English
Related papers

Related papers: PSC: Extending Context Window of Large Language Mo…

200 papers

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

Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during training, rotary phases can enter out-of-distribution regimes, leading to spurious…

Machine Learning · Computer Science 2026-05-12 Riccardo Ali , Alessio Borgi , Christopher Irwin , Mario Severino , Pietro Liò

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

Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-context extension have significantly expanded the context…

Computation and Language · Computer Science 2025-04-29 Yi Lu , Wanxu Zhao , Xin Zhou , Chenxin An , Chenglong Wang , Shuo Li , Yuming Yang , Jun Zhao , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

While context compression can mitigate the growing inference costs of Large Language Models (LLMs) by shortening contexts, existing methods that specify a target compression ratio or length suffer from unpredictable performance degradation,…

Computation and Language · Computer Science 2026-03-23 Runsong Zhao , Shilei Liu , Jiwei Tang , Langming Liu , Haibin Chen , Weidong Zhang , Yujin Yuan , Tong Xiao , Jingbo Zhu , Wenbo Su , Bo Zheng

Rotary Position Embedding (RoPE) has become a core component of modern Transformer architectures across language, vision, and 3D domains. However, existing implementations rely on vector-level split and merge operations that introduce…

Machine Learning · Computer Science 2026-04-14 Chen Minqi , Zhongqi Yue , Shihao Zhang , Yun Xu , Peng Wu , kaixiang Xu , Zeyi Huang , Hanwang Zhang

In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…

Machine Learning · Statistics 2026-03-05 Korel Gundem , Juncheng Dong , Dennis Zhang , Vahid Tarokh , Zhengling Qi

Large language models (LLMs) based on the Transformer architecture usually have their context length limited due to the high training cost. Recent advancements extend the context window by adjusting the scaling factors of RoPE and…

Computation and Language · Computer Science 2025-11-25 Lei Yang , Shaoyang Xu , Jianxiang Peng , Shaolin Zhu , Deyi Xiong

3D Large Vision-Language Models (3D LVLMs) built upon Large Language Models (LLMs) have achieved remarkable progress across various multimodal tasks. However, their inherited position-dependent modeling mechanism, Rotary Position Embedding…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Guanting Ye , Qiyan Zhao , Wenhao Yu , Liangyu Yuan , Mingkai Li , Xiaofeng Zhang , Jianmin Ji , Yanyong Zhang , Qing Jiang , Ka-Veng Yuen

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

Recent studies have demonstrated the effectiveness of using large language language models (LLMs) in passage ranking. The listwise approaches, such as RankGPT, have become new state-of-the-art in this task. However, the efficiency of…

Computation and Language · Computer Science 2025-01-29 Qi Liu , Bo Wang , Nan Wang , Jiaxin Mao

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

Extending the context window support of large language models (LLMs) is crucial for tasks with long-distance dependencies. RoPE-based interpolation and extrapolation methods, such as linear scaling and frequency-aware schemes, enable longer…

Machine Learning · Computer Science 2025-10-02 Ye Qiao , Haocheng Xu , Xiaofan Zhang , Sitao Huang

The attention mechanism is a core primitive in modern large language models (LLMs) and AI more broadly. Since attention by itself is permutation-invariant, position encoding is essential for modeling structured domains such as language.…

Computation and Language · Computer Science 2026-02-05 Songlin Yang , Yikang Shen , Kaiyue Wen , Shawn Tan , Mayank Mishra , Liliang Ren , Rameswar Panda , Yoon Kim

The transformer architecture has been widely applied to many machine learning tasks. A main bottleneck in the time to perform transformer computations is a task called attention computation. [Alman and Song, NeurIPS 2023] have shown that in…

Machine Learning · Computer Science 2025-05-20 Josh Alman , Zhao Song

Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation reveals significant limitations such as fine-grained spatial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jiaye Li , Baoyou Chen , Hui Li , Zilong Dong , Jingdong Wang , Siyu Zhu

Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…

Computation and Language · Computer Science 2025-02-13 Barnaby Schmitt , Alistair Grosvenor , Matthias Cunningham , Clementine Walsh , Julius Pembrokeshire , Jonathan Teel

Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each present distinct…

Robotics · Computer Science 2025-03-20 Jianbo Zhao , Taiyu Ban , Zhihao Liu , Hangning Zhou , Xiyang Wang , Qibin Zhou , Hailong Qin , Mu Yang , Lei Liu , Bin Li

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

Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are…

Computation and Language · Computer Science 2024-10-31 Francesco Periti , Nina Tahmasebi