arXiv subjects

Li Ling

Publications and source records attributed to Li Ling.

14 recordsLinked to original sources

arXiv2026

Story2Proposal: A Scaffold for Structured Scientific Paper Writing

Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment.

cs.CL↗

arXiv2026

WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents

Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a more critical factor: the efficiency of compressing a large language model's (LLM) latent knowledge into actionable agent behavior. We introduce WebFactory, a novel, fully automated closed-loop reinforcement learning pipeline for GUI agents, systematically compressing LLM-encoded internet intelligence into efficient, grounded actions. Our pipeline features a process of scalable environment synthesis, knowledge-aware task generation, LLM-powered trajectory collection, decomposed reward RL training, and systematic agent evaluation. Remarkably, our agent demonstrates exceptional data efficiency and generalization. Trained on synthetic data from only 10 websites within WebFactory, it achieves performance comparable to GUI agents trained on the same amount of human-annotated data from a much larger set of environments. This superior performance is consistent across our internal offline and online transfer benchmarks, where our agent also significantly outperforms the base foundation model. We further provide critical insights into the "embodiment potential" of different LLM foundations, offering a new axis for model evaluation. This work presents a scalable and cost-effective paradigm for transforming passive internet knowledge into active, grounded intelligence, marking a critical step towards general-purpose interactive agents.

cs.AI↗

arXiv2026

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces

We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverage of complex, high-value tasks often missed by synthetic methods. Leveraging this dataset, we propose a Dual Mid-Training recipe that decouples spatial grounding from planning, achieving state-of-the-art performance on our proposed WebChainBench and other public GUI benchmarks. Our work provides the data and insights necessary to build and rigorously evaluate the next generation of scalable web agents.

cs.AI↗

arXiv2026

Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives

Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workflows. However, existing systems largely rely on runtime-centric execution paradigms, repeatedly reading, summarizing, and reasoning over large volumes of scientific literature online. This on-the-spot computation strategy incurs high computational cost, suffers from context window limitations, and often leads to brittle reasoning and hallucination. We propose Idea2Story, a pre-computation-driven framework for autonomous scientific discovery that shifts literature understanding from online reasoning to offline knowledge construction. Idea2Story continuously collects peer-reviewed papers together with their review feedback, extracts core methodological units, composes reusable research patterns, and organizes them into a structured methodological knowledge graph. At runtime, underspecified user research intents are aligned to established research paradigms, enabling efficient retrieval and reuse of high-quality research patterns instead of open-ended generation and trial-and-error. By grounding research planning and execution in a pre-built knowledge graph, Idea2Story alleviates the context window bottleneck of LLMs and substantially reduces repeated runtime reasoning over literature. We conduct qualitative analyses and preliminary empirical studies demonstrating that Idea2Story can generate coherent, methodologically grounded, and novel research patterns, and can produce several high-quality research demonstrations in an end-to-end setting. These results suggest that offline knowledge construction provides a practical and scalable foundation for reliable autonomous scientific discovery.

cs.CE↗

arXiv2025

HiMo: High-Speed Objects Motion Compensation in Point Clouds

LiDAR point cloud is essential for autonomous vehicles, but motion distortions from dynamic objects degrade the data quality. While previous work has considered distortions caused by ego motion, distortions caused by other moving objects remain largely overlooked, leading to errors in object shape and position. This distortion is particularly pronounced in high-speed environments such as highways and in multi-LiDAR configurations, a common setup for heavy vehicles. To address this challenge, we introduce HiMo, a pipeline that repurposes scene flow estimation for non-ego motion compensation, correcting the representation of dynamic objects in point clouds. During the development of HiMo, we observed that existing self-supervised scene flow estimators often produce degenerate or inconsistent estimates under high-speed distortion. We further propose SeFlow++, a real-time scene flow estimator that achieves state-of-the-art performance on both scene flow and motion compensation. Since well-established motion distortion metrics are absent in the literature, we introduce two evaluation metrics: compensation accuracy at a point level and shape similarity of objects. We validate HiMo through extensive experiments on Argoverse 2, ZOD, and a newly collected real-world dataset featuring highway driving and multi-LiDAR-equipped heavy vehicles. Our findings show that HiMo improves the geometric consistency and visual fidelity of dynamic objects in LiDAR point clouds, benefiting downstream tasks such as semantic segmentation and 3D detection. See https://kin-zhang.github.io/HiMo for more details.

