arXiv subjects

Yaohang Li

Publications and source records attributed to Yaohang Li.

At least 19 recordsLinked to original sources

arXiv2026

Learning Transverse Momentum Distributions from Raw Scattering Events via Conditional Diffusion

Extracting transverse momentum dependent parton distribution functions (TMD PDFs) from semi-inclusive deep inelastic scattering (SIDIS) data is a central goal of the nucleon structure program at Jefferson Lab and the future Electron-Ion Collider. Traditional extraction methods rely on parameterized functional forms and iterative fitting, which can limit the flexibility of the resulting distributions and make uncertainty quantification cumbersome. We present a conditional diffusion model that learns to map raw SIDIS event kinematics directly to TMD PDFs, bypassing explicit functional assumptions. Evaluated on simulated SIDIS data at CLAS12 kinematics, the model recovers the underlying TMD with informative uncertainties that narrow steadily with increasing event statistics, and produces reliable estimates even with as few as 1,000 conditioning events, a statistics-limited regime directly relevant to ongoing and planned experiments.

hep-ph↗

arXiv2026

Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors

Many scientific and engineering applications require estimating unknown parameters from experimentally observable data -- an inverse problem that is inherently challenging due to nonlinearity, noise, and ill-posedness. In this paper, we propose an active diffusion-based inverse problem solver. A DM is trained to learn the mapping between the parameter space and the observable space. By iteratively detecting and correcting model misspecification through posterior uncertainty, the method discovers and learns the correct region of parameter space, even when initial training bounds exclude the true parameters. This provides a principled, Bayesian justification for adaptive domain augmentation and ensures robust inference for inverse problems under incomplete prior knowledge. We demonstrate the effectiveness of our inverse solver for a toy inverse problem with infinite solutions, and for the parameterization of the quantum correlation functions to event observables in a Quantum Chromodynamics analysis of nucleon structure.

stat.ML↗

arXiv2026

Direct Bayesian Inference of Helicity Amplitudes from Detector-Level Scattering Data

Helicity amplitudes give the most complete description of a variety of scattering reactions used in studies of strong interactions, but they cannot be measured directly: experiments record bilinear combinations of them folded through a detector response, and conventional analyses recover them through multiple stages that introduce discrete ambiguities and require a separate extraction of the absolute cross sections. Here we replace that chain with a single Bayesian inference that determines the experimentally identifiable amplitude parameters directly from detector-level measurements. A score-based diffusion model, trained on a forward simulator, provides the full posterior in each kinematic bin, with the detector response carried by the forward model and positivity of the spin-density matrix guaranteed by the parameterization. The observable amplitude content in electroproduction of final particles grows with polarization of beams and targets, providing additional sensitivity to underlying phases. In simulation, the posterior achieves empirical coverage at or above the nominal level and delivers the angular observables and the separated contributions from longitudinal and transverse photons with their correlations retained. It transfers without retraining to a realistic detector response absent from training and remains reliable in the weakly constrained nucleon-helicity-flip sector, where per-bin likelihood maximization degrades. The result is a general framework for a broad class of inverse problems, phase retrieval, quantum-state tomography, and partial-wave analysis are further instances. Its core requires only a forward simulation of the complete measurement process, instrumental effects are handled within one statistically consistent posterior, applicable across exclusive vector-meson programs at Jefferson Lab, COMPASS, HERMES, and the future Electron-Ion Collider.

