Mohamed Elhoseiny

467 posts

Mohamed Elhoseiny banner
Mohamed Elhoseiny

Mohamed Elhoseiny

@moElhoseiny

AI Prof @KAUST_news supporting @KAUSTVisionCAIR lab (hiring!), AI artist; formerly @StanfordGSB Igniter,@facebookai,@Baidu,@Adobe,@RutgersU

KAUST Katılım Eylül 2018
812 Takip Edilen1.6K Takipçiler
Mohamed Elhoseiny retweetledi
Aishwarya Agrawal
Aishwarya Agrawal@aagrawalAA·
I will be speaking about "Reasoning, data-efficiency and alignment in vision-language models" at the CLVL workshop tomorrow (Oct 20) at ICCV @ 9.15am! So stop-by if you are interested in these topics, or just want to learn about what my lab is up-to! #home-section" target="_blank" rel="nofollow noopener">iccv-clvl.github.io/2025/#home-sec…
Mohamed Elhoseiny@moElhoseiny

🎉 CLVL 2025: Celebrating a Decade of Vision & Language Innovation! 🎉 Join us for a reflection on a remarkable decade-long journey for the CLVL workshop series with an amazing set of speakers!

English
2
5
34
8.8K
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
🎉 CLVL 2025: Celebrating a Decade of Vision & Language Innovation! 🎉 Join us for a reflection on a remarkable decade-long journey for the CLVL workshop series with an amazing set of speakers!
Mohamed Elhoseiny tweet media
English
0
0
7
9.1K
Mohamed Elhoseiny retweetledi
Kilichbek Haydarov
Kilichbek Haydarov@kilich_bek_·
CLVL: 6th Workshop on Closing the Loop Between Vision & Language (Decade Mark)! is just around the corner ! October 20, 2025 - [8:30 AM – 6:00 PM (GMT-10)] Room 313 C, Hawaii Convention Center — Honolulu, Hawai‘i 🌴🌴🌴 👉 Learn more: iccv-clvl.github.io/2025/
English
1
1
1
296
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
@kilich_bek_ is now a leading PhD in our Neuroscience & AI Lab, focusing on brain-interfaced multimodal models.
English
0
0
1
110
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
Proud advisor moment! 🎉 Congrats to Kilichbek Haydarov for making the Dean’s List — well-deserved! 👏 Kilich has led impactful work in multimodal learning, with first-author papers at CVPR’24, ECCV’24, and EMNLP’25. Check out his work👉 lnkd.in/gBh2n3YF
KAUST CEMSE@KAUST_CEMSE

Join us in celebrating the 2024–2025 Dean's List honorees from the @KAUST_CEMSE Division. These students have gone above and beyond, demonstrating the exceptional drive, curiosity and perseverance that define our community. Earning this distinction is a testament to their passion, hard work and commitment to academic excellence. Their distinction is not only a personal milestone but also a reflection of the vibrant academic environment we cultivate—one that encourages curiosity, innovation and continuous growth. Congratulations to all honorees for this well-deserved recognition. You make our community proud! #KAUST #CEMSE #DeansList #AcademicExcellence #HigherEducation #STEM #StudentSuccess

