activity
20242026
most citedCOIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning

5 citations · 23 across the 14 of their papers we have counts for

collaborators
Showing 2024Show all

11 papers · 1 filter

cs.CL2024

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

Jarvis Guo, Tuney Zheng, Yuelin Bai +7

Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained…

eess.IV2024

Teach Multimodal LLMs to Comprehend Electrocardiographic Images

Ruoqi Liu, Yuelin Bai, Xiang Yue +1

The electrocardiogram (ECG) is an essential non-invasive diagnostic tool for assessing cardiac conditions. Existing automatic interpretation methods suffer from limited generalizab…

cs.CL2024

Can MLLMs Understand the Deep Implication Behind Chinese Images?

Chenhao Zhang, Xi Feng, Yuelin Bai +18

As the capabilities of Multimodal Large Language Models (MLLMs) continue to improve, the need for higher-order capability evaluation of MLLMs is increasing. However, there is a lac…

cs.CL2024

Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models

Jiaming Li, Lei Zhang, Yunshui Li +5

The instruction-following ability of large language models enables humans to interact with AI agents in a natural way. However, when required to generate responses of a specific le…

cs.CL2024★ 4 cited

DeliLaw: A Chinese Legal Counselling System Based on a Large Language Model

Nan Xie, Yuelin Bai, Hengyuan Gao +7

Traditional legal retrieval systems designed to retrieve legal documents, statutes, precedents, and other legal information are unable to give satisfactory answers due to lack of s…

cs.CL2024

II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models

Ziqiang Liu, Feiteng Fang, Xi Feng +23

The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challe…