nucl-ex↗

arXiv2026

Multi-Dataset Inverse Problem Solving with Distributed Generative AI

Extracting a shared set of unknown, not directly measurable quantities from multiple, heterogeneous datasets is a common challenge across scientific domains. A prominent example is the combination of datasets obtained from different measurements with different settings (e.g. varying detector resolutions). Analyzing such datasets jointly, rather than independently or after naive merging, is essential for obtaining precise and unbiased estimates of the unknowns, but requires careful treatment of dataset heterogeneity and is computationally demanding. We present a generalized framework for simultaneously analyzing multiple heterogeneous datasets in the context of generative AI-based inverse problem solvers. Building on our recent Scalable Asynchronous Generative Inverse Problem Solver (SAGIPS) framework, we extend the well-established distributed data-parallel training paradigm to non-identically distributed datasets, where each dataset is controlled by the same set of unknown inference parameters but covers a different region of the available feature space. Each dataset is processed through its own forward operator and discriminator, providing complementary constraints that collectively guide a shared generator toward global parameter consistency. We validate the approach using a controlled setup inspired by a multi-detector scattering experiment. We provide numerical evidence that our framework is robust to different data fidelities, which arise from unknown detector systematics in the Rutherford experiment, and we show the scaling behavior on multi-GPU leadership computing systems. The results show that our approach is well suited for real-world multi-dataset analyses in which experimental conditions vary across measurements.

cs.DC↗

arXiv2026

PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design

Polymer property prediction and inverse generative design targeting desired properties are two crucial tasks in machine learning-assisted polymer design. While the former has received considerable attention, there have been limited methods developed for the latter. Existing methods focus on single-property optimization in the generative process, whereas accurate prediction of macroscopic material behavior requires simultaneous control of multiple physical properties. In this paper, we provide a transformative framework for direct optimization of a large collection of polymer properties. We propose PolymerGPT, a decoder-based GPT model that incorporates up to 37 commonly used polymer properties into the generative process via learned conditioning prefixes. It also supports a scaffold condition that specifies a desired scaffold for predicted structures. Our experimental results demonstrate that PolymerGPT achieves exceptional performance for unconditional and conditional generation while maintaining high validity, uniqueness, and novelty. Conditioning on five key properties yields generated structures whose predicted values closely match all target properties simultaneously.

cs.AI↗

arXiv2026

Neural Network Representation of Generalized Parton Distributions (NNGPD)

We present a neural-network-based framework for modeling generalized parton distributions, referred to as NNGPD, in which GPDs are represented as flexible functions constrained through physically motivated integral relations. In this approach, experimental and theoretical information is incorporated into the training procedure via loss functions enforcing convolution integrals that define Compton form factors, as well as Mellin moments related to generalized form factors accessible in lattice QCD. This formulation reflects the inverse-problem character of GPD phenomenology without assuming a specific functional ansatz. As a proof of concept, we benchmark the NNGPD framework using a phenomenological spectator-based GPD model, from which synthetic training data for Compton form factors and Mellin moments are generated. The neural network is trained solely on these aggregate observables, and the resulting GPDs are compared directly with the underlying model distributions in a closure-type test. We find that the neural-network representation reproduces the main features of the GPDs over the relevant kinematic domain, despite being constrained only by their integral projections. This study demonstrates the viability of neural-network representations of GPDs constrained by global physical observables and provides a basis for future phenomenological applications combining experimental measurements of deeply virtual Compton scattering, including those anticipated at the Electron Ion Collider, with lattice QCD inputs for Mellin moments and generalized form factors.

hep-ph↗

arXiv2026

Gauge-Equivariant Graph Neural Networks for Lattice Gauge Theories

Local gauge symmetry underlies fundamental interactions and strongly correlated quantum matter, yet existing machine-learning approaches lack a general, principled framework for learning under site-dependent symmetries, particularly for intrinsically nonlocal observables. Here we introduce a gauge-equivariant graph neural network that embeds non-Abelian symmetry directly into message passing via matrix-valued, gauge-covariant features and symmetry-compatible updates, extending equivariant learning from global to fully local symmetries. In this formulation, message passing implements gauge-covariant transport across the lattice, allowing nonlocal correlations and loop-like structures to emerge naturally from local operations. We validate the approach across pure gauge, gauge-matter, and dynamical regimes, establishing gauge-equivariant message passing as a general paradigm for learning in systems governed by local symmetry.

cond-mat.str-el↗

arXiv2025

Enhancing Clinical Note Generation with ICD-10, Clinical Ontology Knowledge Graphs, and Chain-of-Thought Prompting Using GPT-4

