Program overview
Important Notice: The schedule is subject to change due to various factors. Please check for updates during the conference.
Parallel Sessions: Sessions designated as "Track A" and "Track B" are conducted simultaneously in separate venues during the same time period. Specific room assignments will be updated soon.
Program Information: The main conference track does not include poster sessions. The Doctor Forum schedule will be announced separately.
Workshops and Tutorials: For detailed information about the workshops and tutorials on Tuesday, December 2nd, please visit the Workshops and Tutorials page.
08:30
DAIRNet Registration
09:00
DAIRNet Symposium
10:30
Morning Tea
11:00
DAIRNet Symposium
12:30
Lunch
13:00
DAIRNet Symposium
15:15
Afternoon Tea
15:30
DAIRNet Symposium
08:00
Registration
08:30
Morning Tea
09:00
10:00
Break
11:15
Break
12:30
Lunch
13:45
14:45
Break
16:00
Afternoon Tea
16:15
PhD Forum — Panel Discussion
Ends 17:30
08:00
Registration
08:30
Morning Tea
09:00
Welcome + Keynote — Marcus Hutter (DeepMind)
10:00
Break
10:15
Keynote — Jing Jiang (ANU)
11:15
Break
11:30
Long Oral Sessions
Papers: 7, 18, 22, 32
Papers: 38, 46, 58, 127
12:30
Lunch
13:45
Keynote — Geoff Webb (Monash)
14:45
Break
15:00
Short Oral Sessions
Papers: 1, 5, 13, 14, E16
Papers: 15, 16, 24, 26, E2
16:00
Afternoon Tea
16:15
Short Oral Sessions
Papers: 27, 34, 50, E9, E10, E15
Papers: 51, 62, 70, E8, E12, E17
Papers: 28, 60, E3, E5, E13, E18
17:15
Break
17:30
Reception
Ends 19:30
08:00
Registration
08:30
Morning Tea
09:00
Keynote — Navinda Kottege (Data61)
10:00
Break
10:15
Parallel Sessions
Papers: 71, 78, 82, 84, 101, E4
Papers: 103, 109, 113, 118, E14
11:15
Break
11:30
Parallel Sessions Continue
Papers: 61, 77, 88, 106
Papers: 112, 114, 120, 132
12:30
Lunch
13:45
Keynote — Toby Walsh (UNSW)
14:45
Break
15:00
Parallel Sessions
Papers: 49, 133, 151, 152, E7
Papers: 2, 25, 48, 65, E6
16:00
Afternoon Tea
16:15
Panel Discussion
17:30
Break
17:45
Buses (×3) leave for Old Parliament House
18:00
Banquet
21:00
Buses (×3) return
08:00
Registration
08:30
Morning Tea
09:00
Keynote — Ling Chen (UTS)
10:00
Break
10:15
Keynote — Mengjie Zhang (VUW)
11:15
Break
11:30
Long Oral Sessions
Papers: 39, 44, 108, 121
Papers: 8, 93, 97, 111
12:30
Lunch
13:45
Keynote — Nicholas Mattei (Tulane University)
14:45
Break
15:00
Short Oral Sessions
Papers: 68, 80, 92, E11, E19
Papers: 99, 102, 105, 110, 117
16:00
Afternoon Tea
16:15
Short Oral Sessions
Papers: 40, 52, 55, 56, E1
Papers: 57, 66, 95, 122
17:15
Closing / Celebration
| Time | Dec. 1st | Dec. 2nd | ||||||||
| 08:00 | Registration (Foyer) | |||||||||
| 08:30 | DAIRNet Registration (outside 2.02 MRTC) | Morning Tea (Foyer) | ||||||||
| 09:00 | DAIRNet Symposium (2.02 MRTC) |
|
||||||||
| 10:00 | Break | |||||||||
| 10:15 |
|
|||||||||
| 10:30 | Morning Tea (MRTC) | |||||||||
| 11:00 | DAIRNet Symposium (2.02 MRTC) | |||||||||
| 11:15 | Break | |||||||||
| 11:30 |
|
|||||||||
| 12:30 | Lunch (MRTC) | Lunch (Foyer) | ||||||||
| 13:00 | DAIRNet Symposium (2.02 MRTC) | |||||||||
| 13:45 |
Track A
Tutorial 2
Manning Clark Hall
|
Track B
Tutorial 3
Cinema
|
Track C
Tutorial 4
Drama Theatre
|
Track D
Tutorial 5
T2
|
Track E
PhD Forum Poster Session
Gallery
|
|||||
| 14:45 | Break | |||||||||
| 15:00 |
Track A
Tutorial 2
Manning Clark Hall
|
Track B
Tutorial 3
Cinema
|
Track C
Tutorial 4
Drama Theatre
|
Track D
Tutorial 5
T2
|
Track E
PhD Forum Poster Session
Gallery
|
|||||
| 15:15 | Afternoon Tea (MRTC) | |||||||||
| 15:30 | DAIRNet Symposium (2.02 MRTC) | |||||||||
| 16:00 | Afternoon Tea (Foyer) | |||||||||
| 16:15 |
PhD Forum
Panel Discussion
Manning Clark Hall
Ends 17:30
|
|||||||||
| 17:00 | ||||||||||
| Time | Dec. 3rd | Dec. 4th | Dec. 5th | |
| 08:00 | Registration (Foyer) | Registration (Foyer) | Registration (Foyer) | |
