arXiv subjects

Jinghui Xu

Publications and source records attributed to Jinghui Xu.

4 recordsLinked to original sources

arXiv2026

Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents

Autonomous Earth Observation (EO) agents are transitioning from passive perception to complex, multi-step task execution. However, current architectures that integrate planning and execution within a single model often struggle with combinatorial complexity and reasoning errors in dynamic EO scenarios. To resolve these challenges, we propose the Lightweight Multimodal Meta-Planner (LMMP) framework. LMMP incorporates a dual-awareness mechanism that grounds strategic plans in both multimodal image features and high-level task semantics. Crucially, we introduce a Meta Task Library to inject remote sensing expert knowledge directly into the workflow, which standardizes domain logic and ensures plans are physically feasible. We further implement a two-stage training pipeline, initializing the Meta-Planner via expert-distilled Supervised Fine-Tuning and refining it through Direct Preference Optimization based on execution feedback. Extensive experiments on a dataset derived from EarthBench and ThinkGeo demonstrate that LMMP significantly improves tool-calling accuracy and task success rates. Moreover, the framework exhibits strong ``plug-and-play'' versatility, consistently enhancing the performance of diverse executor backbones across previously unseen EO missions.

cs.MA↗

arXiv2024

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

With the success of Neural Radiance Field (NeRF) in 3D-aware portrait editing, a variety of works have achieved promising results regarding both quality and 3D consistency. However, these methods heavily rely on per-prompt optimization when handling natural language as editing instructions. Due to the lack of labeled human face 3D datasets and effective architectures, the area of human-instructed 3D-aware editing for open-world portraits in an end-to-end manner remains under-explored. To solve this problem, we propose an end-to-end diffusion-based framework termed InstructPix2NeRF, which enables instructed 3D-aware portrait editing from a single open-world image with human instructions. At its core lies a conditional latent 3D diffusion process that lifts 2D editing to 3D space by learning the correlation between the paired images' difference and the instructions via triplet data. With the help of our proposed token position randomization strategy, we could even achieve multi-semantic editing through one single pass with the portrait identity well-preserved. Besides, we further propose an identity consistency module that directly modulates the extracted identity signals into our diffusion process, which increases the multi-view 3D identity consistency. Extensive experiments verify the effectiveness of our method and show its superiority against strong baselines quantitatively and qualitatively. Source code and pre-trained models can be found on our project page: \url{https://mybabyyh.github.io/InstructPix2NeRF}.

cs.CV↗

arXiv2022

Disappeared Command: Spoofing Attack On Automatic Speech Recognition Systems with Sound Masking

The development of deep learning technology has greatly promoted the performance improvement of automatic speech recognition (ASR) technology, which has demonstrated an ability comparable to human hearing in many tasks. Voice interfaces are becoming more and more widely used as input for many applications and smart devices. However, existing research has shown that DNN is easily disturbed by slight disturbances and makes false recognition, which is extremely dangerous for intelligent voice applications controlled by voice.

cs.SD↗

arXiv2012

Calculation of the transport critical current density of c-axis textured 122 iron-based superconductors

The c-axis textured Sr1-xKxFe2As2 tapes produced by cold rolling and post-annealing, could carry a high super-current over 2*104 A/cm2. However, the magnitude is far from its maximum, because of the current obstacles associated with various defects in the material. To predict the maximal transport critical current density, we modeled the current paths in a c-axis textured polycrystal as a three-dimensional flow network, and calculated the maximum flow with the Ford-Fulkerson algorithm. It indicates that a much higher super-current of about 2*105 A/cm2 could be achieved in an ideal c-axis textured K-doped 122 polycrystal. The dependences of transport Jc on density, content of invalid boundary and grain size and shape were also studied. The results imply that, over 30% of the grain boundaries in the reported c-axis textured Sr1-xKxFe2As2 tapes may act as current obstacles, and the large ratio of width to thickness was expected to be the most favorable grain shape for high transport Jc in c-axis textured 122 superconducting tapes.

cond-mat.supr-con↗