Xu Chen

Beyond Step Pruning: Information Theory Based Step-level Optimization for Self-Refining Large Language Models AAAI 2026 DiP: Taming Diffusion Models in Pixel Space CVPR 2026 Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement ACL 2026 Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation CVPR 2026 CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds NAACL 2025 Enhancing Recommendation Explanations through User-Centric Refinement EMNLP 2025 Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent ACL 2025 GenSim: A General Social Simulation Platform with Large Language Model based Agents NAACL 2025 Improving Retrospective Language Agents via Joint Policy Gradient Optimization NAACL 2025 Incorporating Review-missing Interactions for Generative Explainable Recommendation COLING 2025 Investigating and Extending Homans’ Social Exchange Theory with Large Language Model based Agents ACL 2025 KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understanding ACL 2025 LLM-Based Multi-Agent Systems are Scalable Graph Generative Models ACL 2025 MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents ICLR 2025 MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents ACL 2025 Optimal Transport for Time Series Imputation ICLR 2025 SVFR: A Unified Framework for Generalized Video Face Restoration CVPR 2025 Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation ACL 2025 Towards Effective and Efficient Continual Pre-training of Large Language Models ACL 2025 TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System NAACL 2025 Unbiased Recommender Learning from Implicit Feedback via Weakly Supervised Learning ICML 2025 Uncertainty and Influence aware Reward Model Refinement for Reinforcement Learning from Human Feedback ICLR 2025 A Diffusion-Based Framework for Multi-Class Anomaly Detection AAAI 2024 AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model AAAI 2024 Debiased Collaborative Filtering with Kernel-Based Causal Balancing ICLR 2024 Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control ECCV 2024 Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization ICML 2024 Large Language Model-based Human-Agent Collaboration for Complex Task Solving EMNLP 2024 Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 Relaxing the Accurate Imputation Assumption in Doubly Robust Learning for Debiased Collaborative Filtering ICML 2024 Rethinking Reverse Distillation for Multi-Modal Anomaly Detection AAAI 2024 Towards Tool Use Alignment of Large Language Models EMNLP 2024 Would You Like Your Data to Be Trained? A User Controllable Recommendation Framework AAAI 2024 Bayesian Active Causal Discovery with Multi-Fidelity Experiments NeurIPS 2023 Joint Semantic and Strategy Matching for Persuasive Dialogue EMNLP 2023 Offline Imitation Learning with Variational Counterfactual Reasoning NeurIPS 2023 Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption ICCV 2023 REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths NeurIPS 2023 Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection ICCV 2023 To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion ACL 2023 Learning to Identify Top Elo Ratings: A Dueling Bandits Approach AAAI 2022 Estimating $α$-Rank from A Few Entries with Low Rank Matrix Completion ICML 2021 HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping IJCAI 2021 Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision EMNLP 2018 Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding ACL 2017