arXiv subjects

Zhou Chen

Publications and source records attributed to Zhou Chen.

At least 19 recordsLinked to original sources

arXiv2026

Physics-Aligned Deep Learning Enables SERS Resolving and Sequencing of Dynamic Single-Molecule DNA Oligomers in Plasmonic Nanocavity

Single-molecule surface-enhanced Raman spectroscopy (SM-SERS) captures dynamic molecular behavior with ultrahigh sensitivity, but its biopolymer analysis is hindered by strong spectral heterogeneity, transient hotspot sampling, and background interference. Here, we develop a physics-aligned deep learning framework integrating contrastive attention-based multiple-instance learning (CAMIL), a tri-channel multi-kernel CNN classifier, and trajectory-level transition-guided sequence reconstruction to decode single-molecule DNA oligomer dynamics in a plasmonic nanocavity. In this work, CAMIL mines informative spectra enriched with chain-embedded nucleotide and dinucleotide signatures from contrastive positive and negative DNA trajectory bags, generating a single-molecule DNA-segment spectral-states library. This library trains a 12-class CNN to assign query time-resolved DNA SM-SERS frames to high-confidence DNA-segment states, enabling trajectory-level analysis of state composition, dwell length, entropy, switching frequency, and transition matrix. The transition matrix is further converted into state-transition-edge evidence for candidate sequence scoring, enabling asymmetric DNA sequences inference from confined stochastic sampling dynamics. This framework transforms SM-SERS heterogeneity into quantitative analytical information, advancing dynamic single-molecule decoding.

physics.optics↗

arXiv2026

FUSE: Active Functional Affordance Grounding through Adaptive Semantic-Geometric Evidence Acquisition

Embodied agents must often identify and interact with objects based on their function rather than their identity, requiring them to actively acquire observations that reveal discriminative functional evidence. Existing affordance grounding methods operate from fixed viewpoints and lack mechanisms for deciding where to look when functional cues are occluded or incomplete. We introduce Active Functional Affordance Grounding, a new task in which an agent sequentially explores a scene to identify and spatially ground an object satisfying a functional query. To address this problem, we propose FUSE, an adaptive semantic-geometric evidence acquisition framework that combines explicit uncertainty-driven exploration with a learned amortized planner to efficiently select informative viewpoints. We further introduce a Habitat-based benchmark for evaluating active functional grounding. Experiments show that FUSE achieves the highest observed non-oracle grounding performance while reducing computation by 1.33x relative to fully explicit exploration, and remains effective across multiple affordance knowledge sources.

cs.RO↗

arXiv2026

Class Geometry as Supervision for Sample-Efficient Open-World Detection

Open-world object detection requires models to recognize known categories, reject unfamiliar objects, and incorporate new classes over time. This is especially challenging in scarce-data settings such as biomedical and scientific imaging, where rare categories may have only a few annotated examples and fine-grained classes differ by subtle morphology. Prototype-based detectors are natural for this regime, but they typically learn class prototypes as independent anchors, ignoring relational structure among classes. We propose class-geometry supervision (CGS), a general framework that constrains learned prototype or class-representation spaces to preserve visual or semantic class dissimilarities estimated from training data. CGS introduces a dissimilarity-preserving objective that aligns pairwise distances among learned class representations with a target class-geometry matrix while retaining the standard task loss. We instantiate the same objective across prototype recognition, few-shot biomedical object detection, open-set detection, novel-class insertion, and OWOD adaptation on COCO. Experiments show that CGS improves sample efficiency in recognition and ova detection, substantially strengthens novel-class insertion, and improves unknown recall on COCO while retaining much of the known-class detection performance. Ablations show that meaningful visual geometry provides the most reliable gains, while random geometry can help novel separation but is less consistent for few-shot detection. These results suggest that relational class geometry is an effective supervisory signal for building calibrated and extensible open-world detectors under limited supervision.

cs.CV↗

arXiv2025

Generalized Event Partonomy Inference with Structured Hierarchical Predictive Learning

Humans naturally perceive continuous experience as a hierarchy of temporally nested events, fine-grained actions embedded within coarser routines. Replicating this structure in computer vision requires models that can segment video not just retrospectively, but predictively and hierarchically. We introduce PARSE, a unified framework that learns multiscale event structure directly from streaming video without supervision. PARSE organizes perception into a hierarchy of recurrent predictors, each operating at its own temporal granularity: lower layers model short-term dynamics while higher layers integrate longer-term context through attention-based feedback. Event boundaries emerge naturally as transient peaks in prediction error, yielding temporally coherent, nested partonomies that mirror the containment relations observed in human event perception. Evaluated across three benchmarks, Breakfast Actions, 50 Salads, and Assembly 101, PARSE achieves state-of-the-art performance among streaming methods and rivals offline baselines in both temporal alignment (H-GEBD) and structural consistency (TED, hF1). The results demonstrate that predictive learning under uncertainty provides a scalable path toward human-like temporal abstraction and compositional event understanding.

