English
Related papers

Related papers: A Hidden Semantic Bottleneck in Conditional Embedd…

200 papers

The video composition task aims to integrate specified foregrounds and backgrounds from different videos into a harmonious composite. Current approaches, predominantly trained on videos with adjusted foreground color and lighting, struggle…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Jiaqi Guo , Sitong Su , Junchen Zhu , Lianli Gao , Jingkuan Song

Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector. By contrast, Transformers have little inductive bias…

Machine Learning · Computer Science 2022-10-26 Aniket Didolkar , Kshitij Gupta , Anirudh Goyal , Nitesh B. Gundavarapu , Alex Lamb , Nan Rosemary Ke , Yoshua Bengio

Word embeddings have become a staple of several natural language processing tasks, yet much remains to be understood about their properties. In this work, we analyze word embeddings in terms of their principal components and arrive at a…

Computation and Language · Computer Science 2020-05-22 Vikas Raunak , Vaibhav Kumar , Vivek Gupta , Florian Metze

Foundation model-based semantic transmission has recently shown great potential in wireless image communication. However, existing methods exhibit two major limitations: (i) they overlook the varying importance of semantic components for…

Image and Video Processing · Electrical Eng. & Systems 2025-09-30 Fangyu Liu , Peiwen Jiang , Wenjin Wang , Chao-Kai Wen , Shi Jin , Jun Zhang

Traditional transformer-based semantic segmentation relies on quantized embeddings. However, our analysis reveals that autoencoder accuracy on segmentation mask using quantized embeddings (e.g. VQ-VAE) is 8% lower than continuous-valued…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Masud Ahmed , Zahid Hasan , Syed Arefinul Haque , Abu Zaher Md Faridee , Sanjay Purushotham , Suya You , Nirmalya Roy

Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a strong potential for achieving better non-autoregressive…

Computation and Language · Computer Science 2024-02-26 Yuxuan Liu , Tianchi Yang , Shaohan Huang , Zihan Zhang , Haizhen Huang , Furu Wei , Weiwei Deng , Feng Sun , Qi Zhang

The geometric evolution of token representations in large language models (LLMs) presents a fundamental paradox: while human language inherently organizes semantic information in low-dimensional spaces ($\sim 10^1$ dimensions), modern LLMs…

Computation and Language · Computer Science 2025-03-31 Zhuo-Yang Song , Zeyu Li , Qing-Hong Cao , Ming-xing Luo , Hua Xing Zhu

Text-to-image diffusion models have shown powerful ability on conditional image synthesis. With large-scale vision-language pre-training, diffusion models are able to generate high-quality images with rich texture and reasonable structure…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Hefeng Wang , Jiale Cao , Jin Xie , Aiping Yang , Yanwei Pang

Diffusion models have attained impressive visual quality for image synthesis. However, how to interpret and manipulate the latent space of diffusion models has not been extensively explored. Prior work diffusion autoencoders encode the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Zeyu Lu , Chengyue Wu , Xinyuan Chen , Yaohui Wang , Lei Bai , Yu Qiao , Xihui Liu

Transformer-based models have delivered impressive results on many tasks, particularly vision and language tasks. In many model training situations, conventional configurations are typically adopted. For example, we often set the base model…

Machine Learning · Computer Science 2023-05-19 Fuzhao Xue , Jianghai Chen , Aixin Sun , Xiaozhe Ren , Zangwei Zheng , Xiaoxin He , Yongming Chen , Xin Jiang , Yang You

Diffusion transformers typically incorporate textual information via attention layers and a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Nikita Starodubcev , Daniil Pakhomov , Zongze Wu , Ilya Drobyshevskiy , Yuchen Liu , Zhonghao Wang , Yuqian Zhou , Zhe Lin , Dmitry Baranchuk

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Computation and Language · Computer Science 2026-05-20 Benjamin L. Badger

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Building on recent advances in representation learning for wireless channels, this work investigates the cost-benefit trade-offs of high-dimensional channel embeddings in practical systems. We benchmark multiple wireless representations:…

Signal Processing · Electrical Eng. & Systems 2026-05-05 Murilo Batista , Shirin Salehi , Saeed Mashdour , Paul Zheng , Rodrigo C. de Lamare , Anke Schmeink

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Soumik Mukhopadhyay , Matthew Gwilliam , Vatsal Agarwal , Namitha Padmanabhan , Archana Swaminathan , Srinidhi Hegde , Tianyi Zhou , Abhinav Shrivastava

Contextualized embeddings vary by context, even for the same token, and form a distribution in the embedding space. To analyze this distribution, we focus on the norm of the mean embedding and the variance of the embeddings. In this study,…

Computation and Language · Computer Science 2024-12-18 Hiroaki Yamagiwa , Hidetoshi Shimodaira

Diffusion models have recently received increasing research attention for their remarkable transfer abilities in semantic segmentation tasks. However, generating fine-grained segmentation masks with diffusion models often requires…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Koichi Namekata , Amirmojtaba Sabour , Sanja Fidler , Seung Wook Kim

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

Computation and Language · Computer Science 2019-08-30 Jindřich Libovický , Pranava Madhyastha

Recent advances in denoising diffusion probabilistic models have shown great success in image synthesis tasks. While there are already works exploring the potential of this powerful tool in image semantic segmentation, its application in…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Xinrong Hu , Yu-Jen Chen , Tsung-Yi Ho , Yiyu Shi

Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Hao Chen , Yujin Han , Fangyi Chen , Xiang Li , Yidong Wang , Jindong Wang , Ze Wang , Zicheng Liu , Difan Zou , Bhiksha Raj
‹ Prev 1 3 4 5 6 7 10 Next ›