Demystify ML

Dec 24, 20234 min read

A Model that Retrieves Documents When in Doubt

Summary of Active retrieval augmented generation paper

Training MNIST with MLX on Apple Silicon
Dec 18, 20233 min read
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks
Jul 31, 20233 min read
LLaMA: Open and Efficient Foundation Language Models
Jul 25, 20232 min read
DeiT: Data-Efficient Image Transformer
Jul 10, 20233 min read

DeBERTa-v3: Mastering Language Comprehension with Disentangled Attention and GAN-inspired Training
The Powerful Fusion of DeBERTa and ELECTRA
Jul 3, 20233 min read
DeBERTa: Enhancing Token Positioning Awareness in BERT
Leveraging Positional Information for Improved Language Understanding
Jun 26, 20234 min read
DiT: Unlocking Document Understanding with Unsupervised Pretraining
Alternative Pretraining Models Beyond VGG/ResNet
Jun 12, 20236 min read
Wav2Vec 2.0 Model for Cross-Lingual Phoneme Recognition
A Model for recognizing phoneme of different languages
May 8, 20233 min read
Demystifying Tensorflow Data
Setup preprocessing pipeline with tf.data
May 1, 20234 min read
Efficient Convolutional Neural Network with MobileNet
Reduce CNN operations with depth-wise and point-wise convolutions
Apr 24, 20232 min read