Related papers: Apprentice for Event Generator Tuning
We present the design of the simulation package Pluto, aimed at the study of hadronic interactions at SIS and FAIR energies. Its main mission is to offer a modular framework with an object-oriented structure, thereby making additions such…
Studies of writing revisions rarely focus on revision quality. To address this issue, we introduce a corpus of between-draft revisions of student argumentative essays, annotated as to whether each revision improves essay quality. We…
Recent developments in QCD phenomenology have spurred on several improved approaches to Monte Carlo event generation, relative to the post--LEP state of the art. In this brief review, the emphasis is placed on approaches for 1) consistently…
MCgrid is a software package that provides access to the APPLgrid interpolation tool for Monte Carlo event generator codes, allowing for fast and flexible variations of scales, coupling parameters and PDFs in cutting edge leading and…
Event generators are an indispensable tool for the preparation and analysis of particle-physics experiments. In this contribution, physics principles underlying the construction of such computer programs are discussed. Results, within and…
Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture…
Multi-class classification annotations have significantly advanced AI applications, with truth inference serving as a critical technique for aggregating noisy and biased annotations. Existing state-of-the-art methods typically model each…
This paper presents a robust adaptive learning Model Predictive Control (MPC) framework for linear systems with parametric uncertainties and additive disturbances performing iterative tasks. The approach refines the parameter estimates…
This paper presents a systematic method for the selection of the Model Predictive Control (MPC) stage cost. We match the MPC feedback law to a proportional-integral (PI) controller, which we efficiently tune by high-performance Monte Carlo…
Reinforcement learning synthesizes controllers without prior knowledge of the system. At each timestep, a reward is given. The controllers optimize the discounted sum of these rewards. Applying this class of algorithms requires designing a…
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…
The fine-tuning of pre-trained models has become ubiquitous in generative AI, computer vision, and robotics. Although much attention has been paid to improving the efficiency of fine-tuning model, there has been less scholarship around…
We propose a novel training method based on nonlinear multilevel minimization techniques, commonly used for solving discretized large scale partial differential equations. Our multilevel training method constructs a multilevel hierarchy by…
Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization…
Optimization models used to make discrete decisions often contain uncertain parameters that are context-dependent and estimated through prediction. To account for the quality of the decision made based on the prediction, decision-focused…
The last decade has seen an explosive growth of interest in exploiting developments in machine learning to accelerate lattice QCD calculations. On the sampling side, generative models are a promising approach to mitigating critical slowing…
By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…
One of the goals of learning algorithms is to complement and reduce the burden on human decision makers. The expert deferral setting wherein an algorithm can either predict on its own or defer the decision to a downstream expert helps…
Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks…
We present LLM Trainer, a fully automated pipeline that leverages the world knowledge of Large Language Models (LLMs) to transform a small number of human demonstrations (as few as one) into a large robot dataset for imitation learning. Our…