English
Related papers

Related papers: Circle-RoPE: Cone-like Decoupled Rotary Positional…

200 papers

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Grégoire Dhimoïla , Thomas Fel , Victor Boutin , Agustin Picard

We present Position Interpolation (PI) that extends the context window sizes of RoPE-based pretrained LLMs such as LLaMA models to up to 32768 with minimal fine-tuning (within 1000 steps), while demonstrating strong empirical results on…

Computation and Language · Computer Science 2023-06-29 Shouyuan Chen , Sherman Wong , Liangjian Chen , Yuandong Tian

Vision foundation models have been explored recently to build general-purpose vision systems. However, predominant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality interaction, which…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Yunhang Shen , Chaoyou Fu , Peixian Chen , Mengdan Zhang , Ke Li , Xing Sun , Yunsheng Wu , Shaohui Lin , Rongrong Ji

Neural Machine Translation (NMT) models have traditionally used Sinusoidal Positional Embeddings (PEs), which often struggle to capture long-range dependencies and are inefficient for handling extended context or document-level translation…

Computation and Language · Computer Science 2025-02-11 Varun Gumma , Pranjal A. Chitale , Kalika Bali

Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Zhihong Wei

Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle when references exhibit severe stylistic domain gaps with the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Xiao Cao , Yansong Qu , Xiangzhen , Chang , Wen Xiao , Jiakui Hu , Heyuan Li , Jialun Liu , Zhiyong Huang , Xuelong Li

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned…

Computer Vision and Pattern Recognition · Computer Science 2023-02-14 Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Chunhua Shen

Although a wide variety of deep neural networks for robust Visual Odometry (VO) can be found in the literature, they are still unable to solve the drift problem in long-term robot navigation. Thus, this paper aims to propose novel deep…

Computer Vision and Pattern Recognition · Computer Science 2019-06-25 Yimin Lin , Zhaoxiang Liu , Jianfeng Huang , Chaopeng Wang , Guoguang Du , Jinqiang Bai , Shiguo Lian , Bill Huang

Top-down images play an important role in safety-critical settings such as autonomous navigation and aerial surveillance, where they provide holistic spatial information that front-view images cannot capture. Despite this, Vision Language…

Machine Learning · Computer Science 2025-10-02 Kaiyuan Hou , Minghui Zhao , Lilin Xu , Yuang Fan , Xiaofan Jiang

This paper aims to overcome the "lost-in-the-middle" challenge of large language models (LLMs). While recent advancements have successfully enabled LLMs to perform stable language modeling with up to 4 million tokens, the persistent…

Computation and Language · Computer Science 2024-03-11 Zhenyu Zhang , Runjin Chen , Shiwei Liu , Zhewei Yao , Olatunji Ruwase , Beidi Chen , Xiaoxia Wu , Zhangyang Wang

While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, precise coordinate prediction remains a significant challenge, particularly as high-resolution inputs cause visual positional encodings (VPEs) to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Xingjian Tao , Yiwei Wang , Yujun Cai , Yihong Luo , Kai Han , Jing Tang

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Jiale Liu , Haoming Zhou , Yishu Liu , Bingzhi Chen , Yuncheng Jiang

We introduce a rotation-invariant representation of planar shapes. In particular, this representation encodes shapes as vectors such that the Euclidean distance between them serves as a valid shape distance. For standardized, star-shaped…

Computational Geometry · Computer Science 2026-05-28 Hamid Shafieasl , Jeff M. Phillips

Understanding how language and embedding models encode semantic relationships is fundamental to model interpretability. While early word embeddings exhibited intuitive vector arithmetic (''king'' - ''man'' + ''woman'' = ''queen''), modern…

Computation and Language · Computer Science 2026-02-27 Michael Freenor , Lauren Alvarez

Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce…

Computation and Language · Computer Science 2026-05-11 Xinran Li , Xinze Che , Yifan Lyu , Zhiqi Huang , Xiujuan Xu

We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Zhicheng Huang , Zhaoyang Zeng , Yupan Huang , Bei Liu , Dongmei Fu , Jianlong Fu

Objects undergo varying amounts of perspective distortion as they move across a camera's field of view. Models for predicting 3D from a single image often work with crops around the object of interest and ignore the location of the object…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Aditya Prakash , Arjun Gupta , Saurabh Gupta

Prompt tuning (PT), as an emerging resource-efficient fine-tuning paradigm, has showcased remarkable effectiveness in improving the task-specific transferability of vision-language models. This paper delves into a previously overlooked…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Fei Zhang , Tianfei Zhou , Jiangchao Yao , Ya Zhang , Ivor W. Tsang , Yanfeng Wang

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

Artificial Intelligence · Computer Science 2025-08-14 Zixian Guo , Ming Liu , Qilong Wang , Zhilong Ji , Jinfeng Bai , Lei Zhang , Wangmeng Zuo

In-pipe inspection robots must traverse confined pipeline networks with elbows and three-dimensional fittings, requiring both reliable axial traction and rapid rolling reorientation for posture correction. In compact V-shaped platforms,…

Robotics · Computer Science 2026-03-31 Min Yang , Yang Tian , Longchuang Li , Jun Ma , Shugen Ma
‹ Prev 1 8 9 10 Next ›