SY Shi-Yu Tian

๐Ÿคต๐Ÿป About Me

I am a Ph.D. student in Computer Science at Nanjing University and a member of the LAMDA Group in the School of Artificial Intelligence, advised by Professor Yu-Feng Li. Previously, I worked closely with Professor Lei Feng at Chongqing University. My research focuses on enabling large language models (LLMs) to reason robustly and solve complex tasks, particularly in practical domains such as mathematics, law, and spatial reasoning. Recently, I have been exploring frontier approaches, including agentic reinforcement learning (Agentic RL), on-policy distillation, and self-evolution, to enhance the autonomous learning, continual improvement, and reliable reasoning capabilities of LLMs.

๐ŸŽ“ Education

2024 - Present
Ph.D. in Computer Science
School of Artificial Intelligence, Nanjing University.
2020 - 2024
B.Sc. in Computer Science
College of Computer Science, Chongqing University.

๐Ÿ’ผ Experience

2026.06 - Now
TGT Program Intern, JD Retail.

๐ŸŽ‰ News

  • [2026/08] We released NeSy-Spatial, a self-evolving neuro-symbolic framework for spatial reasoning.
  • [2026/06] NeSy-Route is accepted by ECCV 2026.
  • [2026/06] I started my first talent-program internship in the TGT (Tech Genius Team) Program at JD Retail.
  • [2026/05] On the Learnability of Test-Time Adaptation is accepted by ICML 2026.
  • [2026/04] TabularMath is accepted by ACL 2026.
  • [2026/04] We released the LAST paper, a tool-augmented framework for spatial reasoning.
  • [2025/08] VCSearch is accepted by EMNLP 2025 (Oral).
  • [2025/06] We released the PMC benchmark of VCSearch.
  • [2025/05] We released TabularMath, a reasoning-intensive table QA benchmark.
  • [2024/12] One paper is accepted by Frontiers of Computer Science.
  • [2024/02] CroSel is accepted by CVPR 2024 (Oral).

๐Ÿ“ Publications

๐Ÿค Academic Service

Journal Reviewer Neural Networks.
Conference Reviewer IJCAI 2025; ICLR 2025, 2026; ICML 2026; CVPR 2026; ECCV 2026; ACM MM 2026; AAAI 2027; KDD 2027.
Teaching Assistant
2026 Spring: Matrix Computation, with Prof. Yu-Feng Li.
2026 Spring: Advanced Machine Learning, with Prof. Yu-Feng Li.