arXiv subjects

Yang Gao

Publications and source records attributed to Yang Gao.

At least 397 records · Page 22Linked to original sources

arXiv2024

Measurement of $e^{+}e^{-}\to ωη^{\prime}$ cross sections at $\sqrt{s}=$ 2.000 to 3.080 GeV

The Born cross sections for the process $e^{+}e^{-}\to ωη^{\prime}$ are measured at 22 center-of-mass energies from 2.000 to 3.080 GeV using data collected with the BESIII detector at the BEPCII collider. A resonant structure is observed with a statistical significance of 9.6$σ$. A Breit-Wigner fit determines its mass to be $M_R=(2153\pm30\pm31)~{\rm{MeV}}/c^{2}$ and its width to be $Γ_{R}=(167\pm77\pm7)~\rm{MeV}$, where the first uncertainties are statistical and the second are systematic.

hep-ex↗

arXiv2024

Measurement of the Born cross section for $e^{+}e^{-}\to ηh_c $ at center-of-mass energies between 4.1 and 4.6\,GeV

We measure the Born cross section for the reaction $e^{+}e^{-} \rightarrow ηh_c$ from $\sqrt{s} = 4.129$ to $4.600$~GeV using data sets collected by the BESIII detector running at the BEPCII collider. A resonant structure in the cross section line shape near 4.200~GeV is observed with a statistical significance of 7$σ$. The parameters of this resonance are measured to be \MeasMass\ and \MeasWidth, where the first uncertainties are statistical and the second systematic.

hep-ex↗

arXiv2024

ONNXPruner: ONNX-Based General Model Pruning Adapter

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning.

cs.LG↗

arXiv2024

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD

The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution. Recent efforts have aimed to enhance the high-resolution understanding capabilities of LVLMs, yet they remain capped at approximately 1500 x 1500 pixels and constrained to a relatively narrow resolution range. This paper represents InternLM-XComposer2-4KHD, a groundbreaking exploration into elevating LVLM resolution capabilities up to 4K HD (3840 x 1600) and beyond. Concurrently, considering the ultra-high resolution may not be necessary in all scenarios, it supports a wide range of diverse resolutions from 336 pixels to 4K standard, significantly broadening its scope of applicability. Specifically, this research advances the patch division paradigm by introducing a novel extension: dynamic resolution with automatic patch configuration. It maintains the training image aspect ratios while automatically varying patch counts and configuring layouts based on a pre-trained Vision Transformer (ViT) (336 x 336), leading to dynamic training resolution from 336 pixels to 4K standard. Our research demonstrates that scaling training resolution up to 4K HD leads to consistent performance enhancements without hitting the ceiling of potential improvements. InternLM-XComposer2-4KHD shows superb capability that matches or even surpasses GPT-4V and Gemini Pro in 10 of the 16 benchmarks. The InternLM-XComposer2-4KHD model series with 7B parameters are publicly available at https://github.com/InternLM/InternLM-XComposer.

cs.CV↗

arXiv2024

Search for the Rare Decays $D_s^+\to h^+(h^{0})e^+e^-$

Using 7.33~fb$^{-1}$ of $e^{+}e^{-}$ collision data collected by the BESIII detector at center-of-mass energies in the range of $\sqrt{s}=4.128 - 4.226$~GeV, we search for the rare decays $D_{s}^+\to h^+(h^{0})e^{+}e^{-}$, where $h$ represents a kaon or pion. By requiring the $e^{+}e^{-}$ invariant mass to be consistent with a $ϕ(1020)$, $0.98<M(e^{+}e^{-})<1.04$ ~GeV/$c^2$, the decay $D_s^+\toπ^+ϕ,ϕ\to e^{+}e^{-}$ is observed with a statistical significance of 7.8$σ$, and evidence for the decay $D_s^+\toρ^+ϕ,ϕ\to e^{+}e^{-}$ is found for the first time with a statistical significance of 4.4$σ$. The decay branching fractions are measured to be $\mathcal{B}(D_s^+\toπ^+ϕ, ϕ\to e^{+}e^{-} )=(1.17^{+0.23}_{-0.21}\pm0.03)\times 10^{-5}$, and $\mathcal{B}(D_s^+\toρ^+ϕ, ϕ\to e^{+}e^{-} )=(2.44^{+0.67}_{-0.62}\pm 0.16)\times 10^{-5}$, where the first uncertainties are statistical and the second systematic. No significant signal for the three four-body decays of $D_{s}^{+}\to π^{+}π^{0}e^{+}e^{-},\ D_{s}^{+}\to K^{+}π^{0}e^{+}e^{-}$, and $D_{s}^{+}\to K_{S}^{0}π^{+}e^{+}e^{-}$ is observed. For $D_{s}^{+}\to π^{+}π^{0}e^{+}e^{-}$, the $ϕ$ mass region is vetoed to minimize the long-distance effects. The 90$\%$ confidence level upper limits set on the branching fractions of these decays are in the range of $(7.0-8.1)\times 10^{-5}$.

