DL Posts
-
Long Sequence Pretraining
-
CKConv: Continuous Kernel Convolution
-
Conditioned-RLFT
-
Direct Preference Optimization
-
Mamba: Selective State Space Model
-
S5 & Parallel Scan
-
H3: Hungry Hungry Hippo
-
S4D: Diagonal State Space Models
-
S4: Structured State Space Models
-
LSSL: Linear State-Space Layer
-
HiPPO & Sequential Data Compression
-
Legendre Memory Units
-
RNNs for Irregularly Spaced Time Series
-
Are Transformers Effective for Time Series?
-
Neural Network on Tabular Data
-
Instruction Tuning
-
Efficient Training of LLM
-
LLM Benchmark 2022-2023
-
ViT & Discrete Tokenization
-
LLM Benchmark 2018-2021
-
LLM As A Judge
-
Layout Language Model
-
Vision Language Pre-Training
-
Vision Transformer (ViT)
-
Positional Encoding
-
Parameter Efficient Fine-Tuning
-
Model Intrinsic Dimensionality
-
Text Embeddings I
-
Quantization: 8-bit
-
FlashAttention
-
Online Softmax
-
Multi-Head Attention Variants
-
LLM Scaling Law
-
LLM: 2022 Jan - 2023 Jun
-
Prompt Tuning
-
Prompt Engineering
-
LLM: CodeGen and FLAN
-
Early Open Source LLM
-
GPT Variants: Codex and InstructGPT
-
Forward-Forward Algorithm
-
GPT-1, GPT-2 and GPT-3
-
Pointer Networks
-
Normalization Layer
-
Transformer
-
Temporal Convolutional Network
-
Recurrent Neural Network
-
Speech Representation Learning
-
Contextual Word Embedding
-
Tokenization
-
Contrastive Learning
-
Self-Supervised Learning
-
Word Embedding
-
Transformer in Reinforcement Learning
-
DL Generalization
-
Attention Mechanism
-
Neural Loss Visualization
-
Learning Rate vs Batch Size
-
Residual Network
-
Dropout
-
Batch Normalization
-
Weight Initialization
-
Optimizer
-
Getting Started with Neural Network
-
Automatic Differentiation