Tech
Method teaches generative AI models to locate personalized objects
Say a person takes their French Bulldog, Bowser, to the dog park. Identifying Bowser as he plays among the other canines is easy for the dog owner to do while onsite.
But if someone wants to use a generative AI model like GPT-5 to monitor their pet while they are at work, the model could fail at this basic task. Vision-language models like GPT-5 often excel at recognizing general objects, like a dog, but they perform poorly at locating personalized objects, like Bowser the French Bulldog.
To address this shortcoming, researchers from MIT and the MIT-IBM Watson AI Lab have introduced a new training method that teaches vision-language models to localize personalized objects in a scene.
Their method uses carefully prepared video-tracking data in which the same object is tracked across multiple frames. They designed the dataset so the model must focus on contextual clues to identify the personalized object, rather than relying on knowledge it previously memorized.
When given a few example images showing a personalized object, like someone’s pet, the retrained model is better able to identify the location of that same pet in a new image.
Models retrained with their method outperformed state-of-the-art systems at this task. Importantly, their technique leaves the rest of the model’s general abilities intact.
This new approach could help future AI systems track specific objects across time, like a child’s backpack, or localize objects of interest, such as a species of animal in ecological monitoring. It could also aid in the development of AI-driven assistive technologies that help visually impaired users find certain items in a room.
“Ultimately, we want these models to be able to learn from context, just like humans do. If a model can do this well, rather than retraining it for each new task, we could just provide a few examples and it would infer how to perform the task from that context. This is a very powerful ability,” says Jehanzeb Mirza, an MIT postdoc and senior author of a paper on this technique posted to the arXiv preprint server.
Mirza is joined on the paper by co-lead authors Sivan Doveh, a graduate student at Weizmann Institute of Science; and Nimrod Shabtay, a researcher at IBM Research; James Glass, a senior research scientist and the head of the Spoken Language Systems Group in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL); and others. The work will be presented at the International Conference on Computer Vision (ICCV 2025), held Oct 19–23 in Honolulu, Hawai’i.
An unexpected shortcoming
Researchers have found that large language models (LLMs) can excel at learning from context. If they feed an LLM a few examples of a task, like addition problems, it can learn to answer new addition problems based on the context that has been provided.
A vision-language model (VLM) is essentially an LLM with a visual component connected to it, so the MIT researchers thought it would inherit the LLM’s in-context learning capabilities. But this is not the case.
“The research community has not been able to find a black-and-white answer to this particular problem yet. The bottleneck could arise from the fact that some visual information is lost in the process of merging the two components together, but we just don’t know,” Mirza says.
The researchers set out to improve VLMs abilities to do in-context localization, which involves finding a specific object in a new image. They focused on the data used to retrain existing VLMs for a new task, a process called fine-tuning.
Typical fine-tuning data are gathered from random sources and depict collections of everyday objects. One image might contain cars parked on a street, while another includes a bouquet of flowers.
“There is no real coherence in these data, so the model never learns to recognize the same object in multiple images,” he says.
To fix this problem, the researchers developed a new dataset by curating samples from existing video-tracking data. These data are video clips showing the same object moving through a scene, like a tiger walking across a grassland.
They cut frames from these videos and structured the dataset so each input would consist of multiple images showing the same object in different contexts, with example questions and answers about its location.
“By using multiple images of the same object in different contexts, we encourage the model to consistently localize that object of interest by focusing on the context,” Mirza explains.
Forcing the focus
But the researchers found that VLMs tend to cheat. Instead of answering based on context clues, they will identify the object using knowledge gained during pretraining.
For instance, since the model already learned that an image of a tiger and the label “tiger” are correlated, it could identify the tiger crossing the grassland based on this pretrained knowledge, instead of inferring from context.
To solve this problem, the researchers used pseudo-names rather than actual object category names in the dataset. In this case, they changed the name of the tiger to “Charlie.”
“It took us a while to figure out how to prevent the model from cheating. But we changed the game for the model. The model does not know that ‘Charlie’ can be a tiger, so it is forced to look at the context,” he says.
The researchers also faced challenges in finding the best way to prepare the data. If the frames are too close together, the background would not change enough to provide data diversity.
In the end, finetuning VLMs with this new dataset improved accuracy at personalized localization by about 12% on average. When they included the dataset with pseudo-names, the performance gains reached 21%.
As model size increases, their technique leads to greater performance gains.
In the future, the researchers want to study possible reasons VLMs don’t inherit in-context learning capabilities from their base LLMs. In addition, they plan to explore additional mechanisms to improve the performance of a VLM without the need to retrain it with new data.
