Jifeng Dai

机构：Tsinghua University · ORCID：0000-0002-6785-0785

发表论文 199 篇 · 总被引 36833 次 · h-index 53

代表论文

• BEVFormer: Learning Bird’s-Eye-View Representation From LiDAR-Camera via Spatiotemporal Transformers (2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 232)
• Mini-InternVL: a flexible-transfer pocket multi-modal model with 5% parameters and 90% performance (2024 · Visual Intelligence · 被引 30)
• A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook (2025 · ACM Computing Surveys · 被引 20)
• DriveMLM: aligning multi-modal large language models with behavioral planning states for autonomous driving (2025 · Visual Intelligence · 被引 13)
• Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training (2025 · 被引 11)
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models (2025 · arXiv (Cornell University) · 被引 8)