English
Related papers

Related papers: Layer-Specific Scaling of Positional Encodings for…

200 papers

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…

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

The diminishing ability of large language models (LLMs) to effectively utilize long-range context-the "lost-in-the-middle" phenomenon-poses a significant challenge in retrieval-based LLM applications. To study the impact of this phenomenon…

Computation and Language · Computer Science 2025-11-19 Mihir Gupte , Eshan Dixit , Muhammad Tayyab , Arun Adiththan

Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area…

Computation and Language · Computer Science 2023-08-01 Ting Jiang , Shaohan Huang , Zhongzhi Luan , Deqing Wang , Fuzhen Zhuang

As large language models (LLMs) are progressively deployed in various real-world applications, personalization of LLMs has become increasingly important. While various approaches to LLM personalization such as prompt-based and…

Computation and Language · Computer Science 2025-11-25 Hyungjune Bu , Chanjoo Jung , Minjae Kang , Jaehyung Kim

Recent advances in 3D Large Multimodal Models (LMMs) built on Large Language Models (LLMs) have established the alignment of 3D visual features with LLM representations as the dominant paradigm. However, the inherited Rotary Position…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Guanting Ye , Qiyan Zhao , Wenhao Yu , Xiaofeng Zhang , Jianmin Ji , Yanyong Zhang , Ka-Veng Yuen

Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be over-compressed in the embeddings. Consequently,…

Computation and Language · Computer Science 2025-07-08 Michael Günther , Isabelle Mohr , Daniel James Williams , Bo Wang , Han Xiao

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

Hallucinations pose a significant challenge in Large Vision Language Models (LVLMs), with misalignment between multimodal features identified as a key contributing factor. This paper reveals the negative impact of the long-term decay in…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Qiyan Zhao , Xiaofeng Zhang , Yiheng Li , Yun Xing , Xiaosong Yuan , Feilong Tang , Sinan Fan , Xuhang Chen , Xuyao Zhang , Dahan Wang

This paper introduces a novel approach to position embeddings in transformer models, named "Exact Positional Embeddings" (ExPE). An absolute positional embedding method that can extrapolate to sequences of lengths longer than the ones it…

Computation and Language · Computer Science 2025-10-06 Aleksis Datseris , Sylvia Vassileva , Ivan Koychev , Svetla Boytcheva

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

Positional encodings are essential to transformer-based generative models, yet their behavior in multimodal and attention-sharing settings is not fully understood. In this work, we present a principled analysis of Rotary Positional…

Graphics · Computer Science 2026-02-06 Aryan Mikaeili , Or Patashnik , Andrea Tagliasacchi , Daniel Cohen-Or , Ali Mahdavi-Amiri

Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using…

Computation and Language · Computer Science 2026-02-19 Lucas Bandarkar , Chenyuan Yang , Mohsen Fayyaz , Junlin Hu , Nanyun Peng

We investigate the generalization properties of dense text embeddings when the embedding backbone is a large language model (LLM) versus when it is a non-LLM encoder, and we study the extent to which spherical linear interpolation (SLERP)…

Computation and Language · Computer Science 2025-12-01 Siyaxolisa Kabane

This paper investigates the information encoded in the embeddings of large language models (LLMs). We conduct simulations to analyze the representation entropy and discover a power law relationship with model sizes. Building upon this…

Machine Learning · Computer Science 2024-02-07 Zhiquan Tan , Chenghai Li , Weiran Huang

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary position embedding (RoPE) is commonly used to encode positional…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Hyeongju Kim , Juheon Lee , Jinhyeok Yang , Jacob Morton

Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using…

Machine Learning · Computer Science 2026-05-25 Arnesh Batra , Arush Gumber , Aniket Khandelwal , Jashn Khemani , Anubha Gupta

With the increasing popularity of deep learning in image processing, many learned lossless image compression methods have been proposed recently. One group of algorithms that have shown good performance are based on learned pixel-based…

Image and Video Processing · Electrical Eng. & Systems 2022-12-27 Fatih Kamisli

Over the past several years, we have witnessed impressive progress in the field of learned image compression. Recent learned image codecs are commonly based on autoencoders, that first encode an image into low-dimensional latent…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Zongyu Guo , Zhizheng Zhang , Runsen Feng , Zhibo Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities through pretraining and alignment. However, superior short-context LLMs may underperform in long-context scenarios due to insufficient long-context alignment. This…

Computation and Language · Computer Science 2025-03-04 Guanzheng Chen , Xin Li , Michael Qizhe Shieh , Lidong Bing
‹ Prev 1 4 5 6 7 8 10 Next ›