Junyuan Gao

large language model (3) self-supervised learning (1) visual object tracking (1) multilingual nlp (1) in-context learning (1) llm evaluation (1) instruction tuning (1) benchmark dataset (1) multi-modal large language model (1) hallucination mitigation (1) hallucination reduction (1) reasoning evaluation (1) multilingual evaluation (1) large reasoning model (1) vision language (1) object category (1) image aesthetic assessment (1) refusal capability (1) hungarian language (1) knowledge state (1)