Connect with us

AI Research

Rich human feedback for text-to-image generation

Published

on


Recent text-to-image generation (T2I) models, such as Stable Diffusion and Imagen, have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer from issues like artifacts (e.g., distorted objects, text and body parts), misalignment with text descriptions, and low aesthetic quality. For example, the prompt in the image below says, “A panda riding a motorcycle”, however the generated image shows two pandas, with additional undesired artifacts, including distorted panda noses and wheel spokes.

Inspired by the success of reinforcement learning from human feedback (RLHF) for large language models (LLMs), we explore whether learning from human feedback (LHF) can help improve image generation models. When applied to LLMs, human feedback can range from simple preference ratings (e.g., “thumb up or down”, “A or B”), to more detailed responses like rewriting a problematic answer. However, current work on LHF for T2I mainly focuses on simple responses like preference ratings, since fixing a problematic image often requires advanced skills (e.g., editing), making it too difficult and time consuming.

In “Rich Human Feedback for Text-to-Image Generation“, we design a process to obtain rich human feedback for T2I that is both specific (e.g., telling us what is wrong about the image and where) and easy to obtain. We demonstrate the feasibility and benefits of LHF for T2I. Our main contributions are threefold:

  • We curate and release RichHF-18K, a human feedback dataset covering 18K images generated by Stable Diffusion variants.
  • We train a multimodal transformer model, Rich Automatic Human Feedback (RAHF), to predict different types of human feedback, such as implausibility scores, heatmaps of artifact locations, and missing or misaligned text/keywords.
  • We show that the predicted rich human feedback can be leveraged to improve image generation and that the improvements generalize to models (such as Muse) beyond those used for data collection (Stable Diffusion variants).

To the best of our knowledge, this is the first rich feedback dataset and model for state-of-the-art text-to-image generation.



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

AI Research

Researchers make AI-powered tool to detect plant diseases

Published

on


A team of researchers at Maharshi Dayanand University (MDU), Rohtak, has developed an artificial intelligence (AI)-based tool capable of detecting diseases and nutrient deficiencies in bitter gourd leaves, potentially transforming the way farmers monitor crop health.

The study, recently published in the peer-reviewed journal ‘Current Plant Biology’ (Elsevier), highlights how AI-driven innovations can play a crucial role in real-time crop monitoring and precision farming.

The newly developed web-based application, named ‘AgriCure’, is powered by a layered augmentation-enhanced deep learning model. It allows farmers to diagnose crop health by simply uploading or capturing a photograph of a leaf using a smartphone.

“Unlike traditional methods, which are time-consuming and often require expert intervention, AgriCure instantly analyses the image to determine whether the plant is suffering from a disease or nutrient deficiency, and then offers corrective suggestions,” explained the researchers.

The collaborative research project was led by Dr Kamaldeep Joshi, Dr Rainu Nandal and Dr Yogesh Kumar, along with students Sumit Kumar and Varun Kumar from MDU’s University Institute of Engineering and Technology (UIET). It also involved Prof Narendra Tuteja from the International Centre for Genetic Engineering and Biotechnology (ICGEB), New Delhi and Prof Ritu Gill and Prof Sarvajeet Singh Gill from MDU’s Centre for Biotechnology.

MDU Vice-Chancellor, Prof Rajbir Singh, congratulated the research team on their achievement.

According to the researchers, AgriCure can detect major diseases such as downy mildew, leaf spot, and jassid infestation, as well as key nutrient deficiencies like nitrogen, potassium and magnesium.

“This represents a step towards sustainable agriculture, where AI empowers farmers with real-time decision-making tools,” said corresponding authors Prof Ritu Gill and Prof Sarvajeet Singh Gill. They added that the web-based platform can be integrated with mobile devices for direct use in the field.

The team believes that the technology’s core framework can be extended to other crops such as cereals, legumes, and fruits, creating opportunities for wider applications across Indian agriculture.

Looking ahead, they plan to integrate AgriCure with drones and Internet of Things (IoT) devices for large-scale monitoring, and to develop lighter versions of the model for full offline use on mobile phones.





Source link

Continue Reading

AI Research

How artificial intelligence is transforming hospitals

Published

on


Story highlights

AI is changing healthcare. From faster X-ray reports to early warnings for sepsis, new tools are helping doctors diagnose quicker and more accurately. What the future holds for ethical and safe use of AI in hospitals is worth watching. Know more below.



Source link

Continue Reading

AI Research

AI is becoming the new travel agent for younger generations, survey finds

Published

on


Is travel planning the next space AI is taking over?

A new survey shows that younger Americans are relying on AI and ChatGPT more and more to construct their vacation itineraries.

The survey of 2,000 Americans (split evenly by generation) by Talker Research found that only 29% of millennials have never used AI for this reason, with just 33% of Gen Z saying the same.

This is a stark contrast to older generations that still rely on old-school, traditional methods to sort their travel plans. Seven in ten baby boomers also say they have never used AI for their travel plans.

IN CASE YOU MISSED IT | Travel cutbacks: Americans planning shorter, more frequent trips this summer

So exactly how are people utilizing AI in this way? The interesting results emerged in Talker Research’s new travel trend report.

The top application for AI in travel planning was found to be asking it to compare flight prices for wherever they’re headed, with 29% of all those polled saying they’ve done this.

A similar amount says AI comes in even before that: Twenty-nine percent of respondents have even asked it where they should go for their trip.

Another one in five even let AI complete a detailed plan for their whole trip, complete with sights to see, local things to do and museums to tick off.

While word of mouth and recommendations from loved ones have always been the most common way to learn about fun places to travel, the survey revealed that there’s a new contender.

YouTube (34%) was crowned as the top resource people use for travel inspo, officially topping recommendations from family (30%) and friends (28%).

The generations were split on this, as unsurprisingly, younger generations were a lot more reliant on social media than older generations.

FROM THE ARCHIVES | Affordable travel destinations that can save you thousands of dollars

While YouTube was the most popular when accounting for every survey-taker, Gen Z was overwhelmingly using TikTok for travel inspiration (52%).

In comparison, just 27% of millennials and only 2% of boomers said they use TikTok for this purpose.

While AI is still fairly new, it’s easy to see this trend growing as the technology becomes more sophisticated.

Survey methodology:

This random double-opt-in survey of 2,000 Americans (500 Gen Z, 500 millennials, 500 Gen X, 500 baby boomers) was conducted between May 5 and May 8, 2025 by market research company Talker Research, whose team members are members of the Market Research Society (MRS) and the European Society for Opinion and Marketing Research (ESOMAR).





Source link

Continue Reading

Trending