Imagen de Portada

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Xiaoxiao, Zhao, Feng, Ling, Pengyang, Qiu, Haibo, Wei, Zhixiang, Yu, Hu, Huang, Jie, Zeng, Zhixiong, Ma, Lin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation
por: Ma, Xiaoxiao, et al.
Publicado: (2025)

Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation
por: Zou, Zhen, et al.
Publicado: (2025)

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

Group Critical-token Policy Optimization for Autoregressive Image Generation
por: Zhang, Guohui, et al.
Publicado: (2025)

Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective
por: Chen, Kun, et al.
Publicado: (2026)

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
por: Wei, Zhixiang, et al.
Publicado: (2023)

Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement
por: Gu, Yuxuan, et al.
Publicado: (2024)

Masked Pre-training Enables Universal Zero-shot Denoiser
por: Ma, Xiaoxiao, et al.
Publicado: (2024)

DeepSketcher: Internalizing Visual Manipulation for Multimodal Reasoning
por: Zhang, Chi, et al.
Publicado: (2025)

Frequency Autoregressive Image Generation with Continuous Tokens
por: Yu, Hu, et al.
Publicado: (2025)

From Sequential to Spatial: Reordering Autoregression for Efficient Visual Generation
por: Wang, Siyang, et al.
Publicado: (2025)

UITron-Speech: Towards Automated GUI Agents Based on Speech Instructions
por: Han, Wenkang, et al.
Publicado: (2025)

VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning
por: Zhao, Xuanle, et al.
Publicado: (2025)

Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
por: Chen, Kun, et al.
Publicado: (2025)

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
por: Shen, Tingrui, et al.
Publicado: (2025)

Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation
por: Ye, Zilyu, et al.
Publicado: (2024)

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
por: Li, Xingyao, et al.
Publicado: (2026)

Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning
por: Yang, Siqi, et al.
Publicado: (2025)

Autoregressive Image Generation with Vision Full-view Prompt
por: Cai, Miaomiao, et al.
Publicado: (2025)

MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
por: Zhang, Guohui, et al.
Publicado: (2025)

Learning to Reflect and Correct: Towards Better Decoding Trajectories for Large-Scale Generative Recommendation
por: Xing, Haibo, et al.
Publicado: (2026)

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
por: Chen, Zhi-Kai, et al.
Publicado: (2025)

Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
por: Chen, Lei, et al.
Publicado: (2025)

Know Your Step: Faster and Better Alignment for Flow Matching Models via Step-aware Advantages
por: Yue, Zhixiong, et al.
Publicado: (2026)

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models
por: Ma, Xu, et al.
Publicado: (2025)

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
por: Huang, Zhihao, et al.
Publicado: (2025)

Faster and Better 3D Splatting via Group Training
por: Wang, Chengbo, et al.
Publicado: (2024)

Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner
por: Chen, Lei, et al.
Publicado: (2025)

Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
por: Zhang, Chi, et al.
Publicado: (2025)

LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
por: Chen, Junhao, et al.
Publicado: (2026)

OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
por: Yang, Longrong, et al.
Publicado: (2025)

From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
por: Song, Han, et al.
Publicado: (2026)

Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
por: Zhong, Yufeng, et al.
Publicado: (2025)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
por: Ma, Xiaoxiao, et al.
Publicado: (2026)

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
por: Xu, Haobo, et al.
Publicado: (2026)

FREE: Faster and Better Data-Free Meta-Learning
por: Wei, Yongxian, et al.
Publicado: (2024)

Entropy Regularization and Faster Decremental Matching in General Graphs
por: Chen, Jiale, et al.
Publicado: (2023)

Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective
por: Xie, Shenghao, et al.
Publicado: (2024)

Faster Projected GAN: Towards Faster Few-Shot Image Generation
por: Wang, Chuang, et al.
Publicado: (2024)

MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
por: Wang, Jia, et al.
Publicado: (2025)