相关论文: Value Residual Learning

Transformer-based models have gained increasing popularity achieving state-of-the-art performance in many research fields including speech translation. However, Transformer's quadratic complexity with respect to the input sequence length…

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

The block-based coding structure in the hybrid video coding framework inevitably introduces compression artifacts such as blocking, ringing, etc. To compensate for those artifacts, extensive filtering techniques were proposed in the loop of…

Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video…

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…

Although convolutional neural networks (CNNs) have achieved remarkable progress in weakly supervised semantic segmentation (WSSS), the effective receptive field of CNN is insufficient to capture global context information, leading to…

Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

Transformers, a cornerstone of deep-learning architectures for sequential data, have achieved state-of-the-art results in tasks like Natural Language Processing (NLP). Models such as BERT and GPT-3 exemplify their success and have driven…

The past several years have witnessed Variational Auto-Encoder's superiority in various text generation tasks. However, due to the sequential nature of the text, auto-regressive decoders tend to ignore latent variables and then reduce to…

While LLMs are powerful embedding backbones, their application in training-free settings faces two structural challenges: causal attention restricts early tokens from accessing subsequent context, and the next-token prediction objective…

Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks while taking advantage of parallel processing. Recently, we proposed the SepFormer, which obtains…

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address…

Recent advancements in semantic communication have primarily focused on image transmission, where neural network-based joint source-channel coding modules play a central role. However, such systems often experience semantic communication…

Transformers are the de-facto choice for sequence modelling, yet their quadratic self-attention and weak temporal bias can make long-range forecasting both expensive and brittle. We introduce FreezeTST, a lightweight hybrid that interleaves…

Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design. It can be found in classical CNN architectures and in automatic discovered models. Even CNS methods…

In this paper, we propose an efficient transformer architecture that uses reinforced positional embedding to obtain superior performance with half the number of encoder decoder layers. We demonstrate that concatenating positional encoding…

KV cache compression methods have mainly relied on scalar quantization techniques to reduce the memory requirements during decoding. In this work, we apply residual vector quantization, which has been widely used for high fidelity audio…