Copertina

DiSA: Diffusion Step Annealing in Autoregressive Image Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhao, Qinyu, Singh, Jaskirat, Xu, Ming, Asthana, Akshay, Gould, Stephen, Zheng, Liang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can We Predict Performance of Large Models across Vision-Language Tasks?
di: Zhao, Qinyu, et al.
Pubblicazione: (2024)

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?
di: Zhao, Qinyu, et al.
Pubblicazione: (2024)

ARINAR: Bi-Level Autoregressive Feature-by-Feature Generative Models
di: Zhao, Qinyu, et al.
Pubblicazione: (2025)

Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
di: Zhao, Qinyu, et al.
Pubblicazione: (2024)

Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
di: Snelgar, Francis, et al.
Pubblicazione: (2026)

Gromov Wasserstein Optimal Transport for Semantic Correspondences
di: Snelgar, Francis, et al.
Pubblicazione: (2026)

LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?
di: Wang, Yuchi, et al.
Pubblicazione: (2024)

When Diffusion Breaks Constraints: Sequential Autoregressive Generation with RL and MCTS
di: Zhao, Zirui, et al.
Pubblicazione: (2025)

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
di: Gu, Zeqi, et al.
Pubblicazione: (2025)

SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
di: Zhao, Qinyu, et al.
Pubblicazione: (2025)

Vec2Face+ for Face Dataset Generation
di: Wu, Haiyu, et al.
Pubblicazione: (2025)

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
di: Chen, Liang, et al.
Pubblicazione: (2024)

Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models
di: Xu, Yexing, et al.
Pubblicazione: (2026)

Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors
di: Wu, Haiyu, et al.
Pubblicazione: (2024)

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
di: Zhao, Haozhe, et al.
Pubblicazione: (2025)

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
di: Kou, Siqi, et al.
Pubblicazione: (2024)

WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification
di: Jiang, Yiwen, et al.
Pubblicazione: (2025)

Analyzing Diffusion and Autoregressive Vision Language Models in Multimodal Embedding Space
di: Wang, Zihang, et al.
Pubblicazione: (2026)

DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer
di: Lyu, Hengye, et al.
Pubblicazione: (2026)

Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model
di: Huang, Haoyang, et al.
Pubblicazione: (2025)

IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
di: Yang, Zhaoyuan, et al.
Pubblicazione: (2023)

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
di: Leng, Xingjian, et al.
Pubblicazione: (2025)

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
di: Zhao, Min, et al.
Pubblicazione: (2026)

CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
di: Yu, Hao, et al.
Pubblicazione: (2025)

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
di: Chern, Ethan, et al.
Pubblicazione: (2024)

Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA
di: Li, Zhuowan, et al.
Pubblicazione: (2024)

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
di: Ma, Yiyang, et al.
Pubblicazione: (2024)

ZigMa: A DiT-style Zigzag Mamba Diffusion Model
di: Hu, Vincent Tao, et al.
Pubblicazione: (2024)

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
di: NextStep Team, et al.
Pubblicazione: (2025)

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression
di: Zhen, Dingcheng, et al.
Pubblicazione: (2025)

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
di: Zhang, Yu, et al.
Pubblicazione: (2025)

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
di: Chen, Liang, et al.
Pubblicazione: (2025)

Universal Approximation of Visual Autoregressive Transformers
di: Chen, Yifang, et al.
Pubblicazione: (2025)

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
di: Zhou, Mingyuan, et al.
Pubblicazione: (2024)

EasyGen: Easing Multimodal Generation with BiDiffuser and LLMs
di: Zhao, Xiangyu, et al.
Pubblicazione: (2023)

Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models
di: Huang, Jia-Hong, et al.
Pubblicazione: (2024)

Autoregressive Models in Vision: A Survey
di: Xiong, Jing, et al.
Pubblicazione: (2024)

Autoregressive Pre-Training on Pixels and Texts
di: Chai, Yekun, et al.
Pubblicazione: (2024)

DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models
di: Li, Yizhuo, et al.
Pubblicazione: (2024)