arXiv subjects

Junjie Cao

Publications and source records attributed to Junjie Cao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Quantize More, Lose Less: Autoregressive Generation from Residually Quantized Speech Representations

Text-to-speech (TTS) synthesis has seen renewed progress under the discrete modeling paradigm. Existing autoregressive approaches often rely on single-codebook representations, which suffer from significant information loss. Even with post-hoc refinement techniques such as flow matching, these methods fail to recover fine-grained details (e.g., prosodic nuances, speaker-specific timbres), especially in challenging scenarios like singing voice or music synthesis. We propose QTTS, a novel TTS framework built upon our new audio codec, QDAC. The core innovation of QDAC lies in its end-to-end training of an ASR-based auto-regressive network with a GAN, which achieves superior semantic feature disentanglement for scalable, near-lossless compression. QTTS models these discrete codes using two innovative strategies: the Hierarchical Parallel architecture, which uses a dual-AR structure to model inter-codebook dependencies for higher-quality synthesis, and the Delay Multihead approach, which employs parallelized prediction with a fixed delay to accelerate inference speed. Our experiments demonstrate that the proposed framework achieves higher synthesis quality and better preserves expressive content compared to baseline. This suggests that scaling up compression via multi-codebook modeling is a promising direction for high-fidelity, general-purpose speech and audio generation.

cs.SD↗

arXiv2025

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement

Recently, stepwise supervision on Chain of Thoughts (CoTs) presents an enhancement on the logical reasoning tasks such as coding and math, with the help of Monte Carlo Tree Search (MCTS). However, its contribution to tasks requiring domain-specific expertise and knowledge remains unexplored. Motivated by the interest, we identify several potential challenges of vanilla MCTS within this context, and propose the framework of Stepwise Domain Knowledge-Driven Reasoning Optimization, employing the MCTS algorithm to develop step-level supervision for problems that require essential comprehension, reasoning, and specialized knowledge. Additionally, we also introduce the Preference Optimization towards Reflection Paths, which iteratively learns self-reflection on the reasoning thoughts from better perspectives. We have conducted extensive experiments to evaluate the advantage of the methodologies. Empirical results demonstrate the effectiveness on various legal-domain problems. We also report a diverse set of valuable findings, hoping to encourage the enthusiasm to the research of domain-specific LLMs and MCTS.

cs.AI↗

arXiv2025

PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation

Although supervised deep normal estimators have recently shown impressive results on synthetic benchmarks, their performance deteriorates significantly in real-world scenarios due to the domain gap between synthetic and real data. Building high-quality real training data to boost those supervised methods is not trivial because point-wise annotation of normals for varying-scale real-world 3D scenes is a tedious and expensive task. This paper introduces PointNorm-Net, the first self-supervised deep learning framework to tackle this challenge. The key novelty of PointNorm-Net is a three-stage multi-modal normal distribution estimation paradigm that can be integrated into either deep or traditional optimization-based normal estimation frameworks. Extensive experiments show that our method achieves superior generalization and outperforms state-of-the-art conventional and deep learning approaches across three real-world datasets that exhibit distinct characteristics compared to the synthetic training data.

cs.CV↗

arXiv2025

DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

Controllable human image animation aims to generate videos from reference images using driving videos. Due to the limited control signals provided by sparse guidance (e.g., skeleton pose), recent works have attempted to introduce additional dense conditions (e.g., depth map) to ensure motion alignment. However, such strict dense guidance impairs the quality of the generated video when the body shape of the reference character differs significantly from that of the driving video. In this paper, we present DisPose to mine more generalizable and effective control signals without additional dense input, which disentangles the sparse skeleton pose in human image animation into motion field guidance and keypoint correspondence. Specifically, we generate a dense motion field from a sparse motion field and the reference image, which provides region-level dense guidance while maintaining the generalization of the sparse pose control. We also extract diffusion features corresponding to pose keypoints from the reference image, and then these point features are transferred to the target pose to provide distinct identity information. To seamlessly integrate into existing models, we propose a plug-and-play hybrid ControlNet that improves the quality and consistency of generated videos while freezing the existing model parameters. Extensive qualitative and quantitative experiments demonstrate the superiority of DisPose compared to current methods. Project page: \href{https://github.com/lihxxx/DisPose}{https://github.com/lihxxx/DisPose}.

cs.CV↗

arXiv2024

Unified Interpretation of Muon g-2 anomaly, 95 GeV Diphoton, and $b\bar{b}$ Excesses in the General Next-to-Minimal Supersymmetric Standard Model

