5 papers
Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
Leo Muxing Wang, Pengkun Yang, Lili Su
Despite the popularity of the actor-critic method and the practical needs of collaborative policy training, existing works typically either overlook environmental heterogeneity or…
Accelerating Multi-Condition T2I Generation via Adaptive Condition Offloading and Pruning
Yuxin Kong, Peng Yang, Chongbin Yi +2
Text-to-image (T2I) generation using multiple conditions enables fine-grained user control on the generated image. Yet, incorporating multi-condition inputs incurs substantial comp…
SynerDiff: Synergetic Continuous Batching for Fast and Parallel Diffusion Model Inference
Ziqi Zhou, Peng Yang, Yuxin Liang +2
The expansion of Artificial Intelligence-generated content service requires diffusion model serving to simultaneously achieve high throughput and low task end-to-end (E2E) latency.…
QoE-Aware Service Provision for Mobile AR Rendering: An Agent-Driven Approach
Conghao Zhou, Lulu Sun, Xiucheng Wang +4
Mobile augmented reality (MAR) is envisioned as a key immersive application in 6G, enabling virtual content rendering aligned with the physical environment through device pose esti…
Compression Metadata-assisted RoI Extraction and Adaptive Inference for Efficient Video Analytics
Chengzhi Wang, Peng Yang
Video analytics demand substantial computing resources, posing significant challenges in computing resource-constrained environment. In this paper, to achieve high accuracy with ac…