Collin Burns

5 papers · 2021–2024 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 📈 Trend Setter

Venues

ICLR (3) CVPR (1) ICML (1)

Top co-authors

Jacob Steinhardt (4) Dan Hendrycks (2) Dawn Song (2) Steven Basart (2) Yining Chen (1) Jeffrey Wu (1) Leopold Aschenbrenner (1) Bowen Baker (1) Leo Gao (1) Jan Hendrik Kirchner (1)

Research topics

Artificial Intelligence (5) Core AI (5) Machine Learning (2) Learning Types (2) Deep Learning (1) Natural Language Processing (1) Application Areas (1) Applications (1) Learning Paradigms (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

language model (2) unsupervised learning (1) learning theory (1) reinforcement learning (1) domain adaptation (1) batch normalization (1) question answering (1) unsupervised domain adaptation (1) weak supervision (1) distribution shift (1) pre-trained model (1) human value (1) latent knowledge (1) world knowledge (1) zero-shot accuracy (1) internal activation (1) problem solving (1) machine ethics (1) large language model (1) moral judgment (1)

Papers

Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision ICML 2024 Discovering Latent Knowledge in Language Models Without Supervision ICLR 2023 Aligning AI With Shared Human Values ICLR 2021 Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021 Measuring Massive Multitask Language Understanding ICLR 2021