Publications

Bifurcation Preservation as a Physics Diagnostic for Neural Phase-Field Surrogates
Alejandro Salinas-Medina
Anisleidy Gonzalez-Mitjans
Xue Liu
A common approach for evaluating neural surrogates of phase-field equations is aggregate field error against a reference solver, a measure t… (voir plus)hat can overlook bifurcations: abrupt shifts between qualitatively distinct outcomes, e.g., whether a phase-field droplet dissolves or persists. We propose evaluating neural phase-field surrogates in terms of their capacity for bifurcation preservation. We demonstrate the diagnostic on the Cahn-Hilliard (CH) critical droplet boundary using a droplet-aware Fourier Neural Operator, which reaches a moderate held-out rollout error, with relative
2026-05-29
AI4Physics @ International Conference on Machine Learning (publié)
openreview.net
openreview.net
Compositional Flow Matching with Factored Velocity Fields
Avery Hee-Woon Ryoo
Dane Malenfant
Matthew G Perich
Guillaume Lajoie
Conditional generative models can have difficulty generating attribute combinations absent from training, even when each individual factor i… (voir plus)s densely covered, otherwise known as a failure to compositionally generalize. We propose a factored conditional flow matching architecture that uses a shared base velocity augmented by per-factor heads, summed at the bottleneck. We show that on the Shapes3D and MPI3D-real datasets, the factored architecture matches or beats a parameter-matched monolithic baseline under three structured zero-shot holdout strengths over a two-attribute lattice, notably lowering heldout FID by
2026-05-29
SPIGM @ International Conference on Machine Learning (poster)
openreview.net
openreview.net
CrysTune: Crystal Generation via Fine-Tuning of Large Language Models on Wyckoff Representations
Prashant Govindarajan
KISHALAY DAS
Sarath Chandar
The discovery of novel materials is essential for driving scientific and technological breakthroughs. Recent work has explored fine-tuning l… (voir plus)arge language models (LLMs) for autoregressive crystal generation, but the ideal representation and training strategies for symmetry-based inductive biases remain unclear. We propose CrysTune, a class of LLMs fine-tuned on Wyckoff representations of crystals with two auxiliary tasks: canonicalization and template prediction. CrysTune shows competitive performance and improved stability-related metrics relative to LLMs trained on standard string-encoded representations. We further use these models as initial policies for reinforcement learning (RL) fine-tuning to optimize stability, validity, uniqueness, novelty, and diversity. RL-trained policies produce more valid and metastable crystals, while introducing novelty and diversity trade-offs. We also explore crystal system conditioning, showing that RL-trained policies produce a higher proportion of crystals matching the target condition.
2026-05-29
AI4Science @ International Conference on Machine Learning (poster)
openreview.net
openreview.net
Exploiting weight-space symmetries for approximating curvature
Artem Artemev
Rui Xia
Benjamin M. Boyd
Youjing Yu
Felix Dangel
Guillaume Hennequin
Alberto Bernacchia
Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of moder… (voir plus)n deep networks. Surprisingly, no previous work has exploited the curvature constraints that arise from well known weight-space symmetries in loss landscapes. By analytically averaging over group actions that leave the loss invariant, we construct structured Hessian approximations from single gradients that can be tractably estimated, stored, and inverted. The choice of user-specified symmetry group directly governs the trade-off between approximation accuracy and computational cost. Moreover, our framework provides a unifying theoretical lens for viewing existing methods; in particular, a specific choice of symmetry group recovers Shampoo/Muon-like curvature estimates. We validate our method on a range of network architectures, and deploy it to second-order optimization benchmarks, including a small language model. Our curvature estimation framework might find applications in other machine learning problems such as uncertainty estimation, continual learning, compression/pruning, training data attribution, and more.
