@HOtroshi profile picture
Hatef Otroshi @HOtroshi

Researcher in Computer Vision and Machine Learning | IEEE Senior Member | Postdoc at @Idiap_ch | PhD from @epfl_en

Joined August 2022
  • Tweets 47
  • Following 452
  • Followers 42
18 Photos and videos
📢Thrilled to announce that we are organising the 3rd Workshop on Foundation and Generative Models in Biometrics at #ECCV 2026 ! 📍Malmö, Sweden - @eccvconf 🗓️September 8-9, 2026 🔍More details and call for papers: foundgen-bio.github.io/eccv2… #ECCV2026 #ECCV26
1
8
1,349
Multimodal LLMs are rapidly being adopted for vision-language tasks applications. But how fair are they across demographic groups?🤔 🔍In our recent work, accepted in #CVPR 2026 workshops, we evaluate gender and ethnicity bias in 9 different MLLMs for face verification. 🧵(1/3)
1
1
93
📊Key findings: ✅ Bias persists in MLLMs: Performance varies significantly across demographic groups ✅ Gender and ethnicity disparities can be observed even in advanced models ✅ There is a gap between generative capability and trustworthy decision-making 🧵(2/3)#bias #fairness
2
1
50
📄 Pre-print (arxiv): arxiv.org/abs/2603.25613 🌐 Project page: idiap.ch/paper/mllm-fairness 💻 Code: check our project page! This is a joint work with Unsal Ozturk and Sébastien Marcel. Congratulations to the team! 🚀 🧵(3/3) #bias #fairness #LLM #VLM #MLLM
38
🚨 Deadline Extension! 🚨 The submission deadline for @CVPR Workshop on Foundation and Generative Models in Biometrics is extended to March 10. 🌐 Visit the workshop page for more details and call for papers: foundgen-bio.github.io/cvpr2… #CVPR #CVPR26 #CVPR2026
1
3
8
3,010
📢Thrilled to announce that we are organising the 2nd Workshop on Foundation and Generative Models in Biometrics at #CVPR 2026 ! 📍Denver, USA - @CVPR 🗓️June 3-4, 2026 🔍More details and call for papers: foundgen-bio.github.io/cvpr2…
4
1,156
Hatef Otroshi retweeted
IEEE Signal Processing Society@IEEEsps
Jan 2
✨Paper spotlight! The paper provides an in-depth analysis of state-of-the-art methodologies regarding foundation multi-modal models, their advancements, and their applicability to biometrics tasks. 🔗Read at hubs.la/Q03Zn52z0.
1
4
265
Is there any issue with paperswithcode? All badges seem broken! @paperswithcode #paperswithcode
2
1
233
The badges are now back live! Thanks for the quick fix!
1
140
Not only badges are broken again, but the website (paperswithcode.com) is now down! @paperswithcode #paperswithcode

Trending Papers - Hugging Face

Your daily dose of AI research from AK

huggingface.co
333
Excited to share our new paper, "FaceLLM: A Multimodal Large Language Model for Face Understanding" ! ✨ 📄 Pre-print(arxiv): arxiv.org/pdf/2507.10300 🌐 project page: idiap.ch/paper/facellm/
1
2
186
more replies
We introduce FaceLLM, a MLLM trained specifically for facial image understanding. To construct the training data, we propose a novel weakly supervised pipeline that generates high-quality question-answer pairs based on images from the FairFace dataset.
1
1
78
🏆Our experiments demonstrate that FaceLLM achieves the state-of-the-art performance of MLLMs on various face-centric tasks🎭.
1
58
🚨 Deadline Extension! 🚨 The submission deadline for #ICCV2025 Workshop on Foundation and Generative Models in Biometrics is extended to July 1. @ICCVConference #ICCV 🔍Visit the workshop page for more details and call for papers: foundgen-bio.github.io/iccv2…
2
11
2,426
📢We are thrilled to announce that we are organising the Workshop on Foundation and Generative Models in Biometrics at #ICCV 2025 ! 📍Honolulu, Hawaii - @ICCVConference 🗓October 19-20, 2025 #ICCV2025 🔍More details and call for papers: foundgen-bio.github.io/iccv2…
1
9
2,515
Excited to share that our paper is accepted at #ICML 2025 ! We introduce a novel physics-inspired approach based on Brownian motion to generate synthetic face recognition datasets. 📄 Pre-print(arxiv): arxiv.org/abs/2405.00228 🌐 project page: idiap.ch/paper/synthetics-di… 🧵(1/4)
1
1
8
708
more replies
🧵(3/4) We generate several synthetic face datasets and evaluate them by training face recognition models and benchmarking trained models on real face recognition benchmark datasets. #ICML #ICML2025
1
2
367
🧵(4/4) We also show that our approach can be used to mitigate leakage from the generator's training set and explore the ability of generative models to generate data beyond it. #ICML #ICML2025
2
344
Load more