Image de couverture de livre

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hu, Dongting, Gupta, Aarush, Gabidolla, Magzhan, Sahni, Arpit, Coskun, Huseyin, Li, Yanyu, Idelbayev, Yerlan, Mahmood, Ahsan, Lebedev, Aleksei, Lahiri, Dishani, Goyal, Anujraaj, Hu, Ju, Gong, Mingming, Tulyakov, Sergey, Kag, Anil
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
par: Hu, Dongting, et autres
Publié: (2024)

SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
par: Wu, Yushu, et autres
Publié: (2024)

S2DiT: Sandwich Diffusion Transformer for Mobile Streaming Video Generation
par: Zhao, Lin, et autres
Publié: (2026)

TextCraftor: Your Text Encoder Can be Image Quality Controller
par: Li, Yanyu, et autres
Publié: (2024)

BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
par: Sui, Yang, et autres
Publié: (2024)

Preventing Shortcuts in Adapter Training via Providing the Shortcuts
par: Goyal, Anujraaj Argo, et autres
Publié: (2025)

Scalable Ranked Preference Optimization for Text-to-Image Generation
par: Karthik, Shyamgopal, et autres
Publié: (2024)

EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow
par: Park, Dogyun, et autres
Publié: (2026)

Efficient Training with Denoised Neural Weights
par: Gong, Yifan, et autres
Publié: (2024)

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds
par: Wu, Yushu, et autres
Publié: (2025)

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis
par: Menapace, Willi, et autres
Publié: (2024)

AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
par: Kag, Anil, et autres
Publié: (2024)

E$^{2}$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
par: Gong, Yifan, et autres
Publié: (2024)

COMNETS: COst-sensitive decision trees approach to throughput optimization for Multi-radio IoT NETworkS
par: Sundaram, Jothi Prasanna Shanmuga, et autres
Publié: (2025)

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
par: Wang, Yifan, et autres
Publié: (2026)

LayerComposer: Multi-Human Personalized Generation via Layered Canvas
par: Qian, Guocheng Gordon, et autres
Publié: (2025)

MARS: Multi-radio Architecture with Radio Selection using Decision Trees for emerging mesoscale CPS/IoT applications
par: Sundaram, Jothi Prasanna Shanmuga, et autres
Publié: (2024)

BodyMAP -- Jointly Predicting Body Mesh and 3D Applied Pressure Map for People in Bed
par: Tandon, Abhishek, et autres
Publié: (2024)

Improving Progressive Generation with Decomposable Flow Matching
par: Haji-Ali, Moayed, et autres
Publié: (2025)

Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers
par: Park, Dogyun, et autres
Publié: (2025)

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
par: Wu, Yushu, et autres
Publié: (2025)

Recovering the state and dynamics of autonomous system with partial states solution using neural networks
par: Kag, Vijay
Publié: (2024)

OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
par: Huang, Tianyu, et autres
Publié: (2025)

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
par: Aggarwal, Aarush, et autres
Publié: (2026)

Lightweight Predictive 3D Gaussian Splats
par: Cao, Junli, et autres
Publié: (2024)

KUZATUV KAMERALARI VIDEO OQIMLARIDA HARAKATNI ANIQLASH USULLARI TAHLILI
par: Tashmanov, Yerlan
Publié: (2025)

A Multi-Branched Radial Basis Network Approach to Predicting Complex Chaotic Behaviours
par: Sinha, Aarush
Publié: (2024)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
par: Sinha, Aarush
Publié: (2025)

GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification
par: Sinha, Aarush
Publié: (2025)

SF-V: Single Forward Video Generation Model
par: Zhang, Zhixing, et autres
Publié: (2024)

Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matching
par: Cai, Wenxiao, et autres
Publié: (2024)

Improving the Diffusability of Autoencoders
par: Skorokhodov, Ivan, et autres
Publié: (2025)

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario
par: Liu, Renyang, et autres
Publié: (2024)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
par: Wu, Ziyi, et autres
Publié: (2025)

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
par: Chen, Yunuo, et autres
Publié: (2025)

A novel framework for generalization of deep hidden physics models
par: Kag, Vijay, et autres
Publié: (2024)

Physics-informed neural network for modeling dynamic linear elasticity
par: Kag, Vijay, et autres
Publié: (2023)

SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model
par: Chan, Trevor J., et autres
Publié: (2024)

CFD-DEM modeling of fracture initiation with polymer injection in granular media
par: Kazidenov, Daniyar, et autres
Publié: (2024)

On the origin of super-global spin-up trends of X-ray pulsars in HMXB systems
par: Kim, Vitaliy, et autres
Publié: (2025)