arXiv subjects

Zhen Liu

Publications and source records attributed to Zhen Liu.

At least 109 records · Page 6Linked to original sources

arXiv2025

Orbital chiral lasing in twisted bilayer metasurfaces

Chirality is a fundamental concept in physics that underpins various phenomena in nonlinear optics, quantum physics, and topological photonics. Although the spin of a photon naturally brings chirality, orbital angular momentum can also become chirally active in the structures with a broken mirror symmetry. Here, we observe orbital chiral lasing from a twisted bilayer photonic structure leveraging its inherent structural chirality. Specifically, we design and fabricate a Moire-type optical structure by bonding and rotating two separate semiconductor membrane metasurfaces. We achieve single-mode lasing over a broad spectral range of 250 nm by optically pumping the twisted structure. The lasing emission exhibits orbital chiral characteristics, arising from helical and non-Hermitian couplings between clockwise and counter-clockwise rotating collective guided resonances, confirmed by polarization-resolved imaging and self-interference patterns. Our results provide the first observation of orbital chiral lasing in twisted photonics, and they can contribute to diverse applications of chiral light in diagnostics, optical manipulation, and communication with light.

physics.optics↗

arXiv2025

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards

Generating high-quality and photorealistic 3D assets remains a longstanding challenge in 3D vision and computer graphics. Although state-of-the-art generative models, such as diffusion models, have made significant progress in 3D generation, they often fall short of human-designed content due to limited ability to follow instructions, align with human preferences, or produce realistic textures, geometries, and physical attributes. In this paper, we introduce Nabla-R2D3, a highly effective and sample-efficient reinforcement learning alignment framework for 3D-native diffusion models using 2D rewards. Built upon the recently proposed Nabla-GFlowNet method, which matches the score function to reward gradients in a principled manner for reward finetuning, our Nabla-R2D3 enables effective adaptation of 3D diffusion models using only 2D reward signals. Extensive experiments show that, unlike vanilla finetuning baselines which either struggle to converge or suffer from reward hacking, Nabla-R2D3 consistently achieves higher rewards and reduced prior forgetting within a few finetuning steps.

cs.GR↗

arXiv2025

Neutrino type identification for atmospheric neutrinos in a large homogeneous liquid scintillation detector

Atmospheric neutrino oscillations are important to the study of neutrino properties, including the neutrino mass ordering problem. A good capability to identify neutrinos' flavor and neutrinos against antineutrinos is crucial in such measurements. In this paper, we present a machine-learning-based approach for identifying atmospheric neutrino events in a large homogeneous liquid scintillator detector. This method identifies features of PMT waveforms that reflect event topologies and uses them as input to machine learning models. In addition, neutron-capture information is utilized to achieve neutrino versus antineutrino discrimination. Preliminary performances based on Monte Carlo simulations are presented, which demonstrate such a detector's potential in future measurements of atmospheric neutrinos such as the one planned for the JUNO experiment.

hep-ex↗

arXiv2025

Learning Soft Sparse Shapes for Efficient Time-Series Classification

Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing shapelet-based methods mainly focus on selecting discriminative shapes while discarding others to achieve candidate subsequence sparsification. However, this approach may exclude beneficial shapes and overlook the varying contributions of shapelets to classification performance. To this end, we propose a Soft sparse Shapes (SoftShape) model for efficient time series classification. Our approach mainly introduces soft shape sparsification and soft shape learning blocks. The former transforms shapes into soft representations based on classification contribution scores, merging lower-scored ones into a single shape to retain and differentiate all subsequence information. The latter facilitates intra- and inter-shape temporal pattern learning, improving model efficiency by using sparsified soft shapes as inputs. Specifically, we employ a learnable router to activate a subset of class-specific expert networks for intra-shape pattern learning. Meanwhile, a shared expert network learns inter-shape patterns by converting sparsified shapes into sequences. Extensive experiments show that SoftShape outperforms state-of-the-art methods and produces interpretable results.

cs.LG↗

arXiv2025

Large Language Models Can Achieve Explainable and Training-Free One-shot HRRP ATR

This letter introduces a pioneering, training-free and explainable framework for High-Resolution Range Profile (HRRP) automatic target recognition (ATR) utilizing large-scale pre-trained Large Language Models (LLMs). Diverging from conventional methods requiring extensive task-specific training or fine-tuning, our approach converts one-dimensional HRRP signals into textual scattering center representations. Prompts are designed to align LLMs' semantic space for ATR via few-shot in-context learning, effectively leveraging its vast pre-existing knowledge without any parameter update. We make our codes publicly available to foster research into LLMs for HRRP ATR.

