English
Related papers

Related papers: Latent Multi-Head Attention for Small Language Mod…

200 papers

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

Machine Learning · Computer Science 2026-02-05 Chenwei Cui , Rockwell Jackson , Benjamin Joseph Herrera , Ana María Tárano , Hannah Kerner

With the increasing volumes of Large Language Models (LLMs) and the expanding context lengths, attention computation has become a key performance bottleneck in LLM serving. For fast attention computation, recent practices often parallelize…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-12 Di Liu , Yifei Liu , Chen Chen , Zhibin Yu , Xiaoyi Fan , Quan Chen , Minyi Guo

Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and cumulative contextual loss by completely discarding unselected blocks. To address…

Computation and Language · Computer Science 2026-02-02 Bailin Wang , Dan Friedman , Tao Lei , Chong Wang

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM) architectures demonstrate superior energy efficiency due to…

Computation and Language · Computer Science 2026-03-10 Taiqiang Wu , Chenchen Ding , Wenyong Zhou , Yuxin Cheng , Xincheng Feng , Shuqi Wang , Wendong Xu , Chufan Shi , Zhengwu Liu , Ngai Wong

Recent studies have revealed some issues of Multi-Head Attention (MHA), e.g., redundancy and over-parameterization. Specifically, the heads of MHA were originally designed to attend to information from different representation subspaces,…

Machine Learning · Computer Science 2023-10-17 Jinjie Ni , Rui Mao , Zonglin Yang , Han Lei , Erik Cambria

We study architectural and optimization techniques for sample-efficient language modeling under the constraints of the BabyLM 2025 shared task. Our model, BLaLM, replaces self-attention with a linear-time mLSTM token mixer and explores…

Computation and Language · Computer Science 2025-11-11 Patrick Haller , Jonas Golde , Alan Akbik

Recently, inspired by the concept of sparsity, Mixture-of-Experts (MoE) models have gained increasing popularity for scaling model size while keeping the number of activated parameters constant. In this study, we thoroughly investigate the…

Computation and Language · Computer Science 2024-11-26 Xiaoye Qu , Daize Dong , Xuyang Hu , Tong Zhu , Weigao Sun , Yu Cheng

Fine-tuning large language models (LLMs) with Low-Rank adaption (LoRA) is widely acknowledged as an effective approach for continual learning for new tasks. However, it often suffers from catastrophic forgetting when dealing with multiple…

Computation and Language · Computer Science 2024-10-01 Jialin Liu , Jianhua Wu , Jie Liu , Yutai Duan

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as…

Computation and Language · Computer Science 2022-11-08 Michael Hassid , Hao Peng , Daniel Rotem , Jungo Kasai , Ivan Montero , Noah A. Smith , Roy Schwartz

Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks. Given the higher computational demand of pre-training, it's intuitive to assume that…

Machine Learning · Computer Science 2024-10-15 James Liu , Guangxuan Xiao , Kai Li , Jason D. Lee , Song Han , Tri Dao , Tianle Cai

Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. Considering the heavy cost of training MLLMs, it is efficient to reuse the existing ones and…

Machine Learning · Computer Science 2025-10-23 Dingkun Zhang , Shuhan Qi , Xinyu Xiao , Kehai Chen , Xuan Wang

While linear attention reduces the quadratic complexity of standard Transformers to linear time, it often lags behind in expressivity due to the removal of softmax normalization. This omission eliminates \emph{global competition}, a…

Machine Learning · Computer Science 2026-02-03 Mingwei Xu , Xuan Lin , Xinnan Guo , Wanqing Xu , Wanyun Cui

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

Fine-tuning Large Language Models (LLMs) is a common practice to adapt pre-trained models for specific applications. While methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls…

Computation and Language · Computer Science 2024-07-23 Dengchun Li , Yingzi Ma , Naizheng Wang , Zhengmao Ye , Zhiyuan Cheng , Yinghao Tang , Yan Zhang , Lei Duan , Jie Zuo , Cal Yang , Mingjie Tang

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…

Computation and Language · Computer Science 2022-05-13 Satwinder Singh , Ruili Wang , Feng Hou

The emergence of spontaneous symmetry breaking among a few heads of multi-head attention (MHA) across transformer blocks in classification tasks was recently demonstrated through the quantification of single-nodal performance (SNP). This…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ronit D. Gross , Tal Halevi , Ella Koresh , Yarden Tzach , Ido Kanter

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models…

Computation and Language · Computer Science 2024-09-17 Xiaojing Fan , Chunliang Tao