English
Related papers

Related papers: Beyond flattening: a geometrically principled posi…

200 papers

Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel state information (CSI) modeling, latent characterization, and task-specific prediction.…

Signal Processing · Electrical Eng. & Systems 2026-05-05 Chenyu Zhang , Xinchen Lyu , Chenshan Ren , Shuhan Liu , Qimei Cui

Whole slide images (WSIs) in computational pathology (CPath) pose a major computational challenge due to their gigapixel scale, often requiring the processing of tens to hundreds of thousands of high-resolution patches per slide. This…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Yonghan Shin , SeungKyu Kim , Won-Ki Jeong

Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…

Robotics · Computer Science 2020-09-24 Takayuki Osa , Shuhei Ikemoto

In the realm of large-scale language models, a significant challenge arises when extrapolating sequences beyond the maximum allowable length. This is because the model's position embedding mechanisms are limited to positions encountered…

Computation and Language · Computer Science 2025-02-05 Yui Oka , Taku Hasegawa , Kyosuke Nishida , Kuniko Saito

Fully Homomorphic Encryption (FHE) provides a powerful paradigm for secure computation, but its practical adoption is severely hindered by the prohibitive computational cost of its bootstrapping procedure. The complexity of all current…

Cryptography and Security · Computer Science 2025-10-06 Dongfang Zhao

Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to choice for researchers. We find that although PEFT can…

Machine Learning · Computer Science 2025-05-29 Yongkang Liu , Xingle Xu , Ercong Nie , Zijing Wang , Shi Feng , Daling Wang , Qian Li , Hinrich Schütze

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Computation and Language · Computer Science 2026-05-12 Yu Wang , Sheng Shen , Rémi Munos , Hongyuan Zhan , Yuandong Tian

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Machine Learning · Computer Science 2021-11-04 Shengjie Luo , Shanda Li , Tianle Cai , Di He , Dinglan Peng , Shuxin Zheng , Guolin Ke , Liwei Wang , Tie-Yan Liu

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Ye Du , Zehua Fu , Qingjie Liu , Yunhong Wang

Answering complex queries on knowledge graphs is important but particularly challenging because of the data incompleteness. Query embedding methods address this issue by learning-based models and simulating logical reasoning with set…

Artificial Intelligence · Computer Science 2023-05-09 Zihao Wang , Weizhi Fei , Hang Yin , Yangqiu Song , Ginny Y. Wong , Simon See

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based…

Machine Learning · Computer Science 2022-10-31 Shengjie Luo , Shanda Li , Shuxin Zheng , Tie-Yan Liu , Liwei Wang , Di He

Neural Radiance Fields (NeRF) have attracted significant attention due to their ability to synthesize novel scene views with great accuracy. However, inherent to their underlying formulation, the sampling of points along a ray with zero…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Brian K. S. Isaac-Medina , Chris G. Willcocks , Toby P. Breckon

We investigate the utility of meta-optical encoders for generalizable image compression by leveraging their intrinsic shift-invariant point spread functions (PSFs). Compared with purely digital approaches, such optical encoders offer…

Optics · Physics 2026-02-23 Yubo Zhang , Rui Chen , Zhihao Zhou , Arka Majumdar

Image segmentation is a popular area of research in computer vision that has many applications in automated image processing. A recent technique called piecewise flat embeddings (PFE) has been proposed for use in image segmentation; PFE…

Computer Vision and Pattern Recognition · Computer Science 2016-12-21 Renee T. Meinhold , Tyler L. Hayes , Nathan D. Cahill

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Shaochen Zhang , Zekun Qi , Runpei Dong , Xiuxiu Bai , Xing Wei

To analyze high-dimensional and complex data in the real world, deep generative models, such as variational autoencoder (VAE) embed data in a low-dimensional space (latent space) and learn a probabilistic model in the latent space. However,…

Machine Learning · Computer Science 2020-09-01 Keizo Kato , Jing Zhou , Tomotake Sasaki , Akira Nakagawa

Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision, resulting in…

I present a Variational Autoencoder (VAE) trained on collider physics data (specifically boosted $W$ jets), with reconstruction error given by an approximation to the Earth Movers Distance (EMD) between input and output jets. This VAE…

High Energy Physics - Phenomenology · Physics 2022-04-20 Jack H. Collins

The high-dimensional nature of the 4-D light field (LF) poses great challenges in achieving efficient and effective feature embedding, that severely impacts the performance of downstream tasks. To tackle this crucial issue, in contrast to…

Image and Video Processing · Electrical Eng. & Systems 2024-01-12 Xianqiang Lyu , Junhui Hou

Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks. However, existing metrics for quantifying the strength of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-03 Chieh Hubert Lin , Hsin-Ying Lee , Hung-Yu Tseng , Maneesh Singh , Ming-Hsuan Yang
‹ Prev 1 8 9 10 Next ›