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
ESC: Escaping 2D Diffusion Ambiguity with Geometric Constraints for Consistent Novel View Synthesis
Ge Ya Luo
Daniel Severo
Brian Karrer
Christopher Pal
Adriana Romero
Michal Drozdzal
Generating 3D-consistent novel views from 2D diffusion models remains a fundamental challenge in computer vision. In this work, we introduce… (see more) a framework that enhances geometric alignment for monocular view synthesis under drastic camera changes by jointly generating a target view and its corresponding depth map. By conditioning the diffusion pipeline on the single source image, source depth, and target camera rays, our approach forces the model to inherently reason in 3D space even under extreme viewpoint shifts. To guarantee spatial fidelity, we propose a novel per-pixel depth consistency constraint, which verifies and enforces 3D consistency across generated views. Our framework establishes a robust pipeline for geometrically consistent view synthesis, yielding superior visual accuracy and spatial alignment compared to current state-of-the-art methods. With this work, we pave the road towards robust 3D world models capable of understanding complex environments from a single view image.
Gravitational microlensing probes unresolved quasar accretion disc structure and compact objects in lens galaxies and is an important system… (see more)atic in strong-lens time-delay cosmography. Most analyses use static microlensing map simulations because evolving individual microlenses and caustics is computationally prohibitive. We present Microcaustics, a GPU-accelerated Python package built on PyTorch for dynamical microlensing of time-dependent extended sources in strong gravitational lenses. It combines a local-exact/far-field deflection solver, source-directed lens-plane scouting with temporal reuse, and biquadratic inverse polygon mapping (IPM). GPU batching and fused Triton rasterization accelerate the calculation, while binary caustic labels track source-centred crossings. Across three simulated quadruply lensed quasar systems, our package generates a 10-year, 147-frame multiband light curve in an amortized median of 0.68 s (0.88 s with labels) on a consumer GPU with a median light-curve RMSE of 0.35 mmag, while recovering every reference source-centred caustic crossing. At comparable map accuracy, the batched throughput is 780 times higher than that of a recent CUDA IPM implementation and extrapolates to a speedup of millions relative to classic GPU-D. We demonstrate that our IPM converges as
Large language models (LLMs) trained on vast amounts of data have demonstrated impressive performance over a range of tasks, but future perf… (see more)ormance gains will require increasing amounts of data and compute. Federated Learning (FL) facilitates training on decentralized private data, but client resource limitations can make training impractical, particularly as model sizes continue to expand. These resource constraints make the assumption of a shared server-client architecture impractical. Model heterogeneous FL offers a promising alternative by adapting model size to client capabilities; however, previous work is limited to the pre-training setting, and conclusions on sub-network selection do not necessarily hold for fine-tuning. Furthermore, prior approaches create client sub-networks without considering their unique data distributions, thereby overlooking the opportunity to tailor sub-network architecture to local data. Motivated by evidence that attention heads exhibit task dependency within layer defined feature spaces, we propose Optimal Hydra, a transformer based heterogeneous FL framework for fine-tuning that combines global layer selection with client specific attention head selection, aligned with local data distributions. Optimal Hydra makes explicit use of client data to produce client-specific sub-networks we call Hydra-nets. To our knowledge, this is the first model heterogeneous FL approach tailored to LLM fine-tuning. Experiments on three datasets show significant improvements over baseline methods while also reducing local resource demands.
Revisiting the genetic support of leukotriene pathway drug targets in atherosclerotic cardiovascular disease
Tristan St-Laurent
Julien St.-Pierre
Julien Quang Le Van
Marc‐André Legault
Arachidonate 5-lipoxygenase (5-LO) and its activating protein, encoded by ALOX5 and ALOX5AP respectively, are two leukotriene pathway protei… (see more)ns suspected to play a role in atherosclerotic cardiovascular disease (ASCVD) through inflammatory mechanisms. Prior genetic association studies linking ALOX5 and ALOX5AP to ASCVD have motivated clinical trials of 5-LO inhibitors, such as atreleuton, which was associated with reduced atherosclerotic plaque progression in patients with a recent acute coronary syndrome in a phase II trial. However, the effect of 5-LO inhibition on ASCVD clinical outcomes remains unclear. Using data from the UK Biobank, we revisit previously reported genetic associations of ALOX5 and ALOX5AP with ASCVD using a multi-ancestry meta-analysis including data from 378,962 participants. We characterize ancestral differences in previously studied ALOX5 and ALOX5AP polymorphisms which could have led to population stratification. When adequately accounting for ancestry, these previous associations were not replicated. In addition to our replication efforts, we used association scans and transcriptome-wide association studies to test the involvement of leukotriene pathway genes with ASCVD. Overall, our results do not support a role for genetic variation in ALOX5 or its activating protein in ASCVD risk.