hep-ex↗

arXiv2024

Search for a massless particle beyond the Standard Model in the $Σ^+\rightarrow p+{\rm invisible}$ decay

A massless particle beyond the Standard Model is searched for in the two-body decay $Σ^+\rightarrow p+{\rm invisible}$ using $(1.0087\pm0.0044)\times10^{10}$ $J/ψ$ events collected at a center-of-mass energy of $\sqrt{s}=3.097$ GeV with the BESIII detector at the BEPCII collider. No significant signal is observed, and the upper limit on the branching fraction $B(Σ^+\rightarrow p+{\rm invisible})$ is determined to be $3.2\times10^{-5}$ at the 90% confidence level. This is the first search for a flavor-changing neutral current process with missing energy in hyperon decays which plays an important role in constraining new physics models.

hep-ex↗

arXiv2024

Improved measurements of the Dalitz decays $η/η'\rightarrowγe^{+}e^{-}$

Based on a data sample of 10 billion $J/ψ$ events collected with the BESIII detector, improved measurements of the Dalitz decays $η/η'\rightarrowγe^+e^-$ are performed, where the $η$ and $η'$ are produced through the radiative decays $J/ψ\rightarrowγη/η'$. The branching fractions of $η\rightarrowγe^+e^-$ and $η'\rightarrowγe^+e^-$ are measured to be $(7.07 \pm 0.05 \pm 0.23)\times10^{-3}$ and $(4.83\pm0.07\pm0.14)\times10^{-4}$, respectively. Within the single pole model, the parameter of electromagnetic transition form factor for $η\rightarrowγe^+e^-$ is determined to be $Λ_η=(0.749 \pm 0.027 \pm 0.007)~ {\rm GeV}/c^{2}$. Within the multi-pole model, we extract the electromagnetic transition form factors for $η'\rightarrowγe^+e^-$ to be $Λ_{η'} = (0.802 \pm 0.007\pm 0.008)~ {\rm GeV}/c^{2}$ and $γ_{η'} = (0.113\pm0.010\pm0.002)~ {\rm GeV}/c^{2}$. The results are consistent with both theoretical predictions and previous measurements. The characteristic sizes of the interaction regions for the $η$ and $η'$ are calculated to be $(0.645 \pm 0.023 \pm 0.007 )~ {\rm fm}$ and $(0.596 \pm 0.005 \pm 0.006)~ {\rm fm}$, respectively. In addition, we search for the dark photon in $η/η^\prime\rightarrowγe^{+}e^{-}$, and the upper limits of the branching fractions as a function of the dark photon are given at 90\% confidence level.

hep-ex↗

arXiv2024

Evidence of the $h_c\to K_S^0 K^+π^-+c.c.$ decay

Based on $(2.712\pm0.014)\times10^9$ $ψ(3686)$ events collected by the BESIII collaboration, evidence of the hadronic decay $h_c\to K_S^0K^+π^-+c.c.$ is found with a significance of $4.3σ$ in the $ψ(3686)\toπ^0 h_c$ process. The branching fraction of $h_c\to K_S^0 K^+π^- +c.c.$ is measured to be $(7.3\pm0.8\pm1.8)\times10^{-4}$, where the first and second uncertainties are statistical and systematic, respectively. Combining with the exclusive decay width of $η_c\to K\bar{K}π$, our result indicates inconsistencies with both pQCD and NRQCD predictions.

