Brian Chmiel
7 papers · 2020–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Venues
Top co-authors
Research topics
Keywords
gradient quantization
(2)
neural network quantization
(2)
neural network compression
(1)
model quantization
(1)
neural network training
(1)
model training
(1)
language model
(1)
activation function
(1)
mean square error
(1)
structural pruning
(1)
neural network sparsity
(1)
matrix multiplication
(1)
4-bit quantization
(1)
log-normal distribution
(1)
activation quantization
(1)
bandwidth reduction
(1)
gradient sparsity
(1)
logarithmic quantization
(1)
block sparsity
(1)
compression-aware training
(1)
Papers
Scaling FP8 training to trillion-token LLMs
ICLR 2025
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
ICLR 2023
Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
ICLR 2023
Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks
NeurIPS 2021
CAT: Compression-Aware Training for bandwidth reduction
JMLR 2021
Neural gradients are near-lognormal: improved quantized and sparse training
ICLR 2021
Robust Quantization: One Model to Rule Them All
NeurIPS 2020