Mitchell Wortsman
24 papers · 2019–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+12 more ↓ Show less ↑
🌍 Conference Polyglot (6) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(10)
🌍
Conference Polyglot
(6)
🤝
Dynamic Duo
(15)
👑
Triple Crown
👥
Mega-Team
(60)
🧬
Topic Evolution
💎
Century Club
(24)
⚡
Prolific Year
(7)
🗃️
Keyword Collector
(107)
❓
The Questioner
🔥
Unstoppable
(7)
Conferences
NIPS (9)
CVPR (5)
ICML (5)
ICLR (3)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
vision-language model
(4)
zero-shot learning
(4)
distribution shift
(3)
contrastive learning
(3)
weight averaging
(2)
data filtering
(2)
out-of-distribution performance
(2)
vision language model
(2)
scaling law
(2)
image-text pair
(2)
model compression
(2)
model ensemble
(2)
clip model
(2)
zero-shot classification
(2)
distributional robustness
(2)
visual navigation
(2)
neural network pruning
(2)
model merging
(2)
language model
(2)
gradient-based optimization
(1)
Papers
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
Small-scale proxies for large-scale Transformer training instabilities
ICLR 2024
Scaling Exponents Across Parameterizations and Optimizers
ICML 2024
DataComp-LM: In search of the next generation of training sets for language models
NIPS 2024
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
NIPS 2024
OLMo: Accelerating the Science of Language Models
ACL 2024
DataComp: In search of the next generation of multimodal datasets
NIPS 2023
Reproducible Scaling Laws for Contrastive Language-Image Learning
CVPR 2023
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
CVPR 2023
Editing models with task arithmetic
ICLR 2023
Stable and low-precision training for large-scale vision-language models
NIPS 2023
Robust Fine-Tuning of Zero-Shot Models
CVPR 2022
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
NIPS 2022
LAION-5B: An open large-scale dataset for training next generation image-text models
NIPS 2022
Patching open-vocabulary models by interpolating weights
NIPS 2022
Exploring The Landscape of Distributional Robustness for Question Answering Models
EMNLP 2022
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
ICML 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
ICML 2022
Learning Neural Network Subspaces
ICML 2021
Soft Threshold Weight Reparameterization for Learnable Sparsity
ICML 2020
Supermasks in Superposition
NIPS 2020
What's Hidden in a Randomly Weighted Neural Network?
CVPR 2020
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
CVPR 2019
Discovering Neural Wirings
NIPS 2019