hep-ex↗

arXiv2024

Amplitude Analysis of the Decays $D^0\toπ^+π^-π^+π^-$ and $π^+π^-π^0π^0$

Using $e^+e^-$ annihilation data corresponding to an integrated luminosity of 2.93 $\rm fb^{-1}$ taken at the center-of-mass energy $\sqrt{s}=3.773$~GeV with the BESIII detector, a joint amplitude analysis is performed on the decays $D^0\toπ^+π^-π^+π^-$ and $D^0\toπ^+π^-π^0π^0$(non-$η$). The fit fractions of individual components are obtained, and large interferences among the dominant components of $D^{0}\to a_{1}(1260)π$, $D^{0}\toπ(1300)π$, $D^{0}\toρ(770)ρ(770)$ and $D^{0}\to2(ππ)_{S}$ are found in both channels. With the obtained amplitude model, the $CP$-even fractions of $D^0\to π^+π^-π^+π^-$ and $D^0\toπ^+π^-π^0π^0$(non-$η$) are determined to be $(75.2\pm1.1_{\rm stat.}\pm1.5_{\rm syst.})\%$ and $(68.9\pm1.5_{\rm stat.}\pm 2.4_{\rm syst.})\%$, respectively. The branching fractions of $D^0\to π^+π^-π^+π^-$ and $D^0\toπ^+π^-π^0π^0$(non-$η$) are measured to be $(0.688\pm0.010_{\rm stat.}\pm 0.010_{\rm syst.})\%$ and $(0.951\pm0.025_{\rm stat.}\pm 0.021_{\rm syst.})\%$, respectively. The amplitude analysis provides an important model for binning strategy in the measurements of the strong phase parameters of $D^0 \to 4π$ when used to determine the CKM angle $γ(ϕ_{3})$ via the $B^{-}\to D K^{-}$ decay.

hep-ex↗

arXiv2024

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Dataset distillation has emerged as a promising approach in deep learning, enabling efficient training with small synthetic datasets derived from larger real ones. Particularly, distribution matching-based distillation methods attract attention thanks to its effectiveness and low computational cost. However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness. To address these challenges, we introduce two novel constraints: a class centralization constraint and a covariance matching constraint. The class centralization constraint aims to enhance class discrimination by more closely clustering samples within classes. The covariance matching constraint seeks to achieve more accurate feature distribution matching between real and synthetic datasets through local feature covariance matrices, particularly beneficial when sample sizes are much smaller than the number of features. Experiments demonstrate notable improvements with these constraints, yielding performance boosts of up to 6.6% on CIFAR10, 2.9% on SVHN, 2.5% on CIFAR100, and 2.5% on TinyImageNet, compared to the state-of-the-art relevant methods. In addition, our method maintains robust performance in cross-architecture settings, with a maximum performance drop of 1.7% on four architectures. Code is available at https://github.com/VincenDen/IID.

cs.CV↗

arXiv2024

First observation of the decay $Λ^+_c\to nK^{0}_{S}π^+π^0$

Based on 4.5 fb$^{-1}$ of $e^{+}e^{-}$ collision data accumulated at center-of-mass energies between $4599.53$ MeV and $4698.82$ MeV with the BESIII detector, the decay $Λ_{c}^{+}\to nK_{S}^{0}π^+π^0$ is observed for the first time with a significance of $9.2σ$. The branching fraction is measured to be $(0.85\pm0.13\pm0.03)\%$, where the first uncertainty is statistical and the second systematic, which differs from the theoretical prediction based on isospin by 4.4$σ$. This indicates that there may be resonant contributions or some unknown dynamics in this decay.

hep-ex↗

arXiv2024

Observation of $D^{+}\to K_{S}^{0}a_{0}(980)^{+}$ in the amplitude analysis of $D^{+} \to K_{S}^{0}π^+η$

