Mitchell Wortsman
24 papers · 2019–2025 · 6 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (56) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Triple Crown
π₯
Mega-Team Β· Legion
π€
Dynamic Duo
(15)
π§¬
Topic Evolution
π
Renaissance Researcher
(6)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
ποΈ
Keyword Collector
(119)
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(20)
Deep Learning
(16)
Artificial Intelligence
(12)
Core AI
(11)
Application Areas
(10)
Learning Types Β· Machine Learning
(10)
Learning Types Β· Deep Learning
(9)
Optimization & Theory Β· Machine Learning
(9)
Natural Language Processing
(5)
Models
(5)
Techniques
(5)
Architectures
(3)
Core Methods
(3)
Learning Paradigms
(3)
Optimization & Theory Β· Deep Learning
(3)
Keywords
vision-language model
(5)
zero-shot learning
(4)
distribution shift
(3)
language model
(3)
contrastive learning
(3)
scaling law
(3)
data filtering
(2)
weight averaging
(2)
out-of-distribution performance
(2)
image-text pair
(2)
model compression
(2)
model ensemble
(2)
clip model
(2)
zero-shot classification
(2)
neural network optimization
(2)
visual navigation
(2)
neural network pruning
(2)
model merging
(2)
distributional robustness
(2)
gradient-based optimization
(1)
Papers
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
DataComp-LM: In search of the next generation of training sets for language models
NeurIPS 2024
OLMo: Accelerating the Science of Language Models
ACL 2024
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
NeurIPS 2024
Scaling Exponents Across Parameterizations and Optimizers
ICML 2024
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
CVPR 2023
DataComp: In search of the next generation of multimodal datasets
NeurIPS 2023
Editing models with task arithmetic
ICLR 2023
Reproducible Scaling Laws for Contrastive Language-Image Learning
CVPR 2023
Stable and low-precision training for large-scale vision-language models
NeurIPS 2023
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
ICML 2022
Exploring The Landscape of Distributional Robustness for Question Answering Models
EMNLP 2022
LAION-5B: An open large-scale dataset for training next generation image-text models
NeurIPS 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
ICML 2022
Patching open-vocabulary models by interpolating weights
NeurIPS 2022
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
NeurIPS 2022
Robust Fine-Tuning of Zero-Shot Models
CVPR 2022
Learning Neural Network Subspaces
ICML 2021
Soft Threshold Weight Reparameterization for Learnable Sparsity
ICML 2020
Supermasks in Superposition
NeurIPS 2020
What's Hidden in a Randomly Weighted Neural Network?
CVPR 2020
Discovering Neural Wirings
NeurIPS 2019
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
CVPR 2019