Searcharxiv⌕ Search

arXiv subjects

Tong Wu

Publications and source records attributed to Tong Wu.

At least 235 records · Page 13Linked to original sources
arXiv2023

CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications

Diffusion models (DM) can gradually learn to remove noise, which have been widely used in artificial intelligence generated content (AIGC) in recent years. The property of DM for eliminating noise leads us to wonder whether DM can be applied to wireless communications to help the receiver mitigate the channel noise. To address this, we propose channel denoising diffusion models (CDDM) for semantic communications over wireless channels in this paper. CDDM can be applied as a new physical layer module after the channel equalization to learn the distribution of the channel input signal, and then utilizes this learned knowledge to remove the channel noise. We derive corresponding training and sampling algorithms of CDDM according to the forward diffusion process specially designed to adapt the channel models and theoretically prove that the well-trained CDDM can effectively reduce the conditional entropy of the received signal under small sampling steps. Moreover, we apply CDDM to a semantic communications system based on joint source-channel coding (JSCC) for image transmission. Extensive experimental results demonstrate that CDDM can further reduce the mean square error (MSE) after minimum mean square error (MMSE) equalizer, and the joint CDDM and JSCC system achieves better performance than the JSCC system and the traditional JPEG2000 with low-density parity-check (LDPC) code approach.

cs.IT↗
arXiv2023

Large-Vocabulary 3D Diffusion Model with Transformer

Creating diverse and high-quality 3D assets with an automatic generative model is highly desirable. Despite extensive efforts on 3D generation, most existing works focus on the generation of a single category or a few categories. In this paper, we introduce a diffusion-based feed-forward framework for synthesizing massive categories of real-world 3D objects with a single generative model. Notably, there are three major challenges for this large-vocabulary 3D generation: a) the need for expressive yet efficient 3D representation; b) large diversity in geometry and texture across categories; c) complexity in the appearances of real-world objects. To this end, we propose a novel triplane-based 3D-aware Diffusion model with TransFormer, DiffTF, for handling challenges via three aspects. 1) Considering efficiency and robustness, we adopt a revised triplane representation and improve the fitting speed and accuracy. 2) To handle the drastic variations in geometry and texture, we regard the features of all 3D objects as a combination of generalized 3D knowledge and specialized 3D features. To extract generalized 3D knowledge from diverse categories, we propose a novel 3D-aware transformer with shared cross-plane attention. It learns the cross-plane relations across different planes and aggregates the generalized 3D knowledge with specialized 3D features. 3) In addition, we devise the 3D-aware encoder/decoder to enhance the generalized 3D knowledge in the encoded triplanes for handling categories with complex appearances. Extensive experiments on ShapeNet and OmniObject3D (over 200 diverse real-world categories) convincingly demonstrate that a single DiffTF model achieves state-of-the-art large-vocabulary 3D object generation performance with large diversity, rich semantics, and high quality.

cs.CV↗
arXiv2023

The Hodge-Dirac operator and Dabrowski-Sitarz-Zalecki type theorems for manifolds with boundary

In [10], Dabrowski etc. gave spectral Einstein bilinear functionals of differential forms for the Hodge-Dirac operator $d+δ$ on an oriented even-dimensional Riemannian manifold. In this paper, we generalize the results of Dabrowski etc. to the cases of 4 dimensional oriented Riemannian manifolds with boundary. Furthermore, we give the proof of Dabrowski-Sitarz-Zalecki type theorems associated with the Hodge-Dirac operator for manifolds with boundary.

math.DG↗
arXiv2023

Towards Trustworthy Explanation: On Causal Rationalization

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction. Yet, existing association-based approaches on rationalization cannot identify true rationales when two or more snippets are highly inter-correlated and thus provide a similar contribution to prediction accuracy, so-called spuriousness. To address this limitation, we novelly leverage two causal desiderata, non-spuriousness and efficiency, into rationalization from the causal inference perspective. We formally define a series of probabilities of causation based on a newly proposed structural causal model of rationalization, with its theoretical identification established as the main component of learning necessary and sufficient rationales. The superior performance of the proposed causal rationalization is demonstrated on real-world review and medical datasets with extensive experiments compared to state-of-the-art methods.

cs.LG↗
arXiv2023

Spatio-temporal boundary dissipation measurement in Taylor-Couette flow using Diffusing-Wave Spectroscopy

