arXiv subjects

Lei Ding

Publications and source records attributed to Lei Ding.

At least 37 records · Page 2Linked to original sources

arXiv2026

It Takes Two: Your GRPO Is Secretly DPO

GRPO has emerged as a prominent reinforcement learning algorithm for post-training LLMs. Unlike critic-based methods, GRPO computes advantages by estimating the \emph{value baselines} from group-level statistics, eliminating the need for a critic network. Consequently, the prevailing view emphasizes the necessity of large group sizes, which are assumed to yield more accurate statistical estimates. In this paper, we propose a different view that the efficacy of GRPO stems from its implicit contrastive objective in the optimization, which helps reduce variance via the control variate method. This makes GRPO structurally related to preference learning methods such as DPO. This perspective motivates 2-GRPO, a minimal group-size variant that constructs contrastive signals with only two rollouts. We provide a rigorous theoretical analysis of 2-GRPO and empirically validate its effectiveness: 2-GRPO retains $97.6\%$ of the performance of 16-GRPO, while requiring only $12.5\%$ of the rollouts and $21\%$ of the training time.

cs.LG↗

arXiv2026

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

Large Language Models (LLMs) equipped with modern Retrieval-Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to interface with search engines for complex reasoning tasks. However, such multi-turn interactions inevitably produce long intermediate contexts, as context length grows exponentially with exploration depth. This leads to a well-known limitation of LLMs: their difficulty in effectively leveraging information from long contexts. This problem is further amplified in RAG systems that depend on in-context learning, where few-shot demonstrations must also be included in the prompt, compounding the context-length bottleneck. To address these challenges, we propose Mujica-MyGo, a unified framework for efficient multi-turn reasoning in RAG. Inspired by the divide-and-conquer principle, we introduce Mujica (Multi-hop Joint Intelligence for Complex Question Answering), a multi-agent RAG workflow that decomposes multi-turn interactions into cooperative sub-interactions, thereby mitigating long-context issues. To eliminate the dependency on in-context learning, we further develop MyGO (Minimalist Policy Gradient Optimization), a lightweight and efficient reinforcement learning algorithm that enables effective post-training of LLMs within complex RAG pipelines. We provide theoretical guarantees for MyGO's convergence to the optimal policy. Empirical evaluations across diverse question-answering benchmarks, covering both text corpora and knowledge graphs, show that Mujica-MyGO achieves superior performance.

cs.CL↗

arXiv2025

Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones

Accurately and swiftly assessing damage from conflicts is crucial for humanitarian aid and regional stability. In conflict zones, damaged zones often share similar architectural styles, with damage typically covering small areas and exhibiting blurred boundaries. These characteristics lead to limited data, annotation difficulties, and significant recognition challenges, including high intra-class similarity and ambiguous semantic changes. To address these issues, we introduce a pre-trained DINOv3 model and propose a multi-scale cross-attention difference siamese network (MC-DiSNet). The powerful visual representation capability of the DINOv3 backbone enables robust and rich feature extraction from bi-temporal remote sensing images. The multi-scale cross-attention mechanism allows for precise localization of subtle semantic changes, while the difference siamese structure enhances inter-class feature discrimination, enabling fine-grained semantic change detection. Furthermore, a simple yet powerful lightweight decoder is designed to generate clear detection maps while maintaining high efficiency. We also release a new Gaza-change dataset containing high-resolution satellite image pairs from 2023-2024 with pixel-level semantic change annotations. It is worth emphasizing that our annotations only include semantic pixels of changed areas. We evaluated our method on the Gaza-Change and two classical datasets: the SECOND and Landsat-SCD datasets. Experimental results demonstrate that our proposed approach effectively addresses the MCD task, and its outstanding performance paves the way for practical applications in rapid damage assessment across conflict zones.

cs.CV↗

arXiv2025

ChessMamba: Structure-Aware Interleaving of State Spaces for Change Detection in Remote Sensing Images

