English
Related papers

Related papers: Token Pruning for In-Context Generation in Diffusi…

200 papers

Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One major limitation of current fine-tuning approaches is the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Gordon Chen , Ziqi Huang , Cheston Tan , Ziwei Liu

Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variations in the spatial scale and difficulties of recognition…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Yuchen Ma , Zhengcong Fei , Junshi Huang

We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based…

The attention mechanism in text generation is memory-bounded due to its sequential characteristics. Therefore, off-chip memory accesses should be minimized for faster execution. Although previous methods addressed this by pruning…

Hardware Architecture · Computer Science 2024-07-23 Junyoung Park , Myeonggu Kang , Yunki Han , Yanggon Kim , Jaekang Shin , Lee-Sup Kim

Diffusion Transformer (DiT) has emerged as a powerful model architecture for generating high-quality images and videos. In the case of video DiT, 3D Spatio-Temporal Attention increases token length in proportion to the number of frames,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Hangyeol Lee , Joo-Young Kim

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , Cho-Jui Hsieh

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Sarah Rastegar , Violeta Chatalbasheva , Sieger Falkena , Anuj Singh , Yanbo Wang , Tejas Gokhale , Hamid Palangi , Hadi Jamali-Rad

Despite recent advances, diffusion-based text-to-image models still struggle with accurate text rendering. Several studies have proposed fine-tuning or training-free refinement methods for accurate text rendering. However, the critical…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Kanghyun Baek , Sangyub Lee , Jin Young Choi , Jaewoo Song , Daemin Park , Jooyoung Choi , Chaehun Shin , Bohyung Han , Sungroh Yoon

Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Hongjie Wang , Bhishma Dedhia , Niraj K. Jha

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Ruichen Wang , Zekang Chen , Chen Chen , Jian Ma , Haonan Lu , Xiaodong Lin

The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of tokens within a spatial window shows significant similarity.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-07 Jing Wang , Ao Ma , Jiasong Feng , Dawei Leng , Yuhui Yin , Xiaodan Liang

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

Neural image classifiers are known to undergo severe performance degradation when exposed to inputs that are sampled from environmental conditions that differ from their training data. Given the recent progress in Text-to-Image (T2I)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Jianhao Yuan , Francesco Pinto , Adam Davies , Philip Torr

Text-to-image models (T2I) offer a new level of flexibility by allowing users to guide the creative process through natural language. However, personalizing these models to align with user-provided visual concepts remains a challenging…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Yoad Tewel , Rinon Gal , Gal Chechik , Yuval Atzmon

There is growing demand for performing inference with hundreds of thousands of input tokens on trained transformer models. Inference at this extreme scale demands significant computational resources, hindering the application of…

Computation and Language · Computer Science 2025-02-13 Ryan Synk , Monte Hoover , John Kirchenbauer , Neel Jain , Alex Stein , Manli Shu , Josue Melendez Sanchez , Ramani Duraiswami , Tom Goldstein

Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Ling Yang , Jingwei Liu , Shenda Hong , Zhilong Zhang , Zhilin Huang , Zheming Cai , Wentao Zhang , Bin Cui

Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Wenjie Wei , Xiaolong Zhou , Malu Zhang , Ammar Belatreche , Qian Sun , Yimeng Shan , Dehao Zhang , Zijian Zhou , Zeyu Ma , Yang Yang , Haizhou Li

Large-scale Text-to-Image (T2I) diffusion models demonstrate significant generation capabilities based on textual prompts. Based on the T2I diffusion models, text-guided image editing research aims to empower users to manipulate generated…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Chuanming Tang , Kai Wang , Fei Yang , Joost van de Weijer

Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation. For most applications, we can train the model end-toend with paired…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Nithin Gopalakrishnan Nair , Jeya Maria Jose Valanarasu , Vishal M Patel

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Daniel Bolya , Judy Hoffman