Zexi Kuang

benchmark evaluation (2) claim verification (1) multimodal learning (1) code generation (1) llm evaluation (1) fault detection (1) foundation model (1) vision-language model (1) supervised fine-tuning (1) retrieval-augmented generation (1) scientific literature (1) test case generation (1) large language model (1) fault coverage (1) reinforcement learning with verifiable reward (1) algorithm problem (1) document ocr (1) latex reconstruction (1) page-level reconstruction (1)