Scholar
Xinghua Qu
Google Scholar ID: 2PxlmU0AAAAJ
Bytedance Seed; NTU
Reinforcement Learning
LLM
Trustworthy AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,063
H-index
16
i10-index
24
Publications
20
Co-authors
10
list available
Contact
Email
xinghua.qu@bytedance.com
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
6 items
FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation
2026
Cited
0
Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents
2025
Cited
0
Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
2025
Cited
0
Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?
2025
Cited
0
Adaptive In-Context Learning with Large Language Models for Bundle Generation
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · 2023
Cited
3
Generative Multiform Bayesian Optimization
IEEE Transactions on Cybernetics · 2022
Cited
8
Resume (English only)
Academic Achievements
Multiple papers accepted at top-tier venues including NeurIPS, ICML, ICLR, AAAI, KDD, SIGIR, IJCAI, CIKM, AAMAS, InterSpeech, and IEEE TPAMI
NeurIPS-2025 paper 'Robust SuperAlignment' selected as Spotlight; ICML-2025 Spotlight (acceptance rate 2.6%); one ICCV-2025 paper highlighted
SIGIR-2024 paper nominated for Best Paper; two papers accepted
IJCAI-2023 work on Audio QR Code officially highlighted
Research featured by Chinese media outlets including YuYinZhiJia, Huoshan Voice, PaperWeekly, DeepTech, and Volcano Engine
Google Scholar citations reached 1000
Received A*STAR Singapore Research Highlight Award
Received ByteDance Seed Outstanding Team Award and Spot Bonus for Breakthrough in New Area (top 2 out of 366)
Received Shanda Group Outstanding Employee Award (top 4 out of 360)
Served as judge for GenAI Augmentation Challenge 2025 (co-hosted by NTU and A*STAR)
Invited to give a talk at AI-TIME in August 2023
Led development of RL-based speech-to-speech LLM released on Doubao in February 2025
Co-authors
10 total
Yew-Soon Ong
President Chair Professor of Computer Science, A*Star AI Chief Scientist, FIEEE
ZHU SUN
Singapore University of Technology and Design
WEI PENGFEI
Nanyang Technological University, Singapore
Jie Zhang
Professor of Computer Science, Nanyang Technological University
Abhishek Gupta
Ramanujan Faculty Fellow, IIT Goa; (formerly Scientist at A*STAR and NTU Singapore)
Lu Lu
Bytedance
Junhao Dong
Nanyang Technological University
Hang Xu
Postdoctoral Fellow, HKU
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up