Xu Sun

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters ACL 2026 TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment AAAI 2026 VidTwin: Video VAE with Decoupled Structure and Dynamics CVPR 2025 Modeling Interactions Between Stocks Using LLM-Enhanced Graphs for Volume Prediction COLING 2025 Proxy Tuning for Financial Sentiment Analysis: Overcoming Data Scarcity and Computational Barriers COLING 2025 InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation AAAI 2025 PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension ACL 2025 ATLANTIS: Weak-to-Strong Learning via Importance Sampling ACL 2025 Generative Frame Sampler for Long Video Understanding ACL 2025 Temporal Reasoning Transfer from Text to Video ICLR 2025 Beyond Human Labels: A Multi-Linguistic Auto-Generated Benchmark for Evaluating Large Language Models on Resume Parsing EMNLP 2025 RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction EMNLP 2025 PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization EMNLP 2025 Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs ICLR 2024 Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents NIPS 2024 VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models ECCV 2024 LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation? NAACL 2024 TempCompass: Do Video LLMs Really Understand Videos? ACL 2024 A Survey on In-context Learning EMNLP 2024 TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding CVPR 2024 Modal-adaptive Knowledge-enhanced Graph-based Financial Prediction from Monetary Policy Conference Calls with LLM COLING 2024 Enhancing Byzantine-Resistant Aggregations with Client Embedding EMNLP 2024 Can Language Models Understand Physical Concepts? EMNLP 2023 MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning ACL 2023 Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias ACL 2023 Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter ACL 2023 Delving into the Openness of CLIP ACL 2023 Annotating Discursive Roles of Sentences in Patent Descriptions ACL 2023 TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding EMNLP 2023 Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning EMNLP 2023 Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition NIPS 2023 Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense NIPS 2023 FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation NIPS 2023 Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features EACL 2023 Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation EMNLP 2022 Retrieve, Reason, and Refine: Generating Accurate and Faithful Patient Instructions NIPS 2022 Generalized Brain Image Synthesis with Transferable Convolutional Sparse Coding Networks ECCV 2022 Holistic Sentence Embeddings for Better Out-of-Distribution Detection EMNLP 2022 No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning EMNLP 2022 Hierarchical Inductive Transfer for Continual Dialogue Learning ACL 2022 Well-Classified Examples Are Underestimated in Classification with Deep Neural Networks AAAI 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 Position Offset Label Prediction for Grammatical Error Correction COLING 2022 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022 Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks EMNLP 2022 From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models EMNLP 2022 Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification IJCAI 2022 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 Learning Relation Alignment for Calibrated Cross-modal Retrieval IJCNLP 2021 Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks EMNLP 2021 Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation EMNLP 2021 CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade EMNLP 2021 Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification EMNLP 2021 Collaborative Group Learning AAAI 2021 Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption AAAI 2021 Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation AAAI 2021 EQG-RACE: Examination-Type Question Generation AAAI 2021 Towards Semantics-Enhanced Pre-Training: Can Lexicon Definitions Help Learning Sentence Meanings? AAAI 2021 Dynamic Knowledge Distillation for Pre-trained Language Models EMNLP 2021 Rethinking Denoised Auto-Encoding in Language Pre-Training EMNLP 2021 RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models EMNLP 2021 Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects NAACL 2021 Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models NAACL 2021 A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models NAACL 2021 O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning IJCNLP 2021 Contrastive Attention for Automatic Chest X-ray Report Generation IJCNLP 2021 Rethinking Stealthiness of Backdoor Attack against NLP Models IJCNLP 2021 Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling IJCAI 2021 Topology-Imbalance Learning for Semi-Supervised Node Classification NIPS 2021 KNAS: Green Neural Architecture Search ICML 2021 Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation NIPS 2021 Learning Relation Alignment for Calibrated Cross-modal Retrieval ACL 2021 Rethinking Stealthiness of Backdoor Attack against NLP Models ACL 2021 Contrastive Attention for Automatic Chest X-ray Report Generation ACL 2021 O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning ACL 2021 Rethinking Skip Connection with Layer Normalization COLING 2020 How to Ask Good Questions? Try to Leverage Paraphrases ACL 2020 Parallel Data Augmentation for Formality Style Transfer ACL 2020 Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological View AAAI 2020 Prophet Attention: Predicting Attention with Future Attention NIPS 2020 Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models EMNLP 2020 Regularizing Dialogue Generation by Imitating Implicit Scenarios EMNLP 2020 Visual Agreement Regularized Training