# Yair Amar

> Yair Amar is a research scientist at Accomplish working on safe, performant AI coding agents, and a Technion MSc student probing speech enhancement models.

Hey! I'm a research scientist with a record of delivering results across disciplines, from the defence and health industries to speech technology and coding agents. I get deep satisfaction from making things work. I'm naturally curious and never short on new ideas.

I'm an early member of the technical staff at Accomplish, where I work on AI agent enablement, with the goal of safe and performant agents at scale. I'm also pursuing my MSc at the Technion under the guidance of Dr. Amir Ivry and Prof. Israel Cohen, focused on probing speech enhancement models.

## Research interests

- Deep learning for speech
- AI agents and coding agents

## Publications

- **The Hardening Tax: Policy-Graded Evaluation of Coding Agents under Enterprise Security Constraints**. Yair Amar*, Dotan Davidovich*, Hai Rozencwajg*, Or Hiltch, Ravid Shwartz-Ziv. NeurIPS 2026 Workshop on Agents in the Wild, 2026. * Equal contribution. Extended version on arXiv as "Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments".
  Enterprise security policy costs coding agents up to 18.3 points of success and 167.3% more cost on Terminal-Bench 2.1, and the best model depends on the policy. [arXiv](https://arxiv.org/abs/2608.02670), [Code](https://github.com/boundary-bench/boundary-bench), [Website](https://boundarybench.com/)
- **Probing Layer-Wise Robustness and Sensitivity of Speech Enhancement Models**. Yair Amar, Amir Ivry, Israel Cohen. arXiv preprint arXiv:2512.00482, 2026. Under review at IEEE/ACM Transactions on Audio, Speech, and Language Processing
  A layer-by-layer probe of three speech enhancement models shows where each is robust or sensitive to noise and reverberation, and that this profile is learned during training. [arXiv](https://arxiv.org/abs/2512.00482), [Code](https://github.com/YairAmar/SE-Probe), [Demo](https://yairamar.github.io/seint-show-web/)
- **Speech Enhancement Intelligence: Inspecting a Model Under Controlled Degradation**. Yair Amar, Amir Ivry, Israel Cohen. ICASSP 2026 Show & Tell demo, Barcelona, 2026.
  A live demo: speak into a microphone, add noise with a slider, and watch how a speech enhancement model's internal layers react alongside PESQ, STOI, and SI-SDR. [Demo](https://yairamar.github.io/seint-show-web/), [Session](https://cmsworkshops.com/ICASSP2026/view_demosession.php?mid=54)

## Experience

- Member of Technical Staff, Accomplish, Mar 2026 to present
- Senior Research Scientist, Innovation Center, Sheba Medical Center, Aug 2024 to Mar 2026
- Data Scientist, Defence industry, 2020 to 2026

## Education

- MSc, Electrical Engineering, Technion, Israel Institute of Technology, 2024 to present (expected 2027)
- BSc, Electrical Engineering and Physics, Technion, Israel Institute of Technology, 2016 to 2020

## News

- Sep 2026: The Hardening Tax was accepted to the NeurIPS 2026 Workshop on Agents in the Wild. See you in Sydney in December.
- Sep 2026: Our speech enhancement probing paper is under review at IEEE TASLP. The updated preprint is on arXiv.
- Aug 2026: Permission Denied is on arXiv, and we open-sourced Boundary-Bench for evaluating coding agents under security policy.
- May 2026: Presented our Show & Tell demo, Speech Enhancement Intelligence, at ICASSP 2026 in Barcelona. Try the interactive version.
- Mar 2026: Joined Accomplish as a Member of Technical Staff, working on coding agents under enterprise security policy.
- Nov 2025: First preprint on arXiv: probing layer-wise robustness and sensitivity of speech enhancement models.
- 2024: Started my MSc in Electrical Engineering at the Technion with Dr. Amir Ivry and Prof. Israel Cohen.

## Links

- [Email](mailto:yairamr@gmail.com)
- [GitHub](https://github.com/YairAmar)
- [LinkedIn](https://www.linkedin.com/in/yair-amar-b65b62144/)
- [Google Scholar](https://scholar.google.com/citations?user=XXgJht4AAAAJ)
- [Home page](https://yairamar.github.io/)