Bethgelab

AI & ML interests

Foundation Models, Scaling Laws, Continual Pretraining, Data-centric ML, Neuroscience, Human-Machine comparisons

Recent Activity

lukasthede  published a dataset about 12 hours ago

bethgelab/MedKIT

lukasthede  updated a dataset about 18 hours ago

bethgelab/MedKIT

AmeyaPrabhu  authored a paper 18 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

View all activity

Papers

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

Personalizing Text-to-Image Generation to Individual Taste

View all Papers

Team members 18