English
Related papers

Related papers: Training new operators - the first six months

200 papers

Advanced by rich perception and precise execution, robots possess immense potential to provide professional and customized rehabilitation exercises for patients with mobility impairments caused by strokes. Autonomous robotic rehabilitation…

Robotics · Computer Science 2024-03-11 Xinyu Jiang , Yibei Guo , Mengsha Hu , Ruoming Jin , Hai Phan , Jay Alberts , Rui Liu

Pre-training and fine-tuning have achieved great success in the natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual…

Computation and Language · Computer Science 2019-12-05 Rongxiang Weng , Heng Yu , Shujian Huang , Shanbo Cheng , Weihua Luo

Reinforcement learning (RL) can in principle let robots automatically adapt to new tasks, but current RL methods require a large number of trials to accomplish this. In this paper, we tackle rapid adaptation to new tasks through the…

Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the…

Computation and Language · Computer Science 2022-03-29 Tasnim Mohiuddin , Philipp Koehn , Vishrav Chaudhary , James Cross , Shruti Bhosale , Shafiq Joty

The need for space test professionals is growing rapidly, due to establishment of the US Space Force and the extremely rapid growth of the commercial space industry. The future of space test looks bright and complex; a better training…

Reinforcement learning (RL) has drawn increasing interests in recent years due to its tremendous success in various applications. However, standard RL algorithms can only be applied for single reward function, and cannot adapt to an unseen…

Machine Learning · Computer Science 2022-01-04 Ziyang Tang , Yihao Feng , Qiang Liu

Learning to follow human instructions is a long-pursued goal in artificial intelligence. The task becomes particularly challenging if no prior knowledge of the employed language is assumed while relying only on a handful of examples to…

Computation and Language · Computer Science 2019-04-03 Rezka Leonandya , Elia Bruni , Dieuwke Hupkes , Germán Kruszewski

Four sections of introductory physics for physical scientists and engineers (about 180 students each) are compared. One section, treatment group, was organized so that students worked to learn the classical ideas connecting forces and…

Physics Education · Physics 2012-10-15 D. J. Webb

Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promising new alignment paradigm to mitigate such failures by…

Machine Learning · Computer Science 2026-05-22 Andy Han , Kristina Fujimoto , Avidan Shah , Kiet Nguyen , Kai Xu , Chen Yueh-Han , Ilia Sucholutsky , Rico Angell

Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectional process--where insights from post-training retroactively…

Computation and Language · Computer Science 2026-02-04 Junjie Huang , Jiarui Qin , Di Yin , Weiwen Liu , Yong Yu , Xing Sun , Weinan Zhang

Accelerator science and technology is inherently an integrative discipline that combines aspects of physics, computational science, electrical and mechanical engineering. As few universities offer full academic programs, the education of…

Accelerator Physics · Physics 2017-08-23 William A. Barletta , Swapan Chattopadhyay , Andrei Seryi

We propose a new framework for building and evaluating machine learning algorithms. We argue that many real-world problems require an agent which must quickly learn to respond to demands, yet can continue to perform and respond to new…

Machine Learning · Computer Science 2007-05-23 Jason E. Holt

Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing…

Artificial Intelligence · Computer Science 2023-10-16 Maryam Zare , Parham M. Kebria , Abbas Khosravi

We propose a method to transfer knowledge across neural machine translation (NMT) models by means of a shared dynamic vocabulary. Our approach allows to extend an initial model for a given language pair to cover new languages by adapting…

Computation and Language · Computer Science 2018-11-06 Surafel M. Lakew , Aliia Erofeeva , Matteo Negri , Marcello Federico , Marco Turchi

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…

Machine Learning · Computer Science 2026-04-16 Mark Rofin , Aditya Varre , Nicolas Flammarion

Fermilab's Integrable Optics Test Accelerator is an electron storage ring designed for testing advanced accelerator physics concepts, including implementation of nonlinear integrable beam optics and experiments on optical stochastic…

Accelerator Physics · Physics 2013-01-29 S. Nagaitsev , A. Valishev , V. V. Danilov , D. N. Shatilov

Learning from demonstration (LfD) is a technique that allows expert teachers to teach task-oriented skills to robotic systems. However, the most effective way of guiding novice teachers to approach expert-level demonstrations quantitatively…

Robotics · Computer Science 2025-05-16 Endong Sun , Yuqing Zhu , Matthew Howard

The IOTA Proton Injector (IPI), currently under installation at the Fermilab Accelerator Science and Technology facility, is a beamline capable of delivering 20-mA pulses of protons at 2.5 MeV to the Integrable Optics Test Accelerator…

Accelerator Physics · Physics 2023-05-18 D. Edstrom , D. Broemmelsiek , K. Carlson , J. -P. Carneiro , H. Piekarz , A. Romanov , A. Shemyakin , A. Valishev

In dynamic simulation of complete wheel loaders, one interesting aspect, specific for the working task, is the momentary power distribution between drive train and hydraulics, which is balanced by the operator. This paper presents the…

Computational Engineering, Finance, and Science · Computer Science 2011-08-30 Reno Filla , Allan Ericsson , Jan-Ove Palmberg

The development of the works of the author about adaptive algorithms of teaching the robotic systems with the help of operator is described here. An operator is assumed to be an experience decision-maker and sane carrier of a target which…

Robotics · Computer Science 2015-09-08 Valery Vilisov