Ruoxi Jia

@ruoxijia

Assistant Professor at VT ECE, PhD at Berkeley EECS, researcher in responsible AI, proud mom of two

Joined August 2017

344Following

666Followers

Pinned

Ruoxi Jia Retweeted

Maura Pintor@maurapintor · May 2

🚀 Exciting Announcement! 🚀 Get ready for the 18th ACM Workshop on Artificial Intelligence and Security (AISec 2025)! 📍Co-located: @acm_ccs 🗓️ Deadline: June 20th, 2025 🌐 Website: aisec.cc w/ @ruoxijia and Matthew Jagielski

2.0K

Ruoxi Jia@ruoxijia · Jul 12

Check out our new #ICML2025 paper on a lightweight method for mitigating over-refusal! This work is led by my amazing student Mahavir, and it's his first ICML publication. Thrilled to see his research career take off!

MMahavir@Mahavir_Dabas18 · Jul 12

🎉 Thrilled to be presenting my first paper at @icmlconf! "Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning" We introduce ACTOR—a lightweight, activation-based training method that reduces over-refusal without…

751

Ruoxi Jia Retweeted

Shivalika Singh@singhshiviii · Apr 30

LMArena is widely used for model evaluation, but is it measuring true progress? 🔮 In our work, "The Leaderboard Illusion", we reveal: 🔒 Private testing 📊 Data access asymmetries ⚠️ Overfitting risks 🚫 Silent deprecations Despite best intentions, arena policies favor a few!

190

47.0K

Ruoxi Jia@ruoxijia · Apr 29

It was challenging to organize the workshop as the sole in-person organizer, and I’m deeply grateful to everyone for their incredible support in making it a great success. @danqi_chen @PeterHndrsn @kylelostat @mirrokni @bryanklow @hmgxr128 @brandontrabucco Zheng Xu, Edward Yeo,…

TTianhao Wang ("Jiachen") @ ICML@JiachenWang97 · Apr 27

Join us at @iclr_conf on Monday (4/28) in Hall 4 #4 for a full-day workshop on data problems for foundation models! We'll explore research frontiers in understanding and optimizing data across all aspects of foundation model development. Schedule: datafm.github.io We…

3.0K

Ruoxi Jia@ruoxijia · Apr 25

Congrats @dawnsongtweets you are the inspiration to many of us!

DDawn Song@dawnsongtweets · Apr 24

Deeply humbled and honored to be elected to the American Academy of Arts and Sciences @americanacad! Excited to contribute to the Academy’s mission and advancing the common good! amacad.org/new-members-20…

318

Ruoxi Jia@ruoxijia · Apr 23

Delighted to share that two papers from our group @EPrinceton got recognized by the @iclr_conf award committee. Our paper, "Safety Alignment Should be Made More Than Just a Few Tokens Deep", received the ICLR 2025 Outstanding Paper Award. This paper showcases that many AI…

IICLR 2026@iclr_conf · Apr 23

Outstanding Papers Safety Alignment Should be Made More Than Just a Few Tokens Deep. Xiangyu Qi, et al. Learning Dynamics of LLM Finetuning. Yi Ren and Danica J. Sutherland. AlphaEdit: Null-Space Constrained Model Editing for Language Models. Junfeng Fang, et al.

110

56.0K

Ruoxi Jia Retweeted

Tianhao Wang ("Jiachen") @ ICML@JiachenWang97 · Apr 23

Thrilled to receive ICLR'25 Outstanding Paper Honorable Mention! Heartfelt thanks to my incredible mentors @ruoxijia @dawnsongtweets @prateekmittal_ @james_y_zou. I'll be giving two oral presentations on our recent work in training data attribution & co-organizing a workshop on…

6.0K

Ruoxi Jia@ruoxijia · Apr 22

If you are attending ICLR, check out Yi’s work that presents a systematic way of understanding AI safety risks as well as a policy-grounded benchmark!

