Sebastian Dziadzio

sbdzdz

·

https://sebastiandziadzio.com/

AI & ML interests

Computer vision, continual learning, compositionality.

Recent Activity

liked a Space about 1 month ago

pollen-robotics/microduck-simulator

updated a dataset 3 months ago

bethgelab/revengebench

upvoted a paper 3 months ago

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

View all activity

Organizations

upvoted 3 papers 3 months ago

RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

Paper • 2606.26094 • Published Jun 24 • 1

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Paper • 2606.28551 • Published Jun 26 • 52

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

Paper • 2606.32034 • Published Jun 30 • 10

upvoted a paper over 1 year ago

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published Feb 6, 2025 • 32