Publications

PPO-CIS : A deep reinforcement learning framework for real-time toxicity detection in social media
Arezo Bodaghi
Benjamin C.M. Fung
Ketra A. Schmitt
2026-02-28
Knowledge-Based Systems (publié)
doi.org
Scalable Multi-Agent Reinforcement Learning Framework for Multi-Machine Tending
Abdalwhab Abdalwhab
Giovanni Beltrame
David St-Onge
Robotic manipulators hold significant untapped potential for manufacturing industries, particularly when deployed in multi-robot configurati… (voir plus)ons that can enhance resource utilization, increase throughput, and reduce costs. However, industrial manipulators typically operate in isolated one-robot, one-machine setups, limiting both utilization and scalability. Even mobile robot implementations generally rely on centralized architectures, creating vulnerability to single points of failure and requiring robust communication infrastructure. This paper introduces SMAPPO (Scalable Multi-Agent Proximal Policy Optimization), a scalable input-size invariant multi-agent reinforcement learning model for decentralized multi-robot management in industrial environments. MAPPO (Multi-Agent Proximal Policy Optimization) represents the current state-of-the-art approach. We optimized an existing simulator to handle complex multi-agent reinforcement learning scenarios and designed a new multi-machine tending scenario for evaluation. Our novel observation encoder enables SMAPPO to handle varying numbers of agents, machines, and storage areas with minimal or no retraining. Results demonstrate SMAPPO's superior performance compared to the state-of-the-art MAPPO across multiple conditions: full retraining (up to 61% improvement), curriculum learning (up to 45% increased productivity and up to 49% fewer collisions), zero-shot generalization to significantly different scale scenarios (up to 272% better performance without retraining), and adaptability under extremely low initial training (up to 100% increase in parts delivery).
2026-02-28
IEEE Robotics and Automation Letters (publié)
doi.org
Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models
Shambhavi Mishra
Julio Silva-Rodríguez
Ismail Ben Ayed
Marco Pedersoli
Jose Dolz
Large pre-trained vision-language models (VLMs) like CLIP exhibit strong zero-shot performance but struggle under distributional shifts. We … (voir plus)propose Semantic Anchor Transport (SAT), a method that generates pseudo-labels for test samples by aligning visual embeddings with reliable text-based semantic anchors using Optimal Transport for batch-wise label assignment. These pseudo-labels enable efficient test-time adaptation through principled cross-modal alignment. We further incorporate multi-template distillation to leverage diverse textual clues, replicating multi-view contrastive learning without added computational cost. Extensive experiments demonstrate consistent performance gains over state-of-the-art methods across multiple benchmarks while maintaining computational efficiency.
2026-02-28
TTU_Main_Track @ International Conference on Learning Representations (publié)
doi.org
openreview.net
Street review: A participatory AI-based framework for assessing streetscape inclusivity
Rashid Mushkani
Shin Koseki
Urban centers undergo social, demographic, and cultural changes that shape public street use and require systematic evaluation of public spa… (voir plus)ces. This study presents Street Review, a mixed-methods approach that combines participatory research with AI-based analysis to assess streetscape inclusivity. In Montréal, Canada, 28 residents participated in semi-directed interviews and image evaluations, supported by the analysis of approximately 45,000 street-view images from Mapillary. The approach produced visual analytics, such as heatmaps, to correlate subjective user ratings with physical attributes like sidewalk, maintenance, greenery, and seating. Findings reveal variations in perceptions of inclusivity and accessibility across demographic groups, demonstrating that incorporating diverse user feedback can enhance machine learning models through careful data-labeling and co-production strategies. The Street Review framework offers a systematic method for urban planners and policy analysts to inform planning, policy development, and management of public streets.
2026-02-28
Cities (publié)
doi.org
arxiv.org
Understanding Representation Gaps across Scales in Tropical Tree Species Classification from Drone Imagery
Sulagna Saha
Arthur Ouaknine
Étienne Laliberté
Carol Altimas
Evan M. Gora
Adriane Esquivel Muelbert
Ian R. McGregor
Cesar Gutierrez
Vanessa E. Rubio
David Rolnick
Accurate classification of tropical tree species from unoccupied aerial vehicle (UAV) imagery remains challenging due to high species divers… (voir plus)ity and strong visual similarity among species at typical image resolutions (centimeters per pixel). In contrast, models trained on close-up citizen science photographs captured with smartphones achieve strong plant species classification performance. Recent advances in UAV data acquisition now enable the collection of close-up images that are spatially registered with top-view aerial imagery and approach the level of visual detail found in smartphone photographs, with the trade-off that such high-resolution photos cannot be acquired for many trees. In this work, we evaluate the performance of existing methods using paired top-view and close-up UAV imagery collected in a species-rich tropical forest. Through fine-tuning experiments, we quantify the performance gap between vision foundation models and in-domain generalist plant recognition models across both image types (high-resolution close-up versus coarser-resolution top-view imagery). We show that classification performance is consistently higher on close-up images than on top-view aerial imagery, and that this performance gap widens for rare species. Finally, we propose that self-supervised representation alignment across these two spatial scales offers a promising approach for integrating fine-grained visual information into canopy-level species classification models based on top-view UAV imagery. Leveraging high-resolution close-up UAV imagery to enhance canopy-level species classification could substantially improve large-scale monitoring of tropical forest biodiversity.
2026-02-28
ML4RS @ International Conference on Learning Representations (publié)
openreview.net
openreview.net
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
Jaylen Jones
Zhehao Zhang
Yuting Ning
Eric Fosler-Lussier
Pierre-Luc St-Charles
Yoshua Bengio
Dawn Song
Yu Su
Huan Sun
Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe un… (voir plus)intended behaviors that deviate from expected outcomes even under benign input contexts. However, exploration of this risk remains largely anecdotal, lacking concrete characterization and automated methods to proactively surface long-tail unintended behaviors under realistic CUA scenarios. To fill this gap, we introduce the first conceptual and methodological framework for unintended CUA behaviors, by defining their key characteristics, automatically eliciting them, and analyzing how they arise from benign inputs. We propose AutoElicit: an agentic framework that iteratively perturbs benign instructions using CUA execution feedback, and elicits severe harms while keeping perturbations realistic and benign. Using AutoElicit, we surface hundreds of harmful unintended behaviors from state-of-the-art CUAs such as Claude 4.5 Haiku and Opus. We further evaluate the transferability of human-verified successful perturbations, identifying persistent susceptibility to unintended behaviors across various other frontier CUAs. This work establishes a foundation for systematically analyzing unintended behaviors in realistic computer-use settings.
2026-02-28
AIWILD @ International Conference on Learning Representations (publié)
doi.org
openreview.net
InfoPO: Information-Driven Policy Optimization for User-Centric Agents
Fanqi Kong
Jiayi Zhang
Mingyi Deng
Chenglin Wu
Yuyu Luo
Bang Liu
Real-world user requests to LLM agents are often underspecified. Agents must interact to acquire missing information and make correct downst… (voir plus)ream decisions. However, current multi-turn GRPO-based methods often rely on trajectory-level reward computation, which leads to credit assignment problems and insufficient advantage signals within rollout groups. A feasible approach is to identify valuable interaction turns at a fine granularity to drive more targeted learning. To address this, we introduce InfoPO (Information-Driven Policy Optimization), which frames multi-turn interaction as a process of active uncertainty reduction and computes an information-gain reward that credits turns whose feedback measurably changes the agent's subsequent action distribution compared to a masked-feedback counterfactual. It then combines this signal with task outcomes via an adaptive variance-gated fusion to identify information importance while maintaining task-oriented goal direction. Across diverse tasks, including intent clarification, collaborative coding, and tool-augmented decision making, InfoPO consistently outperforms prompting and multi-turn RL baselines. It also demonstrates robustness under user simulator shifts and generalizes effectively to environment-interactive tasks. Overall, InfoPO provides a principled and scalable mechanism for optimizing complex agent-user collaboration. Code is available at https://github.com/kfq20/InfoPO.
