As the EMCR Informal Talk series are designed to share peoples’ own lives, keeping the Informal Talk as an in-person only event best aligns with its personal nature and can maximize interactions with the audience.
This talk offers a comprehensive review of GNN applications in epidemic modeling, presenting a hierarchical taxonomy for both epidemiological tasks and modeling techniques.
We introduce Dispersing Prompt Expansion DiPEx, a self-supervised prompt learning strategy that overcomes the limitations of manually crafted text queries in VLMs, which often miss objects due to semantic overlap diminishing detection confidence.
While Large Language Models (LLMs) exhibit strong zero-shot capabilities, carefully designed inference-time strategies are crucial for unlocking their full potential. This talk delves into two tasks where this is particularly evident: text ranking and retrieval-augmented generation (RAG).
In this talk, I will discuss an alternative approach through inverse rendering, which enables machine learning models to extract explicit physical representations from raw, unstructured image data, such as Internet photos and videos.
This presentation embarks on a comprehensive exploration of the VLN trajectory, tracing its inception to seminal benchmarks such as Room-to-Room (R2R).
In this talk, we will introduce: (1) The long-term technical goal will the GFMs serve (2) The knowledge gap in the graph domain the GFMs can fill (3) The critical problem GFMs can solve.
Searching the gigantic corpus of online podcasts involves multiple challenges ranging from content and style diversity to expensive audio processing to variable length. In this thesis, we aim to address these challenges and devise novel approaches to improve state-of-the-art performance.
This presentation proposes a series of compression approaches to reduce the computation complexity and memory usage of deep models for efficiency improvement.
Entity Alignment (EA) is crucial for integrating heterogeneous knowledge graphs (KGs) into a unified knowledge base by identifying equivalent entities across them.
This presentation explores the comparative efficacy and influencing factors of three major platforms: Search Engines, Symptom Checkers, and Large Language Model (LLM)-powered Conversational Agents.
Extensive experiments on public benchmark datasets have verified the effectiveness of the two proposed works in retaining excellent recommendation performance.
To ensure DNNs effectively retain past knowledge while accommodating future tasks, we explore CL techniques from the viewpoint of augmenting and modularizing the memorization of DNNs.
In this work, we use MetaMap to map the original dataset, which lacks ground truth, with knowledge from drug-drug interaction databases, thereby deriving the ground truth dataset.
This presentation investigates the role of modularity in advancing neuroevolution algorithms and proposes novel techniques that exploit this property to evolve efficient neural networks.
This talk will discuss a flexible survival analysis method that simultaneously accommodates dependent censoring and eliminates the requirement for specifying the copula.
With the massive development in Information Communication Technology (ICT) in the past decades, people nowadays are used to fast-paced and real-time information exchange and public opinion deliberation.
This seminar introduces several innovations to address challenges of federated GNN-based recommender systems including performance degradation, inflexible architectures, slow convergence, and the demand for substantial local storage resources.
This seminar explores the latest advancements in time series analysis by examining three key aspects: pattern recognition, on-device applications, and complex multivariate time series modelling.
This presentation investigates the potential of large language models (LLMs) for generating personalized online advertisements tailored to specific personality traits and the implications of such technology for political advertising, combining insights from two studies.
In this talk, we first discuss one of the most important aspects of the filter bubble, recommendation diversity, particularly diversified recommendation models and full-stage large-scale online experiments on short-video platforms.
The research findings provide novel insights and understanding of the sensemaking processes in various settings and contribute to modelling practice and the design of supporting tools.
Join us at the 2023 Summer of AI (SAI) from 11-15 December, where you'll hear from UQ's two new Professors of AI, as well as some of our leading academics in the field.
Join us at the 2023 Summer of AI (SAI) from 11-15 December, where you'll hear from UQ's two new Professors of AI, as well as some of our leading academics in the field.
State-of-the-art methods for relational databases date back until the late 1970s, and compute a lossless, dependency-preserving decomposition into Third Normal Form (3NF), which will be in Boyce-Codd Normal Form (BCNF) whenever possible. The talk will showcase two very recent new developments.
In this session, I will provide an overview of database integration, including the motivation, problem definition, important tasks and real-world examples.
In this talk, we will introduce the fundamental notions about scales of measurement and meaningfulness, and we will show how they apply to IR evaluation measures.
This talk will give a high level overview of Large Language Models and present my thoughts on the potential benefits and likely risks of AI and what we should be doing about them.
In this talk I will first briefly introduce my previous work in Immersive Analytics, which includes the visualisation of abstract and 3D data in multiple XR scenarios.
Speaker: Toni Peggrem
Are you interested in the future of artificial intelligence (AI) in Queensland? Join us for an exclusive one-hour talk into the Queensland AI Hub.
Speaker: Dr Maxime Cordeil (University of Queensland)
In this talk I will first briefly introduce my previous work in Immersive Analytics, which includes the visualisation of abstract and 3D data in multiple XR scenarios.