In the past decade a surge in the amount of electronic health record (EHR) data in the United States, attributed to a favorable policy environment created by the Health Information Technology for Economic and Clinical Health (HITECH) Act of 2009 and the 21st Century Cures Act of 2016. Clinical notes for patients' assessments, diagnoses, and treatments are captured in these EHRs in free-form text by physicians, who spend a considerable amount of time entering and editing them. Manually writing clinical notes takes a considerable amount of a doctor's valuable time, increasing the patient's waiting time and possibly delaying diagnoses. Large language models (LLMs) possess the ability to generate news articles that closely resemble human-written ones. We investigate the usage of Chain-of-Thought (CoT) prompt engineering to improve the LLM's response in clinical note generation. In our prompts, we use as input International Classification of Diseases (ICD) codes and basic patient information. We investigate a strategy that combines the traditional CoT with semantic search results to improve the quality of generated clinical notes. Additionally, we infuse a knowledge graph (KG) built from clinical ontology to further enrich the domain-specific knowledge of generated clinical notes. We test our prompting technique on six clinical cases from the CodiEsp test dataset using GPT-4 and our results show that it outperformed the clinical notes generated by standard one-shot prompts.

cs.CL↗

arXiv2025

Toward an event-level analysis of hadron structure using differential programming

Reconstructing the internal properties of hadrons in terms of fundamental quark and gluon degrees of freedom is a central goal in nuclear and particle physics. This effort lies at the core of major experimental programs, such as the Jefferson Lab 12 GeV program and the upcoming Electron-Ion Collider. A primary challenge is the inherent inverse problem: converting large-scale observational data from collision events into the fundamental quantum correlation functions (QCFs) that characterize the microscopic structure of hadronic systems within the theory of QCD. Recent advances in scientific computing and machine learning have opened new avenues for addressing this challenge using deep learning techniques. A particularly promising direction is the integration of theoretical calculations and experimental simulations into a unified framework capable of reconstructing QCFs directly from event-level information. In this work, we introduce a differential sampling method called the local orthogonal inverse transform sampling (LOITS) algorithm. We validate its performance through a closure test, demonstrating the accurate reconstruction of a test distribution from sampled events using Generative Adversarial Networks. The LOITS algorithm provides a central building block for addressing inverse problems involving QCFs and enables end-to-end inference pipelines within the framework of differential programming.

hep-ph↗

arXiv2025

Generalized Parton Distributions from Symbolic Regression

AI/ML informed Symbolic Regression is the next stage of scientific modeling. We utilize a highly customizable symbolic regression package ``PySR" to model the $x$ and $t$ dependence of the flavor isovector combination $H_{u-d}(x,t,ξ)$ at $ξ=0$. These PySR models were trained on GPD results provided by both Lattice QCD and phenomenological sources GGL, GK, and VGG. We demonstrate, for the first time, the consistency and systematic convergence of Symbolic Regression by quantifying the disparate models through their Taylor expansion coefficients. In addition to PySR penalizing models with higher complexity and mean-squared error, we implement schemes that test specific physics hypotheses, including force-factorized $x$ and $t$ dependence and Regge behavior in PySR GPDs. We show that PySR can identify factorizing GPD sources based on their response to the Force-Factorized model. Knowing the precise behavior of the GPDs, and their uncertainties in a wide range in $x$ and $t$, crucially impacts our ability to concretely and quantitatively predict hadronic spatial distributions and their derived quantities.

hep-ph↗

arXiv2025

Likelihood and Correlation Analysis of Compton Form Factors for Deeply Virtual Exclusive Scattering on the Nucleon

