Mechanical Dreams
An automatically generated podcast about machine learning and natural language processing. The two fictional hosts talk about papers that I want to learn more about on my way to work.
It's not good, but it's useful.
- Update frequency
- every 2 days
- Average duration
- 10 minutes
- Episodes
- 80
- Years Active
- 2024 - 2025
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
00:09:07 |
Sun 09 Feb 2025
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
00:09:34 |
Fri 20 Dec 2024
Efficient and Approximate Per-Example Gradient Norms for Gradient Noise Scale
00:11:48 |
Fri 20 Dec 2024
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
00:11:58 |
Thu 12 Dec 2024
Model soups - averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
00:06:14 |
Mon 09 Dec 2024
Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
00:13:13 |
Fri 06 Dec 2024
Disclaimer: The podcast and artwork embedded on this page are the property of Mechanical Dirk. This content is not affiliated with or endorsed by eachpod.com.