arXiv subjects

Qilin Wang

Publications and source records attributed to Qilin Wang.

11 recordsLinked to original sources

arXiv2026

Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusion

LiDAR-based semantic segmentation is essential for autonomous-driving perception, yet dense point-wise annotations are costly, and long-tailed outdoor scenes make small safety-critical objects difficult to discover without supervision. Existing unsupervised methods face three key challenges: they struggle to preserve small and sparsely observed objects under substantial scale variation, have difficulty enforcing intra-region consistency and inter-region discrimination during cross-modal transfer, and lack an efficient feature-preserving mechanism for contextual propagation over superpoint graphs. We therefore propose DDS, an unsupervised 3D semantic segmentation framework. First, a coarse-to-fine multi-granularity mask cascade provides complementary 3D region cues for objects across different scales, improving the preservation of small and sparsely observed objects. Second, region-guided multi-level distillation transfers self-supervised visual knowledge through point-level alignment, mask-level prototype alignment, and prototype-level contrastive learning, enhancing intra-region consistency and inter-region discrimination. Third, restart-based graph diffusion efficiently propagates contextual information among superpoints while anchoring the refined representation to the initial distilled features and avoiding explicit graph eigendecomposition. Experiments on real-world driving datasets show that DDS outperforms representative unsupervised baselines, improving oAcc, mAcc, and mIoU by up to 2.9%, 9.7%, and 4.1%, respectively. These results demonstrate the effectiveness and transferability of DDS for unsupervised 3D scene understanding in autonomous-driving scenarios.

cs.CV↗

arXiv2026

Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation

Large language models (LLMs) have progressed rapidly in complex reasoning and question answering, yet LLM hallucination remains a central bottleneck that hinders practical deployment, especially for commercial black-box LLMs accessible only via APIs. Existing uncertainty quantification methods typically depend on computationally expensive multiple sampling or internal parameters, which prevents real-time estimation and fails to capture information implicit in the black-box reasoning process. To address this issue, we propose Distribution-Aligned Adversarial Distillation (DisAAD), which introduces a generation-discrimination architecture to guide a lightweight proxy model to learn the high-quality regions of the output distribution of the black-box LLM, thus effectively endowing it with the ability to know whether the black-box LLM knows or not. Subsequently, we use the proxy model to reproduce the specific responses of the black-box LLM and estimate the corresponding uncertainty based on evidence learning. Extensive experiments have verified the effectiveness and promise of our proposed method, indicating that a proxy model even one that only accounts for 1\% of the target LLM's size can achieve reliable uncertainty quantification.

cs.CL↗

arXiv2026

Ellipsoidal Time Series Forecasting

We argue that long-term forecasting requires learning local Jacobians with explicit spectral structure, going beyond simple conditional mean matching. Our method, Fern, invokes Brenier's theorem to directly parameterize the Jacobian as a symmetric positive semi-definite (SPD) factorization, treating forecasting as the optimal transport of probability mass from a fixed Gaussian source to data-dependent ellipsoids. This formulation reduces the computational cost of eigendecomposition from cubic to linear time while providing interpretable, geometry-aware projections. To rigorously evaluate robustness, we introduce a synthetic benchmark with controlled non-stationary shocks alongside new metrics like Effective Prediction Time (EPT). Fern demonstrates exceptional stability, outperforming baselines like DLinear and Koopa by over two orders of magnitude (up to 790x) on nonstationary settings where standard benchmarks fail to expose model brittleness.

cs.LG↗

arXiv2026

Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting

Modern time series forecasting is evaluated almost entirely through passive observation of single historical trajectories, rendering claims about a model's robustness to non-stationarity fundamentally unfalsifiable. We propose a paradigm shift toward interventionist, exact-statistical benchmarking. By systematically titrating calibrated Gaussian observation noise into known chaotic and stochastic dynamical systems, we transform forecasting from a black-box sequence matching game into an exact distributional inference task. Because the underlying data-generating process and noise variance are mathematically explicit, evaluation can rely on exact negative log-likelihoods and calibrated distributional tests rather than heuristic approximations. To fully leverage this framework, we extend the Fern architecture into a probabilistic generative model that natively parameterizes the Symmetric Positive Definite (SPD) cone, outputting calibrated joint covariance structures without the computational bottleneck of generic Jacobian modeling. Under this rigorous evaluation, we find that state-of-the-art zero-shot foundation models behave consistently with the context-parroting mechanism, failing systematically under non-stationary regime shifts and elevated noise. In contrast, Fern explicitly captures the invariant measure and multivariate geometry of the underlying dynamics, maintaining structural fidelity and statistically sharp calibration precisely where massive sequence-matching models collapse.

