Yitao Xu
YOU?
Author Swipe
View article: Canonical Latent Representations in Conditional Diffusion Models
Canonical Latent Representations in Conditional Diffusion Models Open
Conditional diffusion models (CDMs) have shown impressive performance across a range of generative tasks. Their ability to model the full data distribution has opened new avenues for analysis-by-synthesis in downstream discriminative learn…
View article: Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata
Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata Open
Artistic stylization of 3D volumetric smoke data is still a challenge in computer graphics due to the difficulty of ensuring spatiotemporal consistency given a reference style image, and that within reasonable time and computational resour…
View article: Distributed beamforming design for UAV‐based integrated communication and jamming systems
Distributed beamforming design for UAV‐based integrated communication and jamming systems Open
The integrated communication and jamming system is proposed by exploiting the diversity gain and flexible deployment of unmanned aerial vehicle (UAV)‐based distributed multiple input multiple output technology, which is expected to gain hi…
View article: AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer Open
Vision Transformers (ViTs) demonstrate remarkable performance in image classification through visual-token interaction learning, particularly when equipped with local information via region attention or convolutions. Although such architec…
View article: NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata
NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata Open
Neural Cellular Automata (NCA) is a class of Cellular Automata where the update rule is parameterized by a neural network that can be trained using gradient descent. In this paper, we focus on NCA models used for texture synthesis, where t…
View article: Emergent Dynamics in Neural Cellular Automata
Emergent Dynamics in Neural Cellular Automata Open
Neural Cellular Automata (NCA) models are trainable variations of traditional Cellular Automata (CA). Emergent motion in the patterns created by NCA has been successfully applied to synthesize dynamic textures. However, the conditions requ…
View article: NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata
NoiseNCA: Noisy Seed Improves Spatio-Temporal Continuity of Neural Cellular Automata Open
Neural Cellular Automata (NCA) is a class of Cellular Automata where the update rule is parameterized by a neural network that can be trained using gradient descent. In this paper, we focus on NCA models used for texture synthesis, where t…
View article: Mesh Neural Cellular Automata
Mesh Neural Cellular Automata Open
Texture modeling and synthesis are essential for enhancing the realism of virtual environments. Methods that directly synthesize textures in 3D offer distinct advantages to the UV-mapping-based methods as they can create seamless textures …
View article: Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method
Alternative Telescopic Displacement: An Efficient Multimodal Alignment Method Open
In the realm of multimodal data integration, feature alignment plays a pivotal role. This paper introduces an innovative approach to feature alignment that revolutionizes the fusion of multimodal information. Our method employs a novel ite…
View article: DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata
DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata Open
Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control ove…
View article: DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata
DyNCA: Real-time Dynamic Texture Synthesis Using Neural Cellular Automata Open
Current Dynamic Texture Synthesis (DyTS) models can synthesize realistic videos. However, they require a slow iterative optimization process to synthesize a single fixed-size short video, and they do not offer any post-training control ove…
View article: Task-Based Network Reconfiguration in Distributed UAV Swarms: A Bilateral Matching Approach
Task-Based Network Reconfiguration in Distributed UAV Swarms: A Bilateral Matching Approach Open
In this paper, we study the problem of network reconfiguration when unmanned aerial vehicle (UAV) swarms suffer damage. Multiple UAVs are divided into several groups to perform various tasks. Each master UAV is connected to the ground cont…
View article: Topology tracking of dynamic UAV wireless networks
Topology tracking of dynamic UAV wireless networks Open
Wireless network is the communication foundation that supports the intelligentization of Unmanned Aerial Vehicle (UAV) swarm. The topology of UAV communication network is the key to understanding and analyzing the behavior of UAV swarm, th…
View article: Distributed Energy-Efficient and Secure Offloading in Air-to-Ground MEC Networks
Distributed Energy-Efficient and Secure Offloading in Air-to-Ground MEC Networks Open
This paper mainly investigates the energy-efficient and secure offloading problem in air-to-ground MEC networks. The proposed efficient offloading mechanism is as per the requirements of the heterogeneous tasks of ground users. Further, th…
View article: Interpreting and Improving Adversarial Robustness of Deep Neural Networks With Neuron Sensitivity
Interpreting and Improving Adversarial Robustness of Deep Neural Networks With Neuron Sensitivity Open
Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they bring, adversarial examples are also valuable for providing…
View article: Proactive optimization of transmission power and 3D trajectory in UAV-assisted relay systems with mobile ground users
Proactive optimization of transmission power and 3D trajectory in UAV-assisted relay systems with mobile ground users Open
In this paper, an Unmanned Aerial Vehicle (UAV)-assisted relay communication system is studied, where a UAV is served as a flying relay to maintain a communication link between a mobile source node and a remote destination node. Specifical…
View article: Understanding adversarial robustness via critical attacking route
Understanding adversarial robustness via critical attacking route Open
Deep neural networks (DNNs) are vulnerable to adversarial examples which are generated by inputs with imperceptible perturbations. Understanding adversarial robustness of DNNs has become an important issue, which would for certain result i…
View article: Adversarial Attacks for Embodied Agents.
