arXiv subjects

Peijia Li

Publications and source records attributed to Peijia Li.

8 recordsLinked to original sources

arXiv2026

Pipette: An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics

Wet-lab robots can improve the reproducibility, throughput, and safety of biomedical experiments, but scaling their learning requires customizable simulators for safe and reproducible task generation, open editable laboratory assets, and efficient pipelines that turn limited demonstrations into usable training data. We present Pipette, an embodied simulation platform, benchmark, and data-efficient augmentation framework for wet-lab robot learning. Pipette provides over 100 open-source and re-editable wet-lab assets through an extensible asset-building pipeline with built-in Tencent Hunyuan support for text- and image-conditioned 3D asset generation, and supports three robotic-arm embodiments through a unified simulation interface for task construction, data collection, augmentation, and evaluation. A key component of Pipette is its simulation-based data augmentation pipeline, which replays human demonstrations in simulation, applies lighting, camera, speed, and action perturbations, and filters generated episodes with automatic task success checks, rapidly expanding usable training data from limited manual demonstrations. We further introduce a 12-task wet-lab embodied benchmark covering sample handling, culture-ware manipulation, device operation, and precision placement. With only 30 demonstrations per task, ACT achieves 60.3% average success rate, while simulation augmentation improves SmolVLA from 40.4% to 71.8% and pi0 from 37.3% to 44.1%, validating the effectiveness of Pipette for data-efficient VLA training and evaluation. Pipette also supports natural-language-driven scene construction and task registration, lowering the barrier for non-expert users to define new wet-lab robotic tasks

cs.RO↗

arXiv2025

Lunar Orbital VLBI Experiment: motivation, scientific purposes and status

The Lunar Orbital VLBI Experiment (LOVEX) is a scientific component of the Chinese Lunar Exploration Project (CLEP) Chang'E-7. The spaceborne component of LOVEX is implemented onboard the relay satellite QueQiao-2, which was launched on 2024 March 20, and later placed into an elliptical selenocentric orbit. The LOVEX-specific payload consists of an X-band cryogenic receiver, a hydrogen maser frequency standard, and VLBI data formatting and acquisition electronics. Several components of the QueQiao-2 nominal onboard instrumentation, such as the 4.2-meter antenna, the data storage device, and the downlink communication system, contribute to the overall spaceborne VLBI instrumentation. This allows us to form a space radio telescope capable of co-observing with Earth-based radio telescopes in VLBI mode. In this space VLBI system, the length of the baseline extends up to approximately 380,000 km. This paper presents the LOVEX scientific objectives, architecture, instrumentation, pre-launch tests, in-flight verification and calibration, and the first in-flight detections of interferometric response (''fringes'') achieved through observations of the quasar AO 0235+164 and the Chang'E-6 orbital module, positioned at the Sun-Earth Lagrange point L2. These initial results demonstrate the successful performance of LOVEX, verifying its capability for both astronomical and spacecraft tracking observations at ultra-long VLBI baselines.

astro-ph.IM↗

arXiv2025

Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance. However, most existing methods rely on static heuristics or task-specific metrics, limiting their robustness and generalizability across domains. In this work, we introduce a dynamic dataset pruning framework that adaptively selects training samples based on both task-driven difficulty and cross-modality semantic consistency. By incorporating supervision from pretrained multimodal foundation models, our approach captures training dynamics while effectively filtering out uninformative samples. Our work highlights the potential of integrating cross-modality alignment for robust sample selection, advancing data-centric learning toward more efficient and robust practices across application domains.

cs.LG↗

arXiv2025

AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation

Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or random magnitudes throughout the training process. While this fosters data diversity, it can also inevitably introduce uncontrolled variability in augmented data, which could potentially cause misalignment with the evolving training status of the target models. Both theoretical and empirical findings suggest that this misalignment increases the risks of both underfitting and overfitting. To address these limitations, we propose AdaAugment, an innovative and tuning-free adaptive augmentation method that leverages reinforcement learning to dynamically and adaptively adjust augmentation magnitudes for individual training samples based on real-time feedback from the target network. Specifically, AdaAugment features a dual-model architecture consisting of a policy network and a target network, which are jointly optimized to adapt augmentation magnitudes in accordance with the model's training progress effectively. The policy network optimizes the variability within the augmented data, while the target network utilizes the adaptively augmented samples for training. These two networks are jointly optimized and mutually reinforce each other. Extensive experiments across benchmark datasets and deep architectures demonstrate that AdaAugment consistently outperforms other state-of-the-art DA methods in effectiveness while maintaining remarkable efficiency. Code is available at https://github.com/Jackbrocp/AdaAugment.

