相关论文: ELASTIC: Efficient Linear Attention for Sequential…

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention retains quadratic complexity, making them computationally…

Transformer architectures have led to remarkable progress in many state-of-art applications. However, despite their successes, modern transformers rely on the self-attention mechanism, whose time- and space-complexity is quadratic in the…

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…

Transformer architectures are now central to sequence modeling tasks. At its heart is the attention mechanism, which enables effective modeling of long-term dependencies in a sequence. Recently, transformers have been successfully applied…

Sparse-Linear Attention (SLA) combines sparse and linear attention to accelerate diffusion models and has shown strong performance in video generation. However, (i) SLA relies on a heuristic split that assigns computations to the sparse or…

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Image compression is a widely used technique to reduce the spatial redundancy in images. Recently, learning based image compression has achieved significant progress by using the powerful representation ability from neural networks.…

The attention mechanism in Transformers is an important primitive for accurate and scalable sequence modeling. Its quadratic-compute and linear-memory complexity however remain significant bottlenecks. Linear attention and state-space…

The quadratic complexity of self-attention in Transformer models remains a significant bottleneck for processing long sequences and deploying large language models efficiently. For this approach, there has been significant research into…

To mitigate the computational complexity in the self-attention mechanism on long sequences, linear attention utilizes computation tricks to achieve linear complexity, while state space models (SSMs) popularize a favorable practice of using…

First-order optimization methods are crucial for solving large-scale data processing problems, particularly those involving convex non-smooth composite objectives. For such problems with convex non-smooth composite objectives, we introduce…

Large language models (LLMs) have recently demonstrated strong potential for sequential recommendation. However, current LLM-based approaches face critical limitations in modeling users' long-term and diverse interests. First, due to…

The lifelong user behavior sequence provides abundant information of user preference and gains impressive improvement in the recommendation task, however increases computational consumption significantly. To meet the severe latency…

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and inefficient. In this paper, we introduce Compressed Latent…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse…

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Attribute-aware sequential recommendation entails predicting the next item a user will interact with based on a chronologically ordered history of past interactions, enriched with item attributes. Existing methods typically leverage…

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…