Yixin Liu

Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation AAAI 2026 BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks ACL 2026 Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time AAAI 2026 Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection ACL 2026 Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-Recursions AAAI 2026 AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research ACL 2025 A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection AAAI 2025 CourtReasoner: Can LLM Agents Reason Like Judges? EMNLP 2025 Evaluating Mathematical Reasoning Beyond Accuracy AAAI 2025 MMVU: Measuring Expert-Level Multi-Discipline Video Understanding CVPR 2025 Physics: Benchmarking Foundation Models on University-Level Physics Problem Solving ACL 2025 Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference NAACL 2025 ReIFE: Re-evaluating Instruction-Following Evaluation NAACL 2025 SCIURus: Shared Circuits for Interpretable Uncertainty Representations in Language Models NAACL 2025 Understanding Reference Policies in Direct Preference Optimization NAACL 2025 Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems EMNLP 2025 Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark ICLR 2025 XAttnMark: Learning Robust Audio Watermarking with Cross-Attention ICML 2025 ARC: A Generalist Graph Anomaly Detector with In-Context Learning NeurIPS 2024 Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization NAACL 2024 Calibrating Long-form Generations From Large Language Models EMNLP 2024 DocMath-Eval: Evaluating Math Reasoning Capabilities of LLMs in Understanding Long and Specialized Documents ACL 2024 EditShield: Protecting Unauthorized Image Editing by Instruction-guided Diffusion Models ECCV 2024 Fair Abstractive Summarization of Diverse Perspectives NAACL 2024 FOLIO: Natural Language Reasoning with First-Order Logic EMNLP 2024 GOODAT: Towards Test-Time Graph Out-of-Distribution Detection AAAI 2024 Improving Interpretation Faithfulness for Vision Transformers ICML 2024 M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models EMNLP 2024 MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning CVPR 2024 MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use ICLR 2024 On Learning to Summarize with Large Language Models as References NAACL 2024 On the Role of Summary Content Units in Text Summarization Evaluation NAACL 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 Rethinking Efficient Multilingual Text Summarization Meta-Evaluation ACL 2024 Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise AAAI 2024 A Needle in a Haystack: An Analysis of High-Agreement Workers on MTurk for Summarization ACL 2023 Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating AAAI 2023 Federated Learning on Non-IID Graphs via Structural Knowledge Sharing AAAI 2023 On Improving Summarization Factual Consistency from Natural Language Feedback ACL 2023 QTSumm: Query-Focused Summarization over Tabular Data EMNLP 2023 Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation ACL 2023 SEAT: Stable and Explainable Attention AAAI 2023 Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation EMNLP 2023 Towards Self-Interpretable Graph-Level Anomaly Detection NeurIPS 2023 Vector-Quantized Prompt Learning for Paraphrase Generation EMNLP 2023 BRIO: Bringing Order to Abstractive Summarization ACL 2022 DataLab: A Platform for Data Analysis and Intervention ACL 2022 GEMv2: Multilingual NLG Benchmarking in a Single Line of Code EMNLP 2022 Leveraging Locality in Abstractive Text Summarization EMNLP 2022 R2D2: Robust Data-to-Text with Replacement Detection EMNLP 2022 ExplainaBoard: An Explainable Leaderboard for NLP ACL 2021 On Learning Text Style Transfer with Direct Rewards NAACL 2021 RefSum: Refactoring Neural Summarization NAACL 2021 SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization ACL 2021 Training and Inference Methods for High-Coverage Neural Machine Translation ACL 2020