Ishan Khatri
@ishan.khatri.io
Researching computer vision stuff at Stack AV in Pittsburgh. Also on Twitter @i_ikhatri
Pinned
Ishan Khatri
@ishan.khatri.io
· Jul 9
My team at Stack just open sourced our runtime shape checking library for PyTorch & Numpy. It's hugely inspired by
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
Uhh guys… did they just build gastown into the model??????
www.kimi.com/blog/kimi-k2...
www.kimi.com/blog/kimi-k2...
Kimi K2.5: Visual Agentic Intelligence
Try Kimi K2.5, the strongest open-source model for visual coding. Explore agent swarm preview for massive tasks. Simplify complex Office work with precision.
www.kimi.com
January 27, 2026 at 7:45 AM
Uhh guys… did they just build gastown into the model??????
www.kimi.com/blog/kimi-k2...
www.kimi.com/blog/kimi-k2...
Guys I just read Gas Town… what the fuck?
January 20, 2026 at 12:54 AM
Guys I just read Gas Town… what the fuck?
Yes….But also I think that this just proves programmers will still be needed… you need to acquire the skills somehow? Everyone else is just playing slots… maybe the barrier to entry for the skills is lower? Though tbh id argue for coding it was already low (see self-taught boot campers)…
if this is how you use claude code then I’m sorry to say: skill issue, not the LLM’s fault
January 20, 2026 at 12:54 AM
Yes….But also I think that this just proves programmers will still be needed… you need to acquire the skills somehow? Everyone else is just playing slots… maybe the barrier to entry for the skills is lower? Though tbh id argue for coding it was already low (see self-taught boot campers)…
Fellow Linux enjoyers, is Gnome still the best DE with good touch support? Or is there something else I can use? (Have an older surface pro tablet I’d like to use for notes and pdfs etc)
January 17, 2026 at 8:18 PM
Fellow Linux enjoyers, is Gnome still the best DE with good touch support? Or is there something else I can use? (Have an older surface pro tablet I’d like to use for notes and pdfs etc)
me sowing: "I'll just use some attention here, a bit of softmax there ezpz"
me reaping: inf/0 = NaN hahahahahahahaha
me reaping: inf/0 = NaN hahahahahahahaha
January 16, 2026 at 12:27 AM
me sowing: "I'll just use some attention here, a bit of softmax there ezpz"
me reaping: inf/0 = NaN hahahahahahahaha
me reaping: inf/0 = NaN hahahahahahahaha
Wrote a whole ass thread om this a while ago: bsky.app/profile/isha...
This is how free and open access works. There is no way to have a free and open access project and then go “wait, no, not like that”.
www.citationneeded.news/free-and-ope...
www.citationneeded.news/free-and-ope...
January 15, 2026 at 9:01 PM
Wrote a whole ass thread om this a while ago: bsky.app/profile/isha...
Kyle is unfortunately not on BlueSky but he wrote this awesome blog post which is a love letter to CVPR. A conference that has in many ways become our “home conference”. It’s a reflection on the past and a call to action to preserve the incredible culture of CVPR.
vedder.io/misc/lover_l...
vedder.io/misc/lover_l...
A Love Letter to CVPR
A Love Letter to CVPR
vedder.io
January 15, 2026 at 7:00 AM
Kyle is unfortunately not on BlueSky but he wrote this awesome blog post which is a love letter to CVPR. A conference that has in many ways become our “home conference”. It’s a reflection on the past and a call to action to preserve the incredible culture of CVPR.
vedder.io/misc/lover_l...
vedder.io/misc/lover_l...
Reposted by Ishan Khatri
Some vibe-coding thoughts: I think the zero-coding-experience vibe coders miss how much of what impresses them when Claude produces what they perceive to be a fully functional app comes from the ready-built frameworks that enable the construction of such apps just by writing some boilerplate.
January 8, 2026 at 9:57 PM
Some vibe-coding thoughts: I think the zero-coding-experience vibe coders miss how much of what impresses them when Claude produces what they perceive to be a fully functional app comes from the ready-built frameworks that enable the construction of such apps just by writing some boilerplate.
The biggest misconception I see online about self-driving is that end-to-end == no LiDAR (camera only).
The sensor suite doesn’t determine the algorithmic approach, you can have an end to end approach with multiple sensors 😑
The sensor suite doesn’t determine the algorithmic approach, you can have an end to end approach with multiple sensors 😑
January 7, 2026 at 3:22 AM
The biggest misconception I see online about self-driving is that end-to-end == no LiDAR (camera only).