| 08:30 | Morning Tea (Foyer) | Morning Tea (Foyer) | Morning Tea (Foyer) | |
| 09:00 |
Keynote
Welcome (5m) + Marcus Hutter (DeepMind)
Manning Clark Hall
|
Keynote
Navinda Kottege (Data61)
Manning Clark Hall
|
Keynote
Ling Chen (UTS)
Manning Clark Hall
|
|
| 10:00 | Break | Break | Break | |
| 10:15 |
Keynote
Jing Jiang (ANU)
Manning Clark Hall
|
Track A
Short Oral Session 6
Manning Clark Hall
Papers: 71, 78, 82, 84, 101, E4
Track B
Short Oral Session 7
Cinema
Papers: 103, 109, 113, 118, E14
|
|
Keynote
Mengjie Zhang (VUW)
Manning Clark Hall
|
| 11:15 | Break | Break | Break | |
| 11:30 |
Track A
Long Oral Session 1
Manning Clark Hall
Papers: 7, 18, 22, 32
Track B
Long Oral Session 2
Cinema
Papers: 38, 46, 58, 127
|
Track A
Long Oral Session 3
Manning Clark Hall
Papers: 61, 77, 88, 106
Track B
Long Oral Session 4
Cinema
Papers: 112, 114, 120, 132
|
|
Track A
Long Oral Session 5
Manning Clark Hall
Papers: 39, 44, 108, 121
Track B
Long Oral Session 6
Cinema
Papers: 8, 93, 97, 111
|
| 12:30 | Lunch (Foyer) | Lunch (Foyer) | Lunch (Foyer) | |
| 13:45 |
Keynote
Geoff Webb (Monash)
Manning Clark Hall
|
Keynote
Toby Walsh (UNSW)
Manning Clark Hall
|
Keynote
Nicholas Mattei (Tulane University)
Manning Clark Hall
|
|
| 14:45 | Break | Break | Break | |
| 15:00 |
Track A
Short Oral Session 1
Manning Clark Hall
Papers: 1, 5, 13, 14, E16
Track B
Short Oral Session 2
Cinema
Papers: 15, 16, 24, 26, E2
|
Track A
Short Oral Session 8
Manning Clark Hall
Papers: 49, 133, 151, 152, E7
Track B
Short Oral Session 9
Cinema
Papers: 2, 25, 48, 65, E6
|
|
Track A
Short Oral Session 10
Manning Clark Hall
Papers: 68, 80, 92, E11, E19
Track B
Short Oral Session 11
Cinema
Papers: 99, 102, 105, 110, 117
|
| 16:00 | Afternoon Tea (Foyer) | Afternoon Tea (Foyer) | Afternoon Tea (Foyer) | |
| 16:15 |
Track A
Short Oral Session 3
Manning Clark Hall
Papers: 27, 34, 50, E9, E10, E15
Track B
Short Oral Session 4
Cinema
Papers: 51, 62, 70, E8, E12, E17
Track C
Short Oral Session 5
Drama Theatre
Papers: 28, 60, E3, E5, E13, E18
|
Panel Discussion
Manning Clark Hall
|
Track A
Short Oral Session 12
Manning Clark Hall
Papers: 40, 52, 55, 56, E1
Track B
Short Oral Session 13
Cinema
Papers: 57, 66, 95, 122
|
|
| 17:15 | Break | Closing / Celebration (Manning Clark Hall) | ||
| 17:30 | Reception (Gallery)Ends 19:30 | Break | ||
| 17:45 | Buses (×3) leave for Old Parliament House (from Kingsley St) | |||
| 18:00 | Banquet — Old Parliament House | |||
| 21:00 | Buses (×3) return (Old Parliament House → Kingsley St) | |||
Session Details
Session Format
Long Oral Sessions: 12-minute presentation followed by 3-minute Q&A session
Short Oral Sessions: 8-minute presentation followed by 2-minute Q&A session
Short Oral Sessions
| Session | Papers |
| Session 1: Graph Learning and Foundation Models | 1: SVDformer: Direction-Aware Spectral Graph Embedding
Learning via SVD and Transformer 5: Price Equilibrium Routing: A Lightweight Framework for Expert Selection in Mixture-of-Experts 13: Analysis of Large Language Model Prompting and Generation using Toulmin's Model 14: Predicting Graph Structure via Adapted Flux Balance Analysis E16: Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025) |
| Session 2: Multi-modal Learning | 15: SimLabel: Consistency-Guided OOD Detection with
Pretrained Vision-Language Models 16: LAPEFT: A Lexicon-Enhanced Approach to Parameter-Efficient Fine-Tuning for Financial News Sentiment Classification 24: Trajectory segmentation and self-supervised classification for subtask discovery 26: Assessing Algorithmic Fairness in Socioeconomic Predictions Using Australian Census Data E2: NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning (ICCV 2025) |
| Session 3: Federated Learning and Graph Learning | 27: An Explainable Graph Learning Framework for Severe
