The upcoming meeting, taking place on November 10 at Mila, will explore how we can collectively develop, govern, and deploy high-performing, reliable, and secure agentic systems by connecting academic researchers, industry experts, and practitioners.
Join us on the Venture Scientist Bootcamp, a full time, 4-month incubator at Mila, built specifically for deep tech founders with elite STEM backgrounds. You have until November 21, 2026 to apply!
We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
Equivalent Numeric Approved Identity of Passport and Immigration Papers -- The Next Generation Identification Program (NGI) [A Short Introduction]
We express an interest to Equivalent Numeric Approved Identity of Passport and Immigration Papers. [We are making a submission to the Journa… (see more)l of Banking and Financial Technology].
A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use i… (see more)n downstream decision-making. We consider two objectives for reliable uncertainty quantification: self-calibration, requiring a point prediction to be unbiased conditional on its own value, and prediction-conditional validity, requiring a prediction interval to attain nominal coverage conditional on the prediction. Self-Calibrating Conformal Prediction (SC-CP) attains both objectives exactly in finite samples, but requires refitting its calibrator for every candidate outcome, which is computationally prohibitive for continuous outcomes. We propose Isotonic Conformal Prediction (ICP), a framework that decouples calibration from prediction-set construction by fitting a single isotonic recalibration map and constructing prediction intervals within strata of similar recalibrated predictions. Within this framework we develop two procedures. Split Isotonic Conformal Prediction (SICP) attains prediction-conditional validity in finite samples and self-calibration asymptotically, at the computational cost of split conformal prediction. Transductive Isotonic Conformal Prediction (TICP) attains both objectives exactly in finite samples through a per-test-point inner loop that avoids refitting the isotonic calibrator. On synthetic heteroscedastic regression problems and a real-world healthcare-utilization dataset, both procedures match the coverage of SC-CP at substantially lower computational cost.
AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior re… (see more)mains poorly understood due to strong context dependence. Current evaluation protocols follow a defense-in-depth paradigm with compounding layers of safeguards, ranging from traditional benchmarks to live or adversarial testing. Such benchmarks remain largely static and single-turn, limiting their ability to capture real-world variability in conversational settings. We propose StabilityBench, a principled, general and model-agnostic benchmark operator that transforms single-turn benchmark queries into multi-turn interaction histories. StabilityBench augments existing benchmarks by injecting realistic user simulations, through demographic proxies or sycophantic baits, while preserving original task intent. We apply StabilityBench to four benchmarks spanning mathematical reasoning, health question-answering and safety, and evaluate nine large language models under these conditions. Our results show that model performance is consistently unstable under these injections, with considerable performance degradations on three out of four benchmarks studied. These highlight important limitations of static evaluations and motivate more realistic evaluation settings. To this end, we propose StabilityBench-Mini: a size-preserving variant of StabilityBench that samples across diversification axes, enabling more realistic evaluation without increasing costs.
Purpose: To compare the cross-site generalization of radiomic features and deep learning embeddings for MRI prediction of substantial lympho… (see more)vascular space invasion (LVSI) in endometrial cancer. Materials and Methods: This retrospective two-center study included 206 women (mean age, 59.8 years) with endometrial cancer who underwent preoperative 3-T MRI from March 2016 to March 2023. Hospital A (n = 130) was used for development and Hospital B (n = 76) for strict external testing. T2-weighted, reduced field-of-view diffusion-weighted, and apparent diffusion coefficient images were manually segmented. Radiomic features and seed-pooled embeddings from 3D ResNet18, DenseNet121, and U-NEXtractor were modeled with elastic-net logistic regression or XGBoost. Out-of-fold Platt calibration and sensitivity-targeted thresholds were estimated using development data only. AUCs were summarized with 95% bootstrap confidence intervals. Results: External radiomics with elastic-net achieved an AUC of 0.609 (95% CI: 0.464, 0.740) and sensitivity of 0 of 12 (0%). DenseNet121 with elastic-net had the highest external AUC (0.685; 95% CI: 0.538, 0.822) but sensitivity of 3 of 12 (25%). U-NEXtractor with elastic-net detected 10 of 12 positive cases (83.3%) with specificity of 32 of 64 (50.0%) and balanced accuracy of 0.667. XGBoost showed higher apparent development performance but weaker external operating behavior. Conclusion: Under real-world cross-site MRI acquisition shift, DenseNet121 and U-NEXtractor embeddings showed better external generalization than handcrafted radiomic features for substantial LVSI prediction.
