4 papers
SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models
You Qin, Linqing Wang, Hao Fei +4
The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundame…
MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
Jinlan Fu, Shenzhen Huangfu, Hao Fei +4
The alt-text generation task produces concise, context-relevant descriptions of images, enabling blind and low-vision users to access online images. Despite the capabilities of lar…
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
Haojian Huang, Haodong Chen, Shengqiong Wu +5
Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video halluc…
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
Jinlan Fu, Shenzhen Huangfu, Hao Fei +4
Multimodal Large Language Models (MLLMs) still struggle with hallucinations despite their impressive capabilities. Recent studies have attempted to mitigate this by applying Direct…