“This work reframes few-shot personalized object localization—adapting on the fly to the same object across new scenes—as an instruction-tuning problem and uses video-tracking sequences to teach VLMs to localize based on visual context rather than class priors. It also introduces the first benchmark for this setting with solid gains across open and proprietary VLMs.
“Given the immense significance of quick, instance-specific grounding—often without finetuning—for users of real-world workflows (such as robotics, augmented reality assistants, creative tools, etc.), the practical, data-centric recipe offered by this work can help enhance the widespread adoption of vision-language foundation models,” says Saurav Jha, a postdoc at the Mila-Quebec Artificial Intelligence Institute, who was not involved with this work.
More information:
Sivan Doveh et al, Teaching VLMs to Localize Specific Objects from In-context Examples, arXiv (2025). DOI: 10.48550/arxiv.2411.13317
This story is republished courtesy of MIT News (web.mit.edu/newsoffice/), a popular site that covers news about MIT research, innovation and teaching.
Citation:
Method teaches generative AI models to locate personalized objects (2025, October 16)
retrieved 16 October 2025
from https://techxplore.com/news/2025-10-method-generative-ai-personalized.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
I love a digital notebook. I write about them all year long here at WIRED, and it’s not often my favorites go on sale. (Or for any to go on sale, besides Amazon’s own sale events.) But this year, multiple digital notebooks I love are on sale for the biggest sale event of the year.
If you’ve thought about getting one of these for yourself, there’s truly no better moment. From reMarkable’s on-sale bundles to Kobo’s deals, you can shop five of the best digital notebooks we’ve ever tried right now at a lower price than you might find until next year. They’re a handy device just about everyone can enjoy, whether you want to digitally annotate your books or write out your grocery list without using a piece of paper.
Looking for more great sales to shop? Don’t miss our guides to the Best Amazon Device and Kindle Deals, Best Laptop Deals, the Absolute Best Cyber Monday Deals, and our liveblog.
Update Dec. 1: We updated prices, links, and deals, and added the Rocketbook Fusion Plus notebook.
The Best Digital Notebook Deals
Some of the best digital notebooks we’ve tried come from reMarkable, and one of reMarkable’s models always seems to reign supreme over our digital notebooks guide. While the Paper Pro Move is the newest model, the reMarkable Paper Pro that launched in September 2024 is my current all-around favorite. It’s not only powerful with tons of tools and an easy interface, but packs a color screen for colorful notes. It also has a gentle front light so that you can use it in darker environments. You can get the bundles on sale right now, so combine one of reMarkable’s markers and folio covers with a Paper Pro to get $50 off.
-
Photograph: Nena Farrell
The best discount from reMarkable is actually for its older device and our previous top pick, the reMarkable 2. It doesn’t have a color screen or the front light, but you’ll get the reMarkable’s great software and options for accessories like the Keyboard Folio to use it like a laptop. The reMarkable 2 bundles are also on sale, so add on your favorite folio of choice on reMarkable’s website to get $70 off.
-
Photograph: Nena Farrell
-
Courtesy of Kobo
-Reviewer-Photo-SOURCE-Nena-Farrell.jpg)
The Kobo Libra Colour is my favorite all-around e-reader with its color screen and page turner buttons, but you can add on a stylus to have it double as a digital notebook. It’s one of the more affordable options, and it’s a smaller screen than the rest of these, but I especially love that you can use the stylus to doodle on the books you’re reading (something you can’t do with the Kindle Scribe). It’s $30 off on Kobo’s site for Cyber Monday.
-
Photograph: Nena Farrell
-
Photograph: Nena Farrell
-
Courtesy of Amazon
Amazon
Kindle Scribe (2024)
The second-generation Kindle Scribe isn’t the best digital notebook, but the long battery life (12 weeks!!) and convenient starting point of it being a Kindle I could already be reading on makes it a great go-to for casual notetakers and doodlers. It’s a good choice for Kindle and Amazon users, and there are new models due out this winter, but they likely won’t be as cheap as this one. (Especially since some of those new models will have color!)
Photograph: Nena Farrell
If you like the idea of getting a Kobo e-reader that doubles as a digital notebook, you can go for more of a classic size with the larger Elipsa 2E. This one comes with the stylus, so you won’t have to add it on, and it’s $50 off.
Photograph: Nena Farrell
The Rocketbook Fusion Plus digital planner and notebook is for those who don’t want to charge their notebook or give up on the whole “paper” experience. Take notes with the included, erasable Pilot Frixion Pen, scan photos of the pages into the app, and erase the whole thing with the damp microfiber cloth (also included). Fusion Plus is on its steepest discount of recent memory, and comes templates that range from monthly and weekly pages to project management and meeting notes.
