Publications

Developing a vision for public health surveillance in Canada: An engagement and expert consensus process
Elissa Giang
Louis Wong
Maureen Anderson
Barrett Halliday
Jessica Hopkins
Chia-Yu Lin
Nnamdi Ndubuka
Aateka Rajab
Chi-Hang Jonathan Sinn
Kate Smolina
Jean-Paul R. Soucy
Tammy Stuart Chester
Jason Wong
Sarry Zheng
David L. Buckeridge
OBJECTIVE: Public health surveillance (PHS) supports the detection of health threats, monitoring of population health, and coordinated publi… (see more)c health action. While its core functions remain unchanged, Canada's last national vision for PHS was articulated in 2016, and the public health landscape has since evolved considerably. These changes have been shaped by lessons from the COVID-19 pandemic, advances in data systems and technologies, evolving data governance expectations, and increasing demand for timely, integrated public health information. We therefore sought to develop a renewed vision for PHS in Canada through broad engagement, qualitative synthesis, and expert consensus. METHODS: This work used a two-phase, multi-method approach. First, national engagement with public health interest holders was conducted between September 2023 and March 2024 through regional consultations, an expert meeting, and an online survey. Qualitative data were analyzed using reflexive thematic analysis to generate draft vision components and statements. Second, a three-round modified Delphi process with Canadian PHS experts was used to iteratively review, refine, and assess agreement on the draft statements. RESULTS: Engagement activities captured input from 1740 participants across Canada, generating 38 draft statements organized within a conceptual framework. Through the Delphi process, experts refined statements based on quantitative agreement measures and qualitative feedback, achieving consensus on a final set of 30 statements. CONCLUSIONS: The resulting vision provides a shared reference point for public health professionals and partners to align efforts to strengthen and modernize PHS systems in Canada.
2026-09-17
Canadian Journal of Public Health (published)
doi.org
Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bank
Yang Zhang
Zhixiang Chi
Xudong Yan
Yang Wang
Songhe Feng
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions with learned primitives (attribute and object… (see more)) knowledge from seen compositions. While previous approaches gain their notable performance through the powerful cross-modal alignment of CLIP, they often overlook the modality gap, an inherent constraint stemming from information-imbalanced training data. In this work, we propose SAM, a novel
2026-09-16
IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)
openreview.net
openreview.net
Continual Enterprise World Model Discovery in Dynamic Systems
Shambhavi Mishra
David Vázquez
Perouz Taslakian
Marco Pedersoli
Jose Dolz
Issam H. Laradji
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business r… (see more)ules that are not built into the platform but written by each organization and revised over time. An agent working in such a system cannot predict the result of its own actions without knowing these rules. We study continual enterprise world model discovery, where an agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes. From those observations it builds a world model, which it revises as the rules change. To evaluate this, we introduce EnterpriseWorldShift, built on a live ServiceNow environment with nine tables, 25 hidden rules and 600 evaluation actions. It presents four versions of the same enterprise world, with the tables and records held fixed while a rule is modified, then added, then removed, so that discovery, revision, extension and retirement are each tested in turn. Our Continual Discovery Agent (CDA) builds such a model and carries it from one world to the next. It predicts the effects of the hidden rules more accurately than looking them up for each question, the approach taken by prior work, by up to 8.98 IoU points, and it answers from its own model without querying the running system.
2026-09-16
arXiv (preprint)
doi.org
arxiv.org
Life is inherently computational, and consciousness probably is too – A commentary on: Conscious artificial intelligence and biological naturalism
Blake A. Richards
Blaise Agüera y Arcas
We agree with Seth that consciousness is grounded in processes related to life, namely prediction, homeostasis, and autopoiesis. However, we… (see more) believe he is wrong to frame these processes as non-computational. In fact, prediction, homeostasis, and autopoiesis are inherently computational, as shown by von Neumann's Universal Constructor theory of general computation. Given this, we believe that AI consciousness is likely.
2026-09-16
Behavioral and Brain Sciences (published)
doi.org
Protocol for telomere-to-telomere assembly of Borrelia genomes using a hybrid method
Atia Amin
Ana Victoria Ibarra‐Meneses
Mathieu Blanchette
Christopher Fernandez‐Prada
David Langlais
.