A likelihood analysis of the observables in deeply virtual exclusive photoproduction off a proton target, $ep \rightarrow e' p' γ'$, is presented. Two processes contribute to the reaction: deeply virtual Compton scattering, where the photon is produced at the proton vertex, and the Bether-Heitler process, where the photon is radiated from the electron. We consider the unpolarized process for which the largest amount of data with all the kinematic dependences are available from corresponding datasets with unpolarized beams and unpolarized targets from Jefferson Lab. We provide and use a method which derives a joint likelihood of the Compton form factors, which parametrize the deeply virtual Compton scattering amplitude in QCD, for each observed combination of the kinematic variables defining the reaction. The unpolarized twist-two cross section likelihood fully constrains only three of the Compton form factors (CFFs). The impact of the twist-three corrections to the analysis is also explored. The derived likelihoods are explored using Markov chain Monte Carlo (MCMC) methods. Using our proposed method we derive CFF error bars and covariances. Additionally, we explore methods which may reduce the magnitude of error bars/contours in the future.

hep-ph↗

arXiv2025

MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot

Large language model agents that interact with PC applications often face limitations due to their singular mode of interaction with real-world environments, leading to restricted versatility and frequent hallucinations. To address this, we propose the Multi-Modal Agent Collaboration framework (MMAC-Copilot), a framework utilizes the collective expertise of diverse agents to enhance interaction ability with application. The framework introduces a team collaboration chain, enabling each participating agent to contribute insights based on their specific domain knowledge, effectively reducing the hallucination associated with knowledge domain gaps. We evaluate MMAC-Copilot using the GAIA benchmark and our newly introduced Visual Interaction Benchmark (VIBench). MMAC-Copilot achieved exceptional performance on GAIA, with an average improvement of 6.8\% over existing leading systems. VIBench focuses on non-API-interactable applications across various domains, including 3D gaming, recreation, and office scenarios. It also demonstrated remarkable capability on VIBench. We hope this work can inspire in this field and provide a more comprehensive assessment of Autonomous agents. The anonymous Github is available at \href{https://anonymous.4open.science/r/ComputerAgentWithVision-3C12}{Anonymous Github}

cs.AI↗

arXiv2025

TopoLa: A Universal Framework to Enhance Cell Representations for Single-cell and Spatial Omics through Topology-encoded Latent Hyperbolic Geometry

Recent advances in cellular research demonstrate that scRNA-seq characterizes cellular heterogeneity, while spatial transcriptomics reveals the spatial distribution of gene expression. Cell representation is the fundamental issue in the two fields. Here, we propose Topology-encoded Latent Hyperbolic Geometry (TopoLa), a computational framework enhancing cell representations by capturing fine-grained intercellular topological relationships. The framework introduces a new metric, TopoLa distance (TLd), which quantifies the geometric distance between cells within latent hyperbolic space, capturing the network's topological structure more effectively. With this framework, the cell representation can be enhanced considerably by performing convolution on its neighboring cells. Performance evaluation across seven biological tasks, including scRNA-seq data clustering and spatial transcriptomics domain identification, shows that TopoLa significantly improves the performance of several state-of-the-art models. These results underscore the generalizability and robustness of TopoLa, establishing it as a valuable tool for advancing both biological discovery and computational methodologies.

q-bio.GN↗

arXiv2024

AI for Nuclear Physics: the EXCLAIM project

In overview of the recent activity of the newly funded EXCLusives with AI and Machine learning (EXCLAIM) collaboration is presented. The main goal of the collaboration is to develop a framework to implement AI and machine learning techniques in problems emerging from the phenomenology of high energy exclusive scattering processes from nucleons and nuclei, maximizing the information that can be extracted from various sets of experimental data, while implementing theoretical constraints from lattice QCD. A specific perspective embraced by EXCLAIM is to use the methods of theoretical physics to understand the working of ML, beyond its standardized applications to physics analyses which most often rely on industrially provided tools, in an automated way.

hep-ph↗

arXiv2024

Variational autoencoder inverse mapper for extraction of Compton form factors: Benchmarks and conditional learning

