English
Related papers

Related papers: Beyond Sequential Distance: Inter-Modal Distance I…

200 papers

Rotary Positional Embeddings (RoPE) have become the standard for Large Language Models (LLMs) due to their ability to encode relative positions through geometric rotation. However, we identify a significant limitation we term ''Spectral…

Computation and Language · Computer Science 2026-02-02 Kanishk Awadhiya

Multimodal Large Language Models (MLLMs) utilize multimodal contexts consisting of text, images, or videos to solve various multimodal tasks. However, we find that changing the order of multimodal input can cause the model's performance to…

Artificial Intelligence · Computer Science 2024-10-23 Zhijie Tan , Xu Chu , Weiping Li , Tong Mo

Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guidance for modeling dependencies between elements across…

Machine Learning · Computer Science 2025-08-27 Avinash Amballa

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information across modalities from in-context examples? We…

Computation and Language · Computer Science 2026-05-27 Yiran Huang , Karsten Roth , Quentin Bouniot , Wenjia Xu , Zeynep Akata

Position embedding is a core component of current Large Language Models (LLMs). Rotary position embedding (RoPE), a technique that encodes the position information with a rotation matrix, has been the de facto choice for position embedding…

Computation and Language · Computer Science 2024-05-24 Xin Men , Mingyu Xu , Bingning Wang , Qingyu Zhang , Hongyu Lin , Xianpei Han , Weipeng Chen

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows $SE(3)$-invariant attention with multi-frequency similarity, and can…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Yu Wu , Minsik Jeon , Jen-Hao Rick Chang , Oncel Tuzel , Shubham Tulsiani

Advances in multi-modal large language models (MLLMs) have inspired time series understanding and reasoning tasks, that enable natural language querying over time series, producing textual analyses of complex temporal dynamics. Recent…

Machine Learning · Computer Science 2026-02-05 Hang Ni , Weijia Zhang , Fei Wang , Zezhi Shao , Hao Liu

We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Sophia Sirko-Galouchenko , Spyros Gidaris , Antonin Vobecky , Andrei Bursuc , Nicolas Thome

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded…

Machine Learning · Computer Science 2025-11-18 Felipe Urrutia , Jorge Salas , Alexander Kozachinskiy , Cristian Buc Calderon , Hector Pasten , Cristobal Rojas

This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with…

Computation and Language · Computer Science 2024-09-05 Suyuchen Wang , Ivan Kobyzev , Peng Lu , Mehdi Rezagholizadeh , Bang Liu

We propose Parabolic Position Encoding (PaPE), a parabola-based position encoding for vision modalities in attention-based architectures. Given a set of vision tokens-such as from videos, event camera streams, images, or point clouds-our…

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Feng Han , Zhixiong Zhang , Zheming Liang , Yibin Wang , Jiaqi Wang

Using special tokens (e.g., gist, memory, or compressed tokens) to compress context information is a common practice for large language models (LLMs). However, existing approaches often neglect that position encodings inherently induce…

Computation and Language · Computer Science 2025-09-29 Runsong Zhao , Xin Liu , Xinyu Liu , Pengcheng Huang , Chunyang Xiao , Tong Xiao , Jingbo Zhu

The rapid growth of Large Language Models (LLMs) usage has highlighted the importance of gradient-free in-context learning (ICL). However, interpreting their inner workings remains challenging. This paper introduces a novel multimodal…

Computation and Language · Computer Science 2024-08-26 Yosuke Miyanishi , Minh Le Nguyen

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key…

Artificial Intelligence · Computer Science 2026-02-03 Yifei Shao , Kun Zhou , Ziming Xu , Mohammad Atif Quamar , Shibo Hao , Zhen Wang , Zhiting Hu , Biwei Huang

Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively enhances the representational capability of LLMs by prepending a few task-related…

Computation and Language · Computer Science 2026-05-05 Ailiang Lin , Zhuoyun Li , Keyu Mao , Kotaro Funakoshi , Manabu Okumura

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…

Computation and Language · Computer Science 2025-10-27 Josip Jukić , Jan Šnajder

Multimodal semantic understanding often has to deal with uncertainty, which means the obtained messages tend to refer to multiple targets. Such uncertainty is problematic for our interpretation, including inter- and intra-modal uncertainty.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-21 Yatai Ji , Junjie Wang , Yuan Gong , Lin Zhang , Yanru Zhu , Hongfa Wang , Jiaxing Zhang , Tetsuya Sakai , Yujiu Yang

High inter-class similarity, extreme scale variation, and limited computational budgets hinder reliable visual recognition across diverse real-world data. Existing vision-centric and cross-modal approaches often rely on rigid fusion…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Qinghui Chen , Zekai Zhang , Zaigui Zhang , Kai Zhang , Dagang Li , Wenmin Wang , Jinglin Zhang , Cong Liu

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Chenshu Hou , Liang Peng , Xiaopei Wu , Xiaofei He , Wenxiao Wang
‹ Prev 1 3 4 5 6 7 10 Next ›