Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Momentum-Guided Semantic Forecasting (MoFore) for Self-Supervised Video Representation Learning
Qinwu Xu
Self-supervised video representation learning has recently advanced through contrastive learning, masked reconstruction, and predictive representation learning. Reconstruction-base…
cs.CV2026
Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision
Qinwu Xu
Hallucination remains a major challenge in vision-language models (VLMs), particularly when linguistically plausible responses are unsupported by visual evidence. We study whether…
cs.CV2026
Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
Qinwu Xu, Yifan Jiang, Haoyu Ren
Optical character recognition (OCR) and multilingual scene-text understanding remain challenging for multimodal large language models (MLLMs), particularly in real-world images con…