相关论文: PAROAttention: Pattern-Aware ReOrdering for Effici…

Attention mechanism has been crucial for image diffusion models, however, their quadratic computational complexity limits the sizes of images we can process within reasonable time and memory constraints. This paper investigates the…

The design of Large Language Models (LLMs) has long been hampered by a fundamental conflict within their core attention mechanism: its remarkable expressivity is built upon a computational complexity of O(H N^2) that grows quadratically…

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block…

Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…

Recently, Transformers have shown promising performance in various vision tasks. However, the high costs of global self-attention remain challenging for Transformers, especially for high-resolution vision tasks. Inspired by one of the most…

Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sampling. Recent methods reduce cost by compressing width, depth, or sampling steps, but…

Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…

Attention mechanisms are the core of foundation models, but their quadratic complexity remains a critical bottleneck for scaling. This challenge has driven the development of efficient attention mechanisms, with sparsity emerging as the…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

Attention-based models have revolutionized AI, but the quadratic cost of self-attention incurs severe computational and memory overhead. Sparse attention methods alleviate this by skipping low-relevance token pairs. However, current…

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Recent advances in diffusion models have enabled high-quality video generation, but the additional temporal dimension significantly increases computational costs, making training and inference on long videos prohibitively expensive. In this…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. Uniform post-training quantization (PTQ) methods are common, since they can be implemented efficiently in hardware…

State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are…

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications by updating only a small subset of parameters. While current PEFT methods have…

Efficient long-context understanding and reasoning are increasingly vital for large language model (LLM) applications such as multi-turn dialogue and program analysis. However, the core self-attention mechanism scales quadratically with…

The quadratic computational cost of the self-attention mechanism is a primary challenge in scaling Transformer models. While attention sparsity is widely studied as a technique to improve computational efficiency, it is almost universally…