arXiv subjects

Yong Zhang

Publications and source records attributed to Yong Zhang.

At least 271 records · Page 15Linked to original sources

arXiv2024

A Combination Model for Time Series Prediction using LSTM via Extracting Dynamic Features Based on Spatial Smoothing and Sequential General Variational Mode Decomposition

In order to solve the problems such as difficult to extract effective features and low accuracy of sales volume prediction caused by complex relationships such as market sales volume in time series prediction, we proposed a time series prediction method of market sales volume based on Sequential General VMD and spatial smoothing Long short-term memory neural network (SS-LSTM) combination model. Firstly, the spatial smoothing algorithm is used to decompose and calculate the sample data of related industry sectors affected by the linkage effect of market sectors, extracting modal features containing information via Sequential General VMD on overall market and specific price trends; Then, according to the background of different Market data sets, LSTM network is used to model and predict the price of fundamental data and modal characteristics. The experimental results of data prediction with seasonal and periodic trends show that this method can achieve higher price prediction accuracy and more accurate accuracy in specific market contexts compared to traditional prediction methods Describe the changes in market sales volume.

eess.SP↗

arXiv2024

ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation

Video generation has made remarkable progress in recent years, especially since the advent of the video diffusion models. Many video generation models can produce plausible synthetic videos, e.g., Stable Video Diffusion (SVD). However, most video models can only generate low frame rate videos due to the limited GPU memory as well as the difficulty of modeling a large set of frames. The training videos are always uniformly sampled at a specified interval for temporal compression. Previous methods promote the frame rate by either training a video interpolation model in pixel space as a postprocessing stage or training an interpolation model in latent space for a specific base video model. In this paper, we propose a training-free video interpolation method for generative video diffusion models, which is generalizable to different models in a plug-and-play manner. We investigate the non-linearity in the feature space of video diffusion models and transform a video model into a self-cascaded video diffusion model with incorporating the designed hidden state correction modules. The self-cascaded architecture and the correction module are proposed to retain the temporal consistency between key frames and the interpolated frames. Extensive evaluations are preformed on multiple popular video models to demonstrate the effectiveness of the propose method, especially that our training-free method is even comparable to trained interpolation models supported by huge compute resources and large-scale datasets.

cs.CV↗

arXiv2024

Reasoning3D -- Grounding and Reasoning in 3D: Fine-Grained Zero-Shot Open-Vocabulary 3D Reasoning Part Segmentation via Large Vision-Language Models

In this paper, we introduce a new task: Zero-Shot 3D Reasoning Segmentation for parts searching and localization for objects, which is a new paradigm to 3D segmentation that transcends limitations for previous category-specific 3D semantic segmentation, 3D instance segmentation, and open-vocabulary 3D segmentation. We design a simple baseline method, Reasoning3D, with the capability to understand and execute complex commands for (fine-grained) segmenting specific parts for 3D meshes with contextual awareness and reasoned answers for interactive segmentation. Specifically, Reasoning3D leverages an off-the-shelf pre-trained 2D segmentation network, powered by Large Language Models (LLMs), to interpret user input queries in a zero-shot manner. Previous research have shown that extensive pre-training endows foundation models with prior world knowledge, enabling them to comprehend complex commands, a capability we can harness to "segment anything" in 3D with limited 3D datasets (source efficient). Experimentation reveals that our approach is generalizable and can effectively localize and highlight parts of 3D objects (in 3D mesh) based on implicit textual queries, including these articulated 3d objects and real-world scanned data. Our method can also generate natural language explanations corresponding to these 3D models and the decomposition. Moreover, our training-free approach allows rapid deployment and serves as a viable universal baseline for future research of part-level 3d (semantic) object understanding in various fields including robotics, object manipulation, part assembly, autonomous driving applications, augment reality and virtual reality (AR/VR), and medical applications. The code, the model weight, the deployment guide, and the evaluation protocol are: http://tianrun-chen.github.io/Reason3D/

cs.CV↗

arXiv2024

One-loop Bern-Carrasco-Johansson Numerators on Quadratic Propagators from the Worldsheet

We introduce a novel approach for deriving one-loop Bern-Carrasco-Johansson (BCJ) numerators and reveal the worldsheet origin of the one-loop double copy. Our work shows that expanding Cachazo-He-Yuan half-integrands into generalized Parke-Taylor factors intrinsically generates BCJ numerators on quadratic propagators satisfying Jacobi identities. We validate our methodology by successfully reproducing one-loop BCJ numerators for Non-Linear Sigma Model as well as those of pure Yang-Mills theory in four dimensions with all-plus or single-minus helicities.

