Image de couverture de livre

Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gu, Tiancheng, Yang, Kaicheng, Feng, Ziyong, Wang, Xingjun, Zhang, Yanzhao, Long, Dingkun, Chen, Yingda, Cai, Weidong, Deng, Jiankang
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

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
par: Gu, Tiancheng, et autres
Publié: (2025)

RWKV-CLIP: A Robust Vision-Language Representation Learner
par: Gu, Tiancheng, et autres
Publié: (2024)

RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
par: Gu, Tiancheng, et autres
Publié: (2025)

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination
par: Yang, Kaicheng, et autres
Publié: (2024)

ORID: Organ-Regional Information Driven Framework for Radiology Report Generation
par: Gu, Tiancheng, et autres
Publié: (2024)

Multi-label Cluster Discrimination for Visual Representation Learning
par: An, Xiang, et autres
Publié: (2024)

LaPA: Latent Prompt Assist Model For Medical Visual Question Answering
par: Gu, Tiancheng, et autres
Publié: (2024)

Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum
par: Guo, Zhuoning, et autres
Publié: (2025)

High-Fidelity Facial Albedo Estimation via Texture Quantization
par: Ran, Zimin, et autres
Publié: (2024)

PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training
par: Xie, Yin, et autres
Publié: (2025)

UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
par: Wang, Jun, et autres
Publié: (2026)

Region-based Cluster Discrimination for Visual Representation Learning
par: Xie, Yin, et autres
Publié: (2025)

ViCToR: Improving Visual Comprehension via Token Reconstruction for Pretraining LMMs
par: Xie, Yin, et autres
Publié: (2024)

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset
par: Shen, Hengyu, et autres
Publié: (2026)

IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models
par: Cui, Siying, et autres
Publié: (2024)

1st Place Solution to the 1st SkatingVerse Challenge
par: Sun, Tao, et autres
Publié: (2024)

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
par: Zheng, Tianlu, et autres
Publié: (2025)

Decoupled Global-Local Alignment for Improving Compositional Understanding
par: Hu, Xiaoxing, et autres
Publié: (2025)

Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
par: Chen, Zhichao, et autres
Publié: (2026)

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
par: Tang, Feilong, et autres
Publié: (2026)

Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
par: Dai, Ziqi, et autres
Publié: (2025)

ForCenNet: Foreground-Centric Network for Document Image Rectification
par: Cai, Peng, et autres
Publié: (2025)

EliGen: Entity-Level Controlled Image Generation with Regional Attention
par: Zhang, Hong, et autres
Publié: (2025)

Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
par: Kong, Fanheng, et autres
Publié: (2025)

Optimizing Multimodal LLMs for Egocentric Video Understanding: A Solution for the HD-EPIC VQA Challenge
par: Yang, Sicheng, et autres
Publié: (2026)

Multimodal LLMs under Pairwise Modalities
par: Li, Yan, et autres
Publié: (2026)

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
par: Hu, Xiaoxing, et autres
Publié: (2025)

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
par: An, Xiang, et autres
Publié: (2025)

Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization
par: Yang, Tiancheng, et autres
Publié: (2025)

Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities
par: Li, Zhiyuan, et autres
Publié: (2024)

Nexus-Gen: Unified Image Understanding, Generation, and Editing via Prefilled Autoregression in Shared Embedding Space
par: Zhang, Hong, et autres
Publié: (2025)

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
par: Jain, Jitesh, et autres
Publié: (2024)

RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
par: Wang, Ruofan, et autres
Publié: (2025)

Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models
par: Chen, Jiaxing, et autres
Publié: (2024)

MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs
par: Lin, Sheng-Chieh, et autres
Publié: (2024)

ObjEmbed: Towards Universal Multimodal Object Embeddings
par: Fu, Shenghao, et autres
Publié: (2026)

Breaking the Discretization Barrier of Continuous Physics Simulation Learning
par: Xu, Fan, et autres
Publié: (2025)

Learning Contrastive Multimodal Fusion with Improved Modality Dropout for Disease Detection and Prediction
par: Gu, Yi, et autres
Publié: (2025)

PLUME: Latent Reasoning Based Universal Multimodal Embedding
par: He, Chenwei, et autres
Publié: (2026)

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs
par: Li, Qi, et autres
Publié: (2026)