arXiv subjects

Gong Cheng

Publications and source records attributed to Gong Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2025

DSEBench: A Test Collection for Explainable Dataset Search with Examples

Dataset search is a well-established task in the Semantic Web and information retrieval research. Current approaches retrieve datasets either based on keyword queries or by identifying datasets similar to a given target dataset. These paradigms fail when the information need involves both keywords and target datasets. To address this gap, we investigate a generalized task, Dataset Search with Examples (DSE), and extend it to Explainable DSE (ExDSE), which further requires identifying relevant fields of the retrieved datasets. We construct DSEBench, the first test collection that provides high-quality dataset-level and field-level annotations to support the evaluation of DSE and ExDSE, respectively. In addition, we employ a large language model to generate extensive annotations for training purposes. We establish comprehensive baselines on DSEBench by adapting and evaluating a variety of lexical, dense, and LLM-based retrieval, reranking, and explanation methods.

cs.IR↗

arXiv2025

Tensor complex renormalization with generalized symmetry and topological bootstrap

Recent progress in generalized symmetry and topological holography has shown that, in conformal field theory (CFT), topological data from one dimensional higher can play a key role in determining local dynamics. Based on this insight, a fixed-point (FP) tensor complex (TC) for CFT has recently been constructed. In this work, we develop a TC renormalization (TCR) algorithm adapted to this CFT-based structure, forming a renormalization-group (RG) framework with generalized symmetry. We show that the full FP tensor can emerge from the RG flow starting with only the three-point function of the primary fields. Remarkably, even when starting solely from topological data, the RG process can still reconstruct the full FP tensor--a method we call as topological bootstrap. This approach deepens the connection between the topological and dynamical aspects of CFT and suggests pathways toward a fully algebraic description of gapless quantum states, with potential extensions to higher dimensions.

cond-mat.str-el↗

arXiv2025

Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition

Deep learning models for complex-valued Synthetic Aperture Radar (CV-SAR) image recognition are fundamentally constrained by a representation trilemma under data-limited and domain-shift scenarios: the concurrent, yet conflicting, optimization of generalization, interpretability, and efficiency. Our work is motivated by the premise that the rich electromagnetic scattering features inherent in CV-SAR data hold the key to resolving this trilemma, yet they are insufficiently harnessed by conventional data-driven models. To this end, we introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture. The first stage performs a physics-guided compression, wherein a novel dictionary processor adaptively embeds physical priors, enabling a compact unfolding network to efficiently extract sparse, physically-grounded signatures. A subsequent aggregation module enriches these representations, followed by a final semantic compression stage that utilizes a compact classification head with self-distillation to learn maximally task-relevant and discriminative embeddings. We instantiate KINN in both CNN (0.7M) and Vision Transformer (0.95M) variants. Extensive evaluations on five SAR benchmarks confirm that KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios and tangible interpretability, thereby providing an effective solution to the representation trilemma and offering a new path for trustworthy AI in SAR image analysis.

cs.CV↗

arXiv2025

LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models

Joint logical-numerical reasoning remains a major challenge for language models, yet existing datasets rely on fixed rule sets and offer limited control over task complexity, constraining their generalizability for evaluation and training. We present LogiNumSynth, a flexible natural language problem synthesizer that synthesizes tasks requiring proficiency in joint logical reasoning (e.g., rule-based reasoning) and numerical reasoning (e.g., arithmetic computation). LogiNumSynth supports fine-grained control over reasoning world richness, logical reasoning depth, and the complexity of numerical computations, enabling flexible data synthesis across difficulty levels. We demonstrate three key contributions: (1) Synthesizer -- synthesizing fully controllable joint reasoning tasks over natural language; (2) Evaluation & Process Analysis -- evaluating both process accuracy and answer accuracy; (3) Targeted Training -- using synthesized data to enhance LLMs' reasoning performance. Experiments with multiple LLMs highlight persistent weaknesses in logical-numerical reasoning, showing that LogiNumSynth can serve as both a diagnostic tool and a source of targeted supervision for advancing integrated reasoning skills.

