Skip To Main Content
Sang Michael on Muck Rack

Sang Michael

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Sang Michael’s profile

Articles by Sang Michael

[2507.08000] Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models

|
By Sang Michael
| arXiv
Open in Who Shared Issue with article?

[2402.16827] A Survey on Data Selection for Language Models

|
By Sang Michael, William Yang
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (693) Issue with article?

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

|
By Sang Michael
| arXiv
Open in Who Shared Issue with article?

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

|
By Sang Michael, Adams Wei
| arXiv
arXiv:2305.10429 (cs) [Submitted on 17 May 2023 (v1), last revised 24 May 2023 (this version, v2)] Download a PDF of the paper titled DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining, by Sang Michael Xie and 9 other authors Download PDF Submission history From: Sang Michael Xie [ view email] [v1] Wed, 17 May 2023 17:58:13 UTC (8,260 KB) [v2] Wed, 24 May 2023 05:13:10 UTC (8,261 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle...
Open in Who Shared View Duplicates (597) Issue with article?

[2303.00001] Reward Design with Language Models

|
By Sang Michael
| arXiv
In just 3 minutes help us understand how you see arXiv.
Open in Who Shared View Duplicates (296) Issue with article?

[2211.09110] Holistic Evaluation of Language Models

|
By Sang Michael
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (28) Issue with article?

[2211.09110] Holistic Evaluation of Language Models

|
By Sang Michael
| arXiv
In just 3 minutes help us understand how you see arXiv.
Open in Who Shared View Duplicates (17) Issue with article?
Show More