activity
20242026
collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2025

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

Tianyu Fu, Tengxuan Liu, Qinghao Han +5

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing to…

cs.CV2025

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate

Zhihang Yuan, Rui Xie, Yuzhang Shang +5

Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency c…

cs.CV2025

DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation

Zhihang Yuan, Siyuan Wang, Rui Xie +6

In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing…

cs.CV2025

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

Hanling Zhang, Rundong Su, Zhihang Yuan +5

Text-to-image generation models, especially Multimodal Diffusion Transformers (MMDiT), have shown remarkable progress in generating high-quality images. However, these models often…

cs.CV2025

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

Shiyao Li, Yingchun Hu, Xuefei Ning +10

Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significa…

cs.CV2025

Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

Yao Teng, Han Shi, Xian Liu +5

The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction du…