cs.CL↗

arXiv2025

An efficient algorithm to compute entanglement in states with low magic

A bottleneck for analyzing the interplay between magic and entanglement is the computation of these quantities in highly entangled quantum many-body magic states. Efficient extraction of entanglement can also inform our understanding of dynamical quantum processes such as measurement-induced phase transition and approximate unitary designs. We develop an efficient classical algorithm to compute the von Neumann entropy and entanglement spectrum for such states under the condition that they have low stabilizer nullity. The algorithm exploits the property of stabilizer codes to separate entanglement into two pieces: one generated by the common stabilizer group and the other from the logical state. The low-nullity constraint ensures both pieces can be computed efficiently. Our algorithm can be applied to study the entanglement in sparsely $T$-doped circuits with possible Pauli measurements as well as certain classes of states that have both high entanglement and magic. Combining with stabilizer learning subroutines, it also enables the efficient learning of von Neumann entropies for low-nullity states prepared on quantum devices.

quant-ph↗

arXiv2025

DeepTopoNet: A Framework for Subglacial Topography Estimation on the Greenland Ice Sheets

Understanding Greenland's subglacial topography is critical for projecting the future mass loss of the ice sheet and its contribution to global sea-level rise. However, the complex and sparse nature of observational data, particularly information about the bed topography under the ice sheet, significantly increases the uncertainty in model projections. Bed topography is traditionally measured by airborne ice-penetrating radar that measures the ice thickness directly underneath the aircraft, leaving data gap of tens of kilometers in between flight lines. This study introduces a deep learning framework, which we call as DeepTopoNet, that integrates radar-derived ice thickness observations and BedMachine Greenland data through a novel dynamic loss-balancing mechanism. Among all efforts to reconstruct bed topography, BedMachine has emerged as one of the most widely used datasets, combining mass conservation principles and ice thickness measurements to generate high-resolution bed elevation estimates. The proposed loss function adaptively adjusts the weighting between radar and BedMachine data, ensuring robustness in areas with limited radar coverage while leveraging the high spatial resolution of BedMachine predictions i.e. bed estimates. Our approach incorporates gradient-based and trend surface features to enhance model performance and utilizes a CNN architecture designed for subgrid-scale predictions. By systematically testing on the Upernavik Isstrøm) region, the model achieves high accuracy, outperforming baseline methods in reconstructing subglacial terrain. This work demonstrates the potential of deep learning in bridging observational gaps, providing a scalable and efficient solution to inferring subglacial topography.

cs.CV↗

arXiv2025

Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction

Efficient trackers achieve faster runtime by reducing computational complexity and model parameters. However, this efficiency often compromises the expense of weakened feature representation capacity, thus limiting their ability to accurately capture target states using single-layer features. To overcome this limitation, we propose Multi-State Tracker (MST), which utilizes highly lightweight state-specific enhancement (SSE) to perform specialized enhancement on multi-state features produced by multi-state generation (MSG) and aggregates them in an interactive and adaptive manner using cross-state interaction (CSI). This design greatly enhances feature representation while incurring minimal computational overhead, leading to improved tracking robustness in complex environments. Specifically, the MSG generates multiple state representations at multiple stages during feature extraction, while SSE refines them to highlight target-specific features. The CSI module facilitates information exchange between these states and ensures the integration of complementary features. Notably, the introduced SSE and CSI modules adopt a highly lightweight hidden state adaptation-based state space duality (HSA-SSD) design, incurring only 0.1 GFLOPs in computation and 0.66 M in parameters. Experimental results demonstrate that MST outperforms all previous efficient trackers across multiple datasets, significantly improving tracking accuracy and robustness. In particular, it shows excellent runtime performance, with an AO score improvement of 4.5\% over the previous SOTA efficient tracker HCAT on the GOT-10K dataset. The code is available at https://github.com/wsumel/MST.

cs.CV↗

arXiv2025

Pipelined Decoder for Efficient Context-Aware Text Generation

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a bottleneck limiting the generation speed. In this paper, we propose a new decoder architecture that efficiently generates text in parallel for context-aware generation tasks. Our proposed pipelined decoder initiates the generation of multiple subsequences simultaneously, and, at each time-step, it generates a new token for each subsequence to realize parallelism. Experiments on multiple text generation tasks, including question answering, text summarization, and keyphrase generation, show that our pipelined decoder significantly improves the generation speed without a significant loss of generation quality or additional memory consumption.

cs.CL↗

arXiv2025

An approach to control design for two-level quantum ensemble systems

Quantum ensemble systems arise in a variety of applications, including NMR spectroscopy and robust quantum control. While their theoretical properties have been extensively studied, relatively little attention has been given to the explicit construction of control inputs. In this paper, we address this gap by presenting a fully implementable control strategy for a one-parameter family of driftless two-level quantum systems. The proposed method is supported by rigorous analysis that guarantees accurate approximation of target distributions on SU(2). Convergence properties are established analytically, and numerical simulations are provided to demonstrate the effectiveness of the approach.

math.OC↗

arXiv2025

Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph

The rapid growth of open source machine learning (ML) resources, such as models and datasets, has accelerated IR research. However, existing platforms like Hugging Face do not explicitly utilize structured representations, limiting advanced queries and analyses such as tracing model evolution and recommending relevant datasets. To fill the gap, we construct HuggingKG, the first large-scale knowledge graph built from the Hugging Face community for ML resource management. With 2.6 million nodes and 6.2 million edges, HuggingKG captures domain-specific relations and rich textual attributes. It enables us to further present HuggingBench, a multi-task benchmark with three novel test collections for IR tasks including resource recommendation, classification, and tracing. Our experiments reveal unique characteristics of HuggingKG and the derived tasks. Both resources are publicly available, expected to advance research in open source resource sharing and management.

cs.IR↗

arXiv2025

mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the capabilities of large language models. However, existing RAG evaluation predominantly focuses on text retrieval and relies on opaque, end-to-end assessments of generated outputs. To address these limitations, we introduce mmRAG, a modular benchmark designed for evaluating multi-modal RAG systems. Our benchmark integrates queries from six diverse question-answering datasets spanning text, tables, and knowledge graphs, which we uniformly convert into retrievable documents. To enable direct, granular evaluation of individual RAG components -- such as the accuracy of retrieval and query routing -- beyond end-to-end generation quality, we follow standard information retrieval procedures to annotate document relevance and derive dataset relevance. We establish baseline performance by evaluating a wide range of RAG implementations on mmRAG.

cs.IR↗

arXiv2025

MEET: A Million-Scale Dataset for Fine-Grained Geospatial Scene Classification with Zoom-Free Remote Sensing Imagery

Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications. However, existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples. This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios. To address this limitation, we introduce the Million-scale finE-grained geospatial scEne classification dataseT (MEET), which contains over 1.03 million zoom-free remote sensing scene samples, manually annotated into 80 fine-grained categories. In MEET, each scene sample follows a scene-inscene layout, where the central scene serves as the reference, and auxiliary scenes provide crucial spatial context for finegrained classification. Moreover, to tackle the emerging challenge of scene-in-scene classification, we present the Context-Aware Transformer (CAT), a model specifically designed for this task, which adaptively fuses spatial context to accurately classify the scene samples. CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes. Based on MEET, we establish a comprehensive benchmark for fine-grained geospatial scene classification, evaluating CAT against 11 competitive baselines. The results demonstrate that CAT significantly outperforms these baselines, achieving a 1.88% higher balanced accuracy (BA) with the Swin-Large backbone, and a notable 7.87% improvement with the Swin-Huge backbone. Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping. The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.