Change detection (CD) in multitemporal remote sensing imagery presents significant challenges for fine-grained recognition, owing to heterogeneity and spatiotemporal misalignment. However, existing methodologies based on vision transformers or state-space models typically disrupt local structural consistency during temporal serialization, obscuring discriminative cues under misalignment and hindering reliable change localization. To address this, we introduce ChessMamba, a structure-aware framework leveraging interleaved state-space modeling for robust CD with multi-temporal inputs. ChessMamba integrates a SpatialMamba encoder with a lightweight cross-source interaction module, featuring two key innovations: (i) Chessboard interleaving with snake scanning order, which serializes multi-temporal features into a unified sequence within a single forward pass, thereby shortening interaction paths and enabling direct comparison for accurate change localization; and (ii) Structure-aware fusion via multi-dilated convolutions, selectively capturing center-and-corner neighborhood contexts within each mono-temporal. Comprehensive evaluations on three CD tasks, including binary CD, semantic CD and multimodal building damage assessment, demonstrate that ChessMamba effectively fuses heterogeneous features and achieves substantial accuracy improvements over state-of-the-art methods.The relevant code will be available at: github.com/DingLei14/ChessMamba.

cs.CV↗

arXiv2025

$\text{R}^2\text{R}$: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers

Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and naive fine-tuning causes surface-form overfitting and catastrophic forgetting. To address this challenge, we introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy, Entity Abstraction for Generalization (EAG). EAG introduces a counter-shortcut mechanism by masking the most predictive surface cues, forcing the reranker to learn domain-invariant relevance patterns rather than memorizing dataset-specific entities. To efficiently activate domain experts, R2R employs a lightweight Latent Semantic Router that probes internal representations from the frozen backbone decoder to select the optimal LoRA expert per query. Extensive experiments across different reranker backbones and diverse domains (legal, medical, and financial) demonstrate that R2R consistently surpasses generalist and single-domain fine-tuned baselines. Our results confirm that R2R is a model-agnostic and modular approach to domain specialization with strong cross-domain robustness.

cs.CL↗

arXiv2025

Adaptive Coopetition: Leveraging Coarse Verifier Signals for Resilient Multi-Agent LLM Reasoning

Inference-time computation is a critical yet challenging paradigm for enhancing the reasoning performance of large language models (LLMs). While existing strategies improve reasoning stability and consistency, they suffer from notable limitations: self-correction often reinforces the model's initial biases, and Multi-Agent Collaboration (MAC) often fails due to the lack of efficient coordination mechanisms, leading to collective errors. Although high-performing verifiers can detect reasoning errors, making them reliable requires substantial training. To address these challenges, we introduce a novel inference-time framework, Adaptive Coopetition (AdCo), in which LLM agents utilize an adaptive, UCB-based "coopetition" mechanism. At each round, agents leverage coarse verifier signals to determine whether to collaborate or compete, and iteratively refine their reasoning based on peer feedback. Without relying on high-performance verifiers, our adaptive strategy achieves significant performance gains on mathematical reasoning benchmarks, yielding a 20% relative improvement over baselines on the more challenging dataset. Our approach remains robust and consistent in terms of accuracy under different sample sizes and configurations. This adaptive, signal-guided "coopetition" framework enhances reasoning robustness by leveraging both model knowledge diversity and reasoning trace measures, while also promoting uncertainty-driven exploration, especially when participants have comparable capabilities. From this perspective, our work offers a fresh lens on inference-time computation and paves the way for more resilient multi-agent LLM systems. Our code is available at: https://github.com/AdCo-Research/adaptive-coopetition.

cs.MA↗

arXiv2025

Colossal Cryogenic Electro-Optic Response Through Metastability in Strained BaTiO$_{3}$ Thin Films

