arXiv subjects

Jitao Xu

Publications and source records attributed to Jitao Xu.

13 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

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↗

arXiv2025

SEO: Stochastic Experience Optimization for Large Language Models

Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in natural language. In SEO, we propose a stochastic validation method to ensure the update direction of experience, avoiding unavailing updates. Experimental results on three tasks for three LLMs demonstrate that experiences optimized by SEO can achieve consistently improved performance. Further analysis indicates that SEO-optimized experience can generalize to out-of-distribution data, boosting the performance of LLMs on similar tasks.

cs.CL↗

arXiv2024

Finding and Exploring Promising Search Space for the 0-1 Multidimensional Knapsack Problem

The 0-1 Multidimensional Knapsack Problem (MKP) is a classical NP-hard combinatorial optimization problem with many engineering applications. In this paper, we propose a novel algorithm combining evolutionary computation with the exact algorithm to solve the 0-1 MKP. It maintains a set of solutions and utilizes the information from the population to extract good partial assignments. To find high-quality solutions, an exact algorithm is applied to explore the promising search space specified by the good partial assignments. The new solutions are used to update the population. Thus, the good partial assignments evolve towards a better direction with the improvement of the population. Extensive experimentation with commonly used benchmark sets shows that our algorithm outperforms the state-of-the-art heuristic algorithms, TPTEA and DQPSO, as well as the commercial solver CPlex. It finds better solutions than the existing algorithms and provides new lower bounds for 10 large and hard instances.

cs.AI↗

arXiv2024

A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models

Machine Translation (MT) has greatly advanced over the years due to the developments in deep neural networks. However, the emergence of Large Language Models (LLMs) like GPT-4 and ChatGPT is introducing a new phase in the MT domain. In this context, we believe that the future of MT is intricately tied to the capabilities of LLMs. These models not only offer vast linguistic understandings but also bring innovative methodologies, such as prompt-based techniques, that have the potential to further elevate MT. In this paper, we provide an overview of the significant enhancements in MT that are influenced by LLMs and advocate for their pivotal role in upcoming MT research and implementations. We highlight several new MT directions, emphasizing the benefits of LLMs in scenarios such as Long-Document Translation, Stylized Translation, and Interactive Translation. Additionally, we address the important concern of privacy in LLM-driven MT and suggest essential privacy-preserving strategies. By showcasing practical instances, we aim to demonstrate the advantages that LLMs offer, particularly in tasks like translating extended documents. We conclude by emphasizing the critical role of LLMs in guiding the future evolution of MT and offer a roadmap for future exploration in the sector.

cs.CL↗

arXiv2023

BiSync: A Bilingual Editor for Synchronized Monolingual Texts

In our globalized world, a growing number of situations arise where people are required to communicate in one or several foreign languages. In the case of written communication, users with a good command of a foreign language may find assistance from computer-aided translation (CAT) technologies. These technologies often allow users to access external resources, such as dictionaries, terminologies or bilingual concordancers, thereby interrupting and considerably hindering the writing process. In addition, CAT systems assume that the source sentence is fixed and also restrict the possible changes on the target side. In order to make the writing process smoother, we present BiSync, a bilingual writing assistant that allows users to freely compose text in two languages, while maintaining the two monolingual texts synchronized. We also include additional functionalities, such as the display of alternative prefix translations and paraphrases, which are intended to facilitate the authoring of texts. We detail the model architecture used for synchronization and evaluate the resulting tool, showing that high accuracy can be attained with limited computational resources. The interface and models are publicly available at https://github.com/jmcrego/BiSync and a demonstration video can be watched on YouTube at https://youtu.be/_l-ugDHfNgU .

cs.CL↗

arXiv2023

Integrating Translation Memories into Non-Autoregressive Machine Translation

Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem well suited to translate with a Translation Memory (TM). This is the scenario considered here. We first analyze the vanilla LevT model and explain why it does not do well in this setting. We then propose a new variant, TM-LevT, and show how to effectively train this model. By modifying the data presentation and introducing an extra deletion operation, we obtain performance that are on par with an autoregressive approach, while reducing the decoding load. We also show that incorporating TMs during training dispenses to use knowledge distillation, a well-known trick used to mitigate the multimodality issue.

cs.CL↗

arXiv2022

Bilingual Synchronization: Restoring Translational Relationships with Editing Operations

Machine Translation (MT) is usually viewed as a one-shot process that generates the target language equivalent of some source text from scratch. We consider here a more general setting which assumes an initial target sequence, that must be transformed into a valid translation of the source, thereby restoring parallelism between source and target. For this bilingual synchronization task, we consider several architectures (both autoregressive and non-autoregressive) and training regimes, and experiment with multiple practical settings such as simulated interactive MT, translating with Translation Memory (TM) and TM cleaning. Our results suggest that one single generic edit-based system, once fine-tuned, can compare with, or even outperform, dedicated systems specifically trained for these tasks.

cs.CL↗

arXiv2022

Blowup dynamics for smooth equivariant solutions to energy critical Landau-Lifschitz flow

In this paper, we study the energy critical 1-equivariant Landau-Lifschitz flow mapping $\mathbb{R}^2$ to $\mathbb{S}^2$ with arbitrary given coefficients $ρ_1\in \mathbb{R}$, $ρ_2>0$. We prove that there exists a codimension one smooth well-localized set of initial data arbitrarily close to the ground state which generates type-II finite-time blowup solutions, and give a precise description of the corresponding singularity formation. In our proof, both the Schrödinger part and the heat part play important roles in the construction of approximate solutions and the mixed energy/Morawetz functional. However, the blowup rate is independent of the coefficients.

math.AP↗

arXiv2022

Joint Generation of Captions and Subtitles with Dual Decoding

As the amount of audio-visual content increases, the need to develop automatic captioning and subtitling solutions to match the expectations of a growing international audience appears as the only viable way to boost throughput and lower the related post-production costs. Automatic captioning and subtitling often need to be tightly intertwined to achieve an appropriate level of consistency and synchronization with each other and with the video signal. In this work, we assess a dual decoding scheme to achieve a strong coupling between these two tasks and show how adequacy and consistency are increased, with virtually no additional cost in terms of model size and training complexity.

cs.CL↗

arXiv2021

One Source, Two Targets: Challenges and Rewards of Dual Decoding

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text. We present an analysis of possible implementations of dual decoding, and experiment with four applications. Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.

cs.CL↗

arXiv2021

Can You Traducir This? Machine Translation for Code-Switched Input

Code-Switching (CSW) is a common phenomenon that occurs in multilingual geographic or social contexts, which raises challenging problems for natural language processing tools. We focus here on Machine Translation (MT) of CSW texts, where we aim to simultaneously disentangle and translate the two mixed languages. Due to the lack of actual translated CSW data, we generate artificial training data from regular parallel texts. Experiments show this training strategy yields MT systems that surpass multilingual systems for code-switched texts. These results are confirmed in an alternative task aimed at providing contextual translations for a L2 writing assistant.

cs.CL↗