Feng Liu

A Unified Perspective on Adversarial Membership Manipulation in Vision Models CVPR 2026 Generalising Traffic Forecasting to Regions Without Traffic Observations AAAI 2026 Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation CVPR 2026 A Closer Look at Backdoor Attacks on CLIP ICML 2025 A Unified Data Representation Learning for Non-parametric Two-sample Testing UAI 2025 Attribute-based Visual Reprogramming for Vision-Language Models ICLR 2025 Deep Kernel Relative Test for Machine-generated Text Detection ICLR 2025 DualCast: A Model to Disentangle Aperiodic Events from Traffic Series IJCAI 2025 DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution CVPR 2025 Endowing Visual Reprogramming with Adversarial Robustness ICLR 2025 Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models ICML 2025 GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs ICML 2025 Learning Imbalanced Data with Beneficial Label Noise ICML 2025 NLPrompt: Noise-Label Prompt Learning for Vision-Language Models CVPR 2025 One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy ICML 2025 Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models AAAI 2025 Sample-specific Noise Injection for Diffusion-based Adversarial Purification ICML 2025 Test-Time Multimodal Backdoor Detection by Contrastive Prompting ICML 2025 Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model CVPR 2025 Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts ICML 2025 Bayesian-guided Label Mapping for Visual Reprogramming NeurIPS 2024 Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data ICML 2024 Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training ICML 2024 In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment NeurIPS 2024 MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence ICML 2024 Mind the Gap Between Prototypes and Images in Cross-domain Finetuning NeurIPS 2024 Negative Label Guided OOD Detection with Pretrained Vision-Language Models ICLR 2024 On the Learnability of Out-of-distribution Detection JMLR 2024 Optimal Kernel Choice for Score Function-based Causal Discovery ICML 2024 Pseudo-Private Data Guided Model Inversion Attacks NeurIPS 2024 Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection ECCV 2024 Sample-specific Masks for Visual Reprogramming-based Prompting ICML 2024 Unveiling Causal Reasoning in Large Language Models: Reality or Mirage? NeurIPS 2024 Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models ICML 2024 Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score ICML 2023 Detecting Out-of-distribution Data through In-distribution Class Prior ICML 2023 Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation ICML 2023 Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection NeurIPS 2023 Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization NeurIPS 2023 Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection ICCV 2023 Learning to Augment Distributions for Out-of-distribution Detection NeurIPS 2023 Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources NeurIPS 2023 Out-of-distribution Detection with Implicit Outlier Transformation ICLR 2023 Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis ICCV 2023 Adversarial Attack and Defense for Non-Parametric Two-Sample Tests ICML 2022 Fast and Reliable Evaluation of Adversarial Robustness with Minimum-Margin Attack ICML 2022 Is Out-of-Distribution Detection Learnable? NeurIPS 2022 Meta Discovery: Learning to Discover Novel Classes given Very Limited Data ICLR 2022 Watermarking for Out-of-distribution Detection NeurIPS 2022 Beyond Max-Margin: Class Margin Equilibrium for Few-Shot Object Detection CVPR 2021 How Does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches? AAAI 2021 Learning Bounds for Open-Set Learning ICML 2021 Maximum Mean Discrepancy Test is Aware of Adversarial Attacks ICML 2021 Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data NeurIPS 2021 Probabilistic Margins for Instance Reweighting in Adversarial Training NeurIPS 2021 TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation NeurIPS 2021 Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation IJCAI 2020 Learning Deep Kernels for Non-Parametric Two-Sample Tests ICML 2020 IVQA: Inverse Visual Question Answering CVPR 2018 Semantic Regularisation for Recurrent Image Annotation CVPR 2017 Sketch Me That Shoe CVPR 2016