Zihan Liu

Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing ACL 2026 CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels ACL 2026 HiPro-CT: A Hierarchical Probabilistic Framework for 3D Medical Vision-Language Alignment MIDL 2026 ResMAS: Resilience Optimization in LLM-based Multi-agent Systems AAAI 2026 DualGuard: A Parameter Space Transformation Approach for Bidirectional Defense in Split-Based LLM Fine-Tuning ACL 2025 AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling ACL 2025 SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation ICML 2025 ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities ICLR 2025 SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition ACL 2025 Retrieval meets Long Context Large Language Models ICLR 2024 An NCDE-based Framework for Universal Representation Learning of Time Series IJCAI 2024 Protein 3D Graph Structure Learning for Robust Structure-Based Protein Property Prediction AAAI 2024 ChatQA: Surpassing GPT-4 on Conversational QA and RAG NIPS 2024 RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs NIPS 2024 SUT: Active Defects Probing for Transcompiler Models EMNLP 2023 Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation AACL 2023 Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training EACL 2023 Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study EMNLP 2023 Cross-Lingual Cross-Age Adaptation for Low-Resource Elderly Speech Emotion Recognition INTERSPEECH 2023 Only 5% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation IJCNLP 2023 RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding ACL 2023 Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning EMNLP 2023 AutoMix: Unveiling the Power of Mixup for Stronger Classifiers ECCV 2022 Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias NIPS 2022 Multi-Stage Prompting for Knowledgeable Dialogue Generation ACL 2022 SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study ACL 2022 Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters ACL 2022 Mere Contrastive Learning for Cross-Domain Sentiment Analysis COLING 2022 Exploiting Sentiment and Common Sense for Zero-shot Stance Detection COLING 2022 CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System ACL 2021 CrossNER: Evaluating Cross-Domain Named Entity Recognition AAAI 2021 On the Importance of Word Order Information in Cross-lingual Sequence Labeling AAAI 2021 Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation ACL 2021 Preserving Cross-Linguality of Pre-trained Models via Continual Learning ACL 2021 X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing ACL 2021 Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization EMNLP 2021 Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer EMNLP 2021 XPersona: Evaluating Multilingual Personalized Chatbot EMNLP 2021 Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation IJCNLP 2021 CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System IJCNLP 2021 Preserving Cross-Linguality of Pre-trained Models via Continual Learning IJCNLP 2021 X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing IJCNLP 2021 Multimodal End-to-End Sparse Model for Emotion Recognition NAACL 2021 AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization NAACL 2021 Are Multilingual Models Effective in Code-Switching? NAACL 2021 Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems EMNLP 2020 Cross-lingual Spoken Language Understanding with Regularized Representation Alignment EMNLP 2020 Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-TaskLearning for Offensive Language Detection SEMEVAL 2020 Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling ACL 2020 Zero-Resource Cross-Domain Named Entity Recognition ACL 2020 Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-TaskLearning for Offensive Language Detection COLING 2020 Learning Fast Adaptation on Cross-Accented Speech Recognition INTERSPEECH 2020 Meta-Transfer Learning for Code-Switched Speech Recognition ACL 2020 Attention-Informed Mixed-Language Training for Zero-Shot Cross-Lingual Task-Oriented Dialogue Systems AAAI 2020 Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition AACL 2020 Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables IJCNLP 2019 Team yeon-zi at SemEval-2019 Task 4: Hyperpartisan News Detection by De-noising Weakly-labeled Data SEMEVAL 2019 Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring ACL 2019 Generalizing Question Answering System with Pre-trained Language Model Fine-tuning EMNLP 2019 Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition EMNLP 2019 Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables EMNLP 2019 Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition IJCNLP 2019