Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous generation model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. This framework enables the flexible selection of feature hierarchies tailored to specific downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model based methods, including 78% top-1 accuracy on ImageNet at a resolution of 64*64. Extensive ablation studies, including out-of-distribution evaluations, further validate the effectiveness of our approach.PRG is available at https://github.com/opendilab/PRG.

Existing local dynamic route planning algorithms, when directly applied to terrain following/terrain avoidance, or dynamic obstacle avoidance for large and medium-sized fixed-wing aircraft, fail to simultaneously meet the requirements of real-time performance, long-distance planning, and the dynamic constraints of large and medium-sized aircraft. To deal with this issue, this paper proposes the Motion Dynamic RRT based Fluid Field - PPO for dynamic TF/TA routing planning. Firstly, the action and state spaces of the proximal policy gradient algorithm are redesigned using disturbance flow fields and artificial potential field algorithms, establishing an aircraft dynamics model, and designing a state transition process based on this model. Additionally, a reward function is designed to encourage strategies for obstacle avoidance, terrain following, terrain avoidance, and safe flight. Experimental results on real DEM data demonstrate that our algorithm can complete long-distance flight tasks through collision-free trajectory planning that complies with dynamic constraints, without the need for prior global planning.

The existing route planning algorithms are directly applied to the remote$\text{TF}/\text{TA}$route planning of large and medium-sized fixed wing aircraft, and cannot simultaneously meet the requirements of efficiency, route consistency, and optimality. To deal with the problem, a motion dynamics RRT*algorithm is proposed. Firstly, the characteristic of ellipses is utilized to effectively reduce the planning space in order to improve search efficiency; Next, in order to reduce the randomness of the RRT algorithm, a motion dynamics model of the aircraft is established and the state transition mode of nodes based on this model is designed; Finally, a cost function was designed to penalize the detour distance, climb altitude, and unsafe flight path. The experimental results on real DEM data show that the proposed algorithm can simultaneously meet the requirements of high efficiency, route consistency, and optimality for long-distance TF/TA route planning of large and medium-sized fixed wing aircraft.