Image de couverture de livre

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jin, Xin, Li, Siyuan, Jian, Siyong, Yu, Kai, Wang, Huan
Format:	Preprint
Publié:	2025
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

SSD: Spatial-Semantic Head Decoupling for Efficient Autoregressive Image Generation
par: Jian, Siyong, et autres
Publié: (2025)

RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-Evolution
par: Jian, Siyong, et autres
Publié: (2026)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
par: Zhang, Luyuan, et autres
Publié: (2026)

Mix-Modality Person Re-Identification: A New and Practical Paradigm
par: Liu, Wei, et autres
Publié: (2024)

MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
par: Li, Siyuan, et autres
Publié: (2025)

VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
par: Jia, Zi-Yi, et autres
Publié: (2026)

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
par: Li, Xinyao, et autres
Publié: (2024)

Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
par: Chen, Xin, et autres
Publié: (2023)

Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models
par: Wang, Wei, et autres
Publié: (2024)

MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding
par: Wang, Jiaze, et autres
Publié: (2024)

AV-Unified: A Unified Framework for Audio-visual Scene Understanding
par: Li, Guangyao, et autres
Publié: (2026)

UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
par: Li, Teng, et autres
Publié: (2025)

EarlyTom: Early Token Compression Completes Fast Video Understanding
par: Wang, Hesong, et autres
Publié: (2026)

OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
par: Zhang, Yiwei, et autres
Publié: (2026)

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
par: Wu, Size, et autres
Publié: (2025)

Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration
par: Liao, Chih-Ting, et autres
Publié: (2025)

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
par: Zhang, Liang, et autres
Publié: (2024)

TerraGen: A Unified Multi-Task Layout Generation Framework for Remote Sensing Data Augmentation
par: Tang, Datao, et autres
Publié: (2025)

Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining
par: Li, Yuxuan, et autres
Publié: (2026)

Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation
par: Huang, Yuqing, et autres
Publié: (2026)

LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
par: Dai, Yifan, et autres
Publié: (2026)

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation
par: Deng, Tianchen, et autres
Publié: (2025)

Dataset Augmentation by Mixing Visual Concepts
par: Rahat, Abdullah Al, et autres
Publié: (2024)

VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding
par: Chen, Jian, et autres
Publié: (2025)

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
par: Song, Wei, et autres
Publié: (2025)

The Shape of Sight: A Homological Framework for Unifying Visual Perception
par: Li, Xin
Publié: (2018)

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding
par: Bao, Xiaoyi, et autres
Publié: (2025)

UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation
par: Zhang, Chi, et autres
Publié: (2025)

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models
par: Li, Yuanbo, et autres
Publié: (2026)

Towards More Unified In-context Visual Understanding
par: Sheng, Dianmo, et autres
Publié: (2023)

UniMoCo: Unified Modality Completion for Robust Multi-Modal Embeddings
par: Qin, Jiajun, et autres
Publié: (2025)

USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images
par: Wang, Jiamu, et autres
Publié: (2025)

Training-Free Model Merging for Multi-target Domain Adaptation
par: Li, Wenyi, et autres
Publié: (2024)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2025)

REF-VLM: Triplet-Based Referring Paradigm for Unified Visual Decoding
par: Tai, Yan, et autres
Publié: (2025)

Unified Open-World Segmentation with Multi-Modal Prompts
par: Liu, Yang, et autres
Publié: (2025)

OracleSage: Towards Unified Visual-Linguistic Understanding of Oracle Bone Scripts through Cross-Modal Knowledge Fusion
par: Jiang, Hanqi, et autres
Publié: (2024)

Unified Reward Model for Multimodal Understanding and Generation
par: Wang, Yibin, et autres
Publié: (2025)

Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding
par: Chen, Boyu, et autres
Publié: (2025)

UniTok: A Unified Tokenizer for Visual Generation and Understanding
par: Ma, Chuofan, et autres
Publié: (2025)