Xinyu Wang

Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026 MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026 TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs ACL 2026 From Sequential to Recursive: Enhancing Decision-Focused Learning with Bidirectional Feedback AAAI 2026 Evaluating and Mitigating Linguistic Discrimination in Large Language Models: Perspectives on Safety Equity and Knowledge Equity IJCAI 2025 In2NeCT: Inter-class and Intra-class Neural Collapse Tuning for Semantic Segmentation of Imbalanced Remote Sensing Images AAAI 2025 Global Attribute-Association Pattern Aggregation for Graph Fraud Detection AAAI 2025 VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints AAAI 2025 Logic-Regularized Verifier Elicits Reasoning from LLMs ACL 2025 PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA ACL 2025 Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark COLING 2025 MITracker: Multi-View Integration for Visual Object Tracking CVPR 2025 HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery CVPR 2025 NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning EMNLP 2025 Boosting Data Utilization for Multilingual Dense Retrieval EMNLP 2025 STRICT: Stress-Test of Rendering Image Containing Text EMNLP 2025 Improving Context Fidelity via Native Retrieval-Augmented Reasoning EMNLP 2025 Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference EMNLP 2025 KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models EMNLP 2025 Cross-View Isolated Sign Language Recognition via View Synthesis and Feature Disentanglement ICCV 2025 Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent ICLR 2025 Are Large Vision Language Models Good Game Players? ICLR 2025 A Novel Local Search Algorithm for the Vertex Bisection Minimization Problem IJCAI 2025 Multi-task Screening for Cervical Diseases via Feature Routing and Asymmetric Distillation MICCAI 2025 Have LLMs Reopened the Pandora’s Box of AI-Generated Fake News? NAACL 2025 RaFe: Ranking Feedback Improves Query Rewriting for RAG EMNLP 2024 Topic Taxonomy Construction from ESG Reports COLING 2024 Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond ACL 2024 Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts ACL 2024 Deciphering Oracle Bone Language with Diffusion Models ACL 2024 ModaVerse: Efficiently Transforming Modalities with LLMs CVPR 2024 Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning ACL 2024 CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation AAAI 2024 E3V-K5: An Authentic Benchmark for Redefining Video-Based Energy Expenditure Estimation ECCV 2024 DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection AAAI 2024 Unsupervised Object Interaction Learning with Counterfactual Dynamics Models AAAI 2024 LION: Linear Group RNN for 3D Object Detection in Point Clouds NIPS 2024 IaC-Eval: A Code Generation Benchmark for Cloud Infrastructure-as-Code Programs NIPS 2024 MetaAD: Metabolism-Aware Anomaly Detection for Parkinson’s Disease in 3D 18F-FDG PET MICCAI 2024 Anomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors AAAI 2023 A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports EMNLP 2023 Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery ICCV 2023 Boomerang: Metadata-Private Messaging under Hardware Trust NSDI 2023 Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization ACL 2023 Polyhedron Attention Module: Learning Adaptive-order Interactions NIPS 2023 DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition SEMEVAL 2022 Named Entity and Relation Extraction with Multi-Modal Retrieval EMNLP 2022 ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition NAACL 2022 DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition NAACL 2022 Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning IJCNLP 2021 Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings IJCNLP 2021 Automated Concatenation of Embeddings for Structured Prediction IJCNLP 2021 Dependency Induction Through the Lens of Visual Perception EMNLP 2021 Dependency Induction Through the Lens of Visual Perception CONLL 2021 Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning ACL 2021 Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor ACL 2021 Automated Concatenation of Embeddings for Structured Prediction ACL 2021 Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings ACL 2021 Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor IJCNLP 2021 Building a Bridge: A Method for Image-Text Sarcasm Detection Without Pretraining on Image-Text Data EMNLP 2020 Correcting the Misuse: A Method for the Chinese Idiom Cloze Test EMNLP 2020 More Embeddings, Better Sequence Labelers? EMNLP 2020 AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network EMNLP 2020 Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training AACL 2020 Structure-Level Knowledge Distillation For Multilingual Sequence Labeling ACL 2020 Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data ACL 2020 On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering CVPR 2020 Second-Order Semantic Dependency Parsing with End-to-End Neural Networks ACL 2019 ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing CONLL 2019