amortization

This paper proposes using graph hypernetworks to explicitly represent relationships in PDEs for amortizing physics-informed neural networks, showing improved accuracy in solving coupled systems.

This paper proposes amortizing the high token cost of reasoning-mode LLMs by distilling domain-specific skills from existing trajectories into system prompts, recovering most of the reasoning gap on agentic benchmarks while emitting far fewer tokens.

This paper decomposes the predictive KL divergence between Gaussian process and latent neural process posteriors into three terms, providing upper bounds that characterize approximation errors and connecting representation dimension to kernel smoothness.