Archana Swaminathan

PhD student at @umdcs | ML, CV and the likes

[Namitha Padmanabhan @namithap10]

@VirginAtlantic It's been 4 days since my BLR→BOM→LHR→IAD trip and there's still no sign of my bags. BOM→LHR leg was delayed and I missed my connection. Was rebooked onto @united, arriving 19 hours late. But my bags never made it to IAD! @united says they never scanned them.

[Archana Swaminathan @TweetsArchana]

@rpobengaluru no update since police verification done a month ago, please share an update. Application number BN1GE6939056924.

[Archana Swaminathan @TweetsArchana]

@eccvconf @abhi2610 @learn2phoenix @kamalgupta09 Work done with @learn2phoenix , @kamalgupta09, Shishira, Vatsal and my awesome advisor @abhi2610.

[Archana Swaminathan @TweetsArchana]

We introduce LEIA, a novel approach for representing 3D articulated objects by learning view-invariant latent embeddings for different articulation states. Visit our poster #299 at @eccvconf #ECCV2024 in Milan on Oct 3rd (Thursday), 10:30am.
Project Page: https://t.co/lZhP6gfexu

[Archana Swaminathan @TweetsArchana]

@eccvconf @abhi2610 @learn2phoenix @kamalgupta09 We see consistent improvement over previous SoTA that was limited to single-part articulation. Additionally, we also show the latent space can be disentangled for representing different object part motion!

[Archana Swaminathan @TweetsArchana]

@eccvconf @abhi2610 @learn2phoenix @kamalgupta09 In conjunction with a hypernetwork that modulates the NeRF weights, LEIA can linearly interpolate between the learned embedding space to generate unseen in-between articulation states. It's robust to both single and multi-part articulation!

[Archana Swaminathan @TweetsArchana]

@eccvconf @abhi2610 @learn2phoenix @kamalgupta09 LEIA is a method of generating unseen articulation states from just observing start and end state of articulation. We have a learnable latent dictionary for state-specific embeddings, and then enforce a manifold loss for structure in latent space.

[Soumik Mukhopadhyay @soumikkanad]

Unconditional #diffusion pretraining learns discriminative representation; hence are great candidates for Unified Models for #GenAI as well as #recognition.
Please join us at our #DiffSSL poster (#101) at #ECCV on 1 Oct 1030AM.
@eccvconf

[Namitha Padmanabhan @namithap10]

I will be speaking about my work in INRs (https://t.co/BS1T05B6MU) at the INRV workshop at #CVPR2024. Come see me in Summit 335-336 at 5PM on Tuesday!

[Archana Swaminathan @TweetsArchana]

@gadelha_m Thank you! I have sent you an email.

[Archana Swaminathan @TweetsArchana]

@gadelha_m Hi Matheus, I’m a 2nd year PhD student at UMD , is there an email ID I can send my CV to? Your DMs are not open!

[Nirat Saini @saini_nirat]

🍎 Imagine chopping an apple: each slice, a new shape, a new stats. Now, imagine teaching a computer to recognize each slice & even predict the next! 🤖 How can AI understand the subtle changes from a whole apple to a sliced one, and apply this knowledge universally? 🤔

[Kamal Gupta @kamalgupta09]

Compositional Generalization is going to be the next big milestone in #GenAI and we need better datasets and benchmarks to make progress.

Checkout our work Chop-N-Learn at #ICCV2023!
https://t.co/5jcm0lXnqY

[Soumik Mukhopadhyay @soumikkanad]

Dubbing feels unnatural due to unsynced lips & audio.
Presenting "Diff2Lip: Audio Conditioned Diffusion Models for Lip-Synchronization"

tl;dr:
#Diff2Lip:arbirary speech+face video→hq lip-sync

website:https://t.co/24fK8uaRI8
arxiv:https://t.co/uR2V7uhVks
@_sakshams_ @abhi2610🧵

[Soumik Mukhopadhyay @soumikkanad]

Have you ever wondered if generative models like #diffusion models inherently can solve discriminative tasks?

Presenting our work:
"Diffusion Models Beat GANs on Image Classification"

arxiv: https://t.co/e8elMf4Rts
website: https://t.co/VXxA0CBYsg
hf: https://t.co/tmoWfyLfVM🧵

[Shramay Palta @PaltaShramay]

Paper Alert!! 📜🧨 #ACL2023NLP #NLProc
FORK: A Bite-Sized Test Set for Probing Culinary Cultural Biases in Commonsense Reasoning Models.
Work done with @rachelrudinger at @ClipUmd
Details in 🧵(1/n) :

[Archana Swaminathan @TweetsArchana]

@damnwolfgirl you should try her Iron series tooo

[Archana Swaminathan @TweetsArchana]

@__mroody__ omg totes😭

[Archana Swaminathan @TweetsArchana]

i change my Apple Watch face everyday to match the colour of my outfit and it feels nice 💅

[Archana Swaminathan @TweetsArchana]

two years in deep learning research and I still prefer to use print statements to debug instead of pdb 🥲