Compress vision-language and unimodal AI models by structured pruning
[ICML 2023] UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers - sdc17/UPop
Compress vision-language and unimodal AI models by structured pruning launched on July 31, 2023 with 7 votes, #1,751 of 4,347 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 3 years on.
Does a similar job
all alternatives →
Ideogram 4.0 – open-weight 9.3B text-to-image modelJun 2026 · github.com · ▲46It's our new text-to-image model: a 9.3B single-stream diffusion transformer trained entirely from scratch. We focused heavily on controllability through structured JSON prompts, with strong text rendering, spatial awareness through bounding box guidance, and color palette control. It has the best text rendering of any open-weight model we've tested so far, and the NF4 quantized checkpoint runs on a single 24GB GPU. For more technical details and examples see our blog post: https://ideogram.ai/blog/ideogram-4.0/ We will be happy to answer any questions :)
onprem unstructured data extraction with 4 lines of code2025 · github.com · ▲8The traditional pipeline for unstructured data extraction typically follows these steps: 1. Image → OCR Model (e.g., Google Vision) → Layout Model (e.g. Surya) → LLM → Final Answer However, this can be streamlined using a Vision-Language Model (VLM): 2. Image → VLM → Final Answer Recently VLMs have improved a lot for OCR and document understanding tasks, specifically the Qwen-2.5-VL series. We can run the Qwen-2.5-VL-7B-AWQ model locally with just 16GB VRAM, and perform end-to-end information extraction (fields and table extraction) without any external models. Hallucination with VLMs One…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, July 2023
the whole month →
Hey everyone, I here is a small open-source project I've been working on lately. I'd love to hear your thoughts and improvement ideas :) GitHub: [github.com/Vincenius/workout-lol](https://github.com/Vincenius/workout-lol)
Dev tools · 2023 · workout.lol
- HN
I saw this [0] pretty cool thread by user revskill, and wanted a quicker way to search through it, but also to keep them all in one place so I can read them at my leisure whenever I get time. Right now is like 60 lines of Ruby using Nokogiri, but I will certainly look into it further down the line and improve the list. There's a cronjob checking the thread every 12 hours but I will eventually shut that down and it will become static after that. There are some really awesome blogs in there. I really recommend going through the list, it made my day. [0] "Could you share your personal blog…
Life & fun · 2023 · dm.hn
Anytype is built on the open-source AnySync protocol: a local-first protocol based on CRDTs. Users of Anytype can create spaces - graph-based databases with modular UI. Each space has unique access rights. Today, Anytype's beta is in single-player mode. Multiplayer mode, which will support local-first collaboration between multiple users, will be launched in the first half of 2024. Anytype fulfils the seven ideals of local first software from here - https://www.inkandswitch.com/local-first/ , our team felt these things are important to all of us: • No spinners: your work…
Commerce · 2023 · anytype.io
