Machine Learning
Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning
Thomas Frost and Steve Harris
Offline reinforcement learning (ORL) offers the potential to improve the quality of clinical decision-making using historical electronic health record (EHR) data. Current training and evaluative practices in this field rely heavily on EHR
datasets that have been temporally discretised into fixed, regular time intervals. Discretisation creates fictional representations of complex clinical scenarios and compromises the generalisability of retrospective model evaluations. In this paper, we introduce Insulin4RL, a healthcare ORL
dataset featuring naturally irregular inputs and actions from real clinical trajectories. Derived from MIMIC-IV, Insulin4RL comprises over 375,000 labelled decisions across 12,209 patients requiring insulin infusion titration in the Intensive Care Unit. The
dataset can thus be used for research into ORL model performance under realistic clinical sampling assumptions. We provide a description of the
dataset's structure and characteristics, baseline performance metrics using model-free offline reinforcement learning, and a standardised evaluation protocol using fitted Q-evaluation. We conclude with suggested areas for future research that could be addressed using this resource.
Read the full abstract ▾
Machine Learning
Can In-Context Learning Support Intrinsic Curiosity?
Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald et al. (+5 more)
Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge. Classic approaches incentivize exploration by rewarding an
agent based on its "learning progress", which measures how much a newly acquired observation improves a world model's predictive ability. However, evaluating these rewards traditionally requires expensive inner loops of gradient descent updates within each trajectory, rendering them computationally impractical at scale. In this work, we investigate whether the emergent in-context learning (ICL) capabilities of sequence models can eliminate this bottleneck by serving as immediate, update-free world models. Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress, using solely the prediction errors and counterfactual context manipulations of an in-context learner. We first prove that in general Markov decision processes, this is in fact impossible in an unbiased way: the resulting intrinsic rewards either suffer from nuisance terms that bias their estimation of true learning progress, or they cannot be implemented using an in-context learner's prediction errors. Conversely, we prove a positive result for a broad subclass of non-temporal settings, encompassing active learning and
Bayesian Experimental Design: here, ICL-derived rewards successfully bound and asymptotically converge to the true learning progress. We corroborate our theory with controlled experiments across continuous and symbolic environments, demonstrating that our ICL-driven framework successfully trains curious data-collection policies that explore optimally.
Read the full abstract ▾
All authors Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald, Rajai Nasser, Blaise Agüera y Arcas, João Sacramento, Rif A. Saurous, Guillaume Lajoie
Machine Learning · Cross-listed from cs.CV
Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers
Fabio De Sousa Ribeiro, Emma A.M. Stanley, Charles Jones et al. (+7 more)
We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer from poor generalisation across patient subpopulations, institutions, and acquisition settings, resulting in limited real-world clinical utility. Controlled, high-fidelity synthesis of chest radiographs is a promising path toward diversifying clinical
datasets and evaluating the robustness of diagnostic models. Therefore, we present the largest specialist generative foundation model for chest radiographs to date, with over 1.3B parameters, trained for 1.6T
tokens on a curated, heterogeneous
dataset comprising 1.2M radiographs and clinical expert-guided metadata. Our model supports controllable radiograph generation and editing across multiple demographic subgroups, acquisition views, and a dozen pathologies. Moreover, we significantly advance the state of the art in radiograph synthesis fidelity, producing images that are indistinguishable from real radiographs to clinical experts.
Read the full abstract ▾
All authors Fabio De Sousa Ribeiro, Emma A.M. Stanley, Charles Jones, Tian Xia, Dominic C. Marshall, Laurent Renard Triché, Christopher V. Cosgriff, Panagiotis Dimitrakopoulos, Sotirios A. Tsaftaris, Ben Glocker
Machine Learning
3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning
Ellina Zhang, Madhaven Iyengar, Amir Zadeh et al. (+4 more)
We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles. Building on the Deep Latent Particles (DLP) framework, each particle encodes disentangled attributes, including 3D keypoint position, bounding box dimensions, and appearance features, and represents a distinct entity in the scene. The model learns interpretable per-particle
segmentation maps through an end-to-end self-supervised reconstruction objective. We demonstrate on both simulated and real-world
datasets that the learned latent space is interpretable and controllable: by manipulating particle positions and decoding, we can generate novel scene configurations. Furthermore, we show that leveraging these compact 3D latent particles for downstream robotic manipulation improves performance over baselines that either lack explicit 3D information or rely on
memory-intensive dense 3D inputs without object-centric structure. Code and
videos are available at https://eubooks3003.github.io/3d-dlp.
