Ishan Khatri
@ishan.khatri.io
Researching computer vision stuff at Stack AV in Pittsburgh. Also on Twitter @i_ikhatri
This is a real rebuttal from the papers I am reviewing at NeurIPS... the reviewer who wrote this gave the paper a 2 (reject) with a confidence of 5 (absolutely certain & familiar with all related work, the highest confidence available).
What the hell are we even doing here...?
What the hell are we even doing here...?
August 5, 2025 at 4:03 AM
This is a real rebuttal from the papers I am reviewing at NeurIPS... the reviewer who wrote this gave the paper a 2 (reject) with a confidence of 5 (absolutely certain & familiar with all related work, the highest confidence available).
What the hell are we even doing here...?
What the hell are we even doing here...?
On my way to @cvprconference.bsky.social! Catch our presentation on the 2025 Argoverse challenges at the Workshop on Autonomous Driving tomorrow at 11:30am in Grand C1!
June 10, 2025 at 11:13 PM
On my way to @cvprconference.bsky.social! Catch our presentation on the 2025 Argoverse challenges at the Workshop on Autonomous Driving tomorrow at 11:30am in Grand C1!
Given a natural language text prompt Ex: "vehicles slowing down for a jaywalker" the goal is to identify, detect & track the relevant actors in the scene. All sensor & map data can be used, and we encourage teams to use pre-trained models as well.
April 22, 2025 at 12:15 AM
Given a natural language text prompt Ex: "vehicles slowing down for a jaywalker" the goal is to identify, detect & track the relevant actors in the scene. All sensor & map data can be used, and we encourage teams to use pre-trained models as well.
Just over a month left to submit to this year's Argoverse 2 challenges! Returning from previous years, are our motion forecasting and lidar scene flow challenges. And NEW for this year with a $10k prize pool is our Scenario Mining challenge!🧵👇
April 22, 2025 at 12:15 AM
Just over a month left to submit to this year's Argoverse 2 challenges! Returning from previous years, are our motion forecasting and lidar scene flow challenges. And NEW for this year with a $10k prize pool is our Scenario Mining challenge!🧵👇
On my way to Singapore for ICLR! If you want to chat about vision or robots, hit me up!
April 19, 2025 at 7:56 PM
On my way to Singapore for ICLR! If you want to chat about vision or robots, hit me up!
Was cleaning out some random papers from my desk and found this shipping receipt from @bhphoto.com from last year when they sent me my SD card that I left in a camera I returned.
I didn’t even realize I left it in there until it showed up at my doorstep. This is why I’ll be a B&H customer for life.
I didn’t even realize I left it in there until it showed up at my doorstep. This is why I’ll be a B&H customer for life.
April 6, 2025 at 6:51 PM
Was cleaning out some random papers from my desk and found this shipping receipt from @bhphoto.com from last year when they sent me my SD card that I left in a camera I returned.
I didn’t even realize I left it in there until it showed up at my doorstep. This is why I’ll be a B&H customer for life.
I didn’t even realize I left it in there until it showed up at my doorstep. This is why I’ll be a B&H customer for life.
MOE really refers to making a certain part of the architecture sparse to save computation. I think that “sparsity” is a better layman’s explanation than “topic experts”. There’s a really good example in this blog. newsletter.maartengrootendorst.com/p/a-visual-g...
January 27, 2025 at 9:25 PM
MOE really refers to making a certain part of the architecture sparse to save computation. I think that “sparsity” is a better layman’s explanation than “topic experts”. There’s a really good example in this blog. newsletter.maartengrootendorst.com/p/a-visual-g...
Ahh nvm I am stupid. There is an option for "official comment" which lets you leave a comment for ACs and PCs only. Screenshot attached if anyone else is having trouble finding it. This page exists per paper so you have to click "submit review" from the reviewer console first.
January 13, 2025 at 10:52 PM
Ahh nvm I am stupid. There is an option for "official comment" which lets you leave a comment for ACs and PCs only. Screenshot attached if anyone else is having trouble finding it. This page exists per paper so you have to click "submit review" from the reviewer console first.
Lots of anti-Indian, anti-immigrant sentiment in the zeitgeist recently. Will use this opportunity to post my 🔥 outfit from a wedding this past week.
Plenty of my non-Indian friends wearing traditional Indian clothing as well and absolutely killing it. Why be racist when you could look this good?
Plenty of my non-Indian friends wearing traditional Indian clothing as well and absolutely killing it. Why be racist when you could look this good?
December 28, 2024 at 7:06 AM
Lots of anti-Indian, anti-immigrant sentiment in the zeitgeist recently. Will use this opportunity to post my 🔥 outfit from a wedding this past week.
Plenty of my non-Indian friends wearing traditional Indian clothing as well and absolutely killing it. Why be racist when you could look this good?
Plenty of my non-Indian friends wearing traditional Indian clothing as well and absolutely killing it. Why be racist when you could look this good?
Unfortunately this is the default ML experience.
December 19, 2024 at 6:56 PM
Unfortunately this is the default ML experience.
Sure, the company could set some TOS (though see the image for how well that works lmao) but the whole point of AT proto is that it's a protocol. Anyone can make a service that contributes to (and reads from) the firehose.
November 29, 2024 at 3:20 AM
Sure, the company could set some TOS (though see the image for how well that works lmao) but the whole point of AT proto is that it's a protocol. Anyone can make a service that contributes to (and reads from) the firehose.
Also not to toot my own horn too much but we did this in ZeroFlow and we have a whole section about the significance of errors compared with the training variance over 3 training runs.
It does cost compute but more people should do this!
It does cost compute but more people should do this!
November 23, 2024 at 4:24 AM
Also not to toot my own horn too much but we did this in ZeroFlow and we have a whole section about the significance of errors compared with the training variance over 3 training runs.
It does cost compute but more people should do this!
It does cost compute but more people should do this!
In the left hand sidebar there’s a section called lists which does this (I haven’t tried it yet):
November 21, 2024 at 10:20 PM
In the left hand sidebar there’s a section called lists which does this (I haven’t tried it yet):
This image is on Chris Amato's Dec-POMDP page which has some excellent explanations. rbr.cs.umass.edu/camato/decpo...
November 11, 2024 at 3:04 AM
This image is on Chris Amato's Dec-POMDP page which has some excellent explanations. rbr.cs.umass.edu/camato/decpo...
Researchers please, I am begging. Pleading. Run your code through mypy or another static analysis tool just once. These kinds of mistakes are so trivially caught. I know that grad student time isn’t worth much, but mypy, pyright, and beartype (to name a few) are all free 🥹
November 9, 2024 at 2:13 PM
Researchers please, I am begging. Pleading. Run your code through mypy or another static analysis tool just once. These kinds of mistakes are so trivially caught. I know that grad student time isn’t worth much, but mypy, pyright, and beartype (to name a few) are all free 🥹
Lmao yeah it was a Wild West out there in the beginning.
September 17, 2024 at 6:00 PM
Lmao yeah it was a Wild West out there in the beginning.
I believe someone has already done this lol.
May 5, 2023 at 9:43 PM
I believe someone has already done this lol.
Yeah, sorry if I explained it poorly. Here’s a screenshot from joinmastodon.org
May 5, 2023 at 9:27 PM
Yeah, sorry if I explained it poorly. Here’s a screenshot from joinmastodon.org