cs.LG↗

arXiv2024

ArtWeaver: Advanced Dynamic Style Integration via Diffusion Model

Stylized Text-to-Image Generation (STIG) aims to generate images from text prompts and style reference images. In this paper, we present ArtWeaver, a novel framework that leverages pretrained Stable Diffusion (SD) to address challenges such as misinterpreted styles and inconsistent semantics. Our approach introduces two innovative modules: the mixed style descriptor and the dynamic attention adapter. The mixed style descriptor enhances SD by combining content-aware and frequency-disentangled embeddings from CLIP with additional sources that capture global statistics and textual information, thus providing a richer blend of style-related and semantic-related knowledge. To achieve a better balance between adapter capacity and semantic control, the dynamic attention adapter is integrated into the diffusion UNet, dynamically calculating adaptation weights based on the style descriptors. Additionally, we introduce two objective functions to optimize the model alongside the denoising loss, further enhancing semantic and style consistency. Extensive experiments demonstrate the superiority of ArtWeaver over existing methods, producing images with diverse target styles while maintaining the semantic integrity of the text prompts.

cs.CV↗

arXiv2024

MDT-A2G: Exploring Masked Diffusion Transformers for Co-Speech Gesture Generation

Recent advancements in the field of Diffusion Transformers have substantially improved the generation of high-quality 2D images, 3D videos, and 3D shapes. However, the effectiveness of the Transformer architecture in the domain of co-speech gesture generation remains relatively unexplored, as prior methodologies have predominantly employed the Convolutional Neural Network (CNNs) or simple a few transformer layers. In an attempt to bridge this research gap, we introduce a novel Masked Diffusion Transformer for co-speech gesture generation, referred to as MDT-A2G, which directly implements the denoising process on gesture sequences. To enhance the contextual reasoning capability of temporally aligned speech-driven gestures, we incorporate a novel Masked Diffusion Transformer. This model employs a mask modeling scheme specifically designed to strengthen temporal relation learning among sequence gestures, thereby expediting the learning process and leading to coherent and realistic motions. Apart from audio, Our MDT-A2G model also integrates multi-modal information, encompassing text, emotion, and identity. Furthermore, we propose an efficient inference strategy that diminishes the denoising computation by leveraging previously calculated results, thereby achieving a speedup with negligible performance degradation. Experimental results demonstrate that MDT-A2G excels in gesture generation, boasting a learning speed that is over 6$\times$ faster than traditional diffusion transformers and an inference speed that is 5.7$\times$ than the standard diffusion model.

cs.CV↗

arXiv2024

VividPose: Advancing Stable Video Diffusion for Realistic Human Image Animation

Human image animation involves generating a video from a static image by following a specified pose sequence. Current approaches typically adopt a multi-stage pipeline that separately learns appearance and motion, which often leads to appearance degradation and temporal inconsistencies. To address these issues, we propose VividPose, an innovative end-to-end pipeline based on Stable Video Diffusion (SVD) that ensures superior temporal stability. To enhance the retention of human identity, we propose an identity-aware appearance controller that integrates additional facial information without compromising other appearance details such as clothing texture and background. This approach ensures that the generated videos maintain high fidelity to the identity of human subject, preserving key facial features across various poses. To accommodate diverse human body shapes and hand movements, we introduce a geometry-aware pose controller that utilizes both dense rendering maps from SMPL-X and sparse skeleton maps. This enables accurate alignment of pose and shape in the generated videos, providing a robust framework capable of handling a wide range of body shapes and dynamic hand movements. Extensive qualitative and quantitative experiments on the UBCFashion and TikTok benchmarks demonstrate that our method achieves state-of-the-art performance. Furthermore, VividPose exhibits superior generalization capabilities on our proposed in-the-wild dataset. Codes and models will be available.

