arXiv subjects

Hao Sun

Publications and source records attributed to Hao Sun.

At least 289 records · Page 16Linked to original sources

arXiv2024

Exploring the molecular scenario of X(4160)

In this work, we investigate the decays of meson $X(4160)$ in the molecular frame. By using an effective lagrangian approach, we calculate the widths of $X(4160)\to J/ψϕ$, $D^*\bar{D}^*$, $D^*\bar{D}$ and $D\bar{D}$ through the triangle loop mechanism in the molecular scenario. Based on the compositeness condition, the coupling between $X(4160)$ and the $D_s^*\bar{D}_s^*$ molecular state is determined. The other coupling constants used are determined phenomenologically. The calculation of the decay widths shows that the $D^*\bar{D}^*$ decay mode has a larger branching ratio. These predictions can be seen as a test for the charmonium assignment of $X(4160)$.

hep-ph↗

arXiv2024

Synthesis of Electron Microbunching Rotation for Generating Isolated Attosecond Soft X-ray Free-electron Laser Pulses

Attosecond x-ray pulses play a crucial role in the study of ultrafast phenomena occurring within inner and valence electrons. Especially isolated attosecond pulses with high photon energy and high peak power are of great significance in single-shot imaging in the soft x-ray region, life sciences, and attosecond pump-probe experiments. In modern accelerators, laser manipulation of electrons can be used to tailor the ultrafast properties of free-electron laser (FEL) pulses. In this paper, we propose a novel laser manipulation technique that makes use of two laser beams with mutual delays and tilted wavefronts to synthesize microbunching rotation on the scale of infrared laser wavelengths within the electron bunch for generating isolated attosecond soft x-ray pulses. This microbunching rotation ultimately leads to an enhanced current contrast ratio between the main peak and the surrounding satellite peaks within the bunch. By properly accounting for the longitudinal space charge fields within the FEL undulator, a tapered undulator can further suppress the side peaks in the radiation pulse and enable the selection of an isolated, hundred-attosecond, GW-level soft x-ray pulse.

physics.acc-ph↗

arXiv2024

Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding

Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos. This leads to unreliable predictions for noisy, corrupted, and out-of-distribution data. Adapting VTG models to dynamically estimate uncertainties based on user input can address this issue. To this end, we introduce SRAM, a robust network module that benefits from a two-stage cross-modal alignment task. More importantly, it integrates Deep Evidential Regression (DER) to explicitly and thoroughly quantify uncertainty during training, thus allowing the model to say "I do not know" in scenarios beyond its handling capacity. However, the direct application of traditional DER theory and its regularizer reveals structural flaws, leading to unintended constraints in VTG tasks. In response, we develop a simple yet effective Geom-regularizer that enhances the uncertainty learning framework from the ground up. To the best of our knowledge, this marks the first successful attempt of DER in VTG. Our extensive quantitative and qualitative results affirm the effectiveness, robustness, and interpretability of our modules and the uncertainty learning paradigm in VTG tasks. The code will be made available.

cs.CV↗

arXiv2024

The Theoretical Study of $π^+p\to pa_0^+ϕ$ Reaction

We study the production of hyperon resonances in the $π^+p\to pa_0^+ϕ$ reaction within an effective Lagrangian approach. The model includes the production of $Δ(1940)$ and $Δ(1920)$ in the intermediate state excited by the $ρ$ and $p$ exchanges between the initial proton and $π$ meson. Due to the large contribution of $ρ$ exchange in $Δ(1940)$ production, $Δ(1940)$ is found a significant contribution near the threshold in this reaction. We provide total and differential cross section predictions for the reation and discuss the possible influence of model parameters, off-shell effects and branching ratios for $Δ(1940)\to pa_0$ and $Δ(1920)\to pa_0$ decays, which will be useful in future experimental studies. This reaction can provide a platform for studying the features of $Δ(1940)$ resonance, especially the coupling to $pa_0$ channel.

hep-ph↗

arXiv2024

Disentangle and denoise: Tackling context misalignment for video moment retrieval

