Jindong Gu

Can Editing LLMs Inject Harm? AAAI 2026 Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society ACL 2026 AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models AAAI 2026 AlignGuard: Scalable Safety Alignment for Text-to-Image Generation ICCV 2025 FedPop: Federated Population-based Hyperparameter Tuning AAAI 2025 Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025 Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models ACL 2025 Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation ACL 2025 FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings ACL 2025 Localizing Events in Videos with Multimodal Queries CVPR 2025 FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models CVPR 2025 Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025 ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos CVPR 2025 Reimagining Safety Alignment with An Image EMNLP 2025 Can an Individual Manipulate the Collective Decisions of Multi-Agents? EMNLP 2025 Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs EMNLP 2025 PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving EMNLP 2025 LLM Jailbreak Detection for (Almost) Free! EMNLP 2025 Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention ICCV 2025 Improved Techniques for Optimization-Based Jailbreaking on Large Language Models ICLR 2025 Primitive Vision: Improving Diagram Understanding in MLLMs ICML 2025 Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning? WACV 2025 CL-Cross VQA: A Continual Learning Benchmark for Cross-Domain Visual Question Answering WACV 2025 Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation CVPR 2024 Initialization Matters for Adversarial Transfer Learning CVPR 2024 Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds CVPR 2024 Latent Guard: a Safety Framework for Text-to-image Generation ECCV 2024 MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models ECCV 2024 Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Models ECCV 2024 Improving Adversarial Transferability via Model Alignment ECCV 2024 Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution ECCV 2024 Dataset Distillation by Automatic Training Trajectories ECCV 2024 Visual Question Decomposition on Multimodal Large Language Models EMNLP 2024 Influencer Backdoor Attack on Semantic Segmentation ICLR 2024 Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images ICLR 2024 Can Large Language Model Agents Simulate Human Trust Behavior? NIPS 2024 FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning AAAI 2024 Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024 Provably Better Explanations with Optimized Aggregation of Feature Attributions ICML 2024 Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression AAAI 2024 An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models ICLR 2024 Do DALL-E and Flamingo Understand Each Other? ICCV 2023 FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation ICCV 2023 Multi-Event Video-Text Retrieval ICCV 2023 Backdoor Defense via Adaptively Splitting Poisoned Dataset CVPR 2023 ECOLA: Enhancing Temporal Knowledge Embeddings with Contextualized Language Representations ACL 2023 Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models NIPS 2023 Are Vision Transformers Robust to Patch Perturbations? ECCV 2022 Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal ECCV 2022 SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness ECCV 2022 Towards Efficient Adversarial Training on Vision Transformers ECCV 2022 Capsule Network Is Not More Robust Than Convolutional Network CVPR 2021 Effective and Efficient Vote Attack on Capsule Networks ICLR 2021 Interpretable Graph Capsule Networks for Object Recognition AAAI 2021 Improving the Robustness of Capsule Networks to Image Affine Transformations CVPR 2020