arXiv subjects

Xing Luo

Publications and source records attributed to Xing Luo.

11 recordsLinked to original sources

arXiv2026

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization

Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by introducing cross-layer residuals to reduce error accumulated from previous layers.However, these residuals may also introduce additional bias arising from the Hessian-approximation (HA) assumption underlying reconstruction-based PTQ, leading to suboptimal quantization performance.In this work, we analyze that multiplying the residual term by a scaling coefficient provides a direct way to mitigate the HA bias associated with residual strength, while preserving accumulated-error correction. More importantly, we observe that this trade-off is module-dependent, making a single global residual strength insufficient to balance effective correction and residual-related bias across modules.Based on these observations, we propose Module-Adaptive Residual Reconstruction (MARR), which assigns a module-specific scaling coefficient to adaptively balance accumulated-error correction and residual-related HA bias for each module.To avoid expensive per-module coefficient search and obtain a stable coefficient estimate, we design a Proportional-Integral-Derivative (PID)-based adaptive update strategy that uses reconstruction error as feedback to progressively refine this coefficient. Experiments on several typical large language models (LLMs) and vision transformers (ViTs) demonstrate the effectiveness of MARR under low-bit quantization (less than or equal to 4-bit), achieving up to 20.2% performance gains on LLMs and up to 4.6% relative gains on ViTs over the residual reconstruction state-of-the-art methods.Code will be made publicly available upon acceptance.

cs.LG↗

arXiv2026

Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline

When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images.

cs.CV↗

arXiv2026

Warm Debris Disk Candidates around Nearby FGK Stars from LAMOST DR12

Warm debris disks around main-sequence stars trace late-stage terrestrial planet formation. Motivated by the need for systematic searches of such systems, we identify debris disk candidates around FGK stars within 150 pc by combining a spectroscopically selected sample from LAMOST DR12 with Gaia astrometry and multi-band infrared photometry. Infrared excesses are identified through SED fitting and validated using conservative, source-by-source checks. This approach yields a final sample of 12 debris disk candidates including ten new detections. Stellar age research indicate that most of the host stars are several billion years old. NEOWISE monitoring reveals no significant W1/W2 variability, consistent with a circumstellar origin of the infrared excess. while a search for co-moving companions using Gaia DR3 reveals possible companions for only two candidates at very large projected separations ($\gtrsim 10^4$~au). Three candidates exhibit excess emission in both the W3 and W4 bands, allowing estimates of characteristic dust properties. This work establishes a small yet reliable sample of debris disk candidates anchored in homogeneous LAMOST spectroscopy, providing a foundation for future studies of debris disk evolution and stellar activity.

astro-ph.EP↗

arXiv2026

Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration

All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are often constrained by coarse-grained control mechanisms or fixed mapping schedules, yielding suboptimal adaptation. To address this, we propose an Uncertainty-Aware Diffusion Bridge Model (UDBM), which innovatively reformulates AiOIR as a stochastic transport problem steered by pixel-wise uncertainty. By introducing a relaxed diffusion bridge formulation which replaces the strict terminal constraint with a relaxed constraint, we model the uncertainty of degradations while theoretically resolving the drift singularity inherent in standard diffusion bridges. Furthermore, we devise a dual modulation strategy: the noise schedule aligns diverse degradations into a shared high-entropy latent space, while the path schedule adaptively regulates the transport trajectory motivated by the viscous dynamics of entropy regularization. By effectively rectifying the transport geometry and dynamics, UDBM achieves state-of-the-art performance across diverse restoration tasks within a single inference step.

cs.CV↗

arXiv2025

SC3EF: A Joint Self-Correlation and Cross-Correspondence Estimation Framework for Visible and Thermal Image Registration

Multispectral imaging plays a critical role in a range of intelligent transportation applications, including advanced driver assistance systems (ADAS), traffic monitoring, and night vision. However, accurate visible and thermal (RGB-T) image registration poses a significant challenge due to the considerable modality differences. In this paper, we present a novel joint Self-Correlation and Cross-Correspondence Estimation Framework (SC3EF), leveraging both local representative features and global contextual cues to effectively generate RGB-T correspondences. For this purpose, we design a convolution-transformer-based pipeline to extract local representative features and encode global correlations of intra-modality for inter-modality correspondence estimation between unaligned visible and thermal images. After merging the local and global correspondence estimation results, we further employ a hierarchical optical flow estimation decoder to progressively refine the estimated dense correspondence maps. Extensive experiments demonstrate the effectiveness of our proposed method, outperforming the current state-of-the-art (SOTA) methods on representative RGB-T datasets. Furthermore, it also shows competitive generalization capabilities across challenging scenarios, including large parallax, severe occlusions, adverse weather, and other cross-modal datasets (e.g., RGB-N and RGB-D).

cs.CV↗

arXiv2025

MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion

Generative models have made remarkable advancements and are capable of producing high-quality content. However, performing controllable editing with generative models remains challenging, due to their inherent uncertainty in outputs. This challenge is praticularly pronounced in motion editing, which involves the processing of spatial information. While some physics-based generative methods have attempted to implement motion editing, they typically operate on single-view images with simple motions, such as translation and dragging. These methods struggle to handle complex rotation and stretching motions and ensure multi-view consistency, often necessitating resource-intensive retraining. To address these challenges, we propose MotionDiff, a training-free zero-shot diffusion method that leverages optical flow for complex multi-view motion editing. Specifically, given a static scene, users can interactively select objects of interest to add motion priors. The proposed Point Kinematic Model (PKM) then estimates corresponding multi-view optical flows during the Multi-view Flow Estimation Stage (MFES). Subsequently, these optical flows are utilized to generate multi-view motion results through decoupled motion representation in the Multi-view Motion Diffusion Stage (MMDS). Extensive experiments demonstrate that MotionDiff outperforms other physics-based generative motion editing methods in achieving high-quality multi-view consistent motion results. Notably, MotionDiff does not require retraining, enabling users to conveniently adapt it for various down-stream tasks.