We investigate three intriguing anomalies within the framework of the General Next-to-Minimal Supersymmetric Standard Model. These anomalies include a significant deviation of the experimental results for the muon anomalous magnetic moment from its Standard Model prediction, with a confidence level of $5.1σ$; a joint observation by the CMS and ATLAS collaborations of a diphoton excess with a local significance of $3.1 σ$ in the invariant mass distribution around 95.4 GeV; and a reported excess in the $b\bar{b}$ production at LEP with a local significance of $2.3 σ$. Through analytical and numerical analyses, we provide unified interpretations across an extensive parameter space that remain consistent with current experimental restrictions from data on the Higgs boson at 125 GeV, B-physics measurements, dark matter observables, as well as existing searches for supersymmetry and extra Higgs bosons. We attribute the muon anomaly to loops involving muon-smuon-neutralino and muon-sneutrino-chargino interactions, while attributing the diphoton and $b \bar{b}$ excesses to the resonant production of a singlet-dominated scalar. These proposed solutions are poised for experimental tests at the high-luminosity LHC and future linear colliders.

hep-ph↗

arXiv2024

UVCG: Leveraging Temporal Consistency for Universal Video Protection

The security risks of AI-driven video editing have garnered significant attention. Although recent studies indicate that adding perturbations to images can protect them from malicious edits, directly applying image-based methods to perturb each frame in a video becomes ineffective, as video editing techniques leverage the consistency of inter-frame information to restore individually perturbed content. To address this challenge, we leverage the temporal consistency of video content to propose a straightforward and efficient, yet highly effective and broadly applicable approach, Universal Video Consistency Guard (UVCG). UVCG embeds the content of another video(target video) within a protected video by introducing continuous, imperceptible perturbations which has the ability to force the encoder of editing models to map continuous inputs to misaligned continuous outputs, thereby inhibiting the generation of videos consistent with the intended textual prompts. Additionally leveraging similarity in perturbations between adjacent frames, we improve the computational efficiency of perturbation generation by employing a perturbation-reuse strategy. We applied UVCG across various versions of Latent Diffusion Models (LDM) and assessed its effectiveness and generalizability across multiple LDM-based editing pipelines. The results confirm the effectiveness, transferability, and efficiency of our approach in safeguarding video content from unauthorized modifications.

cs.CV↗

arXiv2024

Hierarchical Search-Based Cooperative Motion Planning

Cooperative path planning, a crucial aspect of multi-agent systems research, serves a variety of sectors, including military, agriculture, and industry. Many existing algorithms, however, come with certain limitations, such as simplified kinematic models and inadequate support for multiple group scenarios. Focusing on the planning problem associated with a nonholonomic Ackermann model for Unmanned Ground Vehicles (UGV), we propose a leaderless, hierarchical Search-Based Cooperative Motion Planning (SCMP) method. The high-level utilizes a binary conflict search tree to minimize runtime, while the low-level fabricates kinematically feasible, collision-free paths that are shape-constrained. Our algorithm can adapt to scenarios featuring multiple groups with different shapes, outlier agents, and elaborate obstacles. We conduct algorithm comparisons, performance testing, simulation, and real-world testing, verifying the effectiveness and applicability of our algorithm. The implementation of our method will be open-sourced at https://github.com/WYCUniverStar/SCMP.

cs.RO↗

arXiv2024

LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model

Graph foundation models (GFMs) have recently gained significant attention. However, the unique data processing and evaluation setups employed by different studies hinder a deeper understanding of their progress. Additionally, current research tends to focus on specific subsets of graph learning tasks, such as structural tasks, node-level tasks, or classification tasks. As a result, they often incorporate specialized modules tailored to particular task types, losing their applicability to other graph learning tasks and contradicting the original intent of foundation models to be universal. Therefore, to enhance consistency, coverage, and diversity across domains, tasks, and research interests within the graph learning community in the evaluation of GFMs, we propose GFMBench-a systematic and comprehensive benchmark comprising 26 datasets. Moreover, we introduce LangGFM, a novel GFM that relies entirely on large language models. By revisiting and exploring the effective graph textualization principles, as well as repurposing successful techniques from graph augmentation and graph self-supervised learning within the language space, LangGFM achieves performance on par with or exceeding the state of the art across GFMBench, which can offer us new perspectives, experiences, and baselines to drive forward the evolution of GFMs.

cs.LG↗

arXiv2024

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks. In this study, we introduce a challenging task (confusing charge prediction) to better evaluate LLMs' understanding of legal theories and reasoning capabilities. We also propose a novel framework: Multi-Agent framework for improving complex Legal Reasoning capability (MALR). MALR employs non-parametric learning, encouraging LLMs to automatically decompose complex legal tasks and mimic human learning process to extract insights from legal rules, helping LLMs better understand legal theories and enhance their legal reasoning abilities. Extensive experiments on multiple real-world datasets demonstrate that the proposed framework effectively addresses complex reasoning issues in practical scenarios, paving the way for more reliable applications in the legal domain.

