Hossein Resani

You never fail until you stop trying. (Einstein)

✨ Hi, I’m an AI researcher and online instructor.

🤖 My current research interests mainly focus on large language models and world models, especially how LLMs/world models reason about cause-and-effect relationships, how we can compress them efficiently, and how to make their decisions more robust and reliable.

👨🏻‍🏫 Teaching is a significant part of my life, as it allows me to connect with others, share knowledge, and deepen my own understanding. You know, There’s a big difference between knowing something and teaching it!

Research Interests:

👁‍🗨 Large Language Models
📚 World Models
🤖 Causal AI
🏞️ (Visual) Reasoning
🧠 Meta Learning
💥 XAI
🏞️ 3D Vision (NeRF, Gaussian Splatting)

Life Interests:

🎤 Presentation: I love sharing ideas and making complex topics easier to understand. Whether I’m in a classroom or online, creating engaging presentations is something I really enjoy.
😍 Teaching: Teaching is a big part of my life, and it’s honestly one of the most rewarding experiences.
💡 Solving Problems: I get excited by the challenge of tackling tricky problems, whether it’s in research or real-world applications. It’s all about finding that “lightbulb” moment!

news

Oct 01, 2025	👨‍💻 `Life update!` I’ve started my PhD at the Australian Institute for Machine Learning (AIML) under the supervision of Prof. Javen Shi. Excited for this new chapter! 🚀
Sep 07, 2025	🎉 `Milestone Achieved!` Today, I celebrated my 1000th class in Python, ML, and DL!🎊 It’s hard to believe how far we’ve come. A huge thank you to everyone for being part of this journey. Let’s keep learning together! 🚀
Apr 19, 2025	🎉 `Big news!` Won 3rd Place in the WSS Poster Session Competition for presenting my ICLR paper (selected from 60+ poster submissions).
Jan 22, 2025	🎉 `Big news!` My paper got accepted to ICLR 2025 with all positive reviews! couldn’t be happier! 🚀
Jan 03, 2025	🎉 Exciting news! I was awarded a DEI scholarship that covers travel costs to attend the WACV conference. See you in Arizona! 🌵
Dec 12, 2024	📢 `Online Presentation` on Egocentric Video Understanding - [Slides]
Nov 07, 2024	📢 `Online Presentation` Beyond the NeRF (NeRF improvements like Plenoxels, NeRF in the Wild, Instant-NGP, NeRF++, and more!)
Oct 28, 2024	🎉 `Big news!` My paper got accepted to WACV 2025! 🚀 [Read it on arXiv]
Oct 24, 2024	📢 `Online Presentation` on Introduction to 3D Gaussian Splatting - [Slides] [video]
Oct 17, 2024	📢 `Online Presentation` on Introduction to NeRF (in persian) - [Slides] [video]

selected publications

WACV 2025

Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection

Hossein Resani, Behrooz Nasihatkon, and Mohammadreza Alimoradi Jazi

Accepted at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Abs PDF Video

A novel framework for Continual Learning in 3D object classification (CL3D) based on the selection of prototypes from each class using spectral clustering is introduced, and the effectiveness of clustering in the input space, local feature space, and global feature space is explored.
ICLR 2025

MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model construction

Hossein Resani, and Behrooz Nasihatkon

Accepted at International Conference on Learning Representations (ICLR), 2025

Abs PDF Video

This paper presents a novel framework for memory-efficient and privacy-preserving continual learning in 3D point cloud classification. Instead of storing numerous exemplars, our method uses a compact shape model that stores only the mean shape and key modes of variation, significantly reducing memory usage while enhancing privacy. The approach includes Gradient Mode Regularization to improve model robustness and stability against input variations.