Xiaolin Hu

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs ACL 2026 Put the Space of LoRA Initialization to the Extreme to Preserve Pre-trained Knowledge AAAI 2026 FGNet: Leveraging Feature-Guided Attention to Refine SAM2 for 3D EM Neuron Segmentation AAAI 2026 VaccineRAG: Boosting Multimodal Large Language Models’ Immunity to Harmful RAG Samples AAAI 2026 Towards Auto-Regressive Next-Token Prediction: In-context Learning Emerges from Generalization ICLR 2025 PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection ICCV 2025 ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification ICLR 2025 Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology AAAI 2025 PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning COLING 2025 Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization IJCAI 2025 TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation ICLR 2025 SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios ICLR 2025 Improving Accuracy and Calibration via Differentiated Deep Mutual Learning CVPR 2025 GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing CVPR 2025 SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model CVPR 2025 MTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting CVPR 2025 Efficient Neuron Segmentation in Electron Microscopy by Affinity-Guided Queries ICLR 2025 ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning ICLR 2025 Infrared Adversarial Car Stickers CVPR 2024 CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics NIPS 2024 Full-Distance Evasion of Pedestrian Detectors in the Physical World NIPS 2024 Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective CORL 2024 RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation ICLR 2024 Controllable Navigation Instruction Generation with Chain of Thought Prompting ECCV 2024 PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition ECCV 2024 IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation ICML 2024 Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective NIPS 2024 SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection CVPR 2024 Language-Driven Anchors for Zero-Shot Adversarial Robustness CVPR 2024 Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling CVPR 2023 Visual Recognition by Request CVPR 2023 Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses ICLR 2023 NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic Segmentation ICML 2023 HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds NIPS 2023 Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model INTERSPEECH 2023 An efficient encoder-decoder architecture with top-down attention for speech separation ICLR 2023 Adversarial Texture for Fooling Person Detectors in the Physical World CVPR 2022 On the Use of Deep Mask Estimation Module for Neural Source Separation Systems INTERSPEECH 2022 NP-Match: When Neural Processes meet Semi-Supervised Learning ICML 2022 Active Pointly-Supervised Instance Segmentation ECCV 2022 Infrared Invisible Clothing: Hiding From Infrared Detectors at Multiple Angles in Real World CVPR 2022 RSG: A Simple but Effective Module for Learning Imbalanced Datasets CVPR 2021 Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network NIPS 2021 Fooling Thermal Infrared Pedestrian Detectors in Real World Using Small Bulbs AAAI 2021 Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection CVPR 2021 RefineMask: Towards High-Quality Instance Segmentation With Fine-Grained Features CVPR 2021 Look Closer To Segment Better: Boundary Patch Refinement for Instance Segmentation CVPR 2021 DAM: Discrepancy Alignment Metric for Face Recognition ICCV 2021 Boosting Decision-based Black-box Adversarial Attacks with Random Sign Flip ECCV 2020 Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection NIPS 2020 Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning NIPS 2020 Dynamic Network Pruning with Interpretable Layerwise Channel Selection AAAI 2020 Pruning from Scratch AAAI 2020 Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition CVPR 2020 Online Knowledge Distillation via Collaborative Learning CVPR 2020 Knowledge Distillation via Route Constrained Optimization ICCV 2019 Turbo Learning Framework for Human-Object Interactions Recognition and Human Pose Estimation AAAI 2019 Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization ICCV 2019 Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift CVPR 2019 Selective Kernel Networks CVPR 2019 Interpret Neural Networks by Identifying Critical Data Routing Paths CVPR 2018 Boosting Adversarial Attacks With Momentum CVPR 2018 High Performance Visual Tracking With Siamese Region Proposal Network CVPR 2018 Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser CVPR 2018 Scale-Aware Face Detection CVPR 2017 Gated Recurrent Convolution Neural Network for OCR NIPS 2017 Joint Training of Cascaded CNN for Face Detection CVPR 2016 Recurrent Convolutional Neural Network for Object Recognition CVPR 2015 Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling NIPS 2015 A Reverse Hierarchy Model for Predicting Eye Fixations CVPR 2014