Publications

PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification
Charlie Gauthier
Sacha Morin
Liam Paull
Simulation environments are useful for both robot policy learning and planning verification and validation. Traditionally, the process of cr… (voir plus)eating a simulation was onerous. Creating a bespoke simulation environment for each individual environment that a robot would operate in was simply infeasible. In this work, we introduce PerceptTwin, a fully automatic pipeline that constructs interactive simulations directly from semantic scene representations produced by a robot's perception stack. PerceptTwin combines open-vocabulary object maps with 3D asset generation, affordance prediction, and commonsense condition checking. These interactive simulations can be used to validate and refine plans before they are executed on the robot hardware. Borrowing from the AI alignment literature, we also introduce an LLM judge that verifies plan correctness and alignment with human preferences. Experiments show that PerceptTwin feedback allows LLM planners to refine plans, enhance safety, and resist harmful black-box prompting attacks. In our suite of tasks, PerceptTwin improves plan success by an average of approximately 39% for GPT5, GPT5Mini, and GPT5Nano planners. Additionally, PerceptTwin also improves human plan verification by up to 18% on average for plans that fail due to unfilled skill preconditions. Our results demonstrate the potential of open-vocabulary scene simulation from robot perception as a foundation for safer, more reliable robot planning.
2026-06-01
arXiv (prépublication)
doi.org
arxiv.org
Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning
Aditya Sharma
Christopher Pal
Amal Zouaq
Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a fin… (voir plus)al answer. Yet the internal structure of representation space when reasoning remains poorly understood: how do a model's hidden representations differ during thinking versus the embeddings of the input prompt, and can this structure be exploited to elicit stronger reasoning at inference time? We show that both input embeddings and thinking embeddings (mean-pooled last-layer hidden states over the prompt and reasoning trace, respectively) exhibit extremely high conicity, with all vectors clustering tightly around a single mean direction. Crucially, these mean input and thinking directions are non-collinear, with thinking embeddings occupying a geometrically distinct region of embedding space across many different models and benchmark tasks. This observation motivates casting the input-to-thinking transition as a rotation problem admitting a closed-form solution via orthogonal Procrustes analysis. We propose Rotate2Think, a training-free method that estimates this rotation from a small set of correctly solved examples and injects the resulting synthetic thinking vector between thinking delimiters at inference time, providing a geometric primer at the onset of the reasoning trace. Evaluated across multiple benchmarks and model families, Rotate2Think improves accuracy in 30 of 32 model-benchmark configurations across mathematics, science, and code tasks, and generalizes zero-shot to multimodal reasoning on MATH-Vision.
2026-06-01
arXiv (prépublication)
doi.org
arxiv.org
Self-assembled chamber-like cardiac organoids for modeling cardiac chamber formation and cardiotoxicity assessment
Xinle Zou
Fanwen Wang
Huilin Zheng
Xianzhuang Liu
Tianci Kong
Rui Jiang
Yingying Guo
Yu Liang
Hanqing Zhao
Bo Wang
Duanqing Pei
2026-06-01
Nature Communications (publié)
doi.org
Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
Anthony GX-Chen
Ankit Anand
Gheorghe Comanici
Zaheer Abbas
Eser Aygün
David Smalling
Shibl Mourad
Doina Precup
Andre Barreto
Mark Rowland
Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern… (voir plus) applications such as language model fine-tuning or scientific discovery demand diversity. Existing remedies such as entropy regularization or diversity bonuses often require fragile trade-offs that sacrifice performance for stochasticity or rely on heuristic metrics that can misalign policy rankings. We argue that diversity is more naturally understood as the rational response to uncertainty in the reward. When the reward function is not perfectly known--as is the case with ambiguous preferences or imperfect reward models--committing to a single action can be sub-optimal. Building on this, we propose a fundamental reformulation of the RL objective by replacing the scalar reward with a distribution over reward functions, and applying a non-linear objective over sets of actions. The result is a framework in which calibrated behavioural diversity emerges naturally, remains controllable through the reward function distribution, and is obtained without sacrificing expected reward. Focusing on the contextual bandit setting, we derive a principled gradient estimator for this objective and prove that our formulation naturally generalizes both vanilla policy gradient and more recently developed action-set approaches. Our empirical results demonstrate that this framework offers a robust and theoretically grounded alternative for complex RL tasks where the traditional formulation of the problem fails to induce the desired breadth of agent behaviour.
