Thrilled to have "Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models" accepted at #NAACL2025 main conference. final version: arxiv.org/abs/2409.04318 , #NLProc #NAACL NAACL HLT 2025, congrats to, leading grad student, Aliakbar Nafar.

Basic spatial logic can be injected into language models for more generalizability in reasoning..See our #NAACL2025 Finding paper,"Neuro-symbolic Training for Reasoning over Spatial Language"#NLProc,NAACL HLT 2025 : arxiv.org/abs/2406.13828, Kados to grad student Tanawan Premseri.

What a great journey with Dr. Yue Zhang(Yue Zhang), my PhD student! with many interesting ideas and research findings in Vision and Language Navigation! Excited to see her continue to shine in the next chapter of her career. She joins Mohit Bansal's lab at UNC for postdoc👏🥳

LLMs are biased towards certain spatial Frames of References, making then aware of this concept helps more intelligent reasoning over spatial info. See our results in "FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks", github.com/HLR/FoREST #NLProc #AAAI2025

It was a great pleasure to give a talk at the Distinguished Speaker Series in the College of Computing & Information at Drexel. Thanks to the Doctoral Student Association for the invitation.

It was indeed a great pleasure to be in such a nice and energetic meeting. It was an honor to be invited to give a talk. Thanks for the pictures Martin Ziqiao Ma 😊

Many thanks Rada Mihalcea and all for organizing such a great event, it was an honor to be invited as keynote speaker.

I won’t be attending #ICLR2025 in person since #NAACL2025 follows right after, but here are a few things I’m excited about. 🔹 ICLR Oral Paper: Do Vision-Language Models Represent Space and How? 🗓 Oral: Apr 25, 3:42–3:54 a.m. (Session 4C) 🗓 Poster: Thu, Apr 24, 10 p.m.–12:30

Our poster SPARTUN3D: Situated Spatial Understanding of 3D World in LLMs is live at #ICLR2025! 📍Hall 3 + Hall 2B #242 🕙 Thursday, Apr 24 10:00 AM – 12:30 PM SGT Though I won't attend in person, Dr. Parisa Kordjamshidi will be presenting—feel free to stop by!

Find me at: - Fri Apr 25, 10am-12:30pm Hall 3 + Hall 2B #212, presenting the poster below w/ Parisa Kordjamshidi and Michigan SLED Lab - Fri Apr 25, Oral Session 4c w/ Michigan SLED Lab - All mentorship hours (12:30pm-2pm) on Apr 24-26 - proudly chairing the sessions w/ Rosanne Liu (2/)

Poster presentation update: I will present SPARTUN3D at Hall 2B #524, Saturday 3:00-5:30pm SGT. See you! #ICLR2025 ICLR 2026 #ICLR

Thrilled to win an Outstanding Paper Award at #NAACL2025! Huge Congrats to my PhD student Aliakbar Nafar and collaborator Brent Venable! "Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models" arxiv.org/abs/2409.04318 #NLProc NAACL HLT 2025

On my way to NAACL✈️! If you're also there and interested in grounding, don't miss our tutorial on "Learning Language through Grounding"! Mark your calendar: May 3rd, 14:00-17:30, Ballroom A. Another exciting collaboration with Martin Ziqiao Ma Jiayuan Mao Parisa Kordjamshidi Michigan SLED Lab!

Grateful to the Fulbright Program for supporting my visit to Vietnam. It was a great experience, I truly enjoyed engaging with the energy, curiosity, and enthusiasm for learning that defines this young generation. Many thanks to my hosts at UEH for their kindness, hospitality...

نگران فردای پس از سقوط جمهوری اسلامی نباشیم. ایران دچار جنگ داخلی و بی‌ثباتی نخواهد شد. ما برای آینده ایران و شکوفاییش برنامه داریم. ما برای صد روز نخست پس از سقوط، دوران گذار، و استقرار یک حکومت ملی و دموکراتیک، برای ملت ایران و به دست ملت ایران، آماده‌ایم.

Looking forward to SpaVLE workshop at #NeurIPS2025 on "Space in Vision, Language, and Embodied AI"! Plan to join us to explore groundbreaking ideas and engage in deep discussions! See details below 🥳!