arXiv subjects

Lei Xiong

Publications and source records attributed to Lei Xiong.

At least 19 recordsLinked to original sources

arXiv2026

Fine-Grained Visual Preprocessing and Dual-Stream Temporal Modeling for Multimodal Sentiment Analysis on Social Media

Multimodal sentiment analysis often remains text-dominant due to raw-video noise and insufficient temporal modeling. Using CH-SIMS v2.0S, this study proposes three improvements: the NAPS pipeline---a seven-stage system integrating face tracking,identity embedding, and normalized lip-motion analysis to reduce visual noise;DS-TANet, combining an EfficientNetB2 static stream, RAFT optical-flow motion stream, motion-guided attention, and Bi-GRU temporal modeling; and DS-TAFNet, fusing visual and MacBERT-Base textual representations via concatenation fusion. With NAPS, the static visual baseline achieves 80.98\% Macro F1, comparable to the text baseline of 80.55\%; DS-TANet improves visual Macro F1 to 82.58\%;and DS-TAFNet achieves 87.49\% accuracy and 87.48\% Macro F1. These results demonstrate that improving visual input quality and temporal representation is more effective than increasing fusion complexity under limited-data conditions.

cs.CV↗

arXiv2026

An adaptive parameter optimization method for astronomical image alignment using Bayesian optimization. I. A hierarchical search strategy for FWHM and SNR

The alignment and stacking of astronomical images are fundamental steps for detecting faint objects and performing high?precision astrometry. In traditional alignment workflows, the extraction of source lists is critically dependent on key parameters such as the Full Width at Half Maximum (FWHM) and the Signal-to-Noise Ratio (SNR) threshold. These parameters are often selected manually through an inefficient trial-error process that lacks objectivity and does not guarantee optimal results. We present an adaptive method for optimizing astronomical image alignment parameters based on Bayesian Optimization (BO). We frame the parameter search as an optimization problem, with an objective function designed to maximize the number of successfully matched source pairs. By employing a hierarchical search strategy, we perform an efficient global search for FWHM and SNR to automatically determine the optimal combination for a given observational dataset. Experimental results demonstrate that our method effectively handles image data with varying seeing conditions and back?ground noise levels. It rapidly converges to a robust set of alignment parameters, achieving sub-pixel accuracy and significantly improving the automation level and success rate of the alignment process. This work may provide a useful basis for developing large-scale, automated astronomical data processing pipelines

astro-ph.IM↗

arXiv2026

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do more than simply search longer: it should recursively improve its current answer by verifying intermediate results and using the partially verified state to guide subsequent refinement. We introduce AREX, a family of Recursively Self-Improving (RSI) deep research agents. AREX alternates between an inner research loop that gathers evidence and constructs a provisional answer, and an outer self-improvement loop that audits the answer constraint-wise, identifies unresolved claims, and launches targeted follow-up research. To sustain RSI over long horizons, AREX learns an autonomous context-update tool that compresses growing interaction history into a compact improvement state preserving verified evidence and unresolved constraints, without relying on an external model. We train AREX on verified synthetic tasks and high-quality trajectories through agentic mid-training and long-horizon reinforcement learning. To mitigate sparse final rewards during long horizon learning, we emphasize key steps where decisive evidence is acquired or erroneous research directions are corrected. We instantiate a dense 4B model and a 122B-A10B Mixture-of-Experts model. Across BrowseComp, WideSearch, DeepSearchQA, Humanity's Last Exam (HLE), and other reasoning and tool-use benchmarks, AREX substantially outperforms comparable-scale baselines and remains competitive with models using substantially more activated parameters.

cs.AI↗

arXiv2026

HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement

In practical applications, low-light images are often compressed for efficient storage and transmission. Most existing methods disregard compression artifacts removal or hardly establish a unified framework for joint task enhancement of low-light images with varying compression qualities. To address this problem, we propose an efficient hybrid priors-guided network (HPGN) that enhances compressed low-light images by integrating both compression and illumination priors. Our approach fully utilizes the JPEG quality factor (QF) and DCT quantization matrix (QM) to guide the design of efficient plug-and-play modules for joint tasks. Additionally, we employ a random QF generation strategy to guide model training, enabling a single model to enhance low-light images with different compression levels. Experimental results demonstrate the superiority of our proposed method.

