Ye Sun · 孙烨

Beihang University · Computer Science and Technology

Bachelor of Engineering, School of Computer Science and Engineering. GPA: 3.67/4.00; major-course scores include Mathematical Analysis (100), Software Engineering (98), and Deep Learning (94).

Beihang University · Computer Science and Technology

Integrated master’s–PhD program, School of Computer Science and Engineering. Master’s stage: Sep 2021–Jun 2023; PhD stage: Sep 2023–Jun 2027 (expected). GPA: 3.87/4.00; rank: 13/143. Major-course scores include Data Mining (100), Algorithm Design and Analysis (94), Software Engineering (95), and Pattern Recognition (93). Research focuses on knowledge graph reasoning, data mining, and visual analytics; related results have appeared in multiple CCF-A papers.

GeneticPrism · Hierarchical graph layout and scholarly evolution visualization

• Project Description: Addresses the joint representation of within-topic citations and cross-topic influence in multi-topic scholarly evolution by proposing a hierarchical graph representation and IFHL layout.
• Key Contributions: Integrates both relationship types into a unified visualization framework for complex evolutionary structures; Leads the design of GeneticPrism overview and GeneticScroll detail views covering topic overlap, temporal evolution, and cross-topic influence, enabling multi-scale linked exploration.

eXpath · Explainable knowledge graph reasoning framework

• Project Description: Addresses the black-box nature of embedding-model decisions by independently proposing an explanation framework that combines ontological closed-path rules and relational-path evidence.
• Key Contributions: Designs a coordinated rule-mining and path-search mechanism for structured explanation generation, integrating ontological closed-path rules with relational-path evidence into a quantitatively evaluable framework; On standard benchmarks, improves two explanation-quality metrics by approximately 20% and reduces explanation-generation time by 61.4% against the best comparison methods, demonstrating gains in both explanation quality and computational efficiency.

RuleDep · Dependency-aware rule aggregation

• Project Description: Leads the design of sparse second-order corrections and a two-stage training framework to model complementarity and redundancy in rule aggregation.
• Key Contributions: Models dependencies among jointly triggered rules by introducing signed gains in log-failure evidence space to distinguish complementary from redundant evidence; Across seven datasets, raises average MRR from 0.382 to 0.396, achieves 21 best or tied-best metrics among interpretable methods, and improves MRR by approximately 10.7% on dependency-rich subsets.

INSPIRE · Expressive Piano Performance Generation

• Project Description: Builds a note-level structured performance-generation framework that generates expressive performances from discrete symbols through relative-timing modeling and continuous distribution prediction.
• Key Contributions: Designs typed encoding that fuses pitch, duration, loudness, and other note attributes into one Transformer timestep, with score-relative timing deviations for fine-grained expressive control; On ASAP, reduces PP HR by 15.2% against PianistTransformer and lowers inference cost for the specified test task by 95.3%, improving deployability and iteration efficiency.

CueIR · Long-term agent memory

• Project Description: Studies traceable memory organization and retrieval. Memory-graph construction and agent tools are operational, with evaluation on the LoCoMo and MemoryAgentBench datasets.

MaterAgent · Agent Harness for materials R&D

• Project Description: Participates in Agent Harness architecture design for end-to-end materials R&D and builds the core framework supporting agent execution.
• Key Contributions: Designed and developed a Paper Browser MCP tool for automated retrieval and question answering over thousands of materials-science papers. Participates in the research group’s industry-academia collaboration with MaterBrain, supporting deployment of the agent framework and tools in materials R&D workflows.

GeneticFlow V2.0 · Large-scale scholarly literature visualization system

• Project Description: Leads development of a multidimensional visualization system for million-scale scholarly literature, integrating graph-layout computation with visual interaction.
• Key Contributions: The system has served 102,129 users worldwide and supported 507,827 visits, and has received software-copyright registration; Compiled Graphviz C++ sources into browser-side layout components, connecting graph-layout computation with front-end visual interaction and independently maintaining the full stack.

Research-agent-based data classification

• Project Description: Developed LLM entity-extraction tools and a RAG-based data classification pipeline for sensitive-data annotation and refinement.
• Key Contributions: Contributed to the research-agent platform by integrating entity extraction, retrieval-augmented generation, and data classification. The team was named one of Beihang University’s Top Ten Outstanding Teams in Artificial Intelligence.

National Key R&D Program: Rare-earth catalysis knowledge graph and full-process digital R&D platform

• Project Description: Led construction of the database and materials knowledge graph, participating throughout the project from proposal to acceptance and ensuring scheduled delivery reviews.
• Key Contributions: Designed a 10^5-scale multimodal materials database integrating heterogeneous sources to support synthesis-condition recommendation and knowledge discovery. Implemented both functions with a knowledge graph to support intelligent materials R&D.

SenseTime · AI full-stack engineering intern

• Project Description: Contributed deeply to the Miaohua AI-drawing system, designing and implementing back-end APIs for efficient and stable core drawing calls.

SenseTime · Model toolchain intern

• Project Description: Contributed to training-cluster scheduling toolchains and led development of the spring.remote command-line tool for remote cluster login and management, as well as system monitoring tools. Received an Outstanding Intern award.

Technical University of Munich · Research visit

Worked with Prof. Stephen Kobourov on knowledge graph visualization and graph drawing; subsequently collaborated with Maribel Acosta on rule-based reasoning.