43 citations · 55 across the 3 of their papers we have counts for
6 papers
Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent
Zixiao Wang, Xingbo Du, Duzhen Zhang +1
Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regulator, the proxy reward mode…
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Hongjin Qian, Chaofan Li, Kun Luo +11
We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at test time. This ability rest…
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen, Yuyang Hu, Hongjin Qian +8
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model backbone with a harness for planning, execution, memory, and ve…
RedParrot: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching
Tong Wang, Yongqin Xu, Jianfeng Zhang +6
Recently, at Xiaohongshu, the rapid expansion of e-commerce and advertising demands real-time business analytics with high accuracy and low latency. To meet this demand, systems ty…
PRICE: A Pretrained Model for Cross-Database Cardinality Estimation
Tianjing Zeng, Junwei Lan, Jiahong Ma +7
Cardinality estimation (CardEst) is essential for optimizing query execution plans. Recent ML-based CardEst methods achieve high accuracy but face deployment challenges due to high…
ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads (Extended)
Pengfei Li, Wenqing Wei, Rong Zhu +3
For efficient query processing, DBMS query optimizers have for decades relied on delicate cardinality estimation methods. In this work, we propose an Attention-based LEarned Cardin…