Jul 2026
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters.
Yu-Han Zhu, Changlian Ma, Xiangyun Zeng et al.
· arXiv.org · 2 citations