Diffusing-Wave Spectroscopy (DWS) allows for the direct measurement of the squared strain-rate tensor. When combined with commonly available high-speed cameras, we show that DWS gives direct access to the spatio-temporal variations of the viscous dissipation rate of a Newtonian fluid flow. The method is demonstrated using a Taylor-Couette (TC) cell filled with a lipid emulsion or a \ch{TiO2} suspension. We image the boundary dissipation rate in a quantitative and time-resolved fashion by shining coherent light at the experimental cell and measuring the local correlation time of the speckle pattern. The results are validated by comparison with the theoretical prediction for an ideal TC flow and with global measurements using a photomultiplier tube and a photon correlator. We illustrate the method by characterizing the spatial organization of the boundary dissipation rate past the Taylor-Couette instability threshold, and its spatio-temporal dynamics in the wavy vortex flow that arises beyond a secondary instability threshold. This study paves the way for direct imaging of the dissipation rate in a large variety of flows, including turbulent ones.

physics.flu-dyn↗
arXiv2023

A general Dabrowski-Sitarz-Zalecki type theorems for manifold with boundary

In [17], we obtained the spectral Einstein functional associated with the Dirac operator for n-dimensional manifolds without boundary. In this paper, we give the proof of general Dabrowski-Sitarz-Zalecki type theorems for the spectral Einstein functional associated with the Dirac operator on even and odd dimensional manifolds with boundary.

math.DG↗
arXiv2023

Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

Neural surface reconstruction aims to reconstruct accurate 3D surfaces based on multi-view images. Previous methods based on neural volume rendering mostly train a fully implicit model with MLPs, which typically require hours of training for a single scene. Recent efforts explore the explicit volumetric representation to accelerate the optimization via memorizing significant information with learnable voxel grids. However, existing voxel-based methods often struggle in reconstructing fine-grained geometry, even when combined with an SDF-based volume rendering scheme. We reveal that this is because 1) the voxel grids tend to break the color-geometry dependency that facilitates fine-geometry learning, and 2) the under-constrained voxel grids lack spatial coherence and are vulnerable to local minima. In this work, we present Voxurf, a voxel-based surface reconstruction approach that is both efficient and accurate. Voxurf addresses the aforementioned issues via several key designs, including 1) a two-stage training procedure that attains a coherent coarse shape and recovers fine details successively, 2) a dual color network that maintains color-geometry dependency, and 3) a hierarchical geometry feature to encourage information propagation across voxels. Extensive experiments show that Voxurf achieves high efficiency and high quality at the same time. On the DTU benchmark, Voxurf achieves higher reconstruction quality with a 20x training speedup compared to previous fully implicit methods. Our code is available at https://github.com/wutong16/Voxurf.

cs.CV↗
arXiv2023

Dirac operators with torsion, spectral Einstein functionals and the noncommutative residue

Recently Dabrowski etc. \cite{DL} obtained the metric and Einstein functionals by two vector fields and Laplace-type operators over vector bundles, giving an interesting example of the spinor connection and square of the Dirac operator. Pf$\ddot{a}$ffle and Stephan \cite{PS1} considered orthogonal connections with arbitrary torsion on compact Riemannian manifolds and computed the spectral action. Motivated by the spectral functionals and Dirac operators with torsion, we give some new spectral functionals which is the extension of spectral functionals to the noncommutative realm with torsion, and we relate them to the noncommutative residue for manifolds with boundary. Our method of producing these spectral functionals is the noncommutative residue and Dirac operators with torsion.

math.DG↗
arXiv2023

Chat-PM: A Class of Composite Hybrid Aerial/Terrestrial Precise Manipulator

This paper concentrates on the development of Chat-PM, a class of composite hybrid aerial/terrestrial manipulator, in concern with composite configuration design, dynamics modeling, motion control and force estimation. Compared with existing aerial or terrestrial mobile manipulators, Chat-PM demonstrates advantages in terms of reachability, energy efficiency and manipulation precision. To achieve precise manipulation in terrestrial mode, the dynamics is analyzed with consideration of surface contact, based on which a cascaded controller is designed with compensation for the interference force and torque from the arm. Benefiting from the kinematic constraints caused by the surface contact, the position deviation and the vehicle vibration are effectively decreased, resulting in higher control precision of the end gripper. For manipulation on surfaces with unknown inclination angles, the moving horizon estimation (MHE) is exploited to obtain the precise estimations of force and inclination angle, which are used in the control loop to compensate for the effect of the unknown surface. Real-world experiments are performed to evaluate the superiority of the developed manipulator and the proposed controllers.

