Dongyan Zhao

MARS: Multimodal Adaptive Reasoning Model for Avoiding Overthinking AAAI 2026 Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models ACL 2026 E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models COLING 2025 ReMamba: Equip Mamba with Effective Long-Sequence Modeling EMNLP 2025 VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format EMNLP 2025 English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 F2TEval: Human-Aligned Multi-Dimensional Evaluation for Figure-to-Text Task EMNLP 2025 Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding AAAI 2025 EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding ACL 2025 Efficient Domain Continual pretraining by Mitigating the Stability Gap ACL 2025 QAEval: Mixture of Evaluators for Question-Answering Task Evaluation ACL 2025 ReasVQA: Advancing VideoQA with Imperfect Reasoning Process NAACL 2025 Understanding Visual Detail Hallucinations of Large Vision-Language Models IJCAI 2025 OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts CVPR 2025 Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes ICML 2025 Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering COLING 2025 Large Language Models Can Learn Representation in Natural Language ACL 2024 Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text with Large Language Model ACL 2024 PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion ACL 2024 Synergistic Interplay between Search and Large Language Models for Information Retrieval ACL 2024 xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token NIPS 2024 Language Models can be Deductive Solvers NAACL 2024 PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion EMNLP 2024 Learning to Plan by Updating Natural Language EMNLP 2024 Unlocking the Potential of Model Merging for Low-Resource Languages EMNLP 2024 Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules EMNLP 2024 Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge EMNLP 2024 Probing Multimodal Large Language Models for Global and Local Semantic Representations COLING 2024 Your Career Path Matters in Person-Job Fit AAAI 2024 What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation AAAI 2024 STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering AAAI 2024 Multilingual Generation in Abstractive Summarization: A Comparative Study COLING 2024 SCALE: Synergized Collaboration of Asymmetric Language Translation Engines ACL 2024 Graph-Structured Speculative Decoding ACL 2024 Decouple knowledge from paramters for plug-and-play language modeling ACL 2023 Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory NIPS 2023 FAA: Fine-grained Attention Alignment for Cascade Document Ranking ACL 2023 From the One, Judge of the Whole: Typed Entailment Graph Construction with Predicate Generation ACL 2023 Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast ACL 2023 VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions ACL 2023 MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation ACL 2023 More than Classification: A Unified Framework for Event Temporal Relation Extraction ACL 2023 RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank ACL 2023 Dialogue Summarization with Static-Dynamic Structure Fusion Graph ACL 2023 Class-Incremental Learning based on Label Generation ACL 2023 Align-then-Enhance: Multilingual Entailment Graph Enhancement with Soft Predicate Alignment ACL 2023 Rethinking Dictionaries and Glyphs for Chinese Language Pre-training ACL 2023 How Many Answers Should I Give? An Empirical Study of Multi-Answer Reading Comprehension ACL 2023 Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long Documents ACL 2023 Attend, Select and Eliminate: Accelerating Multi-turn Response Selection with Dual-attention-based Content Elimination ACL 2023 Leveraging Denoised Abstract Meaning Representation for Grammatical Error Correction ACL 2023 PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models ACL 2023 The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code ACL 2023 Smart Word Suggestions for Writing Assistance ACL 2023 Dealing With Cross-Task Class Discrimination in Online Continual Learning CVPR 2023 An Intra-Class Relation Guided Approach for Code Comment Generation EACL 2023 Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension EACL 2023 Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting EMNLP 2023 Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning EMNLP 2023 From Simple to Complex: A Progressive Framework for Document-level Informative Argument Extraction EMNLP 2023 Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation EMNLP 2023 Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression EMNLP 2023 Relation-Aware Question Answering for Heterogeneous Knowledge Graphs EMNLP 2023 Learning Dynamic Representations for Discourse Dependency Parsing EMNLP 2023 Improving Input-label Mapping with Demonstration Replay for In-context Learning EMNLP 2023 Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study ICLR 2023 Learning to Express in Knowledge-Grounded Conversation NAACL 2022 Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation ACL 2022 How to Represent Context Better? An Empirical Study on Context Modeling for Multi-turn Response Selection EMNLP 2022 SMASH: Improving SMAll Language Models’ Few-SHot Ability with Prompt-Based Distillation EMNLP 2022 Collaborative Reasoning on Multi-Modal Semantic Graphs for Video-Grounded Dialogue Generation EMNLP 2022 Do Charge Prediction Models Learn Legal Theory? EMNLP 2022 Summarizing Procedural Text: Data and Approach EMNLP 2022 GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval EMNLP 2022 ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation ACL 2022 Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook EMNLP 2022 Counterfactual Recipe Generation: Exploring Compositional Generalization in a Realistic Scenario EMNLP 2022 Online Continual Learning through Mutual Information Maximization ICML 2022 Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure EMNLP 2022 Neural Machine Translation with Contrastive Translation Memories EMNLP 2022 Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations COLING 2022 Things not Written in Text: Exploring Spatial Commonsense from Visual Signals ACL 2022 Adaptive Orthogonal Projection for Batch and Online Continual Learning AAAI 2022 Entailment Graph Learning with Textual Entailment and Soft Transitivity ACL 2022 Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED ACL 2022 Finding the Dominant Winning Ticket in Pre-Trained Language Models ACL 2022 Multi-Granularity Structural Knowledge Distillation for Language Model Compression ACL 2022 Content Learning with Structure-Aware Writing: A Graph-Infused Dual Conditional Variational Autoencoder for Automatic Storytelling AAAI 2021 Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis NAACL 2021 Predictive Adversarial Learning from Positive and Unlabeled Data AAAI 2021 Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models