cs.CV↗

arXiv2024

Score-Based Multibeam Point Cloud Denoising

Multibeam echo-sounder (MBES) is the de-facto sensor for bathymetry mapping. In recent years, cheaper MBES sensors and global mapping initiatives have led to exponential growth of available data. However, raw MBES data contains 1-25% of noise that requires semi-automatic filtering using tools such as Combined Uncertainty and Bathymetric Estimator (CUBE). In this work, we draw inspirations from the 3D point cloud community and adapted a score-based point cloud denoising network for MBES outlier detection and denoising. We trained and evaluated this network on real MBES survey data. The proposed method was found to outperform classical methods, and can be readily integrated into existing MBES standard workflow. To facilitate future research, the code and pretrained model are available online.

cs.LG↗

arXiv2024

Benchmarking Classical and Learning-Based Multibeam Point Cloud Registration

Deep learning has shown promising results for multiple 3D point cloud registration datasets. However, in the underwater domain, most registration of multibeam echo-sounder (MBES) point cloud data are still performed using classical methods in the iterative closest point (ICP) family. In this work, we curate and release DotsonEast Dataset, a semi-synthetic MBES registration dataset constructed from an autonomous underwater vehicle in West Antarctica. Using this dataset, we systematically benchmark the performance of 2 classical and 4 learning-based methods. The experimental results show that the learning-based methods work well for coarse alignment, and are better at recovering rough transforms consistently at high overlap (20-50%). In comparison, GICP (a variant of ICP) performs well for fine alignment and is better across all metrics at extremely low overlap (10%). To the best of our knowledge, this is the first work to benchmark both learning-based and classical registration methods on an AUV-based MBES dataset. To facilitate future research, both the code and data are made available online.

cs.CV↗

arXiv2023

A Dense Subframe-based SLAM Framework with Side-scan Sonar

Side-scan sonar (SSS) is a lightweight acoustic sensor that is commonly deployed on autonomous underwater vehicles (AUVs) to provide high-resolution seafloor images. However, leveraging side-scan images for simultaneous localization and mapping (SLAM) presents a notable challenge, primarily due to the difficulty of establishing sufficient amount of accurate correspondences between these images. To address this, we introduce a novel subframe-based dense SLAM framework utilizing side-scan sonar data, enabling effective dense matching in overlapping regions of paired side-scan images. With each image being evenly divided into subframes, we propose a robust estimation pipeline to estimate the relative pose between each paired subframes, by using a good inlier set identified from dense correspondences. These relative poses are then integrated as edge constraints in a factor graph to optimize the AUV pose trajectory. The proposed framework is evaluated on three real datasets collected by a Hugin AUV. Among one of them includes manually-annotated keypoint correspondences as ground truth and is used for evaluation of pose trajectory. We also present a feasible way of evaluating mapping quality against multi-beam echosounder (MBES) data without the influence of pose. Experimental results demonstrate that our approach effectively mitigates drift from the dead-reckoning (DR) system and enables quasi-dense bathymetry reconstruction. An open-source implementation of this work is available.

cs.RO↗

arXiv2023

Evaluation of a Canonical Image Representation for Sidescan Sonar

Acoustic sensors play an important role in autonomous underwater vehicles (AUVs). Sidescan sonar (SSS) detects a wide range and provides photo-realistic images in high resolution. However, SSS projects the 3D seafloor to 2D images, which are distorted by the AUV's altitude, target's range and sensor's resolution. As a result, the same physical area can show significant visual differences in SSS images from different survey lines, causing difficulties in tasks such as pixel correspondence and template matching. In this paper, a canonical transformation method consisting of intensity correction and slant range correction is proposed to decrease the above distortion. The intensity correction includes beam pattern correction and incident angle correction using three different Lambertian laws (cos, cos2, cot), whereas the slant range correction removes the nadir zone and projects the position of SSS elements into equally horizontally spaced, view-point independent bins. The proposed method is evaluated on real data collected by a HUGIN AUV, with manually-annotated pixel correspondence as ground truth reference. Experimental results on patch pairs compare similarity measures and keypoint descriptor matching. The results show that the canonical transformation can improve the patch similarity, as well as SIFT descriptor matching accuracy in different images where the same physical area was ensonified.