eess.SP↗

arXiv2025

On-shell recursion relations for higher-spin Compton amplitudes

We recursively construct tree-level electromagnetic and gravitational Compton amplitudes of higher-spin massive particles by the all-line transverse momentum shift. With three-point amplitude as input, we demonstrate that higher-point electromagnetic and gravitational Compton amplitudes are on-shell constructible up to spin $s = 3/2$ and $s = 5/2$, respectively, under the all-line transverse shift after imposing the current constraint condition. We unambiguously derive the four-point electromagnetic and gravitational Compton amplitudes for $s \leq 3/2$ and $s \leq 5/2$, which are uniquely determined by the on-shell recursion relation and are free from unphysical spurious poles. In addition, we explore amplitudes of spin-$3/2$ particles with non-minimal three-point interactions with photon, as well as $s > 3/2$ particles, and comment on their notable features. Our work furthers the understanding of on-shell methods for massive amplitudes, with hopes to shed light on physical observables in particle physics and higher-spin amplitudes relevant for Kerr black-hole scattering.

hep-th↗

arXiv2025

FOCUS: Boosting Schema-aware Access for KV Stores via Hierarchical Data Management

Persistent key-value (KV) stores are critical infrastructure for data-intensive applications. Leveraging high-performance Non-Volatile Memory (NVM) to enhance KV stores has gained traction. However, previous work has primarily focused on optimizing KV stores themselves, without adequately addressing their integration into applications. Consequently, existing applications, represented by NewSQL databases, still resort to a flat mapping approach, which simply maps structured records into flat KV pairs to use KV stores. Such semantic mismatch may cause significant I/O amplification and I/O splitting under production workloads, harming the performance. To this end, we propose FOCUS, a log-structured KV store optimized for fine-grained hierarchical data organization and schema-aware access. FOCUS introduces a hierarchical KV model to provide native support for upper-layer structured data. We implemented FOCUS from scratch. Experiments show that FOCUS can increase throughput by 2.1-5.9x compared to mainstream NVM-backed KV stores under YCSB SQL workloads.

cs.DB↗

arXiv2025

Can Large Language Models Understand Symbolic Graphics Programs?

Against the backdrop of enthusiasm for large language models (LLMs), there is a growing need to scientifically assess their capabilities and shortcomings. This is nontrivial in part because it is difficult to find tasks which the models have not encountered during training. Utilizing symbolic graphics programs, we propose a domain well-suited to test multiple spatial-semantic reasoning skills of LLMs. Popular in computer graphics, these programs procedurally generate visual data. While LLMs exhibit impressive skills in general program synthesis and analysis, symbolic graphics programs offer a new layer of evaluation: they allow us to test an LLM's ability to answer semantic questions about the images or 3D geometries without a vision encoder. To semantically understand the symbolic programs, LLMs would need to possess the ability to "imagine" and reason how the corresponding graphics content would look with only the symbolic description of the local curvatures and strokes. We use this task to evaluate LLMs by creating a large benchmark for the semantic visual understanding of symbolic graphics programs, built procedurally with minimal human effort. Particular emphasis is placed on transformations of images that leave the image level semantics invariant while introducing significant changes to the underlying program. We evaluate commercial and open-source LLMs on our benchmark to assess their ability to reason about visual output of programs, finding that LLMs considered stronger at reasoning generally perform better. Lastly, we introduce a novel method to improve this ability -- Symbolic Instruction Tuning (SIT), in which the LLM is finetuned with pre-collected instruction data on symbolic graphics programs. Interestingly, we find that SIT not only improves LLM's understanding on symbolic programs, but it also improves general reasoning ability on various other benchmarks.

cs.LG↗

arXiv2025

HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecasting

Irregular multivariate time series (IMTS) are characterized by irregular time intervals within variables and unaligned observations across variables, posing challenges in learning temporal and variable dependencies. Many existing IMTS models either require padded samples to learn separately from temporal and variable dimensions, or represent original samples via bipartite graphs or sets. However, the former approaches often need to handle extra padding values affecting efficiency and disrupting original sampling patterns, while the latter ones have limitations in capturing dependencies among unaligned observations. To represent and learn both dependencies from original observations in a unified form, we propose HyperIMTS, a Hypergraph neural network for Irregular Multivariate Time Series forecasting. Observed values are converted as nodes in the hypergraph, interconnected by temporal and variable hyperedges to enable message passing among all observations. Through irregularity-aware message passing, HyperIMTS captures variable dependencies in a time-adaptive way to achieve accurate forecasting. Experiments demonstrate HyperIMTS's competitive performance among state-of-the-art models in IMTS forecasting with low computational cost.

