Mark Rofin

3 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner

Venues

ACL (1) EACL (1) ICML (1)

Top co-authors

Michael Hahn (2) Alireza Amiri Bavandpour (1) Elena Tutubalina (1) Vladislav Mikhailov (1) Ekaterina Artemova (1) Xinting Huang (1) Tatiana Shavrina (1) Daniel Karabekyan (1) Mikhail Florinsky (1) Andrey Kravchenko (1)

Research topics

Machine Learning (3) Optimization & Theory · Machine Learning (3) Deep Learning (2) Architectures (2) Artificial Intelligence (1) Mathematics & Optimization (1) Core AI (1) Learning Types (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

transformer architecture (1) chain-of-thought reasoning (1) loss landscape (1) expressivity (1) inductive bia (1) lower bound (1) formal language (1) social choice theory (1) parity function (1) system ranking (1) multi-task benchmark (1) system evaluation (1) input sensitivity (1) benchmark ranking (1) mean average (1) benchmark aggregation (1) missing performance (1) input-space sensitivity (1) expressivity theory (1) hard-attention transformers (1)

Papers

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers ICML 2025 Why are Sensitive Functions Hard for Transformers? ACL 2024 Vote’n’Rank: Revision of Benchmarking with Social Choice Theory EACL 2023