iiinova — where your digital self keeps evolving

Cuong Nguyen @probabilita.bsky.social · 09/08/2026

Congratulation to Wenjie Ai for his second paper entitled "Bias-Breaking Relabeling for Noisy-Label Learning" (openreview.net/forum?id=SKc... ) being accepted to be presented at British Machine Vision Conference 2026 in Lancaster, UK.

openreview.net

Verifying your browser | OpenReview

Please complete the verification above.

010

Cuong Nguyen @probabilita.bsky.social · 02/07/2026

Congrats Cuong Pham for an accepted paper at ACL 2026, entitled “Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models”

000

Cuong Nguyen @probabilita.bsky.social · 01/07/2026

Congratulation Milad for his first conference paper which will be presented at MICCAI 2026 in Strasbourg, France. The paper is to emply unsupervised learning to cluster samples into pseudo-cohorts when cohort attributes are unavailable. Check out the paper at

arxiv.org

Fairness Beyond Demographics: Optimizing Performance Across Appearance-Based Hidden Cohorts in Medical Imaging

Medical image analysis models can exhibit performance disparities across patient subgroups, threatening clinical safety and fairness. Existing methods typically address this issue by optimizing…

000

Cuong Nguyen @probabilita.bsky.social · 23/04/2026

Our paper “Beyond Uniformity: Sample and Frequency Meta Weighting for Post-Training Quantization of Diffusion Models” openreview.net/forum?id=FDd... has been accepted at ICLR 2026. Congrats Cuong Pham and the team at Monash!

openreview.net

Beyond Uniformity: Sample and Frequency Meta Weighting for...

Post-training quantization (PTQ) is an attractive approach for compressing diffusion models to speed up the sampling process and reduce the memory footprint. Most existing PTQ methods uniformly...

000

Cuong Nguyen @probabilita.bsky.social · 01/04/2026

Congratulation, Zheng Zhang for one publication on Pattern Recognition: "Learning to complement with multiple humans" (doi.org/10.1016/j.pa...). The paper proposes having either AI or AI + human rather than human alone to make decisions.

doi.org

Learning to complement with multiple humans

Solution for addressing real-world image classification challenges. Human-AI collaborative classification (HAI-CC) aims to synergise the efficiency of…

000

Cuong Nguyen @probabilita.bsky.social · 08/03/2026

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.

findaphd.com

020

Cuong Nguyen @probabilita.bsky.social · 06/03/2026

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.

000

Cuong Nguyen @probabilita.bsky.social · 02/02/2026

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.

000

Cuong Nguyen @probabilita.bsky.social · 21/01/2026

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.

arxiv.org

Coverage-Constrained Human-AI Cooperation with Multiple Experts

Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expe...

010