Related papers: A Latent Space Framework for Modeling Transient En…
In this work, we aim to optimize the radio resource management of a communication system between a remote controller and its device, whose state is represented through image frames, without compromising the performance of the control task.…
Recently, self-supervised representation learning relying on vast amounts of unlabeled data has been explored as a pre-training method for autonomous driving. However, directly applying popular contrastive or generative methods to this…
Joint-Embedding Predictive Architectures (JEPA) have recently become popular as promising architectures for self-supervised learning. Vision transformers have been trained using JEPA to produce embeddings from images and videos, which have…
Recent advancements in self-supervised learning in the point cloud domain have demonstrated significant potential. However, these methods often suffer from drawbacks, including lengthy pre-training time, the necessity of reconstruction in…
In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow…
Modern Text-to-Image (T2I) generation increasingly relies on token-centric architectures that are trained with self-supervision, yet effectively fusing text with visual tokens remains a challenge. We propose \textbf{JEPA-T}, a unified…
Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask whether latent-space prediction can complement these token-level objectives under matched…
Single-cell foundation models learn by reconstructing masked gene expression, implicitly treating technical noise as signal. With dropout rates exceeding 90%, reconstruction objectives encourage models to encode measurement artifacts rather…
Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable…
The joint-embedding predictive architecture (JEPA) recently has shown impressive results in extracting visual representations from unlabeled imagery under a masking strategy. However, we reveal its disadvantages, notably its insufficient…
Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator…
Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while capturing hidden structure. We recast maximum-likelihood…
Current automated systems have crucial limitations that need to be addressed before artificial intelligence can reach human-like levels and bring new technological revolutions. Among others, our societies still lack Level 5 self-driving…
Machine learning has recently gained traction as a way to overcome the slow accelerator generation and implementation process on an FPGA. It can be used to build performance and resource usage models that enable fast early-stage design…
World models require robust relational understanding to support prediction, reasoning, and control. While object-centric representations provide a useful abstraction, they are not sufficient to capture interaction-dependent dynamics. We…
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables. The joint density of a CEBM decomposes into an intractable distribution over…
Accurate traffic prediction is vital for effective traffic management during hurricane evacuation. This paper proposes a predictive modeling system that integrates Multilayer Perceptron (MLP) and Long-Short Term Memory (LSTM) models to…
This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a broader goal of promoting identifiable and decoupled latent organization by assigning…
Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues,…
In recent advancements in unsupervised visual representation learning, the Joint-Embedding Predictive Architecture (JEPA) has emerged as a significant method for extracting visual features from unlabeled imagery through an innovative…