arXiv subjects

Jiabao Chen

Publications and source records attributed to Jiabao Chen.

11 recordsLinked to original sources

arXiv2026

DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation

World-Action Models (WAMs) build robot control on video-generation backbones, which jointly predict dense future visual trajectories and robot actions. We argue that video generation is an unnecessary intermediate objective for world-action modeling. For robotic manipulation, the goal of a world model is not to reproduce how the world looks at every intermediate moment, but to predict the state that the world will reach after an action is executed. The intermediate frames only describe the visual transition between physical states, which consumes substantial model capacity and computation, but do not directly specify the physical outcome that the robot action is intended to produce. In this paper, we propose DELE-w0.5, which infers robot actions from predicted future states without relying on video generation. Concretely, DELE-w0.5 infers the action sequence from its corresponding compact future latent state. The future latent state captures the action-relevant physical outcome of robot interaction and serves as an explicit bridge between world modeling and action generation. The core design principle of DELE-w0.5 is to model how the physical world changes under robot actions, rather than how its visual appearance evolves frame by frame. This formulation removes the high-dimensional visual redundancy introduced by dense video representations, and it therefore enables cheaper training and low-latency inference. Across 640 real-robot trials on four long-horizon manipulation tasks, our DELE-w0.5 achieves the best performance among all compared policies, attaining 62.5% overall full-task success and 81.3% macro ordered-stage progress. It outperforms the strongest baseline by 32.5 percentage points in full-task success and 20.1 percentage points in macro progress.

cs.RO↗

arXiv2026

Evaluating Agentic Harness Systems for Autonomous Computational Pathology

Autonomous computational pathology (ACP) converts high-level pathology analysis goals into executable, traceable and clinically bounded workflows. Realizing this capability requires adapting general agentic harness systems to pathology-specific tasks, tools, evidence standards and clinical claim boundaries. We contribute ACP-Bench, a framework that adapts existing harness systems from computational pathology support toward ACP workflow capability. ACP-Bench evaluates 41 pathology workflow tasks, including 24 biomarker, 7 morphology and 10 prognosis tasks spanning 6 body-system groups and 9 endpoint families. The benchmark evaluates 9 models and 3 harness groups (Claude Code, Codex and Open Code), yielding 369 complete trajectories. ACP-Bench evaluates each trajectory across workflow execution, diagnostic performance and clinical-boundary alignment, combining expert-adjudicated process audits, diagnostic assessment and pathologist-validated safety review. Across evaluated systems, workflow initiation, task interpretation and diagnostic reporting were more mature than tool-bound execution, result binding and reflective workflow revision, and formal end-to-end completion remained rare. ACP-Bench provides a reusable standard for auditing whether agentic systems can operationalize pathology workflows before claims of reliable clinical autonomy.

cs.CV↗

arXiv2026

Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy

Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent unsupervised domain adaptation (UDA) strategies often demonstrate limited and biased performance, which hinders their practical applications. In this study, we explore sparse points and local human preferences as weak labels in the target domain, thereby presenting a more realistic yet annotation-efficient setting. Specifically, we develop Prefer-DAS, which pioneers sparse promptable learning and local preference alignment. The Prefer-DAS is a promptable multitask model that integrates self-training and prompt-guided contrastive learning. Unlike SAM-like methods, the Prefer-DAS allows for the use of full, partial, and even no point prompts during both training and inference stages and thus enables interactive segmentation. Instead of using image-level human preference alignment for segmentation, we introduce Local direct Preference Optimization (LPO), plug-and-play solutions for alignment with spatially varying human feedback. To address potential missing feedback, we also introduce Unsupervised Preference Optimization (UPO), which leverages self-learned preferences. As a result, the Prefer-DAS model can effectively perform both weakly-supervised and unsupervised DAS, depending on the availability of points and human preferences. Comprehensive experiments on four challenging DAS tasks demonstrate that our model outperforms SAM-like methods as well as unsupervised and weakly-supervised DAS methods in both automatic and interactive segmentation modes, highlighting strong generalizability and flexibility. Additionally, the performance of our model is very close to or even exceeds that of supervised models.

cs.CV↗

arXiv2026

Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy

Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can help mitigate domain shifts and reduce the high costs of annotating each domain, they typically have relatively low performance in practical applications. Thus, we investigate weakly supervised domain adaptation (WDA) that utilizes additional sparse point labels on the target domain, which require minimal annotation effort and minimal expert knowledge. To take full use of the incomplete and imprecise point annotations, we introduce a multitask learning framework that jointly conducts segmentation and center detection with a novel cross-teaching mechanism and class-focused cross-domain contrastive learning. While leveraging unlabeled image regions is essential, we introduce segmentation self-training with a novel instance-aware pseudo-label (IPL) selection strategy. Unlike existing methods that typically rely on pixel-wise pseudo-label filtering, the IPL semantically selects reliable and diverse pseudo-labels with the help of the detection task. Comprehensive validations and comparisons on challenging datasets demonstrate that our method outperforms existing UDA and WDA methods, significantly narrowing the performance gap with the supervised upper bound. Furthermore, under the UDA setting, our method also achieves substantial improvements over other UDA techniques.

cs.CV↗

arXiv2025

Prompt-DAS: Annotation-Efficient Prompt Learning for Domain Adaptive Semantic Segmentation of Electron Microscopy Images

Domain adaptive segmentation (DAS) of numerous organelle instances from large-scale electron microscopy (EM) is a promising way to enable annotation-efficient learning. Inspired by SAM, we propose a promptable multitask framework, namely Prompt-DAS, which is flexible enough to utilize any number of point prompts during the adaptation training stage and testing stage. Thus, with varying prompt configurations, Prompt-DAS can perform unsupervised domain adaptation (UDA) and weakly supervised domain adaptation (WDA), as well as interactive segmentation during testing. Unlike the foundation model SAM, which necessitates a prompt for each individual object instance, Prompt-DAS is only trained on a small dataset and can utilize full points on all instances, sparse points on partial instances, or even no points at all, facilitated by the incorporation of an auxiliary center-point detection task. Moreover, a novel prompt-guided contrastive learning is proposed to enhance discriminative feature learning. Comprehensive experiments conducted on challenging benchmarks demonstrate the effectiveness of the proposed approach over existing UDA, WDA, and SAM-based approaches.

cs.CV↗

arXiv2023

Zero-Shot Enhancement of Low-Light Image Based on Retinex Decomposition

Two difficulties here make low-light image enhancement a challenging task; firstly, it needs to consider not only luminance restoration but also image contrast, image denoising and color distortion issues simultaneously. Second, the effectiveness of existing low-light enhancement methods depends on paired or unpaired training data with poor generalization performance. To solve these difficult problems, we propose in this paper a new learning-based Retinex decomposition of zero-shot low-light enhancement method, called ZERRINNet. To this end, we first designed the N-Net network, together with the noise loss term, to be used for denoising the original low-light image by estimating the noise of the low-light image. Moreover, RI-Net is used to estimate the reflection component and illumination component, and in order to solve the color distortion and contrast, we use the texture loss term and segmented smoothing loss to constrain the reflection component and illumination component. Finally, our method is a zero-reference enhancement method that is not affected by the training data of paired and unpaired datasets, so our generalization performance is greatly improved, and in the paper, we have effectively validated it with a homemade real-life low-light dataset and additionally with advanced vision tasks, such as face detection, target recognition, and instance segmentation. We conducted comparative experiments on a large number of public datasets and the results show that the performance of our method is competitive compared to the current state-of-the-art methods. The code is available at:https://github.com/liwenchao0615/ZERRINNet

cs.CV↗

arXiv2023

Blueprint for quantum computing using electrons on helium

We present a blueprint for building a fault-tolerant quantum computer using the spin states of electrons on the surface of liquid helium. We propose to use ferromagnetic micropillars to trap single electrons on top of them and to generate a local magnetic field gradient. Introducing a local magnetic field gradient hybridizes charge and spin degrees of freedom, which allows us to benefit from both the long coherence time of the spin state and the long-range Coulomb interaction that affects the charge state. We present concrete schemes to realize single- and two-qubit gates and quantum-non-demolition read-out. In our framework, the hybridization of charge and spin degrees of freedom is large enough to perform fast qubit gates and small enough not to degrade the coherence time of the spin state significantly, which leads to the realization of high-fidelity qubit gates.

cond-mat.mes-hall↗

arXiv2023

Analytical formulation of the second-order derivative of energy for orbital-optimized variational quantum eigensolver: application to polarizability

We develop a quantum-classical hybrid algorithm to calculate the analytical second-order derivative of the energy for the orbital-optimized variational quantum eigensolver (OO-VQE), which is a method to calculate eigenenergies of a given molecular Hamiltonian by utilizing near-term quantum computers and classical computers. We show that all quantities required in the algorithm to calculate the derivative can be evaluated on quantum computers as standard quantum expectation values without using any ancillary qubits. We validate our formula by numerical simulations of quantum circuits for computing the polarizability of the water molecule, which is the second-order derivative of the energy with respect to the electric field. Moreover, the polarizabilities and refractive indices of thiophene and furan molecules are calculated as a testbed for possible industrial applications. We finally analyze the error-scaling of the estimated polarizabilities obtained by the proposed analytical derivative versus the numerical one obtained by the finite difference. Numerical calculations suggest that our analytical derivative requires fewer measurements (runs) on quantum computers than the numerical derivative to achieve the same fixed accuracy.

physics.chem-ph↗

arXiv2021

Qulacs: a fast and versatile quantum circuit simulator for research purpose

To explore the possibilities of a near-term intermediate-scale quantum algorithm and long-term fault-tolerant quantum computing, a fast and versatile quantum circuit simulator is needed. Here, we introduce Qulacs, a fast simulator for quantum circuits intended for research purpose. We show the main concepts of Qulacs, explain how to use its features via examples, describe numerical techniques to speed-up simulation, and demonstrate its performance with numerical benchmarks.

quant-ph↗

arXiv2018

Adiabatic preparation of squeezed states of oscillators and large spin systems coupled to a two-level system

We study a single two-level system coupled resonantly to an oscillator mode or a large spin. By adiabatically turning on a linear driving term on the oscillator or the spin, the eigenstates of the system change character and its ground state evolves into squeezed states of the oscillator or the spin. The robust generation of such states is of interest in many experimental systems with applications for sensing and quantum information processing.

quant-ph↗

arXiv2018

Strong coupling of two-dimensional electron ensemble to a single-mode cavity resonator

We investigate the regime of strong coupling of an ensemble of two-dimensional electrons to a single-mode cavity resonator. In particular, we realized such a regime of light-matter interaction by coupling the cyclotron motion of a collection of electrons on the surface of liquid helium to the microwave field in a semi-confocal Fabry-Perot resonator. For the co-rotating component of the microwave field, the strong coupling is pronouncedly manifested by the normal-mode splitting in the spectrum of coupled field-particle motion. We present a complete description of this phenomenon based on classical electrodynamics, as well as show that the full quantum treatment of this problem results in mean-value equations of motion that are equivalent to our classical result. For the counter-rotating component of the microwave field, we observe a strong resonance when the microwave frequency is close to both the cyclotron and cavity frequencies. We show that this surprising effect, which is not expected to occur under the rotating-wave approximation, results from the mixing between two polarization components of the microwave field in our cavity.

cond-mat.mes-hall↗