Read the full abstract ▾
All authors Ellina Zhang, Madhaven Iyengar, Amir Zadeh, Chuan Li, Deepak Pathak, David Held, Tal Daniel
Machine Learning
MortarBench: Evaluating Mortgage Loan Origination Agents
Matthew Toles, Yunan Lu, Manav Munjal et al. (+6 more)
Loan origination is the process by which a lender creates a new loan, from application and underwriting through approval and funding. This process serves a critical role in evaluating the eligibility and level of risk posed by an applicant. Recently, firms have begun using mortgage loan
agents to augment human loan officers, despite a lack of any public
benchmark. To fill this gap, we present MortarBench, a loan origination
agent benchmark. MortarBench uses a financial data synthesis and mutation pipeline to generate examples with broad edge case coverage that match real-world distributions and questions. We find that state-of-the-art large
language models (LLMs) perform poorly, with closed-source models achieving at most 77.1% exact match accuracy. We also discover systematic biases in LLM perception of foreignness related to non-English names. Noting these weaknesses, we introduce CRIT, a confidence calibration framework. Our method increases accuracy to 80.5% while improving risk management steering and reducing bias.
Read the full abstract ▾
All authors Matthew Toles, Yunan Lu, Manav Munjal, Bojun Liu, Yuanhao Deng, Stephanie Selig, Derek Rindner, Cheng Li, Zhou Yu
Machine Learning
Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting
Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen et al. (+1 more)
Multimodal time series
forecasting, which pairs numerical sequences with domain-relevant textual reports, promises to inject world knowledge into
forecasting pipelines. However, we uncover a critical failure mode in existing frameworks that we term text collapse: the text branch converges to a content-independent transformation, contributing negligible discriminative signal regardless of the input description. We argue that text collapse is a consequence of a fundamental asymmetry in time series
forecasting: the numerical input is strongly autocorrelated with the output, making the numerical backbone inherently dominant, while the text branch, despite carrying complementary and often critical information, is insufficiently utilized, leading to its systematic underexploitation. To address this, we propose REST-TS (Residual-Exclusive Supervision for Text in Time Series), which turns the asymmetry into a design principle: the numerical backbone produces its own independent numerical forecast, and the text branch is exclusively supervised to predict the structured components of the residual, the prediction gap that numbers cannot explain. Because no numerical pathway can reduce these losses, the text branch must extract genuine content from the input description. Evaluated across diverse real-world domains and backbone architectures, REST-TS achieves state-of-the-art performance and consistently demonstrates greater text-branch utilization than existing frameworks, providing strong empirical evidence that supervising the text branch on the residual compels it to extract genuine content from the input.
Read the full abstract ▾
All authors Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le
Machine Learning
Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen et al. (+1 more)
Time series
forecasting leverages historical patterns to predict future values, but traditional methods face challenges when dealing with complex, non-stationary patterns that are difficult to memorize during training.
Retrieval-augmented approaches have emerged as promising solutions by retrieving similar historical patterns to enhance predictions. However, existing
retrieval methods suffer from two fundamental limitations: spectral blindness, which overlooks critical frequency-domain characteristics that capture underlying periodic structures, and temporal recency, which treats all historical data equally without emphasizing recent, more relevant patterns. In this paper, we propose SpecReTF, a novel
retrieval method that addresses these issues by converting time series into windowed frequency representations, measuring similarity with a combined metric that captures both amplitude and phase information. To balance recency and historical context, we apply an exponential moving average weighting scheme that emphasizes recent windows. Extensive experiments on
benchmark datasets demonstrate that SpecReTF outperforms time-domain
retrieval methods, achieving superior
forecasting accuracy across diverse, non-stationary time series.
Read the full abstract ▾
All authors Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen, Hung Le
Machine Learning
Spectral Certificates and Projection-DPP Rounding for Determinantal MAP Selection
Richard Yi Da Xu
Selecting a fixed-size subset that maximizes the determinant of a positive semidefinite kernel is the MAP problem for a size-constrained determinantal point process and the classical maximum-
entropy sampling problem. Although this discrete problem is NP-hard, a classical spectral bound gives an efficiently computable ceiling using the leading
eigenvalues. The same ceiling is the exact optimum of the associated Stiefel relaxation, so the continuous problem is already solved by the leading eigenspace. We study what this eigenspace implies for discrete rounding. The leading eigenvectors induce a projection determinantal point process whose probability for a subset equals its squared coordinate volume. We prove that the gap between the determinant of any subset and the spectral ceiling is at most its negative log-probability under this distribution. Consequently, the integrality gap is bounded by the min-
entropy and equals it when the kernel rank matches the subset size. Projection-DPP rounding also has an expected gap bounded by the Shannon
entropy and admits a high-probability additive guarantee. These results identify leading-subspace localization, rather than
eigenvalue decay alone, as the geometry controlling roundability. This analysis yields CertDPP, a
matrix-free pipeline that computes the leading eigenspace, draws projection-DPP samples, optionally improves them by determinant-increasing swaps, and reports the gap from a verified spectral ceiling. Controlled experiments validate the
entropy identities, compare with exact MAP on small instances, and demonstrate linear scaling in the ground-set size for the rounding stage.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Potito Aghilar, Sabino Roccotelli, Stanislao Fidanza et al. (+3 more)
Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S). We prove this on a minimal 3-way XOR structural causal model: faithful indices such as Shapley-Taylor return zero per pair, whereas projective indices such as Shapley Interaction spread the third-order effect into pair scalars that conflate the three mechanisms. We introduce
Stochastic Hi-Fi, a post-hoc, retraining-free predictability decomposition that estimates per-feature U/R/S profiles by interventional masked inference. The
estimator provides exact interventional semantics, finite-sample Monte Carlo bounds, strict variance reduction from coupled diamond sampling, and uniform finite-vocabulary convergence. Across tabular SCMs,
Stochastic Hi-Fi recovers structure missed by scalar baselines (up to 411x larger interaction-magnitude recovery ratios). It also separates redundant and synergistic heads in the GPT-2 IOI
circuit. On NIH ChestX-ray14,
Stochastic Hi-Fi matches GradCAM on Pointing Game and improves substantially on Deletion AUC.
