
Explore hierarchical reinforcement learning using world graphs to accelerate learning in complex environments. Learn about pivotal states, goal-conditioned policies, and efficient task solving.

Explores the paradox of modern machine learning where complex models can generalize well despite overfitting, introducing the "double descent" risk curve that extends beyond the traditional bias-variance trade-off.

Explore population-based search and open-ended algorithms in AI, discussing key concepts and potential applications for advancing machine learning and artificial intelligence.

Explore stochastic non-autoregressive RNNs for unconditional word generation, based on deep state space models. Learn about innovative training techniques without teacher-forcing.

Explore generative neural network models for reinforcement learning environments, learning compressed representations and training agents in hallucinated dreams for efficient task-solving.

Explore how curiosity can be an intrinsic reward for agents in sparse-reward environments, using self-supervised prediction to enable efficient exploration and skill acquisition.

Explore innovative deep reinforcement learning architecture combining model-free and model-based approaches for improved performance and efficiency in complex environments.

Explore composite indexes and Faiss Index Factory for optimizing vector search performance, balancing recall, latency, and memory usage in similarity search applications.

Explore BERT's masked-language modeling technique for NLP tasks. Learn how this innovative approach trains the model to predict masked tokens, enhancing its understanding of language context.

Build an extractive Q&A system using Haystack, FastAPI, and BERT transformer. Implement Elasticsearch with BM25 retriever for efficient information retrieval and answer generation from text documents.

Explore AI alignment and OpenAssistant in this livestream. Yannic Kilcher discusses key concepts, challenges, and developments in the field of artificial intelligence alignment.

Comprehensive analysis of GPT-4's capabilities, improvements, and potential impact on AI technology, based on OpenAI's latest release and research findings.

Hands-on coding session building streaming inference into Hugging Face's text generation server, covering CUDA, Python, Rust, gRPC, WebSockets, and server-sent events for AI development.

Explore ChatGPT's capabilities, origins, and potential risks. Learn about its underlying technology, amazing features, and ways to bypass safety mechanisms, while considering OpenAI's vision for the future.

Explore Galactica, a language model for science. Learn about its capabilities, controversy, dataset construction, reasoning methods, and performance in various scientific tasks.

Explore the controversy surrounding Google's LaMDA chatbot and its alleged sentience. Analyze claims, examine language models, and delve into the philosophical questions of AI consciousness and recognition of machine sentience.

Explore sparse expert models in AI, discussing their architecture, routing, history, applications, and future potential. Learn about Switch Transformers, GLAM, and advancements in efficient large-scale language models.

Explore typical sampling, a new decoding method for language models that balances high-probability and high-information outputs, resulting in more diverse and interesting generated text.

Interview exploring BLIP, a versatile vision-language model that excels in both understanding and generation tasks. Discusses data bootstrapping, architecture evolution, and future directions in multi-modal AI research.

Explores OpenAI's innovative approach to formal mathematics using expert iteration, demonstrating improved performance in automated proof search and solving challenging olympiad-level problems.

Interview exploring EleutherAI's GPT-NeoX-20B, a 20B parameter open-source language model. Discusses training process, hardware acquisition, model capabilities, and how to try it out.