{"links":{"self":"http://dataportal.arc.gov.au/NCGP/API/grants/DE260101993"},"data":{"type":"grant-details","id":"DE260101993","attributes":{"code":"DE260101993","administering-organisation":"The University of Sydney","announcement-administering-organisation":"The University of Sydney","scheme-name":"Discovery Early Career Researcher Award","grant-status":"Active","funding-commencement-year":2026,"years-funded":3,"project-start-date":"2026-01-01","anticipated-end-date":"2028-12-31","grant-summary":"Causal Representation Learning for Controllable Text-To-Image Generation . This project aims to improve the controllability of existing text-to-image generation models. It expects to generate new knowledge for multimodal generative models by leveraging causal representation learning and contributes to the development of more trustworthy, interpretable, and controllable generative AI. Expected outcomes include the creation of a new large-scale multimodal benchmark dataset, the development of multiple practical controllable text-to-image generation models, and the establishment of theoretical guarantees for these models. This research will provide significant benefits by enabling safer AI applications across different domains and mitigating risks associated with unreliable or biased AI outputs.","funding-current":520811.00,"funding-at-announcement":516678,"investigators-current":[{"title":"Dr","firstName":"Yu","familyName":"Yao","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0001-9797-364X "}],"investigators-at-announcement":[{"title":"Dr","firstName":"Yu","familyName":"Yao","roleName":"Discovery Early Career Researcher Award","roleCode":"DECRA","isFellowship":true,"orcidIdentifier":"0000-0001-9797-364X "}],"organisations-current":[{"organisationName":"The University of Sydney","roleName":"Administering Organisation","state":"NSW"}],"organisations-at-announcement":[{"organisationName":"The University of Sydney","roleName":"Administering Organisation","state":"NSW"}],"field-of-research":[{"isPrimary":true,"code":"4603","name":"Computer Vision and Multimedia Computation","type":"FOR20"},{"isPrimary":false,"code":"460307","name":"Multimodal Analysis and Synthesis","type":"FOR20"},{"isPrimary":false,"code":"460308","name":"Pattern Recognition","type":"FOR20"}],"socio-economic-objective":[{"code":"220405","name":"Cybersecurity","type":"SEO20"},{"code":"220501","name":"Animation, Video Games and Computer Generated Imagery Services","type":"SEO20"},{"code":"280115","name":"Expanding Knowledge In the Information and Computing Sciences","type":"SEO20"}],"international-collaboration":["Japan","United States of America"],"lief-register":[],"achievement-summary":null,"national-interest-test-statement":"Australia’s rapid adoption of generative AI presents both opportunities and risks for industry, society, and government. This project will directly strengthen Australia’s role in the global digital economy by developing safer, more interpretable text-to-image AI capable of generating coherent and accurate imagery. By ensuring images align exactly with user intent, these advancements benefit sectors such as design, advertising, healthcare, scientific visualization, and accessibility technologies, enhancing productivity and lowering costs for local businesses. In doing so, the project meets national objectives around fostering innovation, growing advanced technology industries, and ensuring responsible AI development. Further, the research addresses key concerns around AI reliability and trustworthiness by embedding causal reasoning into generative models, making them more transparent and predictable. This aligns with Australia’s commitment to ethical AI, reducing potential biases and misinformation. By building essential expertise in causal representation learning and training the next generation of AI researchers, the project solidifies Australia’s reputation for leading-edge AI innovation. As a result, it attracts international collaboration, supports skilled job creation, and contributes to the broader public interest, ensuring Australia remains competitive and secure in an evolving global digital landscape."}}}