Area of research
Artificial Intelligence · Computer Vision and Pattern Recognition
Research interest
Research interests include Adversarial Robustness in Machine Learning, Advanced Neural Network Applications, Domain Adaptation and Few-Shot Learning, and Topic Modeling.
Uncertainty‐Guided Selective Adaptation Enables Cross‐Platform Predictive Fluorescence Microscopy
Generalized Transferable Attack Across Datasets
<scp>UniDEC</scp>
: Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
Matryoshka Model Learning for Improved Elastic Student Models
Red Teaming Language Model Detectors with Language Models
Understanding the Impact of Negative Prompts: When and How Do They Take Effect?
Gandalf: Learning Label-label Correlations in Extreme Multi-label Classification via Label Features
Adversarial Examples Detection With Bayesian Neural Network
PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models
Entity Disambiguation with Extreme Multi-label Ranking
Incorporating physics into data-driven computer vision
FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search
Training Meta-Surrogate Model for Transferable Adversarial Attack
NeSSA: Near-Storage Data Selection for Accelerated Machine Learning Training
Build Faster with Less: A Journey to Accelerate Sparse Model Building for Semantic Matching in Product Search
Uncertainty Quantification for Extreme Classification
Towards Efficient and Scalable Sharpness-Aware Minimization
A Review of Adversarial Attack and Defense for Classification Methods
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification
Neural Information Processing Systems 2021cited by 94position: middle
Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution
SSE-PT: Sequential Recommendation Via Personalized Transformer
What Does BERT with Vision Look At?
ML-LOO: Detecting Adversarial Examples with Feature Attribution
Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
Neural Information Processing Systems 2020cited by 27position: last
AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks
Rob-GAN: Generator, Discriminator, and Adversarial Attacker
On the Robustness of Self-Attentive Models
A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
Neural Information Processing Systems 2019cited by 75position: middle
Collaborative Research: EAGER: End-to-end Neural Training for Very Large Output Spaces
Collaborative Research: SLES: Verifying and Enforcing Safety Constraints in AI-based Sequential Generation
CAREER: Robustness Verification and Certified Defense for Machine Learning Models
RI: Small: Learning to Optimize: Designing and Improving Optimizers by Machine Learning Algorithms
RI: SMALL: Fast Prediction and Model Compression for Large-Scale Machine Learning
RI: SMALL: Fast Prediction and Model Compression for Large-Scale Machine Learning