Related papers: Training new operators - the first six months

Two current methods used to train autonomous cars are reinforcement learning and imitation learning. This research develops a new learning methodology and systematic approach in both a simulated and a smaller real world environment by…

Pre-training has been investigated to improve the efficiency and performance of training neural operators in data-scarce settings. However, it is largely in its infancy due to the inherent complexity and diversity, such as long…

The fast growing capabilities of large-scale deep learning models, such as Bert, GPT and ViT, are revolutionizing the landscape of NLP, CV and many other domains. Training such models, however, poses an unprecedented demand for computing…

Pre-training on large datasets of robot demonstrations is a powerful technique for learning diverse manipulation skills but is often limited by the high cost and complexity of collecting robot-centric data, especially for tasks requiring…

The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large…

On-robot Reinforcement Learning is a promising approach to train embodiment-aware policies for legged robots. However, the computational constraints of real-time learning on robots pose a significant challenge. We present a framework for…

The process of discovery in the physical, biological and medical sciences can be painstakingly slow. Most experiments fail, and the time from initiation of research until a new advance reaches commercial production can span 20 years. This…

The Integrable Optics Test Accelerator (IOTA) is a research storage ring constructed and operated at Fermilab to demonstrate the advantages of nonlinear integrable lattices. One of the nonlinear lattice configurations with one integral of…

We present a new training methodology for transformers using a multilevel, layer-parallel approach. Through a neural ODE formulation of transformers, our application of a multilevel parallel-in-time algorithm for the forward and…

The short-loading cycle is a repetitive task performed in high quantities, making it a great alternative for automation. In the short-loading cycle, an expert operator navigates towards a pile, fills the bucket with material, navigates to a…

Learning from demonstration (LfD) is commonly considered to be a natural and intuitive way to allow novice users to teach motor skills to robots. However, it is important to acknowledge that the effectiveness of LfD is heavily dependent on…

Energy optimization leveraging artificially intelligent algorithms has been proven effective. However, when buildings are commissioned, there is no historical data that could be used to train these algorithms. On-line Reinforcement Learning…

General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to…

After a 14 month shutdown accelerator modifications and upgrades are in place to allow us doubling of the Main Injector beam power. We will discuss the past MI high power operation and the current progress towards doubling the power.

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…

Flow map models such as Consistency Models (CM) and Mean Flow (MF) enable few-step generation by learning the long jump of the ODE solution of diffusion models, yet training remains unstable, sensitive to hyperparameters, and costly.…

This paper provides a short overview of how to use machine learning to build data-driven models in fluid mechanics. The process of machine learning is broken down into five stages: (1) formulating a problem to model, (2) collecting and…

Modernizing the Fermilab accelerator control system is essential to future operations of the laboratory's accelerator complex. The existing control system has evolved over four decades and uses hardware that is no longer available and…

Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…

During language acquisition, children follow a typical sequence of learning stages, whereby they first learn to categorize phonemes before they develop their lexicon and eventually master increasingly complex syntactic structures. However,…