Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research interests include Advanced Neural Network Applications, Adversarial Robustness in Machine Learning, Domain Adaptation and Few-Shot Learning, and Generative Adversarial Networks and Image Synthesis.
Scaling Textual Gradients via Sampling-Based Momentum
Symbolic Visual Reinforcement Learning: A Scalable Framework With Object-Level Abstraction and Differentiable Expression Search
Neurosymbolic AI as an antithesis to scaling laws
FSGS: Real-Time Few-Shot View Synthesis Using Gaussian Splatting
A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression
DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
LLM-PBE: Assessing Data Privacy in Large Language Models
Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling
Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics
Neuro-Symbolic Computing: Advancements and Challenges in Hardware–Software Co-Design
Complex adaptive systems science in the era of global sustainability crisis
Turning A Curse into A Blessing: Data-Aware Memory-Efficient Training of Graph Neural Networks by Dynamic Exiting
One is Not Enough: Parameter-Efficient Fine-Tuning With Multiplicative Sparse Factorization
Severe aortic stenosis detection by deep learning applied to echocardiography
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
Improving model fairness in image-based computer-aided diagnosis
Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays
Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics
A Multi-Purpose Realistic Haze Benchmark With Quantifiable Haze Levels and Ground Truth
Search Behavior Prediction: A Hypergraph Perspective
Broad Spectrum Image Deblurring via an Adaptive Super-Network
SmartDeal: Remodeling Deep Network Weights for Efficient Inference and Training
Modeling user choice behavior under data corruption: Robust learning of the latent decision threshold model
Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
Taxonomy of Machine Learning Safety: A Survey and Primer
Scalable Perception-Action-Communication Loops With Convolutional and Graph Neural Networks
Collaborative Research: III: Medium: A consolidated framework of computational privacy and machine learning
Collaborative Research: Probabilistic, Geometric, and Topological Analysis of Neural Networks, From Theory to Applications
Collaborative Research: CCSS: Learning to Optimize: From New Algorithms to New Theory
RTML: Large: Collaborative: Harmonizing Predictive Algorithms and Mixed-Signal/Precision Circuits via Computation-Data Access Exchange and Adaptive Dataflows
Collaborative Research: Enabling Intelligent Cameras in Internet-of-Things via a Holistic Platform, Algorithm, and Hardware Co-design
CRII: RI: Learning with Low-Quality Visual Data: Handling Both Passive and Active Degradations
RTML: Large: Collaborative: Harmonizing Predictive Algorithms and Mixed-Signal/Precision Circuits via Computation-Data Access Exchange and Adaptive Dataflows
Collaborative Research: Enabling Intelligent Cameras in Internet-of-Things via a Holistic Platform, Algorithm, and Hardware Co-design
CRII: RI: Learning with Low-Quality Visual Data: Handling Both Passive and Active Degradations