Sound
Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?
Serli Kopar, Alkis Koudounas, Roshan P. Rane et al. (+3 more)
Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors. We ask whether such factors are merely encoded in SSL representations or can systematically alter predictions. Using ADReSSo and three large SSL backbones, we apply controlled noise and reverberation interventions to participant-
speech-only, non-
speech, and full-recording audio. We combine layer-wise linear decoding, input- and representation-space interventions, and
geometric alignment analysis to distinguish acoustic decodability from influence on AD prediction. Our results show that controlled acoustic interventions alter AD predictions across all three SSL backbones. Noise, despite showing no significant diagnostic-group difference in the original data, produces the strongest intervention effects. Importantly, these effects are systematically structured relative to the classifier's decision direction, replicate on the held-out test set and reverse when the representation-space intervention direction is reversed. Together, these findings show that high predictive performance and the absence of a significant diagnostic-group difference in a measured acoustic factor are not sufficient for robustness. We argue that intervention-based robustness tests should become standard for trustworthy clinical
speech models.
Read the full abstract ▾
All authors Serli Kopar, Alkis Koudounas, Roshan P. Rane, Sam Gijsen, Paula A. Perez-Toro, Kerstin Ritter
Artificial Intelligence
Temporal-Difference Learning for Dragonchess
Jim O'Connor, Annika Hoag, Sarah Goyette et al. (+1 more)
Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The game challenges players with its unique board structure and computational load, making it an ideal setting to study how adaptive methods can update evaluation heuristics in novel environments. In this work we re-implement the Dragonchess engine, changing it from a PyGame engine to C++. This enables faster gameplay, allowing us to run 10,000 games with confidence intervals and significance tests, rather than a single small tournament. Both adaptive methods outperform all other
agents in the round-robin tournament. Our results showed that there is no significant difference in the performance between the evolved and learned evaluations. This research establishes the efficacy of adaptive methods in structurally complex, novel game domains.
Read the full abstract ▾
All authors Jim O'Connor, Annika Hoag, Sarah Goyette, Gary B. Parker
Machine Learning · Cross-listed from math.OC
Optimal Stochastic Bilevel Optimization with First-Order Oracles
Linxuan Pan and Junchi Yang
We study nonconvex–strongly-convex bilevel optimization under a
stochastic first-order oracle. We introduce MRT-FD, a single-loop first-order method that simultaneously tracks the upper-level variable, the lower-level solution, and the auxiliary response arising from implicit differentiation of the hyperobjective. MRT-FD performs one update of each variable per iteration and approximates the second-order derivative actions using order-$p$ finite differences. For any fixed finite smoothness order $p\ge1$ in the lower-level variable, MRT-FD finds an $\varepsilon$-stationary point using $\mathcal{O}(\varepsilon^{-4-2/p})$
stochastic gradient queries. We also prove a matching $\Omega(\varepsilon^{-4-2/p})$ oracle lower bound. The lower-bound construction starts from a hard nonconvex minimization chain with a stronger
stochastic oracle, and lifts it to a bilevel problem through a sinusoidal coupling with a scalar lower-level variable. Consequently, the dependence on $\varepsilon$ is optimal for every fixed finite $p$, closing the upper–lower complexity gap in this
stochastic first-order oracle setting.
Read the full abstract ▾
Artificial Intelligence
On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models
Haochen Zhang, Jiaheng Guo, Zhen Xu et al. (+4 more)
A time series world model (TSWM) predicts a controlled system's state from its observed history and planned actions and exogenous inputs. Current approaches build forecasters with actions as
covariates, trained and evaluated on prediction error under the executed plan. Yet world models compare unexecuted plans, but their responses to changed plans remain untested. We ask which design choices matter and whether accurate forecasters respond to changed plans as real systems do. We address both with a formalization and
benchmark. The formalization separates state, actions and exogenous inputs, distinguishes continuous, mode and event actions, and introduces mechanism consistency, a metric built on declared action-state relations with known directions, such as a vasopressor raising blood pressure: it checks whether shifting an action moves the forecast in the declared direction. The
benchmark consolidates eight public
datasets with real actions from engineered infrastructure and clinical care, varying prediction space, plan fusion and plan encoding across seven backbones and five seeds. First, a frozen latent prediction space lowers MAE by 9.9% over observation space and gated output fusion lowers it by 12.7% over input concatenation on average, with both improving all eight
datasets; temporal plan encoding changes average MAE by at most 2.2%. Second, prediction error and mechanism consistency diverge: the lowest-error configuration is at or below chance in consistency on four of five
datasets with declared mechanisms, and no design choice avoids this. Finally, directional supervision, a loss penalizing the wrong-signed part of the response to a shifted action, significantly raises consistency on penalized mechanisms with no change in MAE. Together they give TSWMs a recipe: a frozen latent space and output-side fusion for accuracy, and a training objective for mechanism consistency.