for Multi-Modal Machine Translation AAAI 2020 Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information ACL 2019 Understanding and Improving Layer Normalization NIPS 2019 Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations NIPS 2019 Learning Personalized End-to-End Goal-Oriented Dialog AAAI 2019 LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts AAAI 2019 Imitation Learning for Non-Autoregressive Neural Machine Translation ACL 2019 Enhancing Topic-to-Essay Generation with External Commonsense Knowledge ACL 2019 Towards Fine-grained Text Sentiment Transfer ACL 2019 Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation ACL 2019 MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction ACL 2019 Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model ACL 2019 A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer ACL 2019 A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification ACL 2019 Learning to Control the Fine-grained Sentiment for Story Ending Generation ACL 2019 Asking Clarification Questions in Knowledge-Based Question Answering EMNLP 2019 Pun-GAN: Generative Adversarial Network for Pun Generation EMNLP 2019 Aligning Cross-Lingual Entities with Multi-Aspect Information EMNLP 2019 Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification EMNLP 2019 LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification EMNLP 2019 Incorporating Fine-grained Events in Stock Movement Prediction EMNLP 2019 Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Prediction EMNLP 2019 Adaptive Gradient Methods with Dynamic Bound of Learning Rate ICLR 2019 Exploring and Distilling Cross-Modal Information for Image Captioning IJCAI 2019 A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer IJCAI 2019 Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling IJCAI 2019 Asking Clarification Questions in Knowledge-Based Question Answering IJCNLP 2019 Pun-GAN: Generative Adversarial Network for Pun Generation IJCNLP 2019 Aligning Cross-Lingual Entities with Multi-Aspect Information IJCNLP 2019 Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification IJCNLP 2019 LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification IJCNLP 2019 Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations NAACL 2019 Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach ACL 2018 Question Condensing Networks for Answer Selection in Community Question Answering ACL 2018 Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning EMNLP 2018 An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation EMNLP 2018 SGM: Sequence Generation Model for Multi-label Classification COLING 2018 Global Encoding for Abstractive Summarization ACL 2018 Deconvolution-Based Global Decoding for Neural Machine Translation COLING 2018 A Neural Question Answering Model Based on Semi-Structured Tables COLING 2018 Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data? COLING 2018 Learning Sentiment Memories for Sentiment Modification without Parallel Data EMNLP 2018 simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions EMNLP 2018 Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation EMNLP 2018 Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation EMNLP 2018 Bag-of-Words as Target for Neural Machine Translation ACL 2018 A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation EMNLP 2018 A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification IJCAI 2018 Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation NAACL 2018 Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text NAACL 2018 Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification EMNLP 2018 Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization ACL 2018 Automatic Academic Paper Rating Based on Modularized Hierarchical Convolutional Neural Network ACL 2018 Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization ACL 2017 F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media EACL 2017 meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting ICML 2017 Addressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure IJCNLP 2017 Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification IJCNLP 2017 Cascading Multiway Attentions for Document-level Sentiment Classification IJCNLP 2017 Dependency-based Gated Recursive Neural Network for Chinese Word Segmentation ACL 2016 Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features COLING 2016 Knowledge-Based Semantic Embedding for Machine Translation ACL 2016 Methods and Theories for Large-scale Structured Prediction EMNLP 2016 Multi-label Text Categorization with Joint Learning Predictions-as-Features Method EMNLP 2015 Predicting Chinese Abbreviations with Minimum Semantic Unit and Global Constraints EMNLP 2014 Coarse-grained Candidate Generation and Fine-grained Re-ranking for Chinese Abbreviation Prediction EMNLP 2014 Structure Regularization for Structured Prediction NIPS 2014 Exploring Representations from Unlabeled Data with Co-training for Chinese Word Segmentation EMNLP 2013 Generalized Abbreviation Prediction with Negative Full Forms and Its Application on Improving Chinese Web Search IJCNLP 2013 Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection ACL 2012 Learning Phrase-Based Spelling Error Models from Clickthrough Data ACL 2010 A Large Scale Ranker-Based System for Search Query Spelling Correction COLING 2010 Sequential Labeling with Latent Variables: An Exact Inference Algorithm and its Efficient Approximation EACL 2009 A Discriminative Latent Variable Chinese Segmenter with Hybrid Word/Character Information NAACL 2009 Robust Approach to Abbreviating Terms: A Discriminative Latent Variable Model with Global Information ACL 2009 Robust Approach to Abbreviating Terms: A Discriminative Latent Variable Model with Global Information IJCNLP 2009 Modeling Latent-Dynamic in Shallow Parsing: A Latent Conditional Model with Improved Inference COLING 2008