eess.IV↗

arXiv2026

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to acquire evidence for verifying assumptions and supporting claims. To assess AI agents' capability in driving this process, we present AutoResearchBench, a dedicated benchmark for autonomous scientific literature discovery. AutoResearchBench consists of two complementary task types: (1) Deep Research, which requires tracking down a specific target paper through a progressive, multi-step probing process, and (2) Wide Research, which requires comprehensively collecting a set of papers satisfying given conditions. Compared to previous benchmarks on agentic web browsing, AutoResearchBench is distinguished along three dimensions: it is research-oriented, calling for in-depth comprehension of scientific concepts; literature-focused, demanding fine-grained utilization of detailed information; and open-ended, involving an unknown number of qualified papers and thus requiring deliberate reasoning and search throughout. These properties make AutoResearchBench uniquely suited for evaluating autonomous research capabilities, and extraordinarily challenging. Even the most powerful LLMs, despite having largely conquered general agentic web-browsing benchmarks such as BrowseComp, achieve only 9.39% accuracy on Deep Research and 9.31% IoU on Wide Research, while many other strong baselines fall below 5%. We publicly release the dataset and evaluation pipeline to facilitate future research in this direction. We publicly release the dataset, evaluation pipeline, and code at https://github.com/CherYou/AutoResearchBench.

cs.AI↗

arXiv2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite significant advancements in deep learning for image restoration, existing models still encounter substantial challenges in real-world low-light portrait scenarios. Specifically, they struggle to achieve an optimal balance among noise suppression, detail preservation, and faithful illumination and color reproduction. To bridge this gap, this challenge aims to establish a novel benchmark for real-world low-light portrait restoration. We comprehensively evaluate the proposed algorithms utilizing a hybrid evaluation system that integrates objective quantitative metrics with rigorous subjective assessment protocols. For this competition, we provide a dataset containing 800 groups of real-captured low-light portrait data. Each group consists of a 1K-resolution low-light input image, a 1K ground truth (GT), and a 1K person mask. This challenge has garnered widespread attention from both academia and industry, attracting over 100 participating teams and receiving more than 3,000 valid submissions. This report details the motivation behind the challenge, the dataset construction process, the evaluation metrics, and the various phases of the competition. The released dataset and baseline code for this track are publicly available from the same \href{https://github.com/zsn1434/AI_Flash-BaseLine/tree/main}{GitHub repository}, and the official challenge webpage is hosted on \href{https://www.codabench.org/competitions/12885/}{CodaBench}.

cs.CV↗

arXiv2026

PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific Papers

Leveraging Multi-modal Large Language Models (MLLMs) to accelerate frontier scientific research is promising, yet how to rigorously evaluate such systems remains unclear. Existing benchmarks mainly focus on single-document understanding, whereas real scientific workflows require integrating evidence from multiple papers, including their text, tables, and figures. As a result, multi-modal, multi-document scientific reasoning remains underexplored and lacks systematic evaluation. To address this gap, we introduce PaperScope, a multi-modal multi-document benchmark designed for agentic deep research. PaperScope presents three advantages: (1) Structured scientific grounding. It is built on a knowledge graph of over 2,000 AI papers spanning three years, providing a structured foundation for research-oriented queries. (2) Semantically dense evidence construction. It integrates semantically related key information nodes and employs optimized random-walk article selector to sample thematically coherent paper sets, thereby ensuring adequate semantic density and task complexity. (3) Multi-task evaluation of scientific reasoning. It contains over 2,000 QA pairs across reasoning, retrieval, summarization, and problem solving, enabling evaluation of multi-step scientific reasoning. Experimental results show that even advanced systems such as OpenAI Deep Research and Tongyi Deep Research achieve limited scores on PaperScope, highlighting the difficulty of long-context retrieval and deep multi-source reasoning. PaperScope thus provides a rigorous benchmark alongside a scalable pipeline for constructing large-scale multi-modal, multi-source deep research datasets.

