05-26 Yuyang Hu , Hongjin Qian , Shuting Wang , Jiongnan Liu , Ziliang Zhao , Jiejun Tan , Zheng Liu , Zhicheng Dou

Many animals possess a remarkable capacity to rapidly construct flexible cognitive maps of their environments. These maps are crucial for ethologically relevant behaviors such as navigation, exploration, and planning. Existing computational…

Artificial Intelligence · Computer Science 2026-02-04 Zizhan He , Maxime Daigle , Pouya Bashivan

This document is one of the deliverable reports created for the ESCAPE project. ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project develops world-class, extreme-scale computing…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-08-20 Alastair McKinstry

This paper presents RoboMatch, a novel unified teleoperation platform for mobile manipulation with an auto-matching network architecture, designed to tackle long-horizon tasks in dynamic environments. Our system enhances teleoperation…