Kevin Swersky

kswersky's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 6 months ago

Do generative video models learn physical principles from watching videos?

Paper • 2501.09038 • Published Jan 14 • 35

authored 2 papers about 1 year ago

Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models

Paper • 2405.16759 • Published May 27, 2024 • 8

Directly Fine-Tuning Diffusion Models on Differentiable Rewards

Paper • 2309.17400 • Published Sep 29, 2023 • 1

authored 2 papers over 1 year ago

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Paper • 2312.06585 • Published Dec 11, 2023 • 29

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

Paper • 2311.07587 • Published Nov 8, 2023 • 5