harpreet @DataScienceHarp

🤖 👨🏽‍💻 Hacker-in-residence @voxel51| ❤️open source deep learning | VLMs| Visual AI| Learn. Hack. Write. Teach. Repeat. 🪯 github.com/harpreetsahota… I ship daily Joined April 2020

Tweets

7K
Followers

7K
Following

1K
Likes

27K

Open Data Science @_odsc

2 days ago

🚗📷 How can Vision-Language Models transform computer vision in industry? At #ODSCWest, @DataScienceHarp (@Voxel51) leads a workshop on Visual AI for vehicle damage detection using the CarDD dataset + FiftyOne. 📅 Oct 28–30 | SF 🔗 hubs.li/Q03GX0jy0 #VisualAI #VLMs

2 2 4 544 0

Download Image

harpreet @DataScienceHarp

4 days ago

I saw FastVLM at CVPR Nashville and been patiently waiting for Transformers integration ever since. It's here now. • Every vision token adds LLM latency. ViT generates 576 tokens at 336×336. That's 576 forward passes through your decoder. • FastVLM uses 144 tokens at 768×768…

0 0 1 125 0

harpreet @DataScienceHarp

2 weeks ago

So pumped to be here now

Oasis Mania @OasisMania

2 weeks ago

So pumped to be here now

35 93 2K 160K 80

Download Video

1 0 3 261 0

Voxel51 @Voxel51

3 weeks ago

Traditional annotation is slowing down the race to fully autonomous vehicles. On Sept. 4, join @Porsche, Voxel51, and @databricks for an exclusive look at how cutting-edge VLMs, automated data pipelines, and human-in-the-loop feedback loops are transforming the way AV systems…

0 1 3 184 0

Download Image

Voxel51 @Voxel51

4 weeks ago

@nvidiaomniverse NuRec and @Voxel51 FiftyOne integration tackles a major bottleneck in AV development when working with multi-sensor datasets. As AV systems move from R&D to deployment, issues like misaligned sensor calibrations, drifting ego-poses, and timestamps often introduce…

1 1 3 1K 0

Download Gif

Voxel51 @Voxel51

a month ago

In Part 1, @DataScienceHarp will walk through: 👉 Why standard vision models fail catastrophically on GUI tasks 👉 The annotation bottlenecks that make GUI datasets so expensive to create 👉 The platform fragmentation that makes "click a button" mean 20 different things across…

1 1 3 137 0

Voxel51 @Voxel51

a month ago

Here’s a peek at what’s on the agenda. ➡️ “Foundational models for generalist computer agents” – Raghav Kapoor, @Adobe ➡️ “Evaluating web agents with the BEARCUBS benchmark” – @yixiao_song, @UMassAmherst ➡️ “Building vision-based Android agents in production” – Rasul…