Haoyu Lu

8

Papers

315

Total Citations

Papers (8)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

Efficient Motion-Aware Video MLLM

COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

Compressed Video Contrastive Learning

BMU-MoCo: Bidirectional Momentum Update for Continual Video-Language Modeling

LGDN: Language-Guided Denoising Network for Video-Language Modeling