Skip to content
conftrace_

Core Francisco Park

4 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

Venues

ICLR (3) NeurIPS (1)

Top co-authors

Ekdeep Singh Lubana (4) Hidenori Tanaka (4) Maya Okawa (3) Yongyi Yang (2) Andrew Lee (2) Martin Wattenberg (1) Kento Nishi (1) Wei Hu (1)

Research topics

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

Keywords

learning dynamics (2) concept learning (2) in-context learning (2) representation learning (2) neural network optimization (1) compositional generalization (1) markov chain (1) graph topology (1) generative model (1) diffusion model (1) foundation model (1) hidden capability (1) emergent capability (1) gaussian mixture (1) emergent behavior (1) algorithmic analysis (1) latent intervention (1) semantic organization (1) synthetic task (1) learning theory (1)

Papers

Competition Dynamics Shape Algorithmic Phases of In-Context Learning ICLR 2025 ICLR: In-Context Learning of Representations ICLR 2025 Swing-by Dynamics in Concept Learning and Compositional Generalization ICLR 2025 Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space NeurIPS 2024