2026-05-29
arXiv (prépublication)
doi.org
arxiv.org
IDEAFix: Evaluation Framework for Creative Defixation Prompting in LLMs
Florian Carichon
Soumya Sharma
Meaghan Girard
Romain Rampa
Golnoosh Farnadi
Large language models (LLMs) are increasingly used for tasks involving creative problem solving and idea generation. However, there is a lac… (voir plus)k of consensus concerning their creative capabilities: some studies report superior performances compared to humans, while others highlight structural limitations such as fixation and the homogenization of outputs. Existing evaluation approaches either rely on narrow, decontextualized tasks that do not capture goal-oriented generation or on broader settings that confound multiple aspects of the creative process, making it difficult to isolate the effects of task formulation, prompting, and evaluation design. Significantly, the role of structured prompting strategies in shaping idea generation remains underexplored. Therefore, we introduce IDEAFix, an evaluation framework for analyzing divergent thinking in open-ended idea generation tasks. We prompt models to generate multiple original solutions to controlled variations of short design scenarios, task attributes, and defixation prompting strategies. This design enables systematic analysis of how structured guidance influences LLMs' idea generation. Our results show that both task formulation and attribute selection significantly affect models' performance, and that simple prompting strategies can boost the originality of solutions. However, we also observe persistent output homogenization across models, confirming inherent limits in their ability to generate diverse solutions. Overall, IDEAFix provides a controlled, extensible framework for studying the mechanisms underlying LLMs' creativity.
2026-05-29
arXiv (prépublication)
doi.org
arxiv.org
Microlensing Detection and Inference via Learned Bayes Factors
Nolan Smyth
Laurence Perreault-Levasseur
Yashar Hezaveh
We present a unified framework for gravitational microlensing event detection and parameter inference. Traditional pipelines use determinist… (voir plus)ic hard cuts on photometric statistics, systematically missing low-magnification events in the finite-source regime. We instead frame detection as Bayesian model comparison using Evidence Networks, which learn calibrated Bayes factors from binary-labeled simulations, and combine this with Neural Posterior Estimation (NPE) for amortized parameter inference. Both share a transformer encoder that handles irregularly-sampled time series without imputation. On simulated Roman Space Telescope data, our Evidence Network achieves
2026-05-29
AI4Physics @ International Conference on Machine Learning (publié)
openreview.net
openreview.net
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
Juan Agustin Duque
Sergio García-Heredia
Vinicius Hernandes
Eliška Greplová
Thomas Spriggs
Aaron Courville
Anna Dawid
Neural quantum states (NQS) provides a flexible and scalable framework for approximating quantum many-body wavefunctions. Among NQS paramete… (voir plus)rizations, autoregressive models are especially attractive because they enable exact, independent sampling from the Born distribution, avoiding the autocorrelation and mixing issues of Markov chain methods. Yet their optimization remains comparatively underexplored: Adam is a scalable method but ignores function space geometry, while stochastic reconfiguration is principled but costly and numerically fragile in large models. To address this gap, we show that variational energy minimization can be viewed as an advantage policy-gradient problem over the Born distribution, motivating trust-region optimization for NQS training. We introduce \emph{Proximal Wavefunction Optimization} (PWO), a trust-region algorithm that clips probability-ratio changes in the amplitude channel and wrapped phase increments in the phase channel. PWO avoids explicit matrix inversion, reuses samples across inner updates, and preserves the scalability of first-order optimization. Across Ising, Heisenberg, and frustrated
2026-05-29
AI4Physics @ International Conference on Machine Learning (publié)
doi.org
openreview.net
Path-independent Flow Matching for Multi-parameter Generative Dynamics
Francisco Tellez
Amirhossein Zamani
Philippe Martin
Shuang Ni
Guy Wolf
Eugene Belilovsky
Sina Sanjari
Yanlei Zhang
Flow Matching is a powerful framework for learning transport maps between probability distributions. Yet its standard single-parameter formu… (voir plus)lation is not designed to capture multi-parameter variations where the resulting transport should be path-independent. Path independence is crucial because it ensures that transformations depend only on the initial and target distributions, not on the specific path. In this work, we introduce Path-independent Flow Matching (PiFM), a method for learning vector fields whose induced flows yield path-independent transport between distributions. We show that PiFM generalizes Flow Matching to higher-dimensional parameter domains while enforcing structural conditions that ensure consistency of composed transformations. In addition, we show that, under suitable assumptions, PiFM approximates the Wasserstein barycenter, linking the framework to a notion of distributional interpolation. To enable practical training, we propose a tractable, simulation-free objective that regresses onto multi-parameter conditional probability paths. We showcase empirically that PiFM outperforms other approaches on both synthetic and real world data in interpolating path-independent trajectories and generating desired out of distribution samples.
