arXiv subjects

Yabo Dong

Publications and source records attributed to Yabo Dong.

12 recordsLinked to original sources

arXiv2026

Assessing Parameter Redundancy in Transformers for Jet Tagging

Transformer-based jet taggers, such as the Particle Transformer (ParT) and the More-Interaction Particle Transformer (MIParT), achieve excellent discrimination by exploiting correlations among jet constituents, but often require more trainable parameters than earlier deep-learning taggers. In this paper, we investigate whether comparable discriminating power can be achieved with substantially fewer parameters. We introduce an hourglass structure that replaces the feed-forward networks (FFNs) in the attention blocks while leaving the particle-interaction attention unchanged. We also introduce a lightweight particle-embedding layer to replace the original dense embedding network. Applying both modifications to ParT and MIParT yields the hourglass (HG) variants ParT-HG and MIParT-HG, respectively. We evaluate both models on benchmark datasets for top tagging and quark-gluon discrimination. Both variants retain comparable tagging performance, including background rejection at fixed signal efficiencies, while using only approximately 48% and 39.7% of the parameters of their respective baselines. On the larger JetClass dataset, accuracy and AUC decrease by less than 1%, and background rejection also decreases for several signal classes. Overall, our approach provides an alternative way to reduce the parameter count of Transformer jet taggers while largely retaining their tagging performance.

hep-ph↗

arXiv2026

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient alternative to diffusion models, but practical implementations typically rely on a single finite-capacity global vector-field estimator. In such heterogeneous temporal distributions, distinct regimes may pass through nearby flow states while requiring incompatible conditional velocities. A monolithic estimator trained with the standard $\ell_2$ velocity-matching objective may therefore learn an overly smoothed approximation of the local transport field. This estimator-level smoothing can attenuate branch-specific dynamics, leading to spectral distortion and poor mode coverage. To address this, we propose PrismFlow, a new FM method with Koopman-inspired dynamical experts. Each expert learns residual corrections in a latent space where local nonlinear temporal evolution can be approximated by linear transitions. We further propose a confidence-aware Winner-Take-All (WTA) objective that updates only the expert best aligned with each sample while masking gradients to the others, encouraging mode-specific specialization. During sampling, the selected expert adds a residual dynamical correction to the global transport field, preserving FM stability while recovering fine-grained and high-frequency temporal structures. Across various benchmarks, PrismFlow effectively mitigates the spectral contraction in standard FM and achieves state-of-the-art performance, with a 15.6% gain in Context-FID and a 38.6% improvement in Discriminative Score, while remaining robust in low-data settings and effective for forecasting and imputation.

cs.LG↗

arXiv2026

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection

Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging area, yet a persistent challenge remains: MLLMs rely on coarse time-series heuristics but struggle with multi-dimensional, detailed reasoning, which is vital for understanding complex time-series data. We present AnomSeer to address this by reinforcing the model to ground its reasoning in precise, structural details of time series, unifying anomaly classification, localization, and explanation. At its core, an expert chain-of-thought trace is generated to provide a verifiable, fine-grained reasoning from classical analyses (e.g., statistical measures, frequency transforms). Building on this, we propose a novel time-series grounded policy optimization (TimerPO) that incorporates two additional components beyond standard reinforcement learning: a time-series grounded advantage based on optimal transport and an orthogonal projection to ensure this auxiliary granular signal does not interfere with the primary detection objective. Across diverse anomaly scenarios, AnomSeer, with Qwen2.5-VL-3B/7B-Instruct, outperforms larger commercial baselines (e.g., GPT-4o) in classification and localization accuracy, particularly on point- and frequency-driven exceptions. Moreover, it produces plausible time-series reasoning traces that support its conclusions.

cs.LG↗

arXiv2025

Particle-level transformers for 95 GeV Higgs boson searches at future $e^+e^-$ Higgs factories

