English
Related papers

Related papers: Beyond Real: Imaginary Extension of Rotary Positio…

200 papers

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional…

Computation and Language · Computer Science 2021-09-28 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

Broad textual understanding and in-context learning require language models that utilize full document contexts. Due to the implementation challenges associated with directly training long-context models, many methods have been proposed for…

Computation and Language · Computer Science 2024-09-24 Yi Lu , Jing Nathan Yan , Songlin Yang , Justin T. Chiu , Siyu Ren , Fei Yuan , Wenting Zhao , Zhiyong Wu , Alexander M. Rush

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

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

Computation and Language · Computer Science 2025-09-29 Haoyang Li , Zhanchao Xu , Yiming Li , Xuejia Chen , Darian Li , Anxin Tian , Qingfa Xiao , Cheng Deng , Jun Wang , Qing Li , Lei Chen , Mingxuan Yuan

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

In Transformers, Position Embeddings (PEs) significantly influence Length Generalization (LG) performance, yet their fundamental role remains unclear. In this work, we investigate the limitations and capabilities of PEs in achieving LG. We…

Machine Learning · Computer Science 2025-10-07 Yang Chen , Yitao Liang , Zhouchen Lin

Transformer-based Large Language Models (LLMs) are pioneering advances in many natural language processing tasks, however, their exceptional capabilities are restricted within the preset context window of Transformer. Position Embedding…

Computation and Language · Computer Science 2024-03-26 Guanzheng Chen , Xin Li , Zaiqiao Meng , Shangsong Liang , Lidong Bing

This paper studies how Transformer models with Rotary Position Embeddings (RoPE) develop emergent, wavelet-like properties that compensate for the positional encoding's theoretical limitations. Through an analysis spanning model scales,…

Machine Learning · Computer Science 2025-06-06 Valeria Ruscio , Umberto Nanni , Fabrizio Silvestri

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Artificial Intelligence · Computer Science 2025-08-05 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…

Computation and Language · Computer Science 2021-12-30 Haw-Shiuan Chang , Amol Agrawal , Andrew McCallum

Characterizing the express power of the Transformer architecture is critical to understanding its capacity limits and scaling law. Recent works provide the circuit complexity bounds to Transformer-like architecture. On the other hand,…

Machine Learning · Computer Science 2024-12-03 Bo Chen , Xiaoyu Li , Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we propose Extensible…

Computation and Language · Computer Science 2024-02-20 Ninglu Shao , Shitao Xiao , Zheng Liu , Peitian Zhang

Transformer architectures have established strong baselines in time series forecasting, yet they typically rely on positional encodings that assume uniform, index-based temporal progression. However, real-world systems, from shifting…

Machine Learning · Computer Science 2026-02-10 Yubin Kim , Viresh Pati , Jevon Twitty , Vinh Pham , Shihao Yang , Jiecheng Lu

Generative recommenders, typically transformer-based autoregressive models, predict the next item or action from a user's interaction history. Their effectiveness depends on how the model represents where an interaction event occurs in the…

Information Retrieval · Computer Science 2025-10-24 Xiaokai Wei , Jiajun Wu , Daiyao Yi , Reza Shirkavand , Michelle Gong

In Transformer-based architectures, the attention mechanism is inherently permutation-invariant with respect to the input sequence's tokens. To impose sequential order, token positions are typically encoded using a scheme with either fixed…

Machine Learning · Computer Science 2023-10-31 Giorgio Angelotti

Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant…

Information Retrieval · Computer Science 2025-03-27 Ningya Feng , Junwei Pan , Jialong Wu , Baixu Chen , Ximei Wang , Qian Li , Xian Hu , Jie Jiang , Mingsheng Long

Large-scale knowledge bases have currently reached impressive sizes; however, these knowledge bases are still far from complete. In addition, most of the existing methods for knowledge base completion only consider the direct links between…

Computation and Language · Computer Science 2017-02-27 Xixun Lin , Yanchun Liang , Fausto Giunchiglia , Xiaoyue Feng , Renchu Guan

Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Qing Ma , Jiancheng Pan , Cong Bai

Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to…

Computation and Language · Computer Science 2024-05-29 Jie Wang , Tao Ji , Yuanbin Wu , Hang Yan , Tao Gui , Qi Zhang , Xuanjing Huang , Xiaoling Wang

Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of…

Machine Learning · Computer Science 2026-03-13 Mohammad Aflah Khan , Krishna P. Gummadi , Manish Gupta , Abhilasha Ravichander