arXiv subjects

Cheng Peng

Publications and source records attributed to Cheng Peng.

At least 91 records · Page 5Linked to original sources

arXiv2025

Physics-Guided Dual Implicit Neural Representations for Source Separation

Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for approximating distortions of the physical signal of interest and the other for learning the effective background contribution. Our method learns directly from the raw data by minimizing a reconstruction-based loss function without requiring labeled data or pre-defined dictionaries. We demonstrate the effectiveness of our framework by considering a challenging case study involving large-scale simulated as well as experimental momentum-energy-dependent inelastic neutron scattering data in a four-dimensional parameter space, characterized by heterogeneous background contributions and unknown distortions to the target signal. The method is found to successfully separate physically meaningful signals from a complex or structured background even when the signal characteristics vary across all four dimensions of the parameter space. An analytical approach that informs the choice of the regularization parameter is presented. Our method offers a versatile framework for addressing source separation problems across diverse domains, ranging from superimposed signals in astronomical measurements to structural features in biomedical image reconstructions.

cs.CV↗

arXiv2025

Parametric Gaussian Human Model: Generalizable Prior for Efficient and Realistic Human Avatar Modeling

Photorealistic and animatable human avatars are a key enabler for virtual/augmented reality, telepresence, and digital entertainment. While recent advances in 3D Gaussian Splatting (3DGS) have greatly improved rendering quality and efficiency, existing methods still face fundamental challenges, including time-consuming per-subject optimization and poor generalization under sparse monocular inputs. In this work, we present the Parametric Gaussian Human Model (PGHM), a generalizable and efficient framework that integrates human priors into 3DGS for fast and high-fidelity avatar reconstruction from monocular videos. PGHM introduces two core components: (1) a UV-aligned latent identity map that compactly encodes subject-specific geometry and appearance into a learnable feature tensor; and (2) a disentangled Multi-Head U-Net that predicts Gaussian attributes by decomposing static, pose-dependent, and view-dependent components via conditioned decoders. This design enables robust rendering quality under challenging poses and viewpoints, while allowing efficient subject adaptation without requiring multi-view capture or long optimization time. Experiments show that PGHM is significantly more efficient than optimization-from-scratch methods, requiring only approximately 20 minutes per subject to produce avatars with comparable visual quality, thereby demonstrating its practical applicability for real-world monocular avatar creation.

cs.CV↗

arXiv2025

RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration

The dawn of embodied intelligence has ushered in an unprecedented imperative for resilient, cognition-enabled multi-agent collaboration across next-generation ecosystems, revolutionizing paradigms in autonomous manufacturing, adaptive service robotics, and cyber-physical production architectures. However, current robotic systems face significant limitations, such as limited cross-embodiment adaptability, inefficient task scheduling, and insufficient dynamic error correction. While End-to-end VLA models demonstrate inadequate long-horizon planning and task generalization, hierarchical VLA models suffer from a lack of cross-embodiment and multi-agent coordination capabilities. To address these challenges, we introduce RoboOS, the first open-source embodied system built on a Brain-Cerebellum hierarchical architecture, enabling a paradigm shift from single-agent to multi-agent intelligence. Specifically, RoboOS consists of three key components: (1) Embodied Brain Model (RoboBrain), a MLLM designed for global perception and high-level decision-making; (2) Cerebellum Skill Library, a modular, plug-and-play toolkit that facilitates seamless execution of multiple skills; and (3) Real-Time Shared Memory, a spatiotemporal synchronization mechanism for coordinating multi-agent states. By integrating hierarchical information flow, RoboOS bridges Embodied Brain and Cerebellum Skill Library, facilitating robust planning, scheduling, and error correction for long-horizon tasks, while ensuring efficient multi-agent collaboration through Real-Time Shared Memory. Furthermore, we enhance edge-cloud communication and cloud-based distributed inference to facilitate high-frequency interactions and enable scalable deployment. Extensive real-world experiments across various scenarios, demonstrate RoboOS's versatility in supporting heterogeneous embodiments. Project website: https://github.com/FlagOpen/RoboOS

cs.RO↗

arXiv2025

Scaling Up Biomedical Vision-Language Models: Fine-Tuning, Instruction Tuning, and Multi-Modal Learning

To advance biomedical vison-language model capabilities through scaling up, fine-tuning, and instruction tuning, develop vision-language models with improved performance in handling long text, explore strategies to efficiently adopt vision language models for diverse multi-modal biomedical tasks, and examine the zero-shot learning performance. We developed two biomedical vision language models, BiomedGPT-Large and BiomedGPT-XLarge, based on an encoder-decoder-based transformer architecture. We fine-tuned the two models on 23 benchmark datasets from 6 multi-modal biomedical tasks including one image-only task (image classification), three language-only tasks (text understanding, text summarization and question answering), and two vision-language tasks (visual question answering and image captioning). We compared the developed scaled models with our previous BiomedGPT-Base model and existing prestigious models reported in the literature. We instruction-tuned the two models using a large-scale multi-modal biomedical instruction-tuning dataset and assessed the zero-shot learning performance and alignment accuracy.

cs.AI↗

arXiv2025

AGENT-X: Adaptive Guideline-based Expert Network for Threshold-free AI-generated teXt detection

Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose AGENT-X, a zero-shot multi-agent framework informed by classical rhetoric and systemic functional linguistics. Specifically, we organize detection guidelines into semantic, stylistic, and structural dimensions, each independently evaluated by specialized linguistic agents that provide explicit reasoning and robust calibrated confidence via semantic steering. A meta agent integrates these assessments through confidence-aware aggregation, enabling threshold-free, interpretable classification. Additionally, an adaptive Mixture-of-Agent router dynamically selects guidelines based on inferred textual characteristics. Experiments on diverse datasets demonstrate that AGENT-X substantially surpasses state-of-the-art supervised and zero-shot approaches in accuracy, interpretability, and generalization.

cs.CL↗

arXiv2025

Bounding Neyman-Pearson Region with $f$-Divergences

The Neyman-Pearson region of a simple binary hypothesis testing is the set of points whose coordinates represent the false positive rate and false negative rate of some test. The lower boundary of this region is given by the Neyman-Pearson lemma, and is up to a coordinate change, equivalent to the optimal ROC curve. We establish a novel lower bound for the boundary in terms of any $f$-divergence. Since the bound generated by hockey-stick $f$-divergences characterizes the Neyman-Pearson boundary, this bound is best possible. In the case of KL divergence, this bound improves Pinsker's inequality. Furthermore, we obtain a closed-form refined upper bound for the Neyman-Pearson boundary in terms of the Chernoff $α$-coefficient. Finally, we present methods for constructing pairs of distributions that can approximately or exactly realize any given Neyman-Pearson boundary.

math.ST↗

arXiv2025

Natural Language Generation in Healthcare: A Review of Methods and Applications

Natural language generation (NLG) is the key technology to achieve generative artificial intelligence (AI). With the breakthroughs in large language models (LLMs), NLG has been widely used in various medical applications, demonstrating the potential to enhance clinical workflows, support clinical decision-making, and improve clinical documentation. Heterogeneous and diverse medical data modalities, such as medical text, images, and knowledge bases, are utilized in NLG. Researchers have proposed many generative models and applied them in a number of healthcare applications. There is a need for a comprehensive review of NLG methods and applications in the medical domain. In this study, we systematically reviewed 113 scientific publications from a total of 3,988 NLG-related articles identified using a literature search, focusing on data modality, model architecture, clinical applications, and evaluation methods. Following PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) guidelines, we categorize key methods, identify clinical applications, and assess their capabilities, limitations, and emerging challenges. This timely review covers the key NLG technologies and medical applications and provides valuable insights for future studies to leverage NLG to transform medical discovery and healthcare.

cs.CL↗

arXiv2025

Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes

Production of photorealistic, navigable 3D site models requires a large volume of carefully collected images that are often unavailable to first responders for disaster relief or law enforcement. Real-world challenges include limited numbers of images, heterogeneous unposed cameras, inconsistent lighting, and extreme viewpoint differences for images collected from varying altitudes. To promote research aimed at addressing these challenges, we have developed the first public benchmark dataset for 3D reconstruction and novel view synthesis based on multiple calibrated ground-level, security-level, and airborne cameras. We present datasets that pose real-world challenges, independently evaluate calibration of unposed cameras and quality of novel rendered views, demonstrate baseline performance using recent state-of-practice methods, and identify challenges for further research.

cs.CV↗

arXiv2025

Correlators of long strings on AdS$_3\times$S$^3\times$T$^4$

In this work, we calculate correlators of long strings on AdS$_3\times$S$^3\times$T$^4$ with pure NS-NS flux. We first construct physical vertex operators that correspond to long strings. Due to the GSO projection, they depend on the parity of the spectral flow parameter $w$. For a given $w$, we construct the physical operators that have the lowest space-time weights in both the NS and R sector. Then, we calculate three point correlators for each possible type of parities of spectral flows. We find that the recursion relations of correlators in the bosonic SL$(2,\mathbb{R})$ WZW model can be understood from the equivalence of these superstring correlators with different picture choices. Furthermore, after carefully mapping the vertex operators to appropriate operators in the dual CFT, we find that once the fermionic contributions together with the picture changing effects are correctly taken into account, some mathematical identities of covering maps lead to the matching of the correlators of the two sides. We check this explicitly at the leading order in the conformal perturbation computation and conjecture that this remains correct to all orders.

hep-th↗

arXiv2025

ViralQC: A Tool for Assessing Completeness and Contamination of Predicted Viral Contigs

Motivation: Viruses represent the most abundant biological entities on the planet and play vital roles in diverse ecosystems. Cataloging viruses across various environments is essential for understanding their properties and functions. Metagenomic sequencing has emerged as the most comprehensive method for virus discovery, enabling the sequencing of all genetic materials, including viruses, from host or environmental samples. However, distinguishing viral sequences from the vast background of cellular organism-derived reads in metagenomic data remains a significant challenge. While several learning-based tools, such as VirSorter2 and geNomad, have shown promise in identifying viral contigs, they often experience varying degrees of false positive rates due to noise in sequencing and assembly, shared genes between viruses and their hosts, and the formation of proviruses within host genomes. This highlights the urgent need for an accurate and efficient method to evaluate the quality of viral contigs. Results: To address these challenges, we introduce ViralQC, a tool designed to assess the quality of reported viral contigs or bins. ViralQC identifies contamination regions within putative viral sequences using foundation models trained on viral and cellular genomes and estimates viral completeness through protein organization alignment. We evaluate ViralQC on multiple datasets and compare its performance against CheckV, the state-of-the-art in virus quality assessment. Notably, ViralQC correctly identifies 38% more contamination than CheckV, while maintaining a median absolute error of only 3%. In addition, ViralQC delivers more accurate results for medium- to high-quality (>50% completeness) contigs, demonstrating its superior performance in completeness estimation.

q-bio.GN↗

arXiv2025

Geometry Field Splatting with Gaussian Surfels

Geometric reconstruction of opaque surfaces from images is a longstanding challenge in computer vision, with renewed interest from volumetric view synthesis algorithms using radiance fields. We leverage the geometry field proposed in recent work for stochastic opaque surfaces, which can then be converted to volume densities. We adapt Gaussian kernels or surfels to splat the geometry field rather than the volume, enabling precise reconstruction of opaque solids. Our first contribution is to derive an efficient and almost exact differentiable rendering algorithm for geometry fields parameterized by Gaussian surfels, while removing current approximations involving Taylor series and no self-attenuation. Next, we address the discontinuous loss landscape when surfels cluster near geometry, showing how to guarantee that the rendered color is a continuous function of the colors of the kernels, irrespective of ordering. Finally, we use latent representations with spherical harmonics encoded reflection vectors rather than spherical harmonics encoded colors to better address specular surfaces. We demonstrate significant improvement in the quality of reconstructed 3D surfaces on widely-used datasets.

cs.GR↗

arXiv2025

Speedy MASt3R

Image matching is a key component of modern 3D vision algorithms, essential for accurate scene reconstruction and localization. MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme that accelerates matching by orders of magnitude while preserving theoretical guarantees. This approach has gained strong traction, with DUSt3R and MASt3R collectively cited over 250 times in a short span, underscoring their impact. However, despite its accuracy, MASt3R's inference speed remains a bottleneck. On an A40 GPU, latency per image pair is 198.16 ms, mainly due to computational overhead from the ViT encoder-decoder and Fast Reciprocal Nearest Neighbor (FastNN) matching. To address this, we introduce Speedy MASt3R, a post-training optimization framework that enhances inference efficiency while maintaining accuracy. It integrates multiple optimization techniques, including FlashMatch-an approach leveraging FlashAttention v2 with tiling strategies for improved efficiency, computation graph optimization via layer and tensor fusion having kernel auto-tuning with TensorRT (GraphFusion), and a streamlined FastNN pipeline that reduces memory access time from quadratic to linear while accelerating block-wise correlation scoring through vectorized computation (FastNN-Lite). Additionally, it employs mixed-precision inference with FP16/FP32 hybrid computations (HybridCast), achieving speedup while preserving numerical precision. Evaluated on Aachen Day-Night, InLoc, 7-Scenes, ScanNet1500, and MegaDepth1500, Speedy MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy. This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.

cs.CV↗

arXiv2025

Phase transition in a doubly holographic model of closed $\mathbf{dS_{2} }$ spacetime

Double holography has been proved to be a powerful method in comprehending the spacetime entanglement. In this paper we investigate the doubly holographic construction in ${\mathrm{dS_{2}} }$ spacetime. We find that in this model there exists a new extremal surface besides the Hartman-Maldacena surface and the island surface, which could lead to a more complex phase structure. We then propose a generalized mutual entropy to interpret the phase transition. However, this extremal surface has a subtle property that the length of a part of the geodesic is negative when this saddle is dominant. This is because the negative part of the geodesic is within the horizon of the bulk geometry. We move to the ${\mathrm{AdS_{2}} }$ spacetime and find this subtlety still exists. We purpose a simple solution to this issue.

hep-th↗

arXiv2025

Synthesis of layered gold tellurides AuSbTe and Au$_2$Te$_3$ and their semiconducting and metallic behavior

Previous studies on natural samples of pampaloite (AuSbTe) revealed the crystal structure of a potentially cleavable and/or exfoliable material, while studies on natural and synthetic montbrayite (Sb-containing Au$_2$Te$_3$) claimed various chemical compositions for this low symmetry compound. Few investigations of synthetic samples have been reported for both materials, leaving much of their chemical, thermal and electronic characteristics unknown. Here, we investigate the stability, electronic properties and synthesis of the gold antimony tellurides AuSbTe and Au$_{1.9}$Sb$_{0.46}$Te$_{2.64}$ (montbrayite). Differential thermal analysis and $\textit{in situ}$ powder x-ray diffraction revealed that AuSbTe is incongruently melting, while Au$_{1.9}$Sb$_{0.46}$Te$_{2.64}$ is congruently melting. Calculations of the band structures and four-point resistivity measurements showed that AuSbTe is a semiconductor and Au$_{1.9}$Sb$_{0.46}$Te$_{2.64}$ a metal. Various synthesis attempts confirmed the limited stable chemical composition of Au$_{1.9}$Sb$_{0.46}$Te$_{2.64}$, identified successful methods to synthesize both compounds, and highlighted the challenges associated with single crystal synthesis of AuSbTe.

cond-mat.mtrl-sci↗

arXiv2025

GiantHunter: Accurate detection of giant virus in metagenomic data using reinforcement-learning and Monte Carlo tree search

Motivation: Nucleocytoplasmic large DNA viruses (NCLDVs) are notable for their large genomes and extensive gene repertoires, which contribute to their widespread environmental presence and critical roles in processes such as host metabolic reprogramming and nutrient cycling. Metagenomic sequencing has emerged as a powerful tool for uncovering novel NCLDVs in environmental samples. However, identifying NCLDV sequences in metagenomic data remains challenging due to their high genomic diversity, limited reference genomes, and shared regions with other microbes. Existing alignment-based and machine learning methods struggle with achieving optimal trade-offs between sensitivity and precision. Results: In this work, we present GiantHunter, a reinforcement learning-based tool for identifying NCLDVs from metagenomic data. By employing a Monte Carlo tree search strategy, GiantHunter dynamically selects representative non-NCLDV sequences as the negative training data, enabling the model to establish a robust decision boundary. Benchmarking on rigorously designed experiments shows that GiantHunter achieves high precision while maintaining competitive sensitivity, improving the F1-score by 10% and reducing computational cost by 90% compared to the second-best method. To demonstrate its real-world utility, we applied GiantHunter to 60 metagenomic datasets collected from six cities along the Yangtze River, located both upstream and downstream of the Three Gorges Dam. The results reveal significant differences in NCLDV diversity correlated with proximity to the dam, likely influenced by reduced flow velocity caused by the dam. These findings highlight the potential of GiantSeeker to advance our understanding of NCLDVs and their ecological roles in diverse environments.

q-bio.GN↗

arXiv2025

Rateless Stochastic Coding for Delay-Constrained Semantic Communication

We consider the problem of joint source-channel coding for semantic communication from a rateless perspective, the purpose of which is to settle the balance between reliability (distortion/perception) and effectiveness (rate) of transmission over uncertain channels. In particular, we propose a more general communication objective that minimizes the perceptual distance by incorporating a semantic-level reconstruction objective in addition to the conventional pixel-level reconstruction objective. Based on the proposed objective, we then propose a novel JSCC coding scheme called rateless stochastic coding (RSC) by introducing a generative decoder and dithered quantization. The coding scheme enables reconstruction based on both distortion and perception metrics through rateless transmission. Extensive experiments demonstrate that the proposed RSC can achieve variable rates of transmission maintaining an excellent trade-off between distortion and perception.

cs.IR↗

arXiv2025

GenEx: Generating an Explorable World

Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments. GenEx generates an entire 3D-consistent imaginative environment from as little as a single RGB image, bringing it to life through panoramic video streams. Leveraging scalable 3D world data curated from Unreal Engine, our generative model is rounded in the physical world. It captures a continuous 360-degree environment with little effort, offering a boundless landscape for AI agents to explore and interact with. GenEx achieves high-quality world generation, robust loop consistency over long trajectories, and demonstrates strong 3D capabilities such as consistency and active 3D mapping. Powered by generative imagination of the world, GPT-assisted agents are equipped to perform complex embodied tasks, including both goal-agnostic exploration and goal-driven navigation. These agents utilize predictive expectation regarding unseen parts of the physical world to refine their beliefs, simulate different outcomes based on potential decisions, and make more informed choices. In summary, we demonstrate that GenEx provides a transformative platform for advancing embodied AI in imaginative spaces and brings potential for extending these capabilities to real-world exploration.

cs.CV↗

arXiv2024

An Immersive Multi-Elevation Multi-Seasonal Dataset for 3D Reconstruction and Visualization

Significant progress has been made in photo-realistic scene reconstruction over recent years. Various disparate efforts have enabled capabilities such as multi-appearance or large-scale modeling; however, there lacks a welldesigned dataset that can evaluate the holistic progress of scene reconstruction. We introduce a collection of imagery of the Johns Hopkins Homewood Campus, acquired at different seasons, times of day, in multiple elevations, and across a large scale. We perform a multi-stage calibration process, which efficiently recover camera parameters from phone and drone cameras. This dataset can enable researchers to rigorously explore challenges in unconstrained settings, including effects of inconsistent illumination, reconstruction from large scale and from significantly different perspectives, etc.

cs.CV↗