arXiv subjects

Xintong Liu

Publications and source records attributed to Xintong Liu.

9 recordsLinked to original sources

arXiv2026

Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models

The long-standing goal of multimodal AI is to build unified models in which visual understanding and visual generation mutually enhance one another. Despite recent works such as BAGEL, BLIP3o achieves remarkable progress; In practice, however, this unification remains one-directional: understanding routinely guides generation, yet how and why generation can support understanding is rarely investigated. We revisit this asymmetry and propose Generation-to-Understanding (G2U) synergy, where visual generation becomes an explicit intermediate reasoning step. Our framework enables a model to perform controlled generative acts, such as detail enhancement, context expansion or structural visualisation, to produce self-generated visual thoughts, which are then fed back into the model to refine perception without retraining or external tools. Through a comprehensive evaluation on twelve benchmarks, this reversed information flow consistently improves multimodal understanding. We show that generative fidelity bounds perceptual gain and that distinct families of edit prompts govern transfer efficiency. We further analyse whether models can decide what to imagine. While they can produce plausible edits, these self-generated visual thoughts lack stable task alignment, revealing that current large multimodal models fall short of true self-reflection. This work exposes a missing mechanism in unified cognition and suggests that imagination is not the end of understanding but its beginning.

cs.CV↗

arXiv2025

Human Motion Capture from Loose and Sparse Inertial Sensors with Garment-aware Diffusion Models

Motion capture using sparse inertial sensors has shown great promise due to its portability and lack of occlusion issues compared to camera-based tracking. Existing approaches typically assume that IMU sensors are tightly attached to the human body. However, this assumption often does not hold in real-world scenarios. In this paper, we present Garment Inertial Poser (GaIP), a method for estimating full-body poses from sparse and loosely attached IMU sensors. We first simulate IMU recordings using an existing garment-aware human motion dataset. Our transformer-based diffusion models synthesize loose IMU data and estimate human poses from this challenging loose IMU data. We also demonstrate that incorporating garment-related parameters during training on loose IMU data effectively maintains expressiveness and enhances the ability to capture variations introduced by looser or tighter garments. Our experiments show that our diffusion methods trained on simulated and synthetic data outperform state-of-the-art inertial full-body pose estimators, both quantitatively and qualitatively, opening up a promising direction for future research on motion capture from such realistic sensor placements.

cs.GR↗

arXiv2025

TianQuan-S2S: A Subseasonal-to-Seasonal Global Weather Model via Incorporate Climatology State

Accurate Subseasonal-to-Seasonal (S2S) forecasting is vital for decision-making in agriculture, energy production, and emergency management. However, it remains a challenging and underexplored problem due to the chaotic nature of the weather system. Recent data-driven studies have shown promising results, but their performance is limited by the inadequate incorporation of climate states and a model tendency to degrade, progressively losing fine-scale details and yielding over-smoothed forecasts. To overcome these limitations, we propose TianQuan-S2S, a global S2S forecasting model that integrates initial weather states with climatological means via incorporating climatology into patch embedding and enhancing variability capture through an uncertainty-augmented Transformer. Extensive experiments on the Earth Reanalysis 5 (ERA5) reanalysis dataset demonstrate that our model yields a significant improvement in both deterministic and ensemble forecasting over the climatology mean, traditional numerical methods, and data-driven models. Ablation studies empirically show the effectiveness of our model designs. Remarkably, our model outperforms skillful numerical ECMWF-S2S and advanced data-driven Fuxi-S2S in key meteorological variables. The code implementation can be found in https://github.com/zhangminglang42/TianQuan.

cs.LG↗

arXiv2025

EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity

Research on egocentric tasks in computer vision has mostly focused on head-mounted cameras, such as fisheye cameras or embedded cameras inside immersive headsets. We argue that the increasing miniaturization of optical sensors will lead to the prolific integration of cameras into many more body-worn devices at various locations. This will bring fresh perspectives to established tasks in computer vision and benefit key areas such as human motion tracking, body pose estimation, or action recognition -- particularly for the lower body, which is typically occluded. In this paper, we introduce EgoSim, a novel simulator of body-worn cameras that generates realistic egocentric renderings from multiple perspectives across a wearer's body. A key feature of EgoSim is its use of real motion capture data to render motion artifacts, which are especially noticeable with arm- or leg-worn cameras. In addition, we introduce MultiEgoView, a dataset of egocentric footage from six body-worn cameras and ground-truth full-body 3D poses during several activities: 119 hours of data are derived from AMASS motion sequences in four high-fidelity virtual environments, which we augment with 5 hours of real-world motion data from 13 participants using six GoPro cameras and 3D body pose references from an Xsens motion capture suit. We demonstrate EgoSim's effectiveness by training an end-to-end video-only 3D pose estimation network. Analyzing its domain gap, we show that our dataset and simulator substantially aid training for inference on real-world data. EgoSim code & MultiEgoView dataset: https://siplab.org/projects/EgoSim

cs.CV↗

arXiv2024

LLM-for-X: Application-agnostic Integration of Large Language Models to Support Personal Writing Workflows