cs.CV↗

arXiv2025

CRAFT-E: A Neuro-Symbolic Framework for Embodied Affordance Grounding

Assistive robots operating in unstructured environments must understand not only what objects are, but what they can be used for. This requires grounding language-based action queries to objects that both afford the requested function and can be physically retrieved. Existing approaches often rely on black-box models or fixed affordance labels, limiting transparency, controllability, and reliability for human-facing applications. We introduce CRAFT-E, a modular neuro-symbolic framework that composes a structured verb-property-object knowledge graph with visual-language alignment and energy-based grasp reasoning. The system generates interpretable grounding paths that expose the factors influencing object selection and incorporates grasp feasibility as an integral part of affordance inference. We further construct a benchmark dataset with unified annotations for verb-object compatibility, segmentation, and grasp candidates, and deploy the full pipeline on a physical robot. CRAFT-E achieves competitive performance in static scenes, ImageNet-based functional retrieval, and real-world trials involving 20 verbs and 39 objects. The framework remains robust under perceptual noise and provides transparent, component-level diagnostics. By coupling symbolic reasoning with embodied perception, CRAFT-E offers an interpretable and customizable alternative to end-to-end models for affordance-grounded object selection, supporting trustworthy decision-making in assistive robotic systems.

cs.RO↗

arXiv2025

SACO: Sequence-Aware Constrained Optimization Framework for Coupon Distribution in E-commerce

Coupon distribution is a critical marketing strategy used by online platforms to boost revenue and enhance user engagement. Regrettably, existing coupon distribution strategies fall far short of effectively leveraging the complex sequential interactions between platforms and users. This critical oversight, despite the abundance of e-commerce log data, has precipitated a performance plateau. In this paper, we focus on the scene that the platforms make sequential coupon distribution decision multiple times for various users, with each user interacting with the platform repeatedly. Based on this scenario, we propose a novel marketing framework, named \textbf{S}equence-\textbf{A}ware \textbf{C}onstrained \textbf{O}ptimization (SACO) framework, to directly devise coupon distribution policy for long-term revenue boosting. SACO framework enables optimized online decision-making in a variety of real-world marketing scenarios. It achieves this by seamlessly integrating three key characteristics, general scenarios, sequential modeling with more comprehensive historical data, and efficient iterative updates within a unified framework. Furthermore, empirical results on real-world industrial dataset, alongside public and synthetic datasets demonstrate the superiority of our framework.

cs.LG↗

arXiv2025

CRAFT: A Neuro-Symbolic Framework for Visual Functional Affordance Grounding

We introduce CRAFT, a neuro-symbolic framework for interpretable affordance grounding, which identifies the objects in a scene that enable a given action (e.g., "cut"). CRAFT integrates structured commonsense priors from ConceptNet and language models with visual evidence from CLIP, using an energy-based reasoning loop to refine predictions iteratively. This process yields transparent, goal-driven decisions to ground symbolic and perceptual structures. Experiments in multi-object, label-free settings demonstrate that CRAFT enhances accuracy while improving interpretability, providing a step toward robust and trustworthy scene understanding.

cs.CV↗

arXiv2025

EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization

Active event perception, the ability to dynamically detect, track, and summarize events in real time, is essential for embodied intelligence in tasks such as human-AI collaboration, assistive robotics, and autonomous navigation. However, existing approaches often depend on predefined action spaces, annotated datasets, and extrinsic rewards, limiting their adaptability and scalability in dynamic, real-world scenarios. Inspired by cognitive theories of event perception and predictive coding, we propose EASE, a self-supervised framework that unifies spatiotemporal representation learning and embodied control through free energy minimization. EASE leverages prediction errors and entropy as intrinsic signals to segment events, summarize observations, and actively track salient actors, operating without explicit annotations or external rewards. By coupling a generative perception model with an action-driven control policy, EASE dynamically aligns predictions with observations, enabling emergent behaviors such as implicit memory, target continuity, and adaptability to novel environments. Extensive evaluations in simulation and real-world settings demonstrate EASE's ability to achieve privacy-preserving and scalable event perception, providing a robust foundation for embodied systems in unscripted, dynamic tasks.

cs.RO↗

arXiv2025

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable "super model."

