DEV Community

# computervision

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

Comments
3 min read
Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Keeping a client's VLM inference inside the EU with a self-hosted-first gateway

Comments
4 min read
Winograd convolutions cost us 2 mAP and we didn't notice for a month

Winograd convolutions cost us 2 mAP and we didn't notice for a month

Comments
4 min read
Why Every Computer Vision Team Ends Up Rewriting the Same Video Clip Pipeline

Why Every Computer Vision Team Ends Up Rewriting the Same Video Clip Pipeline

Comments
5 min read
How I Built Production-Grade AI Systems While Still a Student

How I Built Production-Grade AI Systems While Still a Student

Comments
1 min read
Image Reconstruction Using Deep Learning: A Complete Guide

Image Reconstruction Using Deep Learning: A Complete Guide

Comments
37 min read
An AI Module Smaller Than a Smartphone Photo. Are We Underestimating the Computer We Carry Every Day?

An AI Module Smaller Than a Smartphone Photo. Are We Underestimating the Computer We Carry Every Day?

3
Comments 1
16 min read
Basic Stereo Algorithms (Evolution)

Basic Stereo Algorithms (Evolution)

Comments
1 min read
Multi-agent coordination in interceptor drone systems: what real-world autonomy actually looks like

Multi-agent coordination in interceptor drone systems: what real-world autonomy actually looks like

Comments
8 min read
Type 'dog' to detect a dog: running YOLO-World on iPhone

Type 'dog' to detect a dog: running YOLO-World on iPhone

1
Comments
5 min read
Our LiDAR detector spent 40% of its time in voxelization, not convs

Our LiDAR detector spent 40% of its time in voxelization, not convs

1
Comments
4 min read
Centralising tool access for our prompt-assembly agent with Bifrost MCP gateway

Centralising tool access for our prompt-assembly agent with Bifrost MCP gateway

Comments
4 min read
One image schema for four VLM providers: we stopped reformatting payloads

One image schema for four VLM providers: we stopped reformatting payloads

Comments
4 min read
Our event-camera detector lost 6 mAP to a badly chosen accumulation window

Our event-camera detector lost 6 mAP to a badly chosen accumulation window

Comments
4 min read
I-JEPA: the Shift Away From Pixel-Level Learning in Computer Vision from Yann LeCun

I-JEPA: the Shift Away From Pixel-Level Learning in Computer Vision from Yann LeCun

Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.