English
Related papers

Related papers: Length-Aware Rotary Position Embedding for Text-Sp…

200 papers

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

The Transformer architecture has revolutionized various regions since it was proposed, and its effectiveness largely depends on the ability to encode positional information. Traditional position encoding methods exhibit significant…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Hao Yu , Tangyu Jiang , Shuning Jia , Shannan Yan , Shunning Liu , Haolong Qian , Guanghao Li , Shuting Dong , Huaisong Zhang , Chun Yuan

Extending context window sizes allows large language models (LLMs) to process longer sequences and handle more complex tasks. Rotary Positional Embedding (RoPE) has become the de facto standard due to its relative positional encoding…

Computation and Language · Computer Science 2024-11-27 Haonan Wang , Qian Liu , Chao Du , Tongyao Zhu , Cunxiao Du , Kenji Kawaguchi , Tianyu Pang

Scaling the rotary position embedding (RoPE) has become a common method for extending the context window of RoPE-based large language models (LLMs). However, existing scaling methods often rely on empirical approaches and lack a profound…

Computation and Language · Computer Science 2024-10-04 Yingsheng Wu , Yuxuan Gu , Xiaocheng Feng , Weihong Zhong , Dongliang Xu , Qing Yang , Hongtao Liu , Bing Qin

Inspired by the Bloch Sphere representation, we propose a novel rotary position encoding on a three-dimensional sphere, named 3D Rotary Position Encoding (3D-RPE). 3D-RPE is an advanced version of the widely used 2D Rotary Position Encoding…

Computation and Language · Computer Science 2024-06-17 Xindian Ma , Wenyuan Liu , Peng Zhang , Nan Xu

Positional embeddings (PE) play a crucial role in Vision Transformers (ViTs) by providing spatial information otherwise lost due to the permutation invariant nature of self attention. While absolute positional embeddings (APE) have shown…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Md Abtahi Majeed Chowdhury , Md Rifat Ur Rahman , Akil Ahmad Taki

Vision-Language Models (VLMs) have made significant progress in multimodal tasks. However, their performance often deteriorates in long-context scenarios, particularly long videos. While Rotary Position Embedding (RoPE) has been widely…

Machine Learning · Computer Science 2025-10-09 Haoran Li , Yingjie Qin , Baoyuan Ou , Lai Xu , Ruiwen Xu

The Rotary Position Embedding (RoPE) mechanism has become a powerful enhancement to the Transformer architecture, which enables models to capture token relationships when encoding positional information. However, the RoPE mechanisms make…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Jiayan Huo , Yingyu Liang , Zhenmei Shi , Zhao Song

Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…

Computation and Language · Computer Science 2025-03-13 Eric Battenberg , RJ Skerry-Ryan , Daisy Stanton , Soroosh Mariooryad , Matt Shannon , Julian Salazar , David Kao

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

Explaining closed-source Large Language Model (LLM) outputs is challenging because API access prevents gradient-based attribution, while perturbation methods are costly and noisy when they depend on regenerated text. We introduce…

Computation and Language · Computer Science 2026-02-20 Isaac Picov , Ritesh Goru

Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret…

Machine Learning · Computer Science 2026-02-12 Feilong Liu

Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to…

Computation and Language · Computer Science 2024-11-06 Chuanyang Zheng , Yihang Gao , Han Shi , Minbin Huang , Jingyao Li , Jing Xiong , Xiaozhe Ren , Michael Ng , Xin Jiang , Zhenguo Li , Yu Li

We present Relational Sentence Embedding (RSE), a new paradigm to further discover the potential of sentence embeddings. Prior work mainly models the similarity between sentences based on their embedding distance. Because of the complex…

Computation and Language · Computer Science 2023-06-09 Bin Wang , Haizhou Li

We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find…

Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional computational overhead and increased method complexity. We present the Rotary Masked…

Machine Learning · Computer Science 2026-05-13 Uros Zivanovic , Serafina Di Gioia , Andre Scaffidi , Martín de los Rios , Gabriella Contardo , Roberto Trotta

Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When adapted to vision transformers, the standard axial…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Haoyu Liu , Sucheng Ren , Tingyu Zhu , Peng Wang , Cihang Xie , Alan Yuille , Zeyu Zheng , Feng Wang

The ability to process ultra-long contexts is crucial for large language models (LLMs) to perform long-horizon tasks. While recent efforts have extended context windows to 1M and beyond, model performance degrades when sequence length…

Computation and Language · Computer Science 2026-05-28 Simin Huo

Transformer-based Large Language Models (LLMs) rely on positional encodings to provide sequence position information to their attention mechanism. Rotary Positional Encodings (RoPE), which encode relative position by rotating queries and…

Computation and Language · Computer Science 2025-08-25 André Jonasson

So far, expensive finetuning beyond the pretraining sequence length has been a requirement for effectively extending the context of language models (LM). In this work, we break this key bottleneck by Dropping the Positional Embeddings of…

Computation and Language · Computer Science 2025-12-16 Yoav Gelberg , Koshi Eguchi , Takuya Akiba , Edoardo Cetin