Read the full abstract ▾
All authors Potito Aghilar, Sabino Roccotelli, Stanislao Fidanza, Vito Walter Anelli, Sebastiano Stramaglia, Tommaso Di Noia
Machine Learning
FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning
Takanori Yoshimoto, Yang Hu, Naruya Kondo et al. (+1 more)
Latent actions provide a compact interface between action-free
video and downstream decision-making, yet existing Latent Action Models (LAMs) force every transition through a fixed-capacity bottleneck. We identify a bottleneck trade-off: overly tight codes can discard transition cues needed for action
alignment, while overly loose codes preserve additional transition variation that must be resolved when
alignment labels are scarce or narrowly distributed. FlexLAM replaces this fixed capacity with variable-length latent actions trained by nested dropout, yielding prefix-valid codes that capture compact transition structure first and add detail only when needed, without new architectures or losses. A single FlexLAM matches or surpasses separately trained fixed-capacity LAMs at every evaluated
token budget under standard scarce-label supervision and under a low-return single-task
alignment stress test, indicating that FlexLAM is not merely adjustable at inference time but learns a better latent-action interface at the same
token budgets. The same model supports inference-time
token-budget adjustment without retraining, and FlexLAM improves Ego4D transition reconstruction. These results suggest that variable-length latent actions are an architecture-free, drop-in upgrade to the fixed-capacity bottleneck in latent action models, latent-action world models, and
video-pretrained action interfaces.
Read the full abstract ▾
All authors Takanori Yoshimoto, Yang Hu, Naruya Kondo, Tatsuya Matsushima
Machine Learning
Thermodynamic Signatures of Reasoning: Free-Energy and Spectral-Form-Factor Diagnostics for Hallucination Detection in Large Language Models
Salim Khazem
Hallucination detection in large
language models (LLMs) is deployment-critical, and recent work shows that the spectrum of
attention-derived graph
Laplacians carries strong signal about
reasoning quality. Prior spectral diagnostics, however, summarize the
Laplacian spectrum by a handful of
eigenvalues or hand-picked scalars, leaving most of its structure unused. We propose Free-Energy Signatures (Fes), a spectral descriptor that treats each layer's
attention Laplacian as a
Hamiltonian and extracts its thermodynamic potentials partition function, free energy, spectral
entropy, heat capacity together with the random-
matrix-theory (RMT) spectral form factor. We prove three results: (i)~Lipschitz stability of Fes under
attention perturbation; (ii)~an expressiveness result showing that Fes enriches finite spectral summaries and approximates moment-derived spectral functionals under explicit regularity and grid-resolution assumptions; and (iii)~a finite-sample PAC bound on the AUROC of a training-free detector built from Fes. Empirically, across six open-weight LLMs and six
benchmarks, a lightweight probe on Fes descriptors achieves the strongest aggregate AUROC among
attention-spectral baselines, improving over LapEig by $+6.5$ AUROC points and over GoR-4 by $+2.4$ points on average, while requiring no update to the underlying LLM. In the fully unsupervised setting, an RMT-deviation score achieves mean AUROC $0.71$, providing a label-free but weaker detector. A complementary RMT analysis shows that correct generations exhibit more Wigner-Dyson like spectral statistics, whereas
hallucinations exhibit more Poisson-like statistics. The anonymized code and config are provided in the supplementary material.
Read the full abstract ▾
Machine Learning
VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving
Manish Acharya, Zhenyu Liao, Yueke Zhang et al. (+3 more)
LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back into proof search through a two-phase protocol: Best-of-N sampling first, then a critic-guided MCTS pass that ingests Phase 1 failures as explicit negative examples. The protocol preserves every
theorem solved by its own Phase 1 sweep, so Phase 2's additional solves are attributable to feedback-driven exploration. VERITAS reaches 40.6% on miniF2F (vs. an independently run Best-of-5 at 36.9%, Portfolio 26.2%) and 7.3% on VERITAS-CombiBench, a 55-
theorem combinatorics
benchmark we release on which Best-of-5 (1.8%) falls below Portfolio (3.6%), exposing that unguided sampling hurts when correct lemma names must be recovered iteratively from verifier feedback. Artifacts are available on GitHub.
