:: Library Catalog

Omslagsbillede

Saved in:

Bibliografiske detaljer
Main Authors:	Teng, Yao, Wang, Fuyun, Liu, Xian, Chen, Zhekai, Shi, Han, Wang, Yu, Li, Zhenguo, Liu, Weiyang, Zou, Difan, Liu, Xihui
Format:	Preprint
Udgivet:	2025
Fag:	Computer Vision and Pattern Recognition
Online adgang:	https://arxiv.org/abs/2510.08994
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!

Lignende værker

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
af: Teng, Yao, et al.
Udgivet: (2024)

SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation
af: Teng, Yao, et al.
Udgivet: (2025)

Personalized Text-to-Image Generation with Auto-Regressive Models
af: Sun, Kaiyue, et al.
Udgivet: (2025)

Parallelized Autoregressive Visual Generation
af: Wang, Yuqing, et al.
Udgivet: (2024)

SJD-PV: Speculative Jacobi Decoding with Phrase Verification for Autoregressive Image Generation
af: Yu, Zhehao, et al.
Udgivet: (2026)

MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data
af: Chen, Zhekai, et al.
Udgivet: (2026)

SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation
af: Shan, Bingqi, et al.
Udgivet: (2026)

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

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
af: Teng, Yao, et al.
Udgivet: (2024)

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
af: Sun, Kaiyue, et al.
Udgivet: (2024)

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

T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation
af: Huang, Kaiyi, et al.
Udgivet: (2023)

GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
af: Wang, Zhenyu, et al.
Udgivet: (2024)

Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation
af: Wang, Zhenyu, et al.
Udgivet: (2024)

Continuous Speculative Decoding for Autoregressive Image Generation
af: Wang, Zili, et al.
Udgivet: (2024)

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
af: Dong, Haotian, et al.
Udgivet: (2025)

Speculative Decoding for Autoregressive Video Generation
af: Hu, Yuezhou, et al.
Udgivet: (2026)

SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation
af: Kang, Jialiang, et al.
Udgivet: (2026)

Adaptive 1D Video Diffusion Autoencoder
af: Teng, Yao, et al.
Udgivet: (2026)

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
af: So, Junhyuk, et al.
Udgivet: (2025)

Grouped Speculative Decoding for Autoregressive Image Generation
af: So, Junhyuk, et al.
Udgivet: (2025)

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
af: Jang, Doohyuk, et al.
Udgivet: (2024)

HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising
af: Zou, Kai, et al.
Udgivet: (2026)

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
af: Sun, Kaiyue, et al.
Udgivet: (2025)

Streaming Autoregressive Video Generation via Diagonal Distillation
af: Liu, Jinxiu, et al.
Udgivet: (2026)

Editing Massive Concepts in Text-to-Image Diffusion Models
af: Xiong, Tianwei, et al.
Udgivet: (2024)

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

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

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
af: Yue, Xiaoyu, et al.
Udgivet: (2025)

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
af: Liu, Xian, et al.
Udgivet: (2023)

DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation
af: Gu, Jiatao, et al.
Udgivet: (2024)

MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
af: Wei, Yujie, et al.
Udgivet: (2026)

GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
af: Huang, Kaiyi, et al.
Udgivet: (2024)

Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding
af: Lin, Zijian, et al.
Udgivet: (2025)

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
af: Wang, Yuqing, et al.
Udgivet: (2026)

Loong: Generating Minute-level Long Videos with Autoregressive Language Models
af: Wang, Yuqing, et al.
Udgivet: (2024)

GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
af: Xiong, Tianwei, et al.
Udgivet: (2025)

AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
af: Zhang, Haiyu, et al.
Udgivet: (2025)

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
af: Bai, Hanru, et al.
Udgivet: (2025)

HSD: Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding
af: Liao, Wenhui, et al.
Udgivet: (2026)