Ismini Lourentzou

367 posts

Ismini Lourentzou banner
Ismini Lourentzou

Ismini Lourentzou

@Ismini_L

Director, PLAN Lab @iSchoolUI · NeurIPS'26 & ICML'26 Organizing Committee · GenAI, VLMs, Embodied AI, robots 🤖 | PhD @illinoisCDS 🇬🇷 https://t.co/i6SwwVvUwK

United States Katılım Eylül 2013
153 Takip Edilen447 Takipçiler
Sabitlenmiş Tweet
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
I am honored and grateful to receive an 𝗡𝗦𝗙 𝗖𝗔𝗥𝗘𝗘𝗥 award “𝘚𝘩𝘢𝘱𝘪𝘯𝘨 𝘌𝘮𝘣𝘰𝘥𝘪𝘦𝘥 𝘐𝘯𝘵𝘦𝘭𝘭𝘪𝘨𝘦𝘯𝘤𝘦 𝘛𝘩𝘳𝘰𝘶𝘨𝘩 𝘓𝘢𝘯𝘨𝘶𝘢𝘨𝘦-𝘎𝘶𝘪𝘥𝘦𝘥 𝘐𝘯𝘵𝘳𝘰𝘴𝘱𝘦𝘤𝘵𝘪𝘰𝘯.” 🎉 This project will support our work in the 𝗣𝗟𝗔𝗡 𝗟𝗮𝗯 toward more reliable, self-improving embodied AI systems. I am deeply thankful to @NSF, my students, whose creativity and hard work inspire me, as well as my collaborators, mentors, and @iSchoolUI colleagues for their support. I am also grateful to my former academic home @VT_CS where this work began to take shape. Excited for the work ahead! Learn more about our lab 👉 plan-lab.github.io #NSFCAREER #NSFfunded #EmbodiedAI #MultimodalAI #ResponsibleAI #iSchoolUI #PLANLab
iSchool at Illinois@iSchoolUI

#iSchoolUI Assistant Professor Ismini Lourentzou has received a $600K @NSF CAREER award for her project, “Shaping Embodied Intelligence Through Language-Guided Introspection,” which aims to build safer and more reliable AI systems. 🤖 Congrats, Ismini! ▶️ bit.ly/42QoWjn

English
3
0
8
1.6K
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Bumping this for anyone writing an NSF CAREER this cycle. Best of luck to everyone submitting this year! 🤞 calendly.com/lourent2-illin… 🔜 Office hours for PhD applications will be posted in September.
Ismini Lourentzou@Ismini_L

It's been an incredible year, with wonderful collaborators and a CAREER award I'm grateful for. I got a lot of feedback on mine, so I want to do the same for others. Opening office hours for faculty writing/thinking about #NSFCAREER proposals. Bring a draft, questions, or just chat. calendly.com/lourent2-illin… Happy to share tips and give honest feedback.

English
0
3
9
1.5K
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
🎥 Presenting our #CVPR2026 paper Phantom at @Voxel51's 𝗕𝗲𝘀𝘁 𝗼𝗳 𝗖𝗩𝗣𝗥 tomorrow morning, July 9, at 9 AM PT voxel51.com/events/best-of… Open to all and virtual, join us! 👻 Phantom consists of two parallel latent flow-matching branches, video and physics: physics cues guide visual generation, and visual evidence refines physics reasoning. Work led by @YingShen_ys 👏
Ismini Lourentzou@Ismini_L

🚀 Excited that our #CVPR2026 work 𝐏𝐇𝐀𝐍𝐓𝐎𝐌 will be featured in the Voxel51 𝐁𝐞𝐬𝐭 𝐨𝐟 𝐂𝐕𝐏𝐑 𝐬𝐞𝐫𝐢𝐞𝐬 on July 9! 𝐏𝐇𝐀𝐍𝐓𝐎𝐌: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics linkedin.com/feed/update/ur… Great work by @YingShen_ys and collaborators!