We perform for the first time an amplitude analysis of the decay $D^{+}\to K_{S}^{0}π^+η$ and report the observation of the decay $D^{+}\to K_{S}^{0}a_{0}(980)^{+}$ using 2.93 fb$^{-1}$ of $e^+e^-$ collision data taken at a center-of-mass energy of 3.773 GeV with the BESIII detector. As the only W-annihilation free decay among $D$ to $a_{0}(980)$-pseudoscalar, $D^{+}\to K_{S}^{0}a_{0}(980)^{+}$ is the ideal decay to extract the contributions of the external and internal $W$-emission amplitudes involving $a_{0}(980)$ and study the final-state interactions. The absolute branching fraction of $D^{+}\to K_{S}^{0}π^+η$ is measured to be $(1.27\pm0.04_{\rm stat.}\pm0.03_{\rm syst.})\%$. The product branching fractions of $D^{+}\to K_{S}^{0}a_{0}(980)^{+}$ with $a_{0}(980)^{+}\to π^+η$ and $D^{+}\to π^+ K_0^*(1430)^0$ with $K_0^*(1430)^0\to K_{S}^{0}η$ are measured to be $(1.33\pm0.05_{\rm stat.}\pm0.04_{\rm syst.})\%$ and $(0.14\pm0.03_{\rm stat.}\pm0.01_{\rm syst.})\%$, respectively.

hep-ex↗

arXiv2024

Observation of the semileptonic decays $D^0\rightarrow K_S^0π^-π^0 e^+ ν_e$ and $D^+\rightarrow K_S^0π^+π^- e^+ ν_e$

By analyzing $e^+e^-$ annihilation data corresponding to an integrated luminosity of 2.93 $\rm fb^{-1}$ collected at a center-of-mass energy of 3.773 GeV with the \text{BESIII} detector, the first observation of the semileptonic decays $D^0\rightarrow K_S^0π^-π^0 e^+ ν_e$ and $D^+\rightarrow K_S^0π^+π^- e^+ ν_e$ is reported. With a dominant hadronic contribution from $K_1(1270)$, the branching fractions are measured to be $\mathcal{B}(D^0\rightarrow {K}_1(1270)^-(\to K^0_Sπ^-π^0)e^+ν_e)=(1.69^{+0.53}_{-0.46}\pm0.15)\times10^{-4}$ and $\mathcal{B}(D^+\to \bar{K}_1(1270)^0(\to K^0_Sπ^+π^-)e^+ν_e)=(1.47^{+0.45}_{-0.40}\pm0.20)\times10^{-4}$ with statistical significance of 5.4$σ$ and 5.6$σ$, respectively. When combined with measurements of the $K_1(1270)\to K^+π^-π$ decays, the absolute branching fractions are determined to be $\mathcal{B}(D^0\to K_1(1270)^-e^+ν_e)=(1.05^{+0.33}_{-0.28}\pm0.12\pm0.12)\times10^{-3}$ and $\mathcal{B}(D^+\to \bar{K}_1(1270)^0e^+ν_e)=(1.29^{+0.40}_{-0.35}\pm0.18\pm0.15)\times10^{-3}$. The first and second uncertainties are statistical and systematic, respectively, and the third uncertainties originate from the assumed branching fractions of the $K_1(1270)\to Kππ$ decays.

hep-ex↗

arXiv2024

InternLM2 Technical Report

The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI). However, replicating such advancements in open-source models has been challenging. This paper introduces InternLM2, an open-source LLM that outperforms its predecessors in comprehensive evaluations across 6 dimensions and 30 benchmarks, long-context modeling, and open-ended subjective evaluations through innovative pre-training and optimization techniques. The pre-training process of InternLM2 is meticulously detailed, highlighting the preparation of diverse data types including text, code, and long-context data. InternLM2 efficiently captures long-term dependencies, initially trained on 4k tokens before advancing to 32k tokens in pre-training and fine-tuning stages, exhibiting remarkable performance on the 200k ``Needle-in-a-Haystack" test. InternLM2 is further aligned using Supervised Fine-Tuning (SFT) and a novel Conditional Online Reinforcement Learning from Human Feedback (COOL RLHF) strategy that addresses conflicting human preferences and reward hacking. By releasing InternLM2 models in different training stages and model sizes, we provide the community with insights into the model's evolution.

cs.CL↗

arXiv2024

Plug-and-Play Latent Feature Editing for Orientation-Adaptive Quantitative Susceptibility Mapping Neural Networks

