Publications

Deep Spectral Models for Robust Dental Shape Generation
Tibor Kubík
François Guibault
Michal Španěl
Hervé Lombaert
Accurate modeling of dental crown morphology is fundamental for diagnosis, orthodontic planning, and computer-aided restoration design. Howe… (see more)ver, datasets suitable for training such models are typically limited in size. We present ToothForge, a deep spectral generative framework that models dental crown geometries from compact, intrinsic representations. By operating in the spectral domain, ToothForge learns a latent manifold of 3D tooth shapes through synchronized spectral embeddings, ensuring consistent modeling across samples with varying connectivity. Spectral synchronization mitigates the instability of Laplace-Beltrami eigenbases and enables efficient learning in a low-dimensional space. The framework is thoroughly evaluated through robustness analysis, ablation studies, and benchmarking against PCA-based statistical shape models and point-based generative frameworks. Results show that synchronized spectral modeling achieves reconstruction and generative performance comparable to or exceeding spatial approaches, while maintaining compactness and geometric interpretability. Together, the compact synchronized coefficients and low-dimensional learning space make the framework particularly suitable for limited datasets, as often encountered in dental and medical domains, and applicable in real-world scenarios where guaranteeing consistent connectivity across shapes from various clinics is unrealistic.
2026-06-28
Machine Learning for Biomedical Imaging (published)
doi.org
arxiv.org
Influence of Autonomy and Interfaces on Human and Multi-Robot Teams: a Study on Planetary Exploration
Marcel Kaufmann
Giovanni Beltrame
Advances in robotic autonomy and interfaces have transformed human-robot teaming across domains, from disaster response to planetary science… (see more). However, critical gaps remain in understanding how autonomy and interface design affect human performance and cognitive demands, especially in large-scale, unstructured environments such as those on the Moon or Mars. We present a human-in-the-loop system comprising two (semi-)autonomous robots supervised by a single human operator. The system was evaluated in real caves at Lava Beds National Monument (California) and in a controlled within-subject study (n=38) at Polytechnique Montréal exploring both real and simulated caves. Participants interacted using either a traditional screen interface or a novel real-time, immersive VR interface, developed for this study and field-tested during NASA's BRAILLE campaign. We find that continuous physiological measurements (HRV) align with subjective NASA TLX scores in the context of human and multi-robot planetary exploration. Compared to benchmarks from prior studies, the screen interface resulted in low workload, while VR was rated in the low-to-moderate range. The low-autonomy VR-waypoint condition resulted in the least effective performance, with the fewest automated science detections, whereas both the full-autonomy VR and screen-based conditions yielded comparably higher exploration and detection performance. Both interfaces supported high situational awareness, with accuracy measures near 90%. Autonomy did not significantly affect situational awareness, but full-autonomy did reduce operator input effort. Trust levels did not significantly vary across conditions, motivating more detailed assessment methods in future studies. The results inform how to align interface design and autonomy to support effective multi-robot supervision in future missions.
2026-06-28
ACM Transactions on Human-Robot Interaction (published)
doi.org
RAG-Safe: A Recall-First Safety Framework Comparing Open-Source and Commercial LLM Moderation Pipelines
Alejandro Salinas-Medina
Xue Liu
False negatives—missed detections of harmful content—remain the dominant risk in safety-critical moderation pipelines. We introduce RAG-… (see more)Safe, a recall-first framework that integrates distribution-preserving contrastive augmentation, committee-diverse retrieval, and a recall-oriented decision policy into a unified moderation architecture. The framework is evaluated using a compact, fully auditable testbed designed to enforce strict leakage control: original samples alone determine the train–test split, and all paraphrases inherit their parent assignment. Within this controlled setting, conventional retrieval-augmented pipelines—both commercial (API embeddings + hosted LLM) and open-source (FAISS + local LLaMA-3)—consistently under-detect unsafe content (FLAGGED recall 0.44). Applying RAG-Safe raises FLAGGED recall to approximately 0.56 across both stacks while preserving overall accuracy ( 0.66) and macro-F1 ( 0.65). A non-RAG classifier baseline provided in our public repository shows similar recallfirst behaviour, reinforcing that these gains are not architecture-specific. Rather than comparing individual model components, we interpret the results as pipeline-level evidence that boundary-focused augmentation, retrieval diversity, and calibrated thresholds jointly shift LLM moderation into a safer operating regime. We conclude by discussing limitations—particularly domain transferability and adversarial robustness—and outline directions for scaling RAG-Safe to broader moderation contexts. Keywords: Content moderation, Recall-first classification, Distribution-preserving data augmentation, Committee-based retrieval, Retrieval-augmented large language models, Safety-critical AI
2026-06-28
Canadian Conference on Artificial Intelligence (published)
proceedings.mlr.press
proceedings.mlr.press
Special Dedication to Music and Songs Proliferation - [A short Note]
Nonvikan Karl-Augustt Alahassa
Bidossessi R.U. Alahassa
Christiane Rousseau
J. Tossa
Bakary Manga
Suljo Linic
Samuel Bassetto
Dimitrios Koukoulopoulos
Maciej Augustyniak
Bruno Rémillard
Nathalie Lacelle
Leonard Wantchekon
Emmanuel Stip
Jérôme Théau
Damien Échevin
Daniel F. Nadeau
Victor M. Panaretos
Foutse Khomh
Marlène Frigon
David Haziza … (see 2 more)
Julie Carrier
Mylène Bédard
This is a Special Dedication to Music and Songs Proliferation - [A short Note].
2026-06-28
Zenodo (preprint)
doi.org
Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation
MohammadReza Davari
Utkarsh Garg
Weixin Cai
Eugene Belilovsky
An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critic… (see more)al for controlling model behavior. Recent Automatic Prompt Optimization (APO) methods iteratively refine prompts using model-generated critiques (often called as textual gradients), but they predominantly optimize from failures and underutilize information contained in correct predictions, leading to instability and semantic drift. We propose TRAS (Textual Regularization with Aggregated Signals), a feedback-centric framework that is plug-and-play with existing APO search backbones. It retains the standard textual gradient signal from prior work for error correction, and introduces a complementary textual regularizer derived from successful predictions to preserve beneficial prompt components. Because both signals are stochastic and can be noisy, we further introduce Monte Carlo Signal Aggregation (MCSA), which samples multiple gradients or regularizers and aggregates them into a single actionable directive, emphasizing consistent, actionable advice while filtering out outliers. Motivated by rapid model churn, we also formalize Automatic Prompt Migration (APM), the practical problem of adapting an expert prompt across model versions or API providers without losing critical instructions. Across standard APO and APM scenarios, our approach consistently outperforms strong baselines, yielding higher accuracy, faster convergence, and lower query cost, while substantially reducing the degradation observed under naive prompt migration.
2026-06-28
Canadian Conference on Artificial Intelligence (published)
doi.org
proceedings.mlr.press
ToxiSight: Leveraging Moderator Expertise Through Behavioral Measurement in Gaming Toxicity Annotation
Zachary Yang
Vicki Chen
Domenico Tullo
Reihaneh Rabbany
Content moderation systems commonly treat human annotators as interchangeable label sources, resolving disagreements through majority voting… (see more) or expert arbitration. We present ToxiSight, an annotation platform that reframes this assumption: rather than extracting consensus, the system supports moderator reasoning by treating hesitation, revision, and disagreement as signals revealing where content is genuinely ambiguous and where taxonomic guidelines fail. ToxiSight integrates gaming-specific contextual widgets with behavioral telemetry, capturing the cognitive processes underlying toxicity validation decisions. Through deployment with 10 professional moderators across 60,000 lines of gaming chat, we demonstrate that behavioral patterns expose systematic category failures invisible to traditional inter-annotator metrics. The Controversial category shows 72% revision rates with fast processing times, indicating immediate recognition of definitional breakdown, while Threats (Life-Threatening) exhibits 75% revisions with slow processing, signaling genuine interpretive complexity. Completion rates improved from 60% to 95%, and moderators reported reduced decision stress when permitted to express uncertainty. This case study demonstrates that trustworthy toxicity detection requires annotation systems designed around the irreducible complexity of human judgment, not against it.
2026-06-28
Canadian Conference on Artificial Intelligence (published)
proceedings.mlr.press
proceedings.mlr.press
Safety from Honesty in a Disinterested AI Predictor
Yoshua Bengio
Oliver Richardson
Tomáš Gavenčiak
Michael Cohen
Rory Svarc
Damiano Fornasiere
Gaël Gendron
David Hyland
Aton Kamanda
Adam Oberman
Francis Rhys Ward
Anna Gavenčiak
Jacob Livingston Slosser
Vincent Mai
Iulian Serban
Joumana Ghosn
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed… (see more) behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of"epistemically contextualized"natural-language statements. We argue that such a Predictor can honestly predict agents, actions, and their consequences without itself being an agent that selects outputs to achieve goals. This rests on data representation and on the training procedure. Epistemic contextualization of text distinguishes latent factual claims from communication acts, so expressions of goals are treated as evidence to be explained rather than drives the model adopts. With a posterior-seeking training objective, this is intended to drive the Predictor toward calibrated, cautious predictions. Training proceeds so downstream effects of deploying a prediction never serve as a reward signal; any agency the system needs is supplied by explicit scaffolding constrained by guardrails. We prove that, under assumptions on the training dynamics and on the argued sparsity of dangerous Predictors, the probability that training produces a Predictor whose guarded deployment carries residual harm above a specified threshold is small: a dangerous Predictor would have to underestimate harm in a coordinated way across many queries while such coordinated patterns are rare under the initialization distribution and receive no direct training signal. Safety and accuracy are jointly supported in this framework, since the constraints that secure accuracy are the same ones that make coordinated deception costly. These guarantees against misalignment and agency arising from within the Predictor itself do not preclude the use of the Predictor as part of an agentic system.
