|
|
|
Research Interests
- Deep generative modeling, trustworthy AI, and multimodal foundation models.
- Controllability of model behavior, evaluation of model robustness, and better interpretability frameworks.
- Curation of more informative and comprehensive data for robust, performant, and efficient model reasoning.
Recent Works
- Full publication list can be found in Google Scholar.
 |
Concept Lancet: Image Editing with Compositional Representation Transplant |
|
 |
PaCE: Parsimonious Concept Engineering for Large Language Models |
|
 |
Zero-shot Model Diagnosis |
|
 |
LogiCity: Advancing Neural-Symbolic AI with Abstract Urban Simulation |
|
 |
Recent Advances in Adversarial Training for Adversarial Robustness |
|
 |
A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization |
|
 |
ActivityGAN: Data Augmentation in Sensor-Based Human Activity Recognition |
|
 |
Contextual Knowledge Pursuit for Faithful Visual Synthesis |
|
 |
Generating Adversarial yet Inconspicuous Patches with a Single Image |
Services and Activities
- Conference Reviewer: CVPR, NeurIPS, ICLR, NeurIPS DB Track, ICML, ICCV, EMNLP, AISTATS, AAAI, ECCV.
- Journal Reviewer: Neurocomputing, TMLR, TNNLS.
- Organizer: ICLR FM-Wild Workshop.
- Teaching Assistant: [Penn 23Fall] Deep Generative Models (Founding Members). [Penn 24Fall] Deep Generative Models.