Chenhao Zhu — accepted AI-conference papers

2025

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Jiahao Qiu, Yifu Lu, Yifan Zeng, Jiacheng Guo, Jiayi Geng, Chenhao Zhu +6

EMNLP 2025

Inference-time alignment enhances the performance of large language models without requiring additional training or fine-tuning but presents challenges due to balancing computational efficiency with high-quality output. Best-of-N (BoN) sampling, as a simple yet powerful approach, generates multiple

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning

Bikun Wang, Zhipeng Wang, Chenhao Zhu, Zhiqiang Zhang, Zhichen Wang, Penghong Lin +2

IROS 2023poster

Learning-based approaches have achieved remarkable performance in the domain of autonomous driving. Leveraging the impressive ability of neural networks and large amounts of human driving data, complex patterns and rules of driving behavior can be encoded as a model to benefit the autonomous driving…

Cited by 5 Source ↗Scholar ↗