4 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must behave well beyond the specific state-action combinations obs...
The linear representation hypothesis holds that pretrained vision models encode generative factors as linearly decodable directions in feature space, and comes with a standard methodology: train a linear probe, declare a factor represented if accuracy is high. We show this test is too permissive. Asymptotically, any su...
This work computationally extracts population codes from macaque electrophysiology datasets spanning V4 and IT cortex and vision models, introduces an automated method to measure representation interpretability and diversity, and demonstrates through targeted ablations that interpretable representations play a causal r...
DSReg (Dependency-Sparsity Regularization) recovers individual world latents up to signed permutation, without reconstruction or a decoder, without reconstruction or a decoder, and establishes the first fully identifiable JEPA that recovers every world latent.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