cs.LG↗

arXiv2025

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets

While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some reward functions that are either designed by experts or learned from small-scale datasets. Existing post-training methods for reward finetuning of diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. In response to this challenge, we take inspiration from recent successes in generative flow networks (GFlowNets) and propose a reinforcement learning method for diffusion model finetuning, dubbed Nabla-GFlowNet (abbreviated as $\nabla$-GFlowNet), that leverages the rich signal in reward gradients for probabilistic diffusion finetuning. We show that our proposed method achieves fast yet diversity- and prior-preserving finetuning of Stable Diffusion, a large-scale text-conditioned image diffusion model, on different realistic reward functions.

cs.LG↗

arXiv2025

Equating three degrees of graphs

In this paper, we prove that, for every graph with at least 5 vertices, one can delete at most 3 vertices such that the subgraph obtained has at least three vertices with the same degree. This solves an open problem of Caro, Shapira and Yuster [Electron. J. Combin. 21 (2014) P1.24].

math.CO↗

arXiv2025

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in real-world scenarios or lack interactive editing capabilities, ChatGarment can estimate sewing patterns from in-the-wild images or sketches, generate them from text descriptions, and edit garments based on user instructions, all within an interactive dialogue. These sewing patterns can then be draped on a 3D body and animated. This is achieved by finetuning a VLM to directly generate a JSON file that includes both textual descriptions of garment types and styles, as well as continuous numerical attributes. This JSON file is then used to create sewing patterns through a programming parametric model. To support this, we refine the existing programming model, GarmentCode, by expanding its garment type coverage and simplifying its structure for efficient VLM fine-tuning. Additionally, we construct a large-scale dataset of image-to-sewing-pattern and text-to-sewing-pattern pairs through an automated data pipeline. Extensive evaluations demonstrate ChatGarment's ability to accurately reconstruct, generate, and edit garments from multimodal inputs, highlighting its potential to simplify workflows in fashion and gaming applications. Code and data are available at https://chatgarment.github.io/ .

cs.CV↗

arXiv2025

MATHUSLA: An External Long-Lived Particle Detector to Maximize the Discovery Potential of the HL-LHC

We present the current status of the MATHUSLA (MAssive Timing Hodoscope for Ultra-Stable neutraL pArticles) long-lived particle (LLP) detector at the HL-LHC, covering the design, fabrication and installation at CERN Point 5. MATHUSLA40 is a 40 m-scale detector with an air-filled decay volume that is instrumented with scintillator tracking detectors, to be located near CMS. Its large size, close proximity to the CMS interaction point and about 100 m of rock shielding from LHC backgrounds allows it to detect LLP production rates and lifetimes that are one to two orders of magnitude beyond the ultimate reach of the LHC main detectors. This provides unique sensitivity to many LLP signals that are highly theoretically motivated, due to their connection to the hierarchy problem, the nature of dark matter, and baryogenesis. Data taking is projected to commence with the start of HL-LHC operations. We summarize the new 40m design for the detector that was recently presented in the MATHUSLA Conceptual Design Report, alongside new realistic background and signal simulations that demonstrate high efficiency for the main target LLP signals in a background-free HL-LHC search. We argue that MATHUSLA's uniquely robust expansion of the HL-LHC physics reach is a crucial ingredient in CERN's mission to search for new physics and characterize the Higgs boson with precision.

physics.ins-det↗

arXiv2025

Conceptual Design Report for the MATHUSLA Long-Lived Particle Detector near CMS

We present the Conceptual Design Report (CDR) for the MATHUSLA (MAssive Timing Hodoscope for Ultra-Stable neutraL pArticles) long-lived particle detector at the HL-LHC, covering the design, fabrication and installation at CERN Point 5. MATHUSLA is a 40 m-scale detector with an air-filled decay volume that is instrumented with scintillator tracking detectors, to be located near CMS. Its large size, close proximity to the CMS interaction point and about 100 m of rock shielding from HL-LHC backgrounds allows it to detect LLP production rates and lifetimes that are one to two orders of magnitude beyond the ultimate sensitivity of the HL-LHC main detectors for many highly motivated LLP signals. Data taking is projected to commence with the start of HL-LHC operations. We present a new 40m design for the detector: its individual scintillator bars and wavelength-shifting fibers, their organization into tracking layers, tracking modules, tower modules and the veto detector; define a high-level design for the supporting electronics, DAQ and trigger system, including supplying a hardware trigger signal to CMS to record the LLP production event; outline computing systems, civil engineering and safety considerations; and present preliminary cost estimates and timelines for the project. We also conduct detailed simulation studies of the important cosmic ray and HL-LHC muon backgrounds, implementing full track/vertex reconstruction and background rejection, to ultimately demonstrate high signal efficiency and $\ll 1$ background event in realistic LLP searches for the main physics targets at MATHUSLA. This sensitivity is robust with respect to detector design or background simulation details. Appendices provide various supplemental information.

physics.ins-det↗

arXiv2025

A Causal Adjustment Module for Debiasing Scene Graph Generation

While recent debiasing methods for Scene Graph Generation (SGG) have shown impressive performance, these efforts often attribute model bias solely to the long-tail distribution of relationships, overlooking the more profound causes stemming from skewed object and object pair distributions. In this paper, we employ causal inference techniques to model the causality among these observed skewed distributions. Our insight lies in the ability of causal inference to capture the unobservable causal effects between complex distributions, which is crucial for tracing the roots of model bias. Specifically, we introduce the Mediator-based Causal Chain Model (MCCM), which, in addition to modeling causality among objects, object pairs, and relationships, incorporates mediator variables, i.e., cooccurrence distribution, for complementing the causality. Following this, we propose the Causal Adjustment Module (CAModule) to estimate the modeled causal structure, using variables from MCCM as inputs to produce a set of adjustment factors aimed at correcting biased model predictions. Moreover, our method enables the composition of zero-shot relationships, thereby enhancing the model's ability to recognize such relationships. Experiments conducted across various SGG backbones and popular benchmarks demonstrate that CAModule achieves state-of-the-art mean recall rates, with significant improvements also observed on the challenging zero-shot recall rate metric.

cs.CV↗

arXiv2025

Probing Millicharged Particles at an Electron Beam Dump with Ultralow-Threshold Sensors

We propose to search for millicharged particles produced in high-intensity electron beam dumps using small ultralow-threshold sensors. As a concrete example, we consider a Skipper-CCD placed behind the beam dump in Hall A at Jefferson Lab. We compute the millicharged particle flux, including both electromagnetic cascade and meson productions emanating from an aluminum target. We find that the sensitivity of a modest 2x14 array of Skipper-CCDs can exceed the sensitivity of all existing searches for millicharged particle masses below 1.5 GeV, and is either competitive or world leading when compared to other proposed experiments. Our results demonstrate that small-scale ultralow threshold silicon devices can enhance the reach of accelerator-based experiments, while fitting comfortably within existing experimental halls.

hep-ph↗

arXiv2025

ChartInsighter: An Approach for Mitigating Hallucination in Time-series Chart Summary Generation with A Benchmark Dataset

Effective chart summary can significantly reduce the time and effort decision makers spend interpreting charts, enabling precise and efficient communication of data insights. Previous studies have faced challenges in generating accurate and semantically rich summaries of time-series data charts. In this paper, we identify summary elements and common hallucination types in the generation of time-series chart summaries, which serve as our guidelines for automatic generation. We introduce ChartInsighter, which automatically generates chart summaries of time-series data, effectively reducing hallucinations in chart summary generation. Specifically, we assign multiple agents to generate the initial chart summary and collaborate iteratively, during which they invoke external data analysis modules to extract insights and compile them into a coherent summary. Additionally, we implement a self-consistency test method to validate and correct our summary. We create a high-quality benchmark of charts and summaries, with hallucination types annotated on a sentence-by-sentence basis, facilitating the evaluation of the effectiveness of reducing hallucinations. Our evaluations using our benchmark show that our method surpasses state-of-the-art models, and that our summary hallucination rate is the lowest, which effectively reduces various hallucinations and improves summary quality. The benchmark is available at https://github.com/wangfen01/ChartInsighter.

cs.CL↗

arXiv2025

Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation

Bias in Foundation Models (FMs) - trained on vast datasets spanning societal and historical knowledge - poses significant challenges for fairness and equity across fields such as healthcare, education, and finance. These biases, rooted in the overrepresentation of stereotypes and societal inequalities in training data, exacerbate real-world discrimination, reinforce harmful stereotypes, and erode trust in AI systems. To address this, we introduce Trident Probe Testing (TriProTesting), a systematic testing method that detects explicit and implicit biases using semantically designed probes. Here we show that FMs, including CLIP, ALIGN, BridgeTower, and OWLv2, demonstrate pervasive biases across single and mixed social attributes (gender, race, age, and occupation). Notably, we uncover mixed biases when social attributes are combined, such as gender x race, gender x age, and gender x occupation, revealing deeper layers of discrimination. We further propose Adaptive Logit Adjustment (AdaLogAdjustment), a post-processing technique that dynamically redistributes probability power to mitigate these biases effectively, achieving significant improvements in fairness without retraining models. These findings highlight the urgent need for ethical AI practices and interdisciplinary solutions to address biases not only at the model level but also in societal structures. Our work provides a scalable and interpretable solution that advances fairness in AI systems while offering practical insights for future research on fair AI technologies.

cs.LG↗