5 papers
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees
Yuankai Li, Tinghui Zhu, Ha Min Son +3
Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iterat…
ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
Xin Liu, Xudong Wang, Pei Liu +1
The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in lon…
OmniScene: Attention-Augmented Multimodal 4D Scene Understanding for Autonomous Driving
Pei Liu, Hongliang Lu, Haichao Liu +5
Human vision is capable of transforming two-dimensional observations into an egocentric three-dimensional scene understanding, which underpins the ability to translate complex scen…
VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion
Pei Liu, Haipeng Liu, Haichao Liu +3
Human drivers adeptly navigate complex scenarios by utilizing rich attentional semantics, but the current autonomous systems struggle to replicate this ability, as they often lose…
HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
Pei Liu, Xin Liu, Ruoyu Yao +4
While Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge, conventional single-agent RAG remains fundamentally limited in resolving c…