While sensitivity analysis for linear programs with parametric right- hand side vectors is well established, cases involving parametric cons… (see more)traint matrices remain less explored. To address this gap, we investigate linear programs where the constraint matrix depends linearly on a scalar parameter. Our goal is to compute the minimum and maximum optimal values of these parametric linear programs within a fixed parameter range. This corresponds to solving two bilevel programs. We show that both decision versions of these optimization problems are NP-complete by proving both NP-hardness and membership in NP. We additionally identify three sufficient conditions on the parametric matrix under which the bilevel programs are no longer NP-hard. We introduce a reformulation for both problems, together with a Farkas-based certificate for the lower-level feasibility condition, and compare the execution time for solving them on standard benchmark instances. The experiments highlight a practical dichotomy. Although both bilevel optimizations are NP-hard, computing the parameter value corresponding to the minimum of the linear program is fast, whereas computing the value corresponding to the maximum is not. We relate this asymmetry to the parametric equality constraints, whose free dual variables leave the relaxation of the maximum reformulation unbounded.
Flow maps are a recent method of probabilistic generation that amortize diffusion trajectories into one-step samplers, unlocking efficient g… (see more)eneration. While progress has been made in improving their empirical performance, there is still a lack of understanding behind the mechanisms underlying their success. Specifically, many flow map learning methods employ stop gradient operators as a crucial part of their training target. Adaptive weighting also drastically improves the generation capabilities of flow maps. Although many interpretations have been proposed to support the inclusion of these heuristics, none have analyzed the impact of these assumptions on the training dynamics of flow maps themselves. In this work, we address this issue by providing grounded theory explaining why such tricks are required. Analyzing the functional gradient flow induced by the MeanFlow and Lagrangian losses, we show their convergence to the true flow map, settling the validity of these objectives. For finite updates, we highlight a severe roadblock to the usage of these losses in practice: the possible unboundedness of the update. Adaptive normalization not only provides bounded updates, but, combined with a specific weighting, additionally provides convergence guarantees towards a neighborhood of the solution. On synthetic data, we show that our functional gradient flow analysis exactly describes the true training dynamics for flow maps. Experiments on standard image datasets demonstrate that a proper reweighting scheme is essential for strong empirical performance, which is only achieved for a specific range of reweighting strengths.
Before deploying clinical prediction models, their reliability must be assessed to ensure safe use. Errors may arise from distribution shift… (see more)s between training and deployment or from heterogeneous performance where the model systematically underperforms for certain patient subgroups. Yet most post-hoc diagnostic methods evaluate reliability only at the population level, checking whether the deployment data resemble the training data and whether the model performs well on average, without accounting for heterogeneity that may cause some patients to be disproportionately affected. We propose a unified diagnostic pipeline that combines both perspectives. MED3pa first discovers interpretable low-confidence patient profiles, and Detectron is then applied within each profile to test whether its degradation is associated with a detectable harmful covariate shift. Across three clinical prediction tasks and three injected subgroup shifts in MIMIC-IV, we find that shift detectability itself is informative. An injected age shift, undetectable at the population level, was nonetheless localized to specific degraded profiles, whereas sex- and race-related shifts were detected broadly and therefore offered little guidance for identifying the most affected patients.
Understanding neural scaling laws is increasingly important for theory and practice, yet first-principles explanations remain limited even i… (see more)n simple settings. In this work, we study capacity-limited scaling in a bottlenecked bigram model with power-law (Zipf) token statistics, viewed as an analytically tractable toy model of a large language model. Fixed random embeddings serve as a proxy for representational capacity and induce an explicit bottleneck of width, allowing us to derive scaling laws for prediction regret as a function of model width, vocabulary size, and the Zipf exponent. Our results complement recent theoretical accounts based on optimization dynamics by isolating scaling due purely to representational constraints. In the appropriate regime, the theory recovers the functional form of classical neural scaling laws and suggests that heavy-tailed language statistics may underlie both optimization- and capacity-driven scaling. Experiments natural language datasets (WikiText2, OpenWebText) closely match the predicted curves.
