← Authors

Sang Michael Xie

15 papers · 2018–2024 · 4 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (4) πŸ—ΊοΈ Taxonomy Completionist (24) 🐝 Cross-Pollinator (7) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (6) πŸ“› The Namer πŸ‘₯ Mega-Team (23) πŸ‘‘ Triple Crown πŸ’Ž Century Club (15) πŸ”₯ Unstoppable (7) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (51)

Conferences

ICML (6) ICLR (4) NIPS (4) IJCAI (1)

Top co-authors

Percy Liang (9) Tengyu Ma (8) Ananya Kumar (3) Sergey Levine (2) Henrik Marklund (2) Wei Guo (2) Weihua Hu (2) Kendrick Shen (2) Michihiro Yasunaga (2) Aditi Raghunathan (2)

Keywords

transfer learning (3) language model (2) neural network (2) representation learning (1) feature learning (1) domain generalization (1) robust optimization (1) semi-supervised regression (1) kl divergence (1) unsupervised domain adaptation (1) adversarial training (1) feature disentanglement (1) out-of-distribution generalization (1) deep kernel learning (1) feature space (1) gaussian process (1) distribution shift (1) structured output (1) continuous relaxation (1) contrastive learning (1)

Papers

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations ICML 2024
Data Selection for Language Models via Importance Resampling NIPS 2023
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining NIPS 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023
Reward Design with Language Models ICLR 2023
Extending the WILDS Benchmark for Unsupervised Adaptation ICLR 2022
An Explanation of In-context Learning as Implicit Bayesian Inference ICLR 2022
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation ICML 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 NIPS 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 NIPS 2018