Deeply virtual exclusive scattering processes (DVES) serve as precise probes of nucleon quark and gluon distributions in coordinate space. These distributions are derived from generalized parton distributions (GPDs) via Fourier transform relative to proton momentum transfer. QCD factorization theorems enable DVES to be parameterized by Compton form factors (CFFs), which are convolutions of GPDs with perturbatively calculable kernels. Accurate extraction of CFFs from DVCS, benefiting from interference with the Bethe-Heitler (BH) process and a simpler final state structure, is essential for inferring GPDs. This paper focuses on extracting CFFs from DVCS data using a variational autoencoder inverse mapper (VAIM) and its constrained variant (C-VAIM). VAIM is shown to be consistent with Markov Chain Monte Carlo (MCMC) methods in extracting multiple CFF solutions for given kinematics, while C-VAIM effectively captures correlations among CFFs across different kinematic values, providing more constrained solutions. This study represents a crucial first step towards a comprehensive analysis pipeline towards the extraction of GPDs.

hep-ph↗

arXiv2024

VAIM-CFF: A variational autoencoder inverse mapper solution to Compton form factor extraction from deeply virtual exclusive reactions

We develop a new methodology for extracting Compton form factors (CFFs) in from deeply virtual exclusive reactions such as the unpolarized DVCS cross section using a specialized inverse problem solver, a variational autoencoder inverse mapper (VAIM). The VAIM-CFF framework not only allows us access to a fitted solution set possibly containing multiple solutions in the extraction of all 8 CFFs from a single cross section measurement, but also accesses the lost information contained in the forward mapping from CFFs to cross section. We investigate various assumptions and their effects on the predicted CFFs such as cross section organization, number of extracted CFFs, use of uncertainty quantification technique, and inclusion of prior physics information. We then use dimensionality reduction techniques such as principal component analysis to visualize the missing physics information tracked in the latent space of the VAIM framework. Through re-framing the extraction of CFFs as an inverse problem, we gain access to fundamental properties of the problem not comprehensible in standard fitting methodologies: exploring the limits of the information encoded in deeply virtual exclusive experiments.

hep-ph↗

arXiv2024

TopoLa: a novel embedding framework for understanding complex networks

Complex networks, which are the abstractions of many real-world systems, present a persistent challenge across disciplines for people to decipher their underlying information. Recently, hyperbolic geometry of latent spaces has gained traction in network analysis, due to its ability to preserve certain local intrinsic properties of the nodes. In this study, we explore the problem from a much broader perspective: understanding the impact of nodes' global topological structures on latent space placements. Our investigations reveal a direct correlation between the topological structure of nodes and their positioning within the latent space. Building on this deep and strong connection between node distance and network topology, we propose a novel embedding framework called Topology-encoded Latent Hyperbolic Geometry (TopoLa) for analyzing complex networks. With the encoded topological information in the latent space, TopoLa is capable of enhancing both conventional and low-rank networks, using the singular value gap to clarify the mathematical principles behind this enhancement. Meanwhile, we show that the equipped TopoLa distance can also help augment pivotal deep learning models encompassing knowledge distillation and contrastive learning.

cs.SI↗

arXiv2022

TripHLApan: predicting HLA molecules binding peptides based on triple coding matrix and transfer learning

Human leukocyte antigen (HLA) is an important molecule family in the field of human immunity, which recognizes foreign threats and triggers immune responses by presenting peptides to T cells. In recent years, the synthesis of tumor vaccines to induce specific immune responses has become the forefront of cancer treatment. Computationally modeling the binding patterns between peptide and HLA can greatly accelerate the development of tumor vaccines. However, most of the prediction methods performance is very limited and they cannot fully take advantage of the analysis of existing biological knowledge as the basis of modeling. In this paper, we propose TripHLApan, a novel pan-specific prediction model, for HLA molecular peptide binding prediction. TripHLApan exhibits powerful prediction ability by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. The comprehensive evaluations demonstrate the effectiveness of TripHLApan in predicting HLA-I and HLA-II peptide binding in different test environments. The predictive power of HLA-I is further demonstrated in the latest data set. In addition, we show that TripHLApan has strong binding reconstitution ability in the samples of a melanoma patient. In conclusion, TripHLApan is a powerful tool for predicting the binding of HLA-I and HLA-II molecular peptides for the synthesis of tumor vaccines.

q-bio.QM↗