cs.CV↗

arXiv2023

A Fully-automatic Side-scan Sonar SLAM Framework

Side-scan sonar (SSS) is a lightweight acoustic sensor that is frequently deployed on autonomous underwater vehicles (AUVs) to provide high-resolution seafloor images. However, using side-scan images to perform simultaneous localization and mapping (SLAM) remains a challenge when there is a lack of 3D bathymetric information and discriminant features in the side-scan images. To tackle this, we propose a feature-based SLAM framework using side-scan sonar, which is able to automatically detect and robustly match keypoints between paired side-scan images. We then use the detected correspondences as constraints to optimize the AUV pose trajectory. The proposed method is evaluated on real data collected by a Hugin AUV, using as a ground truth reference both manually-annotated keypoints and a 3D bathymetry mesh from multibeam echosounder (MBES). Experimental results demonstrate that our approach is able to reduce drifts from the dead-reckoning system. The framework is made publicly available for the benefit of the community.

cs.RO↗

arXiv2022

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity; yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of combination delivers comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms by competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery.

cs.CV↗

arXiv2019

Trichromatic and Tri-polarization-channel Holography with Non-interleaved Dielectric Metasurface

Metasurfaces hold great potentials for advanced holographic display with extraordinary information capacity and pixel sizes in an ultrathin flat profile. Dual-polarization channel to encode two independent phase profiles or spatially multiplexed meta-holography by interleaved metasurfaces are captivated popular solutions to projecting multiplexed and vectorial images. However, the intrinsic limit of orthogonal polarization-channels, their crosstalk due to coupling between meta-atoms, and interleaving-induced degradation of efficiency and reconstructed image quality set great barriers for sophisticated meta-holography from being widely adopted. Here we report a non-interleaved TiO2 metasurface holography, and three distinct phase profiles are encoded into three orthogonal polarization bases with almost zero crosstalk. The corresponding three independently constructed intensity profiles are therefore assigned to trichromatic (RGB) beams, resulting in high-quality and high-efficiency vectorial meta-holography in the whole visible regime. Our strategy presents an unconventionally advanced holographic scheme by synergizing trichromatic colors and tri-polarization channels, simply realized with a minimalist non-interleaved metasurface. Our work unlocks the metasurface's potentials on massive information storage, polarization optics, polarimetric imaging, holographic data encryption, etc.

physics.optics↗

arXiv2019

An AI-based, Multi-stage detection system of banking botnets

Banking Trojans, botnets are primary drivers of financially-motivated cybercrime. In this paper, we first analyzed how an APT-based banking botnet works step by step through the whole lifecycle. Specifically, we present a multi-stage system that detects malicious banking botnet activities which potentially target the organizations. The system leverages Cyber Data Lake as well as multiple artificial intelligence techniques at different stages. The evaluation results using public datasets showed that Deep Learning based detections were highly successful compared with baseline models.

cs.CR↗

arXiv2018

SCMA based resource management of D2D communications for maximum sum-revenue

The device-to-device (D2D) communication is one of the promising technologies of the future Internet of Things (IoT), but its security-related issues remain challenging. The block-chain is considered to be a secure and reliable distributed ledger, so we can treat the device user equipment (D-UE) request for the reusing resources of cellular user equipment (C-UE) as a transaction and put it into a transaction pool, then package the record into the block-chain. In this paper, we study the D2D communication resource allocation scheme based on sparse code multiple access (SCMA). Firstly, the system's interference model and block-chain-based transaction flow are analyzed. Then we propose the optimization problem so that C-UE can get the maximum revenue by sharing its resources to D-UE. This problem is NP-hard, so we propose a heuristic algorithm based on semi-definite relaxation (SDR) programming to solve it. Finally, the performance of the proposed algorithm is verified by simulation of different system parameters.

eess.SP↗