arXiv subjects

Di Zhang

Publications and source records attributed to Di Zhang.

At least 235 records · Page 13Linked to original sources

arXiv2024

Dynamic Pricing based Near-Optimal Resource Allocation for Elastic Edge Offloading

In mobile edge computing (MEC), task offloading can significantly reduce task execution latency and energy consumption of end user (EU). However, edge server (ES) resources are limited, necessitating efficient allocation to ensure the sustainable and healthy development for MEC systems. In this paper, we propose a dynamic pricing mechanism based near-optimal resource allocation for elastic edge offloading. First, we construct a resource pricing model and accordingly develop the utility functions for both EU and ES, the optimal pricing model parameters are derived by optimizing the utility functions. In the meantime, our theoretical analysis reveals that the EU's utility function reaches a local maximum within the search range, but exhibits barely growth with increased resource allocation beyond this point. To this end, we further propose the Dynamic Inertia and Speed-Constrained particle swarm optimization (DISC-PSO) algorithm, which efficiently identifies the near-optimal resource allocation. Comprehensive simulation results validate the effectiveness of DISC-PSO, demonstrating that it significantly outperforms existing schemes by reducing the average number of iterations to reach a near-optimal solution by 92.11\%, increasing the final user utility function value by 0.24\%, and decreasing the variance of results by 95.45\%.

cs.NI↗

arXiv2024

Renormalization Group Equations for the Dimension-7 SMEFT Operators

In this talk, a Green's basis and a new physical basis for dimension-seven (dim-7) operators in the Standard Model effective field theory (SMEFT) are proposed. The reduction relations between those two bases are also presented, where some redundant dim-6 operators in the Green's basis are involved if the dim-5 operator exists. Taking advantage of these two bases for dim-7 operators and the associated reduction relations, we work out the complete one-loop renormalization group equations (RGEs) for dim-5 and dim-7 operators up to $\mathcal{O} \left( Λ^{-3} \right)$ in the SMEFT, including not only the mixing among the same dimensional operators but also that among different dimensional ones. These results can be exploited to study full one-loop RG effects on some lepton- or baryon-number-violating processes up to $\mathcal{O} \left( Λ^{-3} \right)$ in the SMEFT, such as neutrino masses, neutrinoless double beta decay, meson and nucleon decays.

hep-ph↗

arXiv2024

A General Framework for Optimizing and Learning Nash Equilibrium

One key in real-life Nash equilibrium applications is to calibrate players' cost functions. To leverage the approximation ability of neural networks, we proposed a general framework for optimizing and learning Nash equilibrium using neural networks to estimate players' cost functions. Depending on the availability of data, we propose two approaches (a) the two-stage approach: we need the data pair of players' strategy and relevant function value to first learn the players' cost functions by monotonic neural networks or graph neural networks, and then solve the Nash equilibrium with the learned neural networks; (b) the joint approach: we use the data of partial true observation of the equilibrium and contextual information (e.g., weather) to optimize and learn Nash equilibrium simultaneously. The problem is formulated as an optimization problem with equilibrium constraints and solved using a modified Backpropagation Algorithm. The proposed methods are validated in numerical experiments.

cs.GT↗

arXiv2024

ViMo: Generating Motions from Casual Videos

Although humans have the innate ability to imagine multiple possible actions from videos, it remains an extraordinary challenge for computers due to the intricate camera movements and montages. Most existing motion generation methods predominantly rely on manually collected motion datasets, usually tediously sourced from motion capture (Mocap) systems or Multi-View cameras, unavoidably resulting in a limited size that severely undermines their generalizability. Inspired by recent advance of diffusion models, we probe a simple and effective way to capture motions from videos and propose a novel Video-to-Motion-Generation framework (ViMo) which could leverage the immense trove of untapped video content to produce abundant and diverse 3D human motions. Distinct from prior work, our videos could be more causal, including complicated camera movements and occlusions. Striking experimental results demonstrate the proposed model could generate natural motions even for videos where rapid movements, varying perspectives, or frequent occlusions might exist. We also show this work could enable three important downstream applications, such as generating dancing motions according to arbitrary music and source video style. Extensive experimental results prove that our model offers an effective and scalable way to generate diversity and realistic motions. Code and demos will be public soon.

cs.CV↗

arXiv2024

Polarization entanglement enabled by orthogonally stacked van der Waals NbOCl2 crystals