cs.AI↗

arXiv2026

DeepXiv-SDK: An Agentic Data Interface for Scientific Literature

LLM-agents are increasingly used to accelerate the progress of scientific research. Yet a persistent bottleneck is data access: agents not only lack readily available tools for retrieval, but also have to work with unstrcutured, human-centric data on the Internet, such as HTML web-pages and PDF files, leading to excessive token consumption, limit working efficiency, and brittle evidence look-up. This gap motivates the development of \textit{an agentic data interface}, which is designed to enable agents to access and utilize scientific literature in a more effective, efficient, and cost-aware manner. In this paper, we introduce DeepXiv-SDK, which offers a three-layer agentic data interface for scientific literature. 1) Data Layer, which transforms unstructured, human-centric data into normalized and structured representations in JSON format, improving data usability and enabling progressive accessibility of the data. 2) Service Layer, which presents readily available tools for data access and ad-hoc retrieval. It also enables a rich form of agent usage, including CLI, MCP, and Python SDK. 3) Application Layer, which creates a built-in agent, packaging basic tools from the service layer to support complex data access demands. DeepXiv-SDK currently supports the complete ArXiv corpus, and is synchronized daily to incorporate new releases. It is designed to extend to all common open-access corpora, such as PubMed Central, bioRxiv, medRxiv, and chemRxiv. We release RESTful APIs, an open-source Python SDK, and a web demo showcasing deep search and deep research workflows. DeepXiv-SDK is free to use with registration.

cs.DL↗

arXiv2025

MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios. Existing benchmarks primarily probe surface-level semantic correspondence (e.g., object-text matching) while failing to assess the deeper reasoning required to capture complex relationships between visual and textual information. To address this gap, we introduce MR$^2$-Bench, a reasoning-intensive benchmark for multimodal retrieval. MR$^2$-Bench presents the following critical values: 1) all tasks are reasoning-driven, going beyond shallow matching to effectively assess models' capacity for logical, spatial, and causal inference; 2) it features diverse multimodal data, such as natural images, diagrams, and visual puzzles, enabling comprehensive evaluation across content types; 3) it supports complex queries and documents containing multiple images and covers diverse retrieval scenarios, more accurately reflecting real-world applications. Our benchmark contains 1,309 curated queries, derived either from manual collection and annotation or from selective consolidation of public datasets. Despite achieving strong results on existing benchmarks, current state-of-the-art models still struggle on MR$^2$-Bench: for example, the leading Seed1.6-Embedding model attains a Recall@1 of 77.78 on MMEB, but only 9.91 on MR$^2$-Bench. This substantial performance gap highlights both the increased challenge posed by our benchmark and the pressing need for further advances in reasoning-intensive multimodal retrieval. The dataset and evaluation code will be made publicly available at https://github.com/VectorSpaceLab/MR2-Bench.

cs.IR↗

arXiv2024

Transmission Scheduling of Millimeter Wave Communication for High-Speed Railway in Space-Air-Ground Integrated Network

The space-air-ground integrated network (SAGIN) greatly improves coverage and reliability for millimeter-wave (mmWave) communication in high-speed railway (HSR) scenarios. However, a significant challenge arises in the transmission scheduling due to the rapid changes in channel state, link selection for train mobile relays (MRs), and order of the flow scheduling. To tackle this challenge, we introduce an optimization problem focused on maximizing the weighted sum completed flows that satisfy the quality of service (QoS) requirements for HSR mmWave communication in SAGIN. To facilitate the simultaneous scheduling of flows by base station-MR (BS-MR), satellite-airship-MR, and satellite-MR links, we propose a link selection algorithm, which can help each flow choose a suitable set of links in every frame and determine whether the BS networks need the assistance of the satellite and airship. Furthermore, taking into account the priority and occupied time slots (TSs) resource of different flows, we propose a multi-link weighted flow scheduling (MWFS) algorithm. This algorithm not only prioritizes scheduling high-priority flows but also aims to maximize the weighted sum completed flows for MRs. Our simulation results confirm that the proposed algorithm significantly increases the weighted sum completed flows and the total transmitted bits. Additionally, the proposed algorithm can achieve the optimal flow transmission in different link switching periods and enhance the scheduling of high-priority flows compared to other algorithms.

