arXiv subjects

Cheng Zeng

Publications and source records attributed to Cheng Zeng.

At least 37 records · Page 2Linked to original sources

arXiv2025

High-Fidelity Simulated Data Generation for Real-World Zero-Shot Robotic Manipulation Learning with Gaussian Splatting

The scalability of robotic learning is fundamentally bottlenecked by the significant cost and labor of real-world data collection. While simulated data offers a scalable alternative, it often fails to generalize to the real world due to significant gaps in visual appearance, physical properties, and object interactions. To address this, we propose RoboSimGS, a novel Real2Sim2Real framework that converts multi-view real-world images into scalable, high-fidelity, and physically interactive simulation environments for robotic manipulation. Our approach reconstructs scenes using a hybrid representation: 3D Gaussian Splatting (3DGS) captures the photorealistic appearance of the environment, while mesh primitives for interactive objects ensure accurate physics simulation. Crucially, we pioneer the use of a Multi-modal Large Language Model (MLLM) to automate the creation of physically plausible, articulated assets. The MLLM analyzes visual data to infer not only physical properties (e.g., density, stiffness) but also complex kinematic structures (e.g., hinges, sliding rails) of objects. We demonstrate that policies trained entirely on data generated by RoboSimGS achieve successful zero-shot sim-to-real transfer across a diverse set of real-world manipulation tasks. Furthermore, data from RoboSimGS significantly enhances the performance and generalization capabilities of SOTA methods. Our results validate RoboSimGS as a powerful and scalable solution for bridging the sim-to-real gap.

cs.RO↗

arXiv2025

OViP: Online Vision-Language Preference Learning for VLM Hallucination

Large vision-language models (LVLMs) remain vulnerable to hallucination, often generating content misaligned with visual inputs. Although recent training-based approaches aim to mitigate hallucination, they typically rely on predefined or randomly edited negative samples that do not reflect actual model errors, thus limiting training efficacy. In this work, we propose an Online Vision-language Preference Learning (OViP) framework that dynamically constructs contrastive training data based on the model's own hallucinated outputs. By identifying semantic differences between sampled response pairs and synthesizing negative images using a diffusion model, OViP generates more relevant supervision signals in real time. This failure-driven training enables adaptive alignment of both textual and visual preferences. Moreover, we refine existing evaluation protocols to better capture the trade-off between hallucination suppression and expressiveness. Experiments on hallucination and general benchmarks demonstrate that OViP not only reduces hallucinations while preserving core multi-modal capabilities, but also substantially improves training efficiency. Code is available at https://github.com/lsjlsj35/Online-Vision-Language-Preference-Learning-for-VLM-Hallucination.

cs.CV↗

arXiv2025

Bridged Posterior: Optimization, Profile Likelihood and a New Approach to Generalized Bayes

Optimization is widely used in statistics, and often efficiently delivers point estimates on useful spaces involving structural constraints or combinatorial structure. To quantify uncertainty, Gibbs posterior exponentiates the negative loss function to form a posterior density. Nevertheless, Gibbs posteriors are supported in high-dimensional spaces, and do not inherit the computational efficiency or constraint formulations from optimization. In this article, we explore a new generalized Bayes approach, viewing the likelihood as a function of data, parameters, and latent variables conditionally determined by an optimization sub-problem. Marginally, the latent variable given the data remains stochastic, and is characterized by its posterior distribution. This framework, coined bridged posterior, conforms to the Bayesian paradigm. Besides providing a novel generative model, we obtain a positively surprising theoretical finding that under mild conditions, the $\sqrt{n}$-adjusted posterior distribution of the parameters under our model converges to the same normal distribution as that of the canonical integrated posterior. Therefore, our result formally dispels a long-held belief that partial optimization of latent variables may lead to underestimation of parameter uncertainty. We demonstrate the practical advantages of our approach under several settings, including maximum-margin classification, latent normal models, and harmonization of multiple networks.

stat.ME↗

arXiv2025

Some sharp bounds on the average Steiner (k, l)-eccentricity for trees

In this paper we introduce some transformations for trees that do not increase the average Steiner $(k,l)$-eccentricity for all $0\leq l\leq k\leq n$. Using these transformations, we obtain some sharp bounds on the average Steiner $(k,l)$-eccentricity for trees with some certain conditions, including given nodes, given diameter, given max degree and given leaves, and get the corresponding extremal trees as well.

