Ma, George

4 publications

NeurIPS 2025 Revising and Falsifying Sparse Autoencoder Feature Explanations George Ma, Samuel Pfrommer, Somayeh Sojoudi

NeurIPS 2024 A Canonicalization Perspective on Invariant and Equivariant Learning George Ma, Yifei Wang, Derek Lim, Stefanie Jegelka, Yisen Wang

NeurIPSW 2023 Baking Symmetry into GFlowNets George Ma, Emmanuel Bengio, Yoshua Bengio, Dinghuai Zhang

NeurIPS 2023 Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding George Ma, Yifei Wang, Yisen Wang