Skip to main content
Alexander Wan's user avatar
Alexander Wan's user avatar
Alexander Wan's user avatar
Alexander Wan
  • Member for 9 months
  • Last seen this week
0 votes

Are there transformer-based architectures that can produce fixed-length vector encodings given arbitrary-length text documents?

1 vote

What is an "inference kernel"?

1 vote

How are sentences turned into a vector in LLM

1 vote

What technique is used for training Large Language Models like GPT?

2 votes
Accepted

Why does the latent space in Stable Diffusion have a shape of 64x64x3?

1 vote
Accepted

Attention with Recurrent Neural Networks

1 vote
Accepted

Why is generative QA + RAG so popular when extractive QA models exist that can provide factual information?

1 vote

Handling Variable Output Token Dimensionality in Transformer Decoders During Inference

2 votes
Accepted

How the "quantizantion" of models does work?

1 vote

Why use learning rate schedules if weight updates automatically decrease when approaching local optimal?

0 votes

Are LLM parameters synonymous with dimensions?

1 vote
Accepted

Why is the sinusoidal model classified as absolute positional encoding in some literature?

1 vote
Accepted

Navigating encoder-only text/sentence embedding models

1 vote
Accepted

Overcoming the quadratic scaling in transformer architecture

1 vote

How to Create a 1D Embedding from Tensors of Varying Sizes?

1 vote
Accepted

In the paper "LLM in a flash," what is meant by an up projection or down projection layer?

1 vote
Accepted

Why does skip-gram uses linear maps for embedding?

0 votes

Is there any variant of perceptron convergence algorithm that ensures uniqueness?

0 votes

Data out of scale

0 votes

From where do the Encoders in Transformers gets Input Embedding from?

2 votes
Accepted

What is $\mathbf{S}$ (sample covariance matrix) in image compression based on PCA?

1 vote
Accepted

What are the formulas for the MAE , MSE when output is a vector?

3 votes
Accepted

How to train a sample weight model for another ML model?

1 vote

Where does 0.2023 for normalization on cifar10 come from?

3 votes
Accepted

Aren't context lengths for transformers an artificial restriction?

0 votes

Smaller, competitive LLMs that are not autoregressive transformers?

1 vote

How to train a seq2seq model to rephrase input text following given rules

1 vote

Forum to discuss deep learning ideas

0 votes

Justification of Scaling in Classifier-Free Guidance in Diffusion Models

1 vote
Accepted

Keywords extractions from short names (table and column names)