Publications
Below is a reverse-chronological list of selected papers. For the complete list, please visit Google Scholar. (* denotes equal contribution; correspondence is noted after the author name.)
-
Disentangling Representations from Search Behaviors for Recommendation via Counterfactual LearningACM Transactions on Information Systems (TOIS), vol. 44, no. 5, pp. 1--27, 2026
-
Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal RewardingarXiv / Under review, 2026
-
FishFlow: A LLM-Empowered Dynamic Pricing Framework for Online Fleamarket PlatformACM Web Conference (WWW), pp. 8285--8295, 2026
-
Improving Human Image Animation via Semantic Representation AlignmentIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5704--5714, 2026
-
MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral AlignmentAAAI Conference on Artificial Intelligence (AAAI), vol. 40, no. 38, pp. 32132--32140, 2026
-
Multi-Branch Cooperation Networks for Enhanced Click-Through Rate Prediction in Large-Scale E-Commerce SearchACM Web Conference (WWW), Companion Volume, pp. 1171--1180, 2026
-
Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-trainingIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 29791--29802, 2025
-
Beyond Static Scenes: Camera-Controllable Background Generation for Human MotionarXiv / Under review, 2025
-
CateKV: On Sequential Consistency for Long-Context LLM Inference AccelerationInternational Conference on Machine Learning (ICML), 2025
-
Contrast-Unity for Partially-Supervised Temporal Sentence GroundingIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1--5, 2025
-
Evaluating Multi-Turn Bargain Skills in LLM-Based Seller AgentarXiv / Under review, 2025
-
Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information MinimizationarXiv / Under review, 2025
-
FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced PerformanceIEEE/CVF International Conference on Computer Vision (ICCV), pp. 23614--23625, 2025
-
Leveraging Scene Context with Dual Networks for Sequential User Behavior ModelingarXiv / Under review, 2025
-
MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation FrameworkarXiv / Under review, 2025
-
Squeeze Out Tokens from Sample for Finer-Grained Data GovernancearXiv / Under review, 2025
-
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language ModelsEuropean Conference on Computer Vision (ECCV), pp. 436--455, 2025
-
Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and GenerationarXiv / Under review, 2025
-
DivNet: Diversity-Aware Self-Correcting Sequential Recommendation NetworksACM International Conference on Information and Knowledge Management (CIKM), 2024
-
Enhancing Cross-Domain Click-Through Rate Prediction via Explicit Feature AugmentationACM Web Conference (WWW), Companion Volume, pp. 423--432, 2024
-
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-Dataset 3D Object DetectionIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15291--15300, 2024
-
Tunnel Try-on: Excavating Spatial-Temporal Tunnels for High-Quality Virtual Try-on in VideosACM International Conference on Multimedia (ACM MM), pp. 3199--3208, 2024
-
Wear-Any-Way: Manipulable Virtual Try-On via Sparse Correspondence AlignmentEuropean Conference on Computer Vision (ECCV), pp. 124--142, 2024
-
Automatic Deduction Path Learning via Reinforcement Learning with Environmental CorrectionarXiv / Under review, 2023
-
Cross-domain Augmentation Networks for Click-Through Rate PredictionarXiv / Under review, 2023
-
Forgedit: Text Guided Image Editing via Learning and ForgettingarXiv / Under review, 2023
-
Mixer: Image to Multi-Modal Retrieval Learning for Industrial ApplicationarXiv / Under review, 2023
-
Tile Networks: Learning Optimal Geometric Layout for Whole-page RecommendationInternational Conference on Artificial Intelligence and Statistics (AISTATS), pp. 8360--8369, 2022
-
Traffic Anomaly Prediction Based on Joint Static-Dynamic Spatio-Temporal Evolutionary LearningIEEE Transactions on Knowledge and Data Engineering (TKDE), vol. 35, no. 5, pp. 5356--5370, 2022
-
Learning Time Series Associated Event Sequences With Recurrent Point Process NetworksIEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 30, no. 10, pp. 3124--3136, 2019
-
Model-based Constrained MDP for Budget Allocation in Sequential Incentive MarketingACM International Conference on Information and Knowledge Management (CIKM), pp. 971--980, 2019
-
Learning Conditional Generative Models for Temporal Point ProcessesAAAI Conference on Artificial Intelligence (AAAI), vol. 32, no. 1, 2018
-
Learning Temporal Point Processes via Reinforcement LearningNeural Information Processing Systems (NeurIPS), vol. 31, 2018
-
Publication Popularity Modeling via Adversarial Learning of Profile-Specific Dynamic ProcessIEEE Access, vol. 6, pp. 19984--19992, 2018
-
Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural NetworksarXiv / Under review, 2017
-
Modeling the Intensity Function of Point Process via Recurrent Neural NetworksAAAI Conference on Artificial Intelligence (AAAI), 2017
-
Wasserstein Learning of Deep Generative Point Process ModelsAdvances in Neural Information Processing Systems (NIPS), 2017
-
Modeling Contagious Merger and Acquisition via Point Processes with a Profile Regression PriorInternational Joint Conference on Artificial Intelligence (IJCAI), 2016
-
On Modeling and Predicting Individual Paper Citation Count over TimeInternational Joint Conference on Artificial Intelligence (IJCAI), pp. 2676--2682, 2016
-
Unsupervised Human Skeleton Extraction from Kinect Depth ImagesInternational Conference on Internet Multimedia Computing and Service (ICIMCS), pp. 66--69, 2012