2026-09-16
STAR Protocols (published)
doi.org
RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation
Ganlin Feng
Yuxi Long
Hafsa Ali
Erin Lou
Fahad Butt
Qian Liu
Yang Wang
Pingzhao Hu
Rare diseases often manifest with distinctive facial phenotypes in children, offering valuable diagnostic cues for clinicians and AI-assiste… (see more)d screening systems. However, progress in this field is severely limited by the scarcity of curated, ethically sourced facial data and the high similarity among phenotypes across different conditions. To address these challenges, we introduce RDFace, a curated benchmark dataset comprising 456 pediatric facial images spanning 103 rare genetic conditions (average 4.4 samples per condition). Each ethically verified image is paired with standardized metadata. RDFace enables the development and evaluation of data-efficient AI models for rare disease diagnosis under real-world low-data constraints. We benchmark multiple pretrained vision backbones using cross-validation and explore synthetic augmentation with DreamBooth and FastGAN. Generated images are filtered via facial landmark similarity to maintain phenotype fidelity and merged with real data, improving diagnostic accuracy by up to 13.7% in ultra-low-data regimes. To assess semantic validity, phenotype descriptions generated by a vision–language model from real and synthetic images achieve a report similarity score of 0.84. RDFace establishes a transparent, benchmark-ready dataset for equitable rare disease AI research and presents a scalable framework for evaluating both diagnostic performance and the integrity of synthetic medical imagery.
2026-09-16
IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)
doi.org
openreview.net
TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery
Yanan Wu
Yuhan Yan
Tailai Chen
Zhixiang Chi
ZiZhang Wu
Yi Jin
Yang Wang
Zhenbo Li
On-the-fly category discovery (OCD) aims to recognize known categories while simultaneously discovering novel ones from an unlabeled online … (see more)stream, using a model trained only on labeled data. Existing approaches freeze the feature extractor trained offline and employ a hash-based framework that quantizes features into binary codes as class prototypes. However, discovering novel categories with a fixed knowledge base is counterintuitive, as the learning potential of incoming data is entirely neglected. In addition, feature quantization introduces information loss, diminishes representational expressiveness, and amplifies intra-class variance. It often results in category explosion, where a single class is fragmented into multiple pseudo-classes. To overcome these limitations, we propose a test-time adaptation framework that enables learning through discovery. It incorporates two complementary strategies: a semantic-aware prototype update and a stable test-time encoder update. The former dynamically refines class prototypes to enhance classification, whereas the latter integrates new information directly into the parameter space. Together, these components allow the model to continuously expand its knowledge base with newly encountered samples. Furthermore, we introduce a margin-aware logit calibration in the offline stage to enlarge inter-class margins and improve intra-class compactness, thereby reserving embedding space for future class discovery. Experiments on standard OCD benchmarks demonstrate that our method substantially outperforms existing hash-based state-of-the-art approaches, yielding notable improvements in novel-class accuracy and effectively mitigating category explosion. The code is publicly available at https://github.com/ynanwu/TALON.
2026-09-16
IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)
doi.org
openreview.net
Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs
Houston H. Zhang
Tao Zhang
Baoze Lin
Yuanqi Xue
Yincheng Zhu
Huan Liu
Li Gu
Linfeng Ye
Ziqiang Wang
Xinxin Zuo
Yang Wang
Yuanhao Yu
Zhixiang Chi
User interface to code (UI2Code) aims to generate executable code that can faithfully reconstruct a given input UI. Prior work focuses large… (see more)ly on web pages and mobile screens, leaving app widgets underexplored. Unlike web or mobile UIs with rich hierarchical context, widgets are compact, context-free micro-interfaces that summarize key information through dense layouts and iconography under strict spatial constraints. Moreover, while (image, code) pairs are widely available for web or mobile UIs, widget designs are proprietary and lack accessible markup. We formalize this setting as the Widget-to-Code (Widget2Code) and introduce an image-only widget benchmark with fine-grained, multi-dimensional evaluation metrics. Benchmarking shows that although generalized multimodal large language models (MLLMs) outperform specialized UI2Code methods, they still produce unreliable and visually inconsistent code. To address these limitations, we develop a baseline that jointly advances perceptual understanding and structured code generation. At the perceptual level, we follow widget design principles to assemble atomic components into complete layouts, equipped with icon retrieval and UI composition modules. At the system level, we design an end-to-end infrastructure, WidgetFactory, which includes a framework-agnostic widget-tailored domain-specific language (WidgetDSL) and a compiler that translates it into multiple front-end implementations (e.g., React, HTML). An adaptive rendering module further refines spatial dimensions to satisfy compactness constraints. Together, these contributions substantially enhance visual fidelity, establishing a strong baseline and unified infrastructure for future Widget2Code research.
2026-09-16
IEEE/CVF Conference on Computer Vision and Pattern Recognition (published)
doi.org
openreview.net
Conformal Inverse Optimization for Adherence-Aware Prescriptive Analytics
Timothy C. Y. Chan
Erick Delage
Bo Lin
When “Optimal” Advice Gets Ignored Algorithms can recommend decisions that look optimal on paper but conflict with how people assess the… (see more) situation, making those recommendations less likely to be followed. In “Conformal Inverse Optimization for Adherence-Aware Prescriptive Analytics,” Chan, Delage, and Lin address this challenge by using past decisions to learn how people evaluate different options. Because those decisions may reflect diverse preferences, noisy observations, or imperfect models, the authors do not rely on a single estimated preference profile. Instead, they construct an uncertainty set around the inferred parameters and use robust optimization to generate recommendations that perform well both objectively and from the decision maker’s perspective. Their method comes with statistical and performance guarantees and outperforms standard inverse optimization in numerical experiments. In a simulated Toronto food-delivery study, it substantially improves estimated courier adherence, maintaining comparable delivery times, showing how better-aligned recommendations can benefit both users and organizations.
