Portrait of Hadrien Bertrand

Hadrien Bertrand

hadrien.bertrand@mila.quebec
Senior Applied Research Scientist, Applied Machine Learning Research

Publications

LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
Rashid A. Mushkani
Shravan Nayak
Hugo Berard
Allison Cohen
Shin (Alexandre) Koseki
Hadrien Bertrand
We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment, developed through a t… (see more)wo-year participatory process with 30 community organizations to support the pluralistic alignment of text-to-image (T2I) models in inclusive urban planning. The dataset encodes 37,710 pairwise comparisons across 13,462 images, structured along six criteria—Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity—derived from 634 community-defined concepts. Using Direct Preference Optimization (DPO), we fine-tune Stable Diffusion XL to reflect multi-criteria spatial preferences and evaluate the LIVS dataset and the fine-tuned model through four case studies: (1) DPO increases alignment with annotated preferences, particularly when annotation volume is high; (2) preference patterns vary across participant identities, underscoring the need for intersectional data; (3) human-authored prompts generate more distinctive visual outputs than LLM-generated ones, influencing annotation decisiveness; and (4) intersectional groups assign systematically different ratings across criteria, revealing the limitations of single-objective alignment. While DPO improves alignment under specific conditions, the prevalence of neutral ratings indicates that community values are heterogeneous and often ambiguous. LIVS provides a benchmark for developing T2I models that incorporate local, stakeholder-driven preferences, offering a foundation for context-aware alignment in spatial design.
2025-10-06
Proceedings of the 42nd International Conference on Machine Learning (published)
proceedings.mlr.press
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
Rashid A. Mushkani
Shravan Nayak
Hugo Berard
Allison Cohen
Shin (Alexandre) Koseki
Hadrien Bertrand
2025-03-01
arXiv (published)
doi.org
arxiv.org
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
Rashid A. Mushkani
Shravan Nayak
Hugo Berard
Allison Cohen
Shin (Alexandre) Koseki
Hadrien Bertrand
We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment of text-to-image (T2I) models i… (see more)n inclusive urban planning. Developed through a two-year participatory process with 30 community organizations, LIVS encodes diverse spatial preferences across 634 initial concepts, consolidated into six core criteria: Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity, through 37,710 pairwise comparisons. Using Direct Preference Optimization (DPO) to fine-tune Stable Diffusion XL, we observed a measurable increase in alignment with community preferences, though a significant proportion of neutral ratings highlights the complexity of modeling intersectional needs. Additionally, as annotation volume increases, accuracy shifts further toward the DPO-tuned model, suggesting that larger-scale preference data enhances fine-tuning effectiveness. LIVS underscores the necessity of integrating context-specific, stakeholder-driven criteria into generative modeling and provides a resource for evaluating AI alignment methodologies across diverse socio-spatial contexts.
2025-02-27
ArXiv (preprint)
arxiv.org
arxiv.org