2025
TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
NeurIPS 2025poster
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 Optimizatio…