English
Related papers

Related papers: M2T: Masking Transformers Twice for Faster Decodin…

200 papers

Modern large language models use a fixed tokenizer to effectively compress text drawn from a source domain. However, applying the same tokenizer to a new target domain often leads to inferior compression, more costly inference, and reduced…

Computation and Language · Computer Science 2024-11-07 Zhili Feng , Tanya Marwah , Nicolo Fusi , David Alvarez-Melis , Lester Mackey

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

Networking and Internet Architecture · Computer Science 2025-11-04 Junhe Zhang , Wanli Ni , Pengwei Wang , Dongyu Wang

Large-scale language model pretraining is a very successful form of self-supervised learning in natural language processing, but it is increasingly expensive to perform as the models and pretraining corpora have become larger over time. We…

Computation and Language · Computer Science 2023-06-07 Haoxin Li , Phillip Keung , Daniel Cheng , Jungo Kasai , Noah A. Smith

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Ziyao Wang , Chen Chen , Jingtao Li , Weiming Zhuang , Jiabo Huang , Ang Li , Lingjuan Lyu

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Wenzhao Xiang , Chang Liu , Hongyang Yu , Xilin Chen

Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Kaiwen Zhu , Quansheng Zeng , Yuandong Pu , Shuo Cao , Xiaohui Li , Yi Xin , Qi Qin , Jiayang Li , Yu Qiao , Jinjin Gu , Yihao Liu

We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Fabian Mentzer , George Toderici , David Minnen , Sung-Jin Hwang , Sergi Caelles , Mario Lucic , Eirikur Agustsson

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or…

Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…

Image and Video Processing · Electrical Eng. & Systems 2025-03-17 Tiantian Li , Qunbing Xia , Yue Li , Ruixiao Guo , Gaobo Yang

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

Image and Video Processing · Electrical Eng. & Systems 2023-04-27 Xuhao Jiang , Weimin Tan , Tian Tan , Bo Yan , Liquan Shen

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

Recently, more and more images are compressed and sent to the back-end devices for the machine analysis tasks~(\textit{e.g.,} object detection) instead of being purely watched by humans. However, most traditional or learned image codecs are…

Image and Video Processing · Electrical Eng. & Systems 2022-06-14 Guo Lu , Xingtong Ge , Tianxiong Zhong , Jing Geng , Qiang Hu

This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate…

Image and Video Processing · Electrical Eng. & Systems 2024-02-21 Yi-Hsin Chen , Kuan-Wei Ho , Shiau-Rung Tsai , Guan-Hsun Lin , Alessandro Gnutti , Wen-Hsiao Peng , Riccardo Leonardi

Compressed Neural Networks have the potential to enable deep learning across new applications and smaller computational environments. However, understanding the range of learning tasks in which such models can succeed is not well studied.…

Machine Learning · Computer Science 2023-08-10 Matt Gorbett , Hossein Shirazi , Indrakshi Ray

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Geonung Kim , Beomsu Kim , Eunhyeok Park , Sunghyun Cho

Though image transformers have shown competitive results with convolutional neural networks in computer vision tasks, lacking inductive biases such as locality still poses problems in terms of model efficiency especially for embedded…

Computer Vision and Pattern Recognition · Computer Science 2022-07-08 Ling Li , Ali Shafiee Ardestani , Joseph Hassoun

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

The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address…

Machine Learning · Computer Science 2018-10-23 Qing Qin , Jie Ren , Jialong Yu , Ling Gao , Hai Wang , Jie Zheng , Yansong Feng , Jianbin Fang , Zheng Wang

Overparameterized models have proven to be powerful tools for solving various machine learning tasks. However, overparameterization often leads to a substantial increase in computational and memory costs, which in turn requires extensive…

Machine Learning · Computer Science 2024-03-13 Soo Min Kwon , Zekai Zhang , Dogyoon Song , Laura Balzano , Qing Qu

We propose a neural network model to estimate the current frame from two reference frames, using affine transformation and adaptive spatially-varying filters. The estimated affine transformation allows for using shorter filters compared to…

Image and Video Processing · Electrical Eng. & Systems 2021-02-18 Hyomin Choi , Ivan V. Bajić