Papers

Select a paper to start implementing.

Filter by:
NLPReasoning
2025

Less is More: Recursive Reasoning with Tiny Networks

Alexia Jolicoeur-Martineau

Recursive reasoning with tiny networks, focusing on latent state updates and answer refinement.

CVTransformer
2020

Vision Transformer (ViT)

Dosovitskiy et al.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale - applying Transformers directly to image patches for vision tasks.

RLReinforcement LearningDeep LearningQ-Learning
2015

Human-level Control through Deep Reinforcement Learning

Mnih, Kavukcuoglu et al.

Deep G-Network (DQN) combining G-learning with deep neural networks for end-to-end learning of action values from raw pixels.

OptimizationDeep LearningAdam
2014

Adam: A Method for Stochastic Optimization

Kingma, Ba

Adaptive moment estimation optimizer combining benefits of RMSProp and momentum, computing individual adaptive learning rates.

NLPRNN
1997

Long Short-Term Memory Networks

Hochreiter & Schmidhuber

Implementing core LSTM components from scratch: LSTM cells with gates, forward/backward passes, BPTT, initialization, dropout masks, packed sequences, bidirectional LSTMs, and full LSTM blocks.

CVGAN
2014

Generative Adversarial Networks

Goodfellow et al.

Framework for estimating generative models via an adversarial process.

NLPTransformer
2017

Attention Is All You Need

Vaswani et al.

The seminal transformer architecture replacing recurrence and convolutions entirely with self-attention mechanisms.

RLVAERNN
2018

World Models

Ha & Schmidhuber

Training generative neural network models of popular reinforcement learning environments to learn a compressed representation of the spatial and temporal aspects of the environment.

NLPRNN
1980

Recurrent Neural Networks

Hopfield et al.

Fundamental sequential processing architecture forming the basis of modern recurrent neural architectures.