5 papers · 1 filter
MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
Maoliang Li, Haojing Chen, Jiayu Chen +4
Diffusion Transformers with Mixture-of-Experts (DiT-MoE) improve model capacity under sparse activation, but diffusion inference is still bottlenecked by redundant computation acro…
DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
Zihao Zheng, Hangyu Cao, Sicheng Tian +12
Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Exi…
FedHQ: Hybrid Runtime Quantization for Federated Learning
Zihao Zheng, Ziyao Wang, Xiuping Cui +11
Federated Learning (FL) must balance training efficiency and model accuracy across heterogeneous clients. Post-training quantization (PTQ) avoids the extra computation of quantizat…
DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation
Zihao Zheng, Xiuping Cui, Size Zheng +4
As the Mix-of-Experts (MoE) architecture increases the number of parameters in large models, there is an even greater need for model quantization. However, existing quantization me…
Infinite-Dimensional Feature Interaction
Chenhui Xu, Fuxun Yu, Maoliang Li +4
The past neural network design has largely focused on feature representation space dimension and its capacity scaling (e.g., width, depth), but overlooked the feature interaction s…