Julian Asilis

7 papers · 2024–2026 · 4 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

COLT (3) ALT (2) ACL (1) NeurIPS (1)

Top co-authors

Shaddin Dughmi (5) Vatsal Sharan (5) Siddartha Devic (4) Shang-Hua Teng (4) Ollie Liu (1) Willie Neiswanger (1) Deqing Fu (1) Sky Jafar (1) Grigoris Velegkas (1) Woody Haosheng Gan (1)

Research topics

Machine Learning (5) Optimization & Theory (5) Core Methods (3) Deep Learning (2) Learning Types (2) Artificial Intelligence (1) Mathematics & Optimization (1) Core AI (1) Mathematics (1)

Keywords

transductive learning (3) multi-class classification (3) sample complexity (3) empirical risk minimization (2) visual grounding (1) cross-modal transfer (1) structural risk minimization (1) multiclass learning (1) hypothesis class (1) multimodal large language model (1) sparse autoencoder (1) steering vector (1) mean shift (1) one-inclusion graph (1) local regularization (1) local regularizer (1) pac model (1) proper learner (1) erm (1) graph dimension (1)

Papers

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models ACL 2026 Local Regularizers Are Not Transductive Learners COLT 2025 Proper Learnability and the Role of Unlabeled Data ALT 2025 Understanding Aggregations of Proper Learners in Multiclass Classification ALT 2025 Open Problem: Can Local Regularization Learn All Multiclass Problems? COLT 2024 Regularization and Optimal Multiclass Learning COLT 2024 Transductive Learning is Compact NeurIPS 2024