The sensor suite doesn’t determine the algorithmic approach, you can have an end to end approach with multiple sensors 😑
The sensor suite doesn’t determine the algorithmic approach, you can have an end to end approach with multiple sensors 😑
Alright in the interest of creating the kind of discussion/posting I want to see on this site, I'm gonna share something that I learned in the past few weeks. Not new, not mind blowing, but I was reading the VAE and VQ-VAE papers this winter break for some projects so here we go 🧵
January 6, 2026 at 3:18 AM
Alright in the interest of creating the kind of discussion/posting I want to see on this site, I'm gonna share something that I learned in the past few weeks. Not new, not mind blowing, but I was reading the VAE and VQ-VAE papers this winter break for some projects so here we go 🧵
Working on this 🦾
what i want from ai: please just do my laundry for me and make me tasty snacks
what im getting from ai: here’s some generated anime waifus that we think you might enjoy
what im getting from ai: here’s some generated anime waifus that we think you might enjoy
January 6, 2026 at 1:50 AM
Working on this 🦾
Stack is going to be at ICCV with a booth! And I'm hiring interns for next summer! If you want to work on 4D reconstruction, novel view synthesis and "world modeling" for AVs come to our booth (#230) at ICCV and chat with our team!
stackav.com/announcement...
stackav.com/announcement...
ICCV 2025 - Stack AV
Join Stack AV at ICCV 2025 - Booth #230. Explore how we're advancing autonomous trucking through world-class robotics and computer vision.
stackav.com
October 8, 2025 at 6:29 PM
Stack is going to be at ICCV with a booth! And I'm hiring interns for next summer! If you want to work on 4D reconstruction, novel view synthesis and "world modeling" for AVs come to our booth (#230) at ICCV and chat with our team!
stackav.com/announcement...
stackav.com/announcement...
“exam maxxing kumon monsters” is sending me lmfao 🤣
Interesting how much resentment this photo created from white conservatives who assumed that the dismantling of DEI meant elite schools would return to the 1940s.
August 5, 2025 at 5:21 AM
“exam maxxing kumon monsters” is sending me lmfao 🤣
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...?
My team at Stack just open sourced our runtime shape checking library for PyTorch & Numpy. It's hugely inspired by
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
July 9, 2025 at 3:07 AM
My team at Stack just open sourced our runtime shape checking library for PyTorch & Numpy. It's hugely inspired by
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
@patrickkidger.bsky.social's Jaxtyping but fixes a few key issues we ran into (namely, compatibility with torch.jit.trace & torch.compile).
Try it with `pip install dltype`
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!
Once again I am pleading with researchers. DO NOT HOST YOUR DATASETS ON GOOGLE DRIVE.
Downloading 100s of GB from a web browser with rate limits is a recipe for disaster. Please use large file storage buckets like S3 that have a CLI 😭
Downloading 100s of GB from a web browser with rate limits is a recipe for disaster. Please use large file storage buckets like S3 that have a CLI 😭
May 28, 2025 at 6:06 PM
Once again I am pleading with researchers. DO NOT HOST YOUR DATASETS ON GOOGLE DRIVE.
Downloading 100s of GB from a web browser with rate limits is a recipe for disaster. Please use large file storage buckets like S3 that have a CLI 😭
Downloading 100s of GB from a web browser with rate limits is a recipe for disaster. Please use large file storage buckets like S3 that have a CLI 😭
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!
I apologize if you didn't follow to watch me slowly lose my mind over 3D CV research code, but holy shit guys... a coordinate transformation is GODDAMN useless with a reference frame.
You can't just specify something as the "pose", it has to be "pose w.r.t. origin" which has to be explicit!
You can't just specify something as the "pose", it has to be "pose w.r.t. origin" which has to be explicit!
People who work in 3D vision. PLEASE write your code with UNITS in mind. METRIC depth means you need to have METRIC units. So instead of writing `depth` just post-fix with the unit. For example `depth_m` or `depth_cm`.
Think about how much time we collectively save, and type those extra characters.
Think about how much time we collectively save, and type those extra characters.
April 6, 2025 at 11:18 PM
I apologize if you didn't follow to watch me slowly lose my mind over 3D CV research code, but holy shit guys... a coordinate transformation is GODDAMN useless with a reference frame.
You can't just specify something as the "pose", it has to be "pose w.r.t. origin" which has to be explicit!
You can't just specify something as the "pose", it has to be "pose w.r.t. origin" which has to be explicit!
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.
People who work in 3D vision. PLEASE write your code with UNITS in mind. METRIC depth means you need to have METRIC units. So instead of writing `depth` just post-fix with the unit. For example `depth_m` or `depth_cm`.
Think about how much time we collectively save, and type those extra characters.
Think about how much time we collectively save, and type those extra characters.
April 2, 2025 at 10:20 PM
People who work in 3D vision. PLEASE write your code with UNITS in mind. METRIC depth means you need to have METRIC units. So instead of writing `depth` just post-fix with the unit. For example `depth_m` or `depth_cm`.
Think about how much time we collectively save, and type those extra characters.
Think about how much time we collectively save, and type those extra characters.
One of those "productivity rut" days today. Sitting at my desk. code in front of me, and I just keep opening random tabs of other crap to distract myself. But alas... deadlines don't wait for motivation.
March 23, 2025 at 10:55 PM
One of those "productivity rut" days today. Sitting at my desk. code in front of me, and I just keep opening random tabs of other crap to distract myself. But alas... deadlines don't wait for motivation.