Reliable Machine Learning Models via Uncertainty-Guided Checkpoint Selection
Industrial talk, Deakin Defence Conference 2026, Deakin Downtown, Melbourne, Australia
Talks
2026 (2)
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
Invited talk, Kingston AI Symposium 2026, Adelaide Oval, South Australia
2025 (3)
How Different Memory Types Help Agents Learn and Adapt
Invited talk, RemembeRL Workshop, CORL2025, South Korea (virtual)
AI Horizons – Conversations with Australia’s leading and emerging researchers
Invited talk, Australian Academy of Technology and Engineering, Australia (virtual)
Memory in Autonomous Agents: From Reinforcement Learning to Large Language Models
Invited talk, SydneyAI Meetup, Sydney (virtual) Australia
2024 (3)
Towards Safe and Controlled Large Language Models
Conference talk, AJCAI, Melbourne, Australia
Recent Advanced in LLM Finetuning and Uncertainty, Confidence and Hallucination in LLMs
Industrial talk, Cinnamon AI Bootcamp, Virtual, Vietnam
Unlocking Exploration: Self-Motivated Agents Thrive on Memory-Driven Curiosity
Conference talk, AAMAS, Aukland, New Zealand
2022 (2)
Memory-Based Reinforcement Learning
Conference talk, AJCAI, Perth, Australia
Memory for Lean Reinforcement Learning
Industrial talk, FPT Software AI Center, virtual, Vietnam
2021 (2)
Neural machine reasoning
Conference talk, IJCAI Tutorial, virtual, Canada
From deep learning to deep reasoning
Conference talk, KDD Tutorial, virtual, Singapore
2018 (1)
Generalization for Good: A story on OCR evolution
Industrial talk, Cinnamon AI Marathon, Virtual, Vietnam
2017 (1)
Theory behind conversational agents
Industrial talk, Topdev Vietnam Mobile Day, Hanoi, Vietnam