BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Australia/Melbourne BEGIN:DAYLIGHT DTSTART:20261004T030000 TZOFFSETFROM:+1000 TZOFFSETTO:+1100 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=10 TZNAME:AEDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20270404T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4 TZNAME:AEST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20261110T055455Z UID:19C7BC27-6631-4A00-8438-3133CF59C9B3 DTSTART;TZID=Australia/Melbourne:20261130T113000 DTEND;TZID=Australia/Melbourne:20261130T123000 DESCRIPTION:Speaker:\n\nA/Prof. Hamid Rezatofighi\, Monash University\, Aus tralia\n\nOnline Teams meeting:\n\nMonday\, 30 Nov 2026 at 11.30am\n\nhttp s://teams.microsoft.com/l/meetup-join/19%3ameeting_MzViZjI3MWMtNWQxMy00OWJ iLThmZWEtNzgzOTM5NjVmYTAx%40thread.v2/0?context=%7b%22Tid%22%3a%22df7f7579 -3e9c-4a7e-b844-420280f53859%22%2c%22Oid%22%3a%2269696846-a9c7-4b61-8250-1 5ed5bdb7fe5%22%7d[The online link](https://teams.microsoft.com/l/meetup-jo in/19%3ameeting_MTAzOTljOTItYzg2MS00MzI5LTg4MGEtYzBhOGY1YWI3OWEw%40thread. v2/0?context=%7b%22Tid%22%3a%22df7f7579-3e9c-4a7e-b844-420280f53859%22%2c% 22Oid%22%3a%2269696846-a9c7-4b61-8250-15ed5bdb7fe5%22%7d)\n\nHost: IEEE Vi ctorian Section SMC Chapter and Swinburne University of Technology. Organi zed by A/Prof. Hailing Zhou and Prof. Saeid Nahavandi\n\nAbstract:\n\nRece nt advances in neural foundation models have transformed artificial intell igence\, enabling remarkable capabilities in visual perception\, language understanding\, and robotic control. Yet\, despite the growing emphasis on scaling models\, data\, and computation\, fundamental challenges remain i n complex reasoning\, compositional generalisation\, and interpretable dec ision-making. Inspired by human cognition\, this raises an important quest ion: Can fast\, intuitive\, System 1-like neural foundation models alone d eliver the sophisticated intelligence required for autonomous systems oper ating in complex\, dynamic environments?\n\nIn this talk\, I will advocate for a complementary direction inspired by System 2 cognition: slower\, de liberate\, structured\, and compositional reasoning. I will present our re cent research at Monash on agentic\, compositional neuro-symbolic AI\, com bining the strengths of neural foundation models in perception and languag e understanding with explicit world representations\, logical reasoning\, memory\, and planning. Rather than relying exclusively on monolithic end-t o-end neural architectures\, our approach explores how specialised intelli gent agents and structured reasoning mechanisms can work together to addre ss complex visual reasoning and decision-making challenges.\n\nI will high light some of our recent research contributions that expose limitations of current neural foundation models and demonstrate how agentic neuro-symbol ic approaches can advance visual understanding\, compositional reasoning\, and adaptive decision-making. I will also showcase how these principles e xtend to robotic autonomy\, drawing on our DARPA- and ONR-supported resear ch\, including autonomous robotic systems capable of complex missions unde r uncertainty and dynamic environmental conditions.\n\nCo-sponsored by: Sw inburne University of Technology\n\nSpeaker(s): Hamid \, \n\nRoom: 609A\, Bldg: EN\, John St\, Hawthorn VIC\, Melbourne\, Victoria\, Australia\, 312 2 LOCATION:Room: 609A\, Bldg: EN\, John St\, Hawthorn VIC\, Melbourne\, Victo ria\, Australia\, 3122 ORGANIZER:hailingzhou@swin.edu.au SEQUENCE:13 SUMMARY:In Defence of System 2: Human-Inspired Cognitive Intelligence for R easoning and Robotics URL;VALUE=URI:https://events.vtools.ieee.org/m/592713 X-ALT-DESC:Description: <br /><p><strong>Speaker:&nbsp\;</strong></p>\n<p>A /Prof. Hamid Rezatofighi\, Monash University\, Australia</p>\n<p>&nbsp\;</ p>\n<p><strong>Online Teams meeting:</strong></p>\n<p>Monday\, 30 Nov 2026 at 11.30am</p>\n<p><a href="https://teams.microsoft.com/l/meetup-join/19% 3ameeting_MzViZjI3MWMtNWQxMy00OWJiLThmZWEtNzgzOTM5NjVmYTAx%40thread.v2/0?c ontext=%7b%22Tid%22%3a%22df7f7579-3e9c-4a7e-b844-420280f53859%22%2c%22Oid% 22%3a%2269696846-a9c7-4b61-8250-15ed5bdb7fe5%22%7d" target="_blank" rel="n ofollow noopener"><br></a><a href="https://teams.microsoft.com/l/meetup-jo in/19%3ameeting_MTAzOTljOTItYzg2MS00MzI5LTg4MGEtYzBhOGY1YWI3OWEw%40thread. v2/0?context=%7b%22Tid%22%3a%22df7f7579-3e9c-4a7e-b844-420280f53859%22%2c% 22Oid%22%3a%2269696846-a9c7-4b61-8250-15ed5bdb7fe5%22%7d" target="_blank" rel="nofollow noopener">The online link</a></p>\n<p><br>Host: IEEE Victori an Section SMC Chapter and Swinburne University of Technology. Organized b y A/Prof. Hailing Zhou and Prof. Saeid Nahavandi</p>\n<p>&nbsp\;</p>\n<p>< strong>Abstract:</strong></p>\n<p>Recent advances in neural foundation mod els have transformed artificial intelligence\, enabling remarkable capabil ities in visual perception\, language understanding\, and robotic control. Yet\, despite the growing emphasis on scaling models\, data\, and computa tion\, fundamental challenges remain in complex reasoning\, compositional generalisation\, and interpretable decision-making. Inspired by human cogn ition\, this raises an important question: Can fast\, intuitive\, System 1 -like neural foundation models alone deliver the sophisticated intelligenc e required for autonomous systems operating in complex\, dynamic environme nts?</p>\n<p>In this talk\, I will advocate for a complementary direction inspired by System 2 cognition: slower\, deliberate\, structured\, and com positional reasoning. I will present our recent research at Monash on agen tic\, compositional neuro-symbolic AI\, combining the strengths of neural foundation models in perception and language understanding with explicit w orld representations\, logical reasoning\, memory\, and planning. Rather t han relying exclusively on monolithic end-to-end neural architectures\, ou r approach explores how specialised intelligent agents and structured reas oning mechanisms can work together to address complex visual reasoning and decision-making challenges.</p>\n<p>I will highlight some of our recent r esearch contributions that expose limitations of current neural foundation models and demonstrate how agentic neuro-symbolic approaches can advance visual understanding\, compositional reasoning\, and adaptive decision-mak ing. I will also showcase how these principles extend to robotic autonomy\ , drawing on our DARPA- and ONR-supported research\, including autonomous robotic systems capable of complex missions under uncertainty and dynamic environmental conditions.</p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR