Related papers: Compact Recurrent Transformer with Persistent Memo…

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…

Transformers have become the cornerstone of modern large-scale language models, but their reliance on softmax attention poses a computational bottleneck at both training and inference. Recurrent models offer high efficiency, but compressing…

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is…

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

The Transformer model is widely successful on many natural language processing tasks. However, the quadratic complexity of self-attention limit its application on long text. In this paper, adopting a fine-to-coarse attention mechanism on…

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

Neural end-to-end text-to-speech (TTS) , which adopts either a recurrent model, e.g. Tacotron, or an attention one, e.g. Transformer, to characterize a speech utterance, has achieved significant improvement of speech synthesis. However, it…

Self-attention has recently been adopted for a wide range of sequence modeling problems. Despite its effectiveness, self-attention suffers from quadratic compute and memory requirements with respect to sequence length. Successful approaches…

The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes-glial cells critical for biological…

Transformers have emerged as the architecture of choice for many state-of-the-art AI models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands imposed by Transformers limit their ability…

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as recurrent memory for the next token. Because this source…

Transformer-based methods have demonstrated impressive performance in low-level visual tasks such as Image Super-Resolution (SR). However, its computational complexity grows quadratically with the spatial resolution. A series of works…

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs…

Long short-term memory (LSTM) recurrent neural networks (RNNs) have been shown to give state-of-the-art performance on many speech recognition tasks, as they are able to provide the learned dynamically changing contextual window of all…

Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL) based post-training methods. While longer reasoning traces can improve…

We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. This hybrid approach maintains RNN-T's streaming capability…

Transformer-based approaches have revolutionized image super-resolution by modeling long-range dependencies. However, the quadratic computational complexity of vanilla self-attention mechanisms poses significant challenges, often leading to…

Temporal action segmentation is a topic of increasing interest, however, annotating each frame in a video is cumbersome and costly. Weakly supervised approaches therefore aim at learning temporal action segmentation from videos that are…

The analysis of long sequence data remains challenging in many real-world applications. We propose a novel architecture, ChunkFormer, that improves the existing Transformer framework to handle the challenges while dealing with long time…