Search Results for author:
Found 7 papers, 0 papers with code
Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
By amalgamating soft prompt compression with sophisticated summarization, SoftPromptComp confronts the dual challenges of managing lengthy contexts and ensuring model scalability.
An Evolution Kernel Method for Graph Classification through Heat Diffusion Dynamics
This approach incorporates the physics-based heat kernel and DropNode technique to transform each static graph into a sequence of temporal ones.
Metric Distribution to Vector: Constructing Data Representation via Broad-Scale Discrepancies
Graph embedding provides a feasible methodology to conduct pattern classification for graph-structured data by mapping each data into the vectorial space.
A Graph Data Augmentation Strategy with Entropy Preservation
Considering the preservation of graph entropy, we propose an effective strategy to generate randomly perturbed training data but maintain both graph topology and graph entropy.
Graph Classification Based on Skeleton and Component Features
Most existing popular methods for learning graph embedding only consider fixed-order global structural features and lack structures hierarchical representation.
Composite Pressure Cell for Pulsed Magnets
However, large pressures and fields are often mutually incompatible; the rapidly changing fields provided by pulsed magnets induce eddy currents in the metallic components used in conventional pressure cells, causing serious heating, forces and vibration.
Strongly Correlated Electrons Applied Physics
Serverless inferencing on Kubernetes
Organisations are increasingly putting machine learning models into production at scale.
