Elamur Research⌕
☰
home / authors / Anikait Singh

Anikait Singh

Anikait Singh has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining; often with Kanishk Gandhi, Noah D. Goodman, Stefano Ermon.

2 papers in our library · 2024–2025

OpenAlex · h-index 7 · 25 works · 654 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 447 times in our library · 9 more in our library without a page yet · ⭐ Paper Stars ranking: #6248

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Stanford UniversityStanford · United States2024–2026 · 8 paperscurrent🎓University of California, BerkeleyBerkeley · United States2022–2024 · 5 papers🏢Google DeepMindLondon · United Kingdom2023–2025 · 3 papers🏢GoogleMountain View · United States2023–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 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.

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs (2025 · 123 citations)
    Why do some base language models gain a lot from reinforcement learning on verifiable tasks while others stall? The authors observe that Qwen-2.5-3B improves sharply on the Countdown arithmetic puzzle under a given RL setup, while Llama-3.2-3B, trained the same way, barely moves.
  2. Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation (2024 · 22 citations)
    Best-of-N sampling makes LLM outputs better, but it is expensive. It needs a separate reward model and always generates a fixed, large number of candidates. Manvi, Singh and Ermon propose "capability-aware self-evaluation" to cut this cost. After a partial or complete answer, the model sees a short self-evaluation…

All works

11 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. Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration 0 ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetAbby O'Neill et al.2024 · 231 citations
  2. Open X-Embodiment: Robotic Learning Datasets and RT-X Models ↗arXiv:2310.08864 · no summary yetEmbodiment Collaboration et al.2023 · 204 citations
  3. Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRsarXiv:2503.01307Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, et al.2025 · 123 citations
  4. Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ↗arXiv (Cornell University) · no summary yetFahim Tajwar et al.2024 · 54 citations
  5. Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought ↗arXiv:2501.04682 · no summary yetViolet Xiang et al.2025 · 47 citations
  6. Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models ↗arXiv:2502.17387 · no summary yetAlon Albalak et al.2025 · 43 citations
  7. Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-GenerationarXiv:2410.02725Rohin Manvi, Anikait Singh, Stefano Ermon2024 · 22 citations
  8. Personalized Preference Fine-tuning of Diffusion Models ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMeihua Dang et al.2025 · 5 citations
  9. FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users ↗arXiv (Cornell University) · no summary yetAnikait Singh et al.2025 · 5 citations
  10. RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems ↗arXiv (Cornell University) · no summary yetQu, Yuxiao et al.2025 · 3 citations
  11. MLE-Smith: Scaling MLE Tasks with Automated Multi-Agent Pipeline ↗arXiv (Cornell University) · no summary yetRushi Qiang et al.2025 · 2 citations

 Co-authors here

3 co-authors with a page, the most papers together first.

Venues

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

 Cited by

Papers of our library cite their works 447 times (of the 149,439 papers whose bibliographies we read); 74 citing papers with a page here →.

Updated

↑ back to top

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