English
Related papers

Related papers: KV-weights are all you need for skipless transform…

200 papers

Large Vision Language Models show impressive performance across image and video understanding tasks, yet their computational cost grows rapidly with the number of visual tokens. Existing token pruning methods mitigate this issue through…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Dong-Jae Lee , Sunghyun Baek , Junmo Kim

Compressing the KV cache is a required step to deploy large language models on edge devices. Current quantization methods compress storage but fail to reduce bandwidth as attention calculation requires dequantizing keys from INT4/INT8 to…

Machine Learning · Computer Science 2026-01-16 Aryan Karmore

In this paper, we explore a strategy that uses Mixture-of-Experts (MoE) to streamline, rather than augment, vision transformers. Each expert in an MoE layer is a SwiGLU feedforward network, where V and W2 are shared across the layer. No…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Jen Hong Tan

Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attention modules and multi-layer perceptron. However, calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xiangyu Chen , Qinghao Hu , Kaidong Li , Cuncong Zhong , Guanghui Wang

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data.…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Moab Arar , Ariel Shamir , Amit H. Bermano

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…

Machine Learning · Computer Science 2024-02-08 Michael Zhang , Kush Bhatia , Hermann Kumbong , Christopher Ré

Complex Query Answering (CQA) over Knowledge Graphs (KGs) is a challenging task. Given that KGs are usually incomplete, neural models are proposed to solve CQA by performing multi-hop logical reasoning. However, most of them cannot perform…

Machine Learning · Computer Science 2024-08-13 Chongzhi Zhang , Zhiping Peng , Junhao Zheng , Qianli Ma

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

The Transformer, with its scaled dot-product attention mechanism, has become a foundational architecture in modern AI. However, this mechanism is computationally intensive and incurs substantial energy costs. We propose a new Transformer…

Machine Learning · Computer Science 2025-08-07 Xin Gao , Xingming Xu , Shirin Amiraslani , Hong Xu

Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency. However, their quadratic computational complexity poses a major obstacle for applying them to vision tasks requiring…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Shitao Tang , Jiahui Zhang , Siyu Zhu , Ping Tan

LLM development involves pre-training a foundation model on massive data, followed by fine-tuning on task-specific data to create specialized experts. Serving these experts can pose significant memory challenges, as loading all experts onto…

Computation and Language · Computer Science 2024-10-29 Jing Liu , Ruihao Gong , Mingyang Zhang , Yefei He , Jianfei Cai , Bohan Zhuang

Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator…

Quantum Physics · Physics 2025-10-14 Peng Du , Jinjing Shi , Wenxuan Wang , Yin Ma , Kai Wen , Xuelong Li

This micro-paper describes a trick to speed up inference of transformers with RoPE (such as LLaMA, Mistral, PaLM, and Gemma). For these models, a large portion of the first transformer layer can be precomputed, which results in slightly…

Machine Learning · Computer Science 2024-03-13 Nils Graef

Large Language Models (LLMs) have greatly advanced the natural language processing paradigm. However, the high computational load and huge model sizes pose a grand challenge for deployment on edge devices. To this end, we propose APTQ…

Machine Learning · Computer Science 2024-04-17 Ziyi Guan , Hantao Huang , Yupeng Su , Hong Huang , Ngai Wong , Hao Yu

Large language models (LLMs) with billions of parameters demonstrate impressive performance. However, the widely used Multi-Head Attention (MHA) in LLMs incurs substantial computational and memory costs during inference. While some efforts…

Machine Learning · Computer Science 2024-12-10 Yilong Chen , Linhao Zhang , Junyuan Shang , Zhenyu Zhang , Tingwen Liu , Shuohuan Wang , Yu Sun

Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same…

Computation and Language · Computer Science 2024-04-03 Guangxuan Xiao , Ji Lin , Mickael Seznec , Hao Wu , Julien Demouth , Song Han

Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provide strong token mixing, they suffer from quadratic…

Machine Learning · Computer Science 2026-03-20 Youjin Wang , Jiaqiao Zhao , Rong Fu , Run Zhou , Ruizhe Zhang , Jiani Liang , Suisuai Cao , Feng Zhou

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Guang Liang , Xinyao Liu , Jianxin Wu

Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…

Computation and Language · Computer Science 2025-10-10 Wenhao Li , Yuxin Zhang , Gen Luo , Haiyuan Wan , Ziyang Gong , Fei Chao , Rongrong Ji
‹ Prev 1 8 9 10 Next ›