Motivated by several mild excesses around 95~GeV, we investigate the prospects for a light scalar $S$ produced via Higgsstrahlung, $e^+e^- \to Z(\mu^+\mu^-)S$, at future $e^+e^-$ Higgs factories. We take the CEPC as a benchmark, with a center-of-mass energy of $\sqrt{s}=240$ GeV and an integrated luminosity of $L=20~\mathrm{ab}^{-1}$. We focus on the decay modes $S\to\tau^+\tau^-$ and $S\to b\bar b$. To maximize sensitivity, we employ the particle-level transformer networks Particle Transformer (ParT) and its more-interactive variant MIParT, which exploit the features of all reconstructed objects and their correlations. For a representative signal benchmark, this approach improves the expected statistical precision on the signal strength by factors of 2.3 in the $\tau^+\tau^-$ channel and 1.4 in the $b\bar b$ channel compared to a cut-based analysis. Within the flipped Next-to-Two-Higgs-Doublet Model (N2HDM-F), the CEPC can measure the signal strength with a statistical precision down to 1.0% in the $\tau^+\tau^-$ channel and 0.69% in the $b\bar b$ channel using MIParT. It can achieve a $5\sigma$ discovery for $\mu_{\tau\tau}^{ZS}>1.6\times10^{-2}$ or $\mu_{bb}^{ZS}>5.0\times10^{-3}$, and reach 1% precision for $\mu_{\tau\tau}^{ZS}>0.93$ or $\mu_{bb}^{ZS}>0.14$. These gains are expected to qualitatively carry over to other future lepton colliders such as FCC-ee and the ILC. Our results demonstrate the potential of particle-level machine-learning techniques to strengthen light Higgs searches at future $e^+e^-$ Higgs factories.

hep-ph↗

arXiv2025

Voxel Densification for Serialized 3D Object Detection: Mitigating Sparsity via Pre-serialization Expansion

Recent advances in point cloud object detection have increasingly adopted Transformer-based and State Space Models (SSMs) to capture long-range dependencies. However, these serialized frameworks strictly maintain the consistency of input and output voxel dimensions, inherently lacking the capability for voxel expansion. This limitation hinders performance, as expanding the voxel set is known to significantly enhance detection accuracy, particularly for sparse foreground objects. To bridge this gap, we propose a novel Voxel Densification Module (VDM). Unlike standard convolutional stems, VDM is explicitly designed to promote pre-serialization spatial expansion. It leverages sparse 3D convolutions to propagate foreground semantics to neighboring empty voxels, effectively densifying the feature representation before it is flattened into a sequence. Simultaneously, VDM incorporates residual sparse blocks to aggregate fine-grained local context, ensuring rich geometric feature extraction. To balance the computational overhead of increased voxel density, we introduce a strategic cascaded downsampling mechanism. We integrate VDM into both Transformer-based (DSVT) and SSM-based (LION) detectors. Extensive experiments demonstrate that VDM consistently improves detection accuracy across multiple benchmarks. Specifically, our method achieves 74.8 mAPH (L2) on the Waymo validation set and 70.5 mAP on the nuScenes test set. Furthermore, it attains 42.6 mAP on the Argoverse 2 validation set and 67.6 mAP on the ONCE validation set, consistently outperforming the baseline models. The source code will be made publicly available at https://github.com/qifeng22/VDM.

cs.CV↗

arXiv2025

Testing a 95 GeV Scalar at the CEPC with Machine Learning

Several possible excesses around 95 GeV hint at an additional light scalar beyond the Standard Model. We examine the capability of the CEPC to test this hypothesis in the Higgsstrahlung channel $e^{+}e^{-} \to ZS$ with $Z \to\mu^{+}\mu^{-}$ and $S\to\tau^{+}\tau^{-}$. Full detector simulation shows that the optimal center-of-mass energy to study the 95 GeV light scalar is 210 GeV. A deep neural network classifier reduces the luminosity required for discovery by half. At $L = 20~\mathrm{ab}^{-1}$, the CEPC's $5\sigma$ sensitivity to the signal strength $\mu_{\tau\tau}^{ZS}$ reaches 0.016 and 0.020 for $\sqrt{s} =$ 210 GeV and 240 GeV, respectively. The corresponding thresholds for a 5% precision measurement are $\mu_{\tau\tau}^{ZS} > 0.10$ and $>0.12$. At $\sqrt{s}=$ 210 GeV (240 GeV), $5\sigma$ coverage of all N2HDM-Flipped samples with $\chi^2_{h_{95}}<7.82$ requires $L=800\ \mathrm{fb}^{-1}$ (1.22 $\mathrm{ab}^{-1}$). These results establish a 210 GeV run, augmented by machine-learning selection, as the most efficient strategy to confirm or refute the 95 GeV excess at future lepton colliders.

