Joey Tianyi Zhou

Poisoned Distillation: Injecting Backdoors into Distilled Datasets Without Raw Data Access AAAI 2026 Robust Semi-paired Multimodal Learning for Cross-modal Retrieval AAAI 2026 KPL: Training-Free Medical Knowledge Mining of Vision-Language Models AAAI 2025 PVP: Polar Representation Boost for 3D Semantic Occupancy Prediction WACV 2025 Identifying and Mitigating Social Bias Knowledge in Language Models NAACL 2025 Deep Unsupervised Hashing via External Guidance ICML 2025 Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator ICLR 2025 Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents EMNLP 2025 CondenseLM: LLMs-driven Text Dataset Condensation via Reward Matching EMNLP 2025 Learning with Noisy Triplet Correspondence for Composed Image Retrieval CVPR 2025 ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector CVPR 2025 DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models ACL 2025 Understanding Large Language Model Vulnerabilities to Social Bias Attacks ACL 2025 Multisize Dataset Condensation ICLR 2024 The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection NIPS 2024 Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment NIPS 2024 PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification AAAI 2024 Noisy-Correspondence Learning for Text-to-Image Person Re-identification CVPR 2024 Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning CVPR 2024 CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner ECCV 2024 STSP: Spatial-Temporal Subspace Projection for Video Class-incremental Learning ECCV 2024 Direct Distillation between Different Domains ECCV 2024 Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning EMNLP 2024 MedCoT: Medical Chain of Thought via Hierarchical Expert EMNLP 2024 Video-Text Prompting for Weakly Supervised Spatio-Temporal Video Grounding EMNLP 2024 VPL: Visual Proxy Learning Framework for Zero-Shot Medical Image Diagnosis EMNLP 2024 FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data ICLR 2024 Data-independent Module-aware Pruning for Hierarchical Vision Transformers ICLR 2024 You Only Condense Once: Two Rules for Pruning Condensed Datasets NIPS 2023 Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer NIPS 2023 Provable Dynamic Fusion for Low-Quality Multimodal Data ICML 2023 dugMatting: Decomposed-Uncertainty-Guided Matting ICML 2023 Calibrating Multimodal Learning ICML 2023 Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation CVPR 2023 Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video CVPR 2023 A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image CVPR 2023 Fast Model DeBias with Machine Unlearning NIPS 2023 Meta Knowledge Condensation for Federated Learning ICLR 2023 Sequential Subset Matching for Dataset Distillation NIPS 2023 Towards Distribution-Agnostic Generalized Category Discovery NIPS 2023 Frequency Guidance Matters in Few-Shot Learning ICCV 2023 Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering ICCV 2023 Cross-modal Active Complementary Learning with Self-refining Correspondence NIPS 2023 C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation ECCV 2022 XAI Beyond Classification: Interpretable Neural Clustering JMLR 2022 Multi-Scale Adaptive Network for Single Image Denoising NIPS 2022 Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation WACV 2022 Efficient Sharpness-aware Minimization for Improved Training of Neural Networks ICLR 2022 Sharpness-Aware Training for Free NIPS 2022 Parallel Attention Network with Sequence Matching for Video Grounding ACL 2021 Contrastive Clustering AAAI 2021 Trusted Multi-View Classification ICLR 2021 PointBA: Towards Backdoor Attacks in 3D Point Cloud ICCV 2021 Parallel Attention Network with Sequence Matching for Video Grounding IJCNLP 2021 Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions NIPS 2021 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video CVPR 2020 Hooks in the Headline: Learning to Generate Headlines with Controlled Styles ACL 2020 Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering ACL 2020 Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games NIPS 2020 Partially View-aligned Clustering NIPS 2020 Speaker and Phoneme-Aware Speech Bandwidth Extension with Residual Dual-Path Network INTERSPEECH 2020 Unsupervised Domain Adaptation on Reading Comprehension AAAI 2020 Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment AAAI 2020 Multi-Task Learning for End-to-End Noise-Robust Bandwidth Extension INTERSPEECH 2020 Span-based Localizing Network for Natural Language Video Localization ACL 2020 Query-efficient Meta Attack to Deep Neural Networks ICLR 2020 Multi-class Heterogeneous Domain Adaptation JMLR 2019 A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth Image ICCV 2019 Inter-Class Angular Loss for Convolutional Neural Networks AAAI 2019 CPM-Nets: Cross Partial Multi-View Networks NIPS 2019 Multi-view Spectral Clustering Network IJCAI 2019 COMIC: Multi-view Clustering Without Parameter Selection ICML 2019 Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective AAAI 2019 Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition ACL 2019 MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks With Privileged Information CVPR 2017 Transfer Hashing with Privileged Information IJCAI 2016 Exploit Bounding Box Annotations for Multi-Label Object Recognition CVPR 2016 Heterogeneous Domain Adaptation for Multiple Classes AISTATS 2014 Multi-view Positive and Unlabeled Learning ACML 2012