Read the full abstract ▾
All authors Manish Acharya, Zhenyu Liao, Yueke Zhang, Kevin Leach, Yu Huang, Yifan Zhang
Machine Learning · Cross-listed from cs.CL
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
Denis Peskoff, Joe Barrow, Christopher Vu et al. (+1 more)
Progress in legal AI increasingly depends on access to authoritative legal text at scale. Yet one of the most consequential layers of American law remains largely absent from existing machine-readable corpora: local ordinances. Local codes govern zoning, housing, business licensing, public health, noise, animal control, and many other domains of everyday regulation, but they are fragmented across vendor platforms designed for human browsing rather than bulk research access. We introduce LOCUS - the Local Ordinance Corpus for the United States - a comprehensive corpus and county-harmonized access layer for U.S. municipal and county ordinance codes. The raw corpus, available for release to researchers, represents nearly all publicly available municipal and county ordinance codes. The resulting raw corpus contains codes from 9,239 cities and counties. A smaller county-harmonized LOCUS access layer provides coverage for the largest 2,309 of 3,144 U.S. counties, accounting for a majority of the population. We use OCR to handle the myriad of document formats that have kept the law from being a public resource. We release the corpus with coverage metadata to support reproducibility, downstream legal AI research, and the incremental expansion of machine-readable access to local law. We train a collection of ModernBERT-based classifiers and scorers to facilitate analyzing U.S. local law among several dimensions, such as opacity and paternalism, that have not previously been studied at this scale. LOCUS-v1 and its derivative models are available at: https://huggingface.co/
datasets/LocalLaws/LOCUS-v1
Read the full abstract ▾
All authors Denis Peskoff, Joe Barrow, Christopher Vu, Diag Davenport
Machine Learning · Cross-listed from astro-ph.IM
The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning
V. Samuel Pérez-Díaz, Vinay L. Kashyap, Joshua D. Ingram et al. (+6 more)
We present a framework to cross-match sources from the Chandra Source Catalog (CSC v2.1) with optical sources from
Gaia Data Release 3. Unlike purely spatial approaches, we use source properties such as magnitudes, colors, and distances to identify true counterparts, detect chance coincidences, and resolve ambiguities when multiple plausible candidates exist. We define a training set of high-confidence matches using NWAY, a
Bayesian cross-matching framework that accounts for positional errors and source densities. We train a gradient-boosted classifier (LightGBM) on a variety of features from both catalogs. Of the ~$254$k unique X-ray sources, we find counterparts for ~$113$k sources, of which plausible multiple counterparts are found for ~$7$k. We find no counterparts for ~$20$k sources for which separation-based cross-matching does find a match, and attribute half of these to chance coincidences. We validate the pipeline on the Chandra Orion Ultradeep Project (COUP), where the machine-learning matches reproduce 95% of NWAY cross-matches without using any positional information. We release a catalog of the ~$113$k Chandra-
Gaia counterparts, together with ~$7$k alternative matches and ~$20$k ambiguous NWAY associations, supporting future population studies of sources detectable by both Chandra and
Gaia. We discuss limitations and provide a generalization of the framework that is applicable in other cross-matching scenarios.
Read the full abstract ▾
All authors V. Samuel Pérez-Díaz, Vinay L. Kashyap, Joshua D. Ingram, David Fouhey, Juan Rafael Martínez-Galarza, Pavlos Protopapas, Jeremy J. Drake, Dong-Woo Kim, Cecilia Garraffo
Machine Learning
UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang et al. (+1 more)
Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especially during the early stages of learning. We introduce a model-based approach that actively directs exploration by jointly
reasoning over uncertainties in the reward, dynamics, and value functions. Our method, Uncertainty-Balanced Preference Planning (UBP2), uses ensembles of reward, dynamics, and value function models to evaluate candidate trajectories according to a unified score that combines expected reward, terminal value, and epistemic uncertainty. Planning under this objective yields an explicit tradeoff between exploitation and information acquisition without requiring ad hoc exploration heuristics. Under standard regularity assumptions, we establish sublinear regret guarantees for both finite-horizon and infinite-horizon settings. Empirically, experiments on the Meta-World
benchmark show UBP2 achieves substantially higher sample efficiency than model-free preference-based methods and non-optimistic model-based baselines.
