Shengen Yan
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
arXiv 2025
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
arXiv 2025
Megrez-Omni Technical Report
arXiv 2025
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
arXiv 2025
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
arXiv 2024
Evaluating Quantized Large Language Models
arXiv 2024
FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models
ICCV 2025
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
arXiv 2024
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
arXiv 2024
MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression
arXiv 2024
MBQ: Modality-Balanced Quantization for Large Vision-Language Models
CVPR 2025 1
CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
arXiv 2024
Affiliations
Frequent co-authors
10from 12 papers