Babak Taati
Babak Taati
@babaktaati.bsky.social
Senior Scientist at the Kite Research Institute | Toronto Rehab - University Health Network. Associate Professor, Affiliated Scientist in the Department of Computer Science, University of Toronto (cross appointed at the Institute of Biomedical Engineering)
CARE-PD is the largest publicly available archive of 3D mesh gait data for Parkinson’s Disease, collected across 9 cohorts from 8 clinical centers. It provides standardized, anonymized SMPL representations and benchmark protocols for clinical motion analysis on PD.
October 14, 2025 at 8:12 PM
LIFT uses meta-learning to efficiently encode diverse signals (images, 3D shapes, and more) into multiscale latent representations for downstream tasks like generation and classification.

Paper: arxiv.org/abs/2503.15420
Project page: amirhossein-kz.github.io/lift/
LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding
Implicit Neural Representations (INRs) are proving to be a powerful paradigm in unifying task modeling across diverse data domains, offering key advantages such as memory efficiency and resolution ind...
arxiv.org
October 14, 2025 at 1:51 PM
🙋 I'll be at ICCV and interested in meeting
September 23, 2025 at 4:53 PM
📜 Abstract: arxiv.org/abs/2506.10036
🌐 Project page: github.com/TaatiTeam/To...

Great collaboration with Javad Rajabi, Soroush Mehraban, Seyedmorteza Sadat.
Token Perturbation Guidance for Diffusion Models
Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific train...
arxiv.org
September 22, 2025 at 2:39 PM
TPG outperforms SDXL, PAG, and SEG in unconditional generation, and closely matches CFG in conditional tasks across all metrics.
September 22, 2025 at 2:39 PM
TPG mirrors CFG by producing guidance vectors nearly orthogonal to ground-truth noise and maintaining strong guidance throughout denoising. Unlike PAG/SEG, it avoids negative alignment and weak updates, leading to more effective, high-quality generation.
September 22, 2025 at 2:39 PM
TPG, like CFG, effectively recovers global structure and coarse details during early denoising steps. This stage is crucial for image quality and prompt alignment, as it establishes the foundation for structure and semantics.
September 22, 2025 at 2:39 PM
In conditional generation, TPG produces better results and matches prompts more accurately than other attention-based methods like PAG and SEG. It also behaves more like CFG in how its guidance works and how often it applies.
September 22, 2025 at 2:39 PM
TPG is a novel, training-free approach that boosts diffusion model performance by perturbing (shuffling) intermediate token representations. It improves both conditional and unconditional generation while also strengthening prompt alignment.
September 22, 2025 at 2:39 PM
Developed with Dr. Nimish Mittal, Dr. Amol Deshpande & Andrea Sabo at Kite Research Institute | Toronto Rehab - UHN.
September 20, 2025 at 12:29 AM
The HAT app is approved by Health Canada and, for now, is only available in Canada. We will release it in the US after receiving FDA approval.
September 20, 2025 at 12:26 AM
The app guides users through 9 steps to return the Beighton Score, making hypermobility testing and EDS screening accessible to providers and the public.
September 20, 2025 at 12:26 AM
We did this back in 2023. I’d be curious to see how newer models perform if you get a chance to test them. The dataset is public. We had the first 15 seasons at the time, but I’m sure newer seasons are available now as well.
September 3, 2025 at 2:32 PM