Polarization entanglement holds significant importance for photonic quantum technologies. Recently emerging subwavelength nonlinear quantum light sources, e.g., GaP and LiNbO3 thin films, benefiting from the relaxed phase-matching constraints and volume confinement, has shown intriguing properties, such as high-dimensional hyperentanglement and robust entanglement anti-degradation. Van der Waals (vdW) NbOCl2 crystal, renowned for its superior optical nonlinearities, has emerged as one of ideal candidates for ultrathin quantum light sources [Nature 613, 53 (2023)]. However, polarization-entanglement is inaccessible in NbOCl2 crystal due to its unfavorable nonlinear susceptibility tensor. Here, by leveraging the twist-stacking degree of freedom inherently in vdW systems, we showcase the preparation of tunable polarization entanglement and quantum Bell states. Our work not only provides a new and tunable polarization-entangled vdW photon-pair source, but also introduces a new knob in engineering the entanglement state of quantum light at the nanoscale.

physics.optics↗

arXiv2024

CMOS-Compatible Ultrathin Superconducting NbN Thin Films Deposited by Reactive Ion Sputtering on 300 mm Si Wafer

We report a milestone in achieving large-scale, ultrathin (~5 nm) superconducting NbN thin films on 300 mm Si wafers using a high-volume manufacturing (HVM) industrial physical vapor deposition (PVD) system. The NbN thin films possess remarkable structural uniformity and consistently high superconducting quality across the entire 300 mm Si wafer, by incorporating an AlN buffer layer. High-resolution X-ray diffraction and transmission electron microscopy analyses unveiled enhanced crystallinity of (111)-oriented δ-phase NbN with the AlN buffer layer. Notably, NbN films deposited on AlN-buffered Si substrates exhibited a significantly elevated superconducting critical temperature (~2 K higher for the 10 nm NbN) and a higher upper critical magnetic field or Hc2 (34.06 T boost in Hc2 for the 50 nm NbN) in comparison with those without AlN. These findings present a promising pathway for the integration of quantum-grade superconducting NbN films with the existing 300 mm CMOS Si platform for quantum information applications.

cond-mat.supr-con↗

arXiv2024

The Economic Analysis of the Common Pool Method through the HARA Utility Functions

Water market is a contemporary marketplace for water trading and is deemed to one of the most efficient instruments to improve the social welfare. In modern water markets, the two widely used trading systems are an improved pair-wise trading, and a 'smart market' or common pool method. In comparison with the economic model, this paper constructs a conceptual mathematic model through the HARA utility functions. Mirroring the concepts such as Nash Equilibrium, Pareto optimal and stable matching in economy, three significant propositions are acquired which illustrate the advantages of the common pool method compared with the improved pair-wise trading.

econ.GN↗

arXiv2024

The Stochastic Conjugate Subgradient Algorithm For Kernel Support Vector Machines

Stochastic First-Order (SFO) methods have been a cornerstone in addressing a broad spectrum of modern machine learning (ML) challenges. However, their efficacy is increasingly questioned, especially in large-scale applications where empirical evidence indicates potential performance limitations. In response, this paper proposes an innovative method specifically designed for kernel support vector machines (SVMs). This method not only achieves faster convergence per iteration but also exhibits enhanced scalability when compared to conventional SFO techniques. Diverging from traditional sample average approximation strategies that typically frame kernel SVM as an 'all-in-one' Quadratic Program (QP), our approach adopts adaptive sampling. This strategy incrementally refines approximation accuracy on an 'as-needed' basis. Crucially, this approach also inspires a decomposition-based algorithm, effectively decomposing parameter selection from error estimation, with the latter being independently determined for each data point. To exploit the quadratic nature of the kernel matrix, we introduce a stochastic conjugate subgradient method. This method preserves many benefits of first-order approaches while adeptly handling both nonlinearity and non-smooth aspects of the SVM problem. Thus, it extends beyond the capabilities of standard SFO algorithms for non-smooth convex optimization. The convergence rate of this novel method is thoroughly analyzed within this paper. Our experimental results demonstrate that the proposed algorithm not only maintains but potentially exceeds the scalability of SFO methods. Moreover, it significantly enhances both speed and accuracy of the optimization process.

cs.LG↗

arXiv2024

PlacidDreamer: Advancing Harmony in Text-to-3D Generation

Recently, text-to-3D generation has attracted significant attention, resulting in notable performance enhancements. Previous methods utilize end-to-end 3D generation models to initialize 3D Gaussians, multi-view diffusion models to enforce multi-view consistency, and text-to-image diffusion models to refine details with score distillation algorithms. However, these methods exhibit two limitations. Firstly, they encounter conflicts in generation directions since different models aim to produce diverse 3D assets. Secondly, the issue of over-saturation in score distillation has not been thoroughly investigated and solved. To address these limitations, we propose PlacidDreamer, a text-to-3D framework that harmonizes initialization, multi-view generation, and text-conditioned generation with a single multi-view diffusion model, while simultaneously employing a novel score distillation algorithm to achieve balanced saturation. To unify the generation direction, we introduce the Latent-Plane module, a training-friendly plug-in extension that enables multi-view diffusion models to provide fast geometry reconstruction for initialization and enhanced multi-view images to personalize the text-to-image diffusion model. To address the over-saturation problem, we propose to view score distillation as a multi-objective optimization problem and introduce the Balanced Score Distillation algorithm, which offers a Pareto Optimal solution that achieves both rich details and balanced saturation. Extensive experiments validate the outstanding capabilities of our PlacidDreamer. The code is available at \url{https://github.com/HansenHuang0823/PlacidDreamer}.