Speaker: Yi Zhang
We introduce a client-server framework designed to fortify MARL in real-world scenarios, achieving scalability, parallelization, and privacy preservation.
Speaker: Haodong Hong
Our research introduces a novel task, Vision-and-Language Navigation with Multi-modal Prompts (VLN-MP), in which instructions consist of both natural language and images as prompts.
Speaker: Ekaterina Khramtsova
In this research, we explore various methods for assessing the generalisability of Deep Neural Networks on OOD samples within different scenarios, namely for model selection and for performance estimation.
Speaker: Yawen Zhao
By overcoming three key challenges, we aim to work towards PU boosting methods which have superior performance alongside computational efficiency and minimal dependence on hyperparameter tuning.
Speaker: Yiyun Zhang
In this study, we propose novel unsupervised approaches for BTRS analysis, specifically focusing on change and damage detection in buildings, without the need to use any annotations.
Speaker: Sara Hajari
In this research, a detailed exploration of problem instance generation is carried out, and possible ways this approach can be used in benchmarking practice are discussed.
Speaker: Chenhao Zhang
My research aims to improve recommendation systems in low-data scenarios, benefiting small and medium-sized companies and responding to public emergencies.
Speaker: Cheng Soon Ong, Data61, CSIRO
The AI hype claims that everything can be solved by AI. The reality is that while there are many exciting advances in recent years, many open problems remain.
Speaker: Shaochen Yu
As the role of data amplifies in decision-making, our methodologies promise efficient and streamlined solutions in format identification.
Speaker: Jiechen Xu
The process of data annotation, also referred to as data labeling, is a crucial step in various research fields like machine learning and behavioral studies.
Speaker: Dr Zhen Fang (University of Technology Sydney)
In this talk, we will present the latest advancements in OOD detection theory, and OOD detection algorithms.
Speaker: Sharon Yixuan Li (University of Wisconsin-Madison)
I will introduce a new algorithmic framework, which jointly optimizes for both accurate classification of ID samples, and reliable detection of OOD data.
Speaker: Prof Phoebe Chen (La Trobe University)
There is a large number of possible applications that can benefit from the analysis of multimedia data.
Speaker: Akari Asai (University of Washington)
We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries.
Speaker: Xinyi Gao
This comprehensive experimental study demonstrates that SNS consistently outperforms existing methods in different benchmark datasets.
Speaker: Hechuan Wen
Causal inference is increasingly important in guiding decision-making in high-stake domains, such as healthcare, education, e-commerce, etc.
Speaker: Dr Shoujin Wang (University of Technology Sydney)
In recent years, sequential/session-based recommendations have emerged as a new recommendation paradigm to well model users’ dynamic and short-term preferences for more accurate and timely recommendations.
Speaker: Andrea Parker, Growth ML Engineer (Weights & Biases)
Join us to learn all about experiment tracking at scale with Pachyderm and Weights & Biases.
Speaker: Dr Grace Hui Yang (Georgetown University)
We propose a novel SEgment-based Neural Indexing method, SEINE, which provides a general indexing framework that can flexibly support a variety of interaction-based neural retrieval methods.
Speaker: Prof Stefan Böttcher - Universität Paderborn (Germany)
This talk gives an overview of the key ideas behind grammar-based compression techniques for strings, trees, and graphs.
Speaker: Dr Ziran Wang (Purdue University)
In this talk, a Mobility Digital Twin (MDT) framework is introduced, which is defined as an Artificial Intelligence (AI)-based data-driven cloud-edge-device framework for mobility services.
Speaker: Dr Shixun Huang (RMIT University)
In this talk, recent advances under multiple fields (i.e., data mining, viral marketing and urban computing) of graph analytics will be introduced.
Speaker: Zhuoxiao (Ivan) Chen
Our research focuses on optimising the model performance for 3D object detection, especially when the labelling budget is limited.
Speaker: A/Prof Ujwal Gadiraju (Delft University of Technology, the Netherlands)
This talk will discuss the intriguing and pertinent role of human input in propelling better AI technology in the quickly evolving age of generative models.
Speaker: Dr Matthias Weidlich (Humboldt-Universität zu Berlin (HU))
In this talk, we present some of our recent results on achieving such distribution with the model of MuSE graphs as well as optimizations that rely on push-pull-communication.
Speaker: Dr Jing Zhang (Australian National University)
In this talk, we will explain the basic idea of score-based diffusion models, and explore its potential in 2D/3D vision tasks.
Speaker: Prof Abraham Bernstein (University of Zurich)
This talk highlights that computer science needs to increasingly engage with both the social and normative challenges of our work, possibly producing a new understanding of our discipline.
Speaker: Professor Shane Culpepper, RMIT University
In this talk, we will discuss a novel multi-task learning approach which can be used to produce more effective neural ranking models.