Simone Scardapane
9 papers · 2023–2025 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π Triple Crown π₯ Mega-Team Β· Squad
π
Grand Slam
β‘
Prolific Year Β· Productive
β
The Questioner
Venues
Top co-authors
Research topics
Keywords
model compression
(3)
transformer model
(2)
large language model
(2)
message passing
(2)
latent graph
(2)
automatic speech recognition
(1)
knowledge distillation
(1)
relational learning
(1)
geometric deep learning
(1)
efficient inference
(1)
graph representation
(1)
efficient computing
(1)
attention mechanism
(1)
graph embedding
(1)
missing data imputation
(1)
conditional computation
(1)
adaptive computation
(1)
mixture of expert
(1)
tabular data
(1)
singular value decomposition
(1)
Papers
Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference
AAAI 2025
How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not
Interspeech 2025
Task Singular Vectors: Reducing Task Interference in Model Merging
CVPR 2025
A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression
EMNLP 2024
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
NeurIPS 2024
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
ICLR 2024
Position: Topological Deep Learning is the New Frontier for Relational Learning
ICML 2024
TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
JMLR 2024
EGG-GAE: scalable graph neural networks for tabular data imputation
AISTATS 2023