Cho-jui Hsieh

The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise ICLR 2025 Large Language Models are Interpretable Learners ICLR 2025 SeedLoRA: A Fusion Approach to Efficient LLM Fine-Tuning ICML 2025 An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning NAACL 2025 Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review ACL 2025 Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review CONLL 2025 OR-Bench: An Over-Refusal Benchmark for Large Language Models ICML 2025 QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models EMNLP 2025 LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization ICLR 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 Automatic Engineering of Long Prompts ACL 2024 MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering ACL 2024 Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding ICLR 2024 Combining Axes Preconditioners through Kronecker Approximation for Deep Learning ICLR 2024 Two-stage LLM Fine-tuning with Less Specialization and More Generalization ICLR 2024 Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns? EMNLP 2024 DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers EMNLP 2024 UNICORN: A Unified Causal Video-Oriented Language-Modeling Framework for Temporal Video-Language Tasks EMNLP 2024 When and How do negative prompts take effect? ECCV 2024 Defending LLMs against Jailbreaking Attacks via Backtranslation ACL 2024 Low-rank Matrix Bandits with Heavy-tailed Rewards UAI 2024 Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation ICML 2024 On Discrete Prompt Optimization for Diffusion Models ICML 2024 One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts ICML 2024 Ameliorate Spurious Correlations in Dataset Condensation ICML 2024 Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning ICML 2024 A Computationally Efficient Sparsified Online Newton Method NIPS 2023 Why Does Sharpness-Aware Minimization Generalize Better Than SGD? NIPS 2023 Symbolic Discovery of Optimization Algorithms NIPS 2023 FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning CVPR 2023 PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation ICML 2023 Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory ICML 2023 Representer Point Selection for Explaining Regularized High-dimensional Models ICML 2023 Training Meta-Surrogate Model for Transferable Adversarial Attack AAAI 2023 Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning (Student Abstract) AAAI 2023 Universality and Limitations of Prompt Tuning NIPS 2023 Effective Robustness against Natural Distribution Shifts for Models with Different Training Data NIPS 2023 Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization NIPS 2023 Serving Graph Compression for Graph Neural Networks ICLR 2023 Towards Robustness Certification Against Universal Perturbations ICLR 2023 Concept Gradient: Concept-based Interpretation Without Linear Assumption ICLR 2023 Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories ICLR 2023 Enhancing Unsupervised Semantic Parsing with Distributed Contextual Representations ACL 2023 Robust Lipschitz Bandits to Adversarial Corruptions NIPS 2023 ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation EMNLP 2022 DC-BENCH: Dataset Condensation Benchmark NIPS 2022 Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms NIPS 2022 General Cutting Planes for Bound-Propagation-Based Neural Network Verification NIPS 2022 Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation NIPS 2022 Are AlphaZero-like Agents Robust to Adversarial Perturbations? NIPS 2022 ELIAS: End-to-End Learning to Index and Search in Large Output Spaces NIPS 2022 Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems NIPS 2022 Random Sharpness-Aware Minimization NIPS 2022 Efficient Non-Parametric Optimizer Search for Diverse Tasks NIPS 2022 On the Sensitivity and Stability of Model Interpretations in NLP ACL 2022 Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples ACL 2022 Improving the Adversarial Robustness of NLP Models by Information Bottleneck ACL 2022 Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks AISTATS 2022 Towards Efficient and Scalable Sharpness-Aware Minimization CVPR 2022 Learning to Learn with Smooth Regularization ECCV 2022 Weight Perturbation as Defense against Adversarial Word Substitutions EMNLP 2022 On the Convergence of Certified Robust Training with Interval Bound Propagation ICLR 2022 Generalizing Few-Shot NAS with Gradient Matching ICLR 2022 Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction ICLR 2022 Concurrent Adversarial Learning for Large-Batch Training ICLR 2022 Learning to Schedule Learning rate with Graph Neural Networks ICLR 2022 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations ICLR 2022 A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks ICML 2022 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 Extreme Zero-Shot Learning for Extreme Text Classification NAACL 2022 Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble ACL 2021 Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble IJCNLP 2021 Overcoming Catastrophic Forgetting by Bayesian Generative Regularization ICML 2021 Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification NIPS 2021 Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation NAACL 2021 Robust and Accurate Object Detection via Adversarial Learning CVPR 2021 Label Disentanglement in Partition-based Extreme Multilabel Classification NIPS 2021 DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification NIPS 2021 DRONE: Data-aware Low-rank Compression for Large NLP Models NIPS 2021 On the Transferability of Adversarial Attacks against Neural Text Classifier EMNLP 2021 Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution EMNLP 2021 Multi-Proxy Wasserstein Classifier for Image Classification AAAI 2021 Fast Certified Robust Training with Short Warmup NIPS 2021 RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection ICCV 2021 Towards Robustness of Deep Neural Networks via Regularization ICCV 2021 RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving ICCV 2021 Self-Progressing Robust Training AAAI 2021 An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling AISTATS 2021 Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search AAAI 2021 Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding NIPS 2021 Robust Reinforcement Learning on State Observations with Learned Optimal Adversary ICLR 2021 Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers ICLR 2021 DrNAS: Dirichlet Neural Architecture Search ICLR 2021 Evaluations and Methods for Explanation through