Sign in

Gowthami Somepalli

@gowthami.bsky.social
2.3K followers 190 following 29 posts

PhD-ing at UMD. Knows a little about multimodal generative models. Check out my website to know more - somepago.github.io

PostsRepliesMedia
Reposted by Gowthami Somepalli
Matthew McDowell-Sweet @msweet.net · 21/01/2025
What’s the right resolution for such ontologies? 1,000-10,000 seems like the sweet spot. H/t @aneeshsathe.com aneeshsathe.com/2025/01/15/d...
aneeshsathe.com
Domain Ontologies: Indispensable for Knowledge Graph Construction
AI slop is all around and increasingly extraction of useful information will face difficulties as we start to feed more noise into the already noisy world of knowledge. We are in an era of unpreced…
052
Reposted by Gowthami Somepalli
Rosanne Liu @rosanneliu.com · 19/12/2024
About to send my last DLCT email of the year today (in 2 hours). Join the 7-year-old mailing list if you haven't heard of it. (And if you have heard of it but haven't joined, I trust that it's a well thought decision that suits you the best.) groups.google.com/g/deep-learn...
groups.google.com
Deep Learning Classics and Trends - Google Groups
0132
Reposted by Gowthami Somepalli
Sander Dieleman @sedielem.bsky.social · 18/12/2024
The recording of my #NeurIPS2024 workshop talk on multimodal iterative refinement is now available to everyone who registered: neurips.cc/virtual/2024... My talk starts at 1:10:45 into the recording. I believe this will be made publicly available eventually, but I'm not sure when exactly!
neurips.cc
Adaptive Foundation Models: Evolving AI for Personalized and Efficient LearningNeurIPS 2024
1364
Reposted by Gowthami Somepalli
Sai Kumar Dwivedi @saidwivedi.in · 08/12/2024
One of the best tutorials for understanding Transformers! 📽️ Watch here: www.youtube.com/watch?v=bMXq... Big thanks to @giffmana.ai for this excellent content! 🙌
youtube.com
[M2L 2024] Transformers - Lucas Beyer
YouTube video by Mediterranean Machine Learning (M2L) summer school
0548
Reposted by Gowthami Somepalli
Mathurin Massias @mathurinmassias.bsky.social · 27/11/2024
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
1235299
Reposted by Gowthami Somepalli
kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 27/11/2024
congratulations, @ian-goodfellow.bsky.social, for the test-of-time award at @neuripsconf.bsky.social! this award reminds me of how GAN started with this one email ian sent to the Mila (then Lisa) lab mailing list in May 2014. super insightful and amazing execution!
318727
Reposted by Gowthami Somepalli
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 25/11/2024
Trying to build a "books you must read" list for my lab that everyone gets when they enter. Right now its: - Sutton and Barto - The Structure of Scientific Revolutions - Strunk and White - Maybe "Prediction, Learning, and Games", TBD Kinda curious what's missing in an RL / science curriculum
3614111
Reposted by Gowthami Somepalli
Shubhendu Trivedi @shubhendu.bsky.social · 25/11/2024
This is a simple and good paper, which somehow nobody working on these things cites, or even seems to be aware of arxiv.org/abs/2406.05213 It is simple idea that seems useful; it formulates the subjective uncertainty for natural language generation in a decision-theoretic setup.
arxiv.org
On Subjective Uncertainty Quantification and Calibration in Natural Language Generation
Applications of large language models often involve the generation of free-form responses, in which case uncertainty quantification becomes challenging. This is due to the need to identify task-specif...
2273
Reposted by Gowthami Somepalli
Lucas Beyer (bl16) @giffmana.ai · 23/11/2024
A real-time (or very fast) open-source txt2video model dropped: LTXV. HF: huggingface.co/Lightricks/L... Gradio: huggingface.co/spaces/Light... Github: github.com/Lightricks/L... Look at that prompt example though. Need to be a proper writer to get that quality.
68910
Reposted by Gowthami Somepalli
Ben Recht @beenwrekt.bsky.social · 22/11/2024
Perhaps an unpopular opinion, but I don't think the problem with Large Language Model evaluations is the lack of error bars.
1. Computing standard errors of the mean using the Central Limit Theorem

2. When questions are drawn in related groups, computing clustered standard errors

3. Reducing variance by resampling answers and by analyzing next-token probabilities

4. When two models are being compared, conducting statistical inference on the questionlevel paired differences, rather than the population-level summary statistics