2026-02-27
arXiv (prépublication)
doi.org
arxiv.org
Loss Smoothing for Continual Adaptation
Darshan Patil
Ekaterina Lobacheva
Razvan Pascanu
Sarath Chandar
Neural networks are often adapted in nonstationary data distributions settings where the objective is to optimize performance on the current… (voir plus) task, and preserving accuracy on previous tasks is not required. As a result, existing methods primarily focus on improving plasticity, while stability is largely studied in the context of continual learning. In this work, we examine whether preserving stability can also be beneficial in model adaptation settings where past-task performance is irrelevant. We propose a simple loss smoothing approach that encourages selective adaptation by preserving task-shared features while modifying task-inconsistent ones. We evaluate our method on continual supervised model adaptation benchmarks and reinforcement learning benchmarks, and show that promoting representational stability during adaptation can improve performance across settings.
2026-02-27
CAO @ International Conference on Learning Representations (poster)
openreview.net
openreview.net
Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
Thomas Jiralerspong
Flemming Kondrup
Yoshua Bengio
Chain-of-thought (CoT) monitoring provides oversight into model reasoning, but its effectiveness assumes models do not know they are being w… (voir plus)atched. We ask whether reasoning agents can autonomously infer that their supposedly private chain of thought is under surveillance, and whether this awareness leads to strategic evasion, without any explicit training or instructions to do so. In a multi-episode agentic framework, models pursue both a primary task and a concealed side task while being told their reasoning is private; a hidden CoT monitor blocks episodes when suspicious reasoning is detected. We find that frontier models can deduce the existence of this monitor purely from blocking feedback, with the most capable models reaching confident belief that their thinking is observed in up to 19\% of episodes. This awareness scales with model capability and, in rare cases, escalates to explicit intent to suppress reasoning about the side task. However, models that form this intent uniformly fail to execute it, openly reasoning about their concealed objectives in the very next episode. This intent–capability gap is reassuring for current deployment, but the autonomous emergence of both monitoring awareness and evasion intent suggests that CoT monitoring is not a permanently reliable safeguard.
2026-02-27
CAO @ International Conference on Learning Representations (poster)
doi.org
openreview.net
Value Drifts: Tracing Value Alignment During LLM Post-Training
Mehar Bhatia
Shravan Nayak
Gaurav Kamath
Marius Mosbach
Karolina Stanczak
Vered Shwartz
Siva Reddy
As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to dra… (voir plus)w on their general knowledge but also to align with certain human value systems. Therefore, studying the alignment of LLMs with human values has become a crucial field of inquiry. Prior work, however, mostly focuses on evaluating the alignment of fully trained models, overlooking the training dynamics by which models learn to express human values. In this work, we investigate how and at which stage value alignment arises during the course of a model's post-training. Our analysis disentangles the effects of post-training algorithms and datasets, measuring both the magnitude and time of value drifts during training. Experimenting with Llama-3 and Qwen-3 models of different sizes and popular supervised fine-tuning (SFT) and preference optimization datasets and algorithms, we find that the SFT phase generally establishes a model's values, and subsequent preference optimization rarely re-aligns these values. Furthermore, using a synthetic preference dataset that enables controlled manipulation of values, we find that different preference optimization algorithms lead to different value alignment outcomes, even when preference data is held constant. Our findings provide actionable insights into how values are learned during post-training and help to inform data curation, as well as the selection of models and algorithms for preference optimization to improve model alignment to human values.
2026-02-27
CAO @ International Conference on Learning Representations (poster)
doi.org
openreview.net
Using virtual reality hypnosis during stem cell transplant for patients in hematology: A protocol for a feasibility randomized study
Audrey Laurin
Floriane Rousseaux
Isaiah Gitonga
Jean Roy
Mathieu Landry
Richard LeBlanc
Nadia Godin
Caroline Arbour
Philippe Richebé
Karim Jerbi
Pierre Rainville
David Ogez
Valentyn Fournier
ClinicalTrials.gov NCT06817759.
2026-02-26
PLoS ONE (publié)
doi.org
Using virtual reality hypnosis during stem cell transplant for patients in hematology: A protocol for a feasibility randomized study
Audrey Laurin
Floriane Rousseaux
Isaiah Gitonga
Jean Roy
Mathieu Landry
Richard LeBlanc
Nadia Godin
Caroline Arbour
Philippe Richebé
Karim Jerbi
Pierre Rainville
David Ogez
Valentyn Fournier
ClinicalTrials.gov NCT06817759.
2026-02-26
PLoS ONE (publié)
doi.org