cs.AI↗

arXiv2024

Dark Matter Physics in General NMSSM

In the General Next-to-Minimal Supersymmetric Standard Model (GNMSSM), singlet particles may form a secluded sector of dark matter (DM), in which Singlino-like DM could achieve the observed relic abundance through various channels such as $\tildeχ_1^0 \tildeχ_1^0 \to h_s h_s, A_s A_s, h_s A_s$, where $h_s$ and $A_s$ represent singlet-dominated CP-even and CP-odd Higgs bosons. We provide analytical formulas for both the spin-independent and spin-dependent cross sections of Singlino DM scattering with nucleons, illustrating their dependence on the model's parameters in a clear manner. We also present analytic expressions for the annihilation cross sections of these three important channels. Based on these preparations, we conducted Bayesian analyses of the GNMSSM and concluded that the theory significantly favored Singlino-dominated DM over Bino-like DM across a much broader range of parameters. The combined results from our numerical analyses and the formulas distinctly highlight crucial aspects of DM physics within the GNMSSM.

hep-ph↗

arXiv2023

95 GeV Diphoton and $b \bar{b}$ Excesses in the General Next-to-Minimal Supersymmetric Standard Model

The CMS and ATLAS collaborations recently published their results searching for light Higgs bosons, using the complete Run 2 data of the LHC. Both reported an excess in the diphoton invariant mass distribution at $m_{γγ} \simeq 95.4~{\rm GeV}$ with compatible signal strengths. The combined result corresponded to a local significance of $3.1σ$. Besides, the mass of the diphoton signal coincided with that of the $b\bar{b}$ excess observed at the LEP. Given the remarkable theoretical advantages of the general Next-to-Minimal Supersymmetric Standard Model, we interpret these excesses by the resonant productions of the singlet-dominated CP-even Higgs boson predicted by the theory. Using both analytic formulae and numerical results, we show that the idea can interpret the excesses by broad parameter space without contradicting current experimental restrictions, including those from the 125~{\rm GeV} Higgs data, the dark matter relic abundance and direct detection experiments, and the collider searches for supersymmetry and extra Higgs bosons. Although the explanations are scarcely affected by present Higgs data and the LHC search for supersymmetry, the dark matter physics may leave footprints on them. We also survey the other signals of the light Higgs boson at the LHC.

hep-ph↗

arXiv2023

Electron and Muon Anomalous Magnetic Moment in the $\mathbb{Z}_3$-NMSSM

Inspired by the recent measurements of the muon and electron anomalous magnetic moments, the rapid progress of the LHC search for supersymmetry, and the significantly improved sensitivities of dark matter direct detection experiments, we studied the supersymmetric contribution to the electron \texorpdfstring{$g-2$}{}, $a_e^{\rm SUSY}$, in the Next-to-Minimal Supersymmetric Standard Model with a discrete $\mathbb{Z}_3$ symmetry. We concluded that $a_e^{\rm SUSY}$ was mainly correlated with $a_μ^{\rm SUSY}$ by the formula $a_e^{\rm SUSY}/m_e^2 \simeq a_μ^{\rm SUSY}/m_μ^2$, and significant violations of this correlation might occur only in rare cases. As a result, $a_e^{\rm SUSY}$ was typically around $5 \times 10^{-14}$ when $a_μ^{\rm SUSY} \simeq 2.5 \times 10^{-9}$. We also concluded that the dark matter direct detection and LHC experiments played crucial roles in determining the maximum reach of $a_e^{\rm SUSY}$. Concretely, $a_e^{\rm SUSY}$ might be around $3 \times 10^{-13}$ in the optimum cases if one used the XENON-1T experiment to limit the supersymmetry parameter space. This prediction, however, was reduced to $1.5 \times 10^{-13}$ after implementing the LZ restrictions and $1.0 \times 10^{-13}$ when further considering the LHC restrictions.

hep-ph↗

arXiv2023

DMNR: Unsupervised De-noising of Point Clouds Corrupted by Airborne Particles

LiDAR sensors are critical for autonomous driving and robotics applications due to their ability to provide accurate range measurements and their robustness to lighting conditions. However, airborne particles, such as fog, rain, snow, and dust, will degrade its performance and it is inevitable to encounter these inclement environmental conditions outdoors. It would be a straightforward approach to remove them by supervised semantic segmentation. But annotating these particles point wisely is too laborious. To address this problem and enhance the perception under inclement conditions, we develop two dynamic filtering methods called Dynamic Multi-threshold Noise Removal (DMNR) and DMNR-H by accurate analysis of the position distribution and intensity characteristics of noisy points and clean points on publicly available WADS and DENSE datasets. Both DMNR and DMNR-H outperform state-of-the-art unsupervised methods by a significant margin on the two datasets and are slightly better than supervised deep learning-based methods. Furthermore, our methods are more robust to different LiDAR sensors and airborne particles, such as snow and fog.

