Searcharxiv⌕ Search

arXiv subjects

Jun Li

Publications and source records attributed to Jun Li.

At least 415 records · Page 23Linked to original sources
arXiv2024

Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute

Generating 3D human models directly from text helps reduce the cost and time of character modeling. However, achieving multi-attribute controllable and realistic 3D human avatar generation is still challenging due to feature coupling and the scarcity of realistic 3D human avatar datasets. To address these issues, we propose Text2Avatar, which can generate realistic-style 3D avatars based on the coupled text prompts. Text2Avatar leverages a discrete codebook as an intermediate feature to establish a connection between text and avatars, enabling the disentanglement of features. Furthermore, to alleviate the scarcity of realistic style 3D human avatar data, we utilize a pre-trained unconditional 3D human avatar generation model to obtain a large amount of 3D avatar pseudo data, which allows Text2Avatar to achieve realistic style generation. Experimental results demonstrate that our method can generate realistic 3D avatars from coupled textual data, which is challenging for other existing methods in this field.

cs.CV↗
arXiv2024

Exploring Multi-Modal Control in Music-Driven Dance Generation

Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these issues, we propose a unified framework capable of generating high-quality dance movements and supporting multi-modal control, including genre control, semantic control, and spatial control. First, we decouple the dance generation network from the dance control network, thereby avoiding the degradation in dance quality when adding additional control information. Second, we design specific control strategies for different control information and integrate them into a unified framework. Experimental results show that the proposed dance generation framework outperforms state-of-the-art methods in terms of motion quality and controllability.

cs.SD↗
arXiv2023

Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy

Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to limited transmission bandwidth and the model performance degrades while using differential privacy (DP) protection. In this paper, we propose a gradient sparsification empowered FL framework over wireless channels, in order to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local training, thereby mitigating the performance degradation induced by DP and and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin and delay-minimization algorithms.

cs.DC↗
arXiv2023

Satellite Impact on Astronomical Observations Based on Elliptical Orbit Model

Space-based and ground-based telescopes have extensively documented the impact of satellites on astronomical observations. With the proliferation of satellite mega-constellation programs, their influence on astronomical observations has become undeniable. It is crucial to quantify the impact of satellites on telescopes. To address this need, we have enhanced the circular orbit model for satellites and introduced a methodology based on two-line element (TLE) orbit data. This involves constructing a satellite probability distribution model to evaluate the impact of satellites on telescopes. Using our method, we assessed the satellite impact on global observatories. The results indicate that the regions most severely affected by satellite interference currently are those near the equator, with latitudes around 50 and 80 degrees experiencing the most significant impact from low Earth orbit satellites. Furthermore, we validated the reliability of our method using imaging data obtained from the focal surface acquisition camera of the LAMOST telescope.

astro-ph.IM↗
arXiv2023

Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval

Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, \textit{i.e.}, the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In this paper, we introduce Modal-Enhanced Semantic Modeling (MESM), a novel framework for more balanced alignment through enhancing features at two levels. First, we enhance the video modality at the frame-word level through word reconstruction. This strategy emphasizes the portions associated with query words in frame-level features while suppressing irrelevant parts. Therefore, the enhanced video contains less redundant semantics and is more balanced with the textual modality. Second, we enhance the textual modality at the segment-sentence level by learning complementary knowledge from context sentences and ground-truth segments. With the knowledge added to the query, the textual modality thus maintains more meaningful semantics and is more balanced with the video modality. By implementing two levels of MESM, the semantic information from both modalities is more balanced to align, thereby bridging the modality gap. Experiments on three widely used benchmarks, including the out-of-distribution settings, show that the proposed framework achieves a new start-of-the-art performance with notable generalization ability (e.g., 4.42% and 7.69% average gains of R1@0.7 on Charades-STA and Charades-CG). The code will be available at https://github.com/lntzm/MESM.

cs.CV↗
arXiv2023

Collisionless cooling of perpendicular electron temperature in the thermal quench of a magnetized plasma

