Zeyu Zhang

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models ACL 2026 Prototype-Driven Active Domain Adaptation with Density Consideration AAAI 2026 Compositional Attribute Imbalance in Vision Datasets AAAI 2026 VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery EACL 2026 MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training ACL 2026 V-Pruner: A Fast and Globally-informed Token Pruning Framework for Vision Transformer AAAI 2026 ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models AAAI 2026 CypherSmith: Transforming Text-to-Cypher Generation for LLMs with Synthetic Data ACL 2026 A Two-Stage Method for Specular Highlight Detection and Removal in Medical Images MICCAI 2025 MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents ACL 2025 LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media ACL 2025 OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad CVPR 2025 RATSD: Retrieval Augmented Truthfulness Stance Detection from Social Media Posts Toward Factual Claims NAACL 2025 TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System NAACL 2025 Retrieving Support to Rank Answers in Open-Domain Question Answering EMNLP 2025 ARXSA: A General Negative Feedback Control Theory in Vision-Language Models EMNLP 2025 PresentAgent: Multimodal Agent for Presentation Video Generation EMNLP 2025 Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies NAACL 2025 DHGFormer: Dynamic Hierarchical Graph Transformer for Disorder Brain Disease Diagnosis MICCAI 2025 Effective Training Data Synthesis for Improving MLLM Chart Understanding ICCV 2025 VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders ICCV 2025 Efficient Learning with Sine-Activated Low-Rank Matrices ICLR 2025 Self-Explainable Graph Transformer for Link Sign Prediction AAAI 2025 Adaptive Embedding for Long-Range High-Order Dependencies via Time-Varying Transformer on fMRI MICCAI 2025 Motion Mamba: Efficient and Long Sequence Motion Generation ECCV 2024 DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks NIPS 2024 Reflective Multi-Agent Collaboration based on Large Language Models NIPS 2024 Reviewing the Forgotten Classes for Domain Adaptation of Black-Box Predictors AAAI 2024 Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy AAAI 2024 Granular Analysis of Social Media Users’ Truthfulness Stances Toward Climate Change Factual Claims ACL 2024 Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch CVPR 2024 Device-Wise Federated Network Pruning CVPR 2024 Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization ICML 2024 Exploring the Role of Node Diversity in Directed Graph Representation Learning IJCAI 2024 Reconfigurability-Aware Selection for Contrastive Active Domain Adaptation IJCAI 2024 Reinforcement Learning from Answer Reranking Feedback for Retrieval-Augmented Answer Generation INTERSPEECH 2024 Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries NAACL 2024 Structural Alignment for Network Pruning through Partial Regularization ICCV 2023 Hallucination Mitigation in Natural Language Generation from Large-Scale Open-Domain Knowledge Graphs EMNLP 2023 SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark NIPS 2023 Double Retrieval and Ranking for Accurate Question Answering EACL 2023 Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution ACL 2023 USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network AAAI 2023 Bayesian Active Causal Discovery with Multi-Fidelity Experiments NIPS 2023 Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective NIPS 2023 X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events ICCV 2023 Taxonomy Builder: a Data-driven and User-centric Tool for Streamlining Taxonomy Construction NAACL 2022 A Dashboard for Mitigating the COVID-19 Misinfodemic EACL 2021 Joint Models for Answer Verification in Question Answering Systems IJCNLP 2021 Joint Models for Answer Verification in Question Answering Systems ACL 2021 A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization ACL 2020 2-MAP: Aligned Visualizations for Comparison of High-Dimensional Point Sets WACV 2020