cs.IT↗

arXiv2024

A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis

The rapid advancement of single-cell ATAC sequencing (scATAC-seq) technologies holds great promise for investigating the heterogeneity of epigenetic landscapes at the cellular level. The amplification process in scATAC-seq experiments often introduces noise due to dropout events, which results in extreme sparsity that hinders accurate analysis. Consequently, there is a significant demand for the generation of high-quality scATAC-seq data in silico. Furthermore, current methodologies are typically task-specific, lacking a versatile framework capable of handling multiple tasks within a single model. In this work, we propose ATAC-Diff, a versatile framework, which is based on a latent diffusion model conditioned on the latent auxiliary variables to adapt for various tasks. ATAC-Diff is the first diffusion model for the scATAC-seq data generation and analysis, composed of auxiliary modules encoding the latent high-level variables to enable the model to learn the semantic information to sample high-quality data. Gaussian Mixture Model (GMM) as the latent prior and auxiliary decoder, the yield variables reserve the refined genomic information beneficial for downstream analyses. Another innovation is the incorporation of mutual information between observed and hidden variables as a regularization term to prevent the model from decoupling from latent variables. Through extensive experiments, we demonstrate that ATAC-Diff achieves high performance in both generation and analysis tasks, outperforming state-of-the-art models.

q-bio.GN↗

arXiv2024

iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples

Aspect-based sentiment analysis (ABSA) have been extensively studied, but little light has been shed on the quadruple extraction consisting of four fundamental elements: aspects, categories, opinions and sentiments, especially with implicit aspects and opinions. In this paper, we propose a new method iACOS for extracting Implicit Aspects with Categories and Opinions with Sentiments. First, iACOS appends two implicit tokens at the end of a text to capture the context-aware representation of all tokens including implicit aspects and opinions. Second, iACOS develops a sequence labeling model over the context-aware token representation to co-extract explicit and implicit aspects and opinions. Third, iACOS devises a multi-label classifier with a specialized multi-head attention for discovering aspect-opinion pairs and predicting their categories and sentiments simultaneously. Fourth, iACOS leverages informative and adaptive negative examples to jointly train the multi-label classifier and the other two classifiers on categories and sentiments by multi-task learning. Finally, the experimental results show that iACOS significantly outperforms other quadruple extraction baselines according to the F1 score on two public benchmark datasets.

cs.CL↗

arXiv2024

Texture-guided Coding for Deep Features

With the rapid development of machine vision technology in recent years, many researchers have begun to focus on feature compression that is better suited for machine vision tasks. The target of feature compression is deep features, which arise from convolution in the middle layer of a pre-trained convolutional neural network. However, due to the large volume of data and high level of abstraction of deep features, their application is primarily limited to machine-centric scenarios, which poses significant constraints in situations requiring human-computer interaction. This paper investigates features and textures and proposes a texture-guided feature compression strategy based on their characteristics. Specifically, the strategy comprises feature layers and texture layers. The feature layers serve the machine, including a feature selection module and a feature reconstruction network. With the assistance of texture images, they selectively compress and transmit channels relevant to visual tasks, reducing feature data while providing high-quality features for the machine. The texture layers primarily serve humans and consist of an image reconstruction network. This image reconstruction network leverages features and texture images to reconstruct preview images for humans. Our method fully exploits the characteristics of texture and features. It eliminates feature redundancy, reconstructs high-quality preview images for humans, and supports decision-making. The experimental results demonstrate excellent performance when employing our proposed method to compress the deep features.

cs.CV↗

arXiv2023

The Limits of ChatGPT in Extracting Aspect-Category-Opinion-Sentiment Quadruples: A Comparative Analysis

Recently, ChatGPT has attracted great attention from both industry and academia due to its surprising abilities in natural language understanding and generation. We are particularly curious about whether it can achieve promising performance on one of the most complex tasks in aspect-based sentiment analysis, i.e., extracting aspect-category-opinion-sentiment quadruples from texts. To this end, in this paper we develop a specialized prompt template that enables ChatGPT to effectively tackle this complex quadruple extraction task. Further, we propose a selection method on few-shot examples to fully exploit the in-context learning ability of ChatGPT and uplift its effectiveness on this complex task. Finally, we provide a comparative evaluation on ChatGPT against existing state-of-the-art quadruple extraction models based on four public datasets and highlight some important findings regarding the capability boundaries of ChatGPT in the quadruple extraction.

cs.CL↗

arXiv2022

Polarization-independent resonant lattice Kerker effect in phase-change metasurface

