Mark Kurtz
5 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5) π Cross-Pollinator (10)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(15)
β
The Questioner
(2)
Conferences
ACL (2)
CVPR (1)
EMNLP (1)
ICML (1)
Top co-authors
Research topics
Keywords
sparse model
(2)
convolutional neural network
(2)
inference acceleration
(2)
model pruning
(2)
image classification
(1)
transfer learning
(1)
knowledge distillation
(1)
bert compression
(1)
second-order optimization
(1)
sparse activation
(1)
weight pruning
(1)
sparse neural network
(1)
activation sparsity
(1)
large language model quantization
(1)
bit precision
(1)
accuracy recovery
(1)
large language model
(1)
llm quantization
(1)
int4 quantization
(1)
fp8 quantization
(1)
Papers
βGive Me BF16 or Give Me Deathβ? Accuracy-Performance Trade-Offs in LLM Quantization
ACL 2025
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes
ACL 2023
How Well Do Sparse ImageNet Models Transfer?
CVPR 2022
The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models
EMNLP 2022
Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks
ICML 2020