2026-06-01
arXiv (prépublication)
doi.org
arxiv.org
Accelerated green material and solvent discovery with chemistry- and physics-guided generative AI
Eslam G. Al-Sakkari
Ahmed Ragab
Marzouk Benali
Olumoye Ajao
Daria C. Boffito
Hanane Dagdougui
2026-05-31
Artificial Intelligence Chemistry (publié)
doi.org
Antibiotic dispensing practices and determinants among informal healthcare providers in low- and middle-income countries: a mixed-methods scoping review
M V Pai
Poshan Thapa
Giorgia Sulis
Charity Oga-Omenka
Buna Bhandari
Sumanth Gandra
Genevieve Gore
Surbhi Sheokand
Prachi Shukla
Meera Tandan
Diwash Timalsina
Shweta Bohora
Swostika Thapaliya
Anupama Bhusal
Chandrashekhar Joshi
Md Asadullah
Mili Dutta
Samira Abbasgholizadeh Rahimi
Introduction Antimicrobial stewardship efforts in low- and middle-income countries (LMICs) largely focus on qualified practitioners, yet inf… (voir plus)ormal healthcare providers (IPs) deliver much of the primary care. Although these providers frequently dispense antibiotics, their practices remain poorly documented and are not captured in existing surveillance systems.Methods Using the Joanna Briggs Institute methodology, this scoping review synthesised evidence on antibiotic dispensing and its determinants among IPs in LMICs. Nine databases (MEDLINE, EMBASE, SCOPUS, Global Health, CINAHL, Web of Science, LILACS, African Journals Online via Africa-Wide Information and Index Medicus for the South-East Asia Region) were searched, yielding 12 095 records, of which 37 studies met the inclusion criteria.Results Across 31 studies reporting dispensing practices, antibiotic use by IPs varied widely: 18%–74% in studies using standardised methods, 5%–96% in provider-reported studies and 2%–86% in consumer-reported studies. Eight qualitative studies identified key behavioural and contextual determinants shaping dispensing, including limited knowledge, experience-based learning, patient expectations, peer and pharmaceutical influence, perceived consequences of withholding antibiotics and economic incentives.Conclusion Antibiotic dispensing by IPs is widespread and represents a large but unmeasured component of antibiotic use in LMICs. These findings highlight a critical gap in antimicrobial resistance surveillance and highlight the need for stewardship strategies that effectively engage this provider group.
2026-05-31
BMJ Global Health (inconnu)
doi.org
Automated diagnosis of usual interstitial pneumonia on chest CT via the mean curvature of isophotes
Peter Savadjiev
Morteza Rezanejad
Sahir Bhatnagar
David Camirand
Claude Kauffmann
Kaleem Siddiqi
Ronald J. Dandurand
Patrick Bourgouin
Carl Chartrand-Lefebvre
Alexandre Semionov
To test whether the mean curvature of isophotes (MCI), a geometric image transformation, can be used to improve automatic detection on chest… (voir plus) CT of Usual Interstitial Pneumonia (UIP), a determining radiological pattern in the diagnosis of Interstitial Lung Diseases (ILD). This retrospective study included chest CT scans from 234 patients (123 female,111 male; mean age: 61.6 years; age range: 18-90 years) obtained at two independent institutions between 2007 and 2024. Three different classification models were trained on the original CT images and separately on MCI-transformed CT images: (1) a previously published deep learning model for classifying fibrotic lung disease on chest CT, (2) a classification pipeline based on the EfficientNet-V2 convolutional neural network architecture, and (3) a non-deep-learning model based on the functional principal component analysis (FPCA) of density functions of voxel intensity. All models were trained on data from the first institution and evaluated on data from the second institution with the recall-macro, precision-macro and F1-macro