11 papers
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation
Zeyuan Ma, Jiaxin Chen, Di Huang
UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egocentric visual observations. Cu…
DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images
Ke Wu, Yanan Zhang, Yingjie Gao +5
Object detection for Unmanned Aerial Vehicles (UAVs) working in open and dynamic environments is a highly challenging task. While Vision-Language Models (VLMs) have offered a power…
Beyond Open Vocabulary: Multimodal Prompting for Object Detection in Remote Sensing Images
Shuai Yang, Ziyue Huang, Jiaxin Chen +2
Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories, implicitly assuming that inference-time category queries can…
Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
Zimeng Wu, Donghao Wang, Chaozhe Jin +2
Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and…
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
Zhuguanyu Wu, Shihe Wang, Jiayi Zhang +2
Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years, as it avoids computationally intensive model retraining…
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
Zhuguanyu Wu, Jiayi Zhang, Jiaxin Chen +3
Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops…