Jiasen Lu

机构：Home Office, Apple (United Kingdom)

发表论文 66 篇 · 总被引 15178 次 · h-index 27

代表论文

• Hierarchical Question-Image Co-Attention for Visual Question Answering (2024 · TIB Data Manager · 被引 439)
• Multi-Modal Answer Validation for Knowledge-Based VQA (2022 · Proceedings of the AAAI Conference on Artificial Intelligence · 被引 112)
• Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks (2022 · arXiv (Cornell University) · 被引 111)
• Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action (2024 · 被引 71)
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models (2025 · 被引 37)
• Container: Context Aggregation Networks (2021 · Neural Information Processing Systems · 被引 19)