OpenCodeReasoning: Advancing Data Distillation for Competitive Coding (2025 · 33 citations)
Distilling reasoning from large models into smaller ones has strongly improved coding performance. However, the best recipes usually depend on closed datasets or say little about how the data was curated. NVIDIA researchers address this with OpenCodeReasoning, a large open supervised fine-tuning corpus for…
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models (2026 · 1 citation)
OpenAI and Google DeepMind report gold-medal results at olympiad-level programming contests, but they have disclosed little about how they did it. Open-weight models have lagged behind. NVIDIA researchers present GenCluster, a test-time compute pipeline that aims for the same level openly and reproducibly.

All works

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

OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset ↗arXiv:2402.10176 · no summary yetShubham Toshniwal et al.2024 · 98 citations
TorchAudio: Building Blocks for Audio and Speech Processing ↗arXiv:2110.15018 · no summary yetYao-Yuan Yang et al.2021 · 34 citations
OpenCodeReasoning: Advancing Data Distillation for Competitive CodingarXiv:2504.01943Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, et al.2025 · 33 citations
Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, et al.2026 · 1 citation

Co-authors here

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

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

Papers of our library cite their works 420 times (of the 149,439 papers whose bibliographies we read); 84 citing papers with a page here →.

Updated 31 October 2026