Related papers: A Latent Space Framework for Modeling Transient En…

This study introduces the Perception Latency Mitigation Network (PLM-Net), a modular deep learning framework designed to mitigate perception latency in vision-based imitation-learning lane-keeping systems. Perception latency, defined as the…

Time series data is a prevalent form of data found in various fields. It consists of a series of measurements taken over time. Forecasting is a crucial application of time series models, where future values are predicted based on historical…

This work introduces an ensemble parameter estimation framework that enables the Lumped Parameter Linear Superposition (LPLSP) method to generate reduced order thermal models from a single transient dataset. Unlike earlier implementations…

The long-tailed distribution of sequence lengths in LLM serving and reinforcement learning (RL) sampling causes significant computational waste due to excessive padding in batched inference. Existing methods rely on auxiliary models for…

Obtaining accurate estimates of uncertainty in climate scenarios often requires generating large ensembles of high-resolution climate simulations, a computationally expensive and memory intensive process. To address this challenge, we train…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…

This paper investigates trajectory prediction for robotics, to improve the interaction of robots with moving targets, such as catching a bouncing ball. Unexpected, highly-non-linear trajectories cannot easily be predicted with…

We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulator that captures…

Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pixel variation rather than action-relevant state transitions,…

We present EnergyLens, an end-to-end framework for energy-aware large language model (LLM) inference optimization. As LLMs scale, predicting and reducing their energy footprint has become critical for sustainability and datacenter…

Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended…

Critical events in multivariate time series, from turbine failures to cardiac arrhythmias, demand accurate prediction, yet labeled data is scarce because such events are rare and costly to annotate. We introduce HEPA (Horizon-conditioned…

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to…

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

High-dimensional observations and unknown dynamics are major challenges when applying optimal control to many real-world decision making tasks. The Learning Controllable Embedding (LCE) framework addresses these challenges by embedding the…

Large Language Models (LLMs) obey consistent scaling laws -- empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these laws are descriptive rather than prescriptive: they…

State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computational cost. Light-weight architectures, on the other hand,…

Weather prediction is a quintessential problem involving the forecasting of a complex, nonlinear, and chaotic high-dimensional dynamical system. This work introduces an efficient reduced-order modeling (ROM) framework for short-range…

Time series forecasting plays a crucial role in diverse fields, necessitating the development of robust models that can effectively handle complex temporal patterns. In this article, we present a novel feature selection method embedded in…

Latent space steering methods provide a practical approach to controlling large language models by applying steering vectors to intermediate activations, guiding outputs toward desired behaviors while avoiding retraining. Despite their…