4 papers
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
Yuan Qing, Chengzhi Mao, Boqing Gong
Large Vision-Language Models (LVLMs) rely extensively on Visual Instruction Tuning (VIT) to elicit their multimodal reasoning capabilities. However, we find a discrepancy: VIT ofte…
Moiré Video Authentication: A Physical Signature Against AI Video Generation
Yuan Qing, Kunyu Zheng, Lingxiao Li +2
Recent advances in video generation have made AI-synthesized content increasingly difficult to distinguish from real footage. We propose a physics-based authentication signature th…
The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition
Yuwen Tan, Yuan Qing, Boqing Gong
This paper reveals that many open-source large language models (LLMs) lack hierarchical knowledge about our visual world, unaware of even well-established biology taxonomies. This…
Multi-modal Instance Refinement for Cross-domain Action Recognition
Yuan Qing, Naixing Wu, Shaohua Wan +1
Unsupervised cross-domain action recognition aims at adapting the model trained on an existing labeled source domain to a new unlabeled target domain. Most existing methods solve t…