AI Undergraduate Club at Cornell
@cuai_cornell
Followers
346
Following
37
Media
1
Statuses
31
Cornell Undergraduate Club for AI/ML Research. Registered Student Organization of Cornell University.
Ithaca, New York
Joined August 2020
Excited to share a new framework to design provably efficient inverse reinforcement learning algorithms, to appear at #ICML2024. Special thanks to all my collaborator, especially @g_k_swamy for his incredible mentorship! Check out his tweet for more info! https://t.co/zcfRtRhg1F
It took a lot of work over multiple years but I'm proud to be able to finally share my first #ICML2024 paper: a new, fundamental framework for designing efficient inverse RL algorithms that we're in the process of scaling to real robots: https://t.co/Ebo9Kzsmtq! 1/
0
10
27
I’m excited to share that this Fall I will start a PhD at @MITEECS, supported by the NSF Graduate Research Fellowship Program!
22
6
258
I am elated to present our new NeurIPS 2023 paper, "Riemannian Residual Neural Networks," together with @ericmchen1, @sholalkere, Anna Asch, @aaron_lou, @sernamlim, @chrismdesa! Arxiv: https://t.co/ovJ5R0wJPo Github: https://t.co/gfHMxXQzm2
3
10
42
🤔 Using the dot product as the similarity measure for vision-language foundation models such as CLIP has been the go-to choice. But in our #NeurIPS2023 paper, we showed that CLIP is pre-trained to work the best with another equally simple similarity measure. 🧵(0/n)
7
31
230
Thank you @_akhaliq for sharing! At #ICCV2023, we will present a light-field-inspired method for viewpoint control over generative image models! Come visit our poster on Friday!
Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation abs: https://t.co/3zJFG2YelS project page: https://t.co/isNUrKgJ1m
1
9
65
Come see our talk about Faces Through Time tomorrow at #Eurographics2023! It will be at the Faces session (FP10) from 15:30 - 17:00 Paper: https://t.co/FHSd7g4WnS Thank you to my co-authors Jin Sun, @apoorvkh, @DaniLischinski, @Jimantha, @ElorHadar for making this possible!
2
6
23
Presenting Reflected Diffusion Models w/ @StefanoErmon! Diffusion models should reverse a SDE, but common hacks break this. We provide a fix through a general framework. Arxiv: https://t.co/5ov4mm3rU4 Github: https://t.co/HlagPOGJeU Blog: https://t.co/glGw3DuTEe 🧵(1/n)
12
80
334
Paraphrase Identification models are notoriously fragile from distribution. We identify that manually designed negative samples in the dataset might be a cause! Please check out our #NeurIPS2022 poster on Tue Nov 29 04:00 PM -- 06:00 PM @ Hall J #232! (1/5)
1
2
17
Excited to meet with friends and have a @cuai_cornell reunion at my first in-person conference! @cHHillee
0
1
21
Fantastic SignNet presentation at the TAG in ML Workshop @icmlconf by @dereklim_lzh @Josh_d_robinson 🤗 https://t.co/dsh0ebwF0X
2
2
55
0
0
3
CUAI and alumni at the Topology, Algebra, Geometry in ML workshop. Thank you @TAGinDS for organizing!
2
5
37
Congratulations to Isay! Isay is one of the original key people who helped found the club, secure funding, and served as co-president for the first 2 years!
Happy to announce that I will be joining @Yale to do a PhD in applied mathematics with Prof. Anna Gilbert @annacgilbert after I graduate from @Cornell! A big thank you to my collaborators, advisors, friends, and family for helping me throughout this journey.
1
0
6
Very happy to announce that I’ll be starting my PhD @Berkeley_EECS in the fall! I feel immensely grateful to all my collaborators, advisors, and friends for helping me on this journey. Looking forward to the next chapter of my life!
9
3
143
@aaron_lou @dereklim_lzh @sernamlim @chrismdesa We will be presenting Equivariant Manifold Flows at NeurIPS 2021 shortly, at the 7:30-9:00 EST poster session. Come and chat with us! :) We're at Poster Spot E2 in the gather town. Paper: https://t.co/S1GkKikgcz Code: https://t.co/Wl0B9Mnhh6
0
1
5
Excited about our new NeurIPS paper: “Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods”. @dereklim_lzh @Felix_Hohne @sernamlim et al. arXiv: https://t.co/Tve7eJ2ArQ Data/Code: https://t.co/7yWeBG7c2R 1/
3
19
68
I am happy to present our new work, “Equivariant Manifold Flows”, together with @aaron_lou, @dereklim_lzh, Qingxuan Jiang, @sernamlim, @chrismdesa! Arxiv: https://t.co/S1GkKikgcz
4
23
91
All done @cs_cornell @CornellCIS. The 4 of us are now off to PhDs @MIT @Stanford! With @aaron_lou, @qhwang3, Max (Qingxuan) Jiang, and Dean Kavita Bala
6
5
44
Congratulations to one of our newer members, Derek Lim! Good luck on the next leg in your journey.
I'll be joining the MIT EECS PhD program in Fall 2021! I feel very grateful, thankful, and lucky. Thanks to everyone and everything that has worked with me and helped me! Very excited to start on some good research.
0
1
12
Congratulations to CUAI members @dereklim_lzh @xiuyu_l @Felix_Hohne for their new paper on non-homophilous graph datasets!
Our new paper: “New Benchmarks for Learning on Non-Homophilous Graphs” in the Graph Learning Benchmarks Workshop at WWW 2021. @xiuyu_l @Felix_Hohne @sernamlim arXiv: https://t.co/E7IJrUg9VM Data/Code: https://t.co/RHkObKVJ1h 1/
0
0
8