Chan Young Park

assistant prof @UTAustin
prev: @MSFTResearch @uwnlp @LTIatCMU

love studying human language and humans using computer language

[Chan Young Park @chan_young_park]

Second piece of news, I’m looking to recruit multiple PhD students to work on human-centered AI/alignment/LLM social reasoning this cycle @UTiSchool
While I’m sadly missing #COLM2026 I'll be heading to #EMNLP2026 🇭🇺
Whether you'll be there or not, reach out if you're interested!

[Chan Young Park @chan_young_park]

I’ve been dormant on Twitter for a while but i’m back to share some news. First off, @UTiSchool is hiring! This is an open-rank open-area search. Feel free to reach out if you’d like to know more.

[Information, UT Austin @UTiSchool]

🗣️Information at @UTAustin is growing!

We’re hiring tenured & tenure-track faculty at the Assistant, Associate & Full Professor levels for Fall 2027.

Join the new School of Computing and help shape the future of computing. 🤘

Learn more: https://t.co/mq4578Yw63

[Chan Young Park @chan_young_park]

@melaniesclar Wait who leaked my proprietary chunky model?

[Elias Stengel-Eskin @EliasEskin]

I'll be at #COLM2026 starting tomorrow!

Come find the following posters today, or find me at the conference to chat about all things multi-agent (esp communication/emergent language), confidence/calibration, faithfulness, beliefs, and/or life (and several faculty openings) at UT Austin!

https://t.co/ohw6I100uZ

https://t.co/5AVSMbXYU5

[Chan Young Park @chan_young_park]

We don’t want malicious user instructions to override the constitutional system rules (e.g., “Be civil and safe”)

Releasing our latest work, which ensures LLMs follow the instruction hierarchy through reasoning, thereby enhancing AI safety

[Zishuo Zheng @ZishuoZheng]

✨We are excited to introduce Reasoning for Instruction Hierarchy!

We train LLMs to explicitly reason over instruction hierarchies (IH) with RLVR, producing flexible and robust behavior!

Thanks my coauthers @vidhisha_b , @chan_young_park , @faeze_brh , and my advisor @shocheen

[Hanane Nour Moussa @HananeNMoussa]

📢 As AI becomes increasingly explored for research idea generation, how can we rigorously evaluate the ideas it generates before committing time and resources to them?
We introduce ScholarEval, a literature grounded framework for research idea evaluation across disciplines 👇!

[Chan Young Park @chan_young_park]

My team at MSR is also hiring both principal and senior researchers!

[Jennifer Neville @ProfJenNeville]

For those AI researchers who have recently (re)entered the job market, just a reminder that our team— AI Interaction and Learning at Microsoft Research Redmond—is currently hiring multiple ML/AI researchers.
https://t.co/mhPqFXpX9S
https://t.co/17IV9oeXNE

[Chan Young Park @chan_young_park]

@MaartenSap Congrats✨

[Chan Young Park @chan_young_park]

Looking forward to working with passionate researchers on these important problems💪

If you know someone who'd be a great fit, please share or RT!!

[Chan Young Park @chan_young_park]

📣Hiring! Two opportunities

1. Research internship@MSR AI Interaction and Learning (Current PhD students)

2. Multiple positions in my lab @UTiSchool on LLM Personalization/Human-AI Alignment (Prospective PhD students)

Details in thread below👇

[Chan Young Park @chan_young_park]

For more info on my research interests, please check my website: https://t.co/iJFvarD0AH
(there's a form you can fill out to show your interest and connect with me!)

Application deadline: December 1st https://t.co/pmSu8NaSSf

[Taylor Sorensen @ma_tay_]

🤖➡️📉 Post-training made LLMs better at chat and reasoning—but worse at distributional alignment, diversity, and sometimes even steering(!)

We measure this with our new resource (Spectrum Suite) and introduce Spectrum Tuning (method) to bring them back into our models! 🌈

1/🧵

[Chan Young Park @chan_young_park]

If you’re at COLM, don’t miss Stella’s *spotlight* talk on Thursday!

Really bummed I can’t make it this year. I was hoping to chat with folks interested in UT Austin iSchool (i’m hiring multiple PhD students!!) and internship opportunities at MSR. More on this very soon

[Stella Li @ COLM @StellaLisy]

I will be at #COLM2025 next week, super excited to explore Montreal!🍁

I've been thinking about personalization, question-asking, multi-turn, RL etc. DM if you want to chat!

Catch me at:
📍Poster for ALFA: Tue 1:30pm
💡Spotlight talk for PrefPalette: Thur 10:15am (poster 11am)

[Stella Li @ COLM @StellaLisy]

WHY do you prefer something over another?

Reward models treat preference as a black-box😶‍🌫️but human brains🧠decompose decisions into hidden attributes

We built the first system to mirror how people really make decisions in our #COLM2025 paper🎨PrefPalette✨

Why it matters👉🏻🧵

[Chan Young Park @chan_young_park]

@hyunw_kim @kaist_ai @nvidia Love your lab name! Congratulations Hyunwoo!

[Chan Young Park @chan_young_park]

@riehsooyoung @UTiSchool Thank you for the warm welcome Soo Young. Your support throughout the entire process was instrumental. Can't wait to join @UTiSchool

[Chan Young Park @chan_young_park]

@niloofar_mire @CMU_EPP @LTIatCMU @AIatMeta @kamalikac Congratulations Niloofar!!!