Video Moment Retrieval, which aims to locate in-context video moments according to a natural language query, is an essential task for cross-modal grounding. Existing methods focus on enhancing the cross-modal interactions between all moments and the textual description for video understanding. However, constantly interacting with all locations is unreasonable because of uneven semantic distribution across the timeline and noisy visual backgrounds. This paper proposes a cross-modal Context Denoising Network (CDNet) for accurate moment retrieval by disentangling complex correlations and denoising irrelevant dynamics.Specifically, we propose a query-guided semantic disentanglement (QSD) to decouple video moments by estimating alignment levels according to the global and fine-grained correlation. A Context-aware Dynamic Denoisement (CDD) is proposed to enhance understanding of aligned spatial-temporal details by learning a group of query-relevant offsets. Extensive experiments on public benchmarks demonstrate that the proposed CDNet achieves state-of-the-art performances.

cs.CV↗

arXiv2024

Retrieval Augmented Thought Process for Private Data Handling in Healthcare

Large Language Models (LLMs) have demonstrated the strong potential to assist both clinicians and the general public with their extensive medical knowledge. However, their application in healthcare is constrained due to concerns about the privacy of data used in training, which prevents the integration of private and personal information because of security and ethical issues. Moreover, if their capabilities can be enhanced with information retrieval to access up-to-date knowledge, the current integration of LLMs with Information retrieval lacks robustness to imperfect retrieval, which can hinder their effectiveness and even reduce overall performance. In this work, we address this challenge by introducing the Retrieval-Augmented Thought Process (RATP). Given access to external knowledge, RATP formulates the thought generation of LLMs as a multiple-step decision process. To optimise such a thought process, RATP leverages Monte-Carlo Tree Search and learns a proxy reward function that permits cost-efficient inference. On a private dataset of electronic medical records, deliberately excluded from any LLM training set, RATP achieves 35% additional accuracy compared to in-context retrieval-augmented generation for the question-answering task.

cs.CL↗

arXiv2024

Boosting Disfluency Detection with Large Language Model as Disfluency Generator

Current disfluency detection methods heavily rely on costly and scarce human-annotated data. To tackle this issue, some approaches employ heuristic or statistical features to generate disfluent sentences, partially improving detection performance. However, these sentences often deviate from real-life scenarios, constraining overall model enhancement. In this study, we propose a lightweight data augmentation approach for disfluency detection, utilizing the superior generative and semantic understanding capabilities of large language model (LLM) to generate disfluent sentences as augmentation data. We leverage LLM to generate diverse and more realistic sentences guided by specific prompts, without the need for fine-tuning the LLM. Subsequently, we apply an uncertainty-aware data filtering approach to improve the quality of the generated sentences, utilized in training a small detection model for improved performance. Experiments using enhanced data yielded state-of-the-art results. The results showed that using a small amount of LLM-generated enhanced data can significantly improve performance, thereby further enhancing cost-effectiveness. Our code is available here.

cs.CL↗

arXiv2024

Filtered Stokes G-local Systems in Nonabelian Hodge Theory on Curves

In the wild nonabelian Hodge correspondence on curves, filtered Stokes G-local systems are regarded as the objects on the Betti side. In this paper, we demonstrate a construction of the moduli space of them, called the Betti moduli space, and it reduces to the wild character variety when the Betti weights are trivial. We study some particular examples including Eguch-Hanson space and the Airy equation together with the corresponding moduli spaces. Furthermore, we provide a proof of the correspondence among irregular singular G-connections, Stokes G-local systems, and Stokes G-representations. This correspondence can be viewed as the G-version of irregular Rieman-Hilbert correspondence on curves.

math.AG↗

arXiv2024

Dark matter, leptogenesis and Z' in the B-L model

We discuss the interplay between dark matter, leptogenesis and a new gauge boson $Z^\prime$ in the $B-L$ model. A fermion dark matter $χ$ carrying $U(1)_{B-L}$ charge is introduced to the model but not coupling with other particles. We consider the freeze-out and freeze-in mechanisms, and obtain the correct relic density respectively. We have scanned the feasible parameter space and found that the dark matter direct detection experiments imposed the most stringent constraints on the parameter space. The constraint on the parameter space places a limit on the mass of dark matter with $m_χ \approx 1/2 M_{Z'}$ within a narrow region in the case of freeze-out scenario, and we can obtain the right baryon asymmetry result in the case of $m_χ\subset[654$ GeV, 664 GeV]. For the freeze-in scenario, we have a much broader parameter space for $m_χ$ and $M_{Z^\prime}$ but $g_{BL}$ is restricted at $10^{-5}$ level for $Q=0.1$. In both scenarios, $g_{BL}-M_{Z^\prime}$ is limited within a narrow region by the dark matter relic density, direct detection and baryon asymmetry constraints.

