Simone Scardapane
8 papers · 2023–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Conference Polyglot (8) π Interdisciplinary Bridge π Cross-Pollinator (9) π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (16)
π
Grand Slam
π
Triple Crown
π₯
Mega-Team
(43)
β‘
Prolific Year
(5)
Conferences
AAAI (1)
AISTATS (1)
CVPR (1)
EMNLP (1)
ICLR (1)
ICML (1)
JMLR (1)
NIPS (1)
Top co-authors
Keywords
model compression
(3)
transformer model
(2)
attention mechanism
(1)
knowledge distillation
(1)
model merging
(1)
conditional computation
(1)
efficient inference
(1)
efficient computing
(1)
message passing
(1)
graph embedding
(1)
singular value decomposition
(1)
adaptive computation
(1)
missing data imputation
(1)
mixture of expert
(1)
tabular datum
(1)
task vector
(1)
inference efficiency
(1)
kv cache compression
(1)
task interference
(1)
activation sparsity
(1)
Papers
Task Singular Vectors: Reducing Task Interference in Model Merging
CVPR 2025
Adaptive Computation Modules: Granular Conditional Computation for Efficient Inference
AAAI 2025
TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
JMLR 2024
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
NIPS 2024
A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression
EMNLP 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
EGG-GAE: scalable graph neural networks for tabular data imputation
AISTATS 2023