Scholar
Tingfeng Hui
Google Scholar ID: rOFW8kYAAAAJ
Ph.D of Beijing University of Posts and Telecommunications
LLMs post training
instruction following
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
3,768
H-index
7
i10-index
7
Publications
11
Co-authors
13
list available
Publications
7 items
OpenSkillRisk: Benchmarking Agent Safety When Using Real-World Risky Third-Party Skills
2026
Cited
0
Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions
2026
Cited
0
A Unified Framework for the Evaluation of LLM Agentic Capabilities
2026
Cited
0
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
2026
Cited
0
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
2026
Cited
0
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
2026
Cited
0
DecIF: Improving Instruction-Following through Meta-Decomposition
2025
Cited
0
Co-authors
9 total
Guanting Dong
Remin University of China
Dayuan Fu
MS Student, Beijing University of Posts and Telecommunications
Gang Zhao
AI Engineer, Alibaba Group
Zhuoma Gongque
Beijing University of Posts and Telecommunications
Yanan Wu
Alibaba Group
Zhenyu Zhang
Baidu Inc.
Shuohuan Wang
Baidu
Lulu Zhao
Beijing University of Posts and Telecommunications
