IEEE

TransXNet: Learning Both Global and Local Dynamics With a Dual Dynamic Token Mixer for Visual Recognition

Abstract: Recent studies have integrated convolutions into transformers to introduce inductive bias and improve generalization performance. However, the static nature of conventional convolution ...
Morningstar

XPENG-Peking University Collaborative Research Accepted by AAAI 2026: Introducing a Novel Visual Token Pruning Framework for Autonomous Driving

GUANGZHOU, China, Dec. 28, 2025 /PRNewswire/ -- XPENG, in collaboration with Peking University, has had its paper "FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based ...
Cleveland Daily Banner

XPENG-Peking University Collaborative Research Accepted by AAAI 2026: Introducing a Novel Visual Token Pruning Framework for Autonomous Driving

XPENG-PKU Research Breakthrough: XPENG, in collaboration with Peking University, has developed FastDriveVLA—a novel visual token pruning framework that enables autonomous driving AI to "drive like a ...
IEEE

Window Token Concatenation for Efficient Visual Large Language Models

Abstract: To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Wi ndow Token Co ncatenation (WiCo). Specifically, we employ a sliding ...