Alert button
Picture for Kate Saenko

Kate Saenko

Alert button

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

Feb 01, 2024
Maan Qraitem, Nazia Tasnim, Kate Saenko, Bryan A. Plummer

Viaarxiv icon

SynCDR : Training Cross Domain Retrieval Models with Synthetic Data

Dec 31, 2023
Samarth Mishra, Kate Saenko, Venkatesh Saligrama

Viaarxiv icon

CLAMP: Contrastive LAnguage Model Prompt-tuning

Dec 04, 2023
Piotr Teterwak, Ximeng Sun, Bryan A. Plummer, Kate Saenko, Ser-Nam Lim

Viaarxiv icon

Learning to Compose SuperWeights for Neural Parameter Allocation Search

Dec 03, 2023
Piotr Teterwak, Soren Nelson, Nikoli Dryden, Dina Bashkirova, Kate Saenko, Bryan A. Plummer

Viaarxiv icon

Lasagna: Layered Score Distillation for Disentangled Object Relighting

Nov 30, 2023
Dina Bashkirova, Arijit Ray, Rupayan Mallick, Sarah Adel Bargal, Jianming Zhang, Ranjay Krishna, Kate Saenko

Viaarxiv icon

Video Frame Interpolation with Many-to-many Splatting and Spatial Selective Refinement

Oct 29, 2023
Ping Hu, Simon Niklaus, Lu Zhang, Stan Sclaroff, Kate Saenko

Viaarxiv icon

Socratis: Are large multimodal models emotionally aware?

Sep 05, 2023
Katherine Deng, Arijit Ray, Reuben Tan, Saadia Gabriel, Bryan A. Plummer, Kate Saenko

Figure 1 for Socratis: Are large multimodal models emotionally aware?
Figure 2 for Socratis: Are large multimodal models emotionally aware?
Figure 3 for Socratis: Are large multimodal models emotionally aware?
Figure 4 for Socratis: Are large multimodal models emotionally aware?
Viaarxiv icon

Label Budget Allocation in Multi-Task Learning

Aug 24, 2023
Ximeng Sun, Kihyuk Sohn, Kate Saenko, Clayton Mellina, Xiao Bian

Figure 1 for Label Budget Allocation in Multi-Task Learning
Figure 2 for Label Budget Allocation in Multi-Task Learning
Figure 3 for Label Budget Allocation in Multi-Task Learning
Figure 4 for Label Budget Allocation in Multi-Task Learning
Viaarxiv icon

From Fake to Real (FFR): A two-stage training pipeline for mitigating spurious correlations with synthetic data

Aug 08, 2023
Maan Qraitem, Kate Saenko, Bryan A. Plummer

Figure 1 for From Fake to Real (FFR): A two-stage training pipeline for mitigating spurious correlations with synthetic data
Figure 2 for From Fake to Real (FFR): A two-stage training pipeline for mitigating spurious correlations with synthetic data
Figure 3 for From Fake to Real (FFR): A two-stage training pipeline for mitigating spurious correlations with synthetic data
Viaarxiv icon