Soujanya Poria
সৌজন্য পড়িয়া
Associate Professor, Nanyang Technological University (NTU)
I lead the DeCLaRe Lab (Deep Cognition and Language Research). My current research focuses on memory for AI agents, efficient and reliable multi-agent systems, and reasoning.
Our lab also works on AI safety and trustworthiness, multimodality, AI for science, efficiency, and embodied AI.
Research
Memory for AI agents
What an agent should retain, how that memory updates, and how it shapes the next action.
Multi-agent systems and reliability
How agents learn whom to trust and when to ask for advice.
Efficient learning and attention
How much computation a model needs to learn and to retain what is useful.
Embodied agents and grounded reasoning
Connecting visual reasoning to looking, moving, and testing in the world.
Safety and evaluation
Whether agents stay within their intended role, and how to measure it.
News
I’m excited to be one of the PC Chairs for EMNLP 2027.
2 papers accepted to NeurIPS 2026, including 1 Spotlight
2 papers accepted to ICML 2026
4 papers accepted to ICLR 2026
2 papers accepted to AAAI 2026
Highly Cited Researcher
Recognized by Web of Science, 2026.
VentureBeat features δ-mem
An interview on working memory for long-running AI agents. May 2026.