Cover Image

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xie, Enze, Chen, Junsong, Zhao, Yuyang, Yu, Jincheng, Zhu, Ligeng, Wu, Chengyue, Lin, Yujun, Zhang, Zhekai, Li, Muyang, Chen, Junyu, Cai, Han, Liu, Bingchen, Zhou, Daquan, Han, Song
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
by: Xie, Enze, et al.
Published: (2024)

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
by: Chen, Junsong, et al.
Published: (2025)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
by: Chen, Junsong, et al.
Published: (2025)

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
by: Zhu, Haoyi, et al.
Published: (2026)

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
by: He, Wenkun, et al.
Published: (2025)

SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer
by: Zhao, Yuyang, et al.
Published: (2026)

DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder
by: Chen, Junyu, et al.
Published: (2025)

DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
by: Chen, Junyu, et al.
Published: (2025)

Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
by: Chen, Junyu, et al.
Published: (2024)

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
by: Zhang, Kewei, et al.
Published: (2026)

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
by: Li, Muyang, et al.
Published: (2024)

Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
by: Wu, Chengyue, et al.
Published: (2025)

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
by: Wu, Yecheng, et al.
Published: (2025)

HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
by: Tang, Haotian, et al.
Published: (2024)

PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
by: Chen, Junsong, et al.
Published: (2023)

Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
by: Wu, Chengyue, et al.
Published: (2026)

LEGO: Spatial Accelerator Generation and Optimization for Tensor Applications
by: Lin, Yujun, et al.
Published: (2025)

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling
by: Li, Yitong, et al.
Published: (2026)

Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
by: Ye, Zhen, et al.
Published: (2025)

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training
by: Xi, Haocheng, et al.
Published: (2024)

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
by: Chen, Junsong, et al.
Published: (2024)

Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
by: Xi, Haocheng, et al.
Published: (2025)

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
by: Xi, Haocheng, et al.
Published: (2026)

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
by: Li, Muyang, et al.
Published: (2024)

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
by: Dang, Meihua, et al.
Published: (2025)

Real Matrices as Linear Combinations of Three Orthogonal Matrices
by: Pang, Zhekai
Published: (2026)

DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
by: Ren, Yinuo, et al.
Published: (2025)

Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance
by: Wei, Yujie, et al.
Published: (2025)

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
by: Wang, Hanrui, et al.
Published: (2020)

On-Device Training Under 256KB Memory
by: Lin, Ji, et al.
Published: (2022)

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
by: Chen, Zhekai, et al.
Published: (2025)

Compositional Visual Planning via Inference-Time Diffusion Scaling
by: Zhang, Yixin, et al.
Published: (2026)

Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
by: Chen, Haoxuan, et al.
Published: (2024)

Inference-Time Compute Scaling For Flow Matching
by: Stecklov, Adam, et al.
Published: (2025)

Accelerating Diffusion Sampling with Optimized Time Steps
by: Xue, Shuchen, et al.
Published: (2024)

Chain of Methodologies: Scaling Test Time Computation without Training
by: Liu, Cong, et al.
Published: (2025)

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
by: Wu, Yecheng, et al.
Published: (2024)

Compute Aligned Training: Optimizing for Test Time Inference
by: Ousherovitch, Adam, et al.
Published: (2026)

ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition
by: Zhao, Muyang, et al.
Published: (2026)

FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
by: Bohde, Montgomery, et al.
Published: (2026)