Daniel Tian Levy (@dnllvy) profile picture

PhD candidate at @McGillU and @Mila_Quebec Working on AI for Science

Joined June 2022
Photo by Daniel Tian Levy (@dnllvy)Photo by Daniel Tian Levy (@dnllvy)Photo by Daniel Tian Levy (@dnllvy)Photo by Daniel Tian Levy (@dnllvy)Photo by Daniel Tian Levy (@dnllvy)Photo by Daniel Tian Levy (@dnllvy)
Daniel Tian Levy retweeted
"Equivariance matters even more at larger scales" ~ arxiv.org/abs/2510.09768 All the more reason we need scalable architectures with symmetry awareness. I know this is an obvious ask but I'm still confident that scaling and inductive bias need not be at odds. This paper (alongside arxiv.org/abs/2410.23179) is convincing evidence that believing "equivariance is dead/not necessary" and "scaling is all you need" might be myopic (ofc, no one has made this *strong* claim but it still seems to be an existing "community myth" of sorts) Stay tuned to this space – we're dropping something cool on this topic veryyy soon ;)
1
22
1
182
13,217
Daniel Tian Levy retweeted
Symmetry is the fundamental property of crystals, yet generative models don't yield crystals with realistic symmetries We solved that with SymmCD and can get crystals from any of the 230 space groups Learn more at our #ICLR poster w/@dnllvy @sibasmarak arxiv.org/abs/2502.03638 🧵
5
10
1
41
5,463
Daniel Tian Levy retweeted
⚛️🤗 Announcing LeMaterial ⚛️🤗 @huggingface & @entalpic_ai are teaming up to release LeMaterial -- an open source initiative aiming to facilitate (AI for) materials discovery ! Datasets, hash function, tools to explore the chemical space & more ! huggingface.co/blog/lemateri…
4
27
3
93
10,121
Thrilled to launch EquiAdapt! 🚀 A library for equivariant adaptation of neural networks, including SAM by @AIatMeta, making them robust to transformations without losing efficiency: github.com/arnab39/equiadapt w/ @ArnabMondal96 @DanieBenes @sekoumarkaba @GagnonJikael 🧵
3
24
2
92
12,181
Daniel Tian Levy retweeted
Want to make your model equivariant to certain known transformations without changing the network architecture? Please attend our contributed talk at 11AM @neur_reps to know how we achieve this by adding a simple shallow network that learns to canonicalize the input. #NeurIPS2022