hep-th↗

arXiv2024

Enhancing Emotion Recognition in Conversation through Emotional Cross-Modal Fusion and Inter-class Contrastive Learning

The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the information differences between modalities, resulting in the model being unable to focus on modality-specific emotional information. At the same time, the shared information between modalities was not processed to generate emotions. Information redundancy problem. To overcome these limitations, we propose a cross-modal fusion emotion prediction network based on vector connections. The network mainly includes two stages: the multi-modal feature fusion stage based on connection vectors and the emotion classification stage based on fused features. Furthermore, we design a supervised inter-class contrastive learning module based on emotion labels. Experimental results confirm the effectiveness of the proposed method, demonstrating excellent performance on the IEMOCAP and MELD datasets.

cs.CL↗

arXiv2024

ToonCrafter: Generative Cartoon Interpolation

We introduce ToonCrafter, a novel approach that transcends traditional correspondence-based cartoon video interpolation, paving the way for generative interpolation. Traditional methods, that implicitly assume linear motion and the absence of complicated phenomena like dis-occlusion, often struggle with the exaggerated non-linear and large motions with occlusion commonly found in cartoons, resulting in implausible or even failed interpolation results. To overcome these limitations, we explore the potential of adapting live-action video priors to better suit cartoon interpolation within a generative framework. ToonCrafter effectively addresses the challenges faced when applying live-action video motion priors to generative cartoon interpolation. First, we design a toon rectification learning strategy that seamlessly adapts live-action video priors to the cartoon domain, resolving the domain gap and content leakage issues. Next, we introduce a dual-reference-based 3D decoder to compensate for lost details due to the highly compressed latent prior spaces, ensuring the preservation of fine details in interpolation results. Finally, we design a flexible sketch encoder that empowers users with interactive control over the interpolation results. Experimental results demonstrate that our proposed method not only produces visually convincing and more natural dynamics, but also effectively handles dis-occlusion. The comparative evaluation demonstrates the notable superiority of our approach over existing competitors.

cs.CV↗

arXiv2024

Gain-loss-engineering: a new platform for extreme anisotropic thermal photon tunneling

We explore a novel approach to achieving anisotropic thermal photon tunneling, inspired by the concept of parity-time symmetry in quantum physics. Our method leverages the modulation of constitutive optical parameters, oscillating between loss and gain regimes. This modulation reveals a variety of distinct effects in thermal photon behavior and dispersion. Specifically, we identify complex tunneling modes through gain-loss engineering, which include thermal photonic defect states and Fermi-arc-like phenomena, which surpass those achievable through traditional polariton engineering. Our research also elucidates the laws governing the evolution of radiative energy in the presence of gain and loss interactions, and highlights the unexpected inefficacy of gain in enhancing thermal photon energy transport compared to systems characterized solely by loss. This study not only broadens our understanding of thermal photon tunneling but also establishes a versatile platform for manipulating photon energy transport, with potential applications in thermal management, heat science, and the development of advanced energy devices.

cond-mat.mtrl-sci↗

arXiv2024

Environment Sensing-aided Beam Prediction with Transfer Learning for Smart Factory

In this paper, we propose an environment sensing-aided beam prediction model for smart factory that can be transferred from given environments to a new environment. In particular, we first design a pre-training model that predicts the optimal beam by sensing the present environmental information. When encountering a new environment, it generally requires collecting a large amount of new training data to retrain the model, whose cost severely impedes the application of the designed pre-training model. Therefore, we next design a transfer learning strategy that fine-tunes the pre-trained model by limited labeled data of the new environment. Simulation results show that when the pre-trained model is fine-tuned by 30\% of labeled data from the new environment, the Top-10 beam prediction accuracy reaches 94\%. Moreover, compared with the way to completely re-training the prediction model, the amount of training data and the time cost of the proposed transfer learning strategy reduce 70\% and 75\% respectively.

eess.SP↗

arXiv2024

Phase-field analysis for brittle fracture in ferroelectric materials with flexoelectric effect