cs.CV↗

arXiv2025

Precision reconstruction of rational CFT from exact fixed point tensor network

The novel concept of entanglement renormalization and its corresponding tensor network renormalization technique have been highly successful in developing a controlled real space renormalization group (RG) scheme. Numerically approximate fixed-point (FP) tensors are widely used to extract the conformal data of the underlying conformal field theory (CFT) describing critical phenomena. In this paper, we present an explicit analytical construction of the FP tensor for 2D rational CFT. We define it as a correlation function between the "boundary-changing operators" (BCO) on triangles. Our construction fully captures all the real-space RG conditions. We also provide concrete examples, such as Ising, Yang-Lee and Tri-critical Ising models to compute the scaling dimensions explicitly based on the corresponding FP tensor. The BCO descendants turn out to be an optimal basis such that truncation in bond dimensions naturally produces comparable accuracies with the leading existing FP algorithms. Interestingly, our construction of FP tensors is closely related to a strange correlator, where the holographic picture naturally emerges. Our results also open a new door towards understanding CFT in higher dimensions.

cond-mat.str-el↗

arXiv2025

$\mathbfΦ$-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data

Approaches for improving generative adversarial networks (GANs) training under a few samples have been explored for natural images. However, these methods have limited effectiveness for synthetic aperture radar (SAR) images, as they do not account for the unique electromagnetic scattering properties of SAR. To remedy this, we propose a physics-inspired regularization method dubbed $Φ$-GAN, which incorporates the ideal point scattering center (PSC) model of SAR with two physical consistency losses. The PSC model approximates SAR targets using physical parameters, ensuring that $Φ$-GAN generates SAR images consistent with real physical properties while preventing discriminator overfitting by focusing on PSC-based decision cues. To embed the PSC model into GANs for end-to-end training, we introduce a physics-inspired neural module capable of estimating the physical parameters of SAR targets efficiently. This module retains the interpretability of the physical model and can be trained with limited data. We propose two physical loss functions: one for the generator, guiding it to produce SAR images with physical parameters consistent with real ones, and one for the discriminator, enhancing its robustness by basing decisions on PSC attributes. We evaluate $Φ$-GAN across several conditional GAN (cGAN) models, demonstrating state-of-the-art performance in data-scarce scenarios on three SAR image datasets.

cs.CV↗

arXiv2024

Physics-Guided Detector for SAR Airplanes

The disperse structure distributions (discreteness) and variant scattering characteristics (variability) of SAR airplane targets lead to special challenges of object detection and recognition. The current deep learning-based detectors encounter challenges in distinguishing fine-grained SAR airplanes against complex backgrounds. To address it, we propose a novel physics-guided detector (PGD) learning paradigm for SAR airplanes that comprehensively investigate their discreteness and variability to improve the detection performance. It is a general learning paradigm that can be extended to different existing deep learning-based detectors with "backbone-neck-head" architectures. The main contributions of PGD include the physics-guided self-supervised learning, feature enhancement, and instance perception, denoted as PGSSL, PGFE, and PGIP, respectively. PGSSL aims to construct a self-supervised learning task based on a wide range of SAR airplane targets that encodes the prior knowledge of various discrete structure distributions into the embedded space. Then, PGFE enhances the multi-scale feature representation of a detector, guided by the physics-aware information learned from PGSSL. PGIP is constructed at the detection head to learn the refined and dominant scattering point of each SAR airplane instance, thus alleviating the interference from the complex background. We propose two implementations, denoted as PGD and PGD-Lite, and apply them to various existing detectors with different backbones and detection heads. The experiments demonstrate the flexibility and effectiveness of the proposed PGD, which can improve existing detectors on SAR airplane detection with fine-grained classification task (an improvement of 3.1\% mAP most), and achieve the state-of-the-art performance (90.7\% mAP) on SAR-AIRcraft-1.0 dataset. The project is open-source at \url{https://github.com/XAI4SAR/PGD}.

