Copertina

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Lu, Pengqi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mode Seeking meets Mean Seeking for Fast Long Video Generation
di: Cai, Shengqu, et al.
Pubblicazione: (2026)

MeanFlow Transformers with Representation Autoencoders
di: Hu, Zheyuan, et al.
Pubblicazione: (2025)

Mean-field Chaos Diffusion Models
di: Park, Sungwoo, et al.
Pubblicazione: (2024)

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
di: Gurumurthy, Swaminathan, et al.
Pubblicazione: (2024)

Improved Mean Flows: On the Challenges of Fastforward Generative Models
di: Geng, Zhengyang, et al.
Pubblicazione: (2025)

Doubly Stochastic Mean-Shift Clustering
di: Trigano, Tom, et al.
Pubblicazione: (2026)

Convergence Analysis of Blurring Mean Shift
di: Yamasaki, Ryoya, et al.
Pubblicazione: (2024)

Functional Mean Flow in Hilbert Space
di: Li, Zhiqi, et al.
Pubblicazione: (2025)

Adversarial Training from Mean Field Perspective
di: Kumano, Soichiro, et al.
Pubblicazione: (2025)

Mean Flows for One-step Generative Modeling
di: Geng, Zhengyang, et al.
Pubblicazione: (2025)

Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
di: Ma, Xinyin, et al.
Pubblicazione: (2024)

Residual Denoising Diffusion Models
di: Liu, Jiawei, et al.
Pubblicazione: (2023)

MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers
di: Li, Ao, et al.
Pubblicazione: (2025)

Variance-Aware Adaptive Weighting for Diffusion Model Training
di: Sun, Nanlong, et al.
Pubblicazione: (2026)

AlphaFlow: Understanding and Improving MeanFlow Models
di: Zhang, Huijie, et al.
Pubblicazione: (2025)

Disentangling Mean Embeddings for Better Diagnostics of Image Generators
di: Gruber, Sebastian G., et al.
Pubblicazione: (2024)

MimicNorm: Weight Mean and Last BN Layer Mimic the Dynamic of Batch Normalization
di: Fei, Wen, et al.
Pubblicazione: (2020)

Kernel Correlation-Dissimilarity for Multiple Kernel k-Means Clustering
di: Su, Rina, et al.
Pubblicazione: (2024)

Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
di: Li, Feijiang, et al.
Pubblicazione: (2026)

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification
di: Amini, Sajjad, et al.
Pubblicazione: (2024)

Split Adaptation for Pre-trained Vision Transformers
di: Wang, Lixu, et al.
Pubblicazione: (2025)

Split Gibbs Discrete Diffusion Posterior Sampling
di: Chu, Wenda, et al.
Pubblicazione: (2025)

Shiva-DiT: Residual-Based Differentiable Top-$k$ Selection for Efficient Diffusion Transformers
di: Zhang, Jiaji, et al.
Pubblicazione: (2026)

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
di: Goswami, Dipam, et al.
Pubblicazione: (2024)

M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy
di: Zhang, Hansong, et al.
Pubblicazione: (2023)

Filtered Posterior Mean Collections: A Unified Framework for Analytical Models of Diffusion Generalization
di: Niedoba, Matthew, et al.
Pubblicazione: (2026)

Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance
di: Sani, Matina Mahdizadeh, et al.
Pubblicazione: (2026)

ReflexSplit: Single Image Reflection Separation via Layer Fusion-Separation
di: Lee, Chia-Ming, et al.
Pubblicazione: (2026)

An Analysis of Regularization and Fokker-Planck Residuals in Diffusion Models for Image Generation
di: Niemann, Onno, et al.
Pubblicazione: (2026)

TerDiT: Ternary Diffusion Models with Transformers
di: Lu, Xudong, et al.
Pubblicazione: (2024)

Understanding, Accelerating, and Improving MeanFlow Training
di: Kim, Jin-Young, et al.
Pubblicazione: (2025)

Unsupervised Transformer Pre-Training for Images: Self-Distillation, Mean Teachers, and Random Crops
di: Scardecchia, Mattia
Pubblicazione: (2025)

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
di: Lee, Byung Hyun, et al.
Pubblicazione: (2025)

Synthesizing Accurate and Realistic T1-weighted Contrast-Enhanced MR Images using Posterior-Mean Rectified Flow
di: Brandstötter, Bastian, et al.
Pubblicazione: (2025)

Cross-Modal Domain Adaptation in Brain Disease Diagnosis: Maximum Mean Discrepancy-based Convolutional Neural Networks
di: Zhu, Xuran
Pubblicazione: (2024)

Steer Away From Mode Collisions: Improving Composition In Diffusion Models
di: Dutta, Debottam, et al.
Pubblicazione: (2025)

LAuReL: Learned Augmented Residual Layer
di: Menghani, Gaurav, et al.
Pubblicazione: (2024)

Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
di: Wang, Tianfu, et al.
Pubblicazione: (2024)

Diffusion Transformers with Representation Autoencoders
di: Zheng, Boyang, et al.
Pubblicazione: (2025)

MeanCache: From Instantaneous to Average Velocity for Accelerating Flow Matching Inference
di: Gao, Huanlin, et al.
Pubblicazione: (2026)