{"links":{"self":"http://dataportal.arc.gov.au/NCGP/API/grants/DE260101852"},"data":{"type":"grant-details","id":"DE260101852","attributes":{"code":"DE260101852","administering-organisation":"The University of Western Australia","announcement-administering-organisation":"The University of Western Australia","scheme-name":"Discovery Early Career Researcher Award","grant-status":"Active","funding-commencement-year":2026,"years-funded":3,"project-start-date":"2026-02-16","anticipated-end-date":"2029-02-15","grant-summary":"Agentic Learning for Efficient and Generalisable Visual Grounding. This project aims to develop advanced artificial intelligence systems that can understand and interpret complex visual environments more effectively, efficiently, and transparently. Current artificial intelligence models for tasks often struggle to adapt to new scenarios, require vast amounts of labeled data, and lack clarity in how decisions are made. By combining visual perception with human-like reasoning, this research will create systems that actively refine their understanding of scenes, ask questions when uncertain, and explain their decisions in plain language. The outcomes will enable safer autonomous systems and more reliable healthcare diagnostics while reducing reliance on costly data annotation.","funding-current":528371.00,"funding-at-announcement":524178,"investigators-current":[{"title":"Dr","firstName":"Lian","familyName":"Xu","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0002-1759-2941 "}],"investigators-at-announcement":[{"title":"Dr","firstName":"Lian","familyName":"Xu","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0002-1759-2941 "}],"organisations-current":[{"organisationName":"The University of Western Australia","roleName":"Administering Organisation","state":"WA"}],"organisations-at-announcement":[{"organisationName":"The University of Western Australia","roleName":"Administering Organisation","state":"WA"}],"field-of-research":[{"isPrimary":true,"code":"4603","name":"Computer Vision and Multimedia Computation","type":"FOR20"},{"isPrimary":false,"code":"460304","name":"Computer Vision","type":"FOR20"}],"socio-economic-objective":[{"code":"220403","name":"Artificial Intelligence","type":"SEO20"}],"international-collaboration":["Germany","Hong Kong (SAR of China)","United Arab Emirates"],"lief-register":[],"achievement-summary":null,"national-interest-test-statement":"This research will develop advanced artificial intelligence systems that help Australia tackle critical challenges in healthcare, transport, and aged care while strengthening our economy. By creating technology that interprets visual scenes with human-like reasoning, the project aims to improve safety in self-driving vehicles, reduce errors in medical imaging diagnostics, and enable robots to assist older Australians in living independently. These innovations will lower healthcare costs, address workforce shortages in aged care, and make transportation safer and more efficient. The work will also position Australia as a global leader in ethical and trustworthy AI, creating skilled jobs in the robotics and technology sectors. By reducing reliance on expensive data labeling, the solutions will be accessible to small businesses and regional communities, fostering equitable access to cutting-edge tools. This research directly supports national priorities like healthy aging, road safety, and economic resilience, ensuring public investment delivers tangible benefits for all Australians."}}}