Pin-Yu Chen

ImReasoner: Improving Memory-based Language Models for Reasoning-in-a-Haystack Tasks ACL 2026 MegaCoin: Enhancing Medium-Grained Color Perception for Vision-Language Models AAAI 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness WACV 2026 RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems ACL 2026 ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval ACL 2026 When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers ICLR 2025 Revisiting Mode Connectivity in Neural Networks with Bezier Surface ICLR 2025 DiffuseKronA: A Parameter Efficient Fine-Tuning Method for Personalized Diffusion Models WACV 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025 Retention Score: Quantifying Jailbreak Risks for Vision Language Models AAAI 2025 TabWak: A Watermark for Tabular Diffusion Models ICLR 2025 Attention Tracker: Detecting Prompt Injection Attacks in LLMs NAACL 2025 SPARC: An AI-Based Speech Processing and Real-Time Correction System IJCAI 2025 Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs ACL 2025 Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks ACL 2025 Large Language Models can Become Strong Self-Detoxifiers ICLR 2025 Differentiable Prompt Learning for Vision Language Models IJCAI 2025 STAR: Spectral Truncation and Rescale for Model Merging NAACL 2025 PSBD: Prediction Shift Uncertainty Unlocks Backdoor Detection CVPR 2025 SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection ICLR 2025 REFINE: Inversion-Free Backdoor Defense via Model Reprogramming ICLR 2025 Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis ICLR 2025 Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge ICLR 2025 A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts ICML 2024 It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition ICLR 2024 Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where WACV 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning AAAI 2024 A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques ACL 2024 Duwak: Dual Watermarks in Large Language Models ACL 2024 AutoVP: An Automated Visual Prompting Framework and Benchmark ICLR 2024 Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts ICML 2024 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models ICLR 2024 Large Language Models are Efficient Learners of Noise-Robust Speech Recognition ICLR 2024 Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models? ICLR 2024 Language Agnostic Code Embeddings NAACL 2024 Overload: Latency Attacks on Object Detection for Edge Devices CVPR 2024 Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective ICLR 2024 The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models ICLR 2024 Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR 2024 Computational Complexity of Verifying the Group No-show Paradox IJCAI 2024 Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models NIPS 2024 GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models NIPS 2024 NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes NIPS 2024 Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models NIPS 2024 Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models NIPS 2024 Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes NIPS 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning ICML 2024 Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series ICML 2024 What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding ICML 2024 How Do Nonlinear Transformers Learn and Generalize in In-Context Learning? ICML 2024 What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks ICML 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 Be Your Own Neighborhood: Detecting Adversarial Examples by the Neighborhood Relations Built on Self-Supervised Learning ICML 2024 Larimar: Large Language Models with Episodic Memory Control ICML 2024 Learning to Design Fair and Private Voting Rules (Extended Abstract) IJCAI 2023 Uncovering and Quantifying Social Biases in Code Generation NIPS 2023 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration NIPS 2023 RADAR: Robust AI-Text Detection via Adversarial Learning NIPS 2023 HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models NIPS 2023 VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models NIPS 2023 When Neural Networks Fail to Generalize? A Model Sensitivity Perspective AAAI 2023 Holistic Adversarial Robustness of Deep Learning Models AAAI 2023 NCTV: Neural Clamping Toolkit and Visualization for Neural Network Calibration AAAI 2023 Convex Bounds on the Softmax Function with Applications to Robustness Verification AISTATS 2023 Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations CVPR 2023 How to Backdoor Diffusion Models? CVPR 2023 Understanding and Improving Visual Prompting: A Label-Mapping Perspective CVPR 2023 Locally Differentially Private Document Generation Using Zero Shot Prompting EMNLP 2023 Exploring the Benefits of Visual Prompting in Differential Privacy ICCV 2023 Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification ICCV 2023 Robust Mixture-of-Expert Training for Convolutional Neural Networks ICCV 2023 FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning ICLR 2023 A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity ICLR 2023 Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks ICLR 2023 Identification of the Adversary from a Single Adversarial Example ICML 2023 Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks ICML 2023 MultiRobustBench: Benchmarking Robustness Against Multiple Attacks ICML 2023 Reprogramming Pretrained Language Models for Antibody Sequence Infilling ICML 2023 Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression ICML 2023 Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous Data ICML 2023 Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition INTERSPEECH 2023 Pessimistic Model Selection for Offline Deep Reinforcement Learning UAI 2023 Treatment Learning Causal Transformer for Noisy Image Classification