Phillip Isola
- Papers
- 25
Cite
Notes
Only stored in your browser.
Authored papers
25Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
arXiv 2026
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
arXiv 2025
The Platonic Representation Hypothesis
arXiv 2024
Personalized Representation from Personalized Generation
arXiv 2024
Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings
arXiv 2022
Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning
arXiv 2023
Learning Vision from Models Rivals Learning Vision from Data
CVPR 2024 1
Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
arXiv 2023
The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade
arXiv 2023
Improving CLIP Training with Language Rewrites
improving-clip-training-with-language
Learning to generate line drawings that convey geometry and semantics
CVPR 2022 1
Exploring Visual Prompts for Adapting Large-Scale Models
arXiv 2022
Procedural Image Programs for Representation Learning
arXiv 2022
On the Learning and Learnability of Quasimetrics
arXiv 2022
Denoised MDPs: Learning World Models Better Than the World Itself
arXiv 2022
Learning to See by Looking at Noise
NeurIPS 2021 12
Supervised Contrastive Learning
NeurIPS 2020 12
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
arXiv 2020
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
ECCV 2020 8
Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
arXiv 2019
Contrastive Multiview Coding
ECCV 2020 8
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
the-unreasonable-effectiveness-of-deep-1
Real-Time User-Guided Image Colorization with Learned Deep Priors
arXiv 2017
Colorful Image Colorization
arXiv 2016
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
split-brain-autoencoders-unsupervised-1
Affiliations
Frequent co-authors
10from 25 papers