Understanding the nature of brittle failure in ferroelectric materials is essential, but difficult due to the complex interaction between mechanical and electrical concentrated fields near the crack tip. In this work, an extended phase-field model incorporating multiple order parameters is constructed to analyze the coupled evolution of fracture and domain behavior in ferroelectric materials. The strain gradient is incorporated into the governing equations to evaluate the impact of the flexoelectric effect during the crack propagation process. Our advanced phase-field model demonstrated that, with the consideration of the flexoelectric effect, both the crack extension rate and crack path are related to the initial polarization direction. This phenomenon is associated with the eigenstrain induced by the flexoelectric effect. This study provides in-depth insight into the fracture behavior of ferroelectric materials. The developed model framework can also be employed to investigate electromechanical coupling failures in more complex ferroelectric structures.

cond-mat.mtrl-sci↗

arXiv2024

Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level

Scientific document summarization has been a challenging task due to the long structure of the input text. The long input hinders the simultaneous effective modeling of both global high-order relations between sentences and local intra-sentence relations which is the most critical step in extractive summarization. However, existing methods mostly focus on one type of relation, neglecting the simultaneous effective modeling of both relations, which can lead to insufficient learning of semantic representations. In this paper, we propose HAESum, a novel approach utilizing graph neural networks to locally and globally model documents based on their hierarchical discourse structure. First, intra-sentence relations are learned using a local heterogeneous graph. Subsequently, a novel hypergraph self-attention layer is introduced to further enhance the characterization of high-order inter-sentence relations. We validate our approach on two benchmark datasets, and the experimental results demonstrate the effectiveness of HAESum and the importance of considering hierarchical structures in modeling long scientific documents. Our code will be available at \url{https://github.com/MoLICHENXI/HAESum}

cs.CL↗

arXiv2024

Overdetermined elliptic problems in nontrivial exterior domains of the hyperbolic space

We construct nontrivial unbounded domains $Ω$ in the hyperbolic space $\mathbb{H}^N$, $N \in \{2,3,4\}$, bifurcating from the complement of a ball, such that the overdetermined elliptic problem \begin{equation} -Δ_{\mathbb{H}^N} u+u-u^p=0\,\, \text{in}\,\,Ω, \,\, u=0,\,\,\partial_νu=\text{const}\,\,\text{on}\,\,\partialΩ\nonumber \end{equation} has a positive bounded solution in $C^{2,α}\left(Ω\right) \cap H^1\left(Ω\right)$. We also give a condition under which this construction holds for larger dimensions $N$. This is linked to the Berestycki-Caffarelli-Nirenberg conjecture on overdetermined elliptic problems, and, as far as we know, is the first nontrivial example of solution to an overdetermined elliptic problem in the hyperbolic space.

math.AP↗

arXiv2024

Basis decompositions of genus-one string integrals

One-loop scattering amplitudes in string theories involve configuration-space integrals over genus-one surfaces with coefficients of Kronecker-Eisenstein series in the integrand. A conjectural genus-one basis of integrands under Fay identities and integration by parts was recently constructed out of chains of Kronecker-Eisenstein series. In this work, we decompose a variety of more general genus-one integrands into the conjectural chain basis. The explicit form of the expansion coefficients is worked out for infinite families of cases where the Kronecker-Eisenstein series form cycles. Our results can be used to simplify multiparticle amplitudes in supersymmetric, heterotic and bosonic string theories and to investigate loop-level echoes of the field-theory double-copy structures of string tree-level amplitudes. The multitude of basis reductions in this work strongly validate the recently proposed chain basis and stimulate mathematical follow-up studies of more general configuration-space integrals with additional marked points or at higher genus.

hep-th↗

arXiv2024

In-plane magnetic field driven conductance modulations in topological insulator kinks

We present low-temperature magnetoconductance measurements on Bi$_{1.5}$Sb$_{0.5}$Te$_{1.8}$Se$_{1.2}$ kinks with ribbon-shaped legs. The conductance displays a clear dependence on the in-plane magnetic field orientation. The conductance modulation is consistent with orbital effect-driven trapping of the topological surface states on different side facets of the legs of the kink, which affects their transmission across the kink. This magnetic field-driven trapping and conductance pattern can be explained with a semiclassical picture and is supported by quantum transport simulations. The interpretation is corroborated by varying the angle of the kink and analyzing the temperature dependence of the observed magnetoconductance pattern, indicating the importance of phase coherence along the cross section perimeter of the kink legs.

