Related papers: The Conformer Encoder May Reverse the Time Dimensi…

We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computational resource…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection. With models trained on the normal data, the reconstruction errors of anomalous scenes are usually much larger than…

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

Dynamic graph learning is essential for applications involving temporal networks and requires effective modeling of temporal relationships. Seminal attention-based models like TGAT and DyGFormer rely on sinusoidal time encoders to capture…

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What is its essence? Are…

Time series anomaly detection is important in modern large-scale systems and is applied in a variety of domains to analyze and monitor the operation of diverse systems. Unsupervised approaches have received widespread interest, as they do…

Multimodal large language models (MLLMs) recently showed strong capacity in integrating data among multiple modalities, empowered by a generalizable attention architecture. Advanced methods predominantly focus on language-centric tuning…

Cross encoders (CEs) are trained with sentence pairs to detect relatedness. As CEs require sentence pairs at inference, the prevailing view is that they can only be used as re-rankers in information retrieval pipelines. Dual encoders (DEs)…

Neural IR architectures, particularly cross-encoders, are highly effective models whose internal mechanisms are mostly unknown. Most works trying to explain their behavior focused on high-level processes (e.g., what in the input influences…

We propose the first method to adaptively modify the duration of a given speech signal. Our approach uses a Bayesian framework to define a latent attention map that links frames of the input and target utterances. We train a masked…

We present AttentionBender, a tool that manipulates cross-attention in Video Diffusion Transformers to help artists probe the internal mechanics of black-box video generation. While generative outputs are increasingly realistic, prompt-only…

The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to…

Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However,…

Although Transformer models such as Google's BERT and OpenAI's GPT-3 are successful in many natural language processing tasks, training and deploying these models are costly and inefficient.Even if pre-trained models are used, deploying…

Frame prediction based on AutoEncoder plays a significant role in unsupervised video anomaly detection. Ideally, the models trained on the normal data could generate larger prediction errors of anomalies. However, the correlation between…

Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades. However, in practice, they suffer from a problem called posterior collapse, which occurs when the encoder…

Due to the mismatch between the source and target domains, how to better utilize the biased word information to improve the performance of the automatic speech recognition model in the target domain becomes a hot research topic. Previous…

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…