2026-09-15
Operations Research (published)
doi.org
Assistive algorithms influence neural representations in motor brain-computer interfaces
Pavithra Rajeswaran
Alexandre Payeur
Guillaume Lajoie
Amy L. Orsborn
Task errors are used to learn and refine motor skills. We investigated how task assistance influences learned neural representations using B… (see more)rain-Computer Interfaces (BCIs), which map neural activity into movement via a decoder. We analyzed motor cortex activity as monkeys practiced BCI with a decoder that adapted to improve or maintain performance over days. Over time, task-relevant information became concentrated in fewer neurons, unlike with fixed decoders. At the population level, task information also became largely confined to a few neural modes that accounted for a small fraction of the population variance. A neural network model suggests the adaptive decoders directly contribute to forming these more compact neural representations. Our findings suggest that assistive decoders manipulate error information used for long-term learning computations like credit assignment, which may explain the altered neural representations and inform real-world BCI design. Assistive algorithms are widely used in brain-computer interfaces (BCIs), but their effects on neural representations remain unclear. Here, the authors show that adaptive BCIs lead the brain to learn compact representations, suggesting assistive algorithms shape long-term credit assignment.
2026-09-14
Nature Communications (published)
doi.org
SMC1A is required for fate determinations of human spermatogonial stem cells and male fertility by interacting with YBX1 and stabilizing HMGA2 mRNA via an m5C modification
Wei Liu
Li Du
Yanna Zhu
Yuxuan Xu
Dai Zhou
Bang Liu
Jun Gao
Yinghong Cui
Wei Chen
Chunyun Li
Yongzhe Chen
Fen Jiang
Zuping He
Spermatogonial stem cells (SSCs) are required for initiating and maintaining normal spermatogenesis, and notably, they have significant appl… (see more)ications in both reproductive and regenerative medicine owing to their great plasticity with de-differentiation and trans-differentiation potentials. Nevertheless, molecular mechanisms regulating human SSC fate determinations and male fertility remain elusive. Here we report for the first time that structural maintenance of chromosomes 1A (SMC1A) interacts with RNA-binding protein YBX1 to control fate decisions of human SSCs and an association exists between SMC1A dysfunction with male infertility. SMC1A/YBX1 complex stabilizes high mobility group AT-hook 2 (HMGA2) mRNA in an m5C modification-dependent manner to activate the G1/S phase transition, which ultimately mediates human SSC self-renewal and apoptosis. Transplantation of SSCs into the seminiferous tubules of recipient mice without male germ cells reveals that Smc1a silencing impairs SSC colonization and causes differentiation defect. Notably, Smc1a-conditional knockout (Smc1a-cKO) mice assume spermatogenesis disorder and obviously compromise male fertility. Single-cell transcriptomics demonstrates that Smc1a-cKO mice exhibit the downregulation of genes associated with mitosis, meiosis, and m5C regulation. Significantly, whole-exome sequencing (WES) of 2028 non-obstructive azoospermia (NOA) patients identify two deleterious SMC1A variants and one deleterious HMGA2 variant. SMC1A and HMGA2 expression levels were remarkably decreased in testicular tissues from NOA patients with spermatogenic failure compared to obstructive azoospermia (OA) patients with normal spermatogenesis. Collectively, our findings highlight the critical roles and a novel mechanism by the SMC1A/YBX1/HMGA2 axis in regulating human SSC fate decisions and male fertility via an m5C modification. This study is thus of the utmost significance because it would provide novel molecular mechanisms underlying fate determinations of adult stem cells and human spermatogenesis and it could offer network targets for gene targeting male infertility and other diseases.
2026-09-14
Cell Death and Differentiation (published)
doi.org
What Does Layer-Importance Reveal About Transformers and State-Space Models?
Istabrak Abbes
Nizar Islah
Irina Rish
Sarath Chandar
Transformers and state-space models (SSMs) are the two dominant families of sequence models, and a central open question is how far the anal… (see more)ytical knowledge built for transformers transfers to SSMs. We address this through the lens of layer importance which underpins compression, selective fine-tuning, and interpretability across both families. We decompose layer importance into two distinct notions. \emph{Necessity} captures how much the pretrained model depends on a layer's existing contribution, measured by the loss increase from bypassing it. \emph{Plasticity} captures where the model absorbs new information during fine-tuning, measured by the magnitude of task-specific weight updates. Our analysis reveals that the two families behave fundamentally differently: in every evaluated residual transformer up to
2026-09-14
arXiv (preprint)
doi.org
arxiv.org