AI chatbots hesitant to recommend change
Study finds that chatbots are more likely to recommend what is common or popular, and not necessarily the best options for you or the planet
A new study of multiple large language models (LLMs) found that when users asked chatbots for advice, they were more likely to make suggestions that favour the status quo over alternatives. The tendency of artificial intelligence to default to more common advice could be bad news for the climate.
Researchers from the University of Waterloo assessed 11 LLMs for their tendency to prefer existing conditions over change, known as status quo bias. Well-known in psychology research, this is the first paper to apply the concept to climate advice from LLMs. The team evaluated more than 7,500 queries spanning multiple domains, including vehicle purchases, recipes, home heating, and climate-relevant policy trade-offs. Each of these queries was tested on at least six different LLMs for a total of nearly 55,000 prompts. Where climate trade-offs are possible in policy, platforms reinforced decisions the user already made with double the frequency.
LLMs commonly provide advice that runs counter to changes needed from households and decision makers for climate action. Given the proliferation of AI, progress on climate change is at risk if the status quo favours high emissions.
“I think it's worth being aware that these models, even the new ones, have blind spots,” said Dr. Seth Wynes, professor in the Faculty of Environment. “It's good for consumers to be aware of this bias and if you're asking for advice on a topic, you could ask it to make the case for doing something new.”
While different models responded similarly during the study, the findings were most obvious in policymaking. When models were asked whether to proceed with a plan, they said "yes" 70 per cent of the time for plans that were already in place but only agreed 34 per cent of the time when the plan or policy was new.
While researchers noted that models do take regional patterns into consideration, they still showed a surprising bias here as well. For instance, if you claim to be a user from Norway, where sales of new electric vehicles are very high, the chatbot is more likely to recommend an EV than if you are from Canada. But in both cases, the bot will recommend an EV less often than the pace at which EVs are already being sold in their respective country.
“In almost every jurisdiction, the LLMs are working at at slower pace of change than is needed, so they recommend fewer EV models than what are actually being sold today,” Wynes said. “It might be very good for AI to favour the status quo for lots of other things, such as proven medical advice, but climate is where we really do need change.”
In the future, the researchers will keep tabs on advances in LLMs and if and whether humans are relying on AI to make purchases within the AI platform, amplifying the effect of any status quo bias.
The study, Large language models exhibit status quo bias in climate-relevant advice, appears in Environmental Research Communications.
Journal
Environmental Research Communications
Method of Research
Experimental study
Subject of Research
Not applicable
Article Title
Large language models exhibit status quo bias in climate-relevant advice
Article Publication Date
7-Oct-2026
International, cross-sector collaboration commits nearly $2 billion to build foundational data for AI models to predict and treat disease
Biohub
REDWOOD CITY, CA, October 7, 2026 — Biohub, the U.S. Department of Energy, the National Institutes of Health, and new funding partners today announced a major expansion of an international effort to generate and make accessible the data enabling predictive AI models of biology. Together, the organizations are investing $1.8 billion in funding, data, computation, and new measurement technology, the largest coordinated commitment to generating AI-ready biological data to date. The result will be an open resource for the research community that provides the foundation for greater understanding and ultimately treatment of human diseases.
As part of this announcement, Biohub has partnered with the Department of Energy (DOE) Office of Science and the National Institutes of Health (NIH) to advance the frontier of artificial intelligence in biology. DOE will invest more than $500 million over five years in lab measurement, modeling and computation toward the international effort to build an AI-ready open data resource. NIH will coordinate the contribution of relevant datasets, repositories, and knowledge bases developed through more than $500 million in prior federal investment aligned to this initiative. Biohub will work with NIH to standardize these datasets for AI model training.
In addition, Google DeepMind, Isomorphic Labs, and Meta are collectively investing $300 million in the Virtual Biology Initiative to create the technologies and multi-modal datasets needed to build predictive models of life.
These datasets will enable the global scientific community to collectively build and use AI models that allow researchers to ask, predict, and answer biological questions digitally, accelerating the path to new ways of preventing and treating diseases. This initiative will deliver the foundational measurements to train these models, expanding cell response data to interventions across far more cell types and conditions than have yet been studied, and building and validating technologies for studying cells and cellular interactions at greater scale, speed, and accuracy.