Read the full abstract ▾
All authors Mohamed Nabail, Leo Kaixuan Cheng, Jingmin Wang, Nicholas Rhinehart
Machine Learning
Explaining Attention with Program Synthesis
Amiri Hayes, Belinda Z Li and Jacob Andreas
A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this paper, we propose an approach for approximating the behavior of components of deep networks with executable programs. We focus on
attention heads in
transformer language models. For a given head, we first compute its associated
attention matrices on a collection of randomly selected training examples. Next, we
prompt a pre-trained
language model with a summary of these
matrices, and instruct it to generate a set of Python programs that can reproduce the associated
attention patterns given only text from the input sentence. Finally, we re-rank programs according to how well our final set of programs predict behavior on held-out inputs. We demonstrate that a set of fewer than 1,000 such generated programs can reproduce the
attention patterns of heads in GPT-2, TinyLlama-1.1B, and Llama-3B, achieving an average Intersection-over-Union similarity above 75% on TinyStories. Moreover, the best-fit programs can replace neural
attention heads without substantially affecting model behavior: replacing 25% of
attention heads with programmatic surrogates across the three models incurs only a 16% average perplexity increase, while maintaining performance on a variety of downstream question answering
benchmarks. This work contributes a scalable pipeline for reverse-engineering
attention heads in
transformer models using human-readable, executable code, advancing a path toward symbolic transparency in neural models.
Read the full abstract ▾
Machine Learning
Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation
Ruida Wang, Rui Pan, Pengcheng Wang et al. (+2 more)
Enhancing the formal math
reasoning capabilities of Large
Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-of-the-art Auto-Regressive (AR) LLMs for formal
theorem proving, these models suffer from inherent limitations. Their next-
token prediction generation methods may yield suboptimal performance due to the challenges of long-range coherence and the compounding of errors over long sequences. Recent advancements in
diffusion LLMs (dLLMs), which generate text through iterative denoising of a multi-
token block, offer a promising alternative. However, the application of dLLMs to formal mathematics, where maintaining long-range coherence is critical, remains largely understudied. To address the challenges above, we propose **
Diffusion-Proof**, to the best of our knowledge, the first framework to train and apply dLLMs for formal
theorem proving. Our frameworks contain training and inference methods for two models. The first one is *dLLM-Prover-7B*, which performs whole-proof writing with long-range coherent tactic usage. The second one is *dLLM-Corrector-7B*, which is a novel large block
diffusion-based correction model. It leverages the in-filling capabilities of dLLMs to perform local proof correction using bi-directional information. Extensive experiments demonstrate that **
Diffusion-Proof** relatively significantly outperforms the AR LLM baseline trained under the same
dataset. **
Diffusion-Proof** achieves an absolute improvement of **1.61%** on ProofNet-Test and **6.14%** on MiniF2F-Test
benchmarks compare to the baseline. Notably, **
Diffusion-Proof** successfully resolves one IMO problem that more advanced thinking model DeepSeek-Prover-V2-7B could not solve, showcasing the unique advantage of dLLMs in formal
theorem proving.
Read the full abstract ▾
All authors Ruida Wang, Rui Pan, Pengcheng Wang, Shizhe Diao, Tong Zhang
Machine Learning
P-K-GCN: Physics-augmented Koopman-enhanced Graph Convolutional Network for Deep Spatiotemporal Super-resolution
Xizhuo Zhang, Zekai Wang, Fei Liu et al. (+1 more)
High-fidelity simulation of spatiotemporal dynamics is computationally prohibitive, necessitating efficient super-resolution techniques to reconstruct high-resolution data from coarse-grained inputs. Traditional data-driven methods often lack physical constraints, and simple physics-informed learning struggles with irregular spatial geometries and intricately evolving temporal dynamics. To tackle these challenges, we propose a Physics-augmented Koopman-enhanced Graph Convolutional Network (P-K-GCN) for spatiotemporal super-resolution on irregular geometries. Specifically, a continuous spline-based GCN is first designed to extract spatial dependencies directly from coarse graph, and Koopman operator theory is incorporated to project the nonlinear dynamics into a compact latent space where temporal progression is linearized. Second, we augment the optimization objective with a physics-based loss to force the data-driven reconstructions to adhere to physical laws for improving predictive fidelity and robustness. Finally, we provide a rigorous theoretical analysis, establishing that the physics augmentation and Koopman regularization mathematically guarantees a reduction in super-resolution error by diminishing Rademacher complexity and tightening generalization bounds. We evaluate our framework on reconstructing spatially high-resolution cardiac electrodynamics across a 3D heart geometry from sparse low-resolution measurements. Numerical experiments demonstrate that our method achieves superior accuracy compared to baseline models.
Read the full abstract ▾
All authors Xizhuo Zhang, Zekai Wang, Fei Liu, Bing Yao
Machine Learning · Cross-listed from physics.ao-ph
Optimal scenario design for climate emulation
Christopher B. Womack, Shahine Bouabid, Andrei Sokolov et al. (+4 more)
As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate
climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training
datasets themselves can be optimized to improve generalization. We introduce a method to create
datasets that produce emulators capable of generalizing to new, structurally different scenarios absent from the training data. We use a differentiable Simple
Climate Model (SCM) to calculate the sensitivity of emulator loss to perturbations in the training data, iteratively updating the training data to maximize emulator skill. For an SCM, training on one scenario optimized in this fashion outperforms an emulator trained on six standard ScenarioMIP pathways. We achieve this higher predictive skill despite training on a smaller
dataset, finding that our emulator successfully isolates distinct physical behaviors of different
climate forcing
agents (e.g., greenhouse gases vs. aerosols) without single-forcing runs. We then demonstrate that scenarios optimized using an SCM, when used to drive an intermediate-complexity
climate model, produce a training
dataset that yields a more skillful emulator than training on ScenarioMIP outputs. Our results suggest that, in the compute-constrained environment of running full-scale
climate models, generating a small number of dynamically rich scenarios provides greater marginal value for emulation and characterizing system responses than expanding the suite of traditional emissions pathways.
