Adaptive Sampling Networks

Fri, 01 May 2026 00:00:00 +0000

Co-authored with Navneel Singhal.

Adaptive Sampling Networks explore a simple question: can the decoding strategy of a language model be learned, instead of fixed by hand-tuned heuristics like temperature, top-k, or nucleus sampling?

Problem

Most LLM deployments treat decoding as a hyperparameter choice. The same sampling rule is applied across prompts, uncertainty regimes, and output distributions.

That is useful, but rigid. A sampler should be able to respond to the shape of the probability distribution it receives.

Ai-Systems on Saurav Panigrahi

Adaptive Sampling Networks

Problem