["Published 'CompassVerifier: A Unified and Robust Answer Verifier for LLMs Evaluation and Outcome Reward' at EMNLP 2025 (Top 1% score in ARR May 2025)", "Published 'Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist' at ICLR 2025", 'Contributor to Intern-S1: A Scientific Multimodal Foundation Model (60k+ HuggingFace downloads)', "Co-authored preprint 'CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries'", "Co-authored survey 'Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models'", 'Published 'Learning from "Silly" Questions Improves Large Language Models, But Only Slightly' at AAAI 2025 Workshop', "Published 'Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner' at EMNLP 2024", "Published 'Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation' in ACL 2024 Findings", "Published 'kNN-TL: k-Nearest-Neighbor Transfer Learning for Low-Resource Neural Machine Translation' at ACL 2023", "Published 'Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization' at EMNLP 2023", "Published 'A Graph Attention Interactive Refine Framework with Contextual Regularization for Jointing Intent Detection and Slot Filling' at ICASSP 2022", "Oral presentation of 'Cross-domain Slot Filling with Distinct Slot Entity and Type Prediction' at NLPCC 2021", 'OpenReview Chair for NLPCC 2024', 'PC member / reviewer for NeurIPS, ICML, ICLR, ACL ARR (ACL/EMNLP/NAACL/EACL), AAAI, AISTATS, CCL', 'Journal reviewer for TASLP, Neurocomputing, Information Processing and Management']