Haiyang Yu

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation AAAI 2026 EvoRoute: Experience-Driven Self-Routing LLM Agent Systems ACL 2026 MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement AAAI 2026 SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation ICML 2025 Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking AAAI 2025 DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking ACL 2025 IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization ACL 2025 A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding ACL 2025 DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling ACL 2025 EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models EMNLP 2025 Authentic 4D Driving Simulation with a Video Generation Model ICCV 2025 Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM ICCV 2025 ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models ICCV 2025 Learning to Discover Regulatory Elements for Gene Expression Prediction ICLR 2025 StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization ICLR 2025 Spectro-Riemannian Graph Neural Networks ICLR 2025 On the Role of Attention Heads in Large Language Model Safety ICLR 2025 On Explaining Equivariant Graph Networks via Improved Relevance Propagation ICML 2025 Transferable Post-training via Inverse Value Learning NAACL 2025 Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch ICML 2024 How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States EMNLP 2024 DenseKoopman: A Plug-and-Play Framework for Dense Pedestrian Trajectory Prediction IJCAI 2024 EAFormer: Scene Text Segmentation with Edge-Aware Transformers ECCV 2024 Large Language Models Provide Human-Level Medical Text Snippet Labeling NAACL 2024 NetInfoF Framework: Measuring and Exploiting Network Usable Information ICLR 2024 USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task NAACL 2024 Self-Retrieval: End-to-End Information Retrieval with One Large Language Model NIPS 2024 USTCCTSU at SemEval-2024 Task 1: Reducing Anisotropy for Cross-lingual Semantic Textual Relatedness Task SEMEVAL 2024 Preference Ranking Optimization for Human Alignment AAAI 2024 Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment COLING 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment COLING 2024 Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA EMNLP 2024 API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs EMNLP 2023 Orientation-Independent Chinese Text Recognition in Scene Images IJCAI 2023 Unified Language Representation for Question Answering over Text, Tables, and Images ACL 2023 Causal Document-Grounded Dialogue Pre-training EMNLP 2023 Improving Question Generation with Multi-level Content Planning EMNLP 2023 QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules NIPS 2023 Diversify Question Generation with Retrieval-Augmented Style Transfer EMNLP 2023 Towards Accurate Video Text Spotting with Text-wise Semantic Reasoning IJCAI 2023 Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning ICCV 2023 Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian ICML 2023 Universal Information Extraction with Meta-Pretrained Self-Retrieval ACL 2023 Towards Generalized Open Information Extraction EMNLP 2022 Task-driven augmented data evaluation EMNLP 2022 GraphFM: Improving Large-Scale GNN Training via Feature Momentum ICML 2022 Text Gestalt: Stroke-Aware Scene Text Image Super-resolution AAAI 2022 DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population EMNLP 2022 Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots EMNLP 2022 DIG: A Turnkey Library for Diving into Graph Deep Learning Research JMLR 2021 On Explainability of Graph Neural Networks via Subgraph Explorations ICML 2021 OpenUE: An Open Toolkit of Universal Extraction from Text EMNLP 2020 Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction COLING 2020