Seong Joon Oh

coallaoh's activity

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

upvoted a paper about 2 months ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4 • 266

upvoted 3 papers 2 months ago

Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution

Paper • 2510.18019 • Published Oct 20 • 17

Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published Oct 14 • 31

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Paper • 2510.07959 • Published Oct 9 • 14

upvoted a collection 4 months ago

🫗 Leaky Thoughts

Collection

Data of the "Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers" paper • 2 items • Updated Oct 15 • 1

upvoted a paper 6 months ago

On the rankability of visual embeddings

Paper • 2507.03683 • Published Jul 4 • 15

liked a dataset 6 months ago

parameterlab/c-seo-bench

Viewer • Updated Sep 28 • 16.4k • 110 • 3

authored 6 papers 7 months ago

Calibrating Large Language Models Using Their Generations Only

Paper • 2403.05973 • Published Mar 9, 2024 • 1

Do Deep Neural Network Solutions Form a Star Domain?

Paper • 2403.07968 • Published Mar 12, 2024

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Paper • 2411.00154 • Published Oct 31, 2024 • 1

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally

Paper • 2502.03566 • Published Feb 5 • 4

Intermediate Layer Classifiers for OOD generalization

Paper • 2504.05461 • Published Apr 7 • 1

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Paper • 2505.17955 • Published May 23 • 22

upvoted a paper 7 months ago

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Paper • 2505.17955 • Published May 23 • 22

upvoted a paper 9 months ago

Are We Done with Object-Centric Learning?

Paper • 2504.07092 • Published Apr 9 • 6

authored a paper 9 months ago

Are We Done with Object-Centric Learning?

Paper • 2504.07092 • Published Apr 9 • 6

liked a model about 1 year ago

haritzpuerto/LLaMA2-7B-dcot

Text Generation • Updated Jul 16, 2024 • 7 • 2

authored 3 papers almost 2 years ago

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Paper • 2402.12991 • Published Feb 20, 2024 • 1

Rethinking Spatial Dimensions of Vision Transformers

Paper • 2103.16302 • Published Mar 30, 2021 • 1

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

Paper • 1905.04899 • Published May 13, 2019