9 papers
SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization
Jamison Meindl, Yunsheng Tian, Tony Cui +5
Optimizing an experimental system can be extremely challenging when each experiment is expensive, time-consuming, or difficult to perform. Existing optimizers for expensive black-b…
PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning
Yao Lu, Dengdong Fan, Jianzheng Nie +4
We present PCL-Reasoner-V1.5, a 32-billion-parameter large language model (LLM) for mathematical reasoning. The model is built upon Qwen2.5-32B and refined via supervised fine-tuni…
Teaching Language Models to Critique via Reinforcement Learning
Zhihui Xie, Jie Chen, Liyu Chen +3
Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the abil…
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
Jie Cheng, Gang Xiong, Ruixi Qiao +5
Process reward models (PRMs) have proven effective for test-time scaling of Large Language Models (LLMs) on challenging reasoning tasks. However, reward hacking issues with PRMs li…
ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization
Jamison Meindl, Yunsheng Tian, Tony Cui +6
Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its perf…
Neighborhood Sampling Does Not Learn the Same Graph Neural Network
Zehao Niu, Mihai Anitescu, Jie Chen
Neighborhood sampling is an important ingredient in the training of large-scale graph neural networks. It suppresses the exponential growth of the neighborhood size across network…