Davin Hill (@davinhill_) profile picture

Davin Hill

@davinhill_

PhD Candidate at Northeastern University

 Boston, MA
davinhill.me
Joined July 2022
  • Tweets12
  • Following78
  • Followers34
Excited to present "LVT: Large-Scale Scene Reconstruction via Local View Transformers" at @SIGGRAPHAsia 2025, Hong Kong 🏙️ 💡Linear-complexity, large-scale scene reconstruction in a single inference pass! ⚡Fast-forward: Mon 9am HKT (Hall 3F) 🗣️ Technical Presentation: Thu 1:10pm HKT (S426) 🔗 Project Page: toobaimt.github.io/lvt/ 📄 Paper: dl.acm.org/doi/10.1145/37573… Work done during my internship at @Google Beam, with my amazing collaborators John Flynn, @lucyrchai, Kathryn Heal, @XuanLuo14, and Jungyeon Park ✨ #ACMSIGGRAPH #SIGGRAPHAsia2025 #3DGS
1
15
1
17
2,284
Excited to share that our paper "STAR: Stability Inducing Weight Perturbation for Continual Learning" has been accepted to #ICLR2025 🥳! Openreview link: openreview.net/forum?id=6N5O… Check out more work from our lab at mllabneu.github.io
Image from Masih Eskandar (@meskandars)
1
2
10
489
Interested in robustness and uncertainty in XAI? Come check out our posters at #AISTATS2024 this week! Thursday: arxiv.org/abs/2206.12481 Saturday: arxiv.org/abs/2210.02419 @zq90 @drsandeshgh @MaxTee1996 @JoshBone18 @mllabneu
Analyzing Explainer Robustness via Probabilistic Lipschitzness of...

Analyzing Explainer Robustness via Probabilistic Lipschitzness of...

Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explainers are often...

arxiv.org
7
13
975
Congratulations to Davin and the team for getting the paper accepted in @aistats_conf arxiv.org/pdf/2210.02419… Nice work showing the importance of boundary awareness in explainability and the uncertainty in explanations @davinhill_ @MaxTee1996
2
5
551
Please read the paper for more details: medrxiv.org/content/10.1101/… All code available here: github.com/Google-Health/gen… Also see the related work by collaborators: medrxiv.org/content/10.1101/…
Unsupervised representation learning improves genomic discovery for lung function and respiratory...

Unsupervised representation learning improves genomic discovery for lung function and respiratory...

Background High-dimensional clinical data are becoming more accessible in biobank-scale datasets. However, accurately phenotyping high-dimensional clinical data remains a major impediment to genetic...

medrxiv.org
1
2
10
1,084
We’re excited to describe new @GoogleHealth work that makes phenotyping more scalable. An unsupervised deep learning method, REpresentation learning for Genetic discovery on Low-dimensional Embeddings (REGLE), to perform GWAS on high-dimensional clinical data.
1
23
1
113
31,970
Happy #PiDay! Did you know that: 1- you can hear the sound of pi? youtube.com/watch?v=YOQb_mtk… 2- If you round pi to the nearest integer, you get the number of days till the early registration at #AISTATS closes? virtual.aistats.org/Conferen…
6
8
1,595
Did you know that this year's AISTATS is hosted in sunny Valencia? Now is your chance to enjoy the sunny beaches & learn about the latest & greatest in the ML. Fill out an application to serve as a volunteer and get a free conference registration here virtual.aistats.org/Voluntee…
Image from AISTATS Conference (@aistats_conf)
9
1
56
13,288
If you have a larger number of nominations than is practical to enter individually, then please get in touch with our workflow chairs Christian (@chris_naesseth) and Davin (@davinhill_)
2
5
AISTATS is accepting nominations for reviewers, meta-reviewers, and program commitee members (including self-nominations). You can submit nominations here: forms.gle/5HmYFiNCHfEm7ipt9
1
15
2
50
Load more