collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

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…

cs.LG2026

Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure

Xiang Chen, Alexander Binder

Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership and attachment validity implici…

cs.LG2026

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

Zihao Zheng, Hangyu Cao, Sicheng Tian +9

Vision-Language-Action (VLA) models are dominant in embodied intelligence but are constrained by inference overheads. While model quantization alleviates these bottlenecks for edge…

cs.LG2026

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…

cs.LG2025

FedHQ: Hybrid Runtime Quantization for Federated Learning

Zihao Zheng, Ziyao Wang, Xiuping Cui +6

Federated Learning (FL) is a decentralized model training approach that preserves data privacy but struggles with low efficiency. Quantization, a powerful training optimization tec…

cs.LG2025

Threshold Neuron: A Brain-inspired Artificial Neuron for Efficient On-device Inference

Zihao Zheng, Yuanchun Li, Jiayu Chen +3

Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing. As we aim to execute increasingly compl…