|
What can be done with 3000 random images and their short descriptions?
|
|
6
|
7
|
September 25, 2024
|
|
How to Identify Bad Datasets Before Building Models?
|
|
5
|
6
|
September 25, 2024
|
|
NeurIPS 2024 Decisions
|
|
4
|
6
|
September 25, 2024
|
|
If adversarial learning studies suggest neural networks can be quite fragile to input / weight perturbations, why does quantisation work at all?
|
|
5
|
6
|
September 25, 2024
|
|
Good Graph Database options?
|
|
4
|
8
|
September 25, 2024
|
|
What are the top 3 countries in development of AI model besides America and China?
|
|
5
|
6
|
September 23, 2024
|
|
Planning on building 7x RTX4090 rig. Any tips?
|
|
5
|
6
|
September 23, 2024
|
|
Swapping Embedding Models for an LLM
|
|
3
|
5
|
September 20, 2024
|
|
Interview experience at OpenAI
|
|
8
|
11
|
September 19, 2024
|
|
Mojo / Modular, has anyone used it in a real project?
|
|
10
|
11
|
September 19, 2024
|
|
Torch.function vs torch.nn.functional.function?
|
|
8
|
9
|
September 19, 2024
|
|
An Intuitive Explanation of How LLMs Work
|
|
7
|
9
|
September 19, 2024
|
|
Built gpt2 in C
|
|
5
|
6
|
September 18, 2024
|
|
Breaking down PyTorch functions helped me with understanding what happens under the hood
|
|
3
|
5
|
September 18, 2024
|
|
What Tools Do You Use for AI/ML Development, Training, and Inference?
|
|
5
|
6
|
September 18, 2024
|
|
Audio classification
|
|
9
|
9
|
September 16, 2024
|
|
Why are most Federated Learning methods so dependent on hyperparameters?
|
|
7
|
10
|
September 16, 2024
|
|
Machine learning system design
|
|
8
|
9
|
September 16, 2024
|
|
What makes working with data so hard for ML?
|
|
1
|
2
|
September 16, 2024
|
|
What is the point of encoder only models like bert and roberta anymore?
|
|
5
|
6
|
September 13, 2024
|
|
How to Efficiently Store Pruned Weight Matrices in Practice?
|
|
5
|
7
|
September 13, 2024
|
|
ML Career paths that actually do good and/or make a difference
|
|
7
|
9
|
September 13, 2024
|
|
OpenAI new reasoning model called o10
|
|
7
|
8
|
September 13, 2024
|
|
Why is CUDA so much faster than ROCm?
|
|
5
|
8
|
September 11, 2024
|
|
TensorHue – a tensor visualization library
|
|
5
|
12
|
September 11, 2024
|
|
Implementing papers worth?
|
|
6
|
8
|
September 11, 2024
|
|
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
|
|
7
|
9
|
September 11, 2024
|
|
What if self-attention isn’t the end-all be-all?
|
|
9
|
14
|
September 10, 2024
|
|
Transformers Trainer vs Pytorch Lighting
|
|
9
|
13
|
September 10, 2024
|
|
Which LLM model is best for getting Text-to-SQL to work right?
|
|
10
|
15
|
September 10, 2024
|