Speaker: Dr. Devin Brown, Professor of Neurology at the University of Michigan
Title: Post-stroke sleep apnea
kite-uhn.com/talk/researc...
Speaker: Dr. Devin Brown, Professor of Neurology at the University of Michigan
Title: Post-stroke sleep apnea
kite-uhn.com/talk/researc...
Project page: amirhossein-kz.github.io/lift/
"LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding"
Project page: amirhossein-kz.github.io/lift/
Project page: neurips2025.care-pd.ca
Project page: neurips2025.care-pd.ca
TPG is a simple & effective method based on token shuffling. It extends the benefits of CFG to broader settings, including unconditional generation.
arXiv: arxiv.org/abs/2506.10036
#NeurIPS2025
TPG is a simple & effective method based on token shuffling. It extends the benefits of CFG to broader settings, including unconditional generation.
arXiv: arxiv.org/abs/2506.10036
#NeurIPS2025
kite-uhn.com/news/uhn-app...
kite-uhn.com/news/uhn-app...
DiffuseGaitNet: Diffusion Model Framework for Parkinson's Disease Gait Severity Assessment
Time: 13:00
Location: SRIC-11 Erin Room (W1160)
www.cs.toronto.edu/~taati/journ...
DiffuseGaitNet: Diffusion Model Framework for Parkinson's Disease Gait Severity Assessment
Time: 13:00
Location: SRIC-11 Erin Room (W1160)
www.cs.toronto.edu/~taati/journ...
tl;dr: LLMs were pretty shit at the Connecting Wall and were often fooled by red herring distractors.
proceedings.neurips.cc/paper_files/...
tl;dr: LLMs were pretty shit at the Connecting Wall and were often fooled by red herring distractors.
proceedings.neurips.cc/paper_files/...
contentsharing.net/actions/emai...
contentsharing.net/actions/emai...
Title: Development of physiology-driven machine learning algorithms to assess cardio-respiratory function and diagnose sleep apnea
Date: Jan 27, 2025
Location: TRI 2nd floor auditorium
kite-uhn.com/talk/yadolla...
Title: Development of physiology-driven machine learning algorithms to assess cardio-respiratory function and diagnose sleep apnea
Date: Jan 27, 2025
Location: TRI 2nd floor auditorium
kite-uhn.com/talk/yadolla...
1) Scanning Trojaned Models Using Out-of-Distribution Samples (NeurIPS 2024), and
2) RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024).
1) Scanning Trojaned Models Using Out-of-Distribution Samples (NeurIPS 2024), and
2) RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024).
Date: Wednesday Jan 8
Time: 1 pm
Location: SRIC-11 Minkowski Room (W1148)
Date: Wednesday Jan 8
Time: 1 pm
Location: SRIC-11 Minkowski Room (W1148)
A super cool explanation of recent LLM mechanistic interpretability studies from anthropic etc. from Welch Labs (an awesome channel btw).
see also "The Dark Matter of Neural Networks?" by @colah.bsky.social transformer-circuits.pub/2024/july-up...
A super cool explanation of recent LLM mechanistic interpretability studies from anthropic etc. from Welch Labs (an awesome channel btw).
see also "The Dark Matter of Neural Networks?" by @colah.bsky.social transformer-circuits.pub/2024/july-up...
www.cs.toronto.edu/~taati/journ...
www.cs.toronto.edu/~taati/journ...
www.cs.toronto.edu/~taati/journ...
www.cs.toronto.edu/~taati/journ...
cs.toronto.edu/~taati/journ...
Title: Unmasking Early Motor Deficits in Parkinson's Disease: Leveraging Machine Learning and Video-Based Analysis for Improved Detection and Disease Tracking
kite-uhn.com/talk/rounds-...
cs.toronto.edu/~taati/journ...
cs.toronto.edu/~taati/journ...
Title: Unmasking Early Motor Deficits in Parkinson's Disease: Leveraging Machine Learning and Video-Based Analysis for Improved Detection and Disease Tracking
kite-uhn.com/talk/rounds-...
Title: Unmasking Early Motor Deficits in Parkinson's Disease: Leveraging Machine Learning and Video-Based Analysis for Improved Detection and Disease Tracking
kite-uhn.com/talk/rounds-...