2026-05-29
SPIGM @ International Conference on Machine Learning (poster)
doi.org
openreview.net
Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
Guillaume Payeur
Laurence Perreault-Levasseur
Gabriel Missael Barco
Yashar Hezaveh
Modeling galaxy-galaxy strong gravitational lenses to infer the brightness of the source galaxy and the mass distribution of the foreground … (voir plus)galaxy is computationally challenging, particularly for high-resolution, high signal-to-noise observations. In this regime, high-dimensional representations of both the source and the foreground mass distribution are necessary to model the data down to the noise level. This inference problem has been challenging for both traditional and machine learning-based methods because of its high dimensionality and its non-linearity in the foreground mass distribution. We present a method to generate joint posterior samples of the source galaxy and foreground mass distribution as pixelated images conditioned on observations. The method combines diffusion-based generative modeling and recurrent inference machines. It can model realistic gravitational lensing simulations with background and foreground galaxies drawn from cosmological hydrodynamical simulations down to the noise level.
2026-05-29
AI4Physics @ International Conference on Machine Learning (publié)
openreview.net
openreview.net
DeSQ: Decomposition-based SPARQL Query Generation
Papa Abdou Karim Karou Diallo
Aditya Sharma
Neshat Elhami Fard
Amal Zouaq
Dominant approaches to Knowledge Base Question Answering (KBQA) fall into two categories. First is the generation of a formal query that suf… (voir plus)fers from brittleness and limited explainability, and the second is direct answer retrieval through KB exploration that is computationally costly and prone to hallucination. To combine the strengths of both paradigms while mitigating their respective weaknesses, we introduce DeSQ (Decomposition-based SPARQL Query Generation), a KB-agnostic framework that operates in three stages. First, it decomposes complex questions into Atomic Constraints (ACs) that mirror the relational structure of the underlying KB. Second, it generates a two-part structured output: (a) Mapping of each AC to its corresponding SPARQL Fragment, using standardized variable and URIs placeholders, and (b) URIs Grounding block describing each placeholder. Third, it assembles these fragments into a complete SPARQL query. DeSQ surpasses state-of-the-art approaches on four out of five major benchmarks and demonstrates superior robustness to lexical variation. Beyond performance gains, our framework greatly simplifies evaluation by eliminating the need for a live KB endpoint, and its structured output enables fine-grained error analysis, allowing more targeted interventions for improvement.
2026-05-28
arXiv (prépublication)
doi.org
arxiv.org
Drift Q-Learning
Anas Houssaini
Mohamad H. Danesh
Amin Abyaneh
Scott Fujimoto
Hsiu-Chin Lin
David Meger
Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value … (voir plus)estimates. Diffusion and flow policies handle this trade-off by modeling the behavior distribution to regularize the RL objective, but they require iterative denoising, solver integrations, and in more efficient variants, distillation or other approximations at inference. We propose DriftQL, which combines a drift-based behavioral regularizer with critic-driven policy improvement. The value signal biases the policy toward high-value regions of the data support, while attraction and repulsion together keep generated actions near the data and prevent collapse onto a single mode. DriftQL is implemented as a single network with a unified training objective and generates actions in a single forward pass. On D4RL and OGBench, DriftQL consistently outperforms diffusion and flow methods, advancing the state of the art. Under degraded data quality, where the baselines visibly struggle, DriftQL remains close to its clean-data performance, positioning it as a promising alternative to diffusion and flow-based methods while maintaining the simplicity and efficiency of deterministic approaches. Project page: https://driftql.github.io/
2026-05-28
arXiv (prépublication)
doi.org
arxiv.org
Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
Ezekiel Williams
Alexandre Payeur
Guillaume Lajoie
Biological and neuromorphic recurrent neural networks (RNNs) are subject to spatial and temporal locality constraints on the information tha… (voir plus)t can plausibly be used during learning. A common strategy to satisfy these constraints is to modify gradient descent by neglecting non-local terms to varying degrees, as in random feedback local online (RFLO) learning and truncated backpropagation through time (tBPTT). However, the learning dynamics of these algorithms, and how they compare with BPTT, remain poorly understood. We apply dynamical systems theory to data-aligned linear RNNs -- whose dynamics can be separated into orthogonal modes -- to compare stationary solutions, stability properties, and convergence rates, finding qualitatively distinct behaviour for RFLO versus BPTT and one-step tBPTT. We further observe that the solutions learned by RFLO are restricted to low-rank perturbations of initial parameters, a result which holds beyond the data-aligned setting. Our work provides analytical insight into how locality constraints shape learning dynamics, with implications for neuroscientific models of learning and alternative optimization approaches for RNNs.
2026-05-28
arXiv (prépublication)
doi.org
openreview.net