English
Related papers

Related papers: Post-Norm can Resharpen Attention

200 papers

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To…

Machine Learning · Computer Science 2023-03-09 William Merrill , Vivek Ramanujan , Yoav Goldberg , Roy Schwartz , Noah Smith

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Audio and Speech Processing · Electrical Eng. & Systems 2018-02-02 F A Rezaur Rahman Chowdhury , Quan Wang , Ignacio Lopez Moreno , Li Wan

Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is…

Machine Learning · Computer Science 2019-09-19 Senwei Liang , Zhongzhan Huang , Mingfu Liang , Haizhao Yang

In this paper, I introduce the retrieval problem, a simple yet common reasoning task that can be solved only by transformers with a minimum number of layers, which grows logarithmically with the input size. I empirically show that large…

Machine Learning · Computer Science 2025-10-29 Tiberiu Musat

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

Auto-regressive models (ARMs) have established a dominant paradigm in language modeling. However, their strictly sequential decoding paradigm imposes fundamental constraints on both inference efficiency and modeling flexibility. To address…

Computation and Language · Computer Science 2026-04-13 Yuyan Zhou , Kai Syun Hou , Weiyu Chen , James Kwok

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Computation and Language · Computer Science 2026-02-16 Bangzheng Li , Jianmo Ni , Chen Qu , Ian Miao , Liu Yang , Xingyu Fu , Muhao Chen , Derek Zhiyuan Cheng

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

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Machine Learning · Computer Science 2026-02-02 Shyam Venkatasubramanian , Sean Moushegian , Michael Lin , Mir Park , Ankit Singhal , Connor Lee

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Computation and Language · Computer Science 2025-10-14 Huiyin Xue , Nafise Sadat Moosavi , Nikolaos Aletras

Linear transformers aim to reduce the quadratic space-time complexity of vanilla transformers. However, they usually suffer from degraded performances on various tasks and corpus. In this paper, we examine existing kernel-based linear…

Computation and Language · Computer Science 2022-10-20 Zhen Qin , XiaoDong Han , Weixuan Sun , Dongxu Li , Lingpeng Kong , Nick Barnes , Yiran Zhong

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee

Why do modern language models, trained to do well on next-word prediction, appear to generate coherent documents and capture long-range structure? Here we show that next-token prediction is provably powerful for learning longer-range…

Machine Learning · Computer Science 2025-12-09 Xinyuan Cao , Santosh S. Vempala

The paper studies the capabilities of Recurrent-Neural-Network sequence to sequence (RNN seq2seq) models in learning four transduction tasks: identity, reversal, total reduplication, and quadratic copying. These transductions are…

Computation and Language · Computer Science 2024-04-23 Zhengxiang Wang

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new partially…

Computation and Language · Computer Science 2019-10-29 Jiatao Gu , Changhan Wang , Jake Zhao

Out-of-distribution generalization capabilities of sequence-to-sequence models can be studied from the lens of two crucial forms of generalization: length generalization -- the ability to generalize to longer sequences than ones seen during…

Machine Learning · Computer Science 2025-05-29 Kartik Ahuja , Amin Mansouri

Self-attention mechanisms model long-range context by using pairwise attention between all input tokens. In doing so, they assume a fixed attention granularity defined by the individual tokens (e.g., text characters or image pixels), which…

Machine Learning · Computer Science 2022-07-06 Chen Huang , Walter Talbott , Navdeep Jaitly , Josh Susskind

Neural solvers based on attention mechanism have demonstrated remarkable effectiveness in solving vehicle routing problems. However, in the generalization process from small scale to large scale, we find a phenomenon of the dispersion of…

Artificial Intelligence · Computer Science 2024-01-17 Yang Wang , Ya-Hui Jia , Wei-Neng Chen , Yi Mei

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Artificial Intelligence · Computer Science 2025-03-06 Chenhui Xu , Dancheng Liu , Jiajie Li , Amir Nassereldine , Zhaohui Li , Jinjun Xiong

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Yang Zhang , Teoh Tze Tzun , Lim Wei Hern , Tiviatis Sim , Kenji Kawaguchi
‹ Prev 1 8 9 10 Next ›