Tim Dettmers
17 papers · 2018–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Academic Marathon (7) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (5) π Cross-Pollinator (11)
π
Academic Marathon
(7)
πΊοΈ
Taxonomy Completionist
(31)
π
Renaissance Researcher
(5)
π₯
Mega-Team
(24)
π§¬
Topic Evolution
π
Century Club
(17)
π₯
Unstoppable
(6)
ποΈ
Keyword Collector
(75)
β‘
Prolific Year
(7)
Conferences
NIPS (6)
ICLR (4)
ICML (3)
ACL (2)
EMNLP (2)
Top co-authors
Keywords
large language model
(6)
model compression
(4)
efficient computing
(3)
distributed learning
(2)
knowledge distillation
(2)
model quantization
(2)
embedding space
(1)
neural network training
(1)
transformer architecture
(1)
information retrieval
(1)
language modeling
(1)
distributed computing
(1)
network pruning
(1)
natural language understanding
(1)
question answering
(1)
model parallelism
(1)
neural network optimization
(1)
machine reading comprehension
(1)
natural language inference
(1)
link prediction
(1)
Papers
Holistically Evaluating the Environmental Impact of Creating Language Models
ICLR 2025
OLMoE: Open Mixture-of-Experts Language Models
ICLR 2025
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
ICLR 2024
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
NIPS 2024
MatFormer: Nested Transformer for Elastic Inference
NIPS 2024
Stable and low-precision training for large-scale vision-language models
NIPS 2023
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
ICML 2023
Petals: Collaborative Inference and Fine-tuning of Large Models
ACL 2023
The case for 4-bit precision: k-bit Inference Scaling Laws
ICML 2023
Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model
EMNLP 2023
Distributed Inference and Fine-tuning of Large Language Models Over The Internet
NIPS 2023
QLoRA: Efficient Finetuning of Quantized LLMs
NIPS 2023
GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale
NIPS 2022
8-bit Optimizers via Block-wise Quantization
ICLR 2022
BASE Layers: Simplifying Training of Large, Sparse Models
ICML 2021
High Performance Natural Language Processing
EMNLP 2020
Jack the Reader β A Machine Reading Framework
ACL 2018