相关论文: Maximizing the Position Embedding for Vision Trans…

Since Transformers are introduced into vision architectures, their quadratic complexity has always been a significant issue that many research efforts aim to address. A representative approach involves grouping tokens, performing…

Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…

Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental question: what aspect of the target…

Over the past few years, the vision transformer and its various forms have gained significance in human pose estimation. By treating image patches as tokens, transformers can capture global relationships wisely, estimate the keypoint tokens…

Transformer-based methods have achieved state-of-the-art performance in time series forecasting (TSF) by capturing positional and semantic topological relationships among input tokens. However, it remains unclear whether existing…

Despite the success of vision transformers (ViTs), they still suffer from significant drops in accuracy in the presence of common corruptions, such as noise or blur. Interestingly, we observe that the attention mechanism of ViTs tends to…

Vision Transformers naturally accommodate sparsity, yet standard tokenization methods confine features to discrete patch grids. This constraint prevents models from fully exploiting sparse regimes, forcing awkward compromises. We propose…

Representation Engineering (RepE) has emerged as a powerful paradigm for enhancing AI transparency by focusing on high-level representations rather than individual neurons or circuits. It has proven effective in improving interpretability…

By quantizing network weights and activations to low bitwidth, we can obtain hardware-friendly and energy-efficient networks. However, existing quantization techniques utilizing the straight-through estimator and piecewise constant…

Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their…

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Tables are ubiquitous across various domains for concisely representing structured information. Empowering large language models (LLMs) to reason over tabular data represents an actively explored direction. However, since typical LLMs only…

Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural networks (MPNNs) face well-documented theoretical and…

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

Global pooling is one of the most significant operations in many machine learning models and tasks, which works for information fusion and structured data (like sets and graphs) representation. However, without solid mathematical…

Even for simple arithmetic tasks like integer addition, it is challenging for Transformers to generalize to longer sequences than those encountered during training. To tackle this problem, we propose position coupling, a simple yet…

Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images. However, the imaging gaps between platforms are often significant and the variations in…

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…

Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instruction-conditioning has become the dominant approach for…

In recent years, network embedding methods have garnered increasing attention because of their effectiveness in various information retrieval tasks. The goal is to learn low-dimensional representations of vertexes in an information network…