Resonant lattice Kerker effect in periodic resonators is one of the most interesting generalizations of the Kerker effect that relates to various fascinating functionalities such as scattering management and Huygens metasurfaces. However, so far this effect has been shown to be sensitive to the incident polarization, restricting its applications. Here, we report, for the first time, polarization-independent resonant lattice Kerker effect in metasurfaces composed of periodic Ge$_2$Se$_2$Te$_5$ (GST) disks. For such a metasurface of square lattice, the spectrally overlap of the electric dipole and magnetic dipole surface lattice resonances can be realized by choosing an appropriate GST crystalline fraction regardless of the incident polarization. The operation wavelength and the required GST crystalline fraction can be conveniently tuned over large ranges since these parameters scale linearly with the disk size and the lattice period, greatly facilitating the design. Making use of the obtained resonant lattice Kerker effect, we realize a reconfigurable and polarization-independent lattice Huygens' metasurface with a dynamic phase modulation of close to $2π$ and high transmittance. This work will advance the engineering of the resonant lattice Kerker effect and promote its applications in phase modulation and wavefront control.

physics.optics↗

arXiv2021

Active Tuning of Resonant Lattice Kerker Effect

The Kerker effect has been generalized in nanophotonics and meta-optics, and has recently been of great interest by relating to various fascinating functionalities such as scattering management and perfect transmission, reflection or absorption. One of the most interesting generalizations is the resonant lattice Kerker effect in periodic nanostructures. However, its active tuning has not been explored yet. Here, we report, for the first time, the active control of the resonant lattice Kerker effect in periodic Ge2Se2Te5 nanodisks. By changing the crystalline fraction, we show that the electric dipole lattice resonance (ED-LR), the magnetic dipole resonance (MDR), and thus the resonant lattice Kerker effect are all red-shifted. We therefore realize the transition from the ED-LR to the resonant lattice Kerker effect, which enables multilevel tuning of reflection, transmission and absorption with modulation depths above 86%. Taking advantage of the MDR redshifts, we also observe broadband and multilevel tuning of transmission with modulation depth of 87% over a broadband range of 588 nm. Our work establishes a new path for designing high-performance active nanophotonic devices.

physics.optics↗

arXiv2021

Mirror-backed dielectric metasurface sensor with ultrahigh figure of merit based on super-narrow Rayleigh anomaly

Plasmonic nanostructures with large local field enhancement have been extensively investigated for sensing applications. However, the quality factor and thus the sensing figure of merit are limited due to relatively high ohmic loss. Here we propose a novel plasmonic sensor with ultrahigh figure of merit based on super-narrow Rayleigh anomaly (RA) in a mirror-backed dielectric metasurface. Simulation results show that the RA in such a metasurface can have a super-high quality factor of 16000 in the visible regime, which is an order of magnitude larger than the highest value of reported plasmonic nanostructures. We attribute this striking performance to the enhanced electric fields far away from the metal film. The super-high quality factor and the greatly enhanced field confined to the superstrate region make the mirror-backed dielectric metasurface an ideal platform for sensing. We show that the figure of merit of this RA-based metasurface sensor can be as high as 15930/RIU. Additionally, we reveal that RA-based plasmonic sensors share some typical characteristics, providing guidance for the structure design. We expect this work advance the development of high-performance plasmonic metasurface sensors.

physics.optics↗

arXiv2021

Narrow quadrupolar surface lattice resonances and band reversal in vertical metal-insulator-metal gratings

We report narrow quadrupolar surface lattice resonances (SLRs) under normal incidence, and the observation, for the first time, of the band reversal effect of SLRs supported by a vertical metal-insulator-metal nanograting, which is embedded in a homogeneous dielectric environment. Simulation results show that under normal incidence, quadrupolar SLR with linewidth of 1~nm and high quality factor of 979 can be excited in the near-infrared regime, and that under oblique incidence, out-of-plane dipolar SLRs of relatively large quality factors (>=150) can be launched. By varying the incidence angle, the SLR wavelength can be continuously tuned over an extremely broadband range of 750 nm, covering most of the near-infrared regime, and the quality factor decreases exponentially. Remarkably, the resonance lineshape can also be dynamically tuned from an asymmetric Fano-shaped dip to a peak, a dip/peak pair, and a perfect symmetric Lorentzian peak, suggesting the appearance of the band reversal effect. We expect the high-Q SLRs with broadband tunability and tunable lineshapes will find potential applications in enhanced nanoscale light-matter interactions in nanolasers, nonlinear optics and sensing.

physics.optics↗