Toni J.b. Liu

5 papers · 2024–2025 · 2 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 🗺️ Taxonomy Completionist (15) ❓ The Questioner

Venues

ICLR (3) EMNLP (2)

Top co-authors

Christopher Earls (4) Nicolas Boulle (4) Raphaël Sarfati (4) Haley Moller (1) Tao Yu (1) Christopher De Sa (1) Albert Tseng (1)

Research topics

Machine Learning (5) Optimization & Theory (4) Artificial Intelligence (3) Core AI (3) Core Methods (3) Deep Learning (2) Learning Types · Machine Learning (2) Models (2) Natural Language Processing (1) Learning Types · Deep Learning (1) Resources & Methods (1)

Keywords

in-context learning (2) large language model (2) authorship attribution (1) stochastic process (1) kernel density estimation (1) probability density (1) knowledge graph (1) dynamical system (1) language model (1) latent space (1) partial order (1) hyperbolic space (1) physical law (1) physical modeling (1) literary style (1) prompt embedding (1) neural scaling law (1) dimensionality reduction (1) entailment cone (1) representation learning (1)

Papers

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