Training large language models (LLMs) across geographically distributed and poorly interconnected compute pools or data centers has become a… (see more) topic of significant interest. This has led to increased study of local optimization methods such as DiLoco for LLMs, especially those that use local (or inner) adaptive or preconditioned optimizers, which are critical for high-performance LLM training. However, a central challenge remains: it is well known that increasing the number of model replicas (replica scaling) while fixing the total training budget leads to monotonically decreasing performance. Existing work has empirically demonstrated that the choice of inner optimizer (Muon v.s. AdamW) can significantly improve this trend, but offers only limited explanation of the performance difference. In this work, we consider a range of inner-optimizers and identify two important factors that impact replica scaling: (1) the covariance structure of the pseudo-gradients and (2) the impact of batch size on the pseudogradient's noise scale. Based on these insights, we theoretically and empirically demonstrate that whitening-based pre-conditioning is a powerful inner-optimizer desideratum. Our empirical evaluation extends the results to reveal that whitening-based inner-optimizers achieve strong replica scaling (for 8-96 replicas), with performance relative to DP improving as parameters and data are scaled.
Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be… (see more) easily applied zero-shot or efficiently finetuned for downstream tasks. However, these policies can still have poor generalization, both due to the choice of modeling objective and from learning from a static dataset. In this work, we focus on the challenging task of zero-shot goal generalization, where a policy is evaluated on unseen tasks that require combining its existing knowledge (compositional generalization). An avenue for improving a policy's generalization is by generating new experience with world models; however, such generation has proven difficult for longer horizons. Thus, to alleviate this issue, we propose TD-Aug, which samples from a geometric horizon model and allows for directly imagining novel outcomes that can be achieved by composing existing knowledge. We demonstrate that training on these future outcomes as goals for goal-conditioned BC policies significantly improves generalization in stitching-based OGBench tasks.
People often tackle difficult problems by thinking more deeply or exploring more possibilities. Similarly, recursive reasoners, which reason… (see more) by repeatedly applying a learned update rule to latent states, can also scale inference through more updates (depth) or additional trajectories generated by perturbing latent states (width). When people hit a dead end in their thinking, they may step back and approach the problem from a fresh angle. However, neither depth scaling nor perturbation-based width scaling of recursive reasoners can reliably achieve this: both may converge to incorrect attractors. To address this, we propose to explore diverse reasoning traces by applying different update maps to the same latent state, without any additional training. We realize this idea through \emph{Input-Conditioned Search (ICS)}, which searches over input conditions to induce alternative update maps from the pretrained reasoner. Across six reasoning tasks, ICS achieves the highest mean accuracy, while requiring up to two orders of magnitude fewer model FLOPs than the evaluated scaling baselines. Controlled experiments confirm that ICS can redirect trajectories from the same state. Our theoretical analysis and rigorous numerical verification also confirm that ICS can locally eliminate incorrect attracting fixed points. Together, these findings establish ICS as an effective axis for efficient test-time scaling and motivate further research on shaping recursive reasoning during training and at test time.
In this work, we study grokking in a simple, analytically tractable setting whose rich phenomenology allows us to disentangle the effects of… (see more) initialization, signal strength, weight decay, sample size, and input dimension. These factors can produce superficially similar learning curves through distinct mechanisms, complicating their interpretation. Our analysis distinguishes early fitting through nuisance features, core feature learning, and delayed generalization. We identify sharp conditions under which grokking provably occurs and derive analytic asymptotic expressions for the lengths of the generalization plateaus. Our results also characterize regimes of early generalization and failure to reach a prescribed test accuracy target. We show that the interpolation edge constitutes a distinct dynamical regime, where vanishing spectral gaps separate core learning from generalization, helping clarify the role of proximity to interpolation in existing accounts of grokking. The resulting picture is analogous to fast and slow phases in chemical kinetics and suggests that the lazy-to-rich transition discussed in the literature may reflect a similar separation of dynamical time scales. Our theoretical results are faithfully supported by extensive experiments.