Gowthami
3,839 posts
Gowthami
@gowthami_s
- Pleasant surprise while reading Llama 3 paper! It’s my memorization paper. 🙂 #llama3
- Crossed 1000 citations! I came to US to do a Masters as a result of quarter-life crisis. Gowthami from 5 years ago would’ve laughed at the idea of doing a PhD let alone publish and cross 1k citations! I thank folks at UMD for encouraging me on this journey, especially my
- My parents: Wake up in the morning to beat the traffic on the roads. Me: Wake up in the morning to beat the traffic on the GPU cluster. #phdlife
- All the awesome papers that came out this month are making it extra hard to focus. 😅 #phdlife #gradschool
- For ML roles, instead of asking candidates to solve a LeetCode problem, ask them to list a few prompts from a benchmark relevant to their projects. This reveals if they’re truly battle-tested or just bs-ing!
- Yesterday I completed 50% of the #30daysofDiffusion goal. I learned a lot, however, it's an information overload as well. I am going to take a couple of weeks' break and then resume. Access all the paper &tweet links here - go.umd.edu/30daysofdiffus… #Diffusion #MachineLearning
- How to train a SOTA ViT without pre-training or adding strong augmentations? Just use SAM! Check out my summary of the #ICLR22 paper by @XiangningChen, Cho-Jui Hsieh, @BoqingGo. Paper: openreview.net/forum?id=LtKcM… Blog: link.medium.com/oEzjmQaVPnb #DeepLearning #MachineLearning
- How does the choice of loss affect the transferability of classification models? Check out my summary of the #NeurIPS paper by @skornblith et al. Paper: openreview.net/forum?id=8twKp… Blog: link.medium.com/iYSvlULxsnb #DeepLearning #MachineLearning
- One of my resolutions this year is to read more papers. I decided to read 30 papers on #diffusion models this Jan and do brief tweet threads on them. This is the current schedule. Suggestions are welcome to fill the empty slots! #NewYearResolution #MachineLearning
- Got a paper into Neurips, bombed an interview. You win some, you lose some I guess. 🥲
- ML influencers be like - “my brain is broken from reading this paper” 1) you did not read this paper, you are just copy pasting gpt slop for views 2) your brain was probably broken before otherwise you won’t be posting this shit. #banthetechfluencers
- InstructPix2Pix: Edit an image using text guidance using a single forward pass. Why use any inversion or other stuff,just create a dataset using inversion techniques and train a new model. A 🧶 Paper: arxiv.org/abs/2211.09800 Day 8 #30daysofDiffusion #Diffusion #MachineLearning
- Summer internship in NYC🗽 Expectation: Socialize, soak up the culture, visit museums, shows, etc. Reality: Start project, a broadway show, get scooped, CVPR, work on new idea, Neurips reviews, debug, midterm talk, debug, Neurips rebuttal, final talk. The end. #phdlife 🤦♀️
