English
Related papers

Related papers: Learning Less Is More: Premature Upper-Layer Atten…

200 papers

We study how a one-layer attention-only transformer develops relevant structures while learning to sort lists of numbers. At the end of training, the model organizes its attention heads in two main modes that we refer to as…

Machine Learning · Computer Science 2025-02-03 Einar Urdshals , Jasmina Urdshals

Attention-based Neural Machine Translation (NMT) models suffer from attention deficiency issues as has been observed in recent research. We propose a novel mechanism to address some of these limitations and improve the NMT attention.…

Computation and Language · Computer Science 2016-08-10 Baskaran Sankaran , Haitao Mi , Yaser Al-Onaizan , Abe Ittycheriah

Finding the right initialisation for neural networks is crucial to ensure smooth training and good performance. In transformers, the wrong initialisation can lead to one of two failure modes of self-attention layers: rank collapse, where…

Machine Learning · Statistics 2026-05-22 Alessio Giorlandino , Sebastian Goldt

Attention-based transformers have become the standard architecture in many deep learning fields, primarily due to their ability to model long-range dependencies and handle variable-length input sequences. However, the attention mechanism…

Machine Learning · Computer Science 2024-06-18 Kalle Hilsenbek

Causal self-attention provides positional information to Transformer decoders. Prior work has shown that stacks of causal self-attention layers alone induce a positional bias in attention scores toward earlier tokens. However, this differs…

Computation and Language · Computer Science 2026-04-21 Junu Kim , Xiao Liu , Zhenghao Lin , Lei Ji , Yeyun Gong , Edward Choi

Although Large Vision-Language Models (LVLMs) have made substantial progress, hallucination, where generated text is not grounded in the visual input, remains a challenge. As LVLMs become stronger, previously reported hallucination…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 April Fu

Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in…

Computation and Language · Computer Science 2023-05-16 Damai Dai , Yutao Sun , Li Dong , Yaru Hao , Shuming Ma , Zhifang Sui , Furu Wei

Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Daquan Zhou , Bingyi Kang , Xiaojie Jin , Linjie Yang , Xiaochen Lian , Zihang Jiang , Qibin Hou , Jiashi Feng

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

Machine Learning · Computer Science 2026-01-27 Olaf Yunus Laitinen Imanov

Differential Transformer has recently been proposed to improve performance in Transformer models by canceling out noise through a denoiser attention mechanism. In this work, we introduce DiffLoRA, a parameter-efficient adaptation of the…

Computation and Language · Computer Science 2025-08-01 Alexandre Misrahi , Nadezhda Chirkova , Maxime Louis , Vassilina Nikoulina

Most state-of-the-art techniques for Language Models (LMs) today rely on transformer-based architectures and their ubiquitous attention mechanism. However, the exponential growth in computational requirements with longer input sequences…

Computation and Language · Computer Science 2024-11-26 Kaustubh Ponkshe , Venkatapathy Subramanian , Natwar Modani , Ganesh Ramakrishnan

While pretrained encoders have achieved success in various natural language understanding (NLU) tasks, there is a gap between these pretrained encoders and natural language generation (NLG). NLG tasks are often based on the encoder-decoder…

Computation and Language · Computer Science 2021-08-19 Shuming Ma , Li Dong , Shaohan Huang , Dongdong Zhang , Alexandre Muzio , Saksham Singhal , Hany Hassan Awadalla , Xia Song , Furu Wei

Training Large Language Models (LLMs) presents significant memory challenges, predominantly due to the growing size of weights and optimizer states. Common memory-reduction approaches, such as low-rank adaptation (LoRA), add a trainable…

Machine Learning · Computer Science 2024-06-04 Jiawei Zhao , Zhenyu Zhang , Beidi Chen , Zhangyang Wang , Anima Anandkumar , Yuandong Tian

Fine-tuning pretrained language models has shown promising results on a wide range of tasks, but when encountering a novel task, do they rely more on generic pretrained representation, or develop brand new task-specific solutions? Here, we…

Machine Learning · Computer Science 2024-06-28 Dongyan Lin

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Machine Learning · Computer Science 2026-02-03 Hao Gu , Mao-Lin Luo , Zi-Hao Zhou , Han-Chen Zhang , Min-Ling Zhang , Tong Wei

Why do large language models sometimes output factual inaccuracies and exhibit erroneous reasoning? The brittleness of these models, particularly when executing long chains of reasoning, currently seems to be an inevitable price to pay for…

Machine Learning · Computer Science 2023-10-31 Bingbin Liu , Jordan T. Ash , Surbhi Goel , Akshay Krishnamurthy , Cyril Zhang

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Machine Learning · Computer Science 2025-06-27 Fei Wang , Baochun Li

Large Language Models (LLMs) have advanced rapidly but face significant memory demands. While quantization has shown promise for LLMs, current methods typically require lengthy training to alleviate the performance degradation from…

Artificial Intelligence · Computer Science 2024-05-31 Ke Yi , Yuhui Xu , Heng Chang , Chen Tang , Yuan Meng , Tong Zhang , Jia Li

Large language models (LLMs) have significantly improved various aspects of our daily lives. These models have impacted numerous domains, from healthcare to education, enhancing productivity, decision-making processes, and accessibility. As…

Machine Learning · Computer Science 2023-11-01 Zhao Song , Guangyi Xu , Junze Yin

In decoder-based LLMs, the representation of a given layer serves two purposes: as input to the next layer during the computation of the current token; and as input to the attention mechanism of future tokens. In this work, we show that the…

Computation and Language · Computer Science 2024-11-01 Amit Ben-Artzy , Roy Schwartz