Image de couverture de livre

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jiuhai, Xu, Zhiyang, Pan, Xichen, Hu, Yushi, Qin, Can, Goldstein, Tom, Huang, Lifu, Zhou, Tianyi, Xie, Saining, Savarese, Silvio, Xue, Le, Xiong, Caiming, Xu, Ran
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

BLIP3o-NEXT: Next Frontier of Native Image Generation
par: Chen, Jiuhai, et autres
Publié: (2025)

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models
par: Xue, Le, et autres
Publié: (2024)

X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning
par: Panagopoulou, Artemis, et autres
Publié: (2023)

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs
par: Ryoo, Michael S., et autres
Publié: (2024)

BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions
par: Awadalla, Anas, et autres
Publié: (2024)

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
par: Awadalla, Anas, et autres
Publié: (2024)

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
par: Wang, Zhenhailong, et autres
Publié: (2025)

UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG
par: Peng, Xiangyu, et autres
Publié: (2025)

Unified Training of Universal Time Series Forecasting Transformers
par: Woo, Gerald, et autres
Publié: (2024)

Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research
par: Lan, Tian, et autres
Publié: (2024)

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks
par: Qi, Jingyuan, et autres
Publié: (2023)

Shared Imagination: LLMs Hallucinate Alike
par: Zhou, Yilun, et autres
Publié: (2024)

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
par: Pang, Bo, et autres
Publié: (2025)

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
par: Liu, Ye, et autres
Publié: (2024)

Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
par: Pang, Bo, et autres
Publié: (2025)

INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
par: Le, Hung, et autres
Publié: (2024)

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
par: Zhang, Jianguo, et autres
Publié: (2023)

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
par: Xue, Le, et autres
Publié: (2023)

Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation
par: Xu, Zhiyang, et autres
Publié: (2025)

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
par: Tong, Shengbang, et autres
Publié: (2024)

Transfer between Modalities with MetaQueries
par: Pan, Xichen, et autres
Publié: (2025)

UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers
par: Min, Dehai, et autres
Publié: (2024)

Text2Data: Low-Resource Data Generation with Textual Control
par: Wang, Shiyu, et autres
Publié: (2024)

Future Optical Flow Prediction Improves Robot Control & Video Generation
par: Ranasinghe, Kanchana, et autres
Publié: (2026)

Hierarchical Point Attention for Indoor 3D Object Detection
par: Shu, Manli, et autres
Publié: (2023)

CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
par: Li, Jierui, et autres
Publié: (2024)

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models
par: Zhang, Jieyu, et autres
Publié: (2024)

GenQA: Generating Millions of Instructions from a Handful of Prompts
par: Chen, Jiuhai, et autres
Publié: (2024)

LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer
par: Shen, Ying, et autres
Publié: (2025)

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
par: Nguyen, Xuan-Phi, et autres
Publié: (2025)

GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
par: Aksu, Taha, et autres
Publié: (2024)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
par: Liao, Baohao, et autres
Publié: (2025)

Entropy-Based Block Pruning for Efficient Large Language Models
par: Yang, Liangwei, et autres
Publié: (2025)

PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback
par: Peng, Yun, et autres
Publié: (2024)

Asynchronous Tool Usage for Real-Time Agents
par: Ginart, Antonio A., et autres
Publié: (2024)

HIVE: Harnessing Human Feedback for Instructional Visual Editing
par: Zhang, Shu, et autres
Publié: (2023)

Multimodal Instruction Tuning with Conditional Mixture of LoRA
par: Shen, Ying, et autres
Publié: (2024)

LZ Penalty: An information-theoretic repetition penalty for autoregressive language models
par: Ginart, Antonio A., et autres
Publié: (2025)

Multi-Objective Linguistic Control of Large Language Models
par: Nguyen, Dang, et autres
Publié: (2024)

AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
par: Qi, Jingyuan, et autres
Publié: (2025)