David Krueger
27 papers · 2017–2025 · 5 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 8 separate collaboration groups - the largest holds only 44% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which David Krueger?
3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Stephen Chung, Ekdeep Singh Lubana, Robert Kirk
7 papers
· 2023–2025
· ICLR, NeurIPS, NAACL
Hide ▲
Analyzing (In)Abilities of SAEs via Formal Languages
NAACL 2025
Interpreting Emergent Planning in Model-Free Reinforcement Learning
ICLR 2025
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
ICLR 2024
Predicting Future Actions of Reinforcement Learning Agents
NeurIPS 2024
Reward Model Ensembles Help Mitigate Overoptimization
ICLR 2024
Mechanistic Mode Connectivity
ICML 2023
Thinker: Learning to Plan and Act
NeurIPS 2023
5 papers whose co-authors appear nowhere else under this name
Input Space Mode Connectivity in Deep Neural Networks
ICLR 2025
Position: Humanity Faces Existential Risk from Gradual Disempowerment
ICML 2025
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
ICML 2025
Goal Misgeneralization in Deep Reinforcement Learning
ICML 2022
Nested LSTMs
ACML 2017