Luca Biggio
7 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (3) π Cross-Pollinator (7) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16)
π
Triple Crown
Conferences
ICML (4)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
transformer architecture
(1)
stochastic gradient descent
(1)
autoregressive transformer
(1)
self-attention mechanism
(1)
sharpness-aware minimization
(1)
deep learning
(1)
prior knowledge
(1)
model pruning
(1)
signal propagation
(1)
deep learning model
(1)
stochastic differential equation
(1)
gradient vanishing
(1)
inference efficiency
(1)
symbolic regression
(1)
flat minima
(1)
equation discovery
(1)
search algorithm
(1)
saddle point
(1)
flat minimum
(1)
hessian-dependent noise
(1)
Papers
Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
ICML 2025
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
NIPS 2023
FIGARO: Controllable Music Generation using Learned and Expert Features
ICLR 2023
Controllable Neural Symbolic Regression
ICML 2023
An SDE for Modeling SAM: Theory and Insights
ICML 2023
Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse
NIPS 2022
Neural Symbolic Regression that scales
ICML 2021