scores. Performance difference between classifier pairs was tested with the Stuart-Maxwell marginal homogeneity test. For a fixed model architecture and training algorithm, MCI-transformed images yield comparable or better classification performance than the original CT images. The best performance improvement achieved with MCI compared to CT was: recall-macro 0.83 vs 0.57, precision-macro 0.81 vs 0.50, F1-macro 0.80 vs 0.49, p=4.2e-5. MCI may be a valuable addition to existing AI systems for screening for UIP on chest CT. Machine learning methods for identifying usual interstitial pneumonia on chest CT perform better when the input CT images are transformed via the mean curvature of isophotes (MCI), a geometric transformation method known from classical computer vision. Three machine learning models were trained on a dataset of 158 patients from one institution and tested on another dataset of 76 patients from an independent institution to discriminate for usual interstitial pneumonia (UIP) on chest CT in a 3-group classification task. When keeping the network architecture and parameters fixed, changing the input image domain from the original CT to MCI-transformed images improved classification performance (Stuart-Maxwell test, p < 5e-3) MCI may be a valuable addition to existing machine learning systems for screening for UIP on chest CT, whether based on deep learning or on simpler shallow classifiers.
2026-05-31
European Journal of Radiology Open (publié)
doi.org
Automated robust segmentation of the spinal canal on MRI
Abel Salmona
Sandrine Bédard
Jan Valosek
Kalum Ost
Maxime Bouthillier
Gergely David
Maryam Seif
Armin Curt
Nikolai Pfender
Markus Hupp
Patrick Freund
Tomáš Horák
Petr Kudlička
Josef Bednařík
Fauziyya Muhammad
Zachary A. Smith
Julien Cohen-Adad
2026-05-31
European Journal of Radiology Artificial Intelligence (publié)
doi.org
Cough acoustic analysis using artificial intelligence for COVID-19 detection: A comparative study of patient cohorts from Lima, Peru and Montreal, Canada
A. Zimmer
Vijay Ravi
Patricia Espinoza-Lopez
George P. Kafentzis
Mirco Ravanelli
Samira Abbasgholizadeh Rahimi
Madhukar Pai
César Ugarte-Gil
Serge Lapierre
2026-05-31
Annals of Epidemiology (publié)
doi.org
Danilo Bzdok
Danilo Bzdok
2026-05-31
Neuron (publié)
doi.org
Key Issues and Future Directions in the Construction and Control of Geocentric Orbit Constellations for Gravitational Wave Detection
Yue LIU
Borui YAO
Hanqing Zhao
Meng LU
Yanchao HE
Ming LI
Lihua ZHANG
Jianying WANG
Mingying HUO
2026-05-31
China basic science (publié)
doi.org
Lacuna: A Research Map for Machine Learning Problem Formulation
Martin Weiss
Alejandro Hernandez
Yacine Mkhinini
Miles Q. Li
Christopher Pal
Hugo Larochelle
Nasim Rahaman
Research problem formulation is the cognitive task of turning a vague scientific idea into a testable hypothesis. \textbf{Lacuna} is a resea… (voir plus)rch map that supports this process for machine learning, using LLMs to turn papers and scholarly metadata into markdown summaries, concept elements, research directions, author and venue pages, and research proposals. Each item keeps links to the primary source records and papers that support it. We release the map with web, markdown, and MCP interfaces, plus scripts for reproducing the agent run. On a theorem-proving seed idea, the agent reaches a research proposal in 85.5 seconds and 7 tool calls, vs.\ 289.2 seconds and 27 tool calls for a sequential-PDF baseline. On ScholarQA-CS-ML, an ML/AI subset of the OpenScholar benchmark, Lacuna-GPT-4o scores 0.694 under the ScholarQABench rubric judge, compared with 0.672 for the OpenScholar-GPT-4o baseline on the same questions.
2026-05-31
AI4Research @ International Conference on Machine Learning (poster)
openreview.net
openreview.net