Power up with unlimited access to WIRED. Get best-in-class reporting and exclusive subscriber content that’s too important to ignore. Subscribe Today.
Our muscles are nature’s actuators. The sinewy tissue is what generates the forces that make our bodies move. In recent years, engineers have used real muscle tissue to actuate “biohybrid robots” made from both living tissue and synthetic parts. By pairing lab-grown muscles with synthetic skeletons, researchers are engineering a menagerie of muscle-powered crawlers, walkers, swimmers, and grippers.
But for the most part, these designs are limited in the amount of motion and power they can produce. Now, MIT engineers are aiming to give bio-bots a power lift with artificial tendons.
In a study appearing today in the journal Advanced Science, the researchers developed artificial tendons made from tough and flexible hydrogel. They attached the rubber band-like tendons to either end of a small piece of lab-grown muscle, forming a “muscle-tendon unit.” Then they connected the ends of each artificial tendon to the fingers of a robotic gripper.
When they stimulated the central muscle to contract, the tendons pulled the gripper’s fingers together. The robot pinched its fingers together three times faster, and with 30 times greater force, compared with the same design without the connecting tendons.
The researchers envision the new muscle-tendon unit can be fit to a wide range of biohybrid robot designs, much like a universal engineering element.
“We are introducing artificial tendons as interchangeable connectors between muscle actuators and robotic skeletons,” says lead author Ritu Raman, an assistant professor of mechanical engineering (MechE) at MIT. “Such modularity could make it easier to design a wide range of robotic applications, from microscale surgical tools to adaptive, autonomous exploratory machines.”
The study’s MIT co-authors include graduate students Nicolas Castro, Maheera Bawa, Bastien Aymon, Sonika Kohli, and Angel Bu; undergraduate Annika Marschner; postdoc Ronald Heisser; alumni Sarah J. Wu ’19, SM ’21, PhD ’24 and Laura Rosado ’22, SM ’25; and MechE professors Martin Culpepper and Xuanhe Zhao.
Muscle’s gains
Raman and her colleagues at MIT are at the forefront of biohybrid robotics, a relatively new field that has emerged in the last decade. They focus on combining synthetic, structural robotic parts with living muscle tissue as natural actuators.
“Most actuators that engineers typically work with are really hard to make small,” Raman says. “Past a certain size, the basic physics doesn’t work. The nice thing about muscle is, each cell is an independent actuator that generates force and produces motion. So you could, in principle, make robots that are really small.”
Muscle actuators also come with other advantages, which Raman’s team has already demonstrated: The tissue can grow stronger as it works out, and can naturally heal when injured. For these reasons, Raman and others envision that muscly droids could one day be sent out to explore environments that are too remote or dangerous for humans. Such muscle-bound bots could build up their strength for unforeseen traverses or heal themselves when help is unavailable. Biohybrid bots could also serve as small, surgical assistants that perform delicate, microscale procedures inside the body.
All these future scenarios are motivating Raman and others to find ways to pair living muscles with synthetic skeletons. Designs to date have involved growing a band of muscle and attaching either end to a synthetic skeleton, similar to looping a rubber band around two posts. When the muscle is stimulated to contract, it can pull the parts of a skeleton together to generate a desired motion.
But Raman says this method produces a lot of wasted muscle that is used to attach the tissue to the skeleton rather than to make it move. And that connection isn’t always secure. Muscle is quite soft compared with skeletal structures, and the difference can cause muscle to tear or detach. What’s more, it is often only the contractions in the central part of the muscle that end up doing any work — an amount that’s relatively small and generates little force.
“We thought, how do we stop wasting muscle material, make it more modular so it can attach to anything, and make it work more efficiently?” Raman says. “The solution the body has come up with is to have tendons that are halfway in stiffness between muscle and bone, that allow you to bridge this mechanical mismatch between soft muscle and rigid skeleton. They’re like thin cables that wrap around joints efficiently.”
“Smartly connected”
In their new work, Raman and her colleagues designed artificial tendons to connect natural muscle tissue with a synthetic gripper skeleton. Their material of choice was hydrogel — a squishy yet sturdy polymer-based gel. Raman obtained hydrogel samples from her colleague and co-author Xuanhe Zhao, who has pioneered the development of hydrogels at MIT. Zhao’s group has derived recipes for hydrogels of varying toughness and stretch that can stick to many surfaces, including synthetic and biological materials.
To figure out how tough and stretchy artificial tendons should be in order to work in their gripper design, Raman’s team first modeled the design as a simple system of three types of springs, each representing the central muscle, the two connecting tendons, and the gripper skeleton. They assigned a certain stiffness to the muscle and skeleton, which were previously known, and used this to calculate the stiffness of the connecting tendons that would be required in order to move the gripper by a desired amount.
