selected publications
2026
- ICML 2026DocOS: Towards Proactive Document-Guided Actions in GUI Agents2026
- ACL 2026 MainMem^2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation2026
- ACL 2026 MainPEAP: Proactive Embodied Action Sequence Planning with Joint Understanding of Vision and Audio Perception2026
- ACL 2026 MainBeyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation2026
- ACL 2026 FindingsLive-Aid: A Large-Scale Dialogue Dataset and Benchmark for Interleaved Multi-party Interactions in Live Streaming2026
- ACL 2026 FindingsCharacter-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR2026
- ACL 2026 FindingsPEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes2026
- ACL 2026 FindingsBeyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition2026
- EMNLP 2026 MainJarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition2026
- EMNLP 2026 MainLifeMem: Enabling Lifelong Experience Reuse for LLM Agents2026
- EMNLP 2026 MainBeyond Planning: Sparse Context Reset for Long-Horizon GUI Agents2026
- EMNLP 2026 FindingsBehavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory2026
- EMNLP 2026 FindingsVGE: Towards Generalizable Visually Grounded Exploration of Household Devices2026
- EMNLP 2026 FindingsLearning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards2026
- EMNLP 2026 FindingsA Hyperbolicity Atlas of Large Language Model Hidden States2026
- ACS NanoAccelerating Multi-Elemental Catalyst Discovery with Interpretable Machine Learning and Automated Experimentation2026Corresponding author
- AACL-IJCNLP 2026PersonaPath: Towards Knowledge-Centric Personalized Learning Path Planning2026Corresponding author
- PLOS Computational BiologyCharacterization of the heterogeneity in SARS-CoV-2 fitness dynamics via graph representation learning2026
- Frontiers of Computer SciencePesTest: A Comprehensive Benchmark for Psychological Emotional Support Capability of Large Language Models2026JCR Q1, Corresponding author
- Frontiers of Computer ScienceA^3Bench: An Audience-Aligned Multilingual Benchmark for Video Audience Insights Understanding2026JCR Q1, Corresponding author
- Frontiers of Computer SciencePMMTD: Towards Proactive Multimodal Mixed-Type Dialogues2026JCR Q1, Corresponding author
- ICLR@Lifelong AgentsMem^2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation2026
- NeurocomputingTowards Multi-Language Repository-Level Code Generation: From-Scratch to Guided Tasks2026
- Signal ProcessingLearn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM2026
- IJCNNDistribution-Aware Black-Box Graph Injection Attack via Local Neighborhood Context2026
- 数据与计算发展前沿基于可擦除对抗攻击的图像保护方法2026
2025
- Nature CommunicationsA chemical autonomous robotic platform for end-to-end synthesis of nanoparticles2025
- SCISTowards few-shot mixed-type dialogue generation2025
- ACLHomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices2025
- ACL
- CVPRSeriesBench: A Benchmark for Narrative-Driven Drama Series Understanding2025
- EMNLPRetail: Towards real-world travel planning for large language models2025
- EMNLPPrim: Towards practical in-image multilingual machine translation2025
- EMNLPRepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models2025
- EMNLPSafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs2025
- EMNLPWeak2Wise: An Automated, Lightweight Framework for Weak-LLM-Friendly Reasoning Synthesis2025
- ACL
- ACLTransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments2025
- ACLSelf-reasoning language models: Unfold hidden reasoning chains with few reasoning catalyst2025
- ICLR@LLM Reason and PlanSelf-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst2025
- ACLDocMEdit: Towards Document-Level Model Editing2025
- ACLFlow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability2025
- ACL
- ACL
- AAAISTAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling2025
- AAAIMulti-modal Deepfake Detection via Multi-task Audio-Visual Prompt Learning2025
- AAAIReFF: Reinforcing Format Faithfulness in Language Models Across Varied Tasks2025
- AAAISemi-Supervised Clustering Framework for Fine-grained Scene Graph Generation2025
- TIFSHard-Label Black-Box Adversarial Attacks for Implicit Scene Interactions2025
- NAACLKwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus2025
- NAACLStealthy jailbreak attacks on large language models via benign data mirroring2025
- 智能系统学报中文多技能对话评估2025人工智能学会会刊
2024
- NeurocomputingDual-space Hierarchical Learning for Goal-guided Conversational Recommendation2024
- COLINGTed-el: A corpus for speech entity linking2024
- EMNLPFAME: Towards Factual Multi-Task Model Editing2024
- EMNLPAppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction2024
- ACL
- ACLDeterministic Reversible Data Augmentation for Neural Machine Translation2024
- Applied Intelligence2M-NER: contrastive learning for multilingual and multimodal NER with language and modal fusion2024
- 智能系统学报大语言模型安全性:分类、评估、归因、缓解、展望2024人工智能学会会刊
2023
- EMNLPIn-image neural machine translation with segmented pixel sequence-to-sequence model2023
- ACLXDailyDialog: A multilingual parallel dialogue corpus2023
- ACLMidMed: Towards Mixed-Type Dialogues for Medical Consultation2023
- ACM MMFocusing on flexible masks: A novel framework for panoptic scene graph generation with relation constraints2023
- ACL@DialDocSldt: sequential latent document transformer for multilingual document-based dialogue2023
- EMNLPAutomatic evaluate dialogue appropriateness by using dialogue act2023
2022
- TKDEGraph-grounded goal planning for conversational recommendation2022
- ACLWhere to Go for the Holidays: Towards Mixed-Type Dialogs for Clarification of User Goals2022
2021
- EMNLPDuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation2021
2020
- ACLTowards Conversational Recommendation over Multi-Type Dialogs2020