🧑‍🔬 Vaishaal Shankar

🏛️ Affiliations

🏢AnthropicSan Francisco · United States2025 · 1 papercurrent🎓University of California, BerkeleyBerkeley · United States2015–2021 · 15 papers🏢AppleCupertino · United States2022–2024 · 8 papers🏢AmazonSeattle · United States2021–2024 · 2 papers🎓University of WashingtonSeattle · United States2022–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Language models scale reliably with over-training and on downstream tasks (2024 · 46 citations)
   Scaling laws let teams forecast large language model behaviour from cheap small runs. Most published laws, however, assume Chinchilla-style compute-optimal training and predict only next-token loss. In practice, smaller models are often over-trained on far more tokens to cut inference cost, and they are compared on…
2. Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum (2024 · 16 citations)
   Standard LLM pretraining uses concat-and-chunk: documents are shuffled, joined, and cut into fixed-length sequences.

All works

8 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Cloud Programming Simplified: A Berkeley View on Serverless Computing ↗arXiv (Cornell University) · no summary yetJonas, Eric et al.2019 · 422 citations
2. Measuring Robustness to Natural Distribution Shifts in Image Classification ↗neural information processing systems · no summary yetRohan Taori et al.2020 · 209 citations
3. Predicting with Confidence on Unseen Distributions ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetDevin Guillory et al.2021 · 85 citations
4. numpywren: serverless linear algebra ↗arXiv (Cornell University) · no summary yetVaishaal Shankar et al.2018 · 69 citations
5. Data Filtering Networks ↗arXiv:2309.17425 · no summary yetAlex Fang et al.2023 · 60 citations
6. Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization ↗arXiv (Cornell University) · no summary yetJohn J. Miller et al.2021 · 59 citations
7. Language models scale reliably with over-training and on downstream tasksarXiv:2403.08540Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, et al.2024 · 46 citations
8. Dataset Decomposition: Faster LLM Training with Variable Sequence Length CurriculumConference on Neural Information Processing Systems (NeurIPS)Hadi Pouransari, Chun-Liang Li, Jen-Hao Rick Chang, et al.2024 · 16 citations

🤝 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

• Alex Fang
• Chun-Liang Li
• Georgios Smyrnis
• Jean Mercat
• Jeffrey Li
• Marianna Nezhurina
• Mitchell Wortsman
• Oncel Tuzel
• Rui Xin
• Rulin Shao
• Samir Yitzhak Gadre
• Sedrick Keh

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Conference on Neural Information Processing Systems (NeurIPS) ×3: NeurIPS 2024
• IEEE/CVF International Conference on Computer Vision (ICCV)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 618 times (of the 149,439 papers whose bibliographies we read); 125 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/vaishaal-shankar/