Scholar
Tianshi Zheng
Google Scholar ID: R7jE3X4AAAAJ
HKUST
Natural Language Processing
Logical Inference
Scientific Discovery
Research Agent
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
133
H-index
6
i10-index
4
Publications
20
Co-authors
43
list available
Contact
Email
tzhengad@connect.ust.hk
Twitter
Open ↗
GitHub
Open ↗
Publications
15 items
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
2025
Cited
0
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction
2025
Cited
0
DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
2025
Cited
0
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents
2025
Cited
0
The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
2025
Cited
0
LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game
2025
Cited
0
Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
2025
Cited
0
Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
- Publications:
- TMLR 2025: The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning.
- EMNLP 2025: From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery.
- EMNLP 2025: LogiDynamics: Unraveling the Dynamics of Logical Inference in Large Language Model Reasoning.
- ACL 2025: Enhancing Transformers for Generalizable First-Order Logical Entailment.
- ACL 2025: KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?
- Projects: NewtonBench
- Awards:
- Hong Kong PhD Fellowship 2024
- HKUST RedBird PhD Scholarship 2024
- HKUST Academic Achievement Medal (~top 1% graduate)
- HKUST Dean's Lists (7 semesters)
Research Experience
- Research Internship: NVIDIA AI Technology Center
- PhD Qualification Defense Passed: October 2025
- Committee Members: Junxian and May
Education
- Degree: Ph.D. Candidate
- School: The Hong Kong University of Science and Technology (HKUST)
- Advisor: Prof. Yangqiu Song
- Time: Starting from 2024
- Major: Computer Science
- Bachelor's Degrees: Dual Degree Program (Computer Science and General Business Management) with the highest distinction
Background
- Research Interests: Machine Learning and Natural Language Processing
- Professional Fields: Logical Inference, AI-Driven Autonomous Scientific Discovery
- Brief Introduction: Ph.D. candidate in Computer Science at the Hong Kong University of Science and Technology (HKUST), advised by Prof. Yangqiu Song
Miscellany
- Social Media: Google Scholar, Semantic Scholar, GitHub, Instagram, X (formerly Twitter)
Co-authors
43 total
Yangqiu Song
HKUST
Jiaxin Bai
Hong Kong University of Science and Technology
Weiqi Wang
Final Year PhD @HKUST | Intern @Amazon
Zheye Deng
HKUST
Yauwai Yim
The Hong Kong University of Science and Technology
Chunkit Chan
Ph.D. Student, HKUST | Applied Scientist Intern, Amazon, Palo Alto
Haochen Shi
HKUST
Baixuan Xu
Hong Kong University of Science and Technology
×
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