Qiyao (Catherine) Liang @ ICML
@catherineliangq
Ph.D. student at MIT EECS @FieteGroup, AI + neuro, formerly quantum computing
I will be presenting the poster Thu 17 Jul 2 p.m. EDT — 4:30 p.m. EDT at East Exhibition Hall A-B #E-2903, come say hi ; )
Curious why disentangled representation is insufficient for compositional generalization?🧐 Our new ICML study reveals that standard decoders re-entangle factors in deep layers. By enforcing disentangled rendering in pixel space, we unlock efficient, robust OOD generalization!🙌
Nature research paper: Global modules robustly emerge from local interactions and smooth gradients go.nature.com/3EK6y2N
Meet Willow: Our state-of-the-art quantum chip. It's the first quantum chip to show exponential error reduction as qubits scale, paving the way for large-scale, fault-tolerant quantum computers. Dive in → go.nature.com/3OKVLY6
I will be presenting our results at #NeurIPS2024 on Friday 11-2 at East Exhibit Hall A-C #1608. Drop by and say hi😊
How do diffusion models factorize and generalize? Extending our previous work (arXiv:2402.03305), @ZimingLiu11 @neurostrow @FieteGroup and I further peaked into the model’s internal representation in relation to its ability to compose and generalize arxiv.org/abs/2408.13256.