Related papers: Conditional Positional Encodings for Vision Transf…

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE), such as RoPE, need extrapolating to unseen positions which…

When it comes to clinical images, automatic segmentation has a wide variety of applications and a considerable diversity of input domains, such as different types of Magnetic Resonance Images (MRIs) and Computerized Tomography (CT) scans.…

This study reports an unintuitive finding that positional encoding enhances learning of recurrent neural networks (RNNs). Positional encoding is a high-dimensional representation of time indices on input data. Most famously, positional…

Conditional entropy models effectively leverage spatio-temporal contexts to reduce video redundancy. However, incorporating temporal context often introduces additional model complexity and increases computational cost. In parallel, many…

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial…

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, precise coordinate prediction remains a significant challenge, particularly as high-resolution inputs cause visual positional encodings (VPEs) to…

Human pose estimation (HPE) usually requires large-scale training data to reach high performance. However, it is rather time-consuming to collect high-quality and fine-grained annotations for human body. To alleviate this issue, we revisit…

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows $SE(3)$-invariant attention with multi-frequency similarity, and can…

Operator learning for Partial Differential Equations (PDEs) is rapidly emerging as a promising approach for surrogate modeling of intricate systems. Transformers with the self-attention mechanism$\unicode{x2013}$a powerful tool originally…

Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditional VAEs provide an attractive solution. To…

Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and…

Accurate predictions rely on the expressiveness power of graph deep learning frameworks like graph neural networks and graph transformers, where a positional encoding mechanism has become much more indispensable in recent state-of-the-art…

Systems involving human-robot collaboration necessarily require that steps be taken to ensure safety of the participating human. This is usually achievable if accurate, reliable estimates of the human's pose are available. In this paper, we…

Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits…

We present a central-peripheral vision-inspired framework (CVP), a simple yet effective multimodal model for spatial reasoning that draws inspiration from the two types of human visual fields -- central vision and peripheral vision.…

Real-time, accurate prediction of human steering behaviors has wide applications, from developing intelligent traffic systems to deploying autonomous driving systems in both real and simulated worlds. In this paper, we present ContextVAE, a…

Extending large language models (LLMs) to process longer inputs is crucial for a wide range of applications. However, the substantial computational cost of transformers and limited generalization of positional encoding restrict the size of…

Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial for downstream tasks. However, existing methods primarily…

In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position, our BiPE blends an intra-segment encoding and an…