Valentina Pyatkin

Career

Pyatkin completed a PhD in computer science at the NLP lab of Bar-Ilan University, supervised by Ido Dagan and Reut Tsarfaty, and interned twice at Ai2. Pyatkin then held a postdoctoral position at Ai2 and the University of Washington, advised by Hannaneh Hajishirzi and Yejin Choi.¹

Pyatkin is now a researcher at the ETH AI Center, working on post-training of language models for the Swiss AI Initiative and contributing to the Apertus models.¹

Research

Pyatkin's research centres on post-training and adaptation of language models, including how models follow instructions and constraints and how preference and reward signals shape their behaviour. At Ai2, Pyatkin worked on the Tülu post-training pipelines, which combine supervised finetuning, direct preference optimization and reinforcement learning with verifiable rewards, and contributed to OLMo and OLMo 2.¹²

Pyatkin has also built evaluation benchmarks, including RewardBench and IFBench, and co-authored RewardBench 2, published at ICLR 2026.¹

Work and contributions

• Llama 3.1 Tülu 3.1 8B Open weights

  Third author of the Tülu 3 post-training report, which the Tülu 3.1 8B model card cites as its paper; Pyatkin describes being a core contributor to the Tülu and Open-Instruct project.²³¹

• IF-RLVR: Generalizing Verifiable Instruction Following Published research

  First author of a NeurIPS 2025 paper on generalizing verifiable instruction following, with co-authors including Pradeep Dasigi and Nathan Lambert.¹

Timeline

1. Jan 2023Received the AI2 Outstanding Intern of the Year Award.¹
2. Aug 2024Received the ACL Best Theme Paper Award for OLMo and an ACL Outstanding Paper Award.¹
3. Nov 2024Co-authored the Tülu 3 report on open language model post-training as third author.²
4. Dec 2025Had the IFBench paper accepted to NeurIPS 2025.¹
5. 2026Co-authored RewardBench 2, published at ICLR 2026.¹

Other documented roles

Roles the sources document that are not confirmed as current.

• Postdoctoral researcher and Young Investigator (past), Allen Institute for AI (Ai2) and University of Washington¹

Honors and recognition

• AI2 Outstanding Intern of the Year Award · Allen Institute for AI, 2023¹
• DAAD AInet Fellow · German Academic Exchange Service (DAAD), 2023¹
• ACL Best Theme Paper Award (for OLMo) · Association for Computational Linguistics, 2024¹
• ACL Outstanding Paper Award · Association for Computational Linguistics, 2024¹

Where they work

• ETH AI Center 1 person in the wiki

Related people

• Owain EvansLanguage models · Evaluation and benchmarks
• Nanyun (Violet) PengLanguage models · Evaluation and benchmarks
• Mohit IyyerLanguage models · Evaluation and benchmarks
• Douwe KielaLanguage models · Evaluation and benchmarks
• Shunyu YaoLanguage models · Evaluation and benchmarks
• Noah A. SmithLanguage models · Evaluation and benchmarks
• Ethan PerezEvaluation and benchmarks · Language models
• Marina DanilevskyEvaluation and benchmarks · Language models
• Michael CollinsLanguage models · Evaluation and benchmarks
• Percy LiangLanguage models · Evaluation and benchmarks