43 citations · 119 across the 10 of their papers we have counts for
10 papers
UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
Sejoon Oh, Yiqiao Jin, Megha Sharma +4
Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are metic…
Adversarial Text Rewriting for Text-aware Recommender Systems
Sejoon Oh, Gaurav Verma, Srijan Kumar
Text-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users. The use of textual features helps mit…
FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning
Sejoon Oh, Berk Ustun, Julian McAuley +1
Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the…
Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
Gaurav Verma, Minje Choi, Kartik Sharma +3
Multimodal large language models (MLLMs) like LLaVA and GPT-4(V) enable general-purpose conversations about images with the language modality. As off-the-shelf MLLMs may have limit…
M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations
Walid Shalaby, Sejoon Oh, Amir Afsharinejad +2
Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since…
Implicit Session Contexts for Next-Item Recommendations
Sejoon Oh, Ankur Bhardwaj, Jongseok Han +3
Session-based recommender systems capture the short-term interest of a user within a session. Session contexts (i.e., a user's high-level interests or intents within a session) are…
Rank List Sensitivity of Recommender Systems to Interaction Perturbations
Sejoon Oh, Berk Ustun, Julian McAuley +1
Prediction models can exhibit sensitivity with respect to training data: small changes in the training data can produce models that assign conflicting predictions to individual dat…
Influence-guided Data Augmentation for Neural Tensor Completion
Sejoon Oh, Sungchul Kim, Ryan A. Rossi +1
How can we predict missing values in multi-dimensional data (or tensors) more accurately? The task of tensor completion is crucial in many applications such as personalized recomme…
GIFT: Guided and Interpretable Factorization for Tensors - An Application to Large-Scale Multi-platform Cancer Analysis
Jungwoo Lee, Sejoon Oh, Lee Sael
Given multi-platform genome data with prior knowledge of functional gene sets, how can we extract interpretable latent relationships between patients and genes? More specifically,…
Scalable Tucker Factorization for Sparse Tensors - Algorithms and Discoveries
Sejoon Oh, Namyong Park, Lee Sael +1
Given sparse multi-dimensional data (e.g., (user, movie, time; rating) for movie recommendations), how can we discover latent concepts/relations and predict missing values? Tucker…