Subscribe to this Calendar for Event Updates
VAM! AI Reading Group - 🐋 DeepSeek's 🌀 mHC: Manifold Constrained Hyper Connections
1) 📄 Paper: mHC: Manifold Constrained Hyper Connections
3) Paper 3-line Summary: Let’s take a deep dive into one of the most interesting recent twists on a classic building block of attention networks: residual connections. Hyper-Connections expand these residual paths and unlock more expressivity, but they also bring training instability and significant memory overhead. DeepSeek’s mHC shows how to keep the benefits of hyper-connections while removing much of their cost and instability.
I recommend watching this video on the Manifold Hypothesis: https://www.youtube.com/watch?v=pdNYw6qwuNc
Recommended Action Item:
please message me if you would like to present an AI paper
to maximize engagement during the reading group, please try to read the paper in advance.
Want to present?
The list of papers will be available here: https://docs.google.com/spreadsheets/d/1HET5sjnHjwiF3IaCTipR_ZWspfgglqwdBFRWAfKBhp8/edit?usp=sharing
To connect with the group, join the Discord: https://discord.gg/teJvEejs94
Timeline:
🕠 7:00 PM – Arrival & Networking.
🗣️ 7:10 PM ~ 7:55 – Paper Presentation & Discussions
About the Facilitator
Issam Laradji is a Research Scientist at ServiceNow and an Adjunct Professor at University of British Columbia. He holds a PhD in Computer Science and a PhD from the University of British Columbia, and his research interests include natural language processing, computer vision, and large-scale optimization.
Looking forward to discussing the latest AI Papers!
Subscribe to this Calendar for Event Updates