Read the full abstract ▾
All authors Christopher B. Womack, Shahine Bouabid, Andrei Sokolov, Popat Salunke, Glenn Flierl, Sebastian D. Eastham, Noelle E. Selin
Machine Learning · Cross-listed from cs.CV
Confidence is Not Reliability: Rethinking MC Dropout in Brain Tumour Segmentation
Xin Ci Wong, Duygu Sarikaya, Kieran Zucker et al. (+2 more)
Glioma
segmentation in multiparametric MRI is a critical component of treatment planning. A
segmentation model that fails silently on treatment-critical sub-regions represents a patient safety risk that overlap-based metrics such as Dice scores cannot expose. We ask whether voxel-level uncertainty estimation via Monte Carlo (MC) Dropout can reliably identify
segmentation errors in clinically critical sub-regions, and whether calibration failure modes are detectable from standard reporting metrics alone. In an empirical two-model case study on 126 BraTS21 patients, we evaluate a high-performance pretrained SegResNet and a locally trained UNet with residual units (UNet-Res). MC dropout preserved
segmentation accuracy ($|\Delta \text{Dice}|$ $<0.01$) while achieving strong uncertainty-error
alignment (AUROC for
entropy (H) $\approx$0.97), indicating uncertainty correctly ranks erroneous voxels above correct ones.
Entropy-based patient stratification identified a high-uncertainty subgroup with substantially lower
segmentation performance (median whole-tumour Dice $0.835$ vs. $0.925$), supporting uncertainty as a practical triage signal. However, global
alignment can mask important region-specific differences. Despite similar AUROC, UNet-Res exhibited near-zero enhancing tumour
entropy ($0.054$) and Expected Calibration Error (ECE) of $0.915$, with a Dice of only $0.714$, indicating severely miscalibrated confidence on the most clinically critical sub-region, a failure mode invisible to standard Dice and AUROC reporting. These findings demonstrate that strong uncertainty-error
alignment is necessary but insufficient for clinical safety: sub-region-specific calibration assessment must accompany AUROC evaluation when selecting models for clinical deployment.
Read the full abstract ▾
All authors Xin Ci Wong, Duygu Sarikaya, Kieran Zucker, Marc De Kamps, Nishant Ravikumar
Machine Learning
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Nikita Kachaev, Andrey Moskalenko, Matvey Skripkin et al. (+10 more)
Embodied Vision-
Language-Action (VLA) models are typically obtained by fine-tuning powerful pretrained VLMs on robotics data, yet it is unclear how much commonsense and factual knowledge they retain after adaptation. Failures on knowledge-sensitive tasks are ambiguous, conflating missing knowledge with poor generalization of low-level control. We introduce Act2Answer, a lightweight protocol that adapts VLM knowledge
benchmarks to VLA evaluation by requiring
agents to answer through action. Each question becomes a short tabletop episode where the
agent performs a single object-placement action to select among candidate answers, yielding an action-grounded success rate with reduced control confounds. We curate a test suite of such environments across diverse commonsense and world-knowledge categories and introduce layerwise intent probing to localize answer-relevant information across the VLM backbone and action head. In a large-scale study of 7 VLA models and 9 VLM baselines, we systematically rank models across categories, finding that VLAs show solid performance on simple concepts while exhibiting larger gaps on richer semantic categories relative to their source VLMs, that VQA co-training is associated with better knowledge retention, and that answer-relevant signals peak in middle VLA layers but attenuate in upper layers. Act2Answer is available at https://tttonyalpha.github.io/act2answer/.