cs.CV↗

arXiv2023

Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention

Most of the existing audio-driven 3D facial animation methods suffered from the lack of detailed facial expression and head pose, resulting in unsatisfactory experience of human-robot interaction. In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention. To synthesize real and detailed expression, a hierarchical decomposition strategy is proposed to encode the audio signal into both a global latent feature and a local vertex-wise control feature. Then the local and global audio features combined with vertex spatial features are used to predict the final consistent facial animation via a graph convolutional neural network by fusing the intrinsic spatial topology structure of the face model and the corresponding semantic feature of the audio. To accomplish pose-controllable animation, we introduce a novel pose attribute augmentation method by utilizing the 2D talking face technique. Experimental results indicate that the proposed method can produce more realistic facial expressions and head posture movements. Qualitative and quantitative experiments show that the proposed method achieves competitive performance against state-of-the-art methods.

cs.CV↗

arXiv2023

Status of the singlino-dominated dark matter in general Next-to-Minimal Supersymmetric Standard Model

With the rapid progress of dark matter direct detection experiments, the attractiveness of the popular bino-dominated dark matter in economical supersymmetric theories is fading. As an alternative, the singlino-dominated dark matter in general Next-to-Minimal Supersymmetric Standard Model (NMSSM) is paying due attention. This scenario has the following distinct characteristics: free from the tadpole problem and the domain-wall problem of the NMSSM with a $Z_3$-symmetry, predicting more stable vacuum states than the $Z_3$-NMSSM, capable of forming an economical secluded dark matter sector to yield the dark matter experimental results naturally, and readily weaken the restrictions from the LHC search for SUSY. Consequently, it can explain the muon g-2 anomaly in broad parameter space that agrees with various experimental results while simultaneously breaking the electroweak symmetry naturally. In this study, we show in detail how the scenario coincides with the experiments, such as the SUSY search at the LHC, the dark matter search by the LZ experiment, and the improved measurement of the muon g-2. We provide a simple and clear picture of the physics inherent in the general NMSSM.

hep-ph↗

arXiv2022

Interpreting the $W$ mass anomaly in the vector-like quark models

The new measurement of $W$-boson mass by the CDF collaboration revealed a remarkable $7σ$ disagreement with the Standard Model (SM) prediction. If confirmed by other experiments, then the disagreement strongly indicates the existence of new physics beyond the SM. In this work, seven vectorlike quark (VLQ) extensions of the SM are investigated to interpret the anomaly, and it is found that three can explain the anomaly in broad parameter space. The explanations are consistent with the constraints from oblique parameters, the LHC search for VLQs, the measurements of the properties for the top quark, bottom quark, and Higgs boson, and the perturbativity criterion. The typical size of the involved Yukawa coupling is around 1, which is comparable to the top quark Yukawa coupling in the SM. The other extensions, however, either predict a negative correction to the mass in reasonable parameter space or explain the anomaly by unnatural theoretical input parameters.

hep-ph↗

arXiv2022

Impact of LHC probes of SUSY and recent measurement of $(g-2)_μ$ on $\mathbb{Z}_3$-NMSSM

It is well known that excessively heavy supersymmetric particles (sparticles) are disfavored to explain the $(g-2)_μ$ anomaly, but some people overlook that moderately light sparticles are also disfavored by the LHC probes of supersymmetry. We take the Next-to-Minimal Supersymmetric Standard Model as an example to emphasize the latter point. It is found that, if the theory is required to explain the anomaly at $2σ$ level and meanwhile keep consistent with the LHC results, the following lower bounds may be set: $\tan β\gtrsim 20$, $|M_1| \gtrsim 275~{\rm GeV}$, $M_2 \gtrsim 300~{\rm GeV}$, $μ\gtrsim 460~{\rm GeV}$, $m_{\tildeμ_L} \gtrsim 310~{\rm GeV}$, and $m_{\tildeμ_R} \gtrsim 350~{\rm GeV}$, where $M_1$ and $M_2$ denote gaugino masses, $μ$ represents the Higgsino mass, and $m_{\tildeμ_L}$ and $m_{\tildeμ_R}$ are the mass of Smuons with $L$ and $R$ denoting their dominant chiral component. This observation has significant impacts on dark matter (DM) physics, e.g., the popular $Z$- and Higgs-funnel regions have been excluded, and the Bino-dominated neutralino DM has to co-annihilate with the Wino-dominated electroweakinos (in most cases) and/or Smuons (in few cases) to obtain the correct density. It is also inferred that these conclusions should apply to the Minimal Supersymmetric Standard Model since the underlying physics for the bounds are the same.

hep-ph↗

arXiv2022

Interpreting the $W$-mass anomaly in the vectorlike quark models

hep-ph↗