Yuval Ran-Milo

According to our database, Yuval Ran-Milo authored at least 6 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

A Mechanistic Account of Attention Sinks in GPT-2: One Circuit, Broader Implications for Mitigation.

Yuval Ran-Milo, Hila Ofek, Shahar Mendel

CoRR, April, 2026

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks.

Yuval Ran-Milo

CoRR, March, 2026

Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data.

Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen

CoRR, January, 2026

2025

Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study.

Yotam Alexander, Yonatan Slutzky, Yuval Ran-Milo, Nadav Cohen

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Mamba Knockout for Unraveling Factual Information Flow.

Nir Endy, Idan Daniel Grosbard, Yuval Ran-Milo, Yonatan Slutzky, Itay Tshuva, Raja Giryes

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Provable Benefits of Complex Parameterizations for Structured State Space Models.

Yuval Ran-Milo, Eden Lumbroso, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024