Till Speicher

4 papers · 2014–2026 · 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 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ACL (2) ICML (1) NeurIPS (1)

Top co-authors

Krishna Gummadi (2) Vedant Nanda (2) Adrian Weller (2) Evimaria Terzi (1) Soumi Das (1) Steffen Staab (1) Deepak Garg (1) Soheil Feizi (1) Krishna P. Gummadi (1) Camila Kolling (1)

Research topics

Deep Learning (3) Machine Learning (2) Core Methods (2) Learning Types (2) Artificial Intelligence (1) Natural Language Processing (1) Application Areas (1) Architectures (1) Learning Paradigms (1) Optimization & Theory (1) Resources & Methods (1) Techniques (1)

Keywords

neural network (2) transfer learning (1) in-context learning (1) weight initialization (1) inductive bia (1) pre-trained representation (1) formal language (1) similarity measure (1) feature redundancy (1) representational robustness (1) shared invariance (1) representation similarity (1) large language model (1) representation learning (1) linear probe (1)

Papers

Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective ACL 2026 Diffused Redundancy in Pre-trained Representations NeurIPS 2023 Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022 A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser Ney Smoothing ACL 2014