Imagen de Portada

Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Weizhi, Tian, Yu, Yang, Linjie, Wang, Heng, Yan, Xifeng
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
por: Wang, Weizhi, et al.
Publicado: (2024)

Adaptive Layer-skipping in Pre-trained LLMs
por: Luo, Xuan, et al.
Publicado: (2025)

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
por: Li, Mingxin, et al.
Publicado: (2026)

Qwen2.5-VL Technical Report
por: Bai, Shuai, et al.
Publicado: (2025)

DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models
por: Wang, Chengyu, et al.
Publicado: (2025)

Direct Multi-Token Decoding
por: Luo, Xuan, et al.
Publicado: (2025)

Bot or Human? Detecting ChatGPT Imposters with A Single Question
por: Wang, Hong, et al.
Publicado: (2023)

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
por: Wang, Peng, et al.
Publicado: (2024)

Train a Unified Multimodal Data Quality Classifier with Synthetic Data
por: Wang, Weizhi, et al.
Publicado: (2025)

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs
por: Chen, Feilong, et al.
Publicado: (2025)

Open-FinLLMs: Open Multimodal Large Language Models for Financial Applications
por: Huang, Jimin, et al.
Publicado: (2024)

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
por: Wang, Xiaoyang, et al.
Publicado: (2025)

Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training
por: Luo, Gen, et al.
Publicado: (2024)

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
por: HyperAI Team, et al.
Publicado: (2025)

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
por: Du, Yuwen, et al.
Publicado: (2026)

Qwen2.5 Technical Report
por: Qwen, et al.
Publicado: (2024)

Qwen2 Technical Report
por: Yang, An, et al.
Publicado: (2024)

ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value Extraction
por: Zou, Henry Peng, et al.
Publicado: (2024)

Qwen3 Technical Report
por: Yang, An, et al.
Publicado: (2025)

QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization
por: Shen, Weizhou, et al.
Publicado: (2025)

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
por: Yao, Yuan, et al.
Publicado: (2026)

Qwen3-VL Technical Report
por: Bai, Shuai, et al.
Publicado: (2025)

NVLM: Open Frontier-Class Multimodal LLMs
por: Dai, Wenliang, et al.
Publicado: (2024)

AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
por: Lyu, Yuanjie, et al.
Publicado: (2026)

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
por: Yue, Xiang, et al.
Publicado: (2024)

Toxicity of the Commons: Curating Open-Source Pre-Training Data
por: Arnett, Catherine, et al.
Publicado: (2024)

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
por: Khandelwal, Apoorv, et al.
Publicado: (2024)

Qwen2.5-Coder Technical Report
por: Hui, Binyuan, et al.
Publicado: (2024)

Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models
por: Luo, Gen, et al.
Publicado: (2025)

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
por: Wang, Chen, et al.
Publicado: (2025)

Qwen2.5-1M Technical Report
por: Yang, An, et al.
Publicado: (2025)

Qwen3Guard Technical Report
por: Zhao, Haiquan, et al.
Publicado: (2025)

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
por: Xie, Chengxing, et al.
Publicado: (2025)

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
por: Lee, Jaeyoung, et al.
Publicado: (2024)

A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
por: Wang, Wenkang, et al.
Publicado: (2025)

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
por: Zhang, Kaichen, et al.
Publicado: (2025)

MiMo-VL Technical Report
por: Core Team, et al.
Publicado: (2025)

EEG2TEXT: Open Vocabulary EEG-to-Text Decoding with EEG Pre-Training and Multi-View Transformer
por: Liu, Hanwen, et al.
Publicado: (2024)

Are LLMs Aware that Some Questions are not Open-ended?
por: Yang, Dongjie, et al.
Publicado: (2024)

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
por: Tang, Shengkun, et al.
Publicado: (2026)