Thermal quench of a nearly collisionless plasma against a cooling boundary or region is an undesirable off-normal event in magnetic fusion experiments, but an ubiquitous process of cosmological importance in astrophysical plasmas. There is a well-known mismatch that what experimentally diagnosed is the drop in perpendicular electron temperature $T_{e\perp},$ but the parallel transport theory of ambipolar-constrained tail electron loss produces parallel electron temperature $T_{e\parallel}$ cooling. Here two collisionless mechanisms, dilutional cooling by infalling cold electrons and wave-particle interaction by two families of whistler instabilities, are shown to enable fast $T_{e\perp}$ cooling that closely tracks the mostly collisionless crash of $T_{e\parallel}.$

physics.plasm-ph↗
arXiv2023

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories, suffering from massive GPU memory consumption when there is a large number of categories in the target dataset. Moreover, previous works require to include category names within prompts, exhibiting subpar performance when dealing with ambiguous category names. To address these shortcomings, we propose Compound Text-Guided Prompt Tuning (TGP-T) that significantly reduces resource demand while achieving superior performance. We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly. Specifically, we found that compound text supervisions, i.e., category-wise and content-wise, is highly effective, since they provide inter-class separability and capture intra-class variations, respectively. Moreover, we condition the prompt generation on visual features through a module called Bonder, which facilitates the alignment between prompts and visual features. Extensive experiments on few-shot recognition and domain generalization demonstrate that TGP-T achieves superior performance with consistently lower training costs. It reduces GPU memory usage by 93% and attains a 2.5% performance gain on 16-shot ImageNet. The code is available at https://github.com/EricTan7/TGP-T.

cs.CV↗
arXiv2023

Measuring the speed of scalar induced gravitational waves from observations

We investigate the scalar induced gravitational waves which propagate with a speed different from the speed of light. First, we analytically calculate the expression of the power spectrum of the scalar induced gravitational waves which is based on the speed and the spectrum of the primordial curvature perturbations. Then, we discuss several scalar power spectra and obtain corresponding fractional energy density, such as the monochromatic power spectrum, the scale invariant power spectrum and the power-law power spectrum. Finally, we constrain the scalar induced gravitational waves and evaluate the signatures of the speed from the combination of CMB+BAO and gravitational waves observations. The numerical results are obvious to reveal the influence of speed of scalar induced gravitational waves.

gr-qc↗
arXiv2023

A New Smoothing Technique for Bang-Bang Optimal Control Problems

Bang-bang control is ubiquitous for Optimal Control Problems (OCPs) where the constrained control variable appears linearly in the dynamics and cost function. Based on the Pontryagin's Minimum Principle, the indirect method is widely used to numerically solve OCPs because it enables to derive the theoretical structure of the optimal control. However, discontinuities in the bang-bang control structure may result in numerical difficulties for gradient-based indirect method. In this case, smoothing or regularization procedures are usually applied to eliminating the discontinuities of bang-bang controls. Traditional smoothing or regularization procedures generally modify the cost function by adding a term depending on a small parameter, or introducing a small error into the state equation. Those procedures may complexify the numerical algorithms or degenerate the convergence performance. To overcome these issues, we propose a bounded smooth function, called normalized L2-norm function, to approximate the sign function in terms of the switching function. The resulting optimal control is smooth and can be readily embedded into the indirect method. Then, the simplicity and improved performance of the proposed method over some existing methods are numerically demonstrated by a minimal-time oscillator problem and a minimal-fuel low-thrust trajectory optimization problem that involves many revolutions.

math.OC↗
arXiv2023

Joint Design of Sampler and Compressor for Timely Status Updates: Age-Distortion Tradeoff

We consider a joint sampling and compression system for timely status updates. Samples are taken, quantized and encoded into binary sequences, which are sent to the destination. We formulate an optimization problem to jointly design sampler, quantizer and encoder, minimizing the age of information (AoI) on the basis of satisfying a mean-squared error (MSE) distortion constraint of the samples. We prove that the zero-wait sampling, the uniform quantization, and the real-valued AoI-optimal coding policies together provide an asymptotically optimal solution to this problem, i.e., as the average distortion approaches zero, the combination achieves the minimum AoI asymptotically. Furthermore, we prove that the AoI of this solution is asymptotically linear with respect to the log MSE distortion with a slope of $-\frac{3}{4}$. We also show that the real-valued Shannon coding policy suffices to achieve the optimal performance asymptotically. Numerical simulations corroborate the analysis.