2026-06-27
arXiv (preprint)
doi.org
arxiv.org
Formal Epistemic Structure Leaves Geometric Traces in LLMs: Evidence from S5 Multi-Agent Logic and RoBERTa
David John Lemay
Emil Sayilov
Irina Rish
We ask whether the formal structure of S5 multi-agent epistemic logic leaves recoverable geometric traces in a fine-tuned language model. Va… (see more)n Benthem's product topology for S5 predicts that the state space of
2026-06-26
LogiSymb @ International Joint Conference on Artificial Intelligence (poster)
openreview.net
openreview.net
Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation
Florian Carichon
Romain Rampa
Golnoosh Farnadi
2026-06-24
ACM Conference on Fairness, Accountability, and Transparency (published)
doi.org
arxiv.org
Don't Trust the Process: When Verifiability Undermines AI Accountability
Tamara Paris
AJung Moon
Jin Guo
How do we know if Artificial Intelligence (AI) systems are as performant and responsibly designed as the AI companies claim them to be? In a… (see more) race-driven innovation climate where responsive development requires time and resources, AI developers and providers may be tempted to misrepresent system performance or overstate their commitment to responsible AI principles. Such circumvention is further enabled by limited access to system components and information by external stakeholders, a restriction commonly justified on the grounds of trade secret protection, privacy and security considerations, among others. In response, a growing community of scholars has been developing cryptographic and statistical solutions that aim to enable robust verification of specific claims under constrained access. However, the construction of these solutions rely on a set of shared, yet unexamined, assumptions required to abstract complex real-world governance challenges into computational representations. In this article, we examine the validity of these assumptions. After detailing the conceptual foundation and analytical lens we used to interrogate these abstraction processes, we show that existing technical approaches to developing verifiable AI commit systematic fallacies that compromise the validity of these approaches. While the existing technical verification processes aim to solve critical AI governance problems, we argue that these fallacies create loopholes that can be exploited by dishonest developers and providers, and therefore lead to misplaced trust in these processes. Finally, we discuss how the field of verifiability could be reoriented towards a more nuanced and interdisciplinary approach to develop rigorous verification processes, both technical and non-technical, that support effective AI governance.
2026-06-24
ACM Conference on Fairness, Accountability, and Transparency (published)
doi.org
Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data
Maryam Babaei
Yingke Wang
Hadrien Lautraite
Héber H. Arcolezi
Ulrich Aivodji
Sébastien Gambs
Counterfactuals are typically used in high-stakes decision areas to explain a machine learning model by showing how changes to the user prof… (see more)iles result in the desired outcome. However, explaining the model's decisions through counterfactuals can also be exploited by an adversary to conduct privacy attacks against the model or its training data. Drawing on the analogy that counterfactuals provide realistic substitutes for real training data, similar to synthetic data, we demonstrate in this paper how it is possible to successfully perform privacy attacks on counterfactuals by drawing on the attacks developed against synthetic data. More precisely, we investigate the effectiveness of the membership inference attacks designed for synthetic data on various types of counterfactuals. Additionally, while existing membership inference attacks against counterfactuals usually require to be able to query the model, we show how it is possible to perform successful membership inference attacks using only a set of counterfactuals, with no access to the model from which they are generated. Our results demonstrate that model developers should be more cautious when releasing counterfactuals to various users, as it can lead to a privacy breach.
2026-06-24
ACM Conference on Fairness, Accountability, and Transparency (published)
doi.org
arxiv.org
Societal Frameworks Can Improve LLM Alignment
Karolina Stanczak
Nicholas Meade
Mehar Bhatia
Hattie Zhou
Konstantin Böttinger
Jeremy Barnes
Jason Stanley
Nicolas Papernot
Nicolas Chapados
Denis Therien
Timothy Lillicrap
Ana Marasovic
Sylvie Delacroix
Gillian K. Hadfield
Siva Reddy
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values… (see more) — a process coined alignment. However, aligning LLMs remains challenging due to the inherent disconnect between the complexity of human values and the narrow nature of the technological approaches designed to address them. Current alignment methods often lead to misspecified objectives, reflecting the broader issue of incomplete contracts, the impracticality of specifying a contract between a model developer and the model that accounts for every scenario in LLM alignment. In this paper, we argue that improving LLM alignment requires incorporating insights from societal alignment frameworks, including social, economic, and contractual alignment, and discuss potential solutions drawn from these domains. Given the role of uncertainty within societal alignment frameworks, we then investigate how it manifests in LLM alignment. It is this pervasive uncertainty that necessitates our alternative view on LLM alignment, framing the under-specified nature of its objectives as an opportunity rather than perfect their specification. Beyond technical improvements in LLM alignment, we discuss the need for participatory alignment interface designs.
2026-06-24
ACM Conference on Fairness, Accountability, and Transparency (published)
doi.org