Sang Michael Xie
15 papers · 2018–2024 · 4 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 (29) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
The Namer
π
Triple Crown
π₯
Mega-Team Β· Squad
π§
Keyword Pioneer
π
Trend Setter
β
The Questioner
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(68)
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(13)
Learning Types Β· Machine Learning
(8)
Deep Learning
(7)
Artificial Intelligence
(6)
Application Areas
(6)
Core AI
(5)
Optimization & Theory
(5)
Core Methods
(4)
Learning Types Β· Deep Learning
(3)
Techniques
(3)
Learning Paradigms
(2)
Models
(2)
Reinforcement Learning
(1)
Bayesian & Probabilistic
(1)
Methods
(1)
Keywords
transfer learning
(3)
distribution shift
(2)
neural network
(2)
contrastive learning
(2)
hidden markov model
(2)
domain adaptation
(2)
language model
(2)
large language model
(2)
robust optimization
(1)
bayesian inference
(1)
reinforcement learning
(1)
semi-supervised regression
(1)
in-context learning
(1)
kl divergence
(1)
neural network compression
(1)
deep kernel learning
(1)
out-of-distribution generalization
(1)
feature disentanglement
(1)
domain generalization
(1)
adversarial training
(1)
Papers
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
ICML 2024
Data Selection for Language Models via Importance Resampling
NeurIPS 2023
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
NeurIPS 2023
Reward Design with Language Models
ICLR 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
ICML 2023
An Explanation of In-context Learning as Implicit Bayesian Inference
ICLR 2022
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
ICML 2022
Extending the WILDS Benchmark for Unsupervised Adaptation
ICLR 2022
Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization
ICML 2021
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
ICLR 2021
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning
NeurIPS 2021
WILDS: A Benchmark of in-the-Wild Distribution Shifts
ICML 2021
Understanding and Mitigating the Tradeoff between Robustness and Accuracy
ICML 2020
Reparameterizable Subset Sampling via Continuous Relaxations
IJCAI 2019
Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
NeurIPS 2018