Bohan Zhuang
15 papers · 0 citations
Most-cited papers
- Scalable Vision Transformers With Hierarchical Pooling2021 · 115 citations
- Automated Progressive Learning For Efficient Training Of Vision Transformers2022 · 28 citations
- Dynamic Focus-aware Positional Queries For Semantic Segmentation2022 · 14 citations
- Cov: Chain-of-view Prompting For Spatial Reasoning2026
- Blockvid: Block Diffusion For High-quality And Consistent Minute-long Video Generation2025
- Frequency-aware Autoregressive Modeling For Efficient High-resolution Image Synthesis2025
- Geometrically-constrained Agent For Spatial Reasoning2025
- Omnisparse: Training-aware Fine-grained Sparse Attention For Long-video Mllms2025
- An Empirical Study On How Video-llms Answer Video Questions2025
- Less Detail, Better Answers: Degradation-driven Prompting For VQA2026
Topics