Huan Sun (@hhsun1) / X

Huan Sun

969 posts

Huan Sun

@hhsun1

Prof. @OhioState, endowed CoE Innovation Scholar, advancing the capability and safety/security of LLM-based agents, understanding transformers' limitations

The Ohio State University

u.osu.edu/ihudas/people/

Joined March 2012

Pinned
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.
00:56
mitsuri
@0xmitsurii
Feb 7
How was the show Silicon Valley so ahead of its time?
24K
Huan Sun
@hhsun1
May 27, 2024
Thanks @_akhaliq for sharing our work. Very proud to introduce my star student @BoshiWang2's new work @osunlp: Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization Can transformers reason? Are transformers fundamentally limited in
150K
Huan Sun
@hhsun1
May 21, 2022
Official now! Excited to be promoted to Associate Professor with tenure @OhioStateCSE @OSUengineering Sincerest thanks to my advisors, mentors, collaborators, and colleagues who wrote support letters for me! A warm thank you to students in @osunlp and to my family @ysu_nlp. ☺️
Huan Sun
@hhsun1
Aug 30, 2021
The Department of Computer Science and Engineering (cse.osu.edu) at The Ohio State University @OSUengineering has *20* tenure-track faculty positions open 👏. Retweet is appreciated! @AcademicJobs @ajobsonline @csfacultyjobs Check more:👇cse.osu.edu/faculty-recrui…
Huan Sun
@hhsun1
Dec 9, 2024
I was extremely fortunate to recruit @xiangyue96 as my Ph.D. student in 2018 and witness his remarkable growth into a rising star in NLP and AI. You might know him for his recent contributions like MMMU and MAmmoTH. But to me, long before these influential projects, Xiang
Xiang Yue
@xiangyue96
Dec 9, 2024
✈️Flying to #NeurIPS2024 tmr! Excited to reconnect with old friends and meet new ones. I co-authored 6 papers at NeurIPS👇. I'm on the faculty job market this year. My work focuses on advancing the reasoning abilities of LLMs across modalities and contexts. Ping me for a chat☕
40K
Huan Sun
@hhsun1
Nov 10, 2025
🚀 Worried about faculty openings? Ohio State @OhioState is to hire 100 new faculty with AI expertise over the next five years! 🤖🎓 The new hires will join one of three AI Faculty Cohorts: 🧠 Foundational AI — Elevating the theoretical, mathematical, and algorithmic
39K
Huan Sun
@hhsun1
Jan 29, 2025
Our ScienceAgentBench in @Nature news! DeepSeek R1 @DeepSeekR1 vs. @OpenAI o1 on data-driven scientific coding tasks: We sampled 20 tasks from ScienceAgentBench, with 5 tasks from each of the four scientific disciplines (bioinformatics, comp. chemistry, geo info science, phych.
nature
@Nature
Jan 29, 2025
DeepSeek's open AI model is giving scientists worldwide the opportunity to train custom reasoning models designed to solve problems in their disciplines. go.nature.com/42zO92D
30K
Huan Sun
@hhsun1
Oct 7, 2025
How often do you see two professors (from CMU) to jointly present their poster? @gneubig @dan_fried A must-check! 😆😆😆
Graham Neubig
@gneubig
Oct 7, 2025
Presenting some work at #colm2025 this week! First up is learning how we can turn websites into APIs for agents to use. arxiv.org/abs/2504.06821
42K
Huan Sun
@hhsun1
Mar 10, 2024
Claude 3 Opus gets better than GPT-4 on chemistry! We tested it on our recently released benchmark (SMolInstruct: arxiv.org/pdf/2402.09391…) that has a variety of tasks, including name conversion, property prediction, molecule captioning, molecule generation, forward synthesis,
Huan Sun
@hhsun1
Feb 20, 2024
Large Language Models for Chemistry: Chemistry plays a crucial role in many domains like drug discovery and material science. While LLMs exhibit remarkable capabilities on various NLP tasks, existing work shows their performance on chemistry tasks is discouragingly low.
30K
Huan Sun
@hhsun1
Oct 11, 2025
AutoSDT from @osunlp won the Best Paper Award at the #COLM2025 LLM for Scientific Discovery workshop @lm4sci. Many thanks to the organizers and PC for the recognition. AutoSDT automatically collects data-driven scientific coding tasks at scale for training open models. See
Yifei Li
@YifeiLiPKU
Jun 12, 2025
📢 Introducing AutoSDT, a fully automatic pipeline that collects data-driven scientific coding tasks at scale! We use AutoSDT to collect AutoSDT-5K, enabling open co-scientist models that rival GPT-4o on ScienceAgentBench! Thread below ⬇️ (1/n)
16K
Huan Sun
@hhsun1
Feb 20, 2024
Large Language Models for Chemistry: Chemistry plays a crucial role in many domains like drug discovery and material science. While LLMs exhibit remarkable capabilities on various NLP tasks, existing work shows their performance on chemistry tasks is discouragingly low.
47K
Huan Sun
@hhsun1
May 1, 2024
Finally got a bit time to introduce our recent work on learning to generate adversarial suffixes: arxiv.org/abs/2404.07921: Our generative model, named AmpleGCG, captures the distribution of adversarial suffixes given a harmful query and enables rapid generation of hundreds of
29K
Huan Sun
@hhsun1
Jun 8, 2022
Honored to receive a @GoogleAI Research Scholar Award 2022 to explore pre-trained language models for reasoning. Many thanks to my sponsors (esp. @congyu @JiaMShen) and students at @osunlp (esp. @BoshiWang2 & Xiang Deng). research.google/outreach/resea…
Huan Sun
@hhsun1
May 21, 2025
Super excited to get funded by @schmidtsciences to study computer-use agents (CUAs) under adversarial attacks. Many thanks to the student leads including @LiaoZeyi, Jaylen Jones, Linxi Jiang, and amazing co-PIs @ysu_nlp and @cszlin. As the capabilities of CUAs improve,
Huan Sun joins $10M AI Safety Science initiative
From engineering.osu.edu
8.8K