Hyewon Jeong
@HyewonMandyJ
Followers
447
Following
751
Media
9
Statuses
87
Ph.D. Student, @MIT_CSAIL EECS., Medical Doctor (M.D., M.S.) studying Machine Learning for Healthcare. Previously @Apple 🍎 @kaistcsdept @yonsei_u @AITRICS
Cambridge, MA
Joined December 2019
Poster presentation alert 🚨.I will present the paper “Event-Based Contrastive Learning” in Poster Session B (Poster #156, 3:35-4:55PM) @mlforhc ! .Link to camera-ready version of paper:
🌟 Excited to share our latest work "Event-Based Contrastive Learning for Medical Time Series" now available on Arxiv! 📄 A big shout out to my amazing co-authors: Nassim, @MattBMcDermott @AparnaBee @payal_chandak @MarzyehGhassemi, and Collin! 🌟.
2
6
32
We're seeking work on all the different types of health time-series research, from biosignal foundation models to clinical causal decision making. We are excited to see your research!.
0
0
2
Only 10 days left to submit to the Time-series 4 Health Workshop at #NeurIPS2025 ! .Call for Papers:
1
5
15
RT @jaeh0ng_yoon: 🚀 I'm recruiting PhD students to join my lab ( at NTU Singapore (@NTUsg), starting Spring 2026.….
jaehong31.github.io
Postdoctoral Research Associate, UNC Chapel Hill
0
47
0
Lastly, Huge thanks to our advisory committee: Jim Rehg @RehgJim, Dimitris Spathis @spdimitris, Satya Shukla, Sujay Nagaraj @sujnagaraj, Tom Hartvigsen @tom_hartvigsen, and Sana Tonekaboni @sana_tonekaboni ! .🧵 (6/6).
0
0
1
Big thanks to our co-organizers: Max Xu @maxxu05 Girish Narayanswamy @ILoveBuffs, Wanting Mao @wanting98671 .🧵 (5/6).
1
0
0
🔥 Keynote lineup 🔥.Shwetak Patel (UW / Google).Emily Fox (Stanford / Inistro).Anna Goldenberg (UToronto / SickKids).Jaya Narain (Apple).Edward Choi (KAIST).Mathew McDermott (Columbia) @MattBMcDermott.Xi Zhang (Oura).🧵 (4/6).
1
0
0
Call for Papers!.Submit your work by August 22, 2025 (AOE) ⏳.We're also awarding a $500 Best Paper Prize 🏆.🧵 (3/6).
1
0
0
What makes TS4H special?.✅ Cross-domain discussion.✅ Diverse perspectives: Google, Oura, Apple, and 5 top institutions.✅ Community-driven posters and talks.We’re building bridges between ML & real-world healthcare through physiologically-aware methods. 🧵 (2/6).
1
0
1
🩺📈 The "Learning from Time-series for Health (TS4H)" workshop is BACK at NeurIPS 2025 🥳!. This workshop unites researchers across health time-series domains (from wearables to clinical systems) to tackle shared challenges. Details: 🧵 (1/6).
1
7
17
Excited to present our work Relcon at #ICLR2025 today at 3:00 - 5:30 p.m. SGT on Saturday, April 26. Feel free to come by and say hi to me at Poster 17! .
openreview.net
We present RelCon, a novel self-supervised Relative Contrastive learning approach for training a motion foundation model from wearable accelerometry sensors. First, a learnable distance measure is...
1
0
4
This was led by a wonderful team of Ph.D. students, and was really a joyful collaboration with a large team of ML researchers and physicians. Excited to share our stellar insights to public! (4/4).
0
0
0
4) Demonstrate and Propose clinical tasks to discover and evaluate medical hallucination, and share annotations on hallucinations from physicians. 5) Review on detection, evaluation, and mitigation of medical hallucination (3/4).
1
0
0
2) Share the global physician survey result that captures firsthand concerns about AI-driven medical inaccuracies . 3) Benchmark leading LLMs on evaluation of medical hallucination (2/4).
1
0
0
📜 Check out our latest piece of research work on hallucination in the medical context! . In this work, we:.1) Propose the definition, taxonomy, and critical examples of "Medical Hallucination" (1/4).
🤷♂️ When and why do Foundation Models hallucinate or confabulate in healthcare, and what's the real-world impact on medical practice? 💔 Our work tackles this urgent question, defining "Medical Hallucinations" AND revealing experimental results. Paper:
1
0
9
RT @maxxu05: My paper RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data, from my @Apple internship, ha….
arxiv.org
We present RelCon, a novel self-supervised Relative Contrastive learning approach for training a motion foundation model from wearable accelerometry sensors. First, a learnable distance measure is...
0
10
0
RT @chanwoopark20: Excited to announce that our work, "MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making," has been s….
0
3
0
I'll be organizing @SymposiumML4H at Pinnacle Hotel Harbourfront on 12/15-12/16. Drop by if interested! (5/5).
0
0
2
Monday 12/16 ML4H Demos track poster: Pinnacle Hotel Harbourfront Ballroom III.MEDS Decentralized, Extensible Validation (MEDS-DEV) Benchmark: Establishing Reproducibility and Comparability in ML for Health, led by @MattBMcDermott (4/5).
1
0
4