Jaley Dholakiya

always surprised by math intuition,Senior Datatscientist at Walmart

[Jaley Dholakiya @crazymuse_ai]

@TeamYouTube @TeamYouTube Thanks a lot for responding, since I have been trying now for months to contact google support to help me with this.

[Jaley Dholakiya @crazymuse_ai]

@Google Hi, I have had my email password changed while I was asleep. How do I remove/block the account at the least?

[Riley Goodside @goodside]

this is wild — kNN using a gzip-based distance metric outperforms BERT and other neural methods for OOD sentence classification

intuition: 2 texts similar if cat-ing one to the other barely increases gzip size

no training, no tuning, no params — this is the entire algorithm:

[Aritra 🤗 @ariG23498]

Proud to have worked on it!

[Sayak Paul @RisingSayak]

CVPR'23 is starting this Sunday 🔥

Our (with @hila_chefer) tutorial - "All Thins ViTs" is also ready to go. The website is updated w/ all the latest details. Drop by if you're attending (physically or virtually)!

We'll also have @MokadyRon as our guest!

https://t.co/eXfdnvcMQ1

[Ram Prakash H @_rampi_]

We're all set for the beta launch of The School of AI, an AI-assisted self-study platform for mastering AI/ML concepts. Join the waitlist now at https://t.co/iqHq1IMDy5

#AI #ML #Education #BetaLaunch

[Vision and AI Lab, IISc @val_iisc]

Indian PhD students from @iiscbangalore, who have first-authored papers at prestigious conferences like @CVPR, are facing unjust denials of Canadian visas. With Shocking reasons "limited employment possibilities in India" and "purpose of visit not consistent with a temp. stay."

[Jaley Dholakiya @crazymuse_ai]

@karpathy Totally agree

[Sayak Paul @RisingSayak]

The pipeline has two options:

1. Going from a source concept to a target concept ("cat -> dog" as shown above) with an input prompt.
2. Option 2, but with the support of conditioning the pipeline on a real input image (see below)

[Amro @amrostill]

@DeepMind 5 Act structure?

[Sundar Pichai @sundarpichai]

1/ From today's AI@ event: we announced our Imagen text-to-image model is coming soon to AI Test Kitchen. And for the 1st time, we shared an AI-generated super-resolution video using Phenaki to generate long, coherent videos from text prompts and Imagen Video to increase quality.

[Jaley Dholakiya @crazymuse_ai]

@RisingSayak @huggingface Congratulations Sayak, this is really amazing.

[Jaley Dholakiya @crazymuse_ai]

@KurkureSnacks why is solid masti flavor not available in bangalore?

[Christopher Travers, PhD @DrCT_Phats]

I received a series of rejections this week. It hurts, i won’t deny it. When I started to internalize them, I called one of my bros and he helped me remember that I’m so much more than any opportunity or accomplishment. In short it’s okay to let your folks know when youre down ❤️

[Jaley Dholakiya @crazymuse_ai]

@shiprocket.in I tried ordering three times, but no one is picking the order. Even the customer service is not able help. Please help us, or we will move to some other platform. #shiprocket

[Devi Parikh @deviparikh]

A version of a note I wrote recently on how I sustain and how I approach work-life balance.

https://t.co/sPadE6AbvT

[TensorFlow @TensorFlow]

🥳 Introducing TensorFlow Similarity!

Our newest python package is focused on making similarity learning quick and easy, and is now in Beta.

Full details ↓ https://t.co/9T8o8rz3XZ

[Aran Komatsuzaki @arankomatsuzaki]

H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

Gains +6 points on average on the Long
Range Arena benchmark over the subquadratic alternatives.

Sets a new SOTA ppl on One-Billion Word
dataset with 5x fewer model parameters.

https://t.co/bP66VDZ8de

[Prof. Feynman @ProfFeynman]

Being wrong is not a bad thing like they teach you in school. It is an opportunity to learn something.

There are no mistakes, only lessons. Growth is a process of trial and error. 🧠

[Bojan Tunguz @tunguz]

This is how pros do it