Read the full abstract ▾
All authors Haochen Zhang, Jiaheng Guo, Zhen Xu, Zachary Plotkin, Nicholas Konz, Zhen Tan, Tianlong Chen
Machine Learning · Cross-listed from physics.ao-ph
Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography
Alberto Pennino, Francesco Zanetta, Michele Cattaneo et al. (+28 more)
We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and global forecasts on a 31 km mesh. The system comprises two independently trained stretched-grid Graph
Transformer models with encoder-processor-decoder architecture, developed in the Anemoi framework: a 6-hourly autoregressive forecaster and a temporal downscaler reconstructing hourly forecasts between the forecaster's steps. Its training curriculum includes pre-training on ERA5 reanalysis data, followed by training on a 20-year kilometre-scale regional reanalysis, and finally fine-tuning on operational kilometre-scale analyses. Verified over one year against operational analyses and surface station observations, Varda-single is competitive with or improves on MeteoSwiss' operational numerical weather prediction baselines for most headline scores and variables. It broadly matches the skill of the high-resolution 1 km ICON-CH1-EPS control at lead times up to +33 h and generally outperforms the 2 km ICON-CH2-EPS control at lead times up to +120 h. Despite competitive aggregate scores, Varda-single underestimates some local wind maxima and produces overly smooth convective precipitation fields, consistent with the smoothing associated with squared-error training. To gain insight into the model's behaviour, we investigate three case studies beyond the aggregated headline scores, and find particular weaknesses in Varda-single's representation of local winds over complex terrain. Varda-single represents an important step in the development of high-resolution ML
forecasting over complex terrain, in complementing the operational regional numerical weather prediction models of MeteoSwiss with data-driven models and in providing a pretrained model for researchers and user-specific applications.
Read the full abstract ▾
All authors Alberto Pennino, Francesco Zanetta, Michele Cattaneo, Claire Merker, Radi Radev, Jonas Bhend, Louis Frey, Hugues de Laroussilhe, Ophélia Miralles, Carlos Osuna, Daniele Nerini, Andreas Pauling, Daniel Hupp, Ulrich Hamann, Mary McGlohon, Marti Bosch, Luca Lanzilao, Marco Arpagaus, Lukas Jansing, Daniel Leuenberger, Mark A. Liniger, Katrin Ehlert, Matthew Chantry, Håvard Homleid Haugen, Gert Mertes, Ana Prieto Nemesio, Mario Santa Cruz, Jasper Wijnands, Gabriel Moldovan, Harrison Cook, Oliver Fuhrer
Artificial Intelligence
Code Owns the Simulation, Jev Owns the Evaluation
Yaodong Yang, Hongyao Tang, Yi Ma et al. (+4 more)
Judgment models such as \jev{} return, in a single call and without
reasoning text, a probability for each described option. This makes them attractive as an
agent's action-selection layer, but it is unclear which decisions they can be trusted with. We test \jev{} on reflection tests, one-shot
matrix games, the text game ALFWorld and
robot control, and find a sharp boundary. \jev{} succeeds when the right option can be judged from what the input describes, which we call evaluation. Specifically, it solves 99% of the counterintuitive Cognitive Reflection Test questions. However, it fails when the right option depends on simulation (i.e., predicting something not in the input), such as the opponent's action or the subgoal that must come first. In games, \jev{} plays suboptimally as if its rational opponent acted at random, because the opponent's action is not given. In ALFWorld, \jev{} favors commands that mention an object or place named in the task description. For example, given the task “put a clean knife in the drawer”, \jev{} carries an unwashed knife straight to the drawer instead of first washing it at the sink. Surprisingly, many of these failures are not due to a lack of knowledge. Asked separately what the opponent will do, \jev{} usually answers correctly, and it responds well given the opponent's action. It fails when one call must both perform the simulation and evaluate based on it. This suggests letting code make the prediction or simulation. When code supplies it, such as a lookahead in ALFWorld and physics simulation in
robot control, \jev{} becomes an expert controller through its general evaluation ability.
