ATM-Bench ...
A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data, featuring referential queries, evidence-grounded answering, and multi-source reasoning.
A benchmark for long-term personalized memory QA spanning ~4 years of multimodal data, featuring referential queries, evidence-grounded answering, and multi-source reasoning.
Retrieval-Guided Contrastive Learning for Hateful Meme Detection (ACL 2024) and Robust Adaptation of Large Multimodal Models for Retrieval-Augmented Hateful Meme Detection (EMNLP 2025 Oral).
A dashboard for monitoring and visualizing token usage across LLM API calls.
Turn an agent’s work — progress, reviews, research, comparisons — into a single self-contained, reviewable HTML page.
Learning to Explain-then-Detect for Hateful Meme Detection (ICLR 2026). A novel multimodal RL approach for interpretable and explainable content moderation.
Comprehensive notes and materials for the Cambridge Engineering 3F3 Statistical Signal Processing course.
Course notes for Cambridge Engineering 3F7 covering information theory, source coding, and channel coding.
Implementation and experiments with blue noise sampling algorithms.
Exercises and examples for learning concurrent programming patterns in C++.
Data analysis project exploring correlations between gene expression levels and tumor characteristics.
An agent system that interprets and responds to gesture inputs using computer vision.
A flood warning system for the UK, built with Python for real-time monitoring of flood risk data.