cond-mat.mes-hall↗

arXiv2024

EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted bottleneck features which can not achieve sufficient information disentangling, while pitch and rhythm may still be mixed together. There is a risk of information overlap in the disentangling process which results in less speech naturalness. To overcome such limits, we propose a two-stage model to disentangle speech representations in a self-supervised manner without a human-crafted bottleneck design, which uses the Mutual Information (MI) with the designed upper bound estimator (IFUB) to separate overlapping information between speech components. Moreover, we design a Joint Text-Guided Consistent (TGC) module to guide the extraction of speech content and eliminate timbre leakage issues. Experiments show that our model can achieve a better performance than the baseline, regarding disentanglement effectiveness, speech naturalness, and similarity. Audio samples can be found at https://largeaudiomodel.com/eadvc.

cs.SD↗

arXiv2024

QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering

Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Query Latent Semantic Calibrator (QLSC)'', designed as an auxiliary module for existing MRC models. We propose a unique scaling strategy to capture latent semantic center features of queries. These features are then seamlessly integrated into traditional query and passage embeddings using an attention mechanism. By deepening the comprehension of the semantic queries-passage relationship, our approach diminishes sensitivity to variations in text format and boosts the model's capability in pinpointing accurate answers. Experimental results on robust Question-Answer datasets confirm that our approach effectively handles format-variant but semantically identical queries, highlighting the effectiveness and adaptability of our proposed method.

cs.CL↗

arXiv2024

A general multi-wave quasi-resonance theory for lattice energy diffusion

In this letter, a multi-wave quasi-resonance framework is established to analyze energy diffusion in classical lattices, uncovering that it is fundamentally determined by the characteristics of eigenmodes. Namely, based on the presence and the absence of extended modes, lattices fall into two universality classes with qualitatively different thermalization behavior. In particular, we find that while the one with extended modes can be thermalized under arbitrarily weak perturbations in the thermodynamic limit, the other class can be thermalized only when perturbations exceed a certain threshold, revealing for the first time the possibility that a lattice cannot be thermalized, violating the hypothesis of statistical mechanics. Our study addresses conclusively the renowned Fermi-Pasta-Ulam-Tsingou problem for large systems under weak perturbations, underscoring the pivotal roles of both extended and localized modes in facilitating energy diffusion and thermalization processes.

cond-mat.stat-mech↗

arXiv2024

Fast Gradient Computation for Gromov-Wasserstein Distance

The Gromov-Wasserstein distance is a notable extension of optimal transport. In contrast to the classic Wasserstein distance, it solves a quadratic assignment problem that minimizes the pair-wise distance distortion under the transportation of distributions and thus could apply to distributions in different spaces. These properties make Gromov-Wasserstein widely applicable to many fields, such as computer graphics and machine learning. However, the computation of the Gromov-Wasserstein distance and transport plan is expensive. The well-known Entropic Gromov-Wasserstein approach has a cubic complexity since the matrix multiplication operations need to be repeated in computing the gradient of Gromov-Wasserstein loss. This becomes a key bottleneck of the method. Currently, existing methods accelerate the computation focus on sampling and approximation, which leads to low accuracy or incomplete transport plan. In this work, we propose a novel method to accelerate accurate gradient computation by dynamic programming techniques, reducing the complexity from cubic to quadratic. In this way, the original computational bottleneck is broken and the new entropic solution can be obtained with total quadratic time, which is almost optimal complexity. Furthermore, it can be extended to some variants easily. Extensive experiments validate the efficiency and effectiveness of our method.

cs.LG↗

arXiv2024

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

In the realm of Large Language Models (LLMs), the balance between instruction data quality and quantity is a focal point. Recognizing this, we introduce a self-guided methodology for LLMs to autonomously discern and select cherry samples from open-source datasets, effectively minimizing manual curation and potential cost for instruction tuning an LLM. Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability. Through the application of IFD, cherry samples can be pinpointed, leading to a marked uptick in model training efficiency. Empirical validations on datasets like Alpaca and WizardLM underpin our findings; with a mere $10\%$ of original data input, our strategy showcases improved results. This synthesis of self-guided cherry-picking and the IFD metric signifies a transformative leap in the instruction tuning of LLMs, promising both efficiency and resource-conscious advancements. Codes, data, and models are available: https://github.com/tianyi-lab/Cherry_LLM

cs.CL↗