Searcharxiv⌕ Search

arXiv subjects

Geng Chen

Publications and source records attributed to Geng Chen.

At least 37 records · Page 2Linked to original sources
arXiv2026

Informationally Complete Distributed Metrology Without a Shared Reference Frame

In quantum information processing, implementing arbitrary preparations and measurements on qubits necessitates precise information to identify a specific reference frame (RF). In space quantum communication and sensing, where a shared RF is absent, the interplay between locality and symmetry imposes fundamental restrictions on physical systems. A restriction on realizable unitary operations results in a no-go theorem prohibiting the extraction of locally encoded information in RF-independent distributed metrology. Here, we propose a reversed-encoding method applied to two copies of local-unitary-invariant network states. This approach circumvents the no-go theorem while simultaneously mitigating decoherence-like noise caused by RF misalignment, thereby enabling the complete recovery of the quantum Fisher information (QFI). Furthermore, we confirm local Bell-state measurements as an optimal strategy to saturate the QFI. Our findings pave the way for the field application of distributed quantum sensing, which is inherently subject to unknown RF misalignment and was previously precluded by the no-go theorem.

quant-ph↗
arXiv2026

Non-commutativity as a Universal Characterization for Enhanced Quantum Metrology

A central challenge in quantum metrology is to effectively harness quantum resources to surpass classical precision bounds. Although recent studies suggest that the indefinite causal order may enable sensitivities to attain the super-Heisenberg scaling, the physical origins of such enhancements remain elusive. Here, we introduce the nilpotency index $\mathcal{K}$, which quantifies the depth of non-commutativity between operators during the encoding process, can act as a fundamental parameter governing quantum-enhanced sensing. We show that a finite $\mathcal{K}$ yields an enhanced scaling of root-mean-square error as $N^{-(1+\mathcal{K})}$. Meanwhile, the requirement for indefinite causal order arises only when the nested commutators become constant. Remarkably, in the limit $\mathcal{K} \to \infty$, exponential precision scaling $N^{-1}e^{-N}$ is achievable. We propose experimentally feasible protocols implementing these mechanisms, providing a systematic pathway towards practical quantum-enhanced metrology.

quant-ph↗
arXiv2025

AirCopBench: A Benchmark for Multi-drone Collaborative Embodied Perception and Reasoning

Multimodal Large Language Models (MLLMs) have shown promise in single-agent vision tasks, yet benchmarks for evaluating multi-agent collaborative perception remain scarce. This gap is critical, as multi-drone systems provide enhanced coverage, robustness, and collaboration compared to single-sensor setups. Existing multi-image benchmarks mainly target basic perception tasks using high-quality single-agent images, thus failing to evaluate MLLMs in more complex, egocentric collaborative scenarios, especially under real-world degraded perception conditions.To address these challenges, we introduce AirCopBench, the first comprehensive benchmark designed to evaluate MLLMs in embodied aerial collaborative perception under challenging perceptual conditions. AirCopBench includes 14.6k+ questions derived from both simulator and real-world data, spanning four key task dimensions: Scene Understanding, Object Understanding, Perception Assessment, and Collaborative Decision, across 14 task types. We construct the benchmark using data from challenging degraded-perception scenarios with annotated collaborative events, generating large-scale questions through model-, rule-, and human-based methods under rigorous quality control. Evaluations on 40 MLLMs show significant performance gaps in collaborative perception tasks, with the best model trailing humans by 24.38% on average and exhibiting inconsistent results across tasks. Fine-tuning experiments further confirm the feasibility of sim-to-real transfer in aerial collaborative perception and reasoning.

cs.CV↗
arXiv2025

In-N-On: Scaling Egocentric Manipulation with in-the-wild and on-task Data

Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/

cs.RO↗
arXiv2025

Invested and Potential Magic Resources in Measurement-Based Quantum Computation

Magic states and magic gates are crucial for achieving universal quantum computation, but important questions about how magic resources should be implemented to attain maximal quantum advantage have remained unexplored, especially in the context of measurement-based quantum computation (MQC). This work bridges the gap between MQC and the resource theory of magic by introducing the key concepts of "invested" and "potential" magic resources. The former quantifies the magic cost associated with MQC, serving as both a resource witness and a feasible upper bound for the practical realization, and is gate-order independent; The latter represents the maximal achievable magic resource in a given graph structure defining MQC. We utilize both concepts to analyze the quantum Fourier transform (QFT) and provide a fresh perspective on the universality of MQC, highlighting the crucial role of non-Pauli measurements in injecting magic. In particular, we theoretically prove that high-dimensional graphs can generate an exponential advantage of MQC compared to classical computing. We demonstrate experimentally our theoretical findings in a high-fidelity four-photon setup, surpassing conventional magic state injection (MSI) methods in both qubit efficiency and resource utilization. Our findings pave the way for future research exploring magic resource optimization and novel distillation schemes within the MQC framework, advancing fault-tolerant universal quantum computation.

quant-ph↗
arXiv2025

Channel-Constrained Markovian Quantum Diffusion Model from Open System Perspective

We present a channel-constrained Markovian quantum diffusion (CCMQD) model that prepares quantum states by rigorously framing the generative process within the dynamics of open quantum systems. Our model interprets the forward diffusion process as natural decoherence using quantum master equations, whereas the reverse denoising is achieved by learning inverse quantum channels. Our core innovation is a comprehensive channel-constrained framework: we model the diffusion and denoising steps as quantum channels defined by Kraus operators, ensure their physical validity through optimization on the Stiefel manifold, and introduce tailored training strategies and loss functions that leverage this constrained structure for high-fidelity state reconstruction. Experimental validation on systems ranging from single qubits to entangled states $7$ -qubits demonstrates high-fidelity state generation, achieving fidelities exceeding $0.998$ under both random and depolarizing noise conditions. This work confirms that quantum diffusion can be characterized as a controlled Markov evolution, demonstrating that environmental interactions are not limited to being a source of decoherence but can also be utilized to achieve high-fidelity quantum state synthesis.

quant-ph↗
arXiv2025

Quantitative weak-BV stability of "wild'' solutions to compressible Euler equations, with a view towards higher systems

For hyperbolic systems of conservation laws, including important physical models from continuum mechanics, the question of stability for large data solutions remains a challenging open problem. In recent work (arXiv:2507.23645) the authors introduce a framework for showing Hölder stability of potentially "wild" large data solutions, relative to a class of BV solutions, for systems with two conserved quantities. This is referred to as "weak-BV" stability. In this paper, we give a short introduction to the methods while applying them to the "full" Euler system with three conserved quantities. We discuss applications to future work for higher systems with additional conserved quantities.

math.AP↗
arXiv2025

Solutions to conservation laws are Hölder-stable in $L^2$ in the weak-BV setting

We consider hyperbolic systems of conservation laws in one spatial dimension. For any limit of front tracking solutions $v$, and for a general weak solution $u\in L^\infty$ with no BV assumption, we prove the following Hölder-type stability estimate in $L^2$: $$||u(\cdot,τ)-v(\cdot,τ)||_{L^2} \leq K \sqrt{||u( \cdot,0)-v( \cdot,0)||_{L^2}}$$ for all $τ$ without smallness and for a universal constant $K$. Our result holds for all limits of front tracking solutions $v$ with BV bound, either for general systems with small-BV data, or for special systems (isothermal Euler, Temple-class systems) with large-BV data. Our results apply to physical systems such as isentropic Euler. The stability estimate is completely independent of the BV norm of the potentially very wild solution $u$. We use the $L^2$ theory of shock stability modulo an artificial shift of position (Vasseur [Handbook of Differential Equations: Evolutionary Equations, 4:323 -- 376, 2008]) but our stability results do not depend on an artificial shift. Moreover, we give the first result within this framework which can show uniqueness of some solutions with large $L^\infty$ and infinite BV initial data. We apply these techniques to isothermal Euler.

math.AP↗
arXiv2025

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection

To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly efficient task adaptation by training only a minimal set of additional parameters. To fully unlock the potential of VFMs, we investigate two leading backbones: the Segment Anything Model v2 (SAM2), renowned for its strong segmentation priors, and DINOv3, a state-of-the-art self-supervised representation learner. The framework is complemented by a deliberately lightweight decoder, ensuring the focus remains on the powerful feature representations from the backbones. Extensive experiments demonstrate that PeftCD achieves state-of-the-art performance across multiple public datasets, including SYSU-CD (IoU 73.81%), WHUCD (92.05%), MSRSCD (64.07%), MLCD (76.89%), CDD (97.01%), S2Looking (52.25%) and LEVIR-CD (85.62%), with notably precise boundary delineation and strong suppression of pseudo-changes. In summary, PeftCD presents an optimal balance of accuracy, efficiency, and generalization. It offers a powerful and scalable paradigm for adapting large-scale VFMs to real-world remote sensing change detection applications. The code and pretrained models will be released at https://github.com/dyzy41/PeftCD.

cs.CV↗
arXiv2025

From Navier-Stokes to BV solutions of the barotropic Euler equations

In the realm of mathematical fluid dynamics, a formidable challenge lies in establishing inviscid limits from the Navier-Stokes equations to the Euler equations, wherein physically admissible solutions can be discerned. The pursuit of solving this intricate problem, particularly concerning singular solutions, persists in both compressible and incompressible scenarios. This article focuses on small $BV$ solutions to the barotropic Euler equation in one spatial dimension. Our investigation demonstrates that these solutions are inviscid limits for solutions to the associated compressible Navier-Stokes equation. Moreover, we extend our findings by establishing the well-posedness of such solutions within the broader class of inviscid limits of Navier-Stokes equations with locally bounded energy initial values.

math.AP↗
arXiv2025

Topological resilience of optical skyrmions in local decoherence

The topologically protected configuration embedded in skyrmions has prompted some investigations into their fundamental properties and versatile applications, sparking interest and guiding ongoing development. The topological protection associated with skyrmions was initially observed in systems with interactions. It is widely believed that skyrmions are stable yet relevant confirmation and empirical research remain limited. A pertinent question is whether skyrmion configurations formed by a single classical beam with two coupled degrees of freedom also exhibit topological stability. In this study, we affirm this hypothesis by investigating the effects of local decoherence. We analytically and numerically demonstrate the topological resilience of skyrmions and the occurrence of transition points of skyrmion numbers in local decoherence across three typical decoherence channels. On the other hand, we show that these qualities are independent of the initial state. From the numerical results, we find that inhomogeneous but continuous decoherence channels also have the same behaviors and maintain topological stability of skyrmions as homogeneous decoherence channels do. These properties of skyrmions contribute to further applications in various areas, including communication and imaging.

physics.optics↗
arXiv2025

HuB: Learning Extreme Humanoid Balance

The human body demonstrates exceptional motor capabilities-such as standing steadily on one foot or performing a high kick with the leg raised over 1.5 meters-both requiring precise balance control. While recent research on humanoid control has leveraged reinforcement learning to track human motions for skill acquisition, applying this paradigm to balance-intensive tasks remains challenging. In this work, we identify three key obstacles: instability from reference motion errors, learning difficulties due to morphological mismatch, and the sim-to-real gap caused by sensor noise and unmodeled dynamics. To address these challenges, we propose HuB (Humanoid Balance), a unified framework that integrates reference motion refinement, balance-aware policy learning, and sim-to-real robustness training, with each component targeting a specific challenge. We validate our approach on the Unitree G1 humanoid robot across challenging quasi-static balance tasks, including extreme single-legged poses such as Swallow Balance and Bruce Lee's Kick. Our policy remains stable even under strong physical disturbances-such as a forceful soccer strike-while baseline methods consistently fail to complete these tasks. Project website: https://hub-robot.github.io

cs.RO↗
arXiv2025

M2IO-R1: An Efficient RL-Enhanced Reasoning Framework for Multimodal Retrieval Augmented Multimodal Generation

Current research on Multimodal Retrieval-Augmented Generation (MRAG) enables diverse multimodal inputs but remains limited to single-modality outputs, restricting expressive capacity and practical utility. In contrast, real-world applications often demand both multimodal inputs and multimodal outputs for effective communication and grounded reasoning. Motivated by the recent success of Reinforcement Learning (RL) in complex reasoning tasks for Large Language Models (LLMs), we adopt RL as a principled and effective paradigm to address the multi-step, outcome-driven challenges inherent in multimodal output generation. Here, we introduce M2IO-R1, a novel framework for Multimodal Retrieval-Augmented Multimodal Generation (MRAMG) that supports both multimodal inputs and outputs. Central to our framework is an RL-based inserter, Inserter-R1-3B, trained with Group Relative Policy Optimization to guide image selection and placement in a controllable and semantically aligned manner. Empirical results show that our lightweight 3B inserter achieves strong reasoning capabilities with significantly reduced latency, outperforming baselines in both quality and efficiency.

