Related papers: AdaPerceiver: Transformers with Adaptive Width, De…

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…

Vision transformers have delivered tremendous success in representation learning. This is primarily due to effective token mixing through self attention. However, this scales quadratically with the number of pixels, which becomes infeasible…

One of the main challenges of Topological Data Analysis (TDA) is to extract features from persistent diagrams directly usable by machine learning algorithms. Indeed, persistence diagrams are intrinsically (multi-)sets of points in…

Transformers are at the core of modern AI nowadays. They rely heavily on matrix multiplication and require efficient acceleration due to their substantial memory and computational requirements. Quantization plays a vital role in reducing…

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of computer vision (image…

Attention-based models such as transformers have shown outstanding performance on dense prediction tasks, such as semantic segmentation, owing to their capability of capturing long-range dependency in an image. However, the benefit of…

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…

Despite the recent success of deep learning models in numerous applications, their widespread use on mobile devices is seriously impeded by storage and computational requirements. In this paper, we propose a novel network compression method…

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

In the era of foundation models, achieving a unified understanding of different dynamic objects through a single network has the potential to empower stronger spatial intelligence. Moreover, accurate estimation of animal pose and shape…

Accurate and computationally efficient 3D medical image segmentation remains a critical challenge in clinical workflows. Transformer-based architectures often demonstrate superior global contextual modeling but at the expense of excessive…

As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…

Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…

Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, and scaling laws seem to be the most successful strategy:…

The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at…

Depth-adaptive neural networks can dynamically adjust depths according to the hardness of input words, and thus improve efficiency. The main challenge is how to measure such hardness and decide the required depths (i.e., layers) to conduct.…

Recent years have witnessed the increasing application of place recognition in various environments, such as city roads, large buildings, and a mix of indoor and outdoor places. This task, however, still remains challenging due to the…

Recently, vision transformers (ViTs) have achieved excellent performance on vision tasks by measuring the global self-attention among the image patches. Given $n$ patches, they will have quadratic complexity such as $\mathcal{O}(n^2)$ and…

Multivariate time series forecasting involves predicting future values based on historical observations. However, existing approaches primarily rely on predefined single-scale patches or lack effective mechanisms for multi-scale feature…

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…