Adversarial Attacks for Embodied Agents. Open
Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have mainly focused on static scenes; however, it remains unclear …
View article: Spatiotemporal Attacks for Embodied Agents
Spatiotemporal Attacks for Embodied Agents Open
Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have mainly focused on static scenes; however, it remains unclear …
View article: Energy Efficient Task Cooperation for Multi-UAV Networks: A Coalition Formation Game Approach
Energy Efficient Task Cooperation for Multi-UAV Networks: A Coalition Formation Game Approach Open
In this paper, we study the multi-task cooperation problem for unmanned aerial vehicle (UAV) swarms, where the UAV energy consumption is taken into consideration during location scheduling and task implementation. One task may need the coo…
View article: On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer
On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer Open
With the development of access technologies and artificial intelligence, a deep reinforcement learning (DRL) algorithm is proposed into channel accessing and anti-jamming. Assuming the jamming modes are sweeping, comb, dynamic and statisti…
View article: Context-aware Group Buying in Ultra-dense Small Cell Networks: Unity is Strength
Context-aware Group Buying in Ultra-dense Small Cell Networks: Unity is Strength Open
The ultra-dense small cell networks (SCNs) have been regarded as a promising technology to solve the data traffic explosion in future. However, the complicated relationships among large scale users and cells practically demand a cooperativ…
View article: Self-Organizing Relay Selection in UAV Communication Networks: A Matching Game Perspective
Self-Organizing Relay Selection in UAV Communication Networks: A Matching Game Perspective Open
For large unmanned aerial vehicle (UAV) networks, the timely communication is needed to accomplish a series of missions accurately and effectively. The relay technology will play an important role in UAV networks by helping drones communic…
View article: Distributed Channel Access, Relay Selection and Time Assignment for QoE-Aware Relay Networks
Distributed Channel Access, Relay Selection and Time Assignment for QoE-Aware Relay Networks Open
In this paper, we tackle the comprehensive problem jointing channel access, relay selection, and available time assignment for distributed relay networks which includes multiple source nodes and relay nodes. Driven by various communication…
View article: Distributed relay selection for heterogeneous UAV communication networks using a many-to-many matching game without substitutability
Distributed relay selection for heterogeneous UAV communication networks using a many-to-many matching game without substitutability Open
This paper proposes a distributed multiple relay selection scheme to maximize the satisfaction experiences of unmanned aerial vehicles (UAV) communication networks. The multi-radio and multi-channel (MRMC) UAV communication system is consi…
View article: Self‐organising multiuser matching in cellular networks: a score‐based mutually beneficial approach
Self‐organising multiuser matching in cellular networks: a score‐based mutually beneficial approach Open
In this study, the authors study the self‐organising user assignment problem for the multi‐user cooperation network. In the cellular network with user cooperation, idle users near the base station are seen as potential relay nodes, which c…
View article: A Study on the Positioning of Warehouse Logistics Industry in Yangtze River Region--Based on the Agglomeration Efficiency of Service Industry
A Study on the Positioning of Warehouse Logistics Industry in Yangtze River Region--Based on the Agglomeration Efficiency of Service Industry Open
The storage and logistics industry in the Yangtze River Delta region can draw lessons from the service industry, and exert the benefit of agglomeration to achieve the development of the logistics industry in the Yangtze River Delta region.