NeurIPS 2024 Recap

Created on January 17, 2025

2025   ·   conference-update   ·   talks

Israel Mason-Williams and Nathalie Kirch present on thier time at NeurIPS 2024.

Abstract

This meeting discussed talks and papers at NeurIPS 2024 that Israel and Nathalie saw that are of interest to the group. The papers covered were: ‘Generalization: Shortcuts, Spuriousness, and Stability’, ‘Universal Convergence’, ‘Initialization in GNNs’ and ‘Ablation Schemes for Interpretability’.

References



    Enjoy Reading This Article?

    Here are some more articles you might like to read next:

  1. Agentic AI systems - Promises, Risks and the Paths Forward
  2. A Survey of Cognitive Distortion Detection and Classification in NLP
  3. Reproducibility The New Frontier in AI Governance
  4. The Biology of a Large Language Model (Anthropic)
  5. Reflections on The International AI Safety Report