cs.CV↗

arXiv2024

EVLM: An Efficient Vision-Language Model for Visual Understanding

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside textual tokens. However, when dealing with long sequences of visual signals or inputs such as videos, the self-attention mechanism of language models can lead to significant computational overhead. Additionally, using single-layer ViT features makes it challenging for large language models to perceive visual signals fully. This paper proposes an efficient multi-modal language model to minimize computational costs while enabling the model to perceive visual signals as comprehensively as possible. Our method primarily includes: (1) employing cross-attention to image-text interaction similar to Flamingo. (2) utilize hierarchical ViT features. (3) introduce the Mixture of Experts (MoE) mechanism to enhance model effectiveness. Our model achieves competitive scores on public multi-modal benchmarks and performs well in tasks such as image captioning and video captioning.

cs.CV↗

arXiv2024

Robust Precoding Designs for Multiuser MIMO Systems with Limited Feedback

It has been well known that the achievable rate of multiuser multiple-input multiple-output systems with limited feedback is severely degraded by quantization errors when the number of feedback bits is not sufficient. To overcome such a rate degradation, we propose new robust precoding designs which can compensate for the quantization errors. In this paper, we first analyze the achievable rate of traditional precoding designs for limited feedback systems. Then, we obtain an approximation of the second-order statistics of quantized channel state information. With the aid of the derived approximation, we propose robust precoding designs in terms of the mean square error (MSE) with conditional expectation in non-iterative and iterative fashions. For the non-iterative precoding design, we study a robust minimum MSE (MMSE) precoding algorithm by extending a new channel decomposition. Also, in the case of iterative precoding, we investigate a robust weighted MMSE (WMMSE) precoding to further improve the achievable rate. Simulation results show that the proposed precoding schemes yield significant improvements over traditional precoding designs.

cs.IT↗

arXiv2024

I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models

Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility within the open-source communities and disrupting the model's prior knowledge. Meanwhile, the latter typically fails to preserve the identity of the input image. We present I2V-Adapter to overcome such limitations. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism, maintaining the identity of the input image without any changes to the pretrained T2V model. Notably, I2V-Adapter only introduces a few trainable parameters, significantly alleviating the training cost and also ensures compatibility with existing community-driven personalized models and control tools. Moreover, we propose a novel Frame Similarity Prior to balance the motion amplitude and the stability of generated videos through two adjustable control coefficients. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos. This performance, coupled with its agility and adaptability, represents a substantial advancement in the field of I2V, particularly for personalized and controllable applications.

cs.CV↗

arXiv2024

Long-Term Prediction Accuracy Improvement of Data-Driven Medium-Range Global Weather Forecast

Long-term stability stands as a crucial requirement in data-driven medium-range global weather forecasting. Spectral bias is recognized as the primary contributor to instabilities, as data-driven methods difficult to learn small-scale dynamics. In this paper, we reveal that the universal mechanism for these instabilities is not only related to spectral bias but also to distortions brought by processing spherical data using conventional convolution. These distortions lead to a rapid amplification of errors over successive long-term iterations, resulting in a significant decline in forecast accuracy. To address this issue, a universal neural operator called the Spherical Harmonic Neural Operator (SHNO) is introduced to improve long-term iterative forecasts. SHNO uses the spherical harmonic basis to mitigate distortions for spherical data and uses gated residual spectral attention (GRSA) to correct spectral bias caused by spurious correlations across different scales. The effectiveness and merit of the proposed method have been validated through its application for spherical Shallow Water Equations (SWEs) and medium-range global weather forecasting. Our findings highlight the benefits and potential of SHNO to improve the accuracy of long-term prediction.

cs.LG↗

arXiv2024

Beam shaping by nonlinear moiré metasurfaces

This paper explores the interplay of momentum transfer and nonlinear optical processes through moiré phenomena. Momentum transfer plays a crucial role in the interaction between photons and matter. Here, we study stacked metasurfaces with tailored dispersion and rotated against each other with varying twisted angles. The stacking introduces interlayer interactions, which can be controlled by the relative angle between metasurfaces, significantly enriching the resulting response compared to the single layer counterpart. By focusing on second-harmonic generation (SHG) from these twisted metasurfaces, we delve into the realm of nonlinear moiré photonics. Through experimental observations, we unveil the emergence of intricate far-field SHG radiation patterns, showing their effective tuning by varying the twisted angles. These findings offer a fresh perspective to explore nonlinear wavefront shaping through moiré phenomena, opening new avenues for nonlinear information processing, optical steering, and nonlinear optical switching.

physics.optics↗

arXiv2024

Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is unable to provide fine-grained supervision for complex reasoning tasks, and can not focus on the few key tokens that lead to the incorrectness. To address it, we propose a new RL method named RLMEC that incorporates a generative model as the reward model, which is trained by the erroneous solution rewriting task under the minimum editing constraint, and can produce token-level rewards for RL training. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process. And the both objectives focus on the learning of the key tokens for the erroneous solution, reducing the effect of other unimportant tokens. The experiment results on mathematical tasks and question-answering tasks have demonstrated the effectiveness of our approach. Our code and data are available at https://github.com/RUCAIBox/RLMEC.

cs.CL↗

arXiv2024

A-SDM: Accelerating Stable Diffusion through Model Assembly and Feature Inheritance Strategies

The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these approaches typically maintain the original network architecture. The extensive parameter scale and substantial computational demands have limited research into adjusting the model architecture. This study focuses on reducing redundant computation in SDM and optimizes the model through both tuning and tuning-free methods. 1) For the tuning method, we design a model assembly strategy to reconstruct a lightweight model while preserving performance through distillation. Second, to mitigate performance loss due to pruning, we incorporate multi-expert conditional convolution (ME-CondConv) into compressed UNets to enhance network performance by increasing capacity without sacrificing speed. Third, we validate the effectiveness of the multi-UNet switching method for improving network speed. 2) For the tuning-free method, we propose a feature inheritance strategy to accelerate inference by skipping local computations at the block, layer, or unit level within the network structure. We also examine multiple sampling modes for feature inheritance at the time-step level. Experiments demonstrate that both the proposed tuning and the tuning-free methods can improve the speed and performance of the SDM. The lightweight model reconstructed by the model assembly strategy increases generation speed by $22.4%$, while the feature inheritance strategy enhances the SDM generation speed by $40.0%$.

cs.CV↗

arXiv2024

Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector

Hallucination detection is a challenging task for large language models (LLMs), and existing studies heavily rely on powerful closed-source LLMs such as GPT-4. In this paper, we propose an autonomous LLM-based agent framework, called HaluAgent, which enables relatively smaller LLMs (e.g. Baichuan2-Chat 7B) to actively select suitable tools for detecting multiple hallucination types such as text, code, and mathematical expression. In HaluAgent, we integrate the LLM, multi-functional toolbox, and design a fine-grained three-stage detection framework along with memory mechanism. To facilitate the effectiveness of HaluAgent, we leverage existing Chinese and English datasets to synthesize detection trajectories for fine-tuning, which endows HaluAgent with the capability for bilingual hallucination detection. Extensive experiments demonstrate that only using 2K samples for tuning LLMs, HaluAgent can perform hallucination detection on various types of tasks and datasets, achieving performance comparable to or even higher than GPT-4 without tool enhancements on both in-domain and out-of-domain datasets. We release our dataset and code at https://github.com/RUCAIBox/HaluAgent.

cs.CL↗

arXiv2024

Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement

The advent of Large Language Models (LLMs) has propelled dialogue generation into new realms, particularly in the field of role-playing systems (RPSs). While enhanced with ordinary role-relevant training dialogues, existing LLM-based RPSs still struggle to align with roles when handling intricate and trapped queries in boundary scenarios. In this paper, we design the Modular ORchestrated Trap-setting Interaction SystEm (MORTISE) to benchmark and improve the role-playing LLMs' performance. MORTISE can produce highly role-relevant aggressive queries through the collaborative effort of multiple LLM-based modules, and formulate corresponding responses to create an adversarial training dataset via a consistent response generator. We select 190 Chinese and English roles to construct aggressive queries to benchmark existing role-playing LLMs. Through comprehensive evaluation, we find that existing models exhibit a general deficiency in role alignment capabilities. We further select 180 of the roles to collect an adversarial training dataset (named RoleAD) and retain the other 10 roles for testing. Experiments on models improved by RoleAD indicate that our adversarial dataset ameliorates this deficiency, with the improvements demonstrating a degree of generalizability in ordinary scenarios.

cs.CL↗