Maternal Morbidity Prediction 34: cFedLAD: A Clustered Additive LoRA Framework for Robust and Personalized Federated Learning 50: Personalized Federated Graph Learning for Heterogeneous Incomplete EHRs E9: Probabilistic Active Goal Recognition (KR 2025) E10: Spatiotemporal Generalization Graph Neural Network-Based Prediction Models by Considering Morphological Diversity in Traffic Networks (IEEE TITS) E15: Graph spatiotemporal process for multivariate time series anomaly detection with missing values (Information Fusion) |
| Session 4: Learning Theory and Feature Selection | 51: Policy Gradient–Based Reinforcement Weighted
Aggregation for Efficient Federated Learning on Heterogeneous Data 62: Automating Perdurant Meta-Property Assignment using GPT-4 70: Coordinate-free $k$-means clustering E12: Many-objective Jaccard-based evolutionary feature selection for high-dimensional imbalanced data classification (IEEE TPAMI) E17: Meta Co-Training: Two Views are Better than One (ECAI 2025) E8: MONSTER — Monash Scalable Time Series Evaluation Repository (DMLR) |
| Session 5: Neural Network Design and Computer Vision Applications | 28: Augmentation and Transformation for Nighttime Cloud
Segmentation in All-Sky Camera Images 60: MFiSP: A Multimodal Fire Spread Prediction Framework E3: DWIM — Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning (ICCV 2025) E5: ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks (IJCAI 2025) E13: Local and global trend Bayesian exponential smoothing models (International Journal of Forecasting) E18: PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulations (IEEE TPAMI) |
| Session 6: Metric Learning and Benchmarking | 71: TripletResNet: A Deep Metric Learning Approach for mTBI
Diagnosis from 3D CT 78: PLNet-12: A Vision-Language Benchmark for Zero-Shot Physical Literacy Analysis Across 12 Fundamental Movements 82: Signal Beneath the Surface: A Deep Learning Pipeline for Marine Acoustic Intelligence 84: Do They Understand Them? An Updated Evaluation on Nonbinary Pronoun Handling in Large Language Models 101: Whose Side Are You On: Investigating Political Bias of Foundational Large Language Models E4: Derm1M: A Million-Scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology (ICCV 2025) |
| Session 7: AI Fairness and Safety | 103: Noise-Robust Topology Estimation of 2D Image Data via
Neural Networks and Persistent Homology 109: All Models Are Miscalibrated, But Some Less So: Comparing Calibration with Conditional Mean Operators 113: Concept Control for LLM Safety Using Radial Basis Field Representations 118: Enhancing RAG System Performance Through Semantic Layout Chunking E14: Feature Unlearning: Theoretical Foundations and Practical Applications with Shuffling (NeurIPS 2025) |
| Session 8: Robotic AI | 151: TrashTracer: Enabling efficient real-time detection of
underwater marine debris 152: Large Language Models Imitate Logical Reasoning, but at what Cost? 49: PERCY: Personal Emotional Robotic Conversational System 133: Planner-Independent Extraction of Goals and Constraints from Natural Language for Open-World Mobile Robot Missions E7: TextSLAM: Visual SLAM with Semantic Planar Text Features (IEEE TPAMI) |
| Session 9: 3D Vision | 2: A-PriDiff: Anatomical Prior-Guided Conditional Diffusion
for Ultrasound Spine Image Synthesis 25: NoPo3DFusion: Scaling Two Images to Long Videos via 3D-Aware Iterative Diffusion 48: Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction 65: Street Depth-Aware Gaussian for Modeling Dynamic Urban Scenes E6: Hier-SLAM: Scaling-up Semantics in SLAM with a Hierarchically Categorical Gaussian Splitting (ICRA 2025) |
| Session 10: Visual Detection and Recognition | 68: Efficient Craniofacial Microsomia Detection via
