TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Jun Zhang; Teng Wang; Yuying Ge; Yixiao Ge; Xinhao Li; Ying Shan; Limin Wang

返回文献探索

Paper · arXiv 2512.14698

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, Limin Wang

27 upvotesDecember 16, 2025arXiv 预印本

AI 摘要

TimeLens establishes a robust baseline for video temporal grounding by improving benchmark quality, addressing noisy training data, and developing efficient algorithmic design principles for multimodal large language models.

multimodal large language modelsvideo temporal groundingTimeLensTimeLens-BenchTimeLens-100Kinterleaved textual encodingthinking-free reinforcement learning with verifiable rewardsRLVRGPT-5Gemini-2.5-Flash

Abstract

This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research.