Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Xiaoliang Fu

dblp:233/1869 · DBLP profile ↗
← Back
3ranked-venue papers
2as first author
2since 2021 · last 2026
0000-0003-2550-3600ORCID · reported

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2 · 2 first-author · 2 since 2021Systems, architecture and hardware · 1

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
2 papers
Reinforcement learning · 50% Language models and text generation · 33% Optimization for machine learning · 17%

Topics — the 6 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Natural language and speech › Language models and text generation
chain-of-thought reasoning
1.012026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning · ACL (1) 2026
Machine learning › Optimization for machine learning
gradient clipping
1.012026
From łog π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight · ACL (1) 2026
Natural language and speech › Language models and text generation
large language model training
1.012026
From łog π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight · ACL (1) 2026
Machine learning › Reinforcement learning
policy optimization
1.012026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning · ACL (1) 2026
Machine learning › Reinforcement learning › reinforcement learning for NLP
reinforcement fine-tuning
1.012026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning · ACL (1) 2026
Machine learning › Reinforcement learning › policy optimization
sample-efficient policy optimization
1.012026
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning · ACL (1) 2026

Methods — techniques the papers use, named apart from their topics

signal reliability · 1.0probability mass · 1.0gradient utilization · 1.0bilateral decoupled decay · 1.0
YearPublicationVenuePosition
2026 From łog π to π: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight
abstract
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao, Binbin Zheng, Lu Pan, Ke Zeng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao 0001
ACL (1)1
2026 MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
abstract
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Zekai Shao 0001, Cong Qin
ACL (1)1
2018 Development of FPGA based Hardware-in-the-loop Simulator for RF Cavity Resonator
abstract
This paper presents implementation of a Field Programmable Gate Array (FPGA) emulator for the Low Level Radio Frequency (LLRF) Normal conducting cavity at TRIUMF. Testing waveforms such as phase and amplitude in the cavity on the real hardware can be both difficult and dangerous. To allow testing of the real LLRF system in real time and also to obtain shorter processing time we need to have an effective hardware in the loop simulator of the cavity. Radio frequency(RF) cavity is equivalent to an electrical RLC circuit which acts like a second order filter model, therefore it is possible to emulate the cavity with an analog filter. But when it comes to digital field, the finite word length effect has to be considered and processed carefully. The discrete model of the cavity designed as an IIR bandpass Filter. The SIMULINK and MATLAB model of the cavity and their implementation are presented. An Altera DE4 development board was selected as the emulator of the cavity. And the result of digital designing of the cavity model on FPGA is presented.
Mahsa Keikha, Xiaoliang Fu, Mehrdad Moallem, Ken Fong
IECON2