Why Vector Based Personalization is Better Than Its Alternatives

Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks

LLM-Rec: Personalized Recommendation via Prompting Large Language Models

Causal Inference for Recommender Systems

D2K: Turning Historical Data into Retrievable Knowledge for Recommender Systems

Knowledge Interface Between Humans and AI

In-context Learning with Retrieved Demonstrations for Language Models: A Survey

What is Retrieval-Augmented Generation (RAG)

User Embedding Model for Personalized Language Prompting

Efficient LLM Inference CPUs

Mixtral of Experts

WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs

Unlocking the Potential of AI Chatbots: The Role of Prompt Engineering

Some Yann LeCun Talks

Harnessing LLMs for the Next Wave of Consumer Experiences

Artificial Intelligence Techniques Applied to Cryptocurrency Market Prediction

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Deep Residual Learning for Image Recognition

Long short-term memory

Andreesen Horowitz—written evidence on Large Language Models: House of Lords Communications and Digital Select Committee inquiry

Adam: A Method for Stochastic Optimization

Text Embeddings Reveal (Almost) As Much As Text

Computing Machinery and Intelligence - A. M. Turing (1950)

Artificial Intelligence: A Guide for Thinking Humans. - Melanie Mitchell

German RAG

Some Yann LeCun Talks (1988-2015)

Retrieval meets Long Context Large Language Models by NVIDIA