paper-with-me

홈 › Papers

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

2024-12-26 · CVPR 2025 1 · Ziang Yan, Zhilin Li, Yinan He, Chenting Wang, Kunchang Li, Xinhao Li, Xiangyu Zeng, Zilei Wang, Yali Wang, Yu Qiao, LiMin Wang, Yi Wang

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals though they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. TPO introduces learnable task tokens that establish connections between multiple task-specific heads and the MLLM. By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance. Through multi-task co-training within TPO, we observe synergistic benefits that elevate individual task performance beyond what is achievable through single-task training methodologies. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models. Additionally, MLLM-TPO demonstrates robust zero-shot capabilities across various tasks, performing comparably to state-of-the-art supervised models. The code will be released at https://github.com/OpenGVLab/TPO

📄 PDF Abstract BibTeX arXiv:2412.19326

Code (1)

opengvlab/tpo 공식 구현 pytorch

Similar Papers 제목 키워드 기반

mDPO: Conditional Preference Optimization for Multimodal Large Language Models

2024-06-17 · Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu 외

Direct preference optimization (DPO) has shown to be an effective method for large language model (LLM) alignment. Recent works have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve…

HallucinationLanguage ModelingLanguage ModellingLarge Language Model

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

2024-11-15 · Weiyun Wang, Zhe Chen, Wenhai Wang, Yue Cao 외

Existing open-source multimodal large language models (MLLMs) generally follow a training process involving pre-training and supervised fine-tuning. However, these models suffer from distribution shifts, which limit thei…

Multimodal Reasoning

Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications

2025-05-09 · Da Wu, Zhanliang Wang, Quan Nguyen, Zhuoran Xu 외

The scarcity of high-quality multimodal biomedical data limits the ability to effectively fine-tune pretrained Large Language Models (LLMs) for specialized biomedical tasks. To address this challenge, we introduce MINT (…

Disease PredictionRAGTransfer Learning

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining

2025-05-20 · Chenxi Liu, Tianyi Xiong, Ruibo Chen, Yihan Wu 외

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from seve…

Large Language Model

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

2025-03-23 · CVPR 2025 1 · Zefeng Zhang, Hengzhu Tang, Jiawei Sheng, Zhenyu Zhang 외

Multimodal Large Language Models excel in various tasks, yet often struggle with modality bias, where the model tends to rely heavily on a single modality and overlook critical information in other modalities, which lead…