1 citations · 2 across the 3 of their papers we have counts for
3 papers
cs.LG2024
Next state prediction gives rise to entangled, yet compositional representations of objects
Tankred Saanum, Luca M. Schulze Buschoff, Peter Dayan +1
Compositional representations are thought to enable humans to generalize across combinatorially vast state spaces. Models with learnable object slots, which encode information abou…
cs.LG2024★ 1 cited
Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models
Can Demircan, Tankred Saanum, Akshay K. Jagadish +2
In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learnin…
cs.LG2022★ 1 cited
Learning Parsimonious Dynamics for Generalization in Reinforcement Learning
Tankred Saanum, Eric Schulz
Humans are skillful navigators: We aptly maneuver through new places, realize when we are back at a location we have seen before, and can even conceive of shortcuts that go through…