Haohan Wang

Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization EACL 2026 Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models CVPR 2026 Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain ACL 2026 Learning to Select Visual Tools from Experience CVPR 2026 Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models EACL 2026 Query-Efficient Domain Knowledge Stealing Against Large Language Models AAAI 2026 An Investigation on LLMs' Visual Understanding Ability using SVG for Image-Text Bridging WACV 2025 Customizing Domain Adapters for Domain Generalization ICCV 2025 Dataset Distillation via the Wasserstein Metric ICCV 2025 Examining Alignment of Large Language Models through Representative Heuristics: the case of political stereotypes ICLR 2025 Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation EMNLP 2025 Improving Noise Efficiency in Privacy-preserving Dataset Distillation ICCV 2025 Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization ICML 2025 Towards Adversarially Robust Dataset Distillation by Curvature Regularization AAAI 2025 CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing ECCV 2024 EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models ECCV 2024 Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models ICLR 2024 Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters NeurIPS 2024 Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models ICML 2024 MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification EMNLP 2024 Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NeurIPS 2024 Simple Unsupervised Knowledge Distillation With Space Similarity ECCV 2024 Towards Reliable Advertising Image Generation Using Human Feedback ECCV 2024 Adaptive Test-Time Personalization for Federated Learning NeurIPS 2023 A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance ICCV 2023 Calibrated Teacher for Sparsely Annotated Object Detection AAAI 2023 Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models NeurIPS 2023 Optimizing the Collaboration Structure in Cross-Silo Federated Learning ICML 2023 Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection AAAI 2023 Iterative Few-shot Semantic Segmentation from Image Label Text IJCAI 2022 Measure and Improve Robustness in NLP Models: A Survey NAACL 2022 The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization CVPR 2022 Toward learning human-aligned cross-domain robust models by countering misaligned features UAI 2022 Robust Contrastive Learning Using Negative Samples with Diminished Semantics NeurIPS 2021 High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks CVPR 2020 Self-Challenging Improves Cross-Domain Generalization ECCV 2020 Learning Robust Global Representations by Penalizing Local Predictive Power NeurIPS 2019 Learning Robust Representations by Projecting Superficial Statistics Out ICLR 2019 Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual EMNLP 2019 What if We Simply Swap the Two Text Fragments? A Straightforward yet Effective Way to Test the Robustness of Methods to Confounding Signals in Nature Language Inference Tasks AAAI 2019