conftrace_

Christopher Earls

4 papers · 2024–2025 · 2 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓

🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (13) 🐝 Cross-Pollinator (15) ❓ The Questioner

Conferences

EMNLP (2) ICLR (2)

Top co-authors

Raphaël Sarfati (4) Toni J.b. Liu (4) Nicolas Boulle (4) Haley Moller (1)

Keywords

large language model (2) in-context learning (1) authorship attribution (1) dynamical system (1) language model (1) latent space (1) physical law (1) physical modeling (1) literary style (1) prompt embedding (1) representation learning (1) neural scaling law (1)

Papers

What’s in a prompt? Language models encode literary style in prompt embeddings EMNLP 2025 Density estimation with LLMs: a geometric investigation of in-context learning trajectories ICLR 2025 Lines of Thought in Large Language Models ICLR 2025 LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law EMNLP 2024