Confused as to whether the i.i.d assumption is needed w.r.t the samples given to the denoiser, while training diffusion models :(
Any help is appreciated
I wanted to know how the papers on my reading list fit into the bigger picture of Diffusion models. Thus I set out to write an article series. The first part is out, where we start our journey.
If interested, read here -> bit.ly/3DKiily#AI#diffusion
I was dabbling with NeRFs and came across Sparse Neural Radiance Grids (SNeRG). I built a real-time viewer for these. Reading these papers was an amazing experience.
I also wrote an article on NeRFs and SNeRG - karthiksundar.in/blog/fifth-pos…
Do give it a read, if you are interested!
Came across a cool paper, it has been out there for a while, but it was an engaging read
arxiv.org/abs/1710.08864
Surprising to find that all it takes to mess up these neural networks is a single pixel!
A quick demo of InPhotos and a face reveal of me :)
slowly getting over being camera shy
With this, done with week 2 of nights and weekends
@_buildspace@_nightsweekends
InPhotos Update:
Just added face recognition into InPhotos, and now you can search using names of the people and the context of the image.
I have posted an article about how I built it, here - karthiksundar.in/blog/fourth-po…
suggestions welcomed :)
cc: @_buildspace@_nightsweekends
Inphotos update:
Done with face recognition and integrating it with the search
This is a rough video, a full fledged demo alongside an article will be up tmrw
cc: @_buildspace@_nightsweekends
Suggestions are welcomed
#ai#ml#cv#software#showcase
InPhotos Update:
Updated the Prototype to match the new design With that, I will continue working on the next feature, facial recognition, and packaging and distributing the software.
Suggestions are always welcomed
cc: @_buildspace@_nightsweekends .
1 Followers 33 Following" phenomenal people are always born out of tiny spark, a spark we might not expect".
I always wanted to change something, something really
BIG!!!
637K Followers 35 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
24K Followers 249 Following@Cohere's research lab and open science initiative that seeks to solve complex machine learning problems. Join us in exploring the unknown, together.
46K Followers 1K Following(On mat leave.) Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS.
3K Followers 1K FollowingApplied Policy Researcher @huggingface 🤗 and Researcher at @uconn. Responsible AI Champion. Leading better AI evals with @evaluatingevals!
124K Followers 492 FollowingPrinceton CS prof. Director @PrincetonCITP. I use X to share my research and commentary on the societal impact of AI.
BOOK: AI Snake Oil. Views mine.
6K Followers 272 FollowingComputer Science Professor at Northeastern, Ex-Googler. Believes AI should be transparent. @[email protected] @davidbau.bsky.social https://t.co/wmP5LV0pJ4
30K Followers 123 FollowingMechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
42K Followers 109 Following• Center for AI Safety Director
• xAI and Scale AI advisor
• GELU/MMLU/MATH/HLE
• PhD in AI
• Analyzing AI models, companies, policies, and geopolitics
63K Followers 2K FollowingResearch Scientist at Google DeepMind (WaveNet, Imagen, Veo). I tweet about deep learning (research + software), music, generative models (personal account).
18K Followers 1K FollowingAssistProf @CarnegieMellon. Distinguished Eng @NVIDIA. Creator of @XGBoostProject, @ApacheTVM. Member https://t.co/QYyfjQNp4p, @TheASF. Views are on my own
9K Followers 16 Following@Stanford Prof. National Acad of Eng. Chief Sci @ Visual Layer & Virtue AI. Frm Sr Dir AI @Apple. Co-author of XGBoost, LIME, TextGrad, Alpaca, TVM, GraphLab.