English
Related papers

Related papers: Mean Mode Screaming: Mean--Variance Split Residual…

200 papers

Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image…

Cryptography and Security · Computer Science 2024-01-01 Sheng-Yen Chou , Pin-Yu Chen , Tsung-Yi Ho

Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding for efficient inference and leveraging bidirectional attention for global context. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Sujung Hong , Chanyong Yoon , Seong Jae Hwang

Denoising diffusion models exhibit remarkable generative capabilities, but remain challenging to train due to their inherent stochasticity, where high-variance gradient estimates lead to slow convergence. Previous works have shown that…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Eric Tillman Bill , Cristian Perez Jensen , Sotiris Anagnostidis , Dimitri von Rütte

Diffusion Transformer (DiT) models have achieved unprecedented quality in image and video generation, yet their iterative sampling process remains computationally prohibitive. To accelerate inference, feature caching methods have emerged by…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Guantao Chen , Shikang Zheng , Yuqi Lin , Linfeng Zhang

Distributed multichannel active noise control (DMCANC), which utilizes multiple individual processors to achieve a global noise reduction performance comparable to conventional centralized multichannel active noise control (MCANC), has…

Systems and Control · Electrical Eng. & Systems 2025-03-25 Junwei Ji , Dongyuan Shi , Woon-Seng Gan

This paper introduces a new Transformer, called MS$^2$Dformer, that can be used as a generalized backbone for multi-modal sequence spammer detection. Spammer detection is a complex multi-modal task, thus the challenges of applying…

Machine Learning · Computer Science 2025-02-25 Zhou Yang , Yucai Pang , Hongbo Yin , Yunpeng Xiao

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee

While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the first time identify that memorization induces internal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Yuanmin Huang , Mi Zhang , Chen Chen , Feifei Li , Geng Hong , Xiaoyu You , Min Yang

Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Chaehyun Kim , Heeseong Shin , Eunbeen Hong , Heeji Yoon , Anurag Arnab , Paul Hongsuck Seo , Sunghwan Hong , Seungryong Kim

Starting from flow- and diffusion-based transformers, Multi-modal Diffusion Transformers (MM-DiTs) have reshaped text-to-vision generation, gaining acclaim for exceptional visual fidelity. As these models advance, users continually push the…

Artificial Intelligence · Computer Science 2025-10-07 Seil Kang , Woojung Han , Dayun Ju , Seong Jae Hwang

Resistance switching in multilayer structures are typically based on materials possessing ferroic orders. Here we predict an extremely large resistance switching based on the relative spin-orbit splitting in twisted transition metal…

Mesoscale and Nanoscale Physics · Physics 2023-11-15 Marc Vila

Different from the traditional software vulnerability, the microarchitecture side channel has three characteristics: extensive influence, potent threat, and tough defense. The main reason for the micro-architecture side channel is resource…

Cryptography and Security · Computer Science 2019-10-29 Yue Zhang , Ziyuan Zhu , Dan Meng

We study the conduction band spin splitting that arises in transition metal dichalcogenide (TMD) semiconductor monolayers such as MoS$_2$, MoSe$_2$, WS$_2$ and WSe$_2$ due to the combination of spin-orbit coupling and lack of inversion…

Materials Science · Physics 2014-01-01 K. Kośmider , J. W. González , J. Fernández-Rossier

The general trend in NLP is towards increasing model capacity and performance via deeper neural networks. However, simply stacking more layers of the popular Transformer architecture for machine translation results in poor convergence and…

Computation and Language · Computer Science 2019-08-30 Biao Zhang , Ivan Titov , Rico Sennrich

Uniform-noise discrete diffusion and flow models (e.g., D3PM, SEDD, UDLM, DFM) generate sequences non-autoregressively by iteratively refining randomly initialized vocabulary tokens through multiple context-dependent replacements. These…

Machine Learning · Computer Science 2026-02-18 Seunghwan Jang , SooJean Han

We present mean-shift distillation, a novel diffusion distillation technique that provides a provably good proxy for the gradient of the diffusion output distribution. This is derived directly from mean-shift mode seeking on the…

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Chaowei Chen , Xiang Zhang , Honglie Guo , Shunfang Wang

This study addresses a key limitation in deep learning Automatic Modulation Classification (AMC) models, which perform well at high signal-to-noise ratios (SNRs) but degrade under noisy conditions due to conventional feature extraction…

Machine Learning · Computer Science 2026-04-14 Prakash Suman , Yanzhen Qu

Background: Deep learning has demonstrated significant potential for automated brain metastases (BM) segmentation; however, models trained at a singular institution often exhibit suboptimal performance at various sites due to disparities in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yuchen Yang , Shuangyang Zhong , Haijun Yu , Langcuomu Suo , Hongbin Han , Florian Putz , Yixing Huang