Article

Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment

Unifying retrieval-based ranking and generation for query auto-completion under multi-objective alignment.

K. Yuan

• Feb 1, 2026 • 1 min read

SPEEDY: Single-Step Reinforcement Learning for Efficient Analog Circuit Sizing Optimization

Single-step reinforcement learning for analog circuit sizing: >8× faster than DDPG, >2× faster than Bayesian optimization.

Chun-Yen Yao

• Jan 1, 2026 • 1 min read

Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesis

LLM program synthesis plus gradient-free parameter optimization reaches target control performance in over an order of magnitude fewer search steps.

Carlo Bosio

• Oct 1, 2025 • 1 min read