WACV 2023 Adversarial Examples Can Be Effective Data Augmentation for Unsupervised Machine Learning AAAI 2022 Vision Transformers Are Robust Learners AAAI 2022 Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness ICML 2022 Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning ICML 2022 Distributed adversarial training to robustify deep neural networks at scale UAI 2022 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction NAACL 2022 A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness ECCV 2022 Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis NIPS 2022 CARBEN: Composite Adversarial Robustness Benchmark IJCAI 2022 Auto-Transfer: Learning to Route Transferable Representations ICLR 2022 Towards Creativity Characterization of Generative Models via Group-Based Subset Scanning IJCAI 2022 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 MAML is a Noisy Contrastive Learner in Classification ICLR 2022 How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis ICLR 2022 Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling ICML 2022 Revisiting Contrastive Learning through the Lens of Neighborhood Component Analysis: an Integrated Framework ICML 2022 SenSE: A Toolkit for Semantic Change Exploration via Word Embedding Alignment AAAI 2022 AI Explainability 360: Impact and Design AAAI 2022 Training a Resilient Q-network against Observational Interference AAAI 2022 Zeroth-Order Optimization for Composite Problems with Functional Constraints AAAI 2022 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning ICLR 2021 How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021 Hidden Cost of Randomized Smoothing AISTATS 2021 Rate-improved inexact augmented Lagrangian method for constrained nonconvex optimization AISTATS 2021 Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design ICML 2021 CRFL: Certifiably Robust Federated Learning against Backdoor Attacks ICML 2021 Voice2Series: Reprogramming Acoustic Models for Time Series Classification ICML 2021 Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination NIPS 2021 Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks NIPS 2021 CAFE: Catastrophic Data Leakage in Vertical Federated Learning NIPS 2021 Fake it Till You Make it: Self-Supervised Semantic Shifts for Monolingual Word Embedding Tasks AAAI 2021 Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning AAAI 2021 Self-Progressing Robust Training AAAI 2021 Fast Training of Provably Robust Neural Networks by SingleProp AAAI 2021 Characteristic Examples: High-Robustness, Low-Transferability Fingerprinting of Neural Networks IJCAI 2021 When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? NIPS 2021 Predicting Deep Neural Network Generalization with Perturbation Response Curves NIPS 2021 Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NIPS 2021 Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning NIPS 2021 Adversarial Attack Generation Empowered by Min-Max Optimization NIPS 2021 ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training NIPS 2020 SChME at SemEval-2020 Task 1: A Model Ensemble for Detecting Lexical Semantic Change SEMEVAL 2020 Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent AAAI 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples AAAI 2020 Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States AAAI 2020 Toward a neuro-inspired creative decoder IJCAI 2020 SChME at SemEval-2020 Task 1: A Model Ensemble for Detecting Lexical Semantic Change COLING 2020 Towards Verifying Robustness of Neural Networks Against A Family of Semantic Perturbations CVPR 2020 Adversarial T-shirt! Evading Person Detectors in A Physical World ECCV 2020 DBA: Distributed Backdoor Attacks against Federated Learning ICLR 2020 Higher-Order Certification For Randomized Smoothing NIPS 2020 AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models JMLR 2020 Proper Network Interpretability Helps Adversarial Robustness in Classification ICML 2020 Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing ICML 2020 Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources ICML 2020 Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case ICML 2020 Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases ECCV 2020 Sign-OPT: A Query-Efficient Hard-label Adversarial Attack ICLR 2020 Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness ICLR 2020 Optimizing Mode Connectivity via Neuron Alignment NIPS 2020 TemPEST: Soft Template-Based Personalized EDM Subject Generation through Collaborative Summarization AAAI 2020 On the Design of Black-Box Adversarial Examples by Leveraging Gradient-Free Optimization and Operator Splitting Method ICCV 2019 Characterizing Audio Adversarial Examples Using Temporal Dependency ICLR 2019 Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach ICLR 2019 signSGD via Zeroth-Order Oracle ICLR 2019 PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach ICML 2019 Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications ICML 2019 CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks AAAI 2019 AutoZOOM: Autoencoder-Based Zeroth Order Optimization Method for Attacking Black-Box Neural Networks AAAI 2019 Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective IJCAI 2019 Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses IJCAI 2019 Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019 Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization NIPS 2018 Word Mover’s Embedding: From Word2Vec to Document Embedding EMNLP 2018 Efficient Neural Network Robustness Certification with General Activation Functions NIPS 2018 Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning ACL 2018 Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach ICLR 2018 Zeroth-Order Online Alternating Direction Method of Multipliers: Convergence Analysis and Applications AISTATS 2018 Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives NIPS 2018 Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models ECCV 2018