“An accurate predictive model of biology could dramatically accelerate scientific discovery by enabling scientists to perform experiments digitally. The insights that come from this could unlock a far greater understanding of disease and open up completely new paths for cures,” said Biohub Head of Science Alex Rives. “Because of this potential, the creation of a virtual cell is one of the most important challenges for the next era of science. It will require coordinated data generation efforts at a national and international scale, which is why these partners are coming together. We invite the worldwide scientific community to join us in this project.”
The Virtual Biology Initiative, announced in April 2026, will coordinate data generation across institutions and disciplines to build AI-ready open datasets to enable predictive models of life. Biohub’s founding $500 million commitment anchors that work: $400 million supports new technologies that expand what biologists can measure: cryo-electron tomography, which resolves near-atomic detail inside the cell; microscopy that can image millions to billions of cells in living tissue; and engineering tools to build and perturb biology at molecular, cellular, tissue, and whole-organism levels. A further $100 million funds research outside Biohub.
“Generating the data to solve predictive systems biology requires scaling past the limits of what any single organization can produce today,” said Max Jaderberg, President of Isomorphic Labs. “By joining the Virtual Biology Initiative as a founding member, Isomorphic Labs is helping build a massive, multimodal data foundation. This initiative will generate the data needed to push the industry closer to the next significant breakthrough for biology.”
Through the Genesis Mission, a cross-agency initiative led by the Department of Energy, DOE will contribute more than $500 million over five years in fundamental cell research — data collection, AI analytics, measurement and imaging, modeling, and computation — drawing on exascale supercomputing, X-ray and neutron scattering, cryo-electron microscopy and tomography, and autonomous laboratories across the National Laboratory system.
“This partnership represents a critical step forward in leveraging artificial intelligence for public benefit,” said Darío Gil, DOE’s Under Secretary for Science. “By combining DOE’s exascale computing, experimental measurement, and modeling assets, including premier user facilities at the Joint Genome Institute, the Environmental Molecular Sciences Laboratory, and advanced structural beamlines with the unique AI models, tool development, and biological data capabilities of Biohub, we are setting a new standard for open science that will accelerate discoveries in both medicine and biotechnology.”
Through its Bio Genesis Mission, NIH will bring together existing biomedical datasets, national data infrastructure, and research programs to help build AI-ready resources for the broader scientific community. NIH’s extensive investments in biomedical research provide a foundation for this work; resources include national biomedical repositories catalogued by NIH’s National Library of Medicine (NLM) and the National Center for Biotechnology Information, as well as NIH Common Fund programs that are already developing coordinated biological atlases, shared data standards, and AI-ready biomedical datasets.
“By combining resources and expertise, we can accelerate the development of universal cell models with sufficient biological complexity to predict how any cell responds to an intervention,” said Nicole Kleinstreuer, Ph.D., NIH Deputy Director Program Coordination, Planning, and Strategic Initiatives (DPCPSI). “The return from these models could be broad and profound, resulting in substantially faster timelines for medical breakthroughs as compared with attempting to attain the same results through laboratory experiments alone.”
In addition, leading scientific institutions and consortia with experience in organizing transformative international collaborations, from the Human Genome Project onwards, have come together to help nucleate the scientific community across academia and industry around developing effective scientific strategies to maximize the impact of virtual biology. The groups include the Allen Institute, Broad Institute, Gladstone Institutes, the Human Cell Atlas, the Human Protein Atlas, and the Wellcome Sanger Institute. These groups are committed to working together as part of the Virtual Biology Initiative as well as through independent efforts toward this shared goal. NVIDIA will support the initiative to leverage accelerated computing infrastructure, domain-specific software, and technical expertise. Renaissance Philanthropy is helping to expand funding for data generation.
As the initiative takes shape, Biohub is bringing together partners across disciplines and industries to build the layer that lets their datasets work in a unified fashion — shared standards, common identifiers, and a single point of access. Equally important is building the scientific community around these resources — convening researchers across institutions and disciplines, connecting complementary expertise and capabilities, and creating opportunities to define and pursue ambitious scientific questions together. Over the past decade, Biohub has expanded the reach and impact of measurement technologies and open datasets, leading projects such as Tabula Sapiens, OpenCell, and Zebrahub. It has also built and maintained community data infrastructure, including CELLxGENE and the CryoET Data Portal. The Virtual Biology Initiative builds on these experiences to enable coordinated efforts at a scale that no single institution could achieve alone.