From this modeling, the team derived a recipe for hydrogel of a certain stiffness. Once the gel was made, the researchers carefully etched the gel into thin cables to form artificial tendons. They attached two tendons to either end of a small sample of muscle tissue, which they grew using lab-standard techniques. They then wrapped each tendon around a small post at the end of each finger of the robotic gripper — a skeleton design that was developed by MechE professor Martin Culpepper, an expert in designing and building precision machines.
When the team stimulated the muscle to contract, the tendons in turn pulled on the gripper to pinch its fingers together. Over multiple experiments, the researchers found that the muscle-tendon gripper worked three times faster and produced 30 times more force compared to when the gripper is actuated just with a band of muscle tissue (and without any artificial tendons). The new tendon-based design also was able to keep up this performance over 7,000 cycles, or muscle contractions.
Overall, Raman saw that the addition of artificial tendons increased the robot’s power-to-weight ratio by 11 times, meaning that the system required far less muscle to do just as much work.
“You just need a small piece of actuator that’s smartly connected to the skeleton,” Raman says. “Normally, if a muscle is really soft and attached to something with high resistance, it will just tear itself before moving anything. But if you attach it to something like a tendon that can resist tearing, it can really transmit its force through the tendon, and it can move a skeleton that it wouldn’t have been able to move otherwise.”
The team’s new muscle-tendon design successfully merges biology with robotics, says biomedical engineer Simone Schürle-Finke, associate professor of health sciences and technology at ETH Zürich.
“The tough-hydrogel tendons create a more physiological muscle–tendon–bone architecture, which greatly improves force transmission, durability, and modularity,” says Schürle-Finke, who was not involved with the study. “This moves the field toward biohybrid systems that can operate repeatably and eventually function outside the lab.”
With the new artificial tendons in place, Raman’s group is moving forward to develop other elements, such as skin-like protective casings, to enable muscle-powered robots in practical, real-world settings.
This research was supported, in part, by the U.S. Department of Defense Army Research Office, the MIT Research Support Committee, and the National Science Foundation.
HBO knows you’re bored and cold. It wants you to Max and chill with Noah Wyle in scrubs. The company offers some of the best Cyber Monday streaming deals with a ridiculously low-priced $3/month offer for basic HBO Max (it’s the version with ads and 2K streaming, but still, super-cheap). Disney Plus and Hulu deals are bundled up for $5/month. Apple TV wants back in your life for $6.
Of course, this deal is only meant for new customers. Not boring ol’ existing customers. If you already have basic HBO Max, you’re already paying $11 for the same service, and HBO would like you to keep doing that. Streaming apps are banking on you being complacent and happy in your streaming life. Maybe they’re even taking you for granted.
Sometimes you can get the current deal just by threatening to cancel, or actually canceling, your account. Suddenly, you’re an exciting new customer again! Another method is by using an alternate email account (perhaps your spouse’s or roommate’s?) and alternate payment information as a new customer. If you do use a burner email (you did not hear this from me), check in on your favorite app’s terms of service to make sure you’re not in violation by re-enrolling with different emails. I’ll also issue the caveat that you lose all your viewing data and tailored suggestions if you sign up anew.
But times and wallets are tight! And $3 HBO Max sounds pretty good. After all, every middle-aged American man needs to rewatch The Wire once every five years or so—assuming he’s not the kind of middle-aged man who rewatches The Sopranos instead. Here are the current best streaming deals for Cyber Monday 2025.
Devon Maloney; ARCHIVE ID: 546772
Regular price: $80
I’ve Tried Every Digital Notebook. Here Are the Best Ones on Sale
Flamengo’s Copa Libertadores trophy damaged in title celebrations
Eastpak appoints Marie Gras as vice president, global brand
-
Sports1 week agoWATCH: Ronaldo scores spectacular bicycle kick
-
Entertainment1 week agoWelcome to Derry’ episode 5 delivers shocking twist
-
Politics1 week agoWashington and Kyiv Stress Any Peace Deal Must Fully Respect Ukraine’s Sovereignty
-
Business1 week agoKey economic data and trends that will shape Rachel Reeves’ Budget
-
Politics1 week ago53,000 Sikhs vote in Ottawa Khalistan Referendum amid Carney-Modi trade talks scrutiny
-
Tech6 days agoWake Up—the Best Black Friday Mattress Sales Are Here
-
Tech1 day agoGet Your Steps In From Your Home Office With This Walking Pad—On Sale This Week
-
Fashion1 week agoCanada’s Lululemon unveils team Canada kit for Milano Cortina 2026