Presentations
Research paper walkthroughs.
The Llama 3 Herd of Models: Part 1
The Unreasonable Ineffectiveness of the Deeper Layers
MoAI: Mixture of All Intelligence
Mamba Architecture
Sparks of AGI: Early experiments with GPT-4
A Survey on LLM-based Autonomous Agents
How close is ChatGPT to Human Experts?
OpenAI Assistant API and function calling
RLHF and InstructGPT
Open-domain QA using Dense Retrievers
Marginal log likelihood
Open Retrieval Question Answering (ORQA)
Retrieval Augmented Generation (RAG)
Dense Passage Retrieval (DPR): End to End QA System
Inverse Cloze Task
Dense Passage Retriever (DPR)
Retrieval Augmented Language Model Pre-training (REALM)