Related papers: Learning Generalizable Program and Architecture Re…

The ability to plan for multi-step manipulation tasks in unseen situations is crucial for future home robots. But collecting sufficient experience data for end-to-end learning is often infeasible in the real world, as deploying robots in…

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL…

Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and…

Precise load forecasting in buildings could increase the bill savings potential and facilitate optimized strategies for power generation planning. With the rapid evolution of computer science, data-driven techniques, in particular the Deep…

Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative…

With the tremendous success of deep learning in visual tasks, the representations extracted from intermediate layers of learned models, that is, deep features, attract much attention of researchers. Previous empirical analysis shows that…

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…

A video prediction model that generalizes to diverse scenes would enable intelligent agents such as robots to perform a variety of tasks via planning with the model. However, while existing video prediction models have produced promising…

Generalization of time series prediction remains an important open issue in machine learning, wherein earlier methods have either large generalization error or local minima. We develop an analytically solvable, unsupervised learning scheme…

Pretrained encoders for mathematical texts have achieved significant improvements on various tasks such as formula classification and information retrieval. Yet they remain limited in representing and capturing student strategies for entire…

Recently, large language and vision models (LLVMs) have received significant attention and development efforts due to their remarkable generalization performance across a wide range of tasks requiring perception and cognitive abilities. A…

Most Neural Radiance Fields (NeRFs) exhibit limited generalization capabilities, which restrict their applicability in representing multiple scenes using a single model. To address this problem, existing generalizable NeRF methods simply…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep…

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to…

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and multimodal understanding capability, which quickly set new…

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain…

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to…