Research Projects

Characterisation of Goalkeeper Actions from Skeletal Data
Characterised goalkeeper actions from skeletal data by learning robust representations via contrastive learning and analysing their structure using …
Mechanistic Interpretability of VLM on Spatial Relational Reasoning
Studied LLaVA-1.5-7B using a controlled synthetic benchmark; revealed an existence bias causing yes-bias in binary relational tasks through logit …
Evaluating and Finetuning LLMs for Multilingual Legal Summarisation
Adapted Apertus 8B/70B for Swiss legal summarisation, showing full fine-tuning outperforms GPT-4o and Claude 3.5 Sonnet on BERTScore and ROUGE, while …