cs.RO↗
arXiv2023

Constrained Reinforcement Learning for Predictive Control in Real-Time Stochastic Dynamic Optimal Power Flow

Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goal of maximizing the reward function. However, this approach can lead to infeasible solutions that violate physical constraints such as power flow equations, voltage limits, and dynamic constraints. Ensuring these constraints are met is crucial in power systems, as they are a safety critical infrastructure. To address this issue, existing DRL algorithms remedy the problem by projecting the actions onto the feasible set, which can result in sub-optimal solutions. This paper presents a novel primal-dual approach for learning optimal constrained DRL policies for dynamic optimal power flow problems, with the aim of controlling power generations and battery outputs. We also prove the convergence of the critic and actor networks. Our case studies on IEEE standard systems demonstrate the superiority of the proposed approach in dynamically adapting to the environment while maintaining safety constraints.

eess.SY↗
arXiv2023

Dispersive Perfectly Matched Layer and high order Absorbing Boundary Conditions for the computation of Quasinormal modes of open electromagnetic structures

Resonances, also known as quasinormal modes (QNM) in the non-Hermitian case, play a ubiquitous role in all domains of physics ruled by wave phenomena, notably in continuum mechanics, acoustics, electrodynamics, and quantum theory. The non-Hermiticity arises from the system losses, whether they are material (Joule losses in electromagnetism) or linked to the openness of the problem (radiation losses). In this paper, we focus on the latter delicate matter when considering bounded computational domains mandatory when using e.g. Finite Elements. Dispersive perfectly matched layers and absorbing boundary conditions are studied.

physics.optics↗
arXiv2023

Towards A Proactive ML Approach for Detecting Backdoor Poison Samples

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we uncover a post-hoc workflow underlying most prior work, where defenders passively allow the attack to proceed and then leverage the characteristics of the post-attacked model to uncover poison samples. We reveal that this workflow does not fully exploit defenders' capabilities, and defense pipelines built on it are prone to failure or performance degradation in many scenarios. Second, we suggest a paradigm shift by promoting a proactive mindset in which defenders engage proactively with the entire model training and poison detection pipeline, directly enforcing and magnifying distinctive characteristics of the post-attacked model to facilitate poison detection. Based on this, we formulate a unified framework and provide practical insights on designing detection pipelines that are more robust and generalizable. Third, we introduce the technique of Confusion Training (CT) as a concrete instantiation of our framework. CT applies an additional poisoning attack to the already poisoned dataset, actively decoupling benign correlation while exposing backdoor patterns to detection. Empirical evaluations on 4 datasets and 14 types of attacks validate the superiority of CT over 14 baseline defenses.

cs.LG↗
arXiv2023

Differential Privacy for Class-based Data: A Practical Gaussian Mechanism

In this paper, we present a notion of differential privacy (DP) for data that comes from different classes. Here, the class-membership is private information that needs to be protected. The proposed method is an output perturbation mechanism that adds noise to the release of query response such that the analyst is unable to infer the underlying class-label. The proposed DP method is capable of not only protecting the privacy of class-based data but also meets quality metrics of accuracy and is computationally efficient and practical. We illustrate the efficacy of the proposed method empirically while outperforming the baseline additive Gaussian noise mechanism. We also examine a real-world application and apply the proposed DP method to the autoregression and moving average (ARMA) forecasting method, protecting the privacy of the underlying data source. Case studies on the real-world advanced metering infrastructure (AMI) measurements of household power consumption validate the excellent performance of the proposed DP method while also satisfying the accuracy of forecasted power consumption measurements.

