Paper reading club:
language models + acid

When: 17 Feb Friday 19:00-22:00
Lang: RU
Where: main room

Topics:
- key papers on in-context/zero-shot learning i.e. using language models with minimal finetuning and an instruction finetuning approach to prompt engineering
- a synthesis of hierarchical predictive processing, a default brain function model, and the entropic brain hypothesis, a model of psychedelics action

Papers of the day:
Finetuned Language Models Are Zero-Shot Learners
Multitask Prompted Training Enables Zero-Shot Task Generalization
Training language models to follow instructions with human feedback
Improving alignment of dialogue agents via targeted human judgements
Scaling Instruction-Finetuned Language Models
REBUS and the Anarchic Brain: Toward a Unified Model of the Brain Action of Psychedelics

Read the papers and come discuss them!

Shall you get stuck as you read, pop over to our chat — we’ll try to help.

Event co-organized by F0 and paper reading club.