Demo Data from VLDB 2026 / reviewers in the wild / expert
Bolun Liu
dblp:296/0428
· DBLP profile ↗
4ranked-venue papers
2as first author
4since 2021 · last 2025
0000-0001-8508-9371ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Applied, interdisciplinary, general and emerging computing · 3 · 2 first-author · 3 since 2021Artificial intelligence and machine learning · 1 · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Reinforcement learning · 67% Language models and text generation · 33% | |
| Interdisciplinary, comprehensive, and emerging computing
1 paper |
Medical and health informatics · 100% |
Topics — the 3 heaviest of 4, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Machine learning › Reinforcement learning › reinforcement learning from human feedback
process reward model |
0.9 | 1 | 2025 | Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise · EMNLP 2025 |
Machine learning › Reinforcement learning › reward learning
reward modeling |
0.9 | 1 | 2025 | Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise · EMNLP 2025 |
Medical and health informatics › electronic health records
clinical documentation |
0.3 | 1 | 2025 | Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise · EMNLP 2025 |
Methods — techniques the papers use, named apart from their topics
process supervision · 1.7domain expert guidance · 1.7
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain ExpertiseabstractHanyin Wang, Chufan Gao, Qiping Xu, Bolun Liu, Guleid Hussein, Hariprasad Reddy Korsapati, Mohamad El Labban, Kingsley Iheasirim, Mohamed Hassan, Gokhan Anil, Brian Bartlett, Jimeng Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025. Hanyin Wang, Chufan Gao, Qiping Xu, Bolun Liu, Guleid Hussein, Hariprasad Korsapati, Mohamad El Labban, Kingsley Iheasirim, Gokhan Anil, Brian Bartlett, Jimeng Sun 0001 |
EMNLP | 4 |
| 2022 | A Method to Solve FDA Radar Ambiguous Distance Problem based on Subarray FDA-MIMO RadarabstractIn this paper, a new method for solving target range ambiguity in radar signal processing based on subarray FDA-MIMO is proposed. At the same time, The optimal frequency shift selection of the transmit array is also analyzed. Compared to the FDA-MIMO radar with linear frequency shift, the new method is able to exclude the effect of ambiguous range peaks in FDA detecion and has a better result in supressing noise. The new method also extend the maximum unambiguous range, so it is more advantageous in the detection of multiple targets. Bolun Liu, Zhulin Zong, Libing Huang |
IGARSS | 1 |
| 2022 | An AMF Detection Method Based on FDA-MIMO RadarabstractIn this paper, an AMF detection method based on frequency diverse array(FDA) is proposed. Since the beampattren of FDA has range resolution capability, comparing to phase radar AMF detection, FDA-based radar AMF detection method can give both angular information and range information of the target. The new method also has better detection capability than GLRT method and CFAR method in case of high SNR. Frequency diverse array, AMF detection, FDA-MIMO. Bolun Liu, Zhulin Zong |
IGARSS | 1 |
| 2021 | An FPGA Hardware Implementation for Omega-K SAR Imaging AlgorithmabstractThis paper introduces the hardware design and implementation of Omega-K imaging algorithm. Based on the analysis of Omega-K algorithm theoretical derivation, we plan to use pipeline structure and soft IP multiplexed method to speed up the imaging speed and achieve the purpose of real-time imaging. By evaluating the hardware resources and system running time needed in the design, we can realize the real-time imaging. So, we select the appropriate hardware platform to implement. Finally, we verify the design scheme by using the actual radar echo data of 13 seconds. The experimental results show that the peak signal- to- noise ratio of the imaging results by the hardware platform is 39.23dB, and the imaging time of the hardware platform is 9.38 seconds. This shows that the imaging quality meets the requirements and the purpose of real-time imaging is achieved. Zhulin Zong, Bolun Liu, Shiwei Yuan |
IGARSS | 3 |