Han Qiu

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ACL 2026 New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs ACL 2026 Revisiting the Reliability of Language Models in Instruction-Following ACL 2026 The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning ACL 2026 When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026 A Benchmark for Semantic Sensitive Information in LLMs Outputs ICLR 2025 An Engorgio Prompt Makes Large Language Model Babble on ICLR 2025 Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems ICML 2025 Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings ACL 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Spatial Preference Rewarding for MLLMs Spatial Understanding ICCV 2025 Speculating LLMs’ Chinese Training Data Pollution from Their Tokens EMNLP 2025 Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025 VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking ICLR 2025 VISO: Accelerating In-orbit Object Detection with Language-Guided Mask Learning and Sparse Inference ICCV 2025 When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models EMNLP 2025 COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation NeurIPS 2024 Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024 Masked AutoDecoder is Effective Multi-Task Vision Generalist CVPR 2024 Purifying Quantization-conditioned Backdoors via Layer-wise Activation Correction with Distribution Approximation ICML 2024 "SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models" ECCV 2024 The Earth is Flat because...: Investigating LLMs’ Belief towards Misinformation via Persuasive Conversation ACL 2024 Walking in Others’ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias EMNLP 2024 You Only Query Once: An Efficient Label-Only Membership Inference Attack ICLR 2024 Computation and Data Efficient Backdoor Attacks ICCV 2023 Extracting Robust Models with Uncertain Examples ICLR 2023 MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection ICCV 2023 One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training ICCV 2023 An MRC Framework for Semantic Role Labeling COLING 2022 Improving Adversarial Robustness of 3D Point Cloud Classification Models ECCV 2022 Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models IJCAI 2021 Privacy-Preserving Collaborative Learning With Automatic Transformation Search CVPR 2021 BorderDet: Border Feature for Dense Object Detection ECCV 2020