arXiv subjects

Gong Cheng

Publications and source records attributed to Gong Cheng.

At least 37 records · Page 2Linked to original sources

arXiv2026

Gravitational back-reaction is magical

We study the interplay between magic and entanglement in quantum many-body systems. We show that non-local magic, which is supported by the quantum correlations is lower bounded by the non-flatness of entanglement spectrum and upper bounded by the amount of entanglement in the system. We then argue that a smoothed version of non-local magic bounds the hardness of classical simulations for incompressible states. In conformal field theories, we conjecture that the non-local magic should scale linearly with entanglement entropy but sublinearly when an approximation of the state is allowed. We support the conjectures using both analytical arguments based on unitary distillation and numerical data from an Ising CFT. If the CFT has a holographic dual, then we prove that the non-local magic vanishes if and only if there is no gravitational back-reaction. Furthermore, we show that non-local magic is approximately equal to the rate of change of the minimal surface area in response to the change of cosmic brane tension in the bulk.

hep-th↗

arXiv2026

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning

The application of physics formulas is a fundamental human capability in numerical reasoning. While existing datasets often rely on implicit mathematical knowledge, they rarely explicitate the underlying formulas. To address this, we introduce FormulaReasoning, a new benchmark for formula-based numerical reasoning comprising 5,324 questions requiring calculations grounded in external physics principles. We provide high-quality, fine-grained annotations in English and Chinese--including formula structures, parameter names, symbols, values, and units--curated through manual effort and LLM-assisted validation. Additionally, we provide a consolidated formula database as an external knowledge source. To further challenge model performance, we develop an extended version of the dataset by coupling multiple questions. We evaluate various architectural and methodological frameworks, including retrieval-augmented methods, modular reasoning (formula generation, parameter extraction, and calculation), and preference-based optimization. Our analysis identifies critical challenges in formula-based reasoning, highlighting significant opportunities for future methodological advancement.

cs.CL↗

arXiv2025

Methods for Detecting Gravitational Waves from mini-Extreme-Mass-Ratio Inspirals I: Statistics Based on Time-Frequency Signal Tracks

Mini-extreme-mass-ratio inspirals (mini-EMRIs), composed of a stellar-mass compact object and a much lighter companion, are promising sources of continuous gravitational waves in the frequency band of ground-based interferometers such as LIGO-Virgo-KAGRA. Such systems, consisting of sub-solar-mass compact objects, provide a unique probe of exotic compact objects, including primordial black holes. Detecting such long-lived signals, however, remains challenging. Here, we adapt standard methods used in searches for quasi-monochromatic signals to search for mini-EMRIs, and derive a statistical framework that explicitly handles spectral leakage. In particular, we introduce a new method that sums along the tracks in the time-frequency plane carved out by possible mini-EMRI signals, which we call $Σ$Track. This refinement establishes a general basis for analyzing long-duration transient signals with rapid frequency evolutions, regardless of the underlying mechanism for gravitational-wave emission. We also compute a new semi-analytic sensitivity estimate within our new statistical framework, which is valid under the assumption that the signal is weak with respect to the noise level. We then establish a statistic that quantifies how to discretize the search parameter space for our method, which works for mini-EMRIs, as well as arbitrary signal types. Our results provide a foundation for mini-EMRI searches and demonstrate the potential of current ground-based detectors to probe the existence of sub-solar-mass compact objects.

gr-qc↗

arXiv2025

Methods for Detecting Gravitational Waves from mini-Extreme-Mass-Ratio Inspirals II: A Spectral-Leakage-Aware Framework

Mini-Extreme-Mass-Ratio Inspirals (mini-EMRIs), comprising a sub-solar exotic compact object (such as a primordial black hole or boson star) orbiting a much heavier stellar-origin or exotic compact object, represent key targets for ground-based gravitational-wave detectors to probe the early universe and the nature of dark matter. However, detecting such systems, which could spend hours to years in LIGO, Virgo and KAGRA data, poses a computational challenge to standard matched-filtering methods. However, semi-coherent methods are constrained by the quasi-monochromatic assumption, which restricts the coherence time to avoid spectral leakage caused by frequency evolution. In this work, we extend the development of our method, $Σ$Track, to the regime in which the quasi-monochromatic approximation is relaxed, in two ways. First, we establish an analytical model for the spectral leakage, extending the validity of conventional analyses beyond the quasi-monochromatic regime. Second, we propose the $ΣR$ statistic -- a novel detection metric formed by a weighted summation of power ratios -- which effectively recovers the signal energy dispersed across adjacent frequency bins. Building on this framework, we further introduce an innovative frequency-layered search strategy that dynamically optimizes the coherence time across the observation band. We benchmark our method against a globally optimized Hough transform pipeline using a fiducial mini-EMRI signal from a binary with masses $(1.5, 10^{-5})\,M_\odot$. The results demonstrate that our framework achieves an order-of-magnitude enhancement in the effective detection volume, significantly expanding the horizon for discovering mini-EMRIs and sub-solar exotic compact objects with ground-based gravitational wave detectors. This approach can be similarly applied to EMRI searches for future space-based gravitational wave detectors.

gr-qc↗

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↗