Read the full abstract ▾
All authors Yaodong Yang, Hongyao Tang, Yi Ma, Xingyu Fan, Weixun Wang, Jinpeng Li, Tianpei Yang
Artificial Intelligence
Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills
Ngoc Phuoc An Vo, Aarya Doshi and Vadim Sheinin
Enterprise AI
agent skills evolve as tool APIs, models, and specifications change, yet final-output evaluation can miss process-level behavioral drift. We present a continuous evaluation framework combining outcome-level and process-level checks, applied to Revenue and Productivity variants of a Business Value Determination skill in an enterprise Value Aware Resiliency system. The framework independently computes per-run ground truth, materializes reusable template tests, and evaluates tool selection, arguments, execution order, and database integrity through programmatic checks and a narrowly scoped LLM judge. We evaluate 240 trials across two skills, two specification variants, two
agent harnesses, and three models. Of 175 trials passing all applicable final numerical checks, 162 (92.6 percent; Wilson 95 percent CI: 87.7-95.6 percent) contained another evaluator-detected deviation. Under a broader seven-check final-state definition, 151 of 164 passing runs (92.1 percent; 95 percent CI: 86.9-95.3 percent) still violated a trajectory check. Dependency attribution reduced a mean of 6.34 failed checks per run to 2.65 roots. Specification sensitivity varied by model and harness, with exploratory bootstrap interaction intervals excluding zero for all three Revenue comparisons and one of three Productivity comparisons. Runtime-resolved templates provided reusable regression coverage across the evaluated configurations; longitudinal validation under actual API
evolution remains future work.
Read the full abstract ▾
Machine Learning
Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention
Michael Fore, James Mason Inder, Mrishika Nair et al. (+2 more)
Group
attention, introduced by the time series
forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both multivariate (MV) and in-context learning (ICL)
forecasting. Rather than evaluating this cross-variate
attention design as a whole, we ask which part of the mechanism earns the benefit and probe its applicability to both MV and ICL regimes. By editing the
attention matrix $\alpha$ at inference we separate the two pathways a head comprises: V/O, which projects a weighted summary of the group, and Q/K, which decides the weights. Uniform pooling (V/O without any Q/K weighting) is positive on 18 of our 20 sensor-network configurations, while the learned weighting (Q/K) splits by group type: its contribution is positive or negligible for MV, but materially degrades 8 of the 10 sensor-network ICL configurations, leaving 4 of them worse than univariate inference. By isolating the impact of different layers, we find that uniforming $\alpha$ in the first block alone improves every ICL configuration we test.
Read the full abstract ▾
All authors Michael Fore, James Mason Inder, Mrishika Nair, Praneetha Vaddamanu, Sharlina Keshava
Computation and Language
Haricharan Balasundaram and V. Arvind Rameshwar
Language model (LM)
alignment broadly aims to perturb a given LM $Q$ into an aligned LM $q$ such that i) the outputs produced by $q$ and $Q$ are 'close' in probability, ii) $q$ has a higher expected reward than $Q$. Two common techniques for LM
alignment are: KL-constrained RL, which requires knowledge of the LM distribution and is computationally expensive, and the best-of-$n$
algorithm, which requires only sampling from the LM. The work of Yang et al. established asymptotic closeness between the distributions produced by the two
alignment methods for an $m$–length i.i.d.
token sequence output by the LM, in the limit as $m$ increases to infinity. However, the i.i.d. assumption is not representative of practical LMs, whose output sequences often have
memory. In this paper, we extend the asymptotic closeness result to the case when the $m$–length
token sequence outputted by the LM is Markovian. Further, for finite-length output sequences – particularly, when $m=1$ – we provide a complete characterization of LM distributions and reward functions for which the KL-divergence between the distributions produced by the two
alignment methods is zero – a question first posed in Yang et al.