“The quest to build a virtual cell is one of the great collective scientific challenges and key to understanding the mechanisms of life. We will not solve this challenge without open, experimental biological data at an unprecedented scale, showing how living cells behave and respond to changes,” said Pushmeet Kohli, VP, AI for Science at Google DeepMind and Google Cloud's Chief Scientist. “This investment in biological data generation will help create an open, standardized data commons, which will lay the foundations researchers around the world need to better model biology.”
###
About Biohub
Biohub is a 501(c)(3) nonprofit research institute combining frontier AI and biology to accelerate science. With its compute capacity, AI research and engineering, and state-of-the-art technology for measuring, imaging, and programming biology, Biohub is enabling scientists worldwide to use AI-powered biology to study how cells operate and organize as systems — with the ultimate mission to cure or prevent all disease. Learn more at biohub.org.
Top AI tools accurately identified validated home BP monitors only about 2/3 of the time
American Heart Association Hypertension Scientific Sessions 2026 – Moderated Poster #TH125
Research Highlights:
- Three of the top four popular artificial intelligence (AI) tools – OpenAI’s ChatGPT, Microsoft’s Copilot and Perplexity AI – could not consistently identify if a home blood pressure monitor had passed clinical validation testing, with accuracy only 63% to 83% of the time. Google Gemini performed better but still provided incorrect responses about 10% to 15% of the time.
- All four tools misidentified various home blood pressure monitors as not meeting clinical standards even though the AI tool was verifying against the independent registries that list only validated blood pressure monitors.
- Researchers advise healthcare professionals and the public to confirm validation of home blood pressure monitors according to recognized independent, free and publicly available registries.
- Note: The studies featured in this news release are research abstracts. Abstracts presented at the American Heart Association’s scientific meetings are not peer-reviewed, and the findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.
Arlington, Va., Oct. 8, 2026 — Three of four leading AI-powered search tools accurately identified home blood pressure monitors that met validated clinical standards only 63%-83% of the time, according to preliminary research being presented at the American Heart Association’s Hypertension Scientific Sessions 2026. The meeting is in Arlington, Virginia, October 7-11, 2026, and is the premier scientific exchange focused on recent advances in basic and clinical research on high blood pressure and its relationship to cardiac and kidney disease, stroke, obesity and genetics.
High blood pressure is the number one risk factor for cardiovascular disease, affecting more than 125 million adults in the U.S. – about 47% – according to the American Heart Association’s 2026 Heart Disease and Stroke Statistics Update. Only about 1 in 4 of those adults have their blood pressure within the target range of less than 120 mm Hg/80 mm Hg, and high blood pressure.
The 2025 American Heart Association Guideline for the Prevention, Detection, Evaluation, and Management of High Blood Pressure in Adults recommends that people use a home blood pressure monitoring device that has been validated for accuracy. People can talk with their clinician and visit www.validatebp.org for more information.
Now that AI-powered search tools are integrated into all online platforms, people are increasingly asking AI tools for quick answers to health questions, including whether home health devices such as blood pressure monitors have been validated and meet clinical standards. A home blood pressure monitor is considered validated when independent, third-party testing has proven it gives consistently accurate blood pressure readings, and there are three primary registries that list these devices. In this analysis, researchers found AI-powered chatbots were not reliable at making this determination.
“We found that most AI tools performed only slightly better than if you had flipped a coin for each question. Even Google Gemini, which performed best, was often wrong and couldn’t find information that is easily located,” said Anna Soriano, M.D., a third-year internal medicine resident at the University of Montreal and the study’s presenting author.
“People may unknowingly think a device is validated based on the AI tool’s inaccurate responses. Using that device may result in inaccurate blood pressure readings, which could lead to an inappropriate diagnosis or treatment decisions,” she added.
What are the key findings of the study?
- Researchers found that accuracy at identifying if a home blood pressure monitor meets clinical standards varied significantly depending on the AI-powered tool used.
- Google Gemini scored the highest – answering correctly 86% to 91% of the time depending on how the questions were phrased.
- Correct responses from ChatGPT, Copilot and Perplexity ranged from only about 63% to 83%.
- All four AI tools were less accurate at identifying validated BP monitors vs. unvalidated monitors.
- When researchers retested the AI tools’ responses for devices that had mixed accuracy results, asking the same AI tool the same questions – on a different day or from a different computer – the AI tools often produced a different answer.