Robustness Analysis ICLR 2021 Rethinking Architecture Selection in Differentiable NAS ICLR 2021 Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations NIPS 2020 Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data JMLR 2020 Provably Robust Metric Learning NIPS 2020 Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data NIPS 2020 An Efficient Adversarial Attack for Tree Ensembles NIPS 2020 Multi-Stage Influence Function NIPS 2020 Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond NIPS 2020 How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework CVPR 2020 MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius ICLR 2020 Evaluating and Enhancing the Robustness of Neural Network-based Dependency Parsing Models with Adversarial Examples ACL 2020 Large Batch Optimization for Deep Learning: Training BERT in 76 minutes ICLR 2020 What Does BERT with Vision Look At? ACL 2020 On Lp-norm Robustness of Ensemble Decision Stumps and Trees ICML 2020 Learning to Encode Position for Transformer with Continuous Dynamical Model ICML 2020 Stabilizing Differentiable Architecture Search via Perturbation-based Regularization ICML 2020 Improved Adversarial Training via Learned Optimizer ECCV 2020 MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation ECCV 2020 Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples AAAI 2020 Robustness Verification for Transformers ICLR 2020 Towards Stable and Efficient Training of Verifiably Robust Neural Networks ICLR 2020 Learning to Learn by Zeroth-Order Oracle ICLR 2020 Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering AISTATS 2020 ML-LOO: Detecting Adversarial Examples with Feature Attribution AAAI 2020 Sign-OPT: A Query-Efficient Hard-label Adversarial Attack ICLR 2020 AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks AAAI 2019 Parallel Asynchronous Stochastic Coordinate Descent with Auxiliary Variables AISTATS 2019 A Fast Sampling Algorithm for Maximum Inner Product Search AISTATS 2019 Rob-GAN: Generator, Discriminator, and Adversarial Attacker CVPR 2019 MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model EMNLP 2019 Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks ICCV 2019 The Limitations of Adversarial Training and the Blind-Spot Attack ICLR 2019 Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks ICLR 2019 Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach ICLR 2019 Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network ICLR 2019 Evaluating and Enhancing the Robustness of Dialogue Systems: A Case Study on a Negotiation Agent NAACL 2019 Robustness Verification of Tree-based Models NIPS 2019 A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning NIPS 2019 Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers NIPS 2019 Convergence of Adversarial Training in Overparametrized Neural Networks NIPS 2019 A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks NIPS 2019 Robust Decision Trees Against Adversarial Examples ICML 2019 MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model IJCNLP 2019 On the Robustness of Self-Attentive Models ACL 2019 RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications AAAI 2019 Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning ACL 2018 Using Side Information to Reliably Learn Low-Rank Matrices from Missing and Corrupted Observations JMLR 2018 Extreme Learning to Rank via Low Rank Assumption ICML 2018 Fast Variance Reduction Method with Stochastic Batch Size ICML 2018 Towards Fast Computation of Certified Robustness for ReLU Networks ICML 2018 SQL-Rank: A Listwise Approach to Collaborative Ranking ICML 2018 Learning from Group Comparisons: Exploiting Higher Order Interactions NIPS 2018 GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking NIPS 2018 Efficient Neural Network Robustness Certification with General Activation Functions NIPS 2018 Learning Word Embeddings for Low-Resource Languages by PU Learning NAACL 2018 Towards Robust Neural Networks via Random Self-ensemble ECCV 2018 Distributed Primal-Dual Optimization for Non-uniformly Distributed Data IJCAI 2018 Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach ICLR 2018 Rank Aggregation and Prediction with Item Features AISTATS 2017 Scalable Demand-Aware Recommendation NIPS 2017 Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent NIPS 2017 Memory Efficient Kernel Approximation JMLR 2017 A Greedy Approach for Budgeted Maximum Inner Product Search NIPS 2017 Improved Bounded Matrix Completion for Large-Scale Recommender Systems IJCAI 2017 Gradient Boosted Decision Trees for High Dimensional Sparse Output ICML 2017 A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order NIPS 2016 Computationally Efficient Nyström Approximation using Fast Transforms ICML 2016 Asynchronous Parallel Greedy Coordinate Descent NIPS 2016 Robust Principal Component Analysis with Side Information ICML 2016 Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent NIPS 2015 PU Learning for Matrix Completion ICML 2015 PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent ICML 2015 Matrix Completion with Noisy Side Information NIPS 2015 QUIC & DIRTY: A Quadratic Approximation Approach for Dirty Statistical Models NIPS 2014 Constant Nullspace Strong Convexity and Fast Convergence of Proximal Methods under High-Dimensional Settings NIPS 2014 Fast Prediction for Large-Scale Kernel Machines NIPS 2014 QUIC: Quadratic Approximation for Sparse Inverse Covariance Estimation JMLR 2014 Prediction and Clustering in Signed Networks: A Local to Global Perspective JMLR 2014 A Divide-and-Conquer Solver for Kernel Support Vector Machines ICML 2014 Nuclear Norm Minimization via Active Subspace Selection ICML 2014 Memory Efficient Kernel Approximation ICML 2014 Large Scale Distributed Sparse Precision Estimation NIPS 2013 BIG & QUIC: Sparse Inverse Covariance Estimation for a Million Variables NIPS 2013 A Divide-and-Conquer Method for Sparse Inverse Covariance Estimation NIPS 2012 Sparse Inverse Covariance Matrix Estimation Using Quadratic Approximation NIPS 2011 A Comparison of Optimization Methods and Software for Large-scale L1-regularized Linear Classification JMLR 2010 Training and Testing Low-degree Polynomial Data Mappings via Linear SVM JMLR 2010 Iterative Scaling and Coordinate Descent Methods for Maximum Entropy Models JMLR 2010 Iterative Scaling and Coordinate Descent Methods for Maximum Entropy ACL 2009 Iterative Scaling and Coordinate Descent Methods for Maximum Entropy IJCNLP 2009 Coordinate Descent Method for Large-scale L2-loss Linear Support Vector Machines JMLR 2008 LIBLINEAR: A Library for Large Linear Classification JMLR 2008