The search for thin film electro-optic (EO) materials that can retain superior performance under cryogenic conditions has become critical for quantum computing. Barium titanate thin films show large linear EO coefficients in the tetragonal phase at room temperature, which is severely degraded down to ~200 pm V$^{-1}$ in the rhombohedral phase at cryogenic temperatures. There is immense interest in manipulating these phase transformations and retaining superior EO properties down to liquid helium temperature. Utilizing the thermodynamic theory of optical properties, a large low-temperature EO response is designed by engineering the energetic competition between different ferroelectric phases, leading to a low-symmetry monoclinic phase with a massive EO response. The existence of this phase is demonstrated in a strain-tuned BaTiO$_{3}$ thin film that exhibits a linear EO coefficient of 2516 +/- 100 pm V$^{-1}$ at 5 K, which is an order of magnitude higher than the best reported performance thus far. Importantly, the EO coefficient increases by 100x during cooling, unlike the conventional films, where it degrades. Further, at the lowest temperature, significant higher order EO responses also emerge. These results represent a new framework for designing materials with property enhancements by stabilizing highly tunable metastable phases with strain. Copyright 2025 The Author(s). Advanced Materials published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. (A. Suceava, S. Hazra, A. Ross, et al. "Colossal Cryogenic Electro-Optic Response Through Metastability in Strained BaTiO3 Thin Films." Adv. Mater. (2025): e07564. https://doi.org/10.1002/adma.202507564)

cond-mat.mtrl-sci↗

arXiv2025

VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering

Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git.

cs.IR↗

arXiv2025

Physics-informed neural network enhanced multispectral single-pixel imaging with a chip spectral sensor

Multispectral imaging (MSI) captures data across multiple spectral bands, offering enhanced informational depth compared to standard RGB imaging and benefiting diverse fields such as agriculture, medical diagnostics, and industrial inspection. Conventional MSI systems, however, suffer from high cost, complexity, and limited performance in low-light conditions. Moreover, data-driven MSI methods depend heavily on large, labeled training datasets and struggle with generalization. In this work, we present a portable multispectral single-pixel imaging (MS-SPI) method that integrates a chip-sized multispectral sensor for system miniaturization and leverages an untrained physics-informed neural network (PINN) to reconstruct high-quality spectral images without the need for labeled training data. The physics-informed structure of the network enables the self-corrected reconstruction of multispectral images directly with the input of raw measurements from the multispectral sensor. Our proof-of-concept prototype achieves the reconstruction of 12-channel high-quality spectral images at the sampling rate of 10%. We also experimentally validate its performance under varying sampling rate conditions, by comparing it with conventional compressive sensing algorithms. Furthermore, we demonstrate the application of this technique to an MSI-based image segmentation task, in which spatial regions are discriminated according to their characteristic spectral signatures. This compact, high-fidelity, and portable approach offers promising pathways to lightweight and cost-effective spectral imaging on mobile platforms.

physics.ins-det↗

arXiv2025

S2C: Learning Noise-Resistant Differences for Unsupervised Change Detection in Multimodal Remote Sensing Images

Unsupervised Change Detection (UCD) in multimodal Remote Sensing (RS) images remains a difficult challenge due to the inherent spatio-temporal complexity within data, and the heterogeneity arising from different imaging sensors. Inspired by recent advancements in Visual Foundation Models (VFMs) and Contrastive Learning (CL) methodologies, this research aims to develop CL methodologies to translate implicit knowledge in VFM into change representations, thus eliminating the need for explicit supervision. To this end, we introduce a Semantic-to-Change (S2C) learning framework for UCD in both homogeneous and multimodal RS images. Differently from existing CL methodologies that typically focus on learning multi-temporal similarities, we introduce a novel triplet learning strategy that explicitly models temporal differences, which are crucial to the CD task. Furthermore, random spatial and spectral perturbations are introduced during the training to enhance robustness to temporal noise. In addition, a grid sparsity regularization is defined to suppress insignificant changes, and an IoU-matching algorithm is developed to refine the CD results. Experiments on four benchmark CD datasets demonstrate that the proposed S2C learning framework achieves significant improvements in accuracy, surpassing current state-of-the-art by over 31\%, 9\%, 23\%, and 15\%, respectively. It also demonstrates robustness and sample efficiency, suitable for training and adaptation of various Visual Foundation Models (VFMs) or backbone neural networks. The relevant code will be available at: github.com/DingLei14/S2C.