Read the full abstract ▾
Machine Learning
Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings
Kevin Tirta Wijaya, Alston Lo, Michael Sun et al. (+2 more)
Modern computational methods can now propose candidate molecules, materials, and other scientific designs at an unprecedented scale, creating a validation congestion where candidates are abundant, but experimental capacity to physically evaluate them remains scarce. Discovering novel scientific designs has therefore become increasingly dependent on curation: selecting a small set of promising designs for slow and costly experiments. Existing curation methods typically rely on data-driven regression models that predict absolute scores, but training these models requires substantial experimental data to begin with. Yet, useful curation signals do not have to take the form of absolute measurements, as scientific design discovery is often comparative in nature. Here, we propose that curation can instead be primarily driven by expert pairwise rankings, which are substantially easier to gather. The expertise can come from computational tools or human input of multiple levels of fidelity, ranging from empirical rules of thumb to agentic workflows and experienced scientists. We introduce PRISMS, a framework that uses pairwise rankings from one or more experts, potentially spanning multiple levels of expertise, to identify the most promising candidates without relying on data-hungry regressors. When experts differ in fidelity and cost, PRISMS escalates pairwise queries from lower- to higher-fidelity rankers based on a Fisher-information criterion. In iterative screening that selects designs from fixed drug discovery libraries, PRISMS achieves 50% top-10 discovery recall in ~42% fewer rounds than regression-only active learning, and in ~15% fewer rounds than the ranking-based method with no selective escalation. In optimization that generates new designs without restriction to a predefined library, PRISMS achieves ~18.8% higher hypervolume than the
Bayesian optimization baseline.
Read the full abstract ▾
All authors Kevin Tirta Wijaya, Alston Lo, Michael Sun, Wojciech Matusik, Vahid Babaei
Artificial Intelligence · Cross-listed from eess.SP
Token Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities
Peng Yi and Ying-Chang Liang
Collaborative
embodied artificial intelligence (CEAI) enables multiple physical
agents to perceive, reason, and act cooperatively in dynamic environments. Effective communication is essential for CEAI, yet CEAI
agents must exchange not only large
multimodal observations but also task-relevant insights, intents, and interactive information over long horizons. This article investigates
token communication (TokCom) as a native intelligence interface for CEAI, in which
tokens serve jointly as compact semantic carriers for communication and fundamental inference units for generative foundation models (GFMs). We first discuss how TokCom supports insight sharing, intent
alignment, and interactive control among
embodied agents. We then propose a TokCom-assisted CEAI framework driven by a task-adaptive communication protocol. Comprising a compact codebook, syntax rules, and contextual examples, this protocol guides GFM-based transceivers to distill messages into compact
tokens and reconstruct them after wireless transmission. A case study on collaborative object transport demonstrates that the proposed TokCom framework substantially reduces the source payload bit consumption while preserving task efficiency and showing robustness under noisy channels. Finally, we outline future research directions.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ME
Generalized Engression Models
Xinwei Shen, Zijian Guo and Francis Bach
We consider estimating the conditional distribution of a multivariate outcome given
covariates when its coordinates may be continuous, binary, categorical, ordinal or rankings, and are conditionally dependent on one another. Different statistical methods have been developed for each outcome type, and most of them target a summary of the conditional distribution, such as the mean of each coordinate, rather than the joint distribution of the outcome vector. We develop generalized engression models, a unified nonparametric distributional regression framework for outcomes of any type. The proposed method builds upon engression, a scoring-rule-based deep generative model, and introduces a data-type-specific link function and a
stochastic perturbation that smooths the loss, enabling gradient-based training even with discontinuous links. We establish universal representation results for continuous, discrete and mixed outcomes. In simulations and in two applications, 242 species in a community ecology
benchmark and a 17-dimensional mixed-type health outcome, the method matches type-specific models on marginal scores, improves on them on the joint distribution, and matches or exceeds purpose-built state-of-the-art joint species distribution models. Software is available in Python.
