8 papers
CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference
Xu Li, Yi Zheng, Mengyang Zhao +7
Large Vision-Language Models (LVLMs) typically require processing hundreds to thousands of visual tokens, leading to substantial inference overhead. Existing visual token pruning m…
ResPrune: Text-Conditioned Subspace Reconstruction for Visual Token Pruning in Large Vision-Language Models
Xu Li, Yi Zheng, Yuxuan Liang +5
Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and me…
Wild-Drive: Off-Road Scene Captioning and Path Planning via Robust Multi-modal Routing and Efficient Large Language Model
Zihang Wang, Xu Li, Benwu Wang +7
Explainability and transparent decision-making are essential for the safe deployment of autonomous driving systems. Scene captioning summarizes environmental conditions and risk fa…
Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance
Yuxuan Liang, Xu Li, Xiaolei Chen +4
Large Vision-Language Models (LVLMs) have recently demonstrated strong multimodal understanding, yet their fine-grained visual perception is often constrained by low input resoluti…
HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
Xu Li, Yuxuan Liang, Xiaolei Chen +4
By cropping high-resolution images into local tiles and encoding them independently, High-Resolution Large Vision-Language Models (HR-LVLMs) have demonstrated remarkable fine-grain…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
Yuxuan Liang, Xu Li, Xiaolei Chen +5
As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual informa…
Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models
Xu Li, Yi Zheng, Haotian Chen +5
Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. Howe…