English
Related papers

Related papers: Flash Invariant Point Attention

200 papers

Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It's common that only a few features, called the influential features, meaningfully define the clusters.…

Machine Learning · Computer Science 2026-03-26 Chen Ma , Wanjie Wang , Shuhao Fan

In this paper, we present a deep reinforcement learning platform named FIXAR which employs fixed-point data types and arithmetic units for the first time using a SW/HW co-design approach. Starting from 32-bit fixed-point data,…

Hardware Architecture · Computer Science 2021-02-25 Je Yang , Seongmin Hong , Joo-Young Kim

Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations can be safely removed. While attention scores are commonly…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Samyak Jha , Junho Kim

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its GPU compatibility across all densities. However,…

Machine Learning · Computer Science 2025-08-14 Jialin Zhao , Yingtao Zhang , Carlo Vittorio Cannistraci

Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance. Most existing Vision Transformers divide images into the same number of patches with a fixed size, which may…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Qing Cai , Yiming Qian , Jinxing Li , Jun Lv , Yee-Hong Yang , Feng Wu , David Zhang

Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic processes. While early architectures were developed primarily as a scalable alternative to Gaussian…

AI acceleration has been dominated by GPUs, but the growing need for lower latency, energy efficiency, and fine-grained hardware control exposes the limits of fixed architectures. In this context, Field-Programmable Gate Arrays (FPGAs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Arturo Urías Jiménez

The vanilla self-attention mechanism in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically induced by inputs and whose hidden dimension is equal to the sequence length $N$. As the context extends, the…

Machine Learning · Computer Science 2026-05-12 Qishuai Wen , Zhiyuan Huang , Xianghan Meng , Wei He , Chun-Guang Li

Prior work in multi-task learning has mainly focused on predictions on a single image. In this work, we present a new approach for multi-task learning from videos via efficient inter-frame local attention (MILA). Our approach contains a…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Donghyun Kim , Tian Lan , Chuhang Zou , Ning Xu , Bryan A. Plummer , Stan Sclaroff , Jayan Eledath , Gerard Medioni

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Zhendong Zhang

The term GreenAI refers to a novel approach to Deep Learning, that is more aware of the ecological impact and the computational efficiency of its methods. The promoters of GreenAI suggested the use of Floating Point Operations (FLOPs) as a…

Machine Learning · Computer Science 2025-11-06 Andrea Asperti , Davide Evangelista , Moreno Marzolla

Protein inverse folding, the task of predicting amino acid sequences for desired structures, is pivotal for de novo protein design. However, existing GNN-based methods typically suffer from restricted receptive fields that miss long-range…

Machine Learning · Computer Science 2026-02-05 Sisi Yuan , Jiehuang Chen , Junchuang Cai , Dong Xu , Xueliang Li , Zexuan Zhu , Junkai Ji

Among the array of neural network architectures, the Vision Transformer (ViT) stands out as a prominent choice, acclaimed for its exceptional expressiveness and consistent high performance in various vision applications. Recently, the…

Neural and Evolutionary Computing · Computer Science 2023-11-17 Boxun Xu , Hejia Geng , Yuxuan Yin , Peng Li

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

Factorization Machine (FM) is a widely used supervised learning approach by effectively modeling of feature interactions. Despite the successful application of FM and its many deep learning variants, treating every feature interaction…

Machine Learning · Computer Science 2019-02-28 Fuxing Hong , Dongbo Huang , Ge Chen

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…

Information Retrieval · Computer Science 2024-06-17 Wenhui Yu , Chao Feng , Yanze Zhang , Lantao Hu , Peng Jiang , Han Li

Task failures in prior fine-grained robotic manipulation methods often stem from suboptimal initial grasping, which is critical for subsequent manipulation and reducing the requirement for complex pose adjustments. To address this, we…

Robotics · Computer Science 2025-11-20 Juyi Sheng , Yangjun Liu , Sheng Xu , Zhixin Yang , Mengyuan Liu

As transformers are equivariant to the permutation of input tokens, encoding the positional information of tokens is necessary for many tasks. However, since existing positional encoding schemes have been initially designed for NLP tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Takeru Miyato , Bernhard Jaeger , Max Welling , Andreas Geiger

Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for…

Machine Learning · Computer Science 2025-11-14 Cheng Kevin Qu , Andrew Ly , Pulin Gong
‹ Prev 1 4 5 6 7 8 10 Next ›