Vaishaal Shankar
20 papers · 2019–2025 · 7 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π₯
Mega-Team Β· Legion
π€
Dynamic Duo
(13)
π
Keyword Champion
(2)
π
Century Club Β· Bronze
β
The Questioner
(2)
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(84)
β‘
Prolific Year Β· Productive
Top co-authors
Research topics
Machine Learning
(19)
Application Areas
(12)
Artificial Intelligence
(9)
Deep Learning
(7)
Core AI
(7)
Learning Types Β· Machine Learning
(7)
Optimization & Theory
(7)
Learning Types Β· Deep Learning
(6)
Core Methods
(4)
Learning Paradigms
(3)
Models
(3)
Natural Language Processing
(2)
Architectures
(2)
Computer Science
(1)
Applications
(1)
Keywords
image classification
(4)
distribution shift
(4)
data filtering
(3)
contrastive learning
(2)
large language model
(2)
image-text pair
(2)
zero-shot accuracy
(2)
vision-language model
(2)
continual learning
(2)
transfer learning
(2)
domain adaptation
(2)
catastrophic forgetting
(2)
web-scale data
(2)
domain generalization
(2)
language model
(2)
temporal robustness
(2)
video classification
(1)
curriculum learning
(1)
zero-shot learning
(1)
object recognition
(1)
Papers
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
ACL 2025
DataComp-LM: In search of the next generation of training sets for language models
NeurIPS 2024
Data Filtering Networks
ICLR 2024
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
NeurIPS 2024
Pre-trained Language Models Do Not Help Auto-regressive Text-to-Image Generation
EMNLP 2024
Scalable Pre-training of Large Autoregressive Image Models
ICML 2024
TiC-CLIP: Continual Training of CLIP Models
ICLR 2024
DataComp: In search of the next generation of multimodal datasets
NeurIPS 2023
Masked Autoencoding Does Not Help Natural Language Supervision at Scale
CVPR 2023
Robustness in Multimodal Learning under Train-Test Modality Mismatch
ICML 2023
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
ICML 2022
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
ICML 2021
Do Image Classifiers Generalize Across Time?
ICCV 2021
Predicting With Confidence on Unseen Distributions
ICCV 2021
Evaluating Machine Accuracy on ImageNet
ICML 2020
Measuring Robustness to Natural Distribution Shifts in Image Classification
NeurIPS 2020
Neural Kernels Without Tangents
ICML 2020
A Meta-Analysis of Overfitting in Machine Learning
NeurIPS 2019
Do ImageNet Classifiers Generalize to ImageNet?
ICML 2019