English
Related papers

Related papers: Training new operators - the first six months

200 papers

Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human…

Robotics · Computer Science 2024-01-30 Jesse Zhang , Karl Pertsch , Jiahui Zhang , Joseph J. Lim

Launched by Elon Musk and its Optimus, we are witnessing a new race in which many companies have already engaged. The objective it to put at work a new generation of humanoid robots in demanding industrial environments within 2 or 3 years.…

Computers and Society · Computer Science 2024-04-08 Fabrice R. Noreils

The vision of 5G lies in providing high data rates, low latency (for the aim of near-real-time applications), significantly increased base station capacity, and near-perfect quality of service (QoS) for users, compared to LTE networks. In…

Networking and Internet Architecture · Computer Science 2022-09-14 Hakan Erdol , Xiaoyang Wang , Peizheng Li , Jonathan D. Thomas , Robert Piechocki , George Oikonomou , Rui Inacio , Abdelrahim Ahmad , Keith Briggs , Shipra Kapoor

Continual adaptation is essential for general autonomous agents. For example, a household robot pretrained with a repertoire of skills must still adapt to unseen tasks specific to each household. Motivated by this, building upon…

Robotics · Computer Science 2025-03-28 Ruiqi Zhu , Endong Sun , Guanhe Huang , Oya Celiktutan

Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards. However, recent studies reveal a critical constraint: reinforcement learning succeeds only when the base model already assigns…

Learning requires both study and curiosity. A good learner is not only good at extracting information from the data given to it, but also skilled at finding the right new information to learn from. This is especially true when a human…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Ervin Teng , Bob Iannucci

Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding…

Computation and Language · Computer Science 2026-01-26 Alphaeus Dmonte , Vidhi Gupta , Daniel J Perry , Mark Arehart

Continual Pre-Training (CPT) is widely used for acquiring and updating factual knowledge in LLMs. This practice treats loss as a proxy for knowledge learning, while offering no grounding into how it changes during training. We study CPT as…

Computation and Language · Computer Science 2026-01-08 Seyed Mahed Mousavi , Simone Alghisi , Giuseppe Riccardi

In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources. OPT is constructed in an encoder-decoder framework, including three…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Jing Liu , Xinxin Zhu , Fei Liu , Longteng Guo , Zijia Zhao , Mingzhen Sun , Weining Wang , Hanqing Lu , Shiyu Zhou , Jiajun Zhang , Jinqiao Wang

In this paper, we investigate the effect of TDD, as compared to a non-TDD approach, as well as its retainment (or retention) over a time span of (about) six months. To pursue these objectives, we conducted a (quantitative) longitudinal…

Software Engineering · Computer Science 2021-05-12 Maria Teresa Baldassarre , Danilo Caivano , Davide Fucci , Natalia Juristo , Simone Romano , Giuseppe Scanniello , BurakTurhan

This paper uses a simple state machine to develop a control algorithm for controlling an infant humanoid in the context of a simple model system. The algorithm is inspired by a baby who starts learning to stand and walk at 7 to 12 months of…

Robotics · Computer Science 2022-11-15 Shengjie Xu , Kevin Mok

The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety of the agent during…

Systems and Control · Electrical Eng. & Systems 2024-06-18 Kyle Dunlap , Kochise Bennett , David van Wijk , Nathaniel Hamilton , Kerianne Hobbs

The study of operator learning involves the utilization of neural networks to approximate operators. Traditionally, the focus has been on single-operator learning (SOL). However, recent advances have rapidly expanded this to include the…

Machine Learning · Computer Science 2024-04-09 Zecheng Zhang

Humans are remarkably data-efficient when adapting to new unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using Reinforcement Learning (RL), are highly specialized…

Robotics · Computer Science 2026-04-07 Jonas Eschmann , Dario Albani , Giuseppe Loianno

Fundamental big-picture challenges face the enterprise of burgeoning space test, which may also have an impact on the syllabus and training of a possible future Space Test Pilot School. Test fundamentals and test conduct under stresses of…

Physics Education · Physics 2022-11-18 Michael Nayak , Christina Straight , Evelyn Kent , Jarred Langhals

We present a theoretical model of distributed training, and use it to analyze how far dense and sparse training runs can be scaled. Under our baseline assumptions, given a three month training duration, data movement bottlenecks begin to…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-14 Ege Erdil , David Schneider-Joseph

Calls for reform to instructional labs means many instructors and departments are facing the daunting task of identifying goals for their introductory lab courses. Fortunately, the American Association of Physics Teachers (AAPT) released a…

Physics Education · Physics 2019-05-22 N. G. Holmes , Emily M. Smith

The ability to automatically learn movements and behaviors of increasing complexity is a long-term goal in autonomous systems. Indeed, this is a very complex problem that involves understanding how knowledge is acquired and reused by humans…

Time operator can be introduced by three different approaches: by pertaining it to dynamical variables; by quantizing the classical expression of time; taken as the restriction of energy shift generator to the Hilbert space of a physical…

Quantum Physics · Physics 2009-11-13 Zhi-Yong Wang , Cai-Dong Xiong

The ever-changing telecommunication industry is in severe need of a highly-skilled workforce to shape and deploy future generation communication systems. This article presents an innovative telecommunication training that is designed to…

Signal Processing · Electrical Eng. & Systems 2019-10-28 Ali Fatih Demir , Berker Peköz , Selçuk Köse , Hüseyin Arslan