cs.IT↗
arXiv2023

Colossal Magnetoresistance in Twisted Intertwined Graphene Spirals

Colossal magnetoresistance (CMR) is highly applicable in spintronic devices such as magnetic sensors, magnetic memory, and hard drives. Typically, CMR is found in Weyl semimetals characterized by perfect electron-hole symmetry or exceptionally high electric conductivity and mobility. Our study explores this phenomenon in a recently developed graphene moir$\acute{e}$ system, which demonstrates CMR owing to its topological structure and high-quality crystal formation. We specifically investigate the electronic properties of three-dimensional (3D) intertwined twisted graphene spirals (TGS), manipulating the screw dislocation axis to achieve a rotation angle of 7.3$^{\circ}$. Notably, at 14 T and 2 K, the magnetoresistance of these structures reached 1.7$\times$10$^7$%, accompanied by an unexpected metal-to-insulator transition as the temperature increased. This transition becomes noticeable when the magnetic field exceeds a minimal threshold of approximately 0.1 T. These observations suggest the existence of complex, correlated states within the partially filled three-dimensional Landau levels of the 3D TGS system. Our findings open up new possibilities for achieving CMR by engineering the topological structure of 2D layered moir$\acute{e}$ systems.

cond-mat.mes-hall↗
arXiv2023

Enhancement of photon blockade via topological edge states

Quantum technologies, holding the promise of exponentially superior performance than their classical counterparts for certain tasks, have consistently encountered challenges, including instability in quantum light sources, quantum decoherence and vulnerability to losses that topological photonics happens to adeptly address. Here, we theoretically put forth a quantum Su-Schrieffer-Heeger-type chain designed to greatly enhance single-photon blockade (single-PB) effect with topological protection. By designing the deliberate coupling strengths, the quantum-level lattices take the form of a one-dimensional array with a topological edge state in single-excitation space and a two-dimensional square breathing lattice with topological corner states in two-excitation space, resulting in enhanced single-photon excitation and the suppression of two-photon transitions. Therefore the second-order correlation function is diminished by up to two orders of magnitude at the cavity resonance frequency, accompanied by stronger brightness.Furthermore, the PB effect is robust to local perturbations in cavity-qubit coupling and qubit frequency, benefitting from topological protection.

quant-ph↗
arXiv2023

Real-time optimal control for attitude-constrained solar sailcrafts via neural networks

This work is devoted to generating optimal guidance commands in real time for attitude-constrained solar sailcrafts in coplanar circular-to-circular interplanetary transfers. Firstly, a nonlinear optimal control problem is established, and necessary conditions for optimality are derived by the Pontryagin's Minimum Principle. Under some assumptions, the attitude constraints are rewritten as control constraints, which are replaced by a saturation function so that a parameterized system is formulated to generate an optimal trajectory via solving an initial value problem. This approach allows for the efficient generation of a dataset containing optimal samples, which are essential for training Neural Networks (NNs) to achieve real-time implementation. However, the optimal guidance command may suddenly change from one extreme to another, resulting in discontinuous jumps that generally impair the NN's approximation performance. To address this issue, we use two co-states that the optimal guidance command depends on, to detect discontinuous jumps. A procedure for preprocessing these jumps is then established, thereby ensuring that the preprocessed guidance command remains smooth. Meanwhile, the sign of one co-state is found to be sufficient to revert the preprocessed guidance command back into the original optimal guidance command. Furthermore, three NNs are built and trained offline, and they cooperate together to precisely generate the optimal guidance command in real time. Finally, numerical simulations are presented to demonstrate the developments of the paper.

math.OC↗
arXiv2023

Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autonomous Driving

Radar has stronger adaptability in adverse scenarios for autonomous driving environmental perception compared to widely adopted cameras and LiDARs. Compared with commonly used 3D radars, the latest 4D radars have precise vertical resolution and higher point cloud density, making it a highly promising sensor for autonomous driving in complex environmental perception. However, due to the much higher noise than LiDAR, manufacturers choose different filtering strategies, resulting in an inverse ratio between noise level and point cloud density. There is still a lack of comparative analysis on which method is beneficial for deep learning-based perception algorithms in autonomous driving. One of the main reasons is that current datasets only adopt one type of 4D radar, making it difficult to compare different 4D radars in the same scene. Therefore, in this paper, we introduce a novel large-scale multi-modal dataset featuring, for the first time, two types of 4D radars captured simultaneously. This dataset enables further research into effective 4D radar perception algorithms.Our dataset consists of 151 consecutive series, most of which last 20 seconds and contain 10,007 meticulously synchronized and annotated frames. Moreover, our dataset captures a variety of challenging driving scenarios, including many road conditions, weather conditions, nighttime and daytime with different lighting intensities and periods. Our dataset annotates consecutive frames, which can be applied to 3D object detection and tracking, and also supports the study of multi-modal tasks. We experimentally validate our dataset, providing valuable results for studying different types of 4D radars. This dataset is released on https://github.com/adept-thu/Dual-Radar.

