Xiangyu Zhang

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering ACL 2026 PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning ACL 2026 MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection ACL 2026 Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026 SpatialActor: Exploring Disentangled Spatial Representations for Robust Robotic Manipulation AAAI 2026 Poisoning with a Pill: Circumventing Detection in Federated Learning AAAI 2026 DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation ICLR 2025 CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI CVPR 2025 Taming Teacher Forcing for Masked Autoregressive Video Generation CVPR 2025 Continuous Semi-Implicit Models ICML 2025 ProSec: Fortifying Code LLMs with Proactive Security Alignment ICML 2025 Perception in Reflection ICML 2025 RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing ICML 2025 SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control AAAI 2025 Language Prompt for Autonomous Driving AAAI 2025 Beyond Sequences: Two-dimensional Representation and Dependency Encoding for Code Generation ACL 2025 Exploiting the Shadows: Unveiling Privacy Leaks through Lower-Ranked Tokens in Large Language Models ACL 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information ACL 2025 Multi-matrix Factorization Attention ACL 2025 Reconstructive Visual Instruction Tuning ICLR 2025 Unhackable Temporal Reward for Scalable Video MLLMs ICLR 2025 Glad: A Streaming Scene Generator for Autonomous Driving ICLR 2025 Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning ICLR 2025 JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models ICCV 2025 Holistic Tokenizer for Autoregressive Image Generation ICCV 2025 Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness ICCV 2025 Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation EMNLP 2025 Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis EMNLP 2025 Foot-In-The-Door: A Multi-turn Jailbreak for LLMs EMNLP 2025 Binaural Selective Attention Model for Target Speaker Extraction INTERSPEECH 2024 Striking a Balance between Classical and Deep Learning Approaches in Natural Language Processing Pedagogy ACL 2024 Merlin: Empowering Multimodal LLMs with Foresight Minds ECCV 2024 UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening ECCV 2024 Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection ICLR 2024 ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning IJCAI 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 Panacea: Panoramic and Controllable Video Generation for Autonomous Driving CVPR 2024 LAMP: Learn A Motion Pattern for Few-Shot Video Generation CVPR 2024 Threat Behavior Textual Search by Attention Graph Isomorphism EACL 2024 Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models ECCV 2024 When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search NIPS 2024 BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens NIPS 2024 Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases NIPS 2024 LLMDFA: Analyzing Dataflow in Code with Large Language Models NIPS 2024 DreamLLM: Synergistic Multimodal Comprehension and Creation ICLR 2024 Stream Query Denoising for Vectorized HD-Map Construction ECCV 2024 BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks ICML 2024 Sanitizing Large Language Models in Bug Detection with Data-Flow EMNLP 2024 Reflected Flow Matching ICML 2024 DDAE: Towards Deep Dynamic Vision BERT Pretraining AAAI 2024 Far3D: Expanding the Horizon for Surround-View 3D Object Detection AAAI 2024 Compound Text-Guided Prompt Tuning via Image-Adaptive Cues AAAI 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model EMNLP 2024 When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection EMNLP 2024 MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception ICCV 2023 RevColV2: Exploring Disentangled Representations in Masked Image Modeling NIPS 2023 BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning NIPS 2023 Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration NIPS 2023 Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration NIPS 2023 Slot-guided Volumetric Object Radiance Fields NIPS 2023 ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP NIPS 2023 Backdooring Neural Code Search ACL 2023 Differentiable Architecture Search With Random Features CVPR 2023 VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking CVPR 2023 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 Understanding Imbalanced Semantic Segmentation Through Neural Collapse CVPR 2023 LargeKernel3D: Scaling Up Kernels in 3D Sparse CNNs CVPR 2023 Detecting Backdoors in Pre-Trained Encoders CVPR 2023 Understanding Masked Image Modeling via Learning Occlusion Invariant Feature CVPR 2023 Referring Multi-Object Tracking CVPR 2023 MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors CVPR 2023 Syntax-Aware Retrieval Augmented Code Generation EMNLP 2023 Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection ICCV 