NAACL 2021 Enhancing the Open-Domain Dialogue Evaluation in Latent Space ACL 2021 Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues AAAI 2021 The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement AAAI 2021 BioGen: Generating Biography Summary under Table Guidance on Wikipedia ACL 2021 Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction IJCNLP 2021 Reasoning in Dialog: Improving Response Generation by Context Reading Comprehension AAAI 2021 Why Machine Reading Comprehension Models Learn Shortcuts? IJCNLP 2021 BioGen: Generating Biography Summary under Table Guidance on Wikipedia IJCNLP 2021 Why Machine Reading Comprehension Models Learn Shortcuts? ACL 2021 Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction ACL 2021 Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation ACL 2021 Exploring Distantly-Labeled Rationales in Neural Network Models ACL 2021 Stylized Dialogue Generation with Multi-Pass Dual Learning NIPS 2021 BNS: Building Network Structures Dynamically for Continual Learning NIPS 2021 Exploring Distantly-Labeled Rationales in Neural Network Models IJCNLP 2021 Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation IJCNLP 2021 Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation EMNLP 2021 Extract, Integrate, Compete: Towards Verification Style Reading Comprehension EMNLP 2021 Enhancing the Open-Domain Dialogue Evaluation in Latent Space IJCNLP 2021 Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study NAACL 2021 Understanding Procedural Text using Interactive Entity Networks EMNLP 2020 VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles EMNLP 2020 Towards Context-Aware Code Comment Generation EMNLP 2020 RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search (Student Abstract) AAAI 2020 Learning Sense Representation from Word Representation for Unsupervised Word Sense Disambiguation (Student Abstract) AAAI 2020 Low-Resource Knowledge-Grounded Dialogue Generation ICLR 2020 Neighborhood Matching Network for Entity Alignment ACL 2020 Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling COLING 2020 Transformation of Dense and Sparse Text Representations COLING 2020 A Character-Centric Neural Model for Automated Story Generation AAAI 2020 Draft and Edit: Automatic Storytelling Through Multi-Pass Hierarchical Conditional Variational Autoencoder AAAI 2020 Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce AAAI 2020 Integrating Relation Constraints with Neural Relation Extractors AAAI 2020 Domain Adaptation for Semantic Parsing IJCAI 2020 From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information IJCAI 2020 Knowledge-Grounded Dialogue Generation with Pre-trained Language Models EMNLP 2020 Selection and Generation: Learning towards Multi-Product Advertisement Post Generation EMNLP 2020 Semi-supervised Text Style Transfer: Cross Projection in Latent Space IJCNLP 2019 Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems ACL 2019 One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues ACL 2019 Jointly Learning Entity and Relation Representations for Entity Alignment EMNLP 2019 Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems EMNLP 2019 Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations EMNLP 2019 Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders EMNLP 2019 Learning to Update Knowledge Graphs by Reading News EMNLP 2019 How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing EMNLP 2019 Semi-supervised Text Style Transfer: Cross Projection in Latent Space EMNLP 2019 Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation EMNLP 2019 Lattice CNNs for Matching Based Chinese Question Answering AAAI 2019 Abstractive Text Summarization by Incorporating Reader Comments AAAI 2019 Learning to Write Stories with Thematic Consistency and Wording Novelty AAAI 2019 Find a Reasonable Ending for Stories: Does Logic Relation Help the Story Cloze Test? AAAI 2019 Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation ICLR 2019 Plan-and-Write: Towards Better Automatic Storytelling AAAI 2019 Learning towards Abstractive Timeline Summarization IJCAI 2019 Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References ACL 2019 GSN: A Graph-Structured Network for Multi-Party Dialogues IJCAI 2019 Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs IJCAI 2019 A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots IJCAI 2019 Insufficient Data Can Also Rock! Learning to Converse Using Smaller Data with Augmentation AAAI 2019 Jointly Learning Entity and Relation Representations for Entity Alignment IJCNLP 2019 Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems IJCNLP 2019 Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations IJCNLP 2019 Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders IJCNLP 2019 Learning to Update Knowledge Graphs by Reading News IJCNLP 2019 How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing IJCNLP 2019 Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation IJCNLP 2019 Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism IJCAI 2018 One "Ruler" for All Languages: Multi-Lingual Dialogue Evaluation with Adversarial Multi-Task Learning IJCAI 2018 Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm IJCAI 2018 Modeling discourse cohesion for discourse parsing via memory network ACL 2018 Iterative Document Representation Learning Towards Summarization with Polishing EMNLP 2018 Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training EMNLP 2018 Multi-grained Attention Network for Aspect-Level Sentiment Classification EMNLP 2018 Learning to Converse with Noisy Data: Generation with Calibration IJCAI 2018 An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems IJCAI 2018 Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding ACL 2018 Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations COLING 2018 Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems EMNLP 2017 Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix ACL 2017 How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models ACL 2017 Learning to Predict Charges for Criminal Cases with Legal Basis EMNLP 2017 Diversifying Neural Conversation Model with Maximal Marginal Relevance IJCNLP 2017 Hybrid Question Answering over Knowledge Base and Free Text COLING 2016 Question Answering on Freebase via Relation Extraction and Textual Evidence ACL 2016 Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling EMNLP 2015 Semantic Interpretation of Superlative Expressions via Structured Knowledge Bases ACL 2015 Semantic Interpretation of Superlative Expressions via Structured Knowledge Bases IJCNLP 2015 Joint Inference for Knowledge Base Population EMNLP 2014 Encoding Relation Requirements for Relation Extraction via Joint Inference ACL 2014 Towards Automatic Construction of Knowledge Bases from Chinese Online Resources ACL 2012 Explore Person Specific Evidence in Web Person Name Disambiguation CONLL 2012 Explore Person Specific Evidence in Web Person Name Disambiguation EMNLP 2012