Researchers also tested a wide range of devices, including lesser-known home blood pressure monitors, though researchers noted these still appear on the same official registries as more popular ones. The authors could not determine exactly why AI tools struggled with identifying devices that had already passed validation testing.
“It is surprising, and almost counterintuitive, that AI tools had so much difficulty specifically identifying validated devices, since those devices are the ones with clear listings on official registries,” Soriano said. “In many cases, the AI tools found the blood pressure monitor was listed within an official website, however, it seems AI was not able to interpret being listed on the registry as proof of validation.”
“Artificial intelligence holds great promise to help support clinicians in areas such as cardiac imaging, electrocardiography, mobile devices and other tools,” said Keith C. Ferdinand, M.D., FAHA, an American Heart Association volunteer expert and vice chair of the Association’s 2025 High Blood Pressure Guideline. “The potential shortcomings of AI demonstrated by this study’s results should remind clinicians and the public that the use of AI for clinical decision-making requires caution. In addition, home blood pressure devices need to be both validated [listed on the national registry validatebp.org and accurate. With the proper technique and regular monitoring, readings from home BP devices are a valuable component of integrated, individual treatment plans that can improve patient care and outcomes.” Ferdinand, who was not involved in this study, is the Gerald S. Berenson Endowed Chair in Preventative Cardiology and professor of medicine at Tulane University School of Medicine in New Orleans.
A limitation of the study is that these results are likely to change as AI technology continues to improve with time. In addition, to limit each tool’s ability to learn from previous test searches, scientists used private internet browsing sessions; however, this technique could not fully prevent language model training of the AI tools.
What are the details, background and design of the study?
- Researchers tested 324 home blood pressure monitors in Canada during April - May 2026 – 145 validated devices and 179 not-validated devices – drawn from 3 validation registries (StrideBP, ValidateBP and Hypertension Canada); a list of known non-validated devices; and the list of top-selling blood pressure cuff monitors sold via Amazon in Canada, Australia and the U.S.
- The authors tested each device with four AI search tools: Google Gemini, Microsoft Copilot, ChatGPT and Perplexity.
- Researchers asked each of the AI tools three types of questions about each of the 324 blood pressure devices: a general, public-style question about the device’s validation status; a more specific question directing it to check a named validation registry; and the same question asked with more details and requiring a one-word answer.
- To test consistency, the researchers retested 20% of devices that had produced mixed results, using three different examiners on different computers and on different days primarily in May 2026.
Note: This abstract will be presented at 5:30 p.m., Thursday, October 8, 2026.
Co-authors, their disclosures and funding sources are listed in the abstract.
Statements and conclusions of studies that are presented at the American Heart Association’s scientific meetings are solely those of the study authors and do not necessarily reflect the Association’s policy or position. The Association makes no representation or guarantee as to their accuracy or reliability. Abstracts presented at the Association’s scientific meetings are not peer-reviewed, rather, they are curated by independent review panels and are considered based on the potential to add to the diversity of scientific issues and views discussed at the meeting. The findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.
The Association receives more than 85% of its revenue from sources other than corporations. These sources include contributions from individuals, foundations and estates, as well as investment earnings and revenue from the sale of our educational materials. Corporations (including pharmaceutical, device manufacturers and other companies) also make donations to the Association. The Association has strict policies to prevent any donations from influencing its science content. Overall financial information is available here.
Additional Resources:
- Multimedia, including a video interview with Keith C. Ferdinand, M.D., FAHA, an American Heart Association volunteer expert, is on right column of release link.
- The abstracts will be published at 10 am ET, Nov. 17, 2026, in the Hypertension Scientific Sessions 2026 Supplement of the Hypertension journal.
- American Heart Association news release: Cuffless blood pressure technologies in wearable devices show promise to transform care (Dec. 2025)
- American Heart Association news release: Only 1 in 7 online health images show proper technique to accurately measure blood pressure (Sept. 2025)
- American Heart Association health information: Home Blood Pressure Monitoring
- American Heart Association health information: Understanding Blood Pressure Readings
- Follow American Heart Association news from the meeting on X @HeartNews #Hypertension26
###
The American Heart Association’s Hypertension Scientific Sessions 2026 is a premier scientific conference dedicated to recent advancements in both basic and clinical research related to high blood pressure and its connections to cardiac and kidney diseases, stroke, obesity and genetics. The primary aim of the meeting is to bring together interdisciplinary researchers from around the globe and facilitate engagement with leading experts in the field of hypertension. Attendees will have the opportunity to discover the latest research findings and build lasting relationships with researchers and clinicians across various disciplines and career stages. Follow the conference on X using the hashtag #Hypertension26.
