8 papers
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
Kunjal Panchal, Sunav Choudhary, Yuriy Brun +1
Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language m…
Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
Siqi Chen, Zhiqiang Wang, Yili Shen +8
Mechanistic understanding and rational design of complex chemical systems depend on fast and accurate predictions of electronic structures beyond individual building blocks. Howeve…
ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
Xiao Liu, Lijun Zhang, Deepak Ganesan +1
Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandw…
Aligned Vector Quantization for Edge-Cloud Collabrative Vision-Language Models
Xiao Liu, Lijun Zhang, Deepak Ganesan +1
Vision Language Models (VLMs) are central to Visual Question Answering (VQA) systems and are typically deployed in the cloud due to their high computational demands. However, this…
Reimagining Parameter Space Exploration with Diffusion Models
Lijun Zhang, Xiao Liu, Hui Guan
Adapting neural networks to new tasks typically requires task-specific fine-tuning, which is time-consuming and reliant on labeled data. We explore a generative alternative that pr…
Integrating Graph Neural Networks and Many-Body Expansion Theory for Potential Energy Surfaces
Siqi Chen, Zhiqiang Wang, Xianqi Deng +8
Rational design of next-generation functional materials relied on quantitative predictions of their electronic structures beyond single building blocks. First-principles quantum me…