Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA.However, while these approaches effectively enhance perception abilities, they primarily target holistic content understanding, often lacking explicit supervision for intrinsic temporal coherence and inter-frame correlations.This tendency limits the models' ability to capture intricate dynamics and fine-grained visual causality.To explicitly bridge this gap, we propose a novel posttraining objective: Masked Video Prediction (MVP).By requiring the model to reconstruct a masked continuous segment from a set of challenging distractors, MVP forces the model to attend to the sequential logic and temporal context of events.To support scalable training, we introduce a scalable data synthesis pipeline capable of transforming arbitrary video corpora into MVP training samples, and further employ Group Relative Policy Optimization (GRPO) with a fine-grained reward function to enhance the model's understanding of video context and temporal properties.Comprehensive evaluations demonstrate that MVP enhances video reasoning capabilities by directly reinforcing temporal reasoning and causal understanding.

An air supply strategy based on a centrifugal compressor with turbocharging for Unmanned Aerial Vehicle (UAV) fuel cells is proposed in this paper. The turbocharging is used to recover the energy of the exhausted gas from the fuel cell cathode. The mathematical model of the system is established and analyzed. And the air supply control method is proposed to satisfy the requirement of the fuel cell stack. The validation of the proposed strategy is verified by simulation. The simulation results show that the proposed strategy improves the efficiency of the fuel cell system by 7.8%.