all AI news
Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization
March 14, 2024, 4:46 a.m. | Renjie Pi, Tianyang Han, Wei Xiong, Jipeng Zhang, Runtao Liu, Rui Pan, Tong Zhang
cs.CV updates on arXiv.org arxiv.org
Abstract: Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual information. We treat this bias as a "preference" for pretraining statistics, which hinders the model's grounding in visual input. To mitigate this issue, we propose Bootstrapped Preference Optimization (BPO), which conducts preference learning with datasets containing negative responses bootstrapped from the model …
abstract arxiv bias cs.cl cs.cv excel however importance information inputs language language model language models large language large language model large language models mllms multimodal multimodal large language model optimization pretraining responses statistics type visual
More from arxiv.org / cs.CV updates on arXiv.org
Multi-View Spectrogram Transformer for Respiratory Sound Classification
2 days, 19 hours ago |
arxiv.org
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
2 days, 19 hours ago |
arxiv.org
OTMatch: Improving Semi-Supervised Learning with Optimal Transport
2 days, 19 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)
@ HelloBetter | Remote
Doctoral Researcher (m/f/div) in Automated Processing of Bioimages
@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Principal Data Architect - Azure & Big Data
@ MGM Resorts International | Home Office - US, NV
GN SONG MT Market Research Data Analyst 11
@ Accenture | Bengaluru, BDC7A