most citedQwen Technical Report

110 citations · 143 across the 21 of their papers we have counts for

collaborators

21 papers

cs.CV20241 cited

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding

Anwen Hu, Haiyang Xu, Liang Zhang +6

Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this…

cs.CL2024

MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model

Chaoya Jiang, Jia Hongrui, Haiyang Xu +6

This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image…

cs.CL2024

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

Chenhan Yuan, Fei Huang, Ru Peng +4

Transformer-based large language models (LLMs) exhibit limitations such as generating unsafe responses, unreliable reasoning, etc. Existing inference intervention approaches attemp…

cs.CL20241 cited

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement

Le Yu, Bowen Yu, Haiyang Yu +2

Merging Large Language Models (LLMs) aims to amalgamate multiple homologous LLMs into one with all the capabilities. Ideally, any LLMs sharing the same backbone should be mergeable…

cs.CV20242 cited

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning

Liang Zhang, Anwen Hu, Haiyang Xu +5

Charts are important for presenting and explaining complex data relationships. Recently, multimodal large language models (MLLMs) have shown remarkable capabilities in various char…

cs.CL2024

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment

Feifan Song, Bowen Yu, Hao Lang +4

Alignment with human preference prevents large language models (LLMs) from generating misleading or toxic content while requiring high-cost human feedback. Assuming resources of hu…