Read the full abstract ▾
Systems and Control
Differentiable Hybrid-Action Neural Feedback Control for District Heating Networks
Nicolas Kirsch, Corrado Sgadari, Alessio La Bella et al. (+1 more)
Many cyber-physical systems require control policies that combine continuous setpoints with discrete operational de- cisions, such as equipment switching, mode selection, or resource scheduling. Discrete actions are not differentiable, which ob- structs gradient-based policy training, while conventional mixed- integer formulations remain costly to solve online. This paper proposes a hybrid-action neural controller (HANC) in which a continuous branch, a categorical branch and a differentiable assembly layer jointly generate commands that satisfy complex actuator constraints by construction. Categorical decisions are handled using a straight-through Gumbel
estimator, enabling the policy to be trained by backpropagation through time over full closed-loop rollouts. The proposed framework is deployed on a district heating network (DHN) featuring multiple heat generation units and stratified thermal energy storage. Its performance is evaluated on a simulation of a real DHN located at RSE SpA in Italy. The resulting policy jointly learns switching decisions and continu- ous operating setpoints. Under dynamic electricity pricing, the learned controller reduces operating cost by 30% compared to a rule-based industrial baseline. We also show that, compared with a deterministic straight-through relaxation, injecting noise during training achieves similar cost while reducing hard switching by an order of magnitude, and attribute this difference to the wider decision margins of the resulting policy.
Read the full abstract ▾
All authors Nicolas Kirsch, Corrado Sgadari, Alessio La Bella, Giancarlo Ferrari-Trecate
Machine Learning
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
Tido Specht, Elias Benedict Krey, Nils Neukirch et al. (+1 more)
Understanding information processing in large
language models (LLMs) requires dissecting the
geometric organization of their internal
token representations. While existing mechanistic interpretability (MI) methods seek to extract concepts, they are constrained by a strong linearity assumption challenged by evidence of non-linear feature
manifolds. We move beyond linear concepts by adapting Non-Linear Multi-Dimensional Concept Discovery (NLMCD) from computer
vision to
token-level LLM activations, modeling concepts as low-dimensional
manifolds. To compare concept
manifolds across layers and models, we introduce a concept-based
alignment (CBA) score, a generalized Rand index that measures
geometric proximity without explicit feature matching. Our analysis yields six key findings: (i) a neighboring-layer sanity check shows CBA is more sensitive than PCA- or CKA-based linear baselines; (ii) layer-by-layer
alignment matrices reveal two block structures in intermediate and late layers, consistent across models and obscured by linear metrics; (iii) concept composition remains syntax-dominated through most of the network before giving way to increasingly mixed syntactic-semantic concepts in later layers, with increasing output-orientation toward the final layers; (iv)
multilingual concept sharing between English and Mandarin is training-dependent rather than universal, strongest in Qwen, weaker in Llama, and absent in GPT-2; (v) inter-model
alignment mirrors this structure, with strong correspondence between same-family Qwen models of different scale but weak
alignment across model families; and (vi) across Tulu-3 training stages,
alignment is highest between adjacent stages, with the largest shift between the base model and SFT, while subsequent preference-
alignment stages (DPO, RLVR) leave early layers largely unchanged and RLVR mostly preserves DPO's concepts in late layers.