Edge-focused 3D Point Cloud Network 80: AFFT: Adapter-based Few-shot Fine-Tuning Framework for Remote Sensing Object Detection 92: EyeDentify: A Deep Learning Approach to Non-Invasive Biometric Identification from Eye Blink Patterns E11: Explaining Facial Expression Recognition (AAMAS 2025) E19: SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models (ACL 2025) |
| Session 11: AI Applications | 99: Weather Forecasting System "Four Seasons in One Day"
and Shelter Suggestion for Sydney & Melbourne & Canberra 102: Paired Hierarchical VAEs for Image-to-Image Translation and Cross Reconstruction 105: Privacy-Centric Seizure Detection Using Surface Normals, Pose and Segmentation Masks 110: Dimensionally Reduced Open-World Clustering: DROWCULA 117: Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images |
| Session 12: Human Computer Interaction | 40: Evolving MCTS Macro-Actions in Real-Time
Domains 52: Understanding Human Situation Awareness in One-to-Many Human-Robot Interaction Scenarios 55: Learning Preferences in Additive Separable Hedonic Project Games 56: A Hybrid Multi-Agent Reinforcement Learning Framework for Decentralised Search-And-Interact Tasks Under Partial Observability E1: ST-GDance: Long-Term and Collision-Free Group Choreography from Music (BMVC 2025) |
| Session 13: Reinforcement Learning | 57: Using Individual Problem Instances for Exploratory
Black Box Optimisation Benchmarking: A Case Study Using XOR Neural Networks 66: Synergistic MARL: Unifying Physics-Informed, Meta Learning, and Hybrid Learning to Outperform Communication-Based Coordination 95: Requirements-based Explainability for Multi-Agent Systems 122: Guardrail Guided Policy Optimisation: Learning Disentangled Safety Constraints |
Long Oral Sessions
| Session | Papers |
| Session 1: Data Efficient Graph Learning | 7: Predicting Generalization Error under Graph Distribution
Shifts via Parameter Discrepancy with Accumulated Gradient 18: RePrompt: Towards Robust Continual Test-Time Adaptation via Replay Prompt for CLIP 22: Graph-based Integrated Gradients for Explaining Graph Neural Networks 32: Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-efficient Psychiatric Diagnosis |
| Session 2: Explainable AI | 38: Minimum Message Length t-test 46: TrustGuard: IoT Intrusion Detection with XAI-Driven Feature Refinement for Enhanced Multi-class Edge Classification 58: MammoMix: Leveraging Mixture of Experts for Robust Mammogram Breast Detection 127: On Explaining Proxy Discrimination and Unfairness in Individual Decisions Made by AI Systems |
| Session 3: Multi-modal Learning | 61: Towards Scalable Backpropagation-Free Gradient
Estimation 77: On Knowledge-Informed Deep Learning for Modelling Complex Spatiotemporal Systems 88: Evaluating Large Language Models for Real-World Engineering Tasks 106: MultiRAG: An Agentic Multi-modal and Multi-source Retrieval-Augmented Generation Framework for Scientific Research |
| Session 4: Learning Theory | 112: The Ensemble Kalman Update is an Empirical Matheron
Update 114: Prompting Instability: An Empirical Study of LLM Robustness in Code Vulnerability Detection 132: Solving Partial Graph Matching as a Stable Matching Problem 120: The Consensus Paradox: When Low Disagreement Leads to Catastrophic Failure in Multi-Teacher Reinforcement Learning |
| Session 5: Computer Vision Applications | 39: PP-Pose: Privacy-Preserving Human Pose Estimation Using
Random High-Frequency Channel Combinations 44: When Language Model Guides Vision: Grounding DINO for Cattle Muzzle Detection 108: Depth-aware Audio Visual Segmentation with Geometry-Heuristic Cross Attention 121: Proactive Air Quality Forecasting and Health Alert System for Melbourne |
| Session 6: Explainable AI | 8: Probabilistic Lipschitzness and the Stable Rank for
Measuring XAI Model Robustness 93: Generation of Ethical Rules Using Large Language Models 97: Towards Search Node-Specific HTN Heuristics 111: Categorization Architecture with Predictive Reasoning and Alignment for UNSPSC |