Related papers: Enhancing JEPAs with Spatial Conditioning: Robust …
In this work, we propose a novel data-driven machine learning (ML) technique to model and predict the dynamics of the wireless propagation environment in latent space. Leveraging the idea of channel charting, which learns compressed…
We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding. The approach combines four key components. First,…
Joint Embedding Predictive Architectures (JEPA) are a novel self supervised training technique that have shown recent promise across domains. We introduce BERT-JEPA (BEPA), a training paradigm that adds a JEPA training objective to…
Self-supervised audio representation learning offers an attractive alternative for obtaining generic audio embeddings, capable to be employed into various downstream tasks. Published approaches that consider both audio and words/tags…
Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…
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…
Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video…
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the…
Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…
Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminate the reliance on labels, most of them cannot maintain…
We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…
Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…
Image change detection (ICD) to detect changed objects in front of a vehicle with respect to a place-specific background model using an on-board monocular vision system is a fundamental problem in intelligent vehicle (IV). From the…
Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs. For autoregressive language-model fine-tuning the…
Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been explored to define…
Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods,…
Recently introduced Contrastive Language-Image Pre-Training (CLIP) bridges images and text by embedding them into a joint latent space. This opens the door to ample literature that aims to manipulate an input image by providing a textual…
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is…
Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can…
In wireless networked control systems, ensuring timely and reliable state updates from distributed devices to remote controllers is essential for robust control performance. However, when multiple devices transmit high-dimensional states…