Cover Image

IAR2: Improving Autoregressive Visual Generation with Semantic-Detail Associated Token Prediction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yi, Ran, Hu, Teng, Su, Zihan, Zhang, Jiangning, Ma, Lizhuang
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

Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
by: Hu, Teng, et al.
Published: (2025)

UltraGen: High-Resolution Video Generation with Hierarchical Attention
by: Hu, Teng, et al.
Published: (2025)

InstanceV: Instance-Level Video Generation
by: Chen, Yuheng, et al.
Published: (2025)

PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence
by: Wang, Ruiyan, et al.
Published: (2025)

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
by: Hu, Teng, et al.
Published: (2024)

Evolution of Video Generative Foundations
by: Hu, Teng, et al.
Published: (2026)

MotionMaster: Training-free Camera Motion Transfer For Video Generation
by: Hu, Teng, et al.
Published: (2024)

Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation
by: Chen, Yuheng, et al.
Published: (2026)

Semantic Frame Interpolation
by: Hong, Yijia, et al.
Published: (2025)

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
by: Sun, Haiyue, et al.
Published: (2025)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2025)

Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration
by: Du, Yuzhen, et al.
Published: (2024)

DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction
by: Liu, Yiheng, et al.
Published: (2025)

Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction
by: Guo, Ziyao, et al.
Published: (2025)

Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
by: Chen, Yuheng, et al.
Published: (2026)

MOS: Modeling Object-Scene Associations in Generalized Category Discovery
by: Peng, Zhengyuan, et al.
Published: (2025)

Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation
by: Fan, Ke, et al.
Published: (2024)

Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses
by: Wang, Yuji, et al.
Published: (2025)

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
by: Wang, Yuji, et al.
Published: (2025)

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
by: Ren, Sucheng, et al.
Published: (2025)

M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising
by: Wang, Chengjie, et al.
Published: (2024)

AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius
by: Wang, Xinzhe, et al.
Published: (2024)

ID-Sculpt: ID-aware 3D Head Generation from Single In-the-wild Portrait Image
by: Hao, Jinkun, et al.
Published: (2024)

Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation
by: Liu, Fengqi, et al.
Published: (2024)

Improving Flexible Image Tokenizers for Autoregressive Image Generation
by: Fu, Zixuan, et al.
Published: (2026)

Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning
by: Wang, Bohan, et al.
Published: (2025)

AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
by: Hu, Teng, et al.
Published: (2023)

ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
by: Zhang, Xu, et al.
Published: (2026)

ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation
by: Zhang, Kaixin, et al.
Published: (2025)

Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization
by: Li, Mengtian, et al.
Published: (2024)

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation
by: Zheng, Anlin, et al.
Published: (2025)

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
by: Lei, Jiabao, et al.
Published: (2025)

SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
by: Hu, Teng, et al.
Published: (2024)

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement
by: Hu, Teng, et al.
Published: (2025)

SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation
by: Chen, Sichen, et al.
Published: (2024)

EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
by: Xiong, Tianwei, et al.
Published: (2026)

Harmony: Harmonizing Audio and Video Generation through Cross-Task Synergy
by: Hu, Teng, et al.
Published: (2025)

FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
by: Fan, Ke, et al.
Published: (2024)

Next Patch Prediction for Autoregressive Visual Generation
by: Pang, Yatian, et al.
Published: (2024)

UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy
by: Xu, Yicheng, et al.
Published: (2026)