English
Related papers

Related papers: StableMask: Refining Causal Masking in Decoder-onl…

200 papers

In this paper we provide, to the best of our knowledge, the first comprehensive approach for incorporating various masking mechanisms into Transformers architectures in a scalable way. We show that recent results on linear causal attention…

We identify intrinsic limitations of Rotary Positional Embeddings (RoPE) in Transformer-based long-context language models. Our theoretical analysis abstracts away from the specific content of the context and depends only on its length. We…

Computation and Language · Computer Science 2026-05-18 Yufeng Du , Phillip Harris , Minyang Tian , Eliu A Huerta , Srikanth Ronanki , Subendhu Rongali , Aram Galstyan , Hao Peng

Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effective in many settings, this constraint can limit flexibility in controlling attention…

Computation and Language · Computer Science 2026-02-27 Jeongin Bae , Baeseong Park , Gunho Park , Minsub Kim , Joonhyung Lee , Junhee Yoo , Sunghyeon Woo , Jiwon Ryu , Se Jung Kwon , Dongsoo Lee

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent methods emphasize…

Machine Learning · Computer Science 2025-11-18 Chase van de Geijn , Ayush Paliwal , Timo Lüddecke , Alexander S. Ecker

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer…

Machine Learning · Computer Science 2024-10-08 Lijie Yang , Zhihao Zhang , Zhuofu Chen , Zikun Li , Zhihao Jia

Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. In this work, we introduce a simple yet powerful position encoding (PE) strategy, Random Float Sampling…

Machine Learning · Computer Science 2026-02-17 Atsushi Shimizu , Shohei Taniguchi , Yutaka Matsuo

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…

Computation and Language · Computer Science 2019-09-25 Kazuki Irie , Albert Zeyer , Ralf Schlüter , Hermann Ney

Transformers often struggle to generalize to longer sequences than those seen during training, a limitation known as length extrapolation. Most existing Relative Positional Encoding (RPE) methods attempt to address this by introducing…

Computation and Language · Computer Science 2025-09-23 Ali Veisi , Hamidreza Amirzadeh , Amir Mansourian

Masked diffusion language models (MDLMs) have emerged as a promising alternative to dominant autoregressive approaches. Although they achieve competitive performance on several tasks, a substantial gap remains in open-ended text generation.…

Computation and Language · Computer Science 2026-02-02 Mengyu Ye , Ryosuke Takahashi , Keito Kudo , Jun Suzuki

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

Computation and Language · Computer Science 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Transformer has been widely-used in many Natural Language Processing (NLP) tasks and the scaled dot-product attention between tokens is a core module of Transformer. This attention is a token-wise design and its complexity is quadratic to…

Computation and Language · Computer Science 2020-08-13 Shuai Zhang , Peng Zhang , Xindian Ma , Junqiu Wei , Ningning Wang , Qun Liu

There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in…

Computation and Language · Computer Science 2024-05-09 Arpit Aggarwal

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in…

Computation and Language · Computer Science 2025-06-26 Zhisong Zhang , Yan Wang , Xinting Huang , Tianqing Fang , Hongming Zhang , Chenlong Deng , Shuaiyi Li , Dong Yu

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

Computation and Language · Computer Science 2026-05-29 Pierre-Antoine Lequeu , Camille Barboule , Benjamin Piwowarski

Decoder-only large language models are increasingly used as behavioral encoders for user representation learning, yet the impact of attention masking on the quality of user embeddings remains underexplored. In this work, we conduct a…

Computation and Language · Computer Science 2026-02-12 Jiahao Yuan , Yike Xu , Jinyong Wen , Baokun Wang , Yang Chen , Xiaotong Lin , Wuliang Huang , Ziyi Gao , Xing Fu , Yu Cheng , Weiqiang Wang

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Computation and Language · Computer Science 2025-10-03 Haochen You , Baojing Liu

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various…

Computation and Language · Computer Science 2023-11-09 Jianlin Su , Yu Lu , Shengfeng Pan , Ahmed Murtadha , Bo Wen , Yunfeng Liu