MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

arXiv:2505.20715v2 Announce Type: replace-cross Abstract: Video temporal understanding is crucial for multimodal large language models (MLLMs) to reason over events in videos. Despite recent advances in general video understanding, current MLLMs still struggle with fine-grained temporal reasoning. While reinforcement learning (RL) has been explored to address this issue recently, existing RL approaches remain limited in performance on time-sensitive tasks. In this work, we propose MUSEG, a novel RL-based method that enhances temporal understanding by introducing timestamp-aware multi-segment grounding. MUSEG enables MLLMs to align queries with multiple relevant video segments, promoting more comprehensive temporal reasoning. To facilitate effective learning, we design a customized RL training recipe with phased rewards that progressively guides the model toward temporally grounded reasoning. Extensive experiments on temporal grounding and time-sensitive video question answering (QA) tasks demonstrate that MUSEG significantly outperforms existing methods and generalizes well across diverse temporal understanding scenarios. View our project at https://github.com/THUNLP-MT/MUSEG.

Related

• VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding
• See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
• ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling
• BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning
• HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Source: arXiv cs.CL | 2026-04-21