Back

Shuvodip Ray

 • 

YouTube • 1y

Researchers at Google DeepMind introduced Semantica, an image-conditioned diffusion model capable of generating images based on the semantics of a conditioning image. The paper explores adapting image generative models to different datasets. Instead of finetuning each model, which is impractical for large-scale models, Semantica uses in-context learning. It is trained on web-scale image pairs, where one random image from a webpage is used to condition the generation of another image from the same page, assuming these images share semantic traits

2 Replies
3
Replies (2)

More like this

Recommendations from Medial

Image Description
Image Description

Arpan Dholakiya

Hey I am on Medial • 9m

🚀 Hiring for Generative AI Engineer (Remote) 🚀 AI-based SaaS company in the health sector seeks Generative AI Engineer. Requirements: - 1-3 years of experience in Generative AI - Expertise in LLMs and Diffusion Models - Strong foundation in compu

See More
3 Replies
8
Image Description
Image Description

Vignesh C

Technopreneur • 23d

Granted Patent Patent No. : 511613 Patent Title: Automatic Scene Understanding Assistive System with Refreshable Tactile Device Including Voice for Visually Impaired People This innovation enables the visually impaired people to visualize the images

See More
3 Replies

HEMANT GHUGE

Problem Zeroth, Tech... • 2m

Most people think of RAG (Retrieval-Augmented Generation) as a text-only thing. But when we apply it to images, it unlocks serious potential — especially in safety, retail, and surveillance. I recently explored Vision-RAG using Weaviate + LangChain

See More
Reply
4
10
Image Description
Image Description

AI Engineer

AI Deep Explorer | f... • 4m

Top 10 AI Research Papers Since 2015 🧠 1. Attention Is All You Need (Vaswani et al., 2017) Impact: Introduced the Transformer architecture, revolutionizing natural language processing (NLP). Key contribution: Attention mechanism, enabling models

See More
1 Reply
1
23
1

Gigaversity

Gigaversity.in • 4m

Manual data labeling is one of the biggest bottlenecks in building intelligent image classification systems — especially when the objects are rare, niche, or appear in very few examples. At Gigaversity, we recently faced this challenge while building

See More
Reply
6

Baqer Ali

AI agent developer |... • 15d

What do you think is the best Google nano banana aka Google gemini 2.5 flash or Chat gpt 4o image model I think nano banana wins this match because first it is very fast while I was comparing these two image models I was able to generate 5 ima

See More
Reply
1
10
Image Description

AI Engineer

AI Deep Explorer | f... • 4m

My Favorite AI & ML Books That Shaped My Learning Over the years, I’ve read tons of books in AI, ML, and LLMs — but these are the ones that stuck with me the most. Each book on this list taught me something new about building, scaling, and underst

See More
1 Reply
1
9

Tweak Buzz

TweakBuzz makes you ... • 2m

AI SEO Tools Guide to Skyrocket Your Google AI-Powered SERP Rankings In today’s rapidly evolving digital world, AI SEO tools have become essential for marketers and businesses aiming to dominate Google’s AI-powered SERP rankings. Traditional SEO str

See More
Reply
4
Image Description
Image Description

Ansh Kadam

Founder & CEO at Bui... • 6m

China is on fire. They just released 2 more AI models that further strengthen their dominance in the AI race. Number 1 - Goku This is ByteDance’s open-source video generation model. Unlike OpenAI’s Sora and Google’s Veo, which are closed-source, G

See More
4 Replies
3
10
Image Description
Image Description

Vikas Acharya

Building WelBe| Entr... • 7m

AI infrastructure startup Pipeshift has raised $2.5 million in a seed round led by Y Combinator and SenseAI Ventures. The round also saw participation from Arka Venture Labs, Good News Ventures, Nivesha Ventures, Astir VC, GradCapital, and MyAsiaVC.

See More
5 Replies
11

Download the medial app to read full posts, comements and news.