Pretrained transformers provide general-purpose molecular embeddings for downstream tasks. While these embeddings provide task-agnostic stru… (see more)ctural patterns, they lack task-specific alignment, limiting downstream performance. Here, we introduce Freeze, Diffuse, Decode (FDD), a diffusion-based framework that adapts pretrained transformer embeddings to downstream tasks by building a task supervised diffusion geometry over the frozen embeddings, without any backbone training. Applied to antimicrobial peptide design, FDD yields low-dimensional, predictive, and interpretable representations that support property prediction, retrieval, and latent-space interpolation.
2026-07-15
Topology, Algebra, and Geometry in Data Science (oral)
Using the language of Wilsonian renormalization group theory (RG), we treat the Transformer's attention mechanism as a perturbation of the t… (see more)rained MLP residual-stack fixed point and ask whether it constitutes a relevant, marginal, or irrelevant operator. We derive a fixed-point shift formula and obtain four testable predictions for the fixed-point geometry, effective rank profile, layer specificity, and perturbation decay spectrum. Testing these on synthetic Markov chain sequences with controlled correlation length, we find: (1) For large chains(long correlation), attention is strongly relevant: it closes a residual loss gap the MLP cannot bridge and drives a phase transition in representation space, with effective rank jumping above input dimensionality at layer 1 and stabilizing at a high-dimensional plateau. (2) For short chains(short correlation), attention is irrelevant: the Transformer converges to the same loss and fixed-point geometry as the MLP, though it contracts perturbations faster. (3) The transition is dominated by the first-layer head (L0H0), which accounts for more than 4 times the representational shift of any subsequent head, consistent with the prediction that the relevant operator acts before the MLP begins integrating out positional variation. (4) Perturbation decay experiments reveal a regime reversal: in the long correlation regime the Transformer selectively preserves slow Markov modes (5.4 times the dynamic range in decay length vs. 1.3 times for the MLP); in the short correlation regime it suppresses all modes faster than the MLP, with no spectral selectivity. Together, these results show that the relevance of attention is not a property of the architecture but of the spectral structure of the data-generating process, and that a first-order RG perturbation framework provides a predictive account of that difference.
We study the neural representations learned by deep neural networks trained on alternating group multiplication, discovering that they are S… (see more)chreier coset graphs, a generalization of Cayley graphs. Previous works inspected neural representations learned from cyclic group multiplication and identified them as Cayley graphs. Since cyclic group multiplication is Abelian, all subgroups are normal, and Schreier coset graphs reduce to Cayley graphs in this case. This contribution makes a step toward finding a general theory of what neural representations are in networks learning group multiplications.
2026-07-15
Topology, Algebra, and Geometry in Data Science (oral)
Large neural networks are increasingly combined through weight-space merging and distilled into smaller models, but weights and activations … (see more)are not canonical coordinates: two networks can implement similar functions while differing by permutations, rescalings, or basis changes. We ask whether these operations can instead be guided by the geometry of a model's representation space. For each model, we summarize the relationships among probe examples using a diffusion operator built from internal activations. We then test a simple distillation procedure in which a student is trained to match a fixed diffusion-geometry target derived from a teacher. Across Pythia, BERT, and DeBERTa-v3, this target does not generally make the student inherit the teacher's specific representation geometry. Instead, distilled students usually remain closer to matched task-only controls, and the objective has little effect on held-out performance. These results suggest that representation-geometry objectives must be evaluated against the geometry a student would learn from ordinary training alone.
2026-07-15
Topology, Algebra, and Geometry in Data Science (poster)
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete da… (see more)ta, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research.