PhD student launches ML reading group for top conference papers
Weekend deep dives into interpretability and robustness at ICML/ICLR/NeurIPS.
Deep Dive
A PhD student is organizing a weekend ML reading group focused on interpretability and robustness. They invite fellow PhD students or ML researchers interested in reading recent papers in depth to fill a Google Form to join and receive updates on meeting schedules.
Key Points
- Weekend meetings dedicated to recent papers from ICML, ICLR, and NeurIPS.
- Focus on interpretability and robustness in machine learning.
- Open to PhD students and ML researchers via a Google Form sign-up.
Why It Matters
Collaborative deep dives into interpretability and robustness papers accelerate understanding and innovation in critical AI safety areas.