English
1
0
2
609
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
7️⃣ AURELIA: Test-Time Reasoning Distillation in Audio-Visual LLMs Sanjoy Chowdhury, Hanan Gani, Nishit Anand, Sayan Nag, Ruohan Gao, Mohamed (Mo) Elhoseiny, Salman Khan, Dinesh Manocha 🔗 Paper: lnkd.in/g4NQDNNr 💻 Webpage: lnkd.in/gfYdKXdR
English
0
0
0
121
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
🚀 Thrilled to share that we have 7 papers accepted at ICCV 2025 (main conference)! 🎉 Grateful to all the amazing students, collaborators & co-authors 🙌 — advancing the frontier of multimodal, diffusion, and generative AI. 📢 We’re hiring a Postdoc! 👇 Thread 👇 #ICCV25
English
8
0
4
347
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
6️⃣ AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Yaoting Wang, Mohamed (Mo) Elhoseiny, Ruohan Gao, Dinesh Manocha 🔗 Paper: lnkd.in/g9tdMm4E 🌐 Project/Code: lnkd.in/gttSJQfm
English
0
0
0
85
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
5️⃣ Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description Mahmoud Ahmed Junjie Fei, Jian Ding, Eslam Abdelrahman, Mohamed (Mo) Elhoseiny 🔗 Paper: lnkd.in/gXr-dhbi 🌐 Webpage: lnkd.in/gfzSKVKX
English
0
0
0
60
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
4️⃣ WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation *Zhongyu Yang, *Jun Chen, Dannong Xu, Junjie Fei, Xiaoqian Shen, Liangbing Zhao, Chun-Mei Feng, Mohamed (Mo) Elhoseiny 🔗 Paper: lnkd.in/g2Y33m6D 🌐 Project: lnkd.in/gPaFznuj
Suomi
0
0
0
80
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
3️⃣ Diffusion-Based Imaginative Coordination for Bimanual Manipulation Huilin Xu, Jian Ding, Jiakun XU, Ruixiang Wang, Jun Chen, Jinjie Mai, Yanwei FU, Bernard Ghanem, Feng Xu, Mohamed (Mo) Elhoseiny 🔗 Paper: lnkd.in/gyAPS_HN 🌐 Website: lnkd.in/gQ_7PrSN
Filipino
0
0
0
96
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
2️⃣ 4D-Bench: Benchmarking Multi-Modal Large Language Models for 4D Object Understanding @Wenxuan Zhu, @Bing Li, Cheng Zheng, Jinjie Mai, Jun Chen, Letian Jiang, Abdullah Hamdi, PhD, Sara Rojas Martinez, @Chia-Wen Lin, Mohamed (Mo) Elhoseiny , Bernard Ghanem
Indonesia
0
0
0
198
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
📌 1️⃣ From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning *Le Zhuo, *Liangbing Zhao, Sayak Paul, @Yue Liao, Renrui Zhang, Yi Xin, @Peng Gao, **Mohamed (Mo) Elhoseiny, **Hongsheng Li * Equal contribution
English
1
0
0
95
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
#ICML2025 @xiaoqian_shen and team are presenting LongVU paper at ICML on the 17th this week. The developed mechanism was shown to significantly reduce spatiotemporal redundancy in video LLMs.
Mohamed Elhoseiny@moElhoseiny

📢 New Paper Alert! 🚀📄 Excited to announce "LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding." 📝Paper: lnkd.in/gHYG3ruX 🧑🏻‍💻Code: lnkd.in/gmxunM2C 🚀Project (Demo): lnkd.in/gqKVq25U

English
0
1
11
1.2K
Mohamed Elhoseiny retweetledi
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
📢 New Paper Alert! 🚀📄 Excited to announce "LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding." 📝Paper: lnkd.in/gHYG3ruX 🧑🏻‍💻Code: lnkd.in/gmxunM2C 🚀Project (Demo): lnkd.in/gqKVq25U
Mohamed Elhoseiny tweet mediaMohamed Elhoseiny tweet mediaMohamed Elhoseiny tweet media
English
2
12
89
18.3K
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
🗂️ Archival Track (published in ICCV proceedings) • Submission Deadline: July 7, 2025 • Notification: July 11, 2025 ? • Camera-Ready: August 18, 2025 📝 Non-Archival Track • Submission Deadline: Aug 15, 2025 • Notification: Sept 7, 2025 • Camera-Ready: Sept 15, 2025
English
1
0
2
386
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
🚨 Call for Papers – 6th ICCV 2025 Workshop on Closing the Loop between Vision & Language (CLVL), Decade Mark! Celebrating 10 years of CLVL @ ICCV25! 🎉 Featuring an exciting speaker lineup, including speakers from CLVL’15; see details on linkedin link; bit.ly/3I0ADwD
Mohamed Elhoseiny tweet media
English
1
3
11
6.6K
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
🧠 Organizers: with Angel Chang, Marcus Rohrbach & Anna Rohrbach, Xin Eric Wang, Krishna Kumar Singh, Kilichbek Haydarov, Eslam Bakr, Austin Wang, Yiming Zhang, Tobias Wieczorek, Qianqi Yan Let’s make this Decade Milestone one to remember with bold ideas and groundbreaking work
English
0
0
2
117
Mohamed Elhoseiny
Mohamed Elhoseiny@moElhoseiny·
📅 Workshop Date: October 20, 2025 🌐 Website lnkd.in/gXwBZxKj 💡 Topics include (but not limited to): • Vision–Language Pretraining • Grounded Generation and Retrieval • Multimodal Reasoning • Embodied AI and Robotics • Few-shot & Weakly Supervised Learning
English
1
0
1
90

Keşfet

@kilich_bek_ @Wenxuan @bing @chia @Yue @Peng @amasad @xiaoqian_shen