Stories by zerojames

Microsoft Christmas Sweater (Sold Out)

MobileCLIP: Fast Image-Text Models Through Multi-Modal Reinforced Training

Show HN: Multimodal Maestro – Prompt tools for use with LMMs

My experience starting as a technical writer

You can't parse [X]HTML with regex

MLU-Explain

My personal website is incomplete, imperfect

GPT-4 Vision Alternatives

SAM-CLIP: Combine Grounded Sam and Clip for Instance Segmentation

SAM-GPT-4V: Combining Grounding DINO, SAM, and GPT Vision

How CLIP and GPT-4V Compare for Classification

HuggingFace Daily Papers

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Show HN: OpenAI Vision Experiments

How CLIP and GPT-4V Compare for Classification

Dino-GPT4-V: Use GPT-4V in a Two-Stage Detection Model

Experiments with GPT-4V for Object Detection

Clip Video Investigator: Interactive Video Classification with Clip

Counting US Dollars with Computer Vision

CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Detection

11
12
13
14
15
16
17
18
19