cs.IR↗
arXiv2025

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos

Egocentric videos provide valuable insights into human interactions with the physical world, which has sparked growing interest in the computer vision and robotics communities. A critical challenge in fully understanding the geometry and dynamics of egocentric videos is dense scene reconstruction. However, the lack of high-quality labeled datasets in this field has hindered the effectiveness of current supervised learning methods. In this work, we aim to address this issue by exploring an self-supervised dynamic scene reconstruction approach. We introduce EgoMono4D, a novel model that unifies the estimation of multiple variables necessary for Egocentric Monocular 4D reconstruction, including camera intrinsic, camera poses, and video depth, all within a fast feed-forward framework. Starting from pretrained single-frame depth and intrinsic estimation model, we extend it with camera poses estimation and align multi-frame results on large-scale unlabeled egocentric videos. We evaluate EgoMono4D in both in-domain and zero-shot generalization settings, achieving superior performance in dense pointclouds sequence reconstruction compared to all baselines. EgoMono4D represents the first attempt to apply self-supervised learning for pointclouds sequence reconstruction to the label-scarce egocentric field, enabling fast, dense, and generalizable reconstruction. The interactable visualization, code and trained models are released https://egomono4d.github.io/

cs.CV↗
arXiv2025

DYNAMO: Dynamic Neutral Atom Multi-programming Optimizer Towards Quantum Operating Systems

As quantum computing advances towards practical applications, quantum operating systems become inevitable, where multi-programming -- the core functionality of operating systems -- enables concurrent execution of multiple quantum programs to enhance hardware utilization. However, most quantum compilation work focuses solely on single-circuit execution, severely limiting resource efficiency and hindering quantum operating system development. We propose Dynamic Neutral Atom Multi-programming Optimizer (DYNAMO), a method that realizes multi-programming on neutral atom quantum architectures through parallel compilation and intelligent resource allocation across multiple quantum processing units (QPUs). DYNAMO addresses two critical challenges: inefficient and difficult resource partitioning, and complex scheduling conflicts from concurrent program. Our method enables efficient spatial and temporal resource sharing while maintaining circuit correctness and hardware constraints. Experimental evaluation across circuits ranging from 12 to over 1200 gates demonstrates that DYNAMO achieves up to 14.39x compilation speedup while reducing execution stages by an average of 50.47%. Furthermore, DYNAMO successfully distributes workloads across multiple QPUs with balanced resource utilization. By enabling efficient multi-programming capabilities, DYNAMO establishes a critical foundation towards realizing practical quantum operating systems.

quant-ph↗
arXiv2025

Continual Visual Reinforcement Learning with A Life-Long World Model

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without forgetting previous knowledge. In this paper, we present a new continual learning approach for visual dynamics modeling and explore its efficacy in visual control. The key assumption is that an ideal world model can provide a non-forgetting environment simulator, which enables the agent to optimize the policy in a multi-task learning manner based on the imagined trajectories from the world model. To this end, we first introduce the life-long world model, which learns task-specific latent dynamics using a mixture of Gaussians and incorporates generative experience replay to mitigate catastrophic forgetting. Then, we further address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach. Our model remarkably outperforms the straightforward combinations of existing continual learning and visual RL algorithms on DeepMind Control Suite and Meta-World benchmarks with continual visual control tasks.

cs.LG↗
arXiv2025

Nonlinear Enhancement of Measurement Precision via a Hybrid Quantum Switch

Quantum metrology promises measurement precision beyond the classical limit by using suitably tailored quantum states and detection strategies. However, scaling up this advantage is experimentally challenging, due to the difficulty of generating high-quality large-scale probes. Here, we build a photonic setup that achieves enhanced precision scaling by manipulating the probe's dynamics through operations performed in a coherently controlled order. Our setup applies an unknown rotation and a known orbital angular momentum increase in a coherently controlled order, in a way that reproduces a hybrid quantum SWITCH involving gates generated by both discrete and continuous variables. The unknown rotation angle $θ$ is measured with precision scaling as $1/4ml$ when a photon undergoes a rotation of $2mθ$ and an angular momentum shift of $2l \hbar$. With a practical enhancement factor as high as 2317, the ultimate precision in our experiment is $0.0105^{\prime \prime}$ when using $7.16\times10^7$ photons, corresponding to a normalized precision of $\approx 10^{-4}$rad per photon. No photon interaction occurs in our experiment, and the precision enhancement consumes only a linearly increasing amount of physical resources while achieving a nonlinear scaling of the precision. We further indicate that this nonlinear enhancement roots in an in-depth exploration of the Heisenberg uncertainty principle (HUP), and our findings not only deepen the understanding of the HUP but also pave a pathway for advancements in quantum metrology.

quant-ph↗