Curriculum vitae
Tiancheng Xing · Yuu
Education
2024 – present
Renmin University of China
B.S. candidate in Artificial Intelligence
Gaoling School of Artificial Intelligence · Beijing, China
Research interests
Multimodal reasoning; efficient multimodal inference; video generation; embodied intelligence. Current interests include KV cache compression, token pruning, sparse attention, adaptive caching, and vision-language models.
Publications
Constraint-Guided Prompting and Semantic-Aware Evaluation for LLM-Based ABSA
ICIC 2026 · Springer LNAI
Selected projects
NeneBot
A character conversational AI grounded in original game scripts. Combines FAISS semantic retrieval, pluggable local and cloud LLM backends, multi-turn memory, SSE streaming, and a Vue 3 visual-novel interface.
Python · FastAPI · FAISS · Vue 3
SLAMForge
A C++20 monocular visual SLAM and dense reconstruction system inspired by ORB-SLAM3. Combines geometric tracking, local bundle adjustment, Sim(3) loop closure, and pose-graph optimization with learned depth and multi-view consistency.
C++20 · Python · Ceres · g2o
Technical skills
- Programming: Python, C++, Java.
- AI & perception: Retrieval-augmented generation, FAISS semantic retrieval, visual SLAM, and dense reconstruction.
- Development: Linux, Git, FastAPI, and Vue 3.