To enhance productivity and to streamline workflows, there is a growing trend to embed large language model (LLM) functionality into applications, from browser-based web apps to native apps that run on personal computers. Here, we introduce LLM-for-X, a system-wide shortcut layer that seamlessly augments any application with LLM services through a lightweight popup dialog. Our native layer seamlessly connects front-end applications to popular LLM backends, such as ChatGPT and Gemini, using their uniform chat front-ends as the programming interface or their custom API calls. We demonstrate the benefits of LLM-for-X across a wide variety of applications, including Microsoft Office, VSCode, and Adobe Acrobat as well as popular web apps such as Overleaf. In our evaluation, we compared LLM-for-X with ChatGPT's web interface in a series of tasks, showing that our approach can provide users with quick, efficient, and easy-to-use LLM assistance without context switching to support writing and reading tasks that is agnostic of the specific application.

cs.HC↗

arXiv2024

Deep Learning with Information Fusion and Model Interpretation for Health Monitoring of Fetus based on Long-term Prenatal Electronic Fetal Heart Rate Monitoring Data

Long-term fetal heart rate (FHR) monitoring during the antepartum period, increasingly popularized by electronic FHR monitoring, represents a growing approach in FHR monitoring. This kind of continuous monitoring, in contrast to the short-term one, collects an extended period of fetal heart data. This offers a more comprehensive understanding of fetus's conditions. However, the interpretation of long-term antenatal fetal heart monitoring is still in its early stages, lacking corresponding clinical standards. Furthermore, the substantial amount of data generated by continuous monitoring imposes a significant burden on clinical work when analyzed manually. To address above challenges, this study develops an automatic analysis system named LARA (Long-term Antepartum Risk Analysis system) for continuous FHR monitoring, combining deep learning and information fusion methods. LARA's core is a well-established convolutional neural network (CNN) model. It processes long-term FHR data as input and generates a Risk Distribution Map (RDM) and Risk Index (RI) as the analysis results. We evaluate LARA on inner test dataset, the performance metrics are as follows: AUC 0.872, accuracy 0.816, specificity 0.811, sensitivity 0.806, precision 0.271, and F1 score 0.415. In our study, we observe that long-term FHR monitoring data with higher RI is more likely to result in adverse outcomes (p=0.0021). In conclusion, this study introduces LARA, the first automated analysis system for long-term FHR monitoring, initiating the further explorations into its clinical value in the future.

cs.LG↗

arXiv2022

Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization

The non-line-of-sight imaging technique aims to reconstruct targets from multiply reflected light. For most existing methods, dense points on the relay surface are raster scanned to obtain high-quality reconstructions, which requires a long acquisition time. In this work, we propose a signal-surface collaborative regularization (SSCR) framework that provides noise-robust reconstructions with a minimal number of measurements. Using Bayesian inference, we design joint regularizations of the estimated signal, the 3D voxel-based representation of the objects, and the 2D surface-based description of the targets. To our best knowledge, this is the first work that combines regularizations in mixed dimensions for hidden targets. Experiments on synthetic and experimental datasets illustrated the efficiency and robustness of the proposed method under both confocal and non-confocal settings. We report the reconstruction of the hidden targets with complex geometric structures with only $5 \times 5$ confocal measurements from public datasets, indicating an acceleration of the conventional measurement process by a factor of 10000. Besides, the proposed method enjoys low time and memory complexities with sparse measurements. Our approach has great potential in real-time non-line-of-sight imaging applications such as rescue operations and autonomous driving.

cs.CV↗

arXiv2022

Non-line-of-sight imaging with arbitrary illumination and detection pattern

Non-line-of-sight (NLOS) imaging aims at reconstructing targets obscured from the direct line of sight. Existing NLOS imaging algorithms require dense measurements at rectangular grid points in a large area of the relay surface, which severely hinders their availability to variable relay scenarios in practical applications such as robotic vision, autonomous driving, rescue operations and remote sensing. In this work, we propose a Bayesian framework for NLOS imaging with no specific requirements on the spatial pattern of illumination and detection points. By introducing virtual confocal signals, we design a confocal complemented signal-object collaborative regularization (CC-SOCR) algorithm for high quality reconstructions. Our approach is capable of reconstructing both albedo and surface normal of the hidden objects with fine details under the most general relay setting. Moreover, with a regular relay surface, coarse rather than dense measurements are enough for our approach such that the acquisition time can be reduced significantly. As demonstrated in multiple experiments, the new framework substantially enhances the applicability of NLOS imaging.

eess.IV↗

arXiv2022

A non-local gradient based approach of infinity Laplacian with $Γ$-convergence

We propose an infinity Laplacian method to address the problem of interpolation on an unstructured point cloud. In doing so, we find the labeling function with the smallest infinity norm of its gradient. By introducing the non-local gradient, the continuous functional is approximated with a discrete form. The discrete problem is convex and can be solved efficiently with the split Bregman method. Experimental results indicate that our approach provides consistent interpolations and the labeling functions obtained are globally smooth, even in the case of extreme low sampling rate. More importantly, convergence of the discrete minimizer to the optimal continuous labeling function is proved using $Γ$-convergence and compactness, which guarantees the reliability of the infinity Laplacian method in various potential applications.

math.NA↗