cs.CL↗

arXiv2025

ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries

As the issue of global climate change becomes increasingly severe, the demand for research in climate science continues to grow. Natural language processing technologies, represented by Large Language Models (LLMs), have been widely applied to climate change-specific research, providing essential information support for decision-makers and the public. Some studies have improved model performance on relevant tasks by constructing climate change-related instruction data and instruction-tuning LLMs. However, current research remains inadequate in efficiently producing large volumes of high-precision instruction data for climate change, which limits further development of climate change LLMs. This study introduces an automated method for constructing instruction data. The method generates instructions using facts and background knowledge from documents and enhances the diversity of the instruction data through web scraping and the collection of seed instructions. Using this method, we constructed a climate change instruction dataset, named ClimateChat-Corpus, which was used to fine-tune open-source LLMs, resulting in an LLM named ClimateChat. Evaluation results show that ClimateChat significantly improves performance on climate change question-and-answer tasks. Additionally, we evaluated the impact of different base models and instruction data on LLM performance and demonstrated its capability to adapt to a wide range of climate change scientific discovery tasks, emphasizing the importance of selecting an appropriate base model for instruction tuning. This research provides valuable references and empirical support for constructing climate change instruction data and training climate change-specific LLMs.

cs.CL↗

arXiv2024

Automating the Training and Deployment of Models in MLOps by Integrating Systems with Machine Learning

This article introduces the importance of machine learning in real-world applications and explores the rise of MLOps (Machine Learning Operations) and its importance for solving challenges such as model deployment and performance monitoring. By reviewing the evolution of MLOps and its relationship to traditional software development methods, the paper proposes ways to integrate the system into machine learning to solve the problems faced by existing MLOps and improve productivity. This paper focuses on the importance of automated model training, and the method to ensure the transparency and repeatability of the training process through version control system. In addition, the challenges of integrating machine learning components into traditional CI/CD pipelines are discussed, and solutions such as versioning environments and containerization are proposed. Finally, the paper emphasizes the importance of continuous monitoring and feedback loops after model deployment to maintain model performance and reliability. Using case studies and best practices from Netflix, the article presents key strategies and lessons learned for successful implementation of MLOps practices, providing valuable references for other organizations to build and optimize their own MLOps practices.

cs.SE↗

arXiv2023

Digital twin-assisted three-dimensional electrical capacitance tomography for multiphase flow imaging

Three-dimensional electrical capacitance tomography (3D-ECT) has shown promise for visualizing industrial multiphase flows. However, existing 3D-ECT approaches suffer from limited imaging resolution and lack assessment metrics, hampering their effectiveness in quantitative multiphase flow imaging. This paper presents a digital twin (DT)-assisted 3D-ECT, aiming to overcome these limitations and enhance our understanding of multiphase flow dynamics. The DT framework incorporates a 3D fluid-electrostatic field coupling model (3D-FECM) that digitally represents the physical 3D-ECT system, which enables us to simulate real multiphase flows and generate a comprehensive virtual multiphase flow 3D imaging dataset. Additionally, the framework includes a deep neural network named 3D deep back projection (3D-DBP), which learns multiphase flow features from the virtual dataset and enables more accurate 3D flow imaging in the real world. The DT-assisted 3D-ECT was validated through virtual and physical experiments, demonstrating superior image quality, noise robustness and computational efficiency compared to conventional 3D-ECT approaches. This research contributes to developing accurate and reliable 3D-ECT techniques and their implementation in multiphase flow systems across various industries.

eess.IV↗

arXiv2023

Controlling electron motion with attosecond precision by shaped femtosecond intense laser pulse

We propose the scheme of temporal double-slit interferometer to precisely measure the electric field of shaped intense femtosecond laser pulse directly, and apply it to control the electron tunneling wave packets in attosecond precision. By manipulating the spectra phase of the input femtosecond pulse in frequency domain, one single pulse is split into two sub-pulses whose waveform can be precisely controlled by adjusting the spectra phase. When the shaped pulse interacts with atoms, the two sub-pulses are analogous to the Young's double-slit in time domain. The interference pattern in the photoelectron momentum distribution can be used to precisely retrieve the peak electric field and the time delay between two sub-pulses. Based on the precise characterization of the shaped pulse, we demonstrate that the sub-cycle dynamics of electron can be controlled with attosecond precision. The above scheme is proved to be feasible by both quantum-trajectory Monte Carlo simulations and numerical solutions of three-dimensional time-dependent Schrödinger equation.

physics.atom-ph↗

arXiv2023

Complex-valued Holographic Pseudo Entropy via Real-time AdS/CFT Correspondence

The pseudo entropy is a promising recent generalization of the entanglement entropy to the situations in which both the initial and final state are involved, with the density matrix promoted to the transition matrix. However, in contrast to the non-Hermiticity of the generic transition matrix, the holographic pseudo entropy formulated via the Euclidean AdS/CFT turns out to be always real-valued, which potentially conceals the crucial natures of this novel quantity. In this note, we make the first attempt to formulate a real-time prescription for computations to incorporate naturally the pseudo entropy, as a generally complex-valued entanglement measure, into the AdS/CFT context. It is then conjectured that the holographic pseudo entropy is dual to the extremal codimension-2 area surface in the generally time-dependent Lorentzian asymptotically AdS spacetime, but may also receive imaginary contribution from the regularized extrinsic curvature term of the area surface, which is not included in the covariant holographic entanglement entropy. In this real-time prescription, the holographic pseudo entropy can be considered as a generalization of the covariant holographic entanglement entropy, as well.

hep-th↗

arXiv2023

Touch and deformation perception of soft manipulators with capacitive e-skins and deep learning

Tactile sensing in soft robots remains particularly challenging because of the coupling between contact and deformation information which the sensor is subject to during actuation and interaction with the environment. This often results in severe interference and makes disentangling tactile sensing and geometric deformation difficult. To address this problem, this paper proposes a soft capacitive e-skin with a sparse electrode distribution and deep learning for information decoupling. Our approach successfully separates tactile sensing from geometric deformation, enabling touch recognition on a soft pneumatic actuator subject to both internal (actuation) and external (manual handling) forces. Using a multi-layer perceptron, the proposed e-skin achieves 99.88\% accuracy in touch recognition across a range of deformations. When complemented with prior knowledge, a transformer-based architecture effectively tracks the deformation of the soft actuator. The average distance error in positional reconstruction of the manipulator is as low as 2.905$\pm$2.207 mm, even under operative conditions with different inflation states and physical contacts which lead to additional signal variations and consequently interfere with deformation tracking. These findings represent a tangible way forward in the development of e-skins that can endow soft robots with proprioception and exteroception.

cs.RO↗

arXiv2023

Regularized Shallow Image Prior for Electrical Impedance Tomography

Untrained Neural Network Prior (UNNP) based algorithms have gained increasing popularity in tomographic imaging, as they offer superior performance compared to hand-crafted priors and do not require training. UNNP-based methods usually rely on deep architectures which are known for their excellent feature extraction ability compared to shallow ones. Contrary to common UNNP-based approaches, we propose a regularized shallow image prior method that combines UNNP with hand-crafted prior for Electrical Impedance Tomography (EIT). Our approach employs a 3-layer Multi-Layer Perceptron (MLP) as the UNNP in regularizing 2D and 3D EIT inversion. We demonstrate the influence of two typical hand-crafted regularizations when representing the conductivity distribution with shallow MLPs. We show considerably improved EIT image quality compared to conventional regularization algorithms, especially in structure preservation. The results suggest that combining the shallow image prior and the hand-crafted regularization can achieve similar performance to the Deep Image Prior (DIP) but with less architectural dependency and complexity of the neural network.

eess.IV↗

arXiv2022

Graph neural networks to learn joint representations of disjoint molecular graphs

Graph neural networks are widely used to learn global representations of graphs, which are then used for regression or classification tasks. Typically, the graphs in such data sets are connected, i.e. each training sample consists of a single internally connected graph associated with a global label. However, there is a wide variety of yet unconsidered but application-relevant tasks, where labels are assigned to sets of disjoint graphs, which requires the generation of global representations of disjoint graphs. In this paper, we present a new data set with chemical reactions, which is illustrating this task. Each sample consists of a pair of disjoint molecular graphs and a joint label representing a scalar measure associated with the chemical reaction of the molecules. We show the initial results of graph neural networks that are able to solve the task within a combinatorial subset of the dataset but do not generalize well to the full data set and unseen (sub)graphs.

cs.CE↗

arXiv2022

A Learning-Based 3D EIT Image Reconstruction Method

Deep learning has been widely employed to solve the Electrical Impedance Tomography (EIT) image reconstruction problem. Most existing physical model-based and learning-based approaches focus on 2D EIT image reconstruction. However, when they are directly extended to the 3D domain, the reconstruction performance in terms of image quality and noise robustness is hardly guaranteed mainly due to the significant increase in dimensionality. This paper presents a learning-based approach for 3D EIT image reconstruction, which is named Transposed convolution with Neurons Network (TN-Net). Simulation and experimental results show the superior performance and generalization ability of TN-Net compared with prevailing 3D EIT image reconstruction algorithms.

eess.IV↗