Tianshu Kuai

CS PhD Student @UMontreal and @Mila_Quebec | MSc and BASc @UofT

[Tianshu Kuai @TianshuKuai]

📢 Introducing our #SIGGRAPH2026 work, Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes.

🌐: https://t.co/4cX7cNNgL3
📜: https://t.co/g0hv5c2VjP

[1/8]

[Tianshu Kuai @TianshuKuai]

See our paper for more details and results. We have also released our code, checkpoints, datasets, and data generation scripts at https://t.co/sSvppOIXOV

A huge thank you to my amazing collaborators @ArmanMaesumi, Daniel Ritchie, and @AigermanNoam.

[8/8]

[Tianshu Kuai @TianshuKuai]

📢 Introducing our #SIGGRAPH2026 work, Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes.

🌐: https://t.co/4cX7cNNgL3
📜: https://t.co/g0hv5c2VjP

[1/8]

[Tianshu Kuai @TianshuKuai]

Our model can also generate yoga poses for humanoid meshes that were never seen by the model during training. [7/8]

[Tianshu Kuai @TianshuKuai]

@igilitschenski @ashmrz10 Congrats @ashmrz10 !!!

[Tianshu Kuai @TianshuKuai]

Please see our project page and paper for more details and results. We have also released our code!

This work was done during my internship at Samsung AI Center Toronto in 2024. Huge thanks to my amazing collaborators Sina Honari, @igilitschenski , and Alex Levinshtein! (7/7)

[Tianshu Kuai @TianshuKuai]

📢Missed WACV? Check out our #WACV2025 Oral paper, "Towards Unsupervised Blind Face Restoration using Diffusion Prior." (1/7)

arXiv: https://t.co/X5dgrdmGug
Project page: https://t.co/1Yu3oouzmS
Code: https://t.co/Tuy4tTDdLu

[Tianshu Kuai @TianshuKuai]

Our method only requires a small set of unpaired low-quality images for fine-tuning. We start to outperform the pre-trained model in perceptual quality by a large margin even with only 100 images, and all metrics continue to improve as the data size increases. (6/7)

[Noam Aigerman @AigermanNoam]

I'll be recruiting PhD and MSc students through Mila - consider applying if you want to work at the intersection of machine learning and 3D geometry!

[Mila - Institut québécois d'IA @Mila_Quebec]

Mila's annual supervision request process opens on October 15 to receive MSc and PhD applications for Fall 2025 admission! Join our community! More information here https://t.co/r01eLcXtZw

[Yash Kant @yash2kant]

📢🔍 Super excited to present Spatially Aware Multiview Diffusers (SPAD) at #CVPR2024!

SPAD enables 3D consistent multi-view image generation from text or image inputs. It is trained using a high-quality Objaverse subset on 32 H100s!

Code & Paper links at the end!

🧵👇

[Ziyi Wu @Dazitu_616]

1/ Excited to share our #CVPR2024 work LEOD!

We propose a label-efficient learning framework for object detection with event cameras, which performs on par with SOTA models with **10x fewer labels**!

Paper: https://t.co/olRHp4iphU
Code: https://t.co/RVPaLBfhIQ