hep-ph↗

arXiv2024

A unified moment tensor potential for silicon, oxygen, and silica

Si and its oxides have been extensively explored in theoretical research due to their technological and industrial importance. Simultaneously describing interatomic interactions within both Si and SiO$_2$ without the use of \textit{ab initio} methods is considered challenging, given the charge transfers involved. Herein, this challenge is overcome by developing a unified machine learning interatomic potentials describing the Si/ SiO$_2$/ O system, based on the moment tensor potential (MTP) framework. This MTP is trained using a comprehensive database generated using density functional theory simulations, encompassing a wide range of crystal structures, point defects, extended defects, and disordered structure. Extensive testing of the MTP is performed, indicating it can describe static and dynamic features of very diverse Si, O, and SiO$_2$ atomic structures with a degree of fidelity approaching that of DFT

cond-mat.mtrl-sci↗

arXiv2024

IRGen: Generative Modeling for Image Retrieval

While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image retrieval as a variant of generative modeling and employing a sequence-to-sequence model. This approach is harmoniously aligned with the current trend towards unification in research, presenting a cohesive framework that allows for end-to-end differentiable searching. This, in turn, facilitates superior performance via direct optimization techniques. The development of our model, dubbed IRGen, addresses the critical technical challenge of converting an image into a concise sequence of semantic units, which is pivotal for enabling efficient and effective search. Extensive experiments demonstrate that our model achieves state-of-the-art performance on three widely-used image retrieval benchmarks as well as two million-scale datasets, yielding significant improvement compared to prior competitive retrieval methods. In addition, the notable surge in precision scores facilitated by generative modeling presents the potential to bypass the reranking phase, which is traditionally indispensable in practical retrieval workflows.

cs.CV↗

arXiv2024

Multimodal Infusion Tuning for Large Models

Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoustics. In MiT, we also design a novel adaptive rescaling strategy at the attention head level, which optimizes the representation of infused multimodal features. Notably, all foundation models are kept frozen during the tuning process to reduce the computational burden and only 2.5\% parameters are tunable. We conduct experiments across a range of multimodal tasks, including image-related tasks like referring segmentation and non-image tasks such as sentiment analysis. Our results showcase that MiT achieves state-of-the-art performance in multimodal understanding while significantly reducing computational overhead(10\% of previous methods). Moreover, our tuned model exhibits robust reasoning abilities even in complex scenarios.

cs.MM↗

arXiv2024

Sharing tripartite nonlocality sequentially using only projective measurements

Bell nonlocality is a valuable resource in quantum information processing tasks. Scientists are interested in whether a single entangled state can generate a long sequence of nonlocal correlations. Previous work has accomplished sequential tripartite nonlocality sharing through unsharp measurements. In this paper, we investigate the sharing of tripartite nonlocality using only projective measurements and sharing classical randomness. For the generalized GHZ state, we have demonstrated that using unbiased measurement choices, two Charlies can share the standard tripartite nonlocality with a single Alice and a single Bob, while at most one Charlie can share the genuine tripartite nonlocality with a single Alice and a single Bob. However, with biased measurement choices, the number of Charlies sharing the genuine tripartite nonlocality can be increased to two. Nonetheless, we find that using biased measurements does not increase the number of sequential observers sharing the standard tripartite nonlocality. Moreover, we provide the feasible range of double violation for the parameters of the measurement combination probability with respect to the state.

quant-ph↗

arXiv2024

Robust Latent Representation Tuning for Image-text Classification

Large models have demonstrated exceptional generalization capabilities in computer vision and natural language processing. Recent efforts have focused on enhancing these models with multimodal processing abilities. However, addressing the challenges posed by scenarios where one modality is absent remains a significant hurdle. In response to this issue, we propose a robust latent representation tuning method for large models. Specifically, our approach introduces a modality latent translation module to maximize the correlation between modalities, resulting in a robust representation. Following this, a newly designed fusion module is employed to facilitate information interaction between the modalities. Within this framework, common semantics are refined during training, and robust performance is achieved even in the absence of one modality. Importantly, our method maintains the frozen state of the image and text foundation models to preserve their capabilities acquired through large-scale pretraining. We conduct experiments on several public datasets, and the results underscore the effectiveness of our proposed method.

cs.CV↗

arXiv2024

$Se^2$: Sequential Example Selection for In-Context Learning

The remarkable capability of large language models (LLMs) for in-context learning (ICL) needs to be activated by demonstration examples. Prior work has extensively explored the selection of examples for ICL, predominantly following the "select then organize" paradigm, such approaches often neglect the internal relationships between examples and exist an inconsistency between the training and inference. In this paper, we formulate the problem as a $Se$quential $Se$lection problem and introduce $Se^2$, a sequential-aware method that leverages the LLM's feedback on varying context, aiding in capturing inter-relationships and sequential information among examples, significantly enriching the contextuality and relevance of ICL prompts. Meanwhile, we utilize beam search to seek and construct example sequences, enhancing both quality and diversity. Extensive experiments across 23 NLP tasks from 8 distinct categories illustrate that $Se^2$ markedly surpasses competitive baselines and achieves 42\% relative improvement over random selection. Further in-depth analysis shows the effectiveness of proposed strategies, highlighting $Se^2$'s exceptional stability and adaptability across various scenarios. Code available at https://github.com/microsoft/LMOps.

cs.CL↗

arXiv2024

Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction Tasks

Information Extraction (IE) plays a crucial role in Natural Language Processing (NLP) by extracting structured information from unstructured text, thereby facilitating seamless integration with various real-world applications that rely on structured data. Despite its significance, recent experiments focusing on English IE tasks have shed light on the challenges faced by Large Language Models (LLMs) in achieving optimal performance, particularly in sub-tasks like Named Entity Recognition (NER). In this paper, we delve into a comprehensive investigation of the performance of mainstream Chinese open-source LLMs in tackling IE tasks, specifically under zero-shot conditions where the models are not fine-tuned for specific tasks. Additionally, we present the outcomes of several few-shot experiments to further gauge the capability of these models. Moreover, our study includes a comparative analysis between these open-source LLMs and ChatGPT, a widely recognized language model, on IE performance. Through meticulous experimentation and analysis, we aim to provide insights into the strengths, limitations, and potential enhancements of existing Chinese open-source LLMs in the domain of Information Extraction within the context of NLP.

cs.CL↗

arXiv2024

Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding

Within the context of reading comprehension, the task of Distractor Generation (DG) aims to generate several incorrect options to confuse readers. Traditional supervised methods for DG rely heavily on expensive human-annotated distractor labels. In this paper, we propose an unsupervised DG framework, leveraging Large Language Models (LLMs) as cost-effective annotators to enhance the DG capability of smaller student models. Specially, to perform knowledge distilling, we propose a dual task training strategy that integrates pseudo distractors from LLMs and the original answer in-formation as the objective targets with a two-stage training process. Moreover, we devise a counterfactual contrastive decoding mechanism for increasing the distracting capability of the DG model. Experiments show that our unsupervised generation method with Bart-base greatly surpasses GPT-3.5-turbo performance with only 200 times fewer model parameters. Our proposed unsupervised DG method offers a cost-effective framework for practical reading comprehension applications, without the need of laborious distractor annotation and costly large-size models

cs.CL↗

arXiv2024

Compact dwarfs made of light-quark nuggets

Utilizing an equivparticle model with both linear confinement and leading-order perturbative interactions, we obtain systematically the properties of strangelets and nonstrange quark matter ($ud$QM) nuggets at various baryon ($A$) and charge ($Z$) numbers, where the detailed single-quark-energy levels are fixed by solving Dirac equations in mean-field approximation (MFA). We then examine the structures of compact dwarfs made of light strangelets or $ud$QM nuggets forming body-centered cubic lattices in a uniform electron background. Despite the strangelets and $ud$QM nuggets generally become more stable at larger $A$, the compact dwarfs are still stable since the fusion reactions between those objects do not take place in the presence of a Coulomb barrier, which is similar to the cases of light nuclei in normal white dwarfs. If $ud$QM dwarfs or strangelet dwarfs are covered with normal matter, their masses and radii become larger but do not exceed those of ordinary white dwarfs. Finally, we investigate the radial oscillation frequencies of $ud$QM dwarfs and strangelet dwarfs, and find that their frequencies are typically higher than traditional white dwarfs. The stability of compact dwarfs are then analysised by examining radial oscillation frequencies of the fundamental mode, where compact dwarfs covered by normal matter are still stable.

hep-ph↗