Read the full abstract ▾
All authors Tido Specht, Elias Benedict Krey, Nils Neukirch, Nils Strodthoff
Systems and Control
Finite-Data Safety Informativity Under Dynamic Asymmetric Actuation
Abhinav Sinha, Praveen Kumar Ranjan and Yongcan Cao
When the system model is not fully known, measurement error and limited excitation can leave several models consistent with the same finite data. A command judged safe for one model may fail for another, while limited control authority can prevent the corrective action needed to preserve safety. To ensure safety under model uncertainty and asymmetric input limits, we develop a finite-data certificate that determines whether a command can enforce a prescribed safety inequality. For a linearly parameterized safety channel with exactly known regressors and bounded aggregate residual error, we derive a support formula for the worst-case safety contribution of all data-consistent models. The formula identifies the regressor directions that admit a finite bound, allowing rank-deficient records to contribute to safety certification. Using certified componentwise bounds on actuator tracking error yields an affine inequality with a necessary and sufficient test for pointwise command feasibility. The affine inequality reduces computation of the closest certified command to a scalar root-finding problem. It also yields a closed-form gate that selects the largest certified fraction of a prescribed command segment. The proposed certificate guarantees output safety within its operating domain, provided the feedback is locally Lipschitz and the uncertainty bounds remain valid. Domain retention and full-state continuation extend this guarantee to all time. A vehicle study demonstrates that output safety can be certified from finite measurements in a safety-critical setting with model and actuator uncertainty.
Read the full abstract ▾
Machine Learning
MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
Yifan Guo
Benchmark gains are often mechanism-ambiguous: reproducing an improvement does not by itself identify why it occurs. We study finite-library mechanism discrimination, where posterior-weighted candidate mechanisms, executable probes, and a limited experimental budget define a sequential experiment-selection problem. MECHVAR selects the next probe by maximizing the posterior-weighted variance of its predicted responses. Under a shared-Gaussian predictive model, this score is exactly proportional to the classical Box–Hill posterior-weighted pairwise-KL criterion, yet it admits O(KE) vectorized rescoring and a transparent additive audit over mechanism pairs. A local expansion further links the score to expected information gain (EIG) when predicted response separations are small. In a 25-block stress audit, MECHVAR outperforms confirmation-first in several moderate misspecification regimes, while its primary comparisons with EIG remain statistically unresolved. In a held-out Digits loop, normalized mechanism-identification AUC is 0.8975 for MECHVAR, 0.7825 for a score-greedy policy, and 0.9092 for EIG. At K = 100, E = 200, median single-thread full-library scoring is 10.36 microseconds for MECHVAR versus 57.69 ms for six-node quadrature EIG in the recorded environment. MECHVAR therefore provides a lightweight, auditable acquisition rule for finite-library experiment selection when a shared predictive scale is a defensible approximation.
Read the full abstract ▾
Machine Learning
Debias Anything: Fairness with Diversity without Supervision in Diffusion Models
Théau d'Audiffret, Mariia Vladimirova and Jean-Yves Franceschi
Although
diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their generation process post-training w.r.t. some sensitive attribute usually relies on classifier guidance or explicit text extra-conditioning, but this reduces methods' applicability and output diversity. Conversely, methods promoting diversity alone do not ensure fair attribute representation. In this paper, we propose a method tackling
fairness and diversity jointly that is generally applicable to any
diffusion model and any sensitive attribute. To this end, an adapter connects the frozen
diffusion model to a pretrained
vision-
language embedding space, enabling
fairness and diversity guidance without sensitive-attribute annotations. For
fairness, pairs of text
prompts define attribute directions which guide batch composition towards specific proportions. For diversity, we introduce a score measuring disagreement between the semantic estimates derived from this representation. The formulation supports unconditional and text-conditional
diffusion models, while requiring no prior knowledge or data of sensitive attribute. Experiments confirm that our method improves quality and diversity scores at comparable
fairness levels.
Read the full abstract ▾
Artificial Intelligence
AI-assisted mitotic counting improves reproducibility and efficiency across multiple tumour types
Simon Graham, Mostafa Jahanifar, Quoc Dang Vu et al. (+15 more)
Mitotic counting is an important component of tumour grading, diagnosis and prognostic assessment across several tumour types, but manual assessment is time-consuming and subject to inter-pathologist variability. To help address these challenges, we developed MitPro, an AI tool designed to improve consistency and efficiency by directing pathologists towards regions with the highest predicted mitotic activity and highlighting mitotic figures for review, while retaining pathologist control over region selection and the final count. We evaluated its effect on the reproducibility and efficiency of mitotic counting in a retrospective, non-interventional, paired reader study comprising 385 whole-slide images from 3 centres in 3 countries and 7 tumour types using 3 different scanners. 13 pathologists participated, with each slide assessed independently by 3 pathologists without