2025 arXiv 2025 TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, and Limin Wang arXiv preprint, 2025 arXiv Code Website ICCV 2025 p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay ICCV, 2025 arXiv Code arXiv 2025 VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking arXiv preprint, 2025 arXiv