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM reconstruction problem. However, a significant challenge facing current DL-QSM approaches is their limited adaptability to magnetic dipole field orientation variations during training and testing. In this work, we propose a novel Orientation-Adaptive Latent Feature Editing (OA-LFE) module to learn the encoding of acquisition orientation vectors and seamlessly integrate them into the latent features of deep networks. Importantly, it can be directly Plug-and-Play (PnP) into various existing DL-QSM architectures, enabling reconstructions of QSM from arbitrary magnetic dipole orientations. Its effectiveness is demonstrated by combining the OA-LFE module into our previously proposed phase-to-susceptibility single-step instant QSM (iQSM) network, which was initially tailored for pure-axial acquisitions. The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a self-supervised manner on a specially-designed simulation brain dataset. Comprehensive experiments are conducted on simulated and in vivo human brain datasets, encompassing subjects ranging from healthy individuals to those with pathological conditions. These experiments involve various MRI platforms (3T and 7T) and aim to compare our proposed iQSM+ against several established QSM reconstruction frameworks, including the original iQSM. The iQSM+ yields QSM images with significantly improved accuracies and mitigates artifacts, surpassing other state-of-the-art DL-QSM algorithms.

eess.IV↗

arXiv2024

Observation of structures in the processes $e^+e^-\rightarrowωχ_{c1}$ and $ωχ_{c2}$

We present measurements of the Born cross sections for the processes $e^+e^-\rightarrowωχ_{c1}$ and $ωχ_{c2}$ at center-of-mass energies $\sqrt{s}$ from 4.308 to 4.951 GeV. The measurements are performed with data samples corresponding to an integrated luminosity of 11.0 $\rm{fb}^{-1}$ collected with the BESIII detector operating at the BEPCII storage ring. Assuming the $e^+e^-\rightarrowωχ_{c2}$ signals come from a single resonance, the mass and width are determined to be $M=(4413.6\pm9.0\pm0.8)$ MeV/$c^2$ and $Γ=(110.5\pm15.0\pm2.9)$ MeV, respectively, which is consistent with the parameters of the well-established resonance $ψ(4415)$. In addition, we also use one single resonance to describe the $e^+e^-\rightarrowωχ_{c1}$ lineshape, and determine the mass and width to be $M=(4544.2\pm18.7\pm1.7)$ MeV/$c^2$ and $Γ=(116.1\pm33.5\pm1.7)$ MeV, respectively. The structure of this lineshape, observed for the first time, requires further understanding.

hep-ex↗

arXiv2024

Measurement of $Λ$ transverse polarization in $e^{+}e^{-}$ collisions at $\sqrt{s}= 3.68-3.71$ GeV

With data samples collected with the BESIII detector at seven energy points at $\sqrt{s}= 3.68 - 3.71$ GeV, corresponding to an integrated luminosity of 333 pb$^{-1}$, we present a study of the $Λ$ transverse polarization in the $e^+e^-\toΛ\barΛ$ reaction. The significance of polarization by combining the seven energy points is found to be 2.6$σ$ including the systematic uncertainty, which implies a non-zero phase between the transition amplitudes of the $Λ\barΛ$ helicity states. The modulus ratio and the relative phase of EM-$psionic$ form factors combined with all energy points are measured to be $R^Ψ =$ 0.71$^{+0.10}_{-0.10}$ $\pm$ 0.03 and $ΔΦ^Ψ$ = (23$^{+8.8}_{-8.0}$ $\pm$ 1.6$)^\circ$, where the first uncertainties are statistical and the second systematic.

hep-ex↗

arXiv2024

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

Generalizing Neural Radiance Fields (NeRF) to new scenes is a significant challenge that existing approaches struggle to address without extensive modifications to vanilla NeRF framework. We introduce InsertNeRF, a method for INStilling gEneRalizabiliTy into NeRF. By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations. This novel design allows for more accurate and efficient representations of complex appearances and geometries. Experiments show that this method not only achieves superior generalization performance but also provides a flexible pathway for integration with other NeRF-like systems, even in sparse input settings. Code will be available https://github.com/bbbbby-99/InsertNeRF.

cs.CV↗