Imagen de Portada

Unison: A Fully Automatic, Task-Universal, and Low-Cost Framework for Unified Understanding and Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Shihao, Chen, Yitong, Jiang, Zeyinzi, Zi, Bojia, Hao, Shaozhe, Liu, Yu, Mao, Chaojie, Wong, Kwan-Yee K.
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

Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation
por: Zhao, Shihao, et al.
Publicado: (2024)

BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
por: Hao, Shaozhe, et al.
Publicado: (2024)

CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery
por: Hao, Shaozhe, et al.
Publicado: (2023)

ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction
por: Hao, Shaozhe, et al.
Publicado: (2024)

ArtiFade: Learning to Generate High-quality Subject from Blemished Images
por: Yang, Shuya, et al.
Publicado: (2024)

Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists
por: Zi, Bojia, et al.
Publicado: (2025)

ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editing
por: Pan, Yulin, et al.
Publicado: (2025)

StyleBooth: Image Style Editing with Multimodal Instruction
por: Han, Zhen, et al.
Publicado: (2024)

VACE: All-in-One Video Creation and Editing
por: Jiang, Zeyinzi, et al.
Publicado: (2025)

Locate, Assign, Refine: Taming Customized Promptable Image Inpainting
por: Pan, Yulin, et al.
Publicado: (2024)

Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation
por: Cheng, Shihao, et al.
Publicado: (2026)

Adversarial Prompt Distillation for Vision-Language Models
por: Luo, Lin, et al.
Publicado: (2024)

ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling
por: Mao, Chaojie, et al.
Publicado: (2025)

MiniMax-Remover: Taming Bad Noise Helps Video Object Removal
por: Zi, Bojia, et al.
Publicado: (2025)

ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
por: Han, Zhen, et al.
Publicado: (2024)

Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark
por: Tu, Rong-Cheng, et al.
Publicado: (2024)

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization
por: Li, Jie, et al.
Publicado: (2026)

CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
por: Zi, Bojia, et al.
Publicado: (2024)

Ultra-low Power AMOLED Displays for Smart Wearable Applications: Theory and Practice
por: Lyu, Bojia
Publicado: (2025)

InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping
por: Xu, Zhenhua, et al.
Publicado: (2023)

PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs
por: Duan, Hao, et al.
Publicado: (2025)

FOCUS: A Four‐In‐One Consolidated Unison Strain Sensor with Enhanced Sensitivity
por: Zimeng Wang, et al.
Publicado: (2026)

P‐9.17: Demura Algorithm Based on Generative Adversarial Network
por: Xi Li, et al.
Publicado: (2024)

CusConcept: Customized Visual Concept Decomposition with Diffusion Models
por: Xu, Zhi, et al.
Publicado: (2024)

A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation
por: Wang, Ruihe, et al.
Publicado: (2024)

Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
por: Zhao, Guanqun, et al.
Publicado: (2026)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
por: Zi, Bojia, et al.
Publicado: (2021)

A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation
por: Li, Jiulin, et al.
Publicado: (2025)

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
por: Lyu, Yuanhuiyi, et al.
Publicado: (2025)

VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
por: Xie, Chaohao, et al.
Publicado: (2025)

Sensor Observability Analysis for Maximizing Task-Space Observability of Articulated Robots
por: Wong, Christopher Yee, et al.
Publicado: (2023)

BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos
por: Lin, Jiahao, et al.
Publicado: (2025)

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations
por: Han, Jiaming, et al.
Publicado: (2025)

AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation
por: Cao, Yukang, et al.
Publicado: (2024)

FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding
por: Huang, Siyuan, et al.
Publicado: (2026)

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
por: Zeng, Siqi, et al.
Publicado: (2025)

GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction
por: Zhang, Jian, et al.
Publicado: (2025)

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
por: Gong, Yuan, et al.
Publicado: (2025)

TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation
por: Tang, Datao, et al.
Publicado: (2025)

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