math.CO↗

arXiv2025

Normalizing Flow to Augmented Posterior: Conditional Density Estimation with Interpretable Dimension Reduction for High Dimensional Data

The conditional density characterizes the distribution of a response variable $y$ given other predictor $x$, and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts a motivating starting point. In this work, we extend NF neural networks when external $x$ is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional $y$ and a latent $z$ that comprises two components $[z_P,z_N]$. The $z_P$ component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for $x$, such as logistic/linear regression. The $z_N$ component is a high-dimensional independent Gaussian vector, which explains the variations in $y$ not or less related to $x$. Unlike existing CDE methods, the proposed approach, coined Augmented Posterior CDE (AP-CDE), only requires a simple modification on the common normalizing flow framework, while significantly improving the interpretation of the latent component, since $z_P$ represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of $x$-related variations due to factors such as lighting condition and subject id, from the other random variations. Further, the experiments show that an unconditional NF neural network, based on an unsupervised model of $z$, such as Gaussian mixture, fails to generate interpretable results.

stat.ME↗

arXiv2025

SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds

Transformers have been seldom employed in point cloud roof plane instance segmentation, which is the focus of this study, and existing superpoint Transformers suffer from limited performance due to the use of low-quality superpoints. To address this challenge, we establish two criteria that high-quality superpoints for Transformers should satisfy and introduce a corresponding two-stage superpoint generation process. The superpoints generated by our method not only have accurate boundaries, but also exhibit consistent geometric sizes and shapes, both of which greatly benefit the feature learning of superpoint Transformers. To compensate for the limitations of deep learning features when the training set size is limited, we incorporate multidimensional handcrafted features into the model. Additionally, we design a decoder that combines a Kolmogorov-Arnold Network with a Transformer module to improve instance prediction and mask extraction. Finally, our network's predictions are refined using traditional algorithm-based postprocessing. For evaluation, we annotated a real-world dataset and corrected annotation errors in the existing RoofN3D dataset. Experimental results show that our method achieves state-of-the-art performance on our dataset, as well as both the original and reannotated RoofN3D datasets. Moreover, our model is not sensitive to plane boundary annotations during training, significantly reducing the annotation burden. Through comprehensive experiments, we also identified key factors influencing roof plane segmentation performance: in addition to roof types, variations in point cloud density, density uniformity, and 3D point precision have a considerable impact. These findings underscore the importance of incorporating data augmentation strategies that account for point cloud quality to enhance model robustness under diverse and challenging conditions.

cs.CV↗

arXiv2025

Channel Estimation for XL-MIMO Systems with Decentralized Baseband Processing: Integrating Local Reconstruction with Global Refinement

In this paper, we investigate the channel estimation problem for extremely large-scale multiple-input multiple-output (XL-MIMO) systems with a hybrid analog-digital architecture, implemented within a decentralized baseband processing (DBP) framework with a star topology. Existing centralized and fully decentralized channel estimation methods face limitations due to excessive computational complexity or degraded performance. To overcome these challenges, we propose a novel two-stage channel estimation scheme that integrates local sparse reconstruction with global fusion and refinement. Specifically, in the first stage, by exploiting the sparsity of channels in the angular-delay domain, the local reconstruction task is formulated as a sparse signal recovery problem. To solve it, we develop a graph neural networks-enhanced sparse Bayesian learning (SBL-GNNs) algorithm, which effectively captures dependencies among channel coefficients, significantly improving estimation accuracy. In the second stage, the local estimates from the local processing units (LPUs) are aligned into a global angular domain for fusion at the central processing unit (CPU). Based on the aggregated observations, the channel refinement is modeled as a Bayesian denoising problem. To efficiently solve it, we devise a variational message passing algorithm that incorporates a Markov chain-based hierarchical sparse prior, effectively leveraging both the sparsity and the correlations of the channels in the global angular-delay domain. Simulation results validate the effectiveness and superiority of the proposed SBL-GNNs algorithm over existing methods, demonstrating improved estimation performance and reduced computational complexity.

