Yein Park

CS Ph.D. @ Cambridge | Gates Cambridge Scholar-elect 2026 | M.S., B.S. @ Korea University

[Yein Park @parkyein522]

📢 Our model pre-release is now open!
🩺 Try it: https://t.co/ReoYVaEDVb

It supports EMR-based diagnosis & prescription suggestions with search over guidelines, reimbursement criteria, and drug references.

Use your own input or simply “Try Samples.”

Feedback welcome!

[Yein Park @parkyein522]

I’ll present our team’s recent work at #ICML2026 #SD4H!

📄 Distilling Expert-level Planning for Real-world Diabetes Prescribing

We train medical LLMs to follow expert prescribing workflows using EMR context, insurance-aware search, and RL.

🗓️ Jul 11, 9:50–10:50
📍Hall D2, COEX

[Yein Park @parkyein522]

📄 Paper: https://t.co/2cItgB73st

[Yein Park @parkyein522]

I’ll present our team’s recent work at #ICML2026 #SD4H!

📄 Distilling Expert-level Planning for Real-world Diabetes Prescribing

We train medical LLMs to follow expert prescribing workflows using EMR context, insurance-aware search, and RL.

🗓️ Jul 11, 9:50–10:50
📍Hall D2, COEX

[Richard Zhuang @RichardZ412]

How can we train small agentic models that are highly capable of terminal use and coding?

Announcing OpenThoughts-Agent + OpenThinkerAgent-32B, the strongest Qwen-3 based open-data agentic model: 44.8% avg across 7 agentic benchmarks! (1/n)

[Yein Park @parkyein522]

Honored to join the @Gates_Cambridge community as a Gates Cambridge Scholar.

I’m deeply grateful for this opportunity, and I look forward to learning from and growing with such an inspiring cohort at @Cambridge_Uni .

Thank you to everyone who supported me along the way.

[Gates Cambridge @Gates_Cambridge]

The new 2026 class of Gates Cambridge Scholars has been announced, comprising 68 Scholars from 25 different countries. Read the full story here - https://t.co/wZr7Fi8K6W

@Cambridge_Uni
@GatesAlumni
@gatesfoundation

[Yein Park @parkyein522]

📄 Paper: https://t.co/FTSVVDKlXG
🤗 HF Papers: https://t.co/2ge86BKoXV
💻 Code: https://t.co/xjbP4HAHrS

[Yein Park @parkyein522]

🚨 #ICLR2026 🚨
Introducing ASGuard — a mechanistic safety alignment

LLMs can be jailbroken by simple tweaks → showing a gap in alignment.
So, we
• Identify vulnerable attention heads
• Apply activation scaling and preventative FT
• Decrease ASR without hurting utility

[Yein Park @parkyein522]

I’m delighted to share that I’ve accepted an offer of admission to the Ph.D. program in Computer Science at the @Cambridge_Uni, starting this fall.

I hope to continue this journey with humility and to work toward research that can contribute meaningfully to society!

[Negin Raoof @NeginRaoof_]

How can we make a better TerminalBench agent?
Today, we are announcing the OpenThoughts-Agent project.
OpenThoughts-Agent v1 is the first TerminalBench agent trained on fully open curated SFT and RL environments.
OpenThinker-Agent-v1 is the strongest model of its size on TerminalBench, and sets a new bar on our newly released OpenThoughts-TB-Dev benchmark. (1/n)

[Yein Park @parkyein522]

@nikhil07prakash @jeongminby98858 Appreciate your insightful work; we'll cite and discuss your paper in our revision!

[Yein Park @parkyein522]

📢Attention📢
Excited to share our new paper: Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training
With circuit, we uncover how post-training sparks the emergence of functionally specialized attention heads, supporting reasoning ability! 💡
#AI #RL

[Yein Park @parkyein522]

@nikhil07prakash @jeongminby98858 EAP-IG based circuit construction might make a difference, too. Meanwhile, the recent study (https://t.co/PeLyCtc71t) suggests a similar trend, showing SFT/Distillation introduce novel reasoning patterns in mathematical and coding benchmarks.

[Yein Park @parkyein522]

@nikhil07prakash @jeongminby98858 Thank you so much for your interest! We think both task domain and experimental setup could explain difference. We fine-tuned the model with solely mathematical reasoning datasets, and tracked internal computation triggered by <think> token, in contrast to entity-tracking task.

[Yein Park @parkyein522]

@jeongminby98858 🧵Our paper: https://t.co/o5ib7haZfv
https://t.co/NmYlT75Ytz

[Yein Park @parkyein522]

⏳Just 1 week to go until #ACL2025 in #Vienna!
Our paper, "Temporal Head" will be featured in the poster session:

🗓️ Tuesday, July 29 | 10:30 AM – 12:00 PM
📍 Hall 4/5

Feel free to reach out us! We'd love to hear your thoughts and share ours!✨

[Yein Park @parkyein522]

🔥We are on fire!🔥
Hot on the heels of many interests at #ICLR2025, our work, "Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information," has been accepted to ACL 2025 Main Conference!

Looking forward to see in Austria! 🇦🇹
#ACL2025

[Yein Park @parkyein522]

Our project homepage: https://t.co/igWvS05icS

ICLR Session: https://t.co/Iz41cPh8L7

[Yein Park @parkyein522]

🎉 Countdown for #ICLR2025 in Singapore!
Our paper, "ChroKnowledge", has been showcased in the poster session!

🗓️ Friday, April 25 | 11:00 AM – 1:30 PM
📍 Hall 3 + Hall 2B #305

Come find us to talk about our new evaluation framework for LLMs handling time-variant knowledge!

[Yein Park @parkyein522]

📚Paper: https://t.co/RNDBn6F6xP

[Yein Park @parkyein522]

🚀 Ready to Take the Next Step? 🚀

Here's the question: Does large language models (LLMs) specifically handle temporally facts within their internal structures? 🤔

We introduce Temporal Heads—attention heads within LLMs managing and processing time-sensitive information.