Empathy, safety, and human agency in mental health settings [Link]

Related publications:

• Towards Understanding and Measuring COGNITIVE ATROPHY in LLM Behaviour, NeurIPS 2026

• Keyphrase Generative Representation of Youth Crisis Conversations Beyond Static Taxonomies, under review 2026

• Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support, EMNLP, Findings 2026

• When can we trust LLMs in mental health? large-scale benchmarks for reliable LLM evaluation, EACL (Oral), 2026

• Position: Beyond Assistance – Reimagining LLMs as Ethical and Adaptive Co-Creators in Mental Health Care, ICML, 2025

• The FAIIR conversational AI agent assistant for youth mental health service provision, npj digital medicine, 2025

Trainees involved:

• Abeer Badawi (Postdoctoral Fellow)

• Moyosoreoluwa Olatosi (MA Student)

• Shayan Emzad (MSc Student)

Other Collaborators: 

• Mizanur Rahman

• Elahe Rahimi

Multimodal Deep Learning and Reasoning in VLMs [Link]

Related publications:

• Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs, NeurIPS 2026

• OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models, NeurIPS 2026

• Open-pmc-18m: A high-fidelity large-scale medical dataset for multimodal representation learning, MICCAI, 2026

• Advancing medical representation learning through high-quality data, MICCAI, 2025

• Benchmarking vision-language contrastive methods for medical representation learning, ICML Workshop, 2025

• A Shared Encoder Approach to Multimodal Representation Learning, 2025

• Vldbench: Vision language models disinformation detection benchmark, Information Fusion, 2025

Trainees involved:

• Negin Baghbanzadeh (PhD Student)

• Most Husne Jahan (PhD Student)

• Shayan Emzad (MSc Student)