cs.CV↗

arXiv2024

DiffFAE: Advancing High-fidelity One-shot Facial Appearance Editing with Space-sensitive Customization and Semantic Preservation

Facial Appearance Editing (FAE) aims to modify physical attributes, such as pose, expression and lighting, of human facial images while preserving attributes like identity and background, showing great importance in photograph. In spite of the great progress in this area, current researches generally meet three challenges: low generation fidelity, poor attribute preservation, and inefficient inference. To overcome above challenges, this paper presents DiffFAE, a one-stage and highly-efficient diffusion-based framework tailored for high-fidelity FAE. For high-fidelity query attributes transfer, we adopt Space-sensitive Physical Customization (SPC), which ensures the fidelity and generalization ability by utilizing rendering texture derived from 3D Morphable Model (3DMM). In order to preserve source attributes, we introduce the Region-responsive Semantic Composition (RSC). This module is guided to learn decoupled source-regarding features, thereby better preserving the identity and alleviating artifacts from non-facial attributes such as hair, clothes, and background. We further introduce a consistency regularization for our pipeline to enhance editing controllability by leveraging prior knowledge in the attention matrices of diffusion model. Extensive experiments demonstrate the superiority of DiffFAE over existing methods, achieving state-of-the-art performance in facial appearance editing.

cs.CV↗

arXiv2023

Entanglement Dynamics of Two V-type Atoms with Dipole-Dipole Interaction in Dissipative Cavity

In this work, we study a coupled system of two V-type atoms with dipole-dipole interaction in a dissipative single-mode cavity, which couples with an external environment. We obtain the analytical solution of this model by solving the time dependent Schrodinger equation after we diagonalize Hamiltonian of dissipative cavity by introducing a set of new creation and annihilation operators according to Fano theorem. We also detailedly discuss the influences of cavity-environment coupling, spontaneously generated interference (SGI) parameter and dipole-dipole interaction between two atoms on entanglement dynamics under different initial states. The results show that the SGI parameter has different effects on entanglement dynamics under different initial states. Namely, the SGI parameter will increase the decay rate of the initially maximal entangled state and reduce that of the initially partial entangled state. For the initially product state, the larger SGI parameter corresponds to the more entanglement generated. The entanglement monotonically decreases under the weak cavity-environment coupling, while the oscillation of entanglement will occur under the strong cavity-environment coupling. The larger the dipole-dipole interaction is, the slower the entanglement decays and the more the entanglement will be generated. So the dipole-dipole interaction can not only protect and generate entanglement very effectively, but also enhance the regulation effect of the SGI parameter on entanglement.

quant-ph↗

arXiv2023

Modulating quantum evolution of moving-qubit by using classical driving

In this work, we study quantum evolution of an open moving-qubit modulated by a classical driving field. We obtain the density operator of qubit at zero temperature and analyze its quantum evolution dynamics by using quantum speed limit time (QSLT) and a non-Markovianity measure introduced recently. The results show that both the non-Markovian environment and the classical driving can speed up the evolution process, this quantum speedup process is induced by the non-Markovianity and the critical points only depend on the qubit velocity. Moreover, the qubit motion will delay the evolution process, but this negative effect of the qubit velocity on the quantum speedup can be suppressed by the classical driving. Finally, we give the corresponding physical explanation by using the decoherence rates.

quant-ph↗

arXiv2022

Entanglement dynamics of an open moving-biparticle system driven by classical-field

In this work, the entanglement dynamics of a moving-biparticle system driven by an external classical field are investigated, where the moving-biparticle system is coupled with a zero temperature common environment. The analytical expressions of the density operator and the entanglement can be obtained by using the dressed-state basis when the total excitation number is one. We also discuss in detail the effects of different parameters on the entanglement dynamics. The results show that the classical driving can not only protect the entanglement, but also effectively eliminate the influence of the qubit velocity and the detuning on the quantum entanglement.

quant-ph↗