cs.CV↗

arXiv2024

Constraints on ultra-slow-roll inflation with the NANOGrav 15-Year Dataset

Ultra-slow-roll~(USR) inflation predicts an exponential amplification of scalar perturbations at small scales, which leads to a stochastic gravitational wave background~(SGWB) through the coupling of the scalar and tensor modes at the second-order expansion of the Einstein equation. In this work, we search for such a scalar-induced SGWB from the NANOGrav 15-year (NG15) dataset, and find that the SGWB from USR inflation could explain the observed data. The Bayes factors are $54\pm 5$ for the USR inflation model alone and $68\pm 6$ for the combined USR inflation plus supermassive black hole binaries (SMBHB) models. We place constraints on the amplitude of the scalar power spectrum to $P_{\mathrm{Rp}} > 10^{-1.95}$ at $95\%$ confidence level (C.L.) at the scale of $k\sim 20\, \mathrm{pc}^{-1}$. We find that $\log_{10} P_{\mathrm{Rp}}$ degenerates with the peak scale $\log_{10} k_{\mathrm{p}}$. We also obtain the parameter space allowed by the data in the USR inflationary scenario, where the $e$-folding numbers of the duration of the USR phase has a lower limit $ΔN > 2.80$ ($95\%$ C.L.) when the USR phase ends at $N\approx 20$. With astrophysically motivated priors, the NG15 dataset fits both the USR inflation model and SMBHB model equally well.

astro-ph.CO↗

arXiv2024

Holographic phenomenology via overlapping degrees of freedom

The holographic principle suggests that regions of space contain fewer physical degrees of freedom than would be implied by conventional quantum field theory. Meanwhile, in Hilbert spaces of large dimension $2^n$, it is possible to define $N \gg n$ Pauli algebras that are nearly anti-commuting (but not quite) and which can be thought of as "overlapping degrees of freedom". We propose to model the phenomenology of holographic theories by allowing field-theory modes to be overlapping, and derive potential observational consequences. In particular, we build a Fermionic quantum field whose effective degrees of freedom approximately obey area scaling and satisfy a cosmic Bekenstein bound, and compare predictions of that model to cosmic neutrino observations. Our implementation of holography implies a finite lifetime of plane waves, which depends on the overall UV cutoff of the theory. To allow for neutrino flux from blazar TXS 0506+056 to be observable, our model needs to have a cutoff $k_{\mathrm{UV}} \lesssim 500\, k_{\mathrm{LHC}}\,$. This is broadly consistent with current bounds on the energy spectrum of cosmic neutrinos from IceCube, but high energy neutrinos are a potential challenge for our model of holography. We motivate our construction via quantum mereology, i.e. using the idea that EFT degrees of freedom should emerge from an abstract theory of quantum gravity by finding quasi-classical Hilbert space decompositions. We also discuss how to extend the framework to Bosons. Finally, using results from random matrix theory we derive an analytical understanding of the energy spectrum of our theory. The numerical tools used in this work are publicly available within the GPUniverse package, https://github.com/OliverFHD/GPUniverse .

hep-th↗

arXiv2024

X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images

SAR image simulation has attracted much attention due to its great potential to supplement the scarce training data for deep learning algorithms. Consequently, evaluating the quality of the simulated SAR image is crucial for practical applications. The current literature primarily uses image quality assessment techniques for evaluation that rely on human observers' perceptions. However, because of the unique imaging mechanism of SAR, these techniques may produce evaluation results that are not entirely valid. The distribution inconsistency between real and simulated data is the main obstacle that influences the utility of simulated SAR images. To this end, we propose a novel trustworthy utility evaluation framework with a counterfactual explanation for simulated SAR images for the first time, denoted as X-Fake. It unifies a probabilistic evaluator and a causal explainer to achieve a trustworthy utility assessment. We construct the evaluator using a probabilistic Bayesian deep model to learn the posterior distribution, conditioned on real data. Quantitatively, the predicted uncertainty of simulated data can reflect the distribution discrepancy. We build the causal explainer with an introspective variational auto-encoder to generate high-resolution counterfactuals. The latent code of IntroVAE is finally optimized with evaluation indicators and prior information to generate the counterfactual explanation, thus revealing the inauthentic details of simulated data explicitly. The proposed framework is validated on four simulated SAR image datasets obtained from electromagnetic models and generative artificial intelligence approaches. The results demonstrate the proposed X-Fake framework outperforms other IQA methods in terms of utility. Furthermore, the results illustrate that the generated counterfactual explanations are trustworthy, and can further improve the data utility in applications.

cs.CV↗