About the American Heart Association
The American Heart Association is a relentless force for a world of longer, healthier lives. Dedicated to ensuring equitable health in all communities, the organization has been a leading source of health information for more than one hundred years. Supported by more than 35 million volunteers globally, we fund groundbreaking research, advocate for the public’s health, and provide critical resources to save and improve lives affected by cardiovascular disease and stroke. By driving breakthroughs and implementing proven solutions in science, policy, and care, we work tirelessly to advance health and transform lives every day. Connect with us on heart.org, Facebook, X or by calling 1-800-AHA-USA1.
High performance computing and sustainability through artificial intelligence
New book explores the convergence of AI, high-performance computing and sustainable digital transformation
Bentham Books announces the release of High Performance Computing and Sustainability Through Artificial Intelligence, a timely reference exploring how high-performance computing (HPC), artificial intelligence (AI), cloud technologies and cybersecurity can contribute to sustainable and resilient digital infrastructures.
About the Book
The rapid growth of computational technologies is creating new opportunities to address complex sustainability challenges while improving the efficiency and security of digital systems. High Performance Computing and Sustainability Through Artificial Intelligence examines the integration of HPC, AI, cloud computing and cybersecurity to support environmentally responsible and technologically resilient development.
The book explores emerging developments in big data and cloud computing, AI- and IoT-enabled sustainable agriculture, cloud security, data protection and cybersecurity frameworks. It also examines how HPC and AI can contribute to carbon reduction, smart farming and the protection of critical cyber-physical infrastructure, including smart power grids. Ethical, governance and policy considerations surrounding AI-driven computing are also addressed.
Key Highlights
• Integration of HPC, AI and cloud computing for sustainable digital transformation
• Cloud security, risk assessment, auditing and data protection strategies
• AI- and AIoT-enabled approaches for sustainable agriculture and carbon reduction
• Cybersecurity solutions for critical infrastructure and smart power grids
• Ethical, governance and policy considerations in intelligent computing systems
Readership: Researchers, graduate students, computer scientists and professionals working in artificial intelligence, high-performance computing, cloud computing, cybersecurity and sustainable computing.
About the Editors
Jagdish Chandra Patni and Nilesh Bhaskarrao Bahadure bring together research and professional perspectives on emerging computational technologies, artificial intelligence, cybersecurity and sustainable digital systems.
Book Link: https://bit.ly/4ja78sT
DOI: 10.2174/97988988171141260101
DOI
InterPet4D: capturing human–dog interactions to generate AI-based pet motion generation
InterPet4D is the first large-scale multimodal 4D dataset of natural dog movements in response to human cues
image:
InterPet4D combines synchronized video, audio, and 3D motion data to model human–dog interactions to generate a dataset of human and dog interactions and movements. Using this dataset, InterPetMoGen, a framework that can predict and generate dog movements based on human actions and commands.
view more
Credit: Institute of Science Tokyo, Japan
A new multimodal 4D dataset developed at Institute of Science Tokyo provides a detailed model of how humans and dogs interact through movement, gestures, and speech. The curated dataset “InterPet4D” comprises 6.83 million synchronized frames obtained from 23 human participants and 13 dogs representing 11 breeds. Additionally, the researchers developed an AI framework, InterPetMoGen, using this dataset to predict and generate dog movements responding to human actions and audio cues.
Interactions between humans and dogs involve a continuous exchange of physical and verbal cues. A person may pet a dog, use a hand gesture or give a verbal command, or call the pet from a distance, prompting changes in the dog’s posture, position and/or movement. Understanding these human–animal interactions requires data that captures both participants simultaneously. Yet, AI-based modeling of human–pet interactions remains relatively underexplored compared with human–human and human–object interactions. A major challenge is collecting large-scale data that preserves the timing and context of these interactions, while close-range interactions can cause one participant to block the other from the camera, making detailed motion reconstruction difficult.
