Hao Liu

Hard vs. Noise: Resolving Hard-Noisy Sample Confusion in Recommender Systems via Large Language Models AAAI 2026 A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding ACL 2025 Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting ACL 2025 Erase Then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning AAAI 2025 HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation ACL 2025 MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering ACL 2025 RePST: Language Model Empowered Spatio-Temporal Forecasting via Semantic-Oriented Reprogramming IJCAI 2025 SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction ICLR 2025 TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning EMNLP 2025 WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? EMNLP 2025 A Cross-View Hierarchical Graph Learning Hypernetwork for Skill Demand-Supply Joint Prediction AAAI 2024 Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs NeurIPS 2024 Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation AAAI 2024 Harmonizing Visual Text Comprehension and Generation NeurIPS 2024 Improve Dense Passage Retrieval with Entailment Tuning EMNLP 2024 Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach ICML 2024 Make Large Language Model a Better Ranker EMNLP 2024 Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer CVPR 2024 Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification AAAI 2024 TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy NeurIPS 2024 UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction NeurIPS 2024 Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration ICCV 2023 Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing ICCV 2023 Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA AAAI 2023 TaCo: Textual Attribute Recognition via Contrastive Learning AAAI 2023 The Devil Is in the Frequency: Geminated Gestalt Autoencoder for Self-Supervised Visual Pre-training AAAI 2023 UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction NeurIPS 2023 Feature and Instance Joint Selection: A Reinforcement Learning Perspective IJCAI 2022 GMN: Generative Multi-modal Network for Practical Document Information Extraction NAACL 2022 Knowledge Mining With Scene Text for Fine-Grained Recognition CVPR 2022 Learning to Walk with Dual Agents for Knowledge Graph Reasoning AAAI 2022 Neural Collaborative Graph Machines for Table Structure Recognition CVPR 2022 NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition CVPR 2022 Perceiving Stroke-Semantic Context: Hierarchical Contrastive Learning for Robust Scene Text Recognition AAAI 2022 Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models NeurIPS 2022 Community-Aware Multi-Task Transportation Demand Prediction AAAI 2021 Generalized DataWeighting via Class-Level Gradient Manipulation NeurIPS 2021 Joint Air Quality and Weather Prediction Based on Multi-Adversarial Spatiotemporal Networks AAAI 2021 Out-of-Town Recommendation with Travel Intention Modeling AAAI 2021 Self-Supervised Prototype Representation Learning for Event-Based Corporate Profiling AAAI 2021 Accurate Structured-Text Spotting for Arithmetical Exercise Correction AAAI 2020 Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction AAAI 2020 Why We Go Where We Go: Profiling User Decisions on Choosing POIs IJCAI 2020 Joint Representation Learning for Multi-Modal Transportation Recommendation AAAI 2019