Jinsheng Huang

benchmark evaluation (1) entropy minimization (1) attention mechanism (1) test-time adaptation (1) multi-modal learning (1) benchmark dataset (1) large multimodal model (1) multimodal large language model (1) evaluation metric (1) hallucination detection (1) reasoning evaluation (1) domain shift (1) modality fusion (1) multimodal benchmark (1) chart understanding (1) financial reasoning (1) hallucination penalty (1) multi-modal evaluation (1) cross-modal understanding (1) evaluation calibration (1)