cs.IT↗

arXiv2025

Reconfigurable chiral edge states in synthetic dimensions on an integrated photonic chip

Chiral edge state is a hallmark of topological physics, which has drawn significant attention across quantum mechanics, condensed matter and optical systems. Recently, synthetic dimensions have emerged as ideal platforms for investigating chiral edge states in multiple dimensions, overcoming the limitations of real space. In this work, we demonstrate reconfigurable chiral edge states via synthetic dimensions on an integrated photonic chip. These states are realized by coupling two frequency lattices with opposite pseudospins, which are subjected to programmable artificial gauge potential and long-range coupling within a thin-film lithium niobate microring resonator. Within this system, we are able to implement versatile strategies to observe and steer the chiral edge states, including the realization and frustration of the chiral edge states in a synthetic Hall ladder, the generation of imbalanced chiral edge currents, and the regulation of chiral behaviors as chirality, single-pseudospin enhancement, and complete suppression. This work provides a reconfigurable integrated photonic platform for simulating and steering chiral edge states in synthetic space, paying the way for the realization of high-dimensional and programmable topological photonic systems on chip.

physics.optics↗

arXiv2025

Gradient-bridged Posterior: Bayesian Inference for Models with Implicit Functions

Many statistical problems include model parameters that are defined as the solutions to optimization sub-problems. These include classical approaches such as profile likelihood as well as modern applications involving flow networks or Procrustes distances. In such cases, the likelihood of the data involves an implicit function, often complicating inferential procedures and entailing prohibitive computational cost. In this article, we propose an intuitive and tractable posterior inference approach for this setting. We introduce a class of continuous models that handle implicit function values using the first-order optimality of the sub-problems. Specifically, we apply a shrinkage kernel to the gradient norm, which retains a probabilistic interpretation within a generative model. This can be understood as a generalization of the Gibbs posterior framework to newly enable concentration around partial minimizers in a subset of the parameters. We show that this method, termed the gradient-bridged posterior, is amenable to efficient posterior computation, and enjoys theoretical guarantees, establishing a Bernstein--von Mises theorem for asymptotic normality. The advantages of our approach are highlighted on a synthetic flow network experiment and an application to data integration using Procrustes distances.

stat.ME↗

arXiv2025

NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches

In-band network telemetry (INT) is essential to network management due to its real-time visibility. However, because of the rapid increase in network devices and services, it has become crucial to have targeted access to detailed network information in a dynamic network environment. This paper proposes an intelligent network telemetry system called NTP-INT to obtain more fine-grained network information on high-load switches. Specifically, NTP-INT consists of three modules: network traffic prediction module, network pruning module, and probe path planning module. Firstly, the network traffic prediction module adopts a Multi-Temporal Graph Neural Network (MTGNN) to predict future network traffic and identify high-load switches. Then, we design the network pruning algorithm to generate a subnetwork covering all high-load switches to reduce the complexity of probe path planning. Finally, the probe path planning module uses an attention-mechanism-based deep reinforcement learning (DEL) model to plan efficient probe paths in the network slice. The experimental results demonstrate that NTP-INT can acquire more precise network information on high-load switches while decreasing the control overhead by 50\%.

cs.NI↗

arXiv2025

The comparison of two Zagreb-Fermat eccentricity indices

In this paper, we focus on comparing the first and second Zagreb-Fermat eccentricity indices of graphs. We show that $$\frac{\sum_{uv\in E\left( G \right)}{\varepsilon_3\left( u \right) \varepsilon_3\left( v \right)}}{m\left( G \right)} \leq \frac{\sum_{u\in V\left( G \right)}{\varepsilon_{3}^{2}\left( u \right)}}{n\left( G \right)} $$ holds for all acyclic and unicyclic graphs. Besides, we verify that the inequality may not be applied to graphs with at least two cycles.

math.CO↗

arXiv2025

Flat U-Net: An Efficient Ultralightweight Model for Solar Filament Segmentation in Full-disk H$α$ Images

