Related papers: AdaGen: Learning Adaptive Policy for Image Synthes…

Effectively addressing the challenge of industrial Anomaly Detection (AD) necessitates an ample supply of defective samples, a constraint often hindered by their scarcity in industrial contexts. This paper introduces a novel algorithm…

Humans excel at discovering regular structures from limited samples and applying inferred rules to novel settings. We investigate whether modern generative models can similarly learn underlying rules from finite samples and perform…

The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm…

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the learning rates for…

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse attention - enhance inference speed but typically rely on a…

Deep generative models are proven to be a useful tool for automatic design synthesis and design space exploration. When applied in engineering design, existing generative models face three challenges: 1) generated designs lack diversity and…

Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these models is tributary to the availability of large collections…

To improve business efficiency and minimize costs, Artificial Intelligence (AI) practitioners have adopted a shift from formulating models from scratch towards sharing pretrained models. The pretrained models are then aggregated into a…

Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution…

We introduce Adaptive Procedural Task Generation (APT-Gen), an approach to progressively generate a sequence of tasks as curricula to facilitate reinforcement learning in hard-exploration problems. At the heart of our approach, a task…

Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: 1) Training multiple networks increases the run time and affects the convergence and stability of the generative…

Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations due to limited data diversity. Leveraging powerful 3D generative models and vision…

Diffusion models are emerging expressive generative models, in which a large number of time steps (inference steps) are required for a single image generation. To accelerate such tedious process, reducing steps uniformly is considered as an…

Recently, Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation. However, a notable discrepancy exists between their training and inference procedures. In particular, MDM inference…

To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy…

In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale deep learning models without sacrificing model performance.…

World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training,…

Autoregressive (AR) models have garnered significant attention in image generation for their ability to effectively capture both local and global structures within visual data. However, prevalent AR models predominantly rely on the…