6 papers
CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management
Chao Wang, Xudong Tan, Jianjian Cao +2
Multimodal Large Language Models have achieved significant success in offline video understanding, yet their application to streaming videos is severely limited by the linear explo…
Efficiency Follows Global-Local Decoupling
Zhenyu Yang, Gensheng Pei, Tao Chen +4
Modern vision models must capture image-level context without sacrificing local detail while remaining computationally affordable. We revisit this tradeoff and advance a simple pri…
Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach
Yaoxin Yang, Peng Ye, Xudong Tan +4
Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cach…
RegionE: Adaptive Region-Aware Generation for Efficient Image Editing
Pengtao Chen, Xianfang Zeng, Maosen Zhao +7
Recently, instruction-based image editing (IIE) has received widespread attention. In practice, IIE often modifies only specific regions of an image, while the remaining areas larg…
Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
Pengtao Chen, Xianfang Zeng, Maosen Zhao +5
While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention…
Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning
Maosen Zhao, Pengtao Chen, Chong Yu +3
Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization rema…