hep-ph↗

arXiv2025

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal priors. In this work, we introduce TimeMaster, a reinforcement learning (RL)-based method that enables time-series MLLMs to perform structured, interpretable reasoning directly over visualized time-series inputs and task prompts. TimeMaster adopts a three-part structured output format, reasoning, classification, and domain-specific extension, and is optimized via a composite reward function that aligns format adherence, prediction accuracy, and open-ended insight quality. The model is trained using a two-stage pipeline: we first apply supervised fine-tuning (SFT) to establish a good initialization, followed by Group Relative Policy Optimization (GRPO) at the token level to enable stable and targeted reward-driven improvement in time-series reasoning. We evaluate TimeMaster on the TimerBed benchmark across six real-world classification tasks based on Qwen2.5-VL-3B-Instruct. TimeMaster achieves state-of-the-art performance, outperforming both classical time-series models and few-shot GPT-4o by over 14.6% and 7.3% performance gain, respectively. Notably, TimeMaster goes beyond time-series classification: it also exhibits expert-like reasoning behavior, generates context-aware explanations, and delivers domain-aligned insights. Our results highlight that reward-driven RL can be a scalable and promising path toward integrating temporal understanding into time-series MLLMs.

cs.LG↗

arXiv2025

New Physics Search at the CEPC: a General Perspective

The Circular Electron-Positron Collider (CEPC), a proposed next-generation Higgs factory, provides new opportunities to explore physics beyond the Standard Model (SM). With its clean electron-positron collision environment and the ability to collect large samples of Higgs, W, and Z bosons, the CEPC enables precision measurements and searches for new physics. This white paper outlines the CEPC's discovery potential, including studies of exotic decays of the Higgs, Z, and top quarks, dark matter and dark sector phenomena, long-lived particles, supersymmetry, and neutrino-related signatures. Advanced detector technologies and reconstruction techniques, such as one-to-one correspondence reconstruction and jet origin identification, significantly improve sensitivity to rare and weakly interacting processes. The CEPC is particularly well suited to probe the electroweak phase transition and test models of electroweak baryogenesis and dark sector interactions. In addition, global fit analyses highlight the CEPC's complementary role in constraining a wide range of new physics scenarios. These features position the CEPC as a powerful tool for exploring the next frontier in fundamental particle physics in the post-Higgs discovery era.

hep-ex↗

arXiv2024

Revisiting CMSSM with Non-Universal Gaugino Masses under Current Constraints

To address the longstanding tension between the Constrained Minimal Supersymmetric Standard Model (CMSSM) and recent experimental data, we investigate non-universal gaugino masses within an SU(5) Grand Unified Theory (GUT) framework, focusing on the $\tilde{g}$-SUGRA scenario where $\lvert M_{3} \rvert \gg \lvert M_{1} \rvert, \lvert M_{2} \rvert$. This hierarchy enables a heavier gluino, thereby evading current experimental bounds on supersymmetric particles. Our analysis reveals that precise Higgs measurements place stringent constraints on the model, requiring $\tan\beta \gtrsim 5$ and $ M_{0} \gtrsim 20 \, \tan\beta \,\text{GeV}$. Although the $\tilde{g}$-SUGRA scenario can help reconcile the persistent $(g-2)_\mu$ anomaly, the Higgs constraints significantly restrict its parameter space, making a large contribution to $(g-2)_{\mu}$ challenging. We also assess the discovery prospects in upcoming dark matter direct detection experiments, including PandaX-xT (200 t.y.), LZ (projected), and XENONnT (20 t.y.), which may not fully cover the viable parameter space. In contrast, future collider experiments$-$such as the High-Luminosity LHC at $3\,\mathrm{ab}^{-1}$ and $\mathrm{CLIC}_{1500}$ at $2.5\,\mathrm{ab}^{-1}$$-$can comprehensively probe the remaining regions. These findings highlight $\tilde{g}$-SUGRA as a promising solution to the CMSSM tension and offer clear, testable predictions for upcoming collider searches.

