kim

dahyekim's activity

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

upvoted a paper 3 days ago

Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos

Paper • 2512.01803 • Published 9 days ago • 4

upvoted a paper 5 days ago

Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs

Paper • 2511.22826 • Published 13 days ago • 7

upvoted a paper 6 months ago

Revelio: Interpreting and leveraging semantic information in diffusion models

Paper • 2411.16725 • Published Nov 23, 2024 • 1

liked a Space 7 months ago

Sleeping

1

Steerers

🔥

1

Demo for https://github.com/kim-dahye/steerers

upvoted 2 papers 9 months ago

What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization

Paper • 2503.06698 • Published Mar 9 • 4

How to Steer LLM Latents for Hallucination Detection?

Paper • 2503.01917 • Published Mar 1 • 11

upvoted a paper 10 months ago

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

Paper • 2501.19066 • Published Jan 31 • 13

commented a paper 10 months ago

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

Paper • 2501.19066 • Published Jan 31 • 13 •

2

authored a paper 10 months ago

Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations

Paper • 2501.19066 • Published Jan 31 • 13

authored 2 papers about 1 year ago

$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models

Paper • 2411.16725 • Published Nov 23, 2024 • 1

Language-free Training for Zero-shot Video Grounding

Paper • 2210.12977 • Published Oct 24, 2022