Similar Items: On Computing Total Variation Distance Between Mixtures of Product Distributions
- Fine-Grained Graph Generation through Latent Mixture Scheduling
- Synthetic Computers at Scale for Long-Horizon Productivity Simulation
- UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
- DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
- Variational Inference for Lévy Process-Driven SDEs via Neural Tilting
- Computing Equilibrium beyond Unilateral Deviation