Related papers: Fast-iTPN: Integrally Pre-Trained Transformer Pyra…

Learning pyramidal feature representations is crucial for recognizing object instances at different scales. Feature Pyramid Network (FPN) is the classic architecture to build a feature pyramid with high-level semantics throughout. However,…

Feature pyramid network (FPN) is one of the key components for object detectors. However, there is a long-standing puzzle for researchers that the detection performance of large-scale objects are usually suppressed after introducing FPN. To…

We propose an efficient approach to train large diffusion models with masked transformers. While masked transformers have been extensively explored for representation learning, their application to generative learning is less explored in…

Neural Processes (NPs) have gained attention in meta-learning for their ability to quantify uncertainty, together with their rapid prediction and adaptability. However, traditional NPs are prone to underfitting. Transformer Neural Processes…

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary…

In engineering design, navigating complex decision-making landscapes demands a thorough exploration of the design, performance, and constraint spaces, often impeded by resource-intensive simulations. Data-driven methods can mitigate this…

The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers). Our work is…

Fine-tuning a pre-trained deep neural network has become a successful paradigm in various machine learning tasks. However, such a paradigm becomes particularly challenging with tabular data when there are discrepancies between the feature…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive…

Nowadays, scene text recognition has attracted more and more attention due to its various applications. Most state-of-the-art methods adopt an encoder-decoder framework with attention mechanism, which generates text autoregressively from…

The encoder-decoder framework is state-of-the-art for offline semantic image segmentation. Since the rise in autonomous systems, real-time computation is increasingly desirable. In this paper, we introduce fast segmentation convolutional…

Vision Transformer (ViT) has achieved impressive results across various vision tasks, yet its high computational cost limits practical applications. Recent methods have aimed to reduce ViT's $O(n^2)$ complexity by pruning unimportant…

Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have led to significant progress in 2D body pose estimation. However, achieving a good balance between accuracy, efficiency, and robustness remains a challenge. For…

This paper introduces ITA-MDT, the Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On (IVTON), designed to overcome the limitations of previous approaches by leveraging the Masked Diffusion…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Although deep convolutional neural networks (CNNs) have achieved great success in computer vision tasks, its real-world application is still impeded by its voracious demand of computational resources. Current works mostly seek to compress…

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…

Physics-Informed Neural Networks (PINNs) have emerged as powerful tools for solving partial differential equations (PDEs). However, training PINNs from scratch is often computationally intensive and time-consuming. To address this problem,…

Through exploiting a high level of parallelism enabled by graphics processing units, transformer architectures have enabled tremendous strides forward in the field of natural language processing. In a traditional masked language model,…