English
0
0
1
179
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
In ~1 hour at #ICML2026 🇰🇷 👋 Come by and chat with @onkar_s_13 about UniDFlow and his fantastic first PhD year at PLAN Lab with 3 first-author papers (PyraTok and RewardFlow at @CVPR and UniDFlow at @icmlconf) 🎉 📍Hall A · Poster #3817 · 10:30 AM – 12:15 PM KST UniDFlow is a collaboration with Google, supported by the Google TPU Research Cloud program 🙏
Ismini Lourentzou tweet media
English
0
2
9
697
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
At #ICML2026 in Seoul? Visit our UniDFlow @icmlconf poster tomorrow👇 📍 Hall A · Poster #3817 🗓 Wed Jul 8· AM – PM KST 🌐 plan-lab.github.io/unidflow 🤗 huggingface.co/papers/2602.12… A unified discrete flow model for T2I generation, image understanding, and reasoning-based editing, state-of-the-art across all three with 3× fewer parameters than baselines. Led by @onkar_s_13 👏 A PLAN Lab × Sony Research India × Google × UT Austin × IIT Roorkee collaboration 💫
English
0
1
16
979
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Two posters from my group and collaborators at #ICML2026 🇰🇷 📍 LaTtE-Flow (~6x faster inference): Tue 7/7, 10:30 AM – 12:15 PM KST, Hall A #2612 📍 UniDFlow (3x fewer params, SOTA on generation, understanding, editing): Wed 7/8, 10:30 AM – 12:15 PM KST, Hall A #3817 Will not attend @icmlconf this year, but @onkar_s_13 and @dhjang10 will be there! Stop by 👋
Ismini Lourentzou tweet media
English
0
2
9
519
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
🤖 🧭 How does a robot know how far along it is in a long task? Most VLA policies cannot explicitly track task progress, which is why they are often brittle in long-horizon, multi-step tasks. PALM (#CVPR2026) makes the policy progress-aware, coupling future affordance prediction with continuous progress estimation in a closed loop. Our code and model checkpoints are released 👇
Ismini Lourentzou@Ismini_L

🤖 Code and model checkpoints are out for PALM, our #CVPR2026 work on long-horizon robot manipulation. Work led by Yuanzhe Liu @ PLAN Lab👏 🧵1/4👇

English
0
0
9
807
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
It's been an incredible year, with wonderful collaborators and a CAREER award I'm grateful for. I got a lot of feedback on mine, so I want to do the same for others. Opening office hours for faculty writing/thinking about #NSFCAREER proposals. Bring a draft, questions, or just chat. calendly.com/lourent2-illin… Happy to share tips and give honest feedback.
English
3
2
20
3.8K
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Small note: the calendar is set up in 30-minute slots. For a longer meeting, please feel free to book two consecutive slots. You are also welcome to schedule follow-up conversations as needed.
English
0
0
0
218
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Can I be a Googler for a day? 🌀 Soaking up AI Systems DevLabs 2026 🤩
Ismini Lourentzou tweet mediaIsmini Lourentzou tweet mediaIsmini Lourentzou tweet media
English
0
0
0
205
Ismini Lourentzou retweetledi
The Sanghani Center at Virginia Tech
Eman Abdelrahman, Ph.D. student @SanghaniCtrVT and Spring 2026 Ph.D. grad Makanjuola Ogunleye attended #CVPR2026 w/advisor @Ismini_L, where they teamed up to present their work on “3-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding.”
The Sanghani Center at Virginia Tech tweet mediaThe Sanghani Center at Virginia Tech tweet mediaThe Sanghani Center at Virginia Tech tweet media
English
0
2
3
425
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Check out our #ECCV2026 work on 🎥 Interactive graph-controllable video generation 🧩 Semantically grounded part-level 3D generation 🚶 Children's gait video understanding Huge congratulations to @VedantRShah, @yu_tianjiao, @SivanShen, Boyi Li, @IrohXu, and all coauthors. Excited to share more soon.
Ismini Lourentzou tweet media
English
0
3
9
877
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
How to fix this? Are per-author submission caps and stricter rejects the solution? 🤔
English
0
0
0
116
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Hiring and tenure reward count. And now the pressure peaks early, on the student and postdoc job market. Add field growth, conference deadlines that batch everyone into the same few venues, resubmission churn, and now LLMs lowering the barriers of production.
English
1
0
1
197
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
In every cycle and every conference, the submission numbers climb, and I keep asking what we're optimizing for: more papers, or better science? I don't think those are the same thing anymore...
Kenneth Marino@Kenneth_Marino

Absolutely insane graph here. I’m sorry, if you wrote 40 papers for ACL, no you didn’t. @CVPR put a cap and a bunch of other reforms to try to head off the paper-pocalypse. ACL was caught flat-footed and now it sounds like they’re getting absolutely dogpiled by angry reviewers.

English
1
0
0
388
Ismini Lourentzou
Ismini Lourentzou@Ismini_L·
Nothing keeps you humble like a "after considering the rebuttal and other reviews, I maintain my score" right after a good week of #ECCV2026 acceptances 😂 Respect to everyone doing the unpaid reviewing ... and to the rebuttal genre, truly an art form!
GIF
English
0
0
7
418