Solar filaments are one of the most prominent features observed on the Sun, and their evolutions are closely related to various solar activities, such as flares and coronal mass ejections. Real-time automated identification of solar filaments is the most effective approach to managing large volumes of data. Existing models of filament identification are characterized by large parameter sizes and high computational costs, which limit their future applications in highly integrated and intelligent ground-based and space-borne observation devices. Consequently, the design of more lightweight models will facilitate the advancement of intelligent observation equipment. In this study, we introduce Flat U-Net, a novel and highly efficient ultralightweight model that incorporates simplified channel attention (SCA) and channel self-attention (CSA) convolutional blocks for the segmentation of solar filaments in full-disk H$α$ images. Feature information from each network layer is fully extracted to reconstruct interchannel feature representations. Each block effectively optimizes the channel features from the previous layer, significantly reducing parameters. The network architecture presents an elegant flattening, improving its efficiency, and simplifying the overall design. Experimental validation demonstrates that a model composed of pure SCAs achieves a precision of approximately 0.93, with dice similarity coefficient (DSC) and recall rates of 0.76 and 0.64, respectively, significantly outperforming the classical U-Net. Introducing a certain number of CSA blocks improves the DSC and recall rates to 0.82 and 0.74, respectively, which demonstrates a pronounced advantage, particularly concerning model weight size and detection effectiveness. The data set, models, and code are available as open-source resources.

astro-ph.IM↗

arXiv2024

Flexible Rate-Splitting Multiple Access for Near-Field Integrated Sensing and Communications

This letter presents a flexible rate-splitting multiple access (RSMA) framework for near-field (NF) integrated sensing and communications (ISAC). The spatial beams configured to meet the communication rate requirements of NF users are simultaneously leveraged to sense an additional NF target. A key innovation lies in its flexibility to select a subset of users for decoding the common stream, enhancing interference management and system performance. The system is designed by minimizing the Cramér-Rao bound (CRB) for joint distance and angle estimation through optimized power allocation, common rate allocation, and user selection. This leads to a discrete, non-convex optimization problem. Remarkably, we demonstrate that the preconfigured beams are sufficient for target sensing, eliminating the need for additional probing signals. To solve the optimization problem, an iterative algorithm is proposed combining the quadratic transform and simulated annealing. Simulation results indicate that the proposed scheme significantly outperforms conventional RSMA and space division multiple access (SDMA), reducing distance and angle estimation errors by approximately 100\% and 20\%, respectively.

cs.IT↗

arXiv2024

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model

Plane instance segmentation from RGB-D data is a crucial research topic for many downstream tasks. However, most existing deep-learning-based methods utilize only information within the RGB bands, neglecting the important role of the depth band in plane instance segmentation. Based on EfficientSAM, a fast version of SAM, we propose a plane instance segmentation network called PlaneSAM, which can fully integrate the information of the RGB bands (spectral bands) and the D band (geometric band), thereby improving the effectiveness of plane instance segmentation in a multimodal manner. Specifically, we use a dual-complexity backbone, with primarily the simpler branch learning D-band features and primarily the more complex branch learning RGB-band features. Consequently, the backbone can effectively learn D-band feature representations even when D-band training data is limited in scale, retain the powerful RGB-band feature representations of EfficientSAM, and allow the original backbone branch to be fine-tuned for the current task. To enhance the adaptability of our PlaneSAM to the RGB-D domain, we pretrain our dual-complexity backbone using the segment anything task on large-scale RGB-D data through a self-supervised pretraining strategy based on imperfect pseudo-labels. To support the segmentation of large planes, we optimize the loss function combination ratio of EfficientSAM. In addition, Faster R-CNN is used as a plane detector, and its predicted bounding boxes are fed into our dual-complexity network as prompts, thereby enabling fully automatic plane instance segmentation. Experimental results show that the proposed PlaneSAM sets a new SOTA performance on the ScanNet dataset, and outperforms previous SOTA approaches in zero-shot transfer on the 2D-3D-S, Matterport3D, and ICL-NUIM RGB-D datasets, while only incurring a 10% increase in computational overhead compared to EfficientSAM.

