Lewei Lu
10 papers · 0 citations
Most-cited papers
- Fuseformer: Fusing Fine-grained Information In Transformers For Video Inpainting2021 · 152 citations
- Visionllm V2: An End-to-end Generalist Multimodal Large Language Model For Hundreds Of Vision-language Tasks2024 · 5 citations
- From Pixels To Words -- Towards Native Vision-language Primitives At Scale2025
- Streamline Without Sacrifice -- Squeeze Out Computation Redundancy In LMM2025
- Spatial Preference Rewarding For Mllms Spatial Understanding2025
- Scaling Spatial Intelligence With Multimodal Foundation Models2025
Topics