Tim Dettmers
17 papers · 2018–2025 · 5 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (31) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§
Keyword Pioneer
π§¬
Topic Evolution
π₯
Mega-Team Β· Squad
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(88)
β‘
Prolific Year Β· Productive
Venues
Top co-authors
Research topics
Machine Learning
(14)
Application Areas
(11)
Artificial Intelligence
(10)
Core AI
(10)
Deep Learning
(8)
Optimization & Theory Β· Machine Learning
(7)
Natural Language Processing
(5)
Optimization & Theory Β· Deep Learning
(5)
Learning Types
(3)
Models
(3)
Resources & Methods
(3)
Techniques
(3)
Mathematics & Optimization
(2)
Applications
(2)
Architectures
(2)
Keywords
large language model
(6)
model compression
(5)
efficient computing
(3)
distributed learning
(2)
language modeling
(2)
knowledge distillation
(2)
parameter efficiency
(2)
language model
(2)
model quantization
(2)
parameter-efficient fine-tuning
(2)
expert routing
(2)
network pruning
(1)
embedding space
(1)
natural language understanding
(1)
neural network training
(1)
transformer architecture
(1)
information retrieval
(1)
distributed computing
(1)
question answering
(1)
model parallelism
(1)
Papers
Holistically Evaluating the Environmental Impact of Creating Language Models
ICLR 2025
OLMoE: Open Mixture-of-Experts Language Models
ICLR 2025
MatFormer: Nested Transformer for Elastic Inference
NeurIPS 2024
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
NeurIPS 2024
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
ICLR 2024
Distributed Inference and Fine-tuning of Large Language Models Over The Internet
NeurIPS 2023
Petals: Collaborative Inference and Fine-tuning of Large Models
ACL 2023
QLoRA: Efficient Finetuning of Quantized LLMs
NeurIPS 2023
Stable and low-precision training for large-scale vision-language models
NeurIPS 2023
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient
ICML 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
8-bit Optimizers via Block-wise Quantization
ICLR 2022
GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale
NeurIPS 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