cs.CV↗

arXiv2024

MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient

Medical education relies heavily on Simulated Patients (SPs) to provide a safe environment for students to practice clinical skills, including medical image analysis. However, the high cost of recruiting qualified SPs and the lack of diverse medical imaging datasets have presented significant challenges. To address these issues, this paper introduces MedDiT, a novel knowledge-controlled conversational framework that can dynamically generate plausible medical images aligned with simulated patient symptoms, enabling diverse diagnostic skill training. Specifically, MedDiT integrates various patient Knowledge Graphs (KGs), which describe the attributes and symptoms of patients, to dynamically prompt Large Language Models' (LLMs) behavior and control the patient characteristics, mitigating hallucination during medical conversation. Additionally, a well-tuned Diffusion Transformer (DiT) model is incorporated to generate medical images according to the specified patient attributes in the KG. In this paper, we present the capabilities of MedDiT through a practical demonstration, showcasing its ability to act in diverse simulated patient cases and generate the corresponding medical images. This can provide an abundant and interactive learning experience for students, advancing medical education by offering an immersive simulation platform for future healthcare professionals. The work sheds light on the feasibility of incorporating advanced technologies like LLM, KG, and DiT in education applications, highlighting their potential to address the challenges faced in simulated patient-based medical education.

cs.AI↗

arXiv2024

A Broadband Algorithm for Adiabatic Mode Evolution and its Application on Polarization Splitter-Rotator on LNOI Platform

Adiabatic mode evolution waveguides (AMEWs) are widely utilized in integrated photonics, including tapered waveguides, edge couplers, mode converters, splitters, etc. An analytical theory and a novel AMEW design algorithm are developed to create shortcuts to adiabaticity (STA). This new algorithm is effective in shortening the total length of the AMEW while maintaining the desired wavelength range. Moreover, this analytical algorithm requires much fewer computing resources than traditional numerical algorithms. With the new algorithm, we demonstrate a broadband and highly efficient polarization splitter-rotator (PSR) on a lithium-niobate-on-insulator (LNOI) platform with an LN thickness of 500 nm. According to our simulation, the length of the PSR is shortened by 3.5 times compared to the linear design. The fabricated PSR, with a total length of 2 mm, exhibits an insertion loss (IL) of 0.8 dB and a polarization extinction ratio (ER) of 12.2 dB over a wavelength range exceeding 76 nm.

physics.optics↗

arXiv2024

Compact ultra-broadband light coupling on chip via nonadiabatic pumping

Enlarging bandwidth capacity of the integrated photonic systems demands efficient and broadband light coupling among optical elements, which has been a vital issue in integrated photonics. Here, we have developed a compact ultra-broadband light coupling strategy based on nonadiabatic pumping in coupled optical waveguides, and experimentally demonstrated the designs in thin-film lithium niobate on insulator (LNOI) platform. We found that nonadiabatic transition would produce a decreased dispersion of the phases related to eigenstates in the waveguides. As a consequence, we realized high-efficiency directional transfer between edgestates for various wavelengths covering a 1-dB bandwidth of ~320 nm in experiment (>400 nm in simulation), with a coupling length (~50 μm) approximately 1/10 of that required in the adiabatic regime. Furthermore, we have constructed complex functional devices including beamsplitter and multiple-level cascaded networks for broadband light routing and splitting. Our work preserves significant advantages simultaneously in extending the operation bandwidth and minimizing the footprint, which demonstrates great potential for large-scale and compact photonic integration on chip.

physics.optics↗

arXiv2024

How LLMs Aid in UML Modeling: An Exploratory Study with Novice Analysts

Since the emergence of GPT-3, Large Language Models (LLMs) have caught the eyes of researchers, practitioners, and educators in the field of software engineering. However, there has been relatively little investigation regarding the performance of LLMs in assisting with requirements analysis and UML modeling. This paper explores how LLMs can assist novice analysts in creating three types of typical UML models: use case models, class diagrams, and sequence diagrams. For this purpose, we designed the modeling tasks of these three UML models for 45 undergraduate students who participated in a requirements modeling course, with the help of LLMs. By analyzing their project reports, we found that LLMs can assist undergraduate students as novice analysts in UML modeling tasks, but LLMs also have shortcomings and limitations that should be considered when using them.

cs.SE↗