5 papers
BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design
Yifu Ding, Xianglong Liu, Shenghao Jin +2
Ultra low-bit quantization brings substantial efficiency for Transformer-based models, but the accuracy degradation and limited GPU support hinder its wide usage. In this paper, we…
AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement
Siqi Pei, Liang Tang, Tiaonan Duan +9
GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural…
SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
Jiahui Wang, Zuyan Liu, Yongming Rao +1
Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs…
Ola: Pushing the Frontiers of Omni-Modal Language Model
Zuyan Liu, Yuhao Dong, Jiahui Wang +4
Recent advances in large language models, particularly following GPT-4o, have sparked increasing interest in developing omni-modal models capable of understanding more modalities.…
Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution
Zuyan Liu, Yuhao Dong, Ziwei Liu +3
Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours. Existing multi-modal LLMs usually standardize these diverse visual…