5 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…
Local Information Matters: Inference Acceleration For Grounded Conversation Generation Models Through Adaptive Local-Aware Token Pruning
Bizhe Bai, Jianjian Cao, Yadan Luo +1
Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding obj…
TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
Xudong Tan, Peng Ye, Chongjun Tu +5
Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens…
DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
Yongqi Huang, Peng Ye, Chenyu Huang +5
Upcycled Mixture-of-Experts (MoE) models have shown great potential in various tasks by converting the original Feed-Forward Network (FFN) layers in pre-trained dense models into M…
-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers
Pengtao Chen, Mingzhu Shen, Peng Ye +5
Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusi…