Bo Zhao
16 papers · 0 citations
Most-cited papers
- Image Generation From Layout2018 · 145 citations
- Rag-driver: Generalisable Driving Explanations With Retrieval-augmented In-context Learning In Multi-modal Large Language Model2024 · 97 citations
- Unveiling The Ignorance Of Mllms: Seeing Clearly, Answering Incorrectly2024 · 28 citations
- Omni6dpose: A Benchmark And Model For Universal 6D Object Pose Estimation And Tracking2024 · 21 citations
- Enhancing Long Video Understanding Via Hierarchical Event-based Memory2024 · 16 citations
- Synartifact: Classifying And Alleviating Artifacts In Synthetic Images Via Vision-language Model2024 · 14 citations
- Tele-flm Technical Report2024 · 11 citations
- Megapairs: Massive Data Synthesis For Universal Multimodal Retrieval2024 · 2 citations
- Attribute-guided Image Generation From Layout2020 · 1 citations
- Hidream-i1: A High-efficient Image Generative Foundation Model With Sparse Diffusion Transformer2025
- Robofac: A Comprehensive Framework For Robotic Failure Analysis And Correction2025
- Egograsp: World-space Hand-object Interaction Estimation From Egocentric Videos2026
- Probing Visual Planning In Image Editing Models2026
Topics