eess.SP↗
arXiv2023

CDDM: Channel Denoising Diffusion Models for Wireless Communications

Diffusion models (DM) can gradually learn to remove noise, which have been widely used in artificial intelligence generated content (AIGC) in recent years. The property of DM for removing noise leads us to wonder whether DM can be applied to wireless communications to help the receiver eliminate the channel noise. To address this, we propose channel denoising diffusion models (CDDM) for wireless communications in this paper. CDDM can be applied as a new physical layer module after the channel equalization to learn the distribution of the channel input signal, and then utilizes this learned knowledge to remove the channel noise. We design corresponding training and sampling algorithms for the forward diffusion process and the reverse sampling process of CDDM. Moreover, we apply CDDM to a semantic communications system based on joint source-channel coding (JSCC). Experimental results demonstrate that CDDM can further reduce the mean square error (MSE) after minimum mean square error (MMSE) equalizer, and the joint CDDM and JSCC system achieves better performance than the JSCC system and the traditional JPEG2000 with low-density parity-check (LDPC) code approach.

cs.IT↗
arXiv2023

Fusion-Based Multi-User Semantic Communications for Wireless Image Transmission over Degraded Broadcast Channels

Degraded broadcast channels (DBC) are a typical multi-user communications scenario. There exist classic transmission methods, such as superposition coding with successive interference cancellation, to achieve the DBC capacity region. However, semantic communications method over DBC remains lack of in-depth research. To address this, we design a fusion-based multi-user semantic communications system for wireless image transmission over DBC in this paper. The proposed architecture supports a transmitter extracting semantic features for two users separately, and learns to dynamically fuse these semantic features into a joint latent representation for broadcasting. The key here is to design a flexible image semantic fusion (FISF) module to fuse the semantic features of two users, and to use a multi-layer perceptron (MLP) based neural network to adjust the weights of different user semantic features for flexible adaptability to different users channels. Experiments present the semantic performance region based on the peak signal-to-noise ratio (PSNR) of both users, and show that the proposed system dominates the traditional methods.

cs.IT↗
arXiv2023

OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the development of 3D perception, reconstruction, and generation in the real world, we propose OmniObject3D, a large vocabulary 3D object dataset with massive high-quality real-scanned 3D objects. OmniObject3D has several appealing properties: 1) Large Vocabulary: It comprises 6,000 scanned objects in 190 daily categories, sharing common classes with popular 2D datasets (e.g., ImageNet and LVIS), benefiting the pursuit of generalizable 3D representations. 2) Rich Annotations: Each 3D object is captured with both 2D and 3D sensors, providing textured meshes, point clouds, multiview rendered images, and multiple real-captured videos. 3) Realistic Scans: The professional scanners support highquality object scans with precise shapes and realistic appearances. With the vast exploration space offered by OmniObject3D, we carefully set up four evaluation tracks: a) robust 3D perception, b) novel-view synthesis, c) neural surface reconstruction, and d) 3D object generation. Extensive studies are performed on these four benchmarks, revealing new observations, challenges, and opportunities for future research in realistic 3D vision.

cs.CV↗
arXiv2023

Spatio-Temporal Graph Convolutional Neural Networks for Physics-Aware Grid Learning Algorithms

This paper proposes a model-free Volt-VAR control (VVC) algorithm via the spatio-temporal graph ConvNet-based deep reinforcement learning (STGCN-DRL) framework, whose goal is to control smart inverters in an unbalanced distribution system. We first identify the graph shift operator (GSO) based on the power flow equations. Then, we develop a spatio-temporal graph ConvNet (STGCN), testing both recurrent graph ConvNets (RGCN) and convolutional graph ConvNets (CGCN) architectures, aimed at capturing the spatiotemporal correlation of voltage phasors. The STGCN layer performs the feature extraction task for the policy function and the value function of the reinforcement learning architecture, and then we utilize the proximal policy optimization (PPO) to search the action spaces for an optimum policy function and to approximate an optimum value function. We further utilize the low-pass property of voltage graph signal to introduce an GCN architecture for the the policy whose input is a decimated state vector, i.e. a partial observation. Case studies on the unbalanced 123-bus systems validate the excellent performance of the proposed method in mitigating instabilities and maintaining nodal voltage profiles within a desirable range.

eess.SY↗
arXiv2023

The Spectral Einstein functional and Kastler-Kalau-Walze type theorems

In this paper, on the basis of defining the spectral Einstein functional associated with the Dirac operator for manifolds with boundary, we prove Kastler-Kalau-Walze type theorem for the spectral Einstein functional associated with the Dirac operator on low-dimensional manifolds with boundary.

math.DG↗