YYi Zeng 曾祎@EasonZeng623 · Apr 22

AIR-Bench is a Spotlight @iclr_conf 2025! Catch our poster on Fri, Apr 26, 10 a.m.–12:30 p.m. SGT (Poster Session 5). Sadly, I won’t be there in person (visa woes, again), but the insights—and our incredible team—will be with you in Singapore. Go say hi 👋

453

Ruoxi Jia Retweeted

The Sanghani Center at Virginia Tech@SanghaniCtrVT · Mar 14

Ph.D. student @EasonZeng623 looks at new way of jailbreaking LLMs -- treating them as human-like communicators to examine the interplay between everyday language interaction and AI safety. #VTInnovationCampus opening he discussed his work @SanghaniCtrVT. tinyurl.com/4ma7725v

838

Ruoxi Jia Retweeted

Tianhao Wang ("Jiachen") @ ICML@JiachenWang97 · Jan 27

Excited to announce the ICLR 2025 Workshop on Data Problems for Foundation Models (DATA-FM)! We welcome submissions exploring all aspects of data in foundation model research, including but not limited to data curation, attribution, copyright, synthetic data, benchmark, societal…

6.0K

Ruoxi Jia@ruoxijia · Feb 7

Submission deadline AoE today for our Workshop on Data Problems for Foundation Models! Look forward to your contributions!

HHoàng Anh Just@reds_tiger · Feb 6

Announcing the ICLR 2025 Workshop on Data Problems for Foundation Models (DATA-FM)! We welcome submissions exploring ALL ASPECTS OF DATA in foundation model research. Submission deadline: Feb 7th (this Friday!) 11:59pm AoE datafm.github.io

821

Ruoxi Jia Retweeted

Tianhao Wang ("Jiachen") @ ICML@JiachenWang97 · Dec 12

I will be presenting our NeurIPS spotlight work on gradient-based online data selection for LLMs today (12/12) at 4:30-7:30pm PST (East Hall #4400). Big thanks to my amazing collaborators @ruoxijia @TongWu_Pton @dawnsongtweets @prateekmittal_ Please feel free to come by and…

4.0K

Ruoxi Jia@ruoxijia · Dec 11

Here are all three parts of the slides for "Advancing Data Selection for Foundation Models: From Heuristics to Principled Methods" tutorial at NeurIPS yesterday! Part 1 (Intro + Empirical Methods): tinyurl.com/yc5bhfbn Part 2 (Principled Methods): tinyurl.com/3mzbue3j…

RRuoxi Jia@ruoxijia · Dec 11

Here’s my slide deck from the tutorial. Thanks to everyone who attended yesterday - it was a super rewarding process to prepare for this! tinyurl.com/5b524eaz

2.0K

Ruoxi Jia@ruoxijia · Dec 11

Here’s my slide deck from the tutorial. Thanks to everyone who attended yesterday - it was a super rewarding process to prepare for this! tinyurl.com/5b524eaz

RRuoxi Jia@ruoxijia · Dec 10

Join us Tuesday at 1:30 PM PT at #NeurIPS2024 for our tutorial on data selection for foundation models! With @lschmidt3 & @JiachenWang97, we'll cover principled experimentation, selection algorithms, a unified theoretical framework, and open challenges. Hope to see you there!

4.0K

Ruoxi Jia Retweeted

Myeongseob Ko@KoMyeongseob · Dec 11

Excited to attend #NeurIPS2024 in Vancouver 🇨🇦! I will be presenting our work: "Boosting Alignment for Post-Unlearning Text-to-Image Generative Models." If you are interested in unlearning, stop by our poster: 🕐 Wed, Dec 11 | 11 am - 2 pm PST 📍 West Ballroom #7006

2.0K

Ruoxi Jia@ruoxijia · Dec 10

ruoxijia's tweet image. Join us Tuesday at 1:30 PM PT at #NeurIPS2024 for our tutorial on data selection for foundation models! With @lschmidt3 &amp; @JiachenWang97, we'll cover principled experimentation, selection algorithms, a unified theoretical framework, and open challenges. Hope to see you there!

3.0K

Ruoxi Jia Retweeted

Nathan Lambert@natolambert · Nov 21

I've spent the last two years scouring all available resources on RLHF specifically and post training broadly. Today, with the help of a totally cracked team, we bring you the fruits of that labor — Tülu 3, an entirely open frontier model post training recipe. We beat Llama 3.1…

142

798

636

118.0K

Ruoxi Jia Retweeted

Zhuohao Ni@ppppnnnni · Nov 20

🚀 Excited to announce our latest paper: MLAN: Language-Based Instruction Tuning Improves Zero-Shot Generalization of Multimodal Large Language Models! arxiv.org/abs/2411.10557

3.0K