5. Using power analysis to determine whether an eval (or a random subsample) is capable of testing a hypothesis of interest
91105
Reposted by Gowthami Somepalli
kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 22/11/2024
let me say it once more: "the gap between OAI/Anthropic/Meta/etc. and a large group of companies all over the world you've never cared to know of, in terms of LM pre-training? tiny"
12767
Reposted by Gowthami Somepalli
Andrei Bursuc @abursuc.bsky.social · 22/11/2024
The return of the Autoregressive Image Model: AIMv2 now going multimodal. Excellent work by @alaaelnouby.bsky.social & team with code and checkpoints already up: arxiv.org/abs/2411.14402
1468
Reposted by Gowthami Somepalli
David Picard @davidpicard.eurosky.social · 22/11/2024
Interesting paper on arxiv this morning: arxiv.org/abs/2411.13683 It's a video masked autoencoder in which you learn which tokens to mask to process fewer of them and scale to longer videos. It's a #NeurIPS2024 apparently. I wonder if there could be such strategy in the pure generative setup.
arxiv.org
Extending Video Masked Autoencoders to 128 frames
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) ...
0474
Gowthami Somepalli @gowthami.bsky.social · 22/11/2024
I’m not getting notifications for comments here, anyone facing the same issue?
100
Reposted by Gowthami Somepalli
Mimansa Jaiswal @mimansaj.bsky.social · 22/11/2024
You might enjoy this list I have:
mimansajaiswal.github.io
What softwares do I actually use on my Mac as a software enthusiast? • Mimansa Jaiswal
With several years of using a Mac, it took me time to settle down on a set of apps and softwares that I can heartily recommend. I try almost 30 a month, but end up using around 20 in total for everyth...
3153
Reposted by Gowthami Somepalli
Sasha Rush @srushnlp.bsky.social · 21/11/2024
Discrete diffusion has become a very hot topic again this year. Dozens of interesting ICLR submissions and some exciting attempts at scaling. Here's a bibliography on the topic from the Kuleshov group (my open office neighbors). github.com/kuleshov-gro...
github.com
GitHub - kuleshov-group/awesome-discrete-diffusion-models: A curated list for awesome discrete diffusion models resources.
A curated list for awesome discrete diffusion models resources. - kuleshov-group/awesome-discrete-diffusion-models
17610
Gowthami Somepalli @gowthami.bsky.social · 21/11/2024
I only got to know today this awesome diffusion starter pack exists! I’ll try to fill up my generative models pack with some complementary folks. :)
060
Gowthami Somepalli @gowthami.bsky.social · 21/11/2024
Can people create accounts here without invite now? 🤔
550
Gowthami Somepalli @gowthami.bsky.social · 21/11/2024
I would miss not having a character limit since my rants grew larger, longer I’m in grad school! 😅
240
Gowthami Somepalli @gowthami.bsky.social · 21/11/2024
Started a list of some researchers working on image/video generation. (Not comprehensive at all) Reply with a paper link and TLDR to get added to the list! I request all grad students to not feel imposter-y and just reply if you work in this field! #computervision #diffusion go.bsky.app/SP1uWoE
13348
Reposted by Gowthami Somepalli
Lucas Beyer (bl16) @giffmana.ai · 20/11/2024
www.astralcodexten.com/p/how-did-yo...
89818
Reposted by Gowthami Somepalli
Kosta Derpanis @csprofkgd.bsky.social · 19/11/2024
My growing list of #computervision researchers on Bsky. Missed you? Let me know. go.bsky.app/M7HGC3Y
8813242
Gowthami Somepalli @gowthami.bsky.social · 20/11/2024
I think we broke the app! I’m trying to retweet something and it’s not working! 😅
030
Reposted by Gowthami Somepalli
Chris Offner @chrisoffner3d.bsky.social · 20/11/2024
Importantly, starter packs are intended as a way for newcomers to the platform to conveniently get started with finding people from their community. They cannot and should not be considered authoritative “VIP lists.”
151
Gowthami Somepalli @gowthami.bsky.social · 20/11/2024
Need bookmarks features asap! 🥺 @bsky.app
0161
Reposted by Gowthami Somepalli
David Picard @davidpicard.eurosky.social · 19/11/2024
I'm slowly putting my intro to ML course material on github, starting with the lab sessions: github.com/davidpicard/... These are self-contained notebooks in which you have to implement famous algorithms from the literature (k-NN, SVM, DT, etc), with a custom dataset that I (painstakingly) made!
49815
Gowthami Somepalli @gowthami.bsky.social · 19/11/2024
What are some must-read multimodal generation papers? I am looking for vision-language models (preferably jointly trained from scratch). Some examples - Chameleon - arxiv.org/abs/2405.09818 Transfusion - arxiv.org/abs/2408.11039 JanusFlow - arxiv.org/abs/2411.07975 #computervision #multimodal
1273
Reposted by Gowthami Somepalli
Aaron Hertzmann @aaronhertzmann.com · 11/11/2024
6 years ago, in the days of GAN art, I wrote an article called "Can Computers Create Art?", arguing that computers should not be considered artists, regardless of how good image generation gets. People sometimes ask if my views have changed. I say, 1/🧵 www.mdpi.com/2076-0752/7/...
mdpi.com
Can Computers Create Art?
This essay discusses whether computers, using Artificial Intelligence (AI), could create art. First, the history of technologies that automated aspects of art is surveyed, including photography and an...
35217
Reposted by Gowthami Somepalli
Chris Offner @chrisoffner3d.bsky.social · 11/11/2024
Here's my attempt at assembling a starter pack of the still nascent computer vision community on Bluesky. Feel free to recommend other accounts that should be in this starter pack. :) #computervision (Do we use hashtags here? 😅) go.bsky.app/PkAKJu5
155216