Read the full abstract ▾
All authors Nikita Kachaev, Andrey Moskalenko, Matvey Skripkin, Nikita Kurlaev, Daria Pugacheva, Albina Burlova, Mikhail Kolosov, Denis Shepelev, Andrey Kuznetsov, Elena Tutubalina, Aleksandr I. Panov, Alexey K. Kovalev, Vlad Shakhuro
Machine Learning
Risk Stratification for ICU Delirium using Pervasive Ambient Sensing Information
Jiaqing Zhang, Sabyasachi Bandyopadhyay, Miguel Contreras et al. (+8 more)
Delirium is a common and serious complication in the Intensive Care Unit (ICU), associated with increased morbidity, prolonged hospital stays, and higher healthcare costs. Despite its prevalence, early prediction and prevention remain challenging. Environmental factors such as ambient sound and light may influence the onset of delirium, yet they are often overlooked in risk assessments. In this study, we examined whether light intensity and sound pressure levels can independently predict delirium across multiple prediction horizons. We evaluated four efficient sequential neural network models on data collected from 9 ICUs across 309 patients to predict delirium for 10 prediction-window sizes. We reported feature importance and direction of influence using Shapley Additive Explanations analysis. The convolutional model achieved the strongest discrimination, with AUC = 0.80 on sound data and on combined data. Sound features were the dominant predictors overall. Integrating sound with light improved short-term ($<1$ week) prediction, with the combined model assigning the highest risk immediately after the sensing period. These findings suggest that passive ambient sensing, especially sound, can add a clinically meaningful, interpretable signal for delirium risk estimation and offer a practical pathway to enrich
multimodal ICU prediction and prevention strategies.
Read the full abstract ▾
All authors Jiaqing Zhang, Sabyasachi Bandyopadhyay, Miguel Contreras, Jessica Sena, Yuanfang Ren, Andrea Davidson, Ziyuan Guan, Tezcan Ozrazgat-Baslanti, Subhash Nerella, Azra Bihorac, Parisa Rashidi
Machine Learning · Cross-listed from cs.AI
NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning
Daniel Romero Schellhorn, Till Mossakowski and Björn Gehrke
Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. NeSyCat has so far lacked an account of predicates and functions learned by neural networks. We provide NeSyCat Torch as the missing link and interpret computational symbols via neural networks, implementing the framework in probabilistic programming and tensor-based backends. We use the distribution monad for reference semantics and metric evaluation, and complement it by a monad for numerically stable, differentiable training: the lazy log-tensor monad over the log-semiring. For efficient training in batches, we furthermore employ a batch monad. The axioms are the source code: written once in monad-based do-notation, monadic bind performs marginalisation, lazily
pruning unneeded branches. On MNIST addition, our HaskTorch, JAX, and PyTorch implementations outperform LTN and DeepProbLog in speed and accuracy, while achieving nearly the accuracy of DeepStochLog. However, unlike DeepStochLog, we stay in a uniform framework that applies to many first-order NeSy approaches. Namely, the construction is parametric in the monad; instantiating it with, e.g., the Giry monad extends the approach to continuous probability (working out a neural representation here is left for future work).
Read the full abstract ▾
Machine Learning · Cross-listed from eess.IV
Beyond Algorithms: Conceptual Innovation in Medical Imaging AI
Mark A. Anastasio
Artificial intelligence has driven rapid progress in medical imaging research, producing increasingly sophisticated
algorithms and steady improvements on
benchmark tasks. However, this
algorithm-centric trajectory has also revealed a growing imbalance: while computational methods advance rapidly, the conceptual foundations that define imaging tasks, evaluation metrics, and clinical meaning sometimes remain underexamined. In this Perspective, we distinguish algorithmic innovation, which focuses on improving computational implementations and performance within a fixed problem definition, from conceptual innovation, which reframes what problems are posed, how success is measured, and why an approach is clinically relevant. We argue that prevailing incentive structures, training pathways, and publication norms disproportionately reward algorithmic novelty, particularly for early-career researchers, while at times undervaluing conceptual contributions that are essential for scientific maturation and clinical translation. Through representative examples from medical imaging AI, we show how insufficient conceptual grounding can lead to misaligned objectives, fragile generalization, and limited real-world impact. We conclude with actionable recommendations for researchers, mentors, reviewers, and journals to better recognize, support, and integrate conceptual innovation alongside algorithmic advances.
Read the full abstract ▾
Machine Learning
Structured Inference with Large Language Gibbs
Sanghyeok Choi, Henry Gouk and Esmeralda S. Whitammer
The knowledge encoded in large
language models (LLMs) can serve as a substrate for structured
reasoning over variables describing a complex world, but accessing this knowledge in a probabilistically coherent manner poses a difficult inference problem. We propose Large
Language Gibbs, a scheme for structured probabilistic inference that uses conditional distributions of an LLM as transition operators. Rather than sampling structured objects through single-pass autoregressive generation, we iteratively resample individual variables conditioned on others using an LLM's next-
token conditionals. This approach avoids order-dependent biases and produces a stationary distribution that reflects a compromise between all local conditionals. We apply this approach to sampling from synthetic distributions, consistent
reasoning tasks, and
Bayesian structure learning. The results suggest that the use of LLM conditionals in MCMC is a practical alternative to one-pass generation for structured probabilistic inference under a world prior accessible through noisy LLM conditionals.
Read the full abstract ▾
Machine Learning
Detecting Hidden ML Training With Zero-Overhead Telemetry
Robi Rahman and Sabiha Tajdari
Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable. We evaluate the
adversarial robustness of GPU workload classification using only zero-overhead,
privacy-preserving NVML telemetry: content-agnostic signals that observe physical effects of computation without accessing model weights, training data, or hyperparameters. Across 5 rounds of monitor-evader iteration, we evaluate 20 evasion strategy families on 9 GPU models spanning 4 architecture generations. We develop a classifier that achieves 98.2% binary accuracy at identifying training workloads across the whole corpus, and 43-87% accuracy against the most challenging unexpected workloads even when they are adversarially disguised.
Read the full abstract ▾
Machine Learning
SCAN: Enhance Time Series Anomaly Detection via Multi-Scale Neighborhood-Centered Clustering
Xingze Zheng, Hanyin Cheng, Siyuan Wang et al. (+4 more)
Time series anomaly detection plays a crucial role in a wide range of real-world applications. Reconstruction-based methods have become the mainstream paradigm, but they suffer from over-generalization and under-generalization problems, which are challenging to balance. To address this, we introduce multi-scale clustering to enhance reconstruction-based methods. At the representation level, we integrate the cluster center representations of normal patterns to constrain the model to target representative normal patterns for reconstruction, preventing dominance of powerful capacity and representation capability. At the anomaly criterion level, we derive anomaly confidence score based on cluster membership probability and combine it with reconstruction error, providing dual criteria for detection. Furthermore, the effectiveness of the cluster center representations and anomaly confidence score depends on the clustering performance. Accordingly, we extract neighborhood-centered representations for multi-view clustering to improve clustering performance. Extensive experiments on multiple real-world
datasets from diverse application domains demonstrate the state-of-the-art performance of SCAN.
Read the full abstract ▾
All authors Xingze Zheng, Hanyin Cheng, Siyuan Wang, Yiting Hao, Peng Chen, Yuan Jun, Yang Shu
Machine Learning · Cross-listed from cs.CV
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
Bartłomiej Baranowski, Dave Zhenyu Chen and Matthias Nießner
Existing approaches to 3D scene understanding in
Vision-
Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial
reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position
embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated
reasoning from a specific viewpoint, a common requirement in robotics and
embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial
reasoning tasks, with answer distributions controlled to reduce spatial
reasoning shortcuts. OneCanvas achieves state-of-the-art results on SQA3D and VSI-Bench and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than its competitors closest in
benchmark performance.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.comp-ph
Acceleration of an algebraic multigrid pressure solver using graph neural networks
Eric Chillón, Artur K. Lidtke, Nguyen Anh Khoa Doan et al. (+1 more)
Solving the pressure-Poisson equation remains the primary computational bottleneck in incompressible unstructured flow solvers primarily due to the inherent sensitivity of traditional linear solvers to mesh irregularities. This work introduces a data-driven algebraic multigrid (AMG) smoother that uses a modified graph convolutional isomorphism network (GCIN). The graph neural network predicts optimal
polynomial coefficients to construct a sparse pseudo-inverse operator across diverse grid
topologies. The coefficients are optimized to reduce the residual after each V-cycle iteration. By directly capturing the algebraic structure of the system from the sparse coefficient
matrix, the proposed method maintains the solver's linearity while adapting to local anisotropies in unstructured grids. Our framework demonstrates significant performance gains by reducing the number of V-cycles required for a given tolerance and delivering wall-clock speedups from 4% to 37% across diverse
benchmarks. Notably, the model exhibits robust generalization by maintaining efficiency on meshes up to 128 times larger than those seen in training, and by accelerating the solver's convergence on unseen industry-relevant problems such as the AirfRANS
dataset.
Read the full abstract ▾
All authors Eric Chillón, Artur K. Lidtke, Nguyen Anh Khoa Doan, Bernat Font
Machine Learning · Cross-listed from cs.CV
Transformer Geometry Observatory TGO-I: Spectral Geometry Observatory
Kaustubh Kapil and Kishor P. Upla
Despite the widespread adoption of
Vision Transformers (ViTs) and their success across numerous computer
vision applications, the fundamental understanding of their dimensional and representational geometry remains relatively underexplored. To address this gap, we introduce
Transformer Geometry Observatory (TGO), a systematic framework of experiments and analysis pipelines designed to investigate the representational geometry and dynamics of
Vision Transformers. TGO-I, the first installment of the framework, focuses on the spectral geometry of ViT representations. Using a ViT-Small/16 model trained on ImageNet-100, we analyze Effective Rank, Stable Rank, Participation Ratio, Spectral
Entropy, Spectral Flatness, Spectral Anisotropy, covariance structure, eigenspectra, and singular value spectra throughout training. Our results reveal a consistent increase in dimensional utilization, accompanied by decreasing anisotropy, increasing spectral
entropy, increasing participation ratio, and progressively flatter eigenspectra. Contrary to the common intuition that training should concentrate information into a small number of dominant directions, we observe a progressive redistribution of variance across representational dimensions. This phenomenon is particularly pronounced in the final CLS
token representation, which exhibits the highest effective dimensionality and lowest anisotropy within the network.
Read the full abstract ▾