Kun He

Latent Attention Denoising: A Training-Free Energy-Based Framework for Mitigating Hallucinations in Vision-Language Models ACL 2026 Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning ACL 2026 VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025 Neural Collapse Inspired Knowledge Distillation AAAI 2025 ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers ICCV 2025 Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs ICLR 2025 Synonym-unaware Fast Adversarial Training against Textual Adversarial Attacks NAACL 2025 Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack NAACL 2025 CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning ICML 2025 Refining Adaptive Zeroth-Order Optimization at Ease ICML 2025 Targeted control of fast prototyping through domain-specific interface ICML 2025 Exact Algorithms with New Upper Bounds for the Maximum k-plex Problem IJCAI 2025 Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks NAACL 2024 Long-range Meta-path Search on Large-scale Heterogeneous Graphs NIPS 2024 Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers NIPS 2024 KD-Club: An Efficient Exact Algorithm with New Coloring-Based Upper Bound for the Maximum k-Defective Clique Problem AAAI 2024 Rethinking the Soft Conflict Pseudo Boolean Constraint on MaxSAT Local Search Solvers IJCAI 2024 You Only Need Less Attention at Each Stage in Vision Transformers CVPR 2024 Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects ECCV 2024 Rethinking the Backward Propagation for Adversarial Transferability NIPS 2023 Pointerformer: Deep Reinforced Multi-Pointer Transformer for the Traveling Salesman Problem AAAI 2023 Farsighted Probabilistic Sampling: A General Strategy for Boosting Local Search MaxSAT Solvers AAAI 2023 Hybrid Learning with New Value Function for the Maximum Common Induced Subgraph Problem AAAI 2023 On the Complexity of Bayesian Generalization ICML 2023 Rethinking the Data Annotation Process for Multi-View 3D Pose Estimation With Active Learning and Self-Training WACV 2023 All in Tokens: Unifying Output Space of Visual Tasks via Soft Token ICCV 2023 AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation CVPR 2023 Sparse Black-Box Multimodal Attack for Vision-Language Adversary Generation EMNLP 2023 NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs ICLR 2023 FABind: Fast and Accurate Protein-Ligand Binding NIPS 2023 Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks AAAI 2023 Robustness-Aware Word Embedding Improves Certified Robustness to Adversarial Word Substitutions ACL 2023 Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities CVPR 2022 Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability CVPR 2022 Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack ECCV 2022 Graph Hawkes Transformer for Extrapolated Reasoning on Temporal Knowledge Graphs EMNLP 2022 TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack EMNLP 2022 BandMaxSAT: A Local Search MaxSAT Solver with Multi-armed Bandit IJCAI 2022 A Strengthened Branch and Bound Algorithm for the Maximum Common (Connected) Subgraph Problem IJCAI 2022 Combining Clause Learning and Branch and Bound for MaxSAT (Extended Abstract) IJCAI 2022 Detecting textual adversarial examples through randomized substitution and vote UAI 2022 Robust textual embedding against word-level adversarial attacks UAI 2022 Crafting Adversarial Examples for Neural Machine Translation IJCNLP 2021 Crafting Adversarial Examples for Neural Machine Translation ACL 2021 Admix: Enhancing the Transferability of Adversarial Attacks ICCV 2021 Natural language adversarial defense through synonym encoding UAI 2021 Enhancing the Transferability of Adversarial Attacks Through Variance Tuning CVPR 2021 TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting EMNLP 2021 Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem AAAI 2021 Adversarial Training with Fast Gradient Projection Method against Synonym Substitution Based Text Attacks AAAI 2021 Robust Local Features for Improving the Generalization of Adversarial Training ICLR 2020 Single Image Reflection Removal Through Cascaded Refinement CVPR 2020 A Learning Based Branch and Bound for Maximum Common Subgraph Related Problems AAAI 2020 Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks ICLR 2020 Generalized Majorization-Minimization ICML 2019 Improving the Generalization of Adversarial Training with Domain Adaptation ICLR 2019 Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency ACL 2019 Multilevel Language and Vision Integration for Text-to-Clip Retrieval AAAI 2019 Deep Metric Learning to Rank CVPR 2019 Local Descriptors Optimized for Average Precision CVPR 2018 Hashing as Tie-Aware Learning to Rank CVPR 2018 Hashing with Binary Matrix Pursuit ECCV 2018 Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation NIPS 2018 MIHash: Online Hashing With Mutual Information ICCV 2017 A Powerful Generative Model Using Random Weights for the Deep Image Representation NIPS 2016