cs.CV↗

arXiv2025

RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment

Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more data-efficient training paradigms. Data selection has shown promise to mitigate redundancy by identifying the most representative samples, thereby reducing training costs without compromising performance. Existing methods typically rely on static scoring metrics or pretrained models, overlooking the combined effect of selected samples and their evolving dynamics during training. We introduce the concept of epsilon-sample cover, which quantifies sample redundancy based on inter-sample relationships, capturing the intrinsic structure of the dataset. Based on this, we reformulate data selection as a reinforcement learning (RL) process and propose RL-Selector, where a lightweight RL agent optimizes the selection policy by leveraging epsilon-sample cover derived from evolving dataset distribution as a reward signal. Extensive experiments across benchmark datasets and diverse architectures demonstrate that our method consistently outperforms existing state-of-the-art baselines. Models trained with our selected datasets show enhanced generalization performance with improved training efficiency.

cs.LG↗

arXiv2024

Doppler Tracking Data of Martian Mission Tianwen-I and Upper Limit of Stochastic Gravitational Wave Background

Two way ranging data for spacecraft tracking of China's first Martian mission Tianwen-I is analysed. Shortly before the spacecraft entered the Mars parking orbit, the two way coherent microwave link between the spacecraft and the Earth resembles a long arm gravitational wave interferometer, with both the spacecraft and the Earth regarded as in an approximate free falling state. By carefully selecting and analysing data segments of the time series of the two way ranging data during this time span, a parametric statistical model is built for the data segments and an upper limit for the stochastic gravitational waves background (SGWB) is then estimated within the frequency window 0.1Hz to 0.1 mHz. The upper bound improves considerably on those obtained before. In particular, around the deci-Hz band, there is a three orders improvement on the bound obtained previously by the two way ranging data of the Chang e 3 mission. Scientific applications of the upper bound is then considered and a weak upper bound is worked out for axions which is a promising candidate for ultra light dark matter.

gr-qc↗

arXiv2022

Detecting the oscillation and propagation of the nascent dynamic solar wind structure at 2.6 solar radii using VLBI radio telescopes

Probing the solar corona is crucial to study the coronal heating and solar wind acceleration. However, the transient and inhomogeneous solar wind flows carry large-amplitude inherent Alfven waves and turbulence, which make detection more difficult. We report the oscillation and propagation of the solar wind at 2.6 solar radii (Rs) by observation of China Tianwen and ESA Mars Express with radio telescopes. The observations were carried out on Oct.9 2021, when one coronal mass ejection (CME) passed across the ray paths of the telescope beams. We obtain the frequency fluctuations (FF) of the spacecraft signals from each individual telescope. Firstly, we visually identify the drift of the frequency spikes at a high spatial resolution of thousands of kilometers along the projected baselines. They are used as traces to estimate the solar wind velocity. Then we perform the cross-correlation analysis on the time series of FF from different telescopes. The velocity variations of solar wind structure along radial and tangential directions during the CME passage are obtained. The oscillation of tangential velocity confirms the detection of streamer wave. Moreover, at the tail of the CME, we detect the propagation of an accelerating fast field-aligned density structure indicating the presence of magnetohydrodynamic waves. This study confirm that the ground station-pairs are able to form particular spatial projection baselines with high resolution and sensitivity to study the detailed propagation of the nascent dynamic solar wind structure.

astro-ph.SR↗

arXiv2021

VLBI data processing on coronal radio-sounding experiments of Mars express

The ESA's Mars Express solar corona experiments were performed at two solar conjunctions in the years 2015 and 2017 by a number of radio telescopes in the European VLBI Network. This paper presents the methods to measure the frequency and phase fluctuations of the spacecraft radio signal, and the applications to study the characteristics of the plasma turbulence effects on the signal at a single station and at multiple stations via cross-correlation. The power spectra of the frequency fluctuations observed between 4.9 and 76.3 $\rm R_{s}$ have a power-law shape close to a Kolmogorov spectrum over the frequency interval $ ν_{lo}< ν<ν_{up}$, where the nominal value of $ν_{lo}$ is set to 3 mHz and $ν_{up}$ is in the range of 0.03 $\sim$ 0.15 Hz. The RMS of the frequency fluctuations is presented as a function of the heliocentric distance. Furthermore, we analyse the variations of the electron column density fluctuations at solar offsets 4.9 $\rm{R_{s}}$ and 9.9 $\rm{R_{s}}$ and the cross-correlation products between the VLBI stations. The power density of the differential fluctuations between different stations decreases at $ν< 0.01$ Hz. Finally, the fast flow speeds of solar wind $>700$ $\rm{km~s^{-1}}$ are derived from the cross-correlation of frequency fluctuations at $ν< 0.01$ Hz. The fast flow speeds of solar wind correspond to the high heliolatitude of the coronal region that the radio rays passed. The VLBI observations and analysis methods can be used to study the electron column density fluctuations and the turbulence at multiple spatial points in the inner solar wind by providing multiple lines of sight between the Earth and the spacecraft.

astro-ph.IM↗