English
Related papers

Related papers: When Precision Meets Position: BFloat16 Breaks Dow…

200 papers

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

Computation and Language · Computer Science 2024-08-13 Tsendsuren Munkhdalai , Manaal Faruqui , Siddharth Gopal

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

Transformer-based end-to-end speech recognition models have received considerable attention in recent years due to their high training speed and ability to model a long-range global context. Position embedding in the transformer…

Sound · Computer Science 2021-07-14 Shengqiang Li , Menglong Xu , Xiao-Lei Zhang

Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports,…

Computation and Language · Computer Science 2024-06-21 Yushi Bai , Xin Lv , Jiajie Zhang , Hongchang Lyu , Jiankai Tang , Zhidian Huang , Zhengxiao Du , Xiao Liu , Aohan Zeng , Lei Hou , Yuxiao Dong , Jie Tang , Juanzi Li

Positional encoding mechanisms enable Transformers to model sequential structure and long-range dependencies in text. While absolute positional encodings struggle with extrapolation to longer sequences due to fixed positional…

Computation and Language · Computer Science 2025-09-09 Chang Dai , Hongyu Shan , Mingyang Song , Di Liang

We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model…

With the development of large language models (LLMs), there has been an increasing need for significant advancements in handling long contexts. To enhance long-context capabilities, constructing high-quality training data with long-range…

Computation and Language · Computer Science 2025-02-28 Longyun Wu , Dawei Zhu , Guangxiang Zhao , Zhuocheng Yu , Junfeng Ran , Xiangyu Wong , Lin Sun , Sujian Li

Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of the context window. Extensive studies have been proposed to…

Computation and Language · Computer Science 2024-11-19 Zican Dong , Junyi Li , Xin Men , Wayne Xin Zhao , Bingbing Wang , Zhen Tian , Weipeng Chen , Ji-Rong Wen

Long-context large language models (LLMs) are prone to be distracted by irrelevant contexts. The reason for distraction remains poorly understood. In this paper, we first identify the contextual heads, a special group of attention heads…

Computation and Language · Computer Science 2025-04-01 Youxiang Zhu , Ruochen Li , Danqing Wang , Daniel Haehn , Xiaohui Liang

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mitigates this by focusing computation on critical regions,…

Computation and Language · Computer Science 2025-03-21 Ruyi Xu , Guangxuan Xiao , Haofeng Huang , Junxian Guo , Song Han

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

Computation and Language · Computer Science 2026-02-05 Gang Lin , Dongfang Li , Zhuoen Chen , Yukun Shi , Xuhui Chen , Baotian Hu , Min Zhang

Recent advancements in model architectures and length extrapolation techniques have significantly extended the context length of large language models (LLMs), paving the way for their application in increasingly complex tasks. However,…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…

Computation and Language · Computer Science 2024-05-31 Lei Zhu , Xinjiang Wang , Wayne Zhang , Rynson W. H. Lau

A fundamental reason for the dominance of attention over RNNs and LSTMs in LLMs is its ability to capture long-range dependencies by modeling direct interactions between all tokens, overcoming the sequential limitations of recurrent…

Artificial Intelligence · Computer Science 2025-09-30 Junyang Zhang , Tianyi Zhu , Thierry Tambe

Recent large reasoning models (LRMs) have demonstrated strong reasoning capabilities through reinforcement learning (RL). These improvements have primarily been observed within the short-context reasoning tasks. In contrast, extending LRMs…

Computation and Language · Computer Science 2025-05-28 Fanqi Wan , Weizhou Shen , Shengyi Liao , Yingcheng Shi , Chenliang Li , Ziyi Yang , Ji Zhang , Fei Huang , Jingren Zhou , Ming Yan

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

We present LongQLoRA, an efficient and effective method to extend context length of large language models with less training resources. LongQLoRA combines the advantages of Position Interpolation, QLoRA and Shift Short Attention of…

Computation and Language · Computer Science 2023-11-10 Jianxin Yang

This paper describes how to apply self-attention with relative positional encodings to the task of relation extraction. We propose to use the self-attention encoder layer together with an additional position-aware attention layer that takes…

Computation and Language · Computer Science 2018-07-10 Ivan Bilan , Benjamin Roth

Long-context capability and computational efficiency are among the central challenges facing today's large language models. Existing efficient attention methods reduce computational complexity, but they typically suffer from a limited…

Computation and Language · Computer Science 2026-02-05 Yunao Zheng , Xiaojie Wang , Lei Ren , Wei Chen