Cover Image

A Simple Baseline for Unifying Understanding, Generation, and Editing via Vanilla Next-token Prediction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Jie, Ma, Hanghang, Wang, Jia, Guan, Yayong, Zeng, Yanbing, Gao, Lishuai, Wu, Junqiang, Hu, Jie, Wang, Leye
Format:	Preprint
Published:	2026
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

Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models
by: Zeng, Yanbing, et al.
Published: (2026)

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

LongCat-Image Technical Report
by: Meituan LongCat Team, et al.
Published: (2025)

Image Editing with Diffusion Models: A Survey
by: Wang, Jia, et al.
Published: (2025)

Auditing Data Provenance in Real-world Text-to-Image Diffusion Models for Privacy and Copyright Protection
by: Zhu, Jie, et al.
Published: (2025)

A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
by: Zhu, Jie, et al.
Published: (2024)

A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
by: Zhu, Jie, et al.
Published: (2025)

Interpretable Next-token Prediction via the Generalized Induction Head
by: Kim, Eunji, et al.
Published: (2024)

Physics in Next-token Prediction
by: An, Hongjun, et al.
Published: (2024)

OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
by: Wu, Size, et al.
Published: (2025)

FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection
by: Li, Jie, et al.
Published: (2026)

SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
by: Wu, Wei, et al.
Published: (2024)

A Unified Editing Method for Co-Speech Gesture Generation via Diffusion Inversion
by: Zhao, Zeyu, et al.
Published: (2024)

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
by: Zhang, Huichao, et al.
Published: (2026)

Unified Personalized Understanding, Generating and Editing
by: Zhong, Yu, et al.
Published: (2026)

Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
by: Tran, Hoan My, et al.
Published: (2026)

Revisiting Day-ahead Electricity Price: Simple Model Save Millions
by: Wang, Linian, et al.
Published: (2024)

Resolved properties of classical bulge and pseudo-bulge galaxies
by: Hu, Jia, et al.
Published: (2023)

UniVideo: Unified Understanding, Generation, and Editing for Videos
by: Wei, Cong, et al.
Published: (2025)

Non-asymptotic Convergence of Training Transformers for Next-token Prediction
by: Huang, Ruiquan, et al.
Published: (2024)

LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing
by: Zhang, Zhenghao, et al.
Published: (2025)

Easy over Hard: A Simple Baseline for Test Failures Causes Prediction
by: Gao, Zhipeng, et al.
Published: (2024)

Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
by: Zhu, Jie, et al.
Published: (2024)

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

Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
by: Zhu, Jie, et al.
Published: (2023)

A Unified Model for Spatio-Temporal Prediction Queries with Arbitrary Modifiable Areal Units
by: Chen, Liyue, et al.
Published: (2024)

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
by: Chen, Boyuan, et al.
Published: (2024)

Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark
by: Chen, Liyue, et al.
Published: (2021)

A Simple Baseline for Streaming Video Understanding
by: Shen, Yujiao, et al.
Published: (2026)

Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation
by: Han, Yue, et al.
Published: (2023)

MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
by: Zhu, Jie, et al.
Published: (2024)

NEP: Autoregressive Image Editing via Next Editing Token Prediction
by: Wu, Huimin, et al.
Published: (2025)

LinVT: Empower Your Image-level Large Language Model to Understand Videos
by: Gao, Lishuai, et al.
Published: (2024)

DreamOmni: Unified Image Generation and Editing
by: Xia, Bin, et al.
Published: (2024)

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
by: Yan, Canxiang, et al.
Published: (2025)

Vanilla Group Equivariant Vision Transformer: Simple and Effective
by: Fu, Jiahong, et al.
Published: (2026)

Next-token pretraining implies in-context learning
by: Riechers, Paul M., et al.
Published: (2025)

Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning
by: Wang, Linian, et al.
Published: (2025)

SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations
by: Zhao, Yize, et al.
Published: (2024)