Mechanical Dreams

By Mechanical DirkScience Natural Sciences

Mechanical Dreams episodes

December 12, 2024 Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
12 min
December 11, 2024 EXAONE 3.5
9 min
December 09, 2024 Model soups - averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
7 min
December 06, 2024 Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
14 min
December 05, 2024 Nemotron-CC
13 min
December 02, 2024 Tülu 3
13 min
November 29, 2024 The Zamba2 Suite
14 min
November 26, 2024 Small-scale proxies for large-scale Transformer training instabilities
11 min
November 25, 2024 Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training
I slightly tweaked the personality of the hosts.
11 min
November 19, 2024 Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
9 min

About Mechanical Dreams

From the publisher's feed

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,…

Share Mechanical Dreams

Sign up to save your podcasts

Mechanical Dreams

Mechanical Dreams episodes

About Mechanical Dreams