Image de couverture de livre

Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiang, Hongbo, Li, Jie, Shen, Yunhang, Dai, Pingyang, Sun, Xing, Cao, Haoyu, Cao, Liujuan
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation
par: Jiang, Hongbo, et autres
Publié: (2026)

FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification
par: Sun, Zhen, et autres
Publié: (2025)

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
par: Li, Lijiang, et autres
Publié: (2026)

DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
par: Tan, Lei, et autres
Publié: (2026)

Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search
par: Tan, Lei, et autres
Publié: (2024)

PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification
par: Tan, Lei, et autres
Publié: (2024)

Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
par: Ye, Kai, et autres
Publié: (2025)

HUWSOD: Holistic Self-training for Unified Weakly Supervised Object Detection
par: Cao, Liujuan, et autres
Publié: (2024)

Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification
par: Xia, Jiaer, et autres
Publié: (2023)

More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV
par: Ye, Kai, et autres
Publié: (2025)

RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentation
par: Ye, Kai, et autres
Publié: (2025)

Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
par: Ye, Kai, et autres
Publié: (2025)

What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
par: Lin, Jianghang, et autres
Publié: (2025)

Pseudo-Label Quality Decoupling and Correction for Semi-Supervised Instance Segmentation
par: Lin, Jianghang, et autres
Publié: (2025)

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models
par: Li, Xudong, et autres
Publié: (2024)

Multi-Modal Prompt Learning on Blind Image Quality Assessment
par: Pan, Wensheng, et autres
Publié: (2024)

Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
par: Dai, Shaohui, et autres
Publié: (2025)

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
par: Tang, Zhenwei, et autres
Publié: (2025)

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
par: Li, Xudong, et autres
Publié: (2023)

WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images
par: Guo, Yansong, et autres
Publié: (2025)

Cantor: Inspiring Multimodal Chain-of-Thought of MLLM
par: Gao, Timin, et autres
Publié: (2024)

GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
par: Qu, Yansong, et autres
Publié: (2024)

UniVST: A Unified Framework for Training-free Localized Video Style Transfer
par: Song, Quanjian, et autres
Publié: (2024)

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization
par: Shen, You, et autres
Publié: (2025)

StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision
par: Chen, Ziyang, et autres
Publié: (2026)

DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion
par: Qu, Yansong, et autres
Publié: (2025)

Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
par: Li, Xin, et autres
Publié: (2024)

UniPTS: A Unified Framework for Proficient Post-Training Sparsity
par: Xie, Jingjing, et autres
Publié: (2024)

Unified Personalized Understanding, Generating and Editing
par: Zhong, Yu, et autres
Publié: (2026)

Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation
par: Yang, Yilong, et autres
Publié: (2026)

Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection
par: Wang, Siwei, et autres
Publié: (2025)

Feature Denoising Diffusion Model for Blind Image Quality Assessment
par: Li, Xudong, et autres
Publié: (2024)

RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-identification
par: Tan, Lei, et autres
Publié: (2024)

Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
par: Cao, Xinzi, et autres
Publié: (2025)

Depth-Guided Semi-Supervised Instance Segmentation
par: Chen, Xin, et autres
Publié: (2024)

Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
par: Li, Xinyang, et autres
Publié: (2024)

UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception
par: Song, Xinyang, et autres
Publié: (2025)

UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings
par: Zhao, Bo, et autres
Publié: (2026)

Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion
par: Li, Xinyang, et autres
Publié: (2024)

FlashWorld: High-quality 3D Scene Generation within Seconds
par: Li, Xinyang, et autres
Publié: (2025)