Botao Yu

@BotaoYu24

PhD student @ OSU NLP Group @osunlp.

Columbus, OH, USA

btyu.github.io

Joined September 2022

264 Following

198 Followers

Replies Reposts Media

Botao Yu
@BotaoYu24
Oct 15
Next summer internship opportunity at MSR, highly recommend!
Yuanqi Du
@YuanqiD
Oct 14
We are hiring research interns in the broad area of machine learning and statistics @MSRNE @MSFTResearch! Come work with us! Personally I have very broad interests and I’d love to learn about your favorite problems!
Botao Yu
@BotaoYu24
Jun 8
AI Scientist Summer Workshop @ MSR New England, on Aug 4. Come join the fun! 🚀
wengong jin
@WengongJin
Jun 8
Thrilled to announce the AI Scientist Summer Workshop @AdaFang_ @YuanqiD 📅 Aug 4, 2026 📍Microsoft Research New England, Cambridge MA Join speakers from Anthropic, Google, Microsoft, AI2, Harvard, and MIT to discuss the future of AI Scientists! Register: ai-scientist-workshop.github.io
Botao Yu
@BotaoYu24
Apr 1
🚀Excited to share 𝗦𝗔𝗚𝗔! Most AI for science asks: “How do we optimize better?” We asked a different question: “How do we know we're optimizing for the right thing?” Scientists don't arrive at perfect objectives — they discover them. SAGA automates exactly that: the messy,
Yuanqi Du
@YuanqiD
Apr 1
❓How can we build AI agents that do what scientists actually do? Is scientific discovery merely a search problem? 🚀 Meet SAGA: Scientific Autonomous Goal-evolving Agents. Five discovery tasks across chemistry, biology & materials science, with wet-lab validation.
2
Botao Yu
@BotaoYu24
Feb 17
As CUAs become more powerful, “Son of Anton”-style unintended behaviors are no longer fiction. In AutoElicit, we show how even benign instructions can lead to harmful behaviors. Check this out ⬇️
Huan Sun
@hhsun1
Feb 17
The 'Son of Anton' unintended behaviors from Silicon Valley? They're no longer satire—they're happening in real computer-use agents, even Claude Opus 4.6. Concrete example (OSWorld-style task): Instruction: “I want to convert the Impress file into a document editable in Writer.
Botao Yu
@BotaoYu24
Aug 19, 2025
Introducing LARC🐦, our agentic AI for safer and more controllable retrosynthesis! Simply specify your target and state your constraint (e.g., avoiding toxic chemicals) in natural language, and it can plan a route that respects your rules, with a human expert-level success rate!
Frazier Baker
@FrazierBaker
Aug 19, 2025
In synthetic chemistry, constrained retrosynthesis planning is NOT just about finding a valid synthetic route–the route must also satisfy practical constraints🥽. However, current AI retrosynthesis methods focus on unconstrained planning, ignoring key constraints in
1

Botao Yu

Botao Yu’s posts