2025 presentations
17 October 2025
CBDRH presentation:
Universal Verifier
Larry Bi
PhD student
10 October 2025
CBDRH presentation on OpenAI ArXiv paper:
Why Language Models Hallucinate
Sandy Sa, PhD candidate
Larry Bi, PhD student
3 October 2025
CBDRH presentation:
DSPy in practice
Tim Chard
School of Computing, Macquarie University
26 September 2025
Discussion on Stanford CS336 Language Modeling from Scratch:
Alignment - RL
Tatsunori Hashimoto
Assistant Professor of Computer Science
19 September 2025
Discussion on Stanford CS336 Language Modeling from Scratch:
Alignment - SFT/RLHF
Tatsunori Hashimoto
Assistant Professor of Computer Science
12 September 2025
Summary and discussion on the Stanford CS25 guest lecture:
Large Language Model Reasoning
Denny Zhou, Google Deepmind
Stanford CS25
29 August 2025
Discussion on the Stanford CS25 presentation:
Large Language Model Reasoning
Denny Zhou, Google Deepmind
Stanford CS25
15 August 2025
Discussion on the Welch Labs presentation:
Why Deep Learning Works Unreasonably Well
Welch Labs
1 August 2025
Discussion on the Stanford Online presentation:
Language Modeling from Scratch: Evaluation
Percy Liang
Associate Professor of Computer Science
Stanford CS336
25 July 2025
Presentation 1:
Automating Clinical Coding Using Prompt Engineering with Large Language Models
Usha Kaur Khalsa
CBDRH UNSW
Presentation 2:
Do Thinking-LLMs Dream of Reasoning Minds?
Larry Bi
CBDRH UNSW
18 July 2025
Discussion on the Stanford Online presentation:
Language Modeling from Scratch: Overview
Percy Liang
Associate Professor of Computer Science
Stanford CS336
4 July 2025
Discussion on the online presentation:
Demystifying Mixtral of Experts Part2
Larry Albert Jiang, Mistral AI / University of Cambridge
Stanford CS25: V4 Stanford online
20 June 2025
CBDRH guest presentation:
Graph Kernel Methods and Some Applications
Dr David Kohan Marzagao
King's College London
13 June 2025
Discussion on the online presentation:
Demystifying Mixtral of Experts
Larry Albert Jiang, Mistral AI / University of Cambridge
Stanford CS25: V4 Stanford online
6 June 2025
Training superhuman coding models at Cursor
30 May 2025
Presentation & Discussion:
How AI Tools Are Quietly Breaking the Healthcare System in US
Larry Bi
CBDRH, UNSW
11 April 2025
CBDRH joint presentation:
Extracting Health Entities from Discharge Summaries: A Pilot Study Using Fine-Tuned LLMs
Alan Jincong Chen
Prompt Engineering Approaches for Automated Health Entity Extraction In Hospital Notes
Ida Made Hrisikesa Wiweka
21 March 2025
Presentation:
OxonFair: A Flexible Toolkit for Algorithmic Fairness
Dr Eoin Delaney
University of Oxford
21 February 2025
CBDRH Presentation:
Sufficient vs. Necessary Explanations (and what lies in between)
Beepul Bharti
PhD student
Johns Hopkins University
7 February 2025
CSIRO's Data61 Presentation:
Swiss Cheese Model for AI Safety
Dr Qinghua Lu
Principal research scientist
Data61 CSIRO