hep-ph↗

arXiv2024

Probing Type-I 2HDM light Higgs in the top-pair-associated diphoton channel

Motivated by the possible 95 GeV diphoton excess, we investigate the capability of the Type-I Two-Higgs-Doublet Model (2HDM-I) to explain this signal under current theoretical and experimental constraints. Using full Monte Carlo (MC) simulations for the process of $pp \to t(\to W^+ b)\bar{t}(\to W^- \bar{b})h(\to \gamma\gamma)$, we evaluate the discovery potential of a 95 GeV Higgs boson at future colliders. Direct Higgs searches strongly constrain the parameter $\alpha$, excluding the region with $\alpha \lesssim 0.95$. Monte Carlo results indicate that a minimum cross section of 0.3 fb is required to achieve a $5\sigma$ signal statistical significance at the HL-LHC with $L = 3~\mathrm{ab}^{-1}$. For the same luminosity, HE-LHC and FCC-hh require 0.67 fb and 2.36 fb, respectively. At the 14 TeV HL-LHC with an integrated luminosity of $3~\mathrm{ab}^{-1}$, parameter regions with $\sin(\beta-\alpha) \gtrsim 0.4$ and $\sin(\beta-\alpha) \gtrsim 0.25$ can be probed at the $5\sigma$ and $2\sigma$ significance levels, respectively. At the 27 TeV HE-LHC with $L = 10~\mathrm{ab}^{-1}$, the sensitivity improves to $\sin(\beta-\alpha) \gtrsim 0.25$ ($5\sigma$) and $\gtrsim 0.15$ ($2\sigma$). For the 100 TeV FCC-hh with $L = 30~\mathrm{ab}^{-1}$, even regions with $\sin(\beta-\alpha) \gtrsim 0.1$ or $\sin(\beta-\alpha) \lesssim -0.05$ can be covered at the $5\sigma$ level. Parameter regions near $\sin(\beta-\alpha) \approx 0$ remain challenging to probe in the diphoton channel, even with increased energy or luminosity.

hep-ph↗

arXiv2024

Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition

Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a broad range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.

cs.LG↗

arXiv2023

Temporal Convolutional Explorer Helps Understand 1D-CNN's Learning Behavior in Time Series Classification from Frequency Domain

While one-dimensional convolutional neural networks (1D-CNNs) have been empirically proven effective in time series classification tasks, we find that there remain undesirable outcomes that could arise in their application, motivating us to further investigate and understand their underlying mechanisms. In this work, we propose a Temporal Convolutional Explorer (TCE) to empirically explore the learning behavior of 1D-CNNs from the perspective of the frequency domain. Our TCE analysis highlights that deeper 1D-CNNs tend to distract the focus from the low-frequency components leading to the accuracy degradation phenomenon, and the disturbing convolution is the driving factor. Then, we leverage our findings to the practical application and propose a regulatory framework, which can easily be integrated into existing 1D-CNNs. It aims to rectify the suboptimal learning behavior by enabling the network to selectively bypass the specified disturbing convolutions. Finally, through comprehensive experiments on widely-used UCR, UEA, and UCI benchmarks, we demonstrate that 1) TCE's insight into 1D-CNN's learning behavior; 2) our regulatory framework enables state-of-the-art 1D-CNNs to get improved performances with less consumption of memory and computational overhead.

cs.LG↗