 LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression ComprehensionConference on Empirical Methods in Natural Language Processing (EMNLP), 2025 |
 Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMsInternational Conference on Learning Representations (ICLR), 2025 |
 Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow ThinkingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 MLLM can see? Dynamic Correction Decoding for Hallucination MitigationInternational Conference on Learning Representations (ICLR), 2024 |
 ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple DomainsInternational Conference on Learning Representations (ICLR), 2024 |
 ADEPT: A DEbiasing PrompT FrameworkAAAI Conference on Artificial Intelligence (AAAI), 2022 |
