Skip to content
View SiyuanChenToDo's full-sized avatar
7 followers · 13 following
  • HUST

Block or report SiyuanChenToDo

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SiyuanChenToDo/README.md

Typing SVG

👋 About Me

Hi! I'm Siyuan Chen (陈思远), an AI undergraduate at Huazhong Agricultural University (HZAU, 211 & Double First-Class University) and an incoming master's student at Huazhong University of Science and Technology (HUST).

🎓 B.Eng. in Artificial Intelligence, HZAU · 2023.9 – 2027.6
🎯 Incoming M.Sc. Student, HUST · 2027.9

My research focuses on:

🧠 LLM-based Multi-Agent Systems
🔬 Automated Scientific Hypothesis Generation (ASHG)
🕸️ Knowledge Graph-enhanced Reasoning & Retrieval
📚 AI for Scientific Discovery (AI4Science)
🎭 Multimodal Understanding & Reasoning

📄 Research Highlights

Work Venue Topic
FIG-MAC NLPCC Oral (CCF-C) Fine-grained inspiration graph + multi-agent scientific hypothesis generation
BnHypo EMNLP Findings (CCF-B) Knowledge-graph-driven mechanistic hypothesis generation for Brassica napus
MemeScope EMNLP Main (CCF-B) Pragmatic reasoning & causal localization in multimodal LLMs

Hubei Provincial Undergraduate Innovation Project — rated Excellent (PI, BnHypo).

🌱 Open Source · 开源贡献

199 commits · 16 pull requests · 4 merged · 4 issues
past 12 months · core contributor to ragflow & Auto-claude-code-research-in-sleep

Repository Contribution
ragflow · ⭐ 92.5k ✅ PR #21114 — Architected a resilient retry-classification layer for the RAG harness: replaced brittle string-prefix checks with multi-signal detection, extending transient-failure coverage and hardening long-chain inference
a2a-rs · ⭐ 91 ✅ PR #119 — Fixed a retry-policy defect in the Rust A2A framework: sub-millisecond exponential backoff rounded down to zero and retried immediately; backoff now keeps nanosecond precision, with a regression test
Auto-claude-code-research-in-sleep · ⭐ 17.7k ✅ PR #471 — Eliminated tool-grant metadata parsing defects in the skill inventory
✅ PR #470 — Shipped Codex invocation-policy auditing and a capability-catalog probe, establishing verifiable capability boundaries for the plugin ecosystem

Also contributed to
deepchem ⭐ 7.1k · dspy ⭐ 38.7k · langgraph ⭐ 43.5k · paper-qa ⭐ 9.4k · deepmd-kit ⭐ 2.1k · pymatgen ⭐ 2.0k · ms-agent ⭐ 4.4k · graphiti ⭐ 32.1k

🐍 Contribution Snake

github-snake

💻 Tech Stack

📊 GitHub Stats

📮 Connect with Me

🎓 Incoming M.Sc. at HUST (2027.9) · 🔭 Open to 2027 Fall PhD opportunities · 🤝 Open to research collaborations & visiting internships

Pinned Loading

  1. Reading-Between-the-Panels-Structured-Multimodal-Reasoning-for-Comic-Narrative-Understanding Reading-Between-the-Panels-Structured-Multimodal-Reasoning-for-Comic-Narrative-Understanding Public

    Python 6

  2. FIG-MAC-Fine-grained-Inspiration-Graph-Empowered-Multi-Agent-Collaboration-for-Automated-Scientific FIG-MAC-Fine-grained-Inspiration-Graph-Empowered-Multi-Agent-Collaboration-for-Automated-Scientific Public

    A knowledge graph enhanced llm for linking prediction

    Python 2

  3. SiyuanChenToDo SiyuanChenToDo Public

    2

  4. ai-memory ai-memory Public

    Forked from akitaonrails/ai-memory

    Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

    Rust

  5. deepseek-harness deepseek-harness Public

    Forked from deepseek-ai/deepseek-harness

    DeepSeek Harness: Everything is a Plugin.

    TypeScript

  6. wanshuiyin/Auto-claude-code-research-in-sleep wanshuiyin/Auto-claude-code-research-in-sleep Public

    ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

    Python 17.8k 1.5k