TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

Yunheng Li, JingCheng, Shaoyong Jia, Hangyi Kuang, Shaohui Jiao, Qibin Hou, Ming-Ming Cheng

Keywords: Temporal Grounding; Multimodal Large Language Model; Reinforcement Fine-Tuning

TL;DR: TempSamp-R1 is a reinforcement fine-tuning framework that integrates off-policy supervision, soft advantage shaping, and hybrid Chain-of-Thought training to enhance the temporal grounding capabilities of MLLMs.

Abstract: This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video temporal grounding tasks. We reveal that existing reinforcement learning methods, such as Group Relative Policy Optimization (GRPO), rely on on-policy sampling for policy updates. However, in tasks with large temporal search spaces, this strategy becomes both inefficient and limited in performance, as it often fails to identify temporally accurate solutions. To address this limitation, TempSamp-R1 leverages ground-truth annotations as off-policy supervision to provide temporally precise guidance, effectively compensating for the sparsity and misalignment in on-policy solutions. To further stabilize training and reduce variance in reward-based updates, TempSamp-R1 provides a non-linear soft advantage computation method that dynamically reshapes the reward feedback via an asymmetric transformation. By employing a hybrid Chain-of-Thought (CoT) training paradigm, TempSamp-R1 optimizes a single unified model to support both CoT and non-CoT inference modes, enabling efficient handling of queries with varying reasoning complexity. Experimental results demonstrate that TempSamp-R1 outperforms GRPO-based baselines, establishing new state-of-the-art performance on benchmark datasets:Charades-STA (R1\@0.7: 52.9\%, +**2.7**\%), ActivityNet Captions (R1\@0.5: 56.0\%, +**5.3**\%), and QVHighlights (mAP: 30.0\%, +**3.0**\%). Moreover, TempSamp-R1 shows robust few-shot generalization capabilities under limited data. Code is available at https://github.com/HVision-NKU/TempSamp-R1.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 3411