Ipsit ✈️ NeurIPS 2024

First time attending @neuripsconf.bsky.social to present my paper. Any tips on how to make the most of the conference?
#NeurIPS2024

Me 👋

Can you please add me too?🙏

Graph structure typically influences only node embeddings in GNNs. What if activation functions were graph-adaptive too? Introducing DiGRAF: a novel activation function for GNNs powered by learnable diffeomorphisms. Discover more at our poster #33 tomorrow at @logconference.bsky.social 🧠📈

Can you please add me🙏

Please add me 🙏

Can you please add me?

P.S. I have exciting ideas on all things geometry - ranging from neural operators to weight spaces to 3D vision to invariant/equivariant representation learning. Happy to connect and chat. I’m attending NeurIPS

DiGRAF: Diffeomorphic Graph-Adaptive Activation Function In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible activation functions, ...

Passionate about exploring geometric deep learning, I aim to design AI systems that leverage natural symmetries and invariances for robustness, interpretability, and efficiency. See, my recent works accepted at @neuripsconf.bsky.social
arxiv.org/abs/2407.02013
openreview.net/forum?id=FFQ...

DiGRAF: Diffeomorphic Graph-Adaptive Activation Function In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible activation functions, ...

My paper DiGRAF got into NeurIPS 2024. I’m looking for PhD positions in equivariant representation and geometric deep learning. Happy to have a coffee chat !!! arxiv.org/abs/2407.02013

New here. Anyone attending NeurIPS 2024?