3 papers
cs.AI2026
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
Wenwen Si, Insup Lee, Osbert Bastani
Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. On…
cs.LG2026
Conformal Constrained Policy Optimization for Cost-Effective LLM Agents
Wenwen Si, Sooyong Jang, Insup Lee +1
While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API cos…
cs.LG2025
Pattern-Guided Diffusion Models
Vivian Lin, Kuk Jin Jang, Wenwen Si +1
Diffusion models have shown promise in forecasting future data from multivariate time series. However, few existing methods account for recurring structures, or patterns, that appe…