Cover Image

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Junke, Tian, Zhi, Wang, Xun, Zhang, Xinyu, Huang, Weilin, Wu, Zuxuan, Jiang, Yu-Gang
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

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
by: Wang, Junke, et al.
Published: (2024)

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
by: Zheng, Peng, et al.
Published: (2025)

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

OmniVid: A Generative Framework for Universal Video Understanding
by: Wang, Junke, et al.
Published: (2024)

Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning
by: You, Zuyao, et al.
Published: (2025)

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
by: Meng, Lingchen, et al.
Published: (2024)

GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets
by: He, Mingqian, et al.
Published: (2025)

Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities
by: Zhou, Ziwei, et al.
Published: (2025)

OmniTracker: Unifying Object Tracking by Tracking-with-Detection
by: Wang, Junke, et al.
Published: (2023)

SpectralAR: Spectral Autoregressive Visual Generation
by: Huang, Yuanhui, et al.
Published: (2025)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
by: Wang, Sudong, et al.
Published: (2026)

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
by: Shi, Jiapeng, et al.
Published: (2026)

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
by: Zou, Zhen, et al.
Published: (2026)

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
by: Pang, Ziqi, et al.
Published: (2024)

Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy
by: Gao, Shujian, et al.
Published: (2026)

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
by: Qi, Jingyuan, et al.
Published: (2025)

Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection
by: Chen, Yitong, et al.
Published: (2024)

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation
by: Sun, Shikun, et al.
Published: (2026)

TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
by: Ma, Yukuo, et al.
Published: (2025)

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction
by: Ji, Longbin, et al.
Published: (2026)

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL
by: Pan, Kaihang, et al.
Published: (2025)

Learning Accurate Segmentation Purely from Self-Supervision
by: You, Zuyao, et al.
Published: (2026)

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation
by: Liao, Chao, et al.
Published: (2025)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
by: Xie, Yiweng, et al.
Published: (2026)

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
by: Li, Youpeng, et al.
Published: (2026)

Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning
by: You, Zuyao, et al.
Published: (2025)

Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead
by: Kang, Feiyang, et al.
Published: (2025)

EditAR: Unified Conditional Generation with Autoregressive Models
by: Mu, Jiteng, et al.
Published: (2025)

DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
by: Hu, Hanxu, et al.
Published: (2026)

AR-MOT: Autoregressive Multi-object Tracking
by: Jia, Lianjie, et al.
Published: (2026)

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
by: Tian, Jiahao, et al.
Published: (2026)

DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
by: Wu, Fangtai, et al.
Published: (2025)

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
by: Zhang, Kaichen, et al.
Published: (2025)

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
by: Han, Feng, et al.
Published: (2025)

DDT: Decoupled Diffusion Transformer
by: Wang, Shuai, et al.
Published: (2025)

Mirai: Autoregressive Visual Generation Needs Foresight
by: Yu, Yonghao, et al.
Published: (2026)

FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
by: Zheng, Peng, et al.
Published: (2025)

Paint by Odor: An Exploration of Odor Visualization through Large Language Model and Generative AI
by: Yu, Gang, et al.
Published: (2026)

Pushing Frontiers for Proteoglycans
by: Marissa L. Maciej‐Hulme
Published: (2026)

Bin Packing and Covering: Pushing the Frontier on the Maximin Share Fairness
by: Li, Bo, et al.
Published: (2025)