cs.CV↗
arXiv2023

A physics-informed and attention-based graph learning approach for regional electric vehicle charging demand prediction

Along with the proliferation of electric vehicles (EVs), optimizing the use of EV charging space can significantly alleviate the growing load on intelligent transportation systems. As the foundation to achieve such an optimization, a spatiotemporal method for EV charging demand prediction in urban areas is required. Although several solutions have been proposed by using data-driven deep learning methods, it can be found that these performance-oriented methods may suffer from misinterpretations to correctly handle the reverse relationship between charging demands and prices. To tackle the emerging challenges of training an accurate and interpretable prediction model, this paper proposes a novel approach that enables the integration of graph and temporal attention mechanisms for feature extraction and the usage of physic-informed meta-learning in the model pre-training step for knowledge transfer. Evaluation results on a dataset of 18,013 EV charging piles in Shenzhen, China, show that the proposed approach, named PAG, can achieve state-of-the-art forecasting performance and the ability in understanding the adaptive changes in charging demands caused by price fluctuations.

cs.LG↗
arXiv2023

Cross-modal Consistency Learning with Fine-grained Fusion Network for Multimodal Fake News Detection

Previous studies on multimodal fake news detection have observed the mismatch between text and images in the fake news and attempted to explore the consistency of multimodal news based on global features of different modalities. However, they fail to investigate this relationship between fine-grained fragments in multimodal content. To gain public trust, fake news often includes relevant parts in the text and the image, making such multimodal content appear consistent. Using global features may suppress potential inconsistencies in irrelevant parts. Therefore, in this paper, we propose a novel Consistency-learning Fine-grained Fusion Network (CFFN) that separately explores the consistency and inconsistency from high-relevant and low-relevant word-region pairs. Specifically, for a multimodal post, we divide word-region pairs into high-relevant and low-relevant parts based on their relevance scores. For the high-relevant part, we follow the cross-modal attention mechanism to explore the consistency. For low-relevant part, we calculate inconsistency scores to capture inconsistent points. Finally, a selection module is used to choose the primary clue (consistency or inconsistency) for identifying the credibility of multimodal news. Extensive experiments on two public datasets demonstrate that our CFFN substantially outperforms all the baselines.

cs.SI↗
arXiv2023

Constructing the Fulde-Ferrell-Larkin-Ovchinnikov state in antiferromagnetic insulator CrOCl

Time reversal symmetry breaking in superconductors, resulting from external magnetic fields or spontaneous magnetization, often leads to unconventional superconducting properties. In this way, a conventional Fulde-Ferrell-Larkin-Ovchinnikov (FFLO) state, characterized by the Cooper pairs with nonzero total momentum, may be realized by the Zeeman effect caused from external magnetic fields. Here, we report the observation of superconductivity in a few-layer antiferromagnetic insulator CrOCl by utilizing superconducting proximity effect with NbSe2 flakes. The superconductivity demonstrates a considerably weak gap of about 0.12 meV and the in-plane upper critical field reveals as behavior of the FFLO state at low temperature. Our first-principles calculations indicate that the proximitized superconductivity may exist in the CrOCl layer with Cr vacancies or line-defects. Moreover, the FFLO state could be induced by the inherent larger spin splitting in the CrOCl layer. Our findings not only demonstrate the fascinating interaction between superconductivity and magnetism, but also provide a possible path to construct FFLO state by intrinsic time reversal symmetry breaking and superconducting proximity effect.

cond-mat.supr-con↗
arXiv2023

Proximity effect induced intriguing superconductivity in van der Waals heterostructure of magnetic topological insulator and conventional superconductor

Nontrivial topological superconductivity has received enormous research attentions due to its potential for diverse applications in topological quantum computing. The intrinsic issue concerning the correlation between a topological insulator and a superconductor is, however, still widely open. Here, we systemically report an emergent superconductivity in a cross-junction composed of a magnetic topological insulator MnBi2Te4 and a conventional superconductor NbSe2. Remarkably, the interface indicates existence of a reduced superconductivity at surface of NbSe2 and a proximity-effectinduced superconductivity at surface of MnBi2Te4. Furthermore, the in-plane angular-dependent magnetoresistance measurements reveal the fingerprints of the paring symmetry behaviors for these superconducting gaps as a unconventional nature. Our findings extend our views and ideas of topological superconductivity in the superconducting heterostructures with time-reversal symmetry breaking, offering an exciting opportunity to elucidate the cooperative effects on the surface state of a topological insulator aligning a superconductor.

cond-mat.supr-con↗