Related papers: Multi-Task Learning with Multi-Query Transformer f…

Predicting time-series is of great importance in various scientific and engineering fields. However, in the context of limited and noisy data, accurately predicting dynamics of all variables in a high-dimensional system is a challenging…

To improve persistence diagram representation learning, we propose Multiset Transformer. This is the first neural network that utilizes attention mechanisms specifically designed for multisets as inputs and offers rigorous theoretical…

Data-efficient neural decoding is a central challenge for speech brain-computer interfaces. We present the first demonstration of transfer learning and cross-task decoding for MEG-based speech models spanning perception and production. We…

This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…

Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have…

Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction. They apply uni-directional…

Due to shortage of water resources and increasing water demands, the joint operation of multireservoir systems for balancing power generation, ecological protection, and the residential water supply has become a critical issue in hydropower…

Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that…

In this paper, we propose an encoder-decoder neural architecture (called Channelformer) to achieve improved channel estimation for orthogonal frequency-division multiplexing (OFDM) waveforms in downlink scenarios. The self-attention…

Although transformer has achieved great progress on computer vision tasks, the scale variation in dense image prediction is still the key challenge. Few effective multi-scale techniques are applied in transformer and there are two main…

Predictive business process monitoring focuses on predicting future characteristics of a running process using event logs. The foresight into process execution promises great potentials for efficient operations, better resource management,…

Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented, which increases…

Transformer-based models are unable to process long sequences due to their self-attention operation, which scales quadratically with the sequence length. To address this limitation, we introduce the Longformer with an attention mechanism…

Complex Logical Query Answering (CLQA) over incomplete knowledge graphs is a challenging task. Recently, Query Embedding (QE) methods are proposed to solve CLQA by performing multi-hop logical reasoning. However, most of them only consider…

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task…

Aiming at the problems of computational inefficiency and insufficient interpretability faced by large models in complex tasks such as multi-round reasoning and multi-modal collaboration, this study proposes a three-layer collaboration…