2023 Cross Modal Transformer: Towards Fast and Robust 3D Object Detection ICCV 2023 PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images ICCV 2023 OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation ICCV 2023 FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning ICLR 2023 Re-parameterizing Your Optimizers rather than Architectures ICLR 2023 Reversible Column Networks ICLR 2023 Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks ICLR 2023 Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining ICML 2023 MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization INTERSPEECH 2023 Bounded Adversarial Attack on Deep Content Features CVPR 2022 Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation CVPR 2022 Relieving Long-Tailed Instance Segmentation via Pairwise Class Balance CVPR 2022 Progressive End-to-End Object Detection in Crowded Scenes CVPR 2022 Focal Sparse Convolutional Networks for 3D Object Detection CVPR 2022 Anchor DETR: Query Design for Transformer-Based Detector AAAI 2022 GL-RG: Global-Local Representation Granularity for Video Captioning IJCAI 2022 Self-Supervised Visual Representation Learning with Semantic Grouping NIPS 2022 RepMLPNet: Hierarchical Vision MLP With Re-Parameterized Locality CVPR 2022 Complex Backdoor Detection by Symmetric Feature Differencing CVPR 2022 LGD: Label-Guided Self-Distillation for Object Detection AAAI 2022 Simple Baselines for Image Restoration ECCV 2022 PETR: Position Embedding Transformation for Multi-View 3D Object Detection ECCV 2022 MOTR: End-to-End Multiple-Object Tracking with TRansformer ECCV 2022 Revisiting the Critical Factors of Augmentation-Invariant Representation Learning ECCV 2022 Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense ICML 2022 Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches ECCV 2022 Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs CVPR 2022 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022 Instance-Conditional Knowledge Distillation for Object Detection NIPS 2021 Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay NIPS 2021 Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection AAAI 2021 Towards Feature Space Adversarial Attack by Style Perturbation AAAI 2021 Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021 Dynamic Region-Aware Convolution CVPR 2021 Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification AAAI 2021 RepVGG: Making VGG-Style ConvNets Great Again CVPR 2021 Activate or Not: Learning Customized Activation CVPR 2021 Neural Architecture Search With Random Labels CVPR 2021 You Only Look One-Level Feature CVPR 2021 Diverse Branch Block: Building a Convolution as an Inception-Like Unit CVPR 2021 Points As Queries: Weakly Semi-Supervised Object Detection by Points CVPR 2021 Image Synthesis via Semantic Composition ICCV 2021 SOLQ: Segmenting Objects by Learning Queries NIPS 2021 Constrained Two-step Look-Ahead Bayesian Optimization NIPS 2021 Funnel Activation for Visual Recognition ECCV 2020 Single Path One-Shot Neural Architecture Search with Uniform Sampling ECCV 2020 Angle-based Search Space Shrinking for Neural Architecture Search ECCV 2020 LabelEnc: A New Intermediate Supervision Method for Object Detection ECCV 2020 Detection in Crowded Scenes: One Proposal, Multiple Predictions CVPR 2020 Learning Dynamic Routing for Semantic Segmentation CVPR 2020 Attentive Normalization for Conditional Image Generation CVPR 2020 Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization ICLR 2020 Rethinking Learnable Tree Filter for Generic Feature Transform NIPS 2020 Learning Human-Object Interaction Detection Using Interaction Points CVPR 2020 Learning Delicate Local Representations for Multi-Person Pose Estimation ECCV 2020 WeightNet: Revisiting the Design Space of Weight Networks ECCV 2020 DetNAS: Backbone Search for Object Detection NIPS 2019 Meta-SR: A Magnification-Arbitrary Network for Super-Resolution CVPR 2019 Bounding Box Regression With Uncertainty for Accurate Object Detection CVPR 2019 Objects365: A Large-Scale, High-Quality Dataset for Object Detection ICCV 2019 MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning ICCV 2019 DetNet: Design Backbone for Object Detection ECCV 2018 Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples NIPS 2018 MetaAnchor: Learning to Detect Objects with Customized Anchors NIPS 2018 ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design ECCV 2018 MegDet: A Large Mini-Batch Object Detector CVPR 2018 ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices CVPR 2018 ExFuse: Enhancing Feature Fusion for Semantic Segmentation ECCV 2018 Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network CVPR 2017 Channel Pruning for Accelerating Very Deep Neural Networks ICCV 2017 Deep Residual Learning for Image Recognition CVPR 2016 Efficient and Accurate Approximations of Nonlinear Convolutional Networks CVPR 2015 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification ICCV 2015