Daniele Paliotta
4 papers · 2023–2024 · 1 conference · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(13)
🗺️
Taxonomy Completionist
(19)
🐣
Hot Topic Early Bird
Conferences
NIPS (4)
Top co-authors
Keywords
model compression
(2)
generative modeling
(1)
transformer architecture
(1)
model quantization
(1)
point cloud generation
(1)
knowledge distillation
(1)
model distillation
(1)
geometric deep learning
(1)
neural network optimization
(1)
state space model
(1)
language model
(1)
sparse attention
(1)
inference acceleration
(1)
flash attention
(1)
speculative decoding
(1)
transformer training
(1)
linear rnn
(1)
outlier feature
(1)
activation normalization
(1)
long sequence
(1)
Papers
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
NIPS 2024
Understanding and Minimising Outlier Features in Transformer Training
NIPS 2024
Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention
NIPS 2023
SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics
NIPS 2023