Shengen Yan

8

Papers

94

Total Citations

Papers (8)

MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models

MBQ: Modality-Balanced Quantization for Large Vision-Language Models

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

DLFR-Gen: Diffusion-based Video Generation with Dynamic Latent Frame Rate

Evaluating Quantized Large Language Models