 APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference TrainingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as OfflineAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 DRPruning: Efficient Large Language Model Pruning through Distributionally Robust OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 NewTerm: Benchmarking Real-Time New Terms for Large Language Models with
Annual UpdatesNeural Information Processing Systems (NeurIPS), 2024 |
 Holistic Exploration on Universal Decompositional Semantic Parsing:
Architecture, Data Augmentation, and LLM ParadigmWorkshop on Chinese Language Processing (CLP), 2023 |
 Adapting Offline Speech Translation Models for Streaming with
Future-Aware Distillation and InferenceConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