cs.CV↗

arXiv2023

BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models

Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles. However, their robustness against diverse style shifts, crucial for practical applications, remains largely unexplored. In this paper, we propose a new benchmark, BenchLMM, to assess the robustness of LMMs against three different styles: artistic image style, imaging sensor style, and application style, where each style has five sub-styles. Utilizing BenchLMM, we comprehensively evaluate state-of-the-art LMMs and reveal: 1) LMMs generally suffer performance degradation when working with other styles; 2) An LMM performs better than another model in common style does not guarantee its superior performance in other styles; 3) LMMs' reasoning capability can be enhanced by prompting LMMs to predict the style first, based on which we propose a versatile and training-free method for improving LMMs; 4) An intelligent LMM is expected to interpret the causes of its errors when facing stylistic variations. We hope that our benchmark and analysis can shed new light on developing more intelligent and versatile LMMs.

cs.CV↗

arXiv2021

An Adaptive Deep Learning Framework for Day-ahead Forecasting of Photovoltaic Power Generation

Accurate forecasts of photovoltaic power generation (PVPG) are essential to optimize operations between energy supply and demand. Recently, the propagation of sensors and smart meters has produced an enormous volume of data, which supports the development of data based PVPG forecasting. Although emerging deep learning (DL) models, such as the long short-term memory (LSTM) model, based on historical data, have provided effective solutions for PVPG forecasting with great successes, these models utilize offline learning. As a result, DL models cannot take advantage of the opportunity to learn from newly-arrived data, and are unable to handle concept drift caused by installing extra PV units and unforeseen PV unit failures. Consequently, to improve day-ahead PVPG forecasting accuracy, as well as eliminate the impacts of concept drift, this paper proposes an adaptive LSTM (AD-LSTM) model, which is a DL framework that can not only acquire general knowledge from historical data, but also dynamically learn specific knowledge from newly-arrived data. A two-phase adaptive learning strategy (TP-ALS) is integrated into AD-LSTM, and a sliding window (SDWIN) algorithm is proposed, to detect concept drift in PV systems. Multiple datasets from PV systems are utilized to assess the feasibility and effectiveness of the proposed approaches. The developed AD-LSTM model demonstrates greater forecasting capability than the offline LSTM model, particularly in the presence of concept drift. Additionally, the proposed AD-LSTM model also achieves superior performance in terms of day-ahead PVPG forecasting compared to other traditional machine learning models and statistical models in the literature.

cs.LG↗

arXiv2019

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving and video surveillance. However, it still remains a crucial challenge to train a reliable detector working well in different multispectral pedestrian datasets without manual annotations. In this paper, we propose a novel unsupervised domain adaptation framework for multispectral pedestrian detection, by iteratively generating pseudo annotations and updating the parameters of our designed multispectral pedestrian detector on target domain. Pseudo annotations are generated using the detector trained on source domain, and then updated by fixing the parameters of detector and minimizing the cross entropy loss without back-propagation. Training labels are generated using the pseudo annotations by considering the characteristics of similarity and complementarity between well-aligned visible and infrared image pairs. The parameters of detector are updated using the generated labels by minimizing our defined multi-detection loss function with back-propagation. The optimal parameters of detector can be obtained after iteratively updating the pseudo annotations and parameters. Experimental results show that our proposed unsupervised multimodal domain adaptation method achieves significantly higher detection performance than the approach without domain adaptation, and is competitive with the supervised multispectral pedestrian detectors.

cs.CV↗

arXiv2017

In situ high resolution real-time quantum efficiency imaging for photocathodes

Aspects of the preparation process and performance degradation are two major problems of photocathodes. The lack of a means for dynamic quantum efficiency measurements results in the inability to observe the inhomogeneity of the cathode surface by fine structural analysis and in real time.Here we present a simple and scalable technique for in situ real-time quantum efficiency diagnosis. An incoherent light source provides uniform illumination on the cathode surface, and solenoid magnets are used as lens for focusing and imaging the emitted electron beam on a downstream scintillator screen, which converts the quantum efficiency information into fluorescence intensity distribution. The microscopic discontinuity and the dynamic changes of the quantum efficiency of a gallium arsenide photocathode are observed at a resolution of a few microns. An unexpected uneven decrease of the quantum efficiency is also recorded. The work demonstrates a new observation method for photoemission materials research.

physics.app-ph↗

arXiv2014

Design and test of frequency tuner for CAEP high power THz free-electron laser

Peking University is developing a 1.3 GHz superconducting accelerating section for China Academy of Engineering Physics (CAEP) high power THz free-electron laser. A compact fast/slow tuner has developed by Institute of High Energy Physics (IHEP) for the accelerating section, to control Lorentz detuning, beam loading effect, compensate for microphonics and liquid Helium pressure fluctuations. The tuner design, warm test and cold test of the first prototype are presented.

physics.acc-ph↗