cs.CV↗

arXiv2025

A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges

In the last decade, the rapid development of deep learning (DL) has made it possible to perform automatic, accurate, and robust Change Detection (CD) on large volumes of Remote Sensing Images (RSIs). However, despite advances in CD methods, their practical application in real-world contexts remains limited due to the diverse input data and the applicational context. For example, the collected RSIs can be time-series observations, and more informative results are required to indicate the time of change or the specific change category. Moreover, training a Deep Neural Network (DNN) requires a massive amount of training samples, whereas in many cases these samples are difficult to collect. To address these challenges, various specific CD methods have been developed considering different application scenarios and training resources. Additionally, recent advancements in image generation, self-supervision, and visual foundation models (VFMs) have opened up new approaches to address the 'data-hungry' issue of DL-based CD. The development of these methods in broader application scenarios requires further investigation and discussion. Therefore, this article summarizes the literature methods for different CD tasks and the available strategies and techniques to train and deploy DL-based CD methods in sample-limited scenarios. We expect that this survey can provide new insights and inspiration for researchers in this field to develop more effective CD methods that can be applied in a wider range of contexts.

cs.CV↗

arXiv2024

Right this way: Can VLMs Guide Us to See More to Answer Questions?

In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assisting visually impaired individuals who often need guidance to capture images correctly. To evaluate this capability of current VLMs, we introduce a human-labeled dataset as a benchmark for this task. Additionally, we present an automated framework that generates synthetic training data by simulating ``where to know'' scenarios. Our empirical results show significant performance improvements in mainstream VLMs when fine-tuned with this synthetic data. This study demonstrates the potential to narrow the gap between information assessment and acquisition in VLMs, bringing their performance closer to humans.

cs.CV↗

arXiv2024

Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding

Graphical User Interfaces (GUIs) are central to our interaction with digital devices and growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (ScreenPR) task. Currently, this task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a novel ToL grounding mechanism, to address the ScreenPR task. Based on the input point coordinate and the corresponding GUI screenshot, our ToL agent constructs a Hierarchical Layout Tree. Based on the tree, our ToL agent not only comprehends the content of the indicated area but also articulates the layout and spatial relationships between elements. Such layout information is crucial for accurately interpreting information on the screen, distinguishing our ToL agent from other screen reading tools. We also thoroughly evaluate the ToL agent against other baselines on a newly proposed ScreenPR benchmark, which includes GUIs from mobile, web, and operating systems. Last but not least, we test the ToL agent on mobile GUI navigation tasks, demonstrating its utility in identifying incorrect actions along the path of agent execution trajectories. Code and data: https://screen-point-and-read.github.io

cs.CL↗

arXiv2024

Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solution

As Artificial Intelligence models, such as Large Video-Language models (VLMs), grow in size, their deployment in real-world applications becomes increasingly challenging due to hardware limitations and computational costs. To address this, we design a hybrid edge-cloud solution that leverages the efficiency of smaller models for local processing while deferring to larger, more accurate cloud-based models when necessary. Specifically, we propose a novel unsupervised data generation method, Dual-Model Distillation (DMD), to train a lightweight switcher model that can predict when the edge model's output is uncertain and selectively offload inference to the large model in the cloud. Experimental results on the action classification task show that our framework not only requires less computational overhead, but also improves accuracy compared to using a large model alone. Our framework provides a scalable and adaptable solution for action classification in resource-constrained environments, with potential applications beyond healthcare. Noteworthy, while DMD-generated data is used for optimizing performance and resource usage in our pipeline, we expect the concept of DMD to further support future research on knowledge alignment across multiple models.

