Hyesu Lim's picture

6 1

Hyesu Lim

hyesulim

·

https://sites.google.com/view/hyesulim

AI & ML interests

None yet

Recent Activity

updated a model about 2 months ago

hyesulim/fastsae-models

published a model about 2 months ago

hyesulim/fastsae-models

updated a collection about 2 months ago

View all activity

Organizations

updated a model about 2 months ago

hyesulim/fastsae-models

published a model about 2 months ago

hyesulim/fastsae-models

updated a collection about 2 months ago

SAE

3 items • Updated Nov 4

upvoted 3 papers about 2 months ago

CytoSAE: Interpretable Cell Embeddings for Hematology

Paper • 2507.12464 • Published Jul 16 • 1

Sparse autoencoders reveal selective remapping of visual concepts during adaptation

Paper • 2412.05276 • Published Dec 6, 2024 • 1

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

Paper • 2510.26186 • Published Oct 30 • 2

upvoted a paper 2 months ago

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published Oct 18 • 48

upvoted a paper 5 months ago

DesignLab: Designing Slides Through Iterative Detection and Correction

Paper • 2507.17202 • Published Jul 23 • 50

liked a dataset 8 months ago

rayguan/HallusionBench

Updated Dec 10, 2023 • 1.09k • 5

updated a Space 9 months ago

Patchsae Demo

Explore image features using CLIP and MaPLE models

published a Space 9 months ago

Patchsae Demo

Explore image features using CLIP and MaPLE models

upvoted a paper about 1 year ago

Designing a Dashboard for Transparency and Control of Conversational AI

Paper • 2406.07882 • Published Jun 12, 2024 • 12

updated 2 Spaces about 1 year ago

Patchsae Demo

Explore image features using CLIP and MaPLE models

Patchsae Demo

Explore image features using CLIP and MaPLE models