@marcusjmin

Ph.D. Computer Science Student @Penn

marcusm117.github.io/
Joined November 2022
  • Tweets42
  • Following41
  • Followers68
20Media
🥳 Excited to share that our proposal, "Reliable Equivalence Checking for Autoformalization", was selected to receive the AI for Math Fund 2026 by @RenPhil21 with funding support from @xtxmarkets! renaissancephilanthropy.org/…

Reliable Equivalence Checking for Autoformalization — Renaissance Philanthropy – A brighter future...

renaissancephilanthropy.org
1
2
2
11
672
Marcus Min retweeted
Jiayi (Raina) Xin@RainaXinOct 9
1/9 🧵 🚨 New Paper accepted at #NeurIPS2026: PA Score Should rewording change an LLM’s uncertainty? We tackle this through conformal score design. 📄 Paper: arxiv.org/abs/2610.04239 💻 Code: github.com/Raina-Xin/PA_Scor… 📖 Blog: raina-xin.github.io/research…
The title and author list of Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification above its motivation figure. A conceptual multiple-choice example shows how rewording can change an answer prediction set, then illustrates paraphrase-aware scoring.

ALT The title and author list of Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification above its motivation figure. A conceptual multiple-choice example shows how rewording can change an answer prediction set, then illustrates paraphrase-aware scoring.

3
17
1
34
1,597
Learn more about the AI for Math Fund and our fellow grantees here: renaissancephilanthropy.org/…

AI for Math 2026 Winners — Renaissance Philanthropy – A brighter future for all through science,...

renaissancephilanthropy.org
1
31
❤️ Huge congrats and thank you to my advisors and collaborators: Prof. @XujieSi , Prof. Aarti Gupta, Prof. Sharad Malik, @1SHL10, Yu-An Shih, @_Zhaoyu_Li_ , Yeqi Gao
56
Marcus Min retweeted
Ao Qu
@ao_qu18465Sep 1

Your Inference Server is Secretly a Learner: Open-Sourcing Reef for Continual Self-Improving Agents

Article · @ao_qu18465
11
50
15
275
181,011
😊 Excited to share our work accepted to #ICML2026 🇰🇷 as a Spotlight paper Theory-Level Autoformalization: From Isolated Statements to Unified Formal Knowledge Bases Paper: papers.ssrn.com/sol3/papers.… Survey: github.com/marcusm117/Awesom… #AI4Math #Autoformalization 🧵[1/8]
2
5
1
12
1,153
❤️ Many thanks to my amazing co-authors and advisors @1SHL10 , @_Zhaoyu_Li_ , @yi_zixuan, Prof. Sharad Malik, Prof. Aarti Gupta, Prof. @XujieSi, and Prof. @obastani
1
4
62
🙋‍♀️ DM me if you're also interested in Autoformalization and would love to talk more, or if you're also going to ICML 🇰🇷 and would love to hang out! Our poster session is: icml.cc/virtual/2026/poster/… Wednesday, Jul 8, 2026 • 10:30 AM – 12:15 PM, at HALL A #4517 🧵[7/8]
1
1
3
85
We are also planning on an informal AI4Math social! Please join us in the community channel 🚀 icml.cc/chat-directory?chann… 🧵[8/8]
1
2
46
thanks for the photo lol, please stop by our real poster session tmrw! Saturday, Apr 25, 2026 • 10:30 AM – 1:00 PM; Pavilion 4 P4 - #5310 Link: iclr.cc/virtual/2026/poster/… Channel: iclr.cc/chat-directory?chann…
Fazl Barez
@FazlBarezApr 24
Authors @iclr_conf went so deep on DNA they forgot posters don’t have to be genome-sized
7
577
🥳 Excited to share our paper accepted to #ICLR2026 🇧🇷 Divide and Abstract (DNA): Autoformalization via Decomposition and Abstraction Learning Paper: openreview.net/forum?id=Njga… Code: github.com/marcusm117/DNA #AI4Math #Autoformalization #TheoremProving
4
4
1
23
2,276
Feel free to stop by our poster session! Time & Location: Friday, Apr 24, 2026 • 10:30 AM – 1:00 PM; Pavilion 3 P3 - # 1722 【UPDATED】Saturday, Apr 25, 2026 • 10:30 AM – 1:00 PM; Pavilion 4 P4 - #5310 I'll still be there Friday morning anyway! Link: iclr.cc/virtual/2026/poster/… Channel: iclr.cc/chat-directory?chann…
136
@minimario1729 and I are also planning on an informal social for everyone who's interested in AI for Math, join us in the community channel 🙌 iclr.cc/chat-directory?chann…
3
5
1,239
Load more