I'm recruiting a PhD student to work on human-AI collaboration and multi-agent consensus by exploring communication protocols from AI debate to hybrid human-AI systems. This studentship is for UK home students. Deadline is: 20/3/2026.
Congrat Wenjie for his first PhD paper on multi-rater learning (MRL): "Reciprocal Teaching: Dynamic multi-model teacher-student learning for multiple noisy annotations" accepted at WACV 2026. The main idea is to integrate noisy label learning into MRL.
Congrat Arpit for the acceptance of his article "PASS: Peer-agreement based sample selection for training with instance dependent noisy labels" (doi.org/10.1016/j.im...) on Image and Vision Computing. This paper proposes a new way to select samples for training on datasets with noisy labels.
Congratulate Zheng for his AAAI 2026 paper "Coverage-constrained human-AI cooperation with multiple experts" (arxiv.org/abs/2411.11976) that frames the human-AI collaboration as a constrained optimisation trading off between efficiency and effectiveness, and employs penalty method to optimise.
Our implementation in Jax can be found on Github at github.com/cnguyen10/pl2d
This research is a part of the PecMan project (sites.google.com/view/pecmanp...) funded by EPSRC - UKRI, led by Professor Gustavo Carneiro from CVSSP - University of Surrey, and in collaboration with Dr Toan Do from @monashuniversity.bsky.social
A workload constraint is also integrated into, allowing the system to distribute workload evenly across all experts (otherwise, the system will not learn and defer all samples to the best team member, causing unfairness and burnout).
This paper addresses the problem of missing annotations made by human experts, meaning that each human expert annotates only a part of the training dataset.
Excited to share that our research in "Probabilistic learning to defer" (openreview.net/forum?id=zl0...) has been accepted as an oral presentation at #ICLR2025.
