1. EachPod
EachPod
Mechanical Dreams - Podcast

Mechanical Dreams

 Mechanical Dirk

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.

Science Natural Sciences
Update frequency
every 2 days
Average duration
10 minutes
Episodes
79
Years Active
2024 - 2025
Share to:
The Pitfalls of Next-Token Prediction

The Pitfalls of Next-Token Prediction

00:10:57  |   Thu 11 Sep 2025
Large Language Models and Games

Large Language Models and Games

00:17:01  |   Tue 09 Sep 2025
UQ - Assessing Language Models on Unsolved Questions

UQ - Assessing Language Models on Unsolved Questions

00:13:35  |   Fri 05 Sep 2025
Signal and Noise - A Framework for Reducing Uncertainty in Language Model Evaluation

Signal and Noise - A Framework for Reducing Uncertainty in Language Model Evaluation

00:14:19  |   Tue 19 Aug 2025
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training

Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training

00:14:42  |   Mon 18 Aug 2025
Thinking Like Transformers

Thinking Like Transformers

00:13:19  |   Tue 29 Jul 2025
Kimi K2

Kimi K2

00:13:28  |   Mon 28 Jul 2025
ERNIE Technical Report

ERNIE Technical Report

00:11:16  |   Fri 25 Jul 2025
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

00:14:30  |   Thu 24 Jul 2025
Gemini 2.5

Gemini 2.5

00:11:11  |   Fri 04 Jul 2025
How new data permeates LLM knowledge and how to dilute it

How new data permeates LLM knowledge and how to dilute it

00:11:17  |   Wed 18 Jun 2025
Harnessing the Universal Geometry of Embeddings

Harnessing the Universal Geometry of Embeddings

00:12:23  |   Tue 17 Jun 2025
Model Merging in Pre-training of Large Language Models

Model Merging in Pre-training of Large Language Models

00:10:56  |   Mon 16 Jun 2025
Learning Dynamics in Continual Pre-Training for Large Language Models

Learning Dynamics in Continual Pre-Training for Large Language Models

00:11:10  |   Fri 13 Jun 2025
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs

00:11:49  |   Thu 12 Jun 2025
Scalable-Softmax Is Superior for Attention

Scalable-Softmax Is Superior for Attention

00:10:20  |   Wed 11 Jun 2025
Breast Cancer Recurrence Prediction

Breast Cancer Recurrence Prediction

00:10:20  |   Fri 06 Jun 2025
Shareable artificial intelligence to extract cancer outcomes from electronic health records for precision oncology research

Shareable artificial intelligence to extract cancer outcomes from electronic health records for precision oncology research

00:10:27  |   Wed 04 Jun 2025
Native Sparse Attention

Native Sparse Attention

00:11:40  |   Wed 04 Jun 2025
Critical Batch Size Revisited

Critical Batch Size Revisited

00:10:57  |   Tue 03 Jun 2025
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.