cs.CV↗

arXiv2024

Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking

Many people use search engines to find online guidance to solve computer or mobile device problems. Users frequently encounter challenges in identifying effective solutions from search results, often wasting time trying ineffective solutions that seem relevant yet fail to solve real problems. This paper introduces a novel approach to improving the accuracy and relevance of online technical support search results through automated search results verification and reranking. Taking "How-to" queries specific to on-device execution as a starting point, we developed the first solution that allows an AI agent to interpret and execute step-by-step instructions in the search results in a controlled Android environment. We further integrated the agent's findings into a reranking mechanism that orders search results based on the success indicators of the tested solutions. The paper details the architecture of our solution and a comprehensive evaluation of the system through a series of tests across various application domains. The results demonstrate a significant improvement in the quality and reliability of the top-ranked results. Our findings suggest a paradigm shift in how search engine ranking for online technical support help can be optimized, offering a scalable and automated solution to the pervasive challenge of finding effective and reliable online help.

cs.IR↗

arXiv2024

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. To address this, we propose a soft deduplication method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. Central to our approach is the concept of "data commonness", a metric we introduce to quantify the degree of duplication by measuring the occurrence probabilities of samples using an n-gram model. Empirical analysis shows that this method significantly improves training efficiency, achieving comparable perplexity scores with at least a 26% reduction in required training steps. Additionally, it enhances average few-shot downstream accuracy by 1.77% when trained for an equivalent duration. Importantly, this approach consistently improves performance, even on rigorously deduplicated datasets, indicating its potential to complement existing methods and become a standard pre-training process for LLMs.

cs.CL↗

arXiv2024

Multi-photon super-linear image scanning microscopy using upconversion nanoparticles

Super-resolution fluorescence microscopy is of great interest in life science studies for visualizing subcellular structures at the nanometer scale. Among various kinds of super-resolution approaches, image scanning microscopy (ISM) offers a doubled resolution enhancement in a simple and straightforward manner, based on the commonly used confocal microscopes. ISM is also suitable to be integrated with multi-photon microscopy techniques, such as two-photon excitation and second-harmonic generation imaging, for deep tissue imaging, but it remains the twofold limited resolution enhancement and requires expensive femtosecond lasers. Here, we present and experimentally demonstrate the super-linear ISM (SL-ISM) to push the resolution enhancement beyond the factor of two, with a single low-power, continuous-wave, and near-infrared laser, by harnessing the emission nonlinearity within the multiphoton excitation process of lanthanide-doped upconversion nanoparticles (UCNPs). Based on a modified confocal microscope, we achieve a resolution of about 120 nm, 1/8th of the excitation wavelength. Furthermore, we demonstrate a parallel detection strategy of SL-ISM with the multifocal structured excitation pattern, to speed up the acquisition frame rate. This method suggests a new perspective for super-resolution imaging or sensing, multi-photon imaging, and deep-tissue imaging with simple, low-cost, and straightforward implementations.

physics.optics↗

arXiv2024

Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images

Vision Foundation Models (VFMs) such as the Segment Anything Model (SAM) allow zero-shot or interactive segmentation of visual contents, thus they are quickly applied in a variety of visual scenes. However, their direct use in many Remote Sensing (RS) applications is often unsatisfactory due to the special imaging characteristics of RS images. In this work, we aim to utilize the strong visual recognition capabilities of VFMs to improve the change detection of high-resolution Remote Sensing Images (RSIs). We employ the visual encoder of FastSAM, an efficient variant of the SAM, to extract visual representations in RS scenes. To adapt FastSAM to focus on some specific ground objects in the RS scenes, we propose a convolutional adaptor to aggregate the task-oriented change information. Moreover, to utilize the semantic representations that are inherent to SAM features, we introduce a task-agnostic semantic learning branch to model the semantic latent in bi-temporal RSIs. The resulting method, SAMCD, obtains superior accuracy compared to the SOTA methods and exhibits a sample-efficient learning ability that is comparable to semi-supervised CD methods. To the best of our knowledge, this is the first work that adapts VFMs for the CD of HR RSIs.

cs.CV↗