🧑‍🔬 Emmanuel J. Candès

🏛️ Affiliations

🎓Stanford UniversityStanford · United States1999–2026 · 157 papersEducation until 1998Employmentcurrent🏢BlackRockNew York · United States2025–2026 · 4 paperscurrent🎓California Institute of TechnologyPasadena · United States2001–2011 · 58 papersEmployment🎓University of California San DiegoSan Diego · United States2008–2011 · 3 papers🎓University of California, Los AngelesLos Angeles · United States2007 · 3 papers🎓École PolytechniquePalaiseau · France2008 · 1 paperEducation

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 11 more institutions 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. s1: Simple test-time scaling (2025 · 608 citations)
   The paper looks for the most minimal recipe that gives a language model both strong reasoning and clear test-time scaling, meaning accuracy rises as the model is allowed to think longer.
2. Can Unconfident LLM Annotations Be Used for Confident Conclusions? (2025 · 19 citations)
   Computational social scientists increasingly add LLM annotations to costly human labels. However, LLM errors and biases can quietly distort downstream statistics such as prevalences or regression coefficients. The authors propose CONFIDENCE-DRIVEN INFERENCE, which asks an LLM for both a label and a verbalized…
3. Towards Execution-Grounded Automated AI Research (2026 · 7 citations)
   LLMs can propose research ideas that sound convincing but fail when tested. This paper asks two questions: can idea testing be automated at scale, and can models improve from the measured results? The authors built an automated executor. An Implementer turns natural-language ideas into code diffs, a Scheduler assigns…

All works

13 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information ↗IEEE Transactions on Information Theory · no summary yetEmmanuel J. Candès, Justin K. Romberg, Terence Tao2004 · 15,569 citations
2. Decoding by Linear Programming ↗IEEE Transactions on Information Theory · no summary yetEmmanuel J. Candès, Terence Tao2005 · 7,132 citations
3. Robust principal component analysis? ↗Journal of the ACM · no summary yetEmmanuel J. Candès et al.2009 · 6,945 citations
4. Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies? ↗IEEE Transactions on Information Theory · no summary yetEmmanuel J. Candès, Terence Tao2004 · 6,845 citations
5. s1: Simple test-time scalingConference on Empirical Methods in Natural Language Processing (EMNLP)Niklas Muennighoff, Zitong Yang, Weijia Shi, et al.2025 · 608 citations
6. Uncertainty Quantification over Graph with Conformalized Graph Neural Networks ↗neural information processing systems · no summary yetKexin Huang et al.2023 · 39 citations
7. Can Unconfident LLM Annotations Be Used for Confident Conclusions?Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)Kristina Gligorić, Tijana Zrnic, Cinoo Lee, et al.2025 · 19 citations
8. Automated Hypothesis Validation with Agentic Sequential Falsifications ↗arXiv:2502.09858 · no summary yetKexin Huang et al.2025 · 19 citations
9. Large language model validity via enhanced conformal prediction methods ↗arXiv:2406.09714 · no summary yetJohn J. Cherian, Isaac Gibbs, Emmanuel J. Candes2024 · 18 citations
10. Towards Execution-Grounded Automated AI ResearcharXiv:2601.14525Chenglei Si, Zitong Yang, Yejin Choi, et al.2026 · 7 citations
11. One-Step Generative Modeling via Wasserstein Gradient Flows ↗arXiv (Cornell University) · no summary yetJiaqi Han et al.2026 · 2 citations
12. TxConformal: Controlling False Discoveries in AI-Driven Therapeutic Discovery ↗bioRxiv (Cold Spring Harbor Laboratory) · no summary yetYing Jin et al.2026
13. Automating discovery with AI ↗Stanford Digital Repository · no summary yetKexin Huang et al.2025

🤝 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

• Tatsunori Hashimoto ×2
• Zitong Yang ×2
• Chenglei Si
• Cinoo Lee
• Dan Jurafsky
• Diyi Yang
• Hannaneh Hajishirzi
• Kristina Gligorić
• Li Fei-Fei
• Luke Zettlemoyer
• Niklas Muennighoff
• Percy Liang

Venues

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

• IEEE Transactions on Information Theory ×3
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025
• Journal of the ACM
• Stanford Digital Repository
• bioRxiv (Cold Spring Harbor Laboratory)
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 651 times (of the 149,439 papers whose bibliographies we read); 177 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/emmanuel-j-candes/