Stanford Seminar - Decision Transformer: Reinforcement Learning via Sequence Modeling
Innovative approach to reinforcement learning using sequence modeling and Transformer architecture, offering simplicity and scalability while matching or exceeding state-of-the-art performance in various tasks.
Deep Generative Models - Autoregressive Models - Lecture 3
Explore autoregressive models in deep learning, focusing on their architecture, training, and applications in generating sequential data like text and images.
Distortion-Free Mechanisms for Language Model Provenance - Watermarking and Training Independence
Explore groundbreaking watermarking techniques and independence testing methods for language models, focusing on text generation provenance and model weight verification.
Time Series Class - Part 1 - Dr Ioannis Papastathopoulos, University of Edinburgh
Learn fundamental concepts and advanced techniques for analyzing time series data, including ARMA models, state-space models, and neural networks for forecasting and inference.
Time Series Class - Part 1 - Dr. Ioannis Papastathopoulos, University of Edinburgh
Learn fundamental concepts and advanced techniques in time series analysis, including ARMA models, state-space models, and neural networks for forecasting and inference.
Time Series Class - Part 2 - Professor Chris Williams, University of Edinburgh
Explore time series analysis, from moving average models to advanced state-space techniques and recurrent neural networks. Gain practical skills in parameter estimation, forecasting, and applying models to real-world data.
Autoregressive Long-Context Music Generation with Perceiver AR
Explore autoregressive long-context music generation using Perceiver AR, presented by DeepMind's Cătălina Cangea. Gain insights into cutting-edge AI techniques for creating music.
VQ-VAEs - Neural Discrete Representation Learning - Paper + PyTorch Code Explained
Explore VQ-VAEs for neural discrete representation learning, covering key concepts, implementation details, and applications in generative modeling. Gain insights into this important AI technique.
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Explore Parti, a groundbreaking autoregressive text-to-image model. Learn about its architecture, datasets, experimental results, and capabilities in generating realistic, accurate images from text prompts.
Imputer - Sequence Modelling via Imputation and Dynamic Programming
Explore a novel sequence-to-sequence model that balances efficiency and performance using imputation and dynamic programming for faster inference in various applications.
Normalizing Flows - Priyank Jaini
Explore normalizing flows, density estimation, and autoregressive models. Learn about change of variables, increasing triangular maps, and neural autoregressive flows.
Text to Image AI Models - Different Methodologies and How It Works
Explore various AI methodologies for text-to-image generation, including Autoregressive models, GANs, VQ-VAE Transformers, and Diffusion models. Learn their inner workings and compare advanced systems like DALL-E 2 and Google Imagen.
Tractable Control for Autoregressive Language Generation
Explores using tractable probabilistic models to impose lexical constraints in autoregressive text generation, achieving state-of-the-art performance on constrained text generation benchmarks.
Time Series Forecasting with Regression Model
Learn to implement regression models for long-term and short-term time series forecasting, focusing on trend and seasonality modeling and auto-regressive techniques using the AirPassengers dataset.
Understanding Text Generation Through Diffusion Models - From Theory to Implementation
Dive into discrete diffusion modeling for text generation, exploring probability distributions, score-based modeling, and practical applications in generative AI that rival GPT-2's capabilities.
The Continuous Language of Protein Structure
Explore a novel approach to protein structure generation using continuous autoregressive language models. Learn about innovative techniques for in silico protein design and their potential applications.
Robust Distortion-free Watermarks for Language Models
Explore robust watermarking techniques for language models, focusing on edit-resistant methods that preserve text distribution. Learn about key-based protocols and their applications.
Deep Generative Models - Lectures 2 and 3
Explore advanced deep generative models with expert insights on latest techniques, applications, and theoretical foundations in probabilistic AI.
Deep Generative Models 1 - Lecture
Explore deep generative models with experts, covering fundamental concepts and advanced techniques in probabilistic AI. Gain insights into cutting-edge research and applications.
Adaptive Data Collection via Autoregressive Generation in News Recommendation Systems
Discover how autoregressive models can enhance adaptive data collection and decision-making through Thompson sampling, with applications in news recommendation systems and cold-start problems.