Xianglong Liu

50

Papers

6

Total Citations

Papers (50)

Dual-view X-ray Detection: Can AI Detect Prohibited Items from Dual-view X-ray Images like Humans?

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

NeurIPS 2025arXiv

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints

Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes

Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

PTQ4SAM: Post-Training Quantization for Segment Anything

NAPGuard: Towards Detecting Naturalistic Adversarial Patches

Scene-adaptive and Region-aware Multi-modal Prompt for Open Vocabulary Object Detection

Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector

LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling

Compressing Large Language Models by Joint Sparsification and Quantization

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

Flexible Residual Binarization for Image Super-Resolution

Multilinear Hyperplane Hashing

Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval

Direct Shape Regression Networks for End-to-End Face Alignment

Forward and Backward Information Retention for Accurate Binary Neural Networks

Towards Unified INT8 Training for Convolutional Neural Network

Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition

Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization

Learning Unseen Concepts via Hierarchical Decomposition and Composition

Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World

Diversifying Sample Generation for Accurate Data-Free Quantization

Delving Deep Into the Generalization of Vision Transformers Under Distribution Shifts

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack

Exploring Endogenous Shift for Cross-Domain Detection: A Large-Scale Benchmark and Perturbation Suppression Network

Defensive Patches for Robust Recognition in the Physical World

Delving Into the Estimation Shift of Batch Normalization in a Network

Annealing-Based Label-Transfer Learning for Open World Object Detection

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

Multi-View Complementary Hash Tables for Nearest Neighbor Search

Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition

Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks

Towards Real-World Prohibited Item Detection: A Large-Scale X-Ray Benchmark

Towards Real-World X-Ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection

Bias-based Universal Adversarial Patch Attack for Automatic Check-out

Spatiotemporal Attacks for Embodied Agents

Patch-wise Attack for Fooling Deep Neural Network

Frequency Domain Model Augmentation for Adversarial Attack

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

Centered Weight Normalization in Accelerating Training of Deep Neural Networks

Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

BiMatting: Efficient Video Matting via Binarization

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution