B / ARTIFACT Materialized signal MM-OPERA (NeurIPS 2025 Poster) FormatPAPER Released2025/10/31 VenueNeurIPS 2025 Poster Benchmarking Open-ended Association Reasoning for Large Vision-Language Models,并引入 LLM-as-a-Judge 进行解释质量评估。 Signal taxonomy VLM ReasoningLLM-as-a-JudgeBenchmark External bearingsLinks 01 arXiv ↗ OBSERVATION OBJECT mm-opera-neurips-2025 该成果是我在 HCPLab 阶段的重要研究实践之一。 我主要参与评测框架设计,聚焦解释的 rationality、stability 与 human alignment。