Bohan Zhuang

11

Papers

238

Total Citations

Papers (11)

LongVLM: Efficient Long Video Understanding via Large Language Models

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Neighboring Autoregressive Modeling for Efficient Visual Generation

FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion

Efficient Stitchable Task Adaptation

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Stitched ViTs are Flexible Vision Backbones

ZipVL: Accelerating Vision-Language Models through Dynamic Token Sparsity

Channel Merging: Preserving Specialization for Merged Experts

ModaVerse: Efficiently Transforming Modalities with LLMs

Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis