Related papers: Probabilistic Attention for Interactive Segmentati…

Incremental learning of semantic segmentation has emerged as a promising strategy for visual scene interpretation in the open- world setting. However, it remains challenging to acquire novel classes in an online fashion for the segmentation…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Attention is an operation that selects some largest element from some set, where the notion of largest is defined elsewhere. Applying this operation to sequence to sequence mapping results in significant improvements to the task at hand. In…

Most cognitive architectures rely on discrete representation, both in space (e.g., objects) and in time (e.g., events). However, a robot interaction with the world is inherently continuous, both in space and in time. The segmentation of the…

Transformers are state-of-the-art in a wide range of NLP tasks and have also been applied to many real-world products. Understanding the reliability and certainty of transformer model predictions is crucial for building trustable machine…

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

Attention-based models are successful when trained on large amounts of data. In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively. To this end, we start with discrete human-annotated…

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

In this paper, we extend the standard Attention in transformer by exploiting the consensus discrepancy from a distributed optimization perspective, referred to as AttentionX. It is noted that the primal-dual method of multipliers (PDMM)…

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Transformer-based models consist of interleaved feed-forward blocks - that capture content meaning, and relatively more expensive self-attention blocks - that capture context meaning. In this paper, we explored trade-offs and ordering of…

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their…

The standard paradigm of modeling marked point processes is by parameterizing the intensity function using an attention-based (Transformer-style) architecture. Despite the flexibility of these methods, their inference is based on the…

Learning high-quality embeddings for rare words is a hard problem because of sparse context information. Mimicking (Pinter et al., 2017) has been proposed as a solution: given embeddings learned by a standard algorithm, a model is first…

In many real-world applications, users rely on natural language instructions to guide large language models (LLMs) across a wide range of tasks. These instructions are often complex, diverse, and subject to frequent change. However, LLMs do…

Visual affordances identify regions in an image with potential interactions, offering a novel paradigm for scene understanding. Recognizing affordances allows autonomous robots to act more naturally, could enhance human-robot interactions,…

The change point is a moment of an abrupt alteration in the data distribution. Current methods for change point detection are based on recurrent neural methods suitable for sequential data. However, recent works show that transformers based…

Most state-of-the-art neural machine translation systems, despite being different in architectural skeletons (e.g. recurrence, convolutional), share an indispensable feature: the Attention. However, most existing attention methods are…

Information diffusion prediction aims at predicting the target users in the information diffusion path on social networks. Prior works mainly focus on the observed structure or sequence of cascades, trying to predict to whom this cascade…

While modern text-to-image models excel at prompt-based generation, they often lack the fine-grained control necessary for specific user requirements like spatial layouts or subject appearances. Multi-condition control addresses this, yet…