To fill this gap, a research team led by Specially Appointed Assistant Professor Yichen Peng along with Professor Hideki Koike from the Department of Computer Science, School of Computing, Institute of Science Tokyo (Science Tokyo), Japan, in collaboration with researchers from Carnegie Mellon University, USA, and other institutions, has developed “InterPet4D,” a multimodal 4D dataset for human–dog interactions. Here, “4D” refers to 3D information captured over time, allowing researchers to study not only what humans and dogs look like, but also how their movements change throughout an interaction. The findings of this study was presented at the 19th European Conference on Computer Vision (ECCV) 2026, one of the leading international conferences in the field of computer vision, to be held on September 9, 2026.
InterPet4D combines several types of information including multi-view video, egocentric video, audio, and 3D motion. To develop this, the team recorded 161 sessions involving 23 human participants and 13 dogs representing 11 breeds. 12 synchronized third-person cameras recorded the interactions from different viewpoints, while an egocentric camera captured the movements from the human participant’s perspective. The recordings were processed to estimate human body and hand motion with the dog’s 3D pose. Along with this, aligned audio and text captions were also provided. The interactions were organized into four categories: petting, commanding, calling, and free-form activities such as fetch, tug-of-war, and chase.
“By capturing human–dog interactions, we wanted to create a dataset that reflects their multimodal nature and supports more systematic research,” says Peng.
Researchers then used the InterPet4D dataset to develop InterPetMoGen (IPMG), an AI framework for generating plausible dog motion from human body and hand movements and accompanying audio cues. This technology converts complex motions into compact “motion tokens” that represent the movements that AI can process. It utilizes an autoregressive transformer, which generates motion sequentially while considering the context of the interaction. A PetVAE module (an autoencoder) learns a compact representation of dog movements, while modality-aware attention helps the model determine how information from different input types should influence the generated motion.
The team also evaluated the generated movements using Fréchet Inception Distance (FID), which measures how closely generated motion resembles real motion, with lower values indicating greater similarity. They used Retrieval Precision to measure how well-generated dog movements correspond to human cues provided to the model and diversity to assess how diverse the generated movements are.
IPMG achieved a kinetic FID of 11.21, compared with 21.22 for the Seq2Seq-Transformer baseline, a 47.2% reduction. It also improved hand-motion alignment from 0.41 to 0.63 and body-motion alignment from 0.38 to 0.59, while increasing motion diversity from 5.01 to 5.93. A user study with 12 participants further evaluated the naturalness and appropriateness of the generated dog responses on a seven-point scale. The full IPMG model received scores of 6.58 for naturality, 6.55 for responsiveness, and 6.63 for overall quality, compared with 4.04, 3.67, and 3.67, respectively, for the Seq2Seq-Transformer.
"The results suggest that modeling different modalities and broader interaction context can help AI-based frameworks predict and generate dog movements that are both more realistic and consistent with human cues,” says Peng.
InterPet4D thus provides a standardized foundation to study human–pet interactions and could support future research in behavioral analysis, animation, virtual agents, and socially aware robotics. The current work focuses on dogs, but does not model physical contact forces and generates fixed-length 10-second motion clips. In the future, the approach could be extended to other species, physical interactions, and longer sequences.
***
About Institute of Science Tokyo (Science Tokyo)
Institute of Science Tokyo (Science Tokyo) was established on October 1, 2024, following the merger between Tokyo Medical and Dental University (TMDU) and Tokyo Institute of Technology (Tokyo Tech), with the mission of “Advancing science and human wellbeing to create value for and with society.”
Method of Research
Computational simulation/modeling
Subject of Research
Animals
Article Title
InterPet4D: A Multimodal 4D Human-Pet Interaction Dataset for Pet Motion Generation
InterPet4D and InterPetMoGen: Advancing AI for Human–Dog Motion Generation [VIDEO]
A new large-scale multimodal 4D dataset, InterPet4D, captures how dogs respond to human movements, gestures, and speech. Developed by researchers at Institute of Science Tokyo and collaborating institutions, the dataset includes 6.83 million synchronized frames from interactions involving 23 people and 13 dogs across 11 breeds. Using this dataset, the researchers developed InterPetMoGen, an AI framework that can generate realistic dog movements in response to human actions and audio cues.
Credit
Institute of Science Tokyo | Video link: https://www.youtube.com/watch?v=B2lUM264VfQ
No comments:
Post a Comment