Africa
A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems Yi Ma
To address this problem, existing methods partition the overall DPDP into fixed-size sub-problems by caching online generated orders and solve each sub-problem, or on this basis to utilize the predicted future orders to optimize each sub-problem further. However, the solution quality and efficiency of these methods are unsatisfactory, especially when the problem scale is very large.
Appendix to: B
Batch evaluation, an important element of modern computing, enables automatic dispatch of independent operations across multiple computational resources (e.g.
ContraGAN: Contrastive Learning for Conditional Image Generation
The discriminator of ContraGAN discriminates the authenticity of given samples and minimizes a contrastive objective to learn the relations between training images.
Counterfactual Temporal Point Processes
In this work, our goal is to fill this gap.
OST: Improving Generalization of DeepFake Detection via One-Shot Test-Time Training
Our key idea is to construct a test-sample-specific auxiliary task to update the model before applying it to the sample. Specifically, we synthesize pseudo-training samples from each test image and create a test-time training objective to update the model.
