Copertina

A one-step generation model with a Single-Layer Transformer: Layer number re-distillation of FreeFlow

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wei, Haonan, Wang, Linyuan, Sun, Nuolin, Zheng, Zhizhong, Li, Lei, Yan, Bin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MFI-ResNet: Efficient ResNet Architecture Optimization via MeanFlow Compression and Selective Incubation
di: Sun, Nuolin, et al.
Pubblicazione: (2025)

Are classical deep neural networks weakly adversarially robust?
di: Sun, Nuolin, et al.
Pubblicazione: (2025)

Dual-Domain CLIP-Assisted Residual Optimization Perception Model for Metal Artifact Reduction
di: Zhang, Xinrui, et al.
Pubblicazione: (2024)

Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers
di: Ma, Jian, et al.
Pubblicazione: (2025)

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
di: Song, Yiren, et al.
Pubblicazione: (2025)

A solvable generative model with a linear, one-step denoiser
di: Halder, Indranil
Pubblicazione: (2024)

Step-by-step Layered Design Generation
di: Khan, Faizan Farooq, et al.
Pubblicazione: (2025)

Learning few-step posterior samplers by unfolding and distillation of diffusion models
di: Mbakam, Charlesquin Kemajou, et al.
Pubblicazione: (2025)

Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance
di: Xue, Naifu, et al.
Pubblicazione: (2025)

LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow
di: Wen, Hongyu, et al.
Pubblicazione: (2024)

LayerFlow: A Unified Model for Layer-aware Video Generation
di: Ji, Sihui, et al.
Pubblicazione: (2025)

SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer
di: Hui, Zheng, et al.
Pubblicazione: (2026)

OmniPSD: Layered PSD Generation with Diffusion Transformer
di: Liu, Cheng, et al.
Pubblicazione: (2025)

Stable Flow: Vital Layers for Training-Free Image Editing
di: Avrahami, Omri, et al.
Pubblicazione: (2024)

Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging
di: Fu, Zihang, et al.
Pubblicazione: (2026)

Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
di: Xue, Chaocan, et al.
Pubblicazione: (2025)

Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
di: Chen, Ruidong, et al.
Pubblicazione: (2026)

LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models
di: Zhang, Dingkun, et al.
Pubblicazione: (2024)

DanceText: A Training-Free Layered Framework for Controllable Multilingual Text Transformation in Images
di: Yu, Zhenyu, et al.
Pubblicazione: (2025)

Training-free image inversion for one-step diffusion models
di: Wu, Tao, et al.
Pubblicazione: (2026)

Aligned with LLM: a new multi-modal training paradigm for encoding fMRI activity in visual cortex
di: Ma, Shuxiao, et al.
Pubblicazione: (2024)

Interpretable and Sparse Linear Attention with Decoupled Membership-Subspace Modeling via MCR2 Objective
di: Liu, Tianyuan, et al.
Pubblicazione: (2026)

Cycle-Consistent Tuning for Layered Image Decomposition
di: Gu, Zheng, et al.
Pubblicazione: (2026)

LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
di: Fu, Fengyi, et al.
Pubblicazione: (2025)

HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations
di: Xu, Yiran, et al.
Pubblicazione: (2025)

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference
di: Li, Guandong
Pubblicazione: (2026)

Adversarial Score Distillation: When score distillation meets GAN
di: Wei, Min, et al.
Pubblicazione: (2023)

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode
di: Huang, Junjia, et al.
Pubblicazione: (2025)

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
di: Cheng, Zhenglin, et al.
Pubblicazione: (2025)

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition
di: Yin, Shengming, et al.
Pubblicazione: (2025)

LayerAnimate: Layer-level Control for Animation
di: Yang, Yuxue, et al.
Pubblicazione: (2025)

Segmentation-guided Layer-wise Image Vectorization with Gradient Fills
di: Zhou, Hengyu, et al.
Pubblicazione: (2024)

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
di: Ricci, Simone, et al.
Pubblicazione: (2024)

LayerShuffle: Enhancing Robustness in Vision Transformers by Randomizing Layer Execution Order
di: Freiberger, Matthias, et al.
Pubblicazione: (2024)

GALA: Generating Animatable Layered Assets from a Single Scan
di: Kim, Taeksoo, et al.
Pubblicazione: (2024)

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training
di: Tareen, Shaharyar Ahmed Khan, et al.
Pubblicazione: (2025)

Streamline pathology foundation model by cross-magnification distillation
di: Su, Ziyu, et al.
Pubblicazione: (2025)

Pruning Self-attentions into Convolutional Layers in Single Path
di: He, Haoyu, et al.
Pubblicazione: (2021)

Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
di: Zhou, Junsheng, et al.
Pubblicazione: (2024)

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
di: Wei, Tianyi, et al.
Pubblicazione: (2025)