conftrace_

budget-aware optimization

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

subnetwork search (1) token budget (1) large language model (1) chain of thought (1) stochastic gradient hamiltonian monte carlo (1) reasoning model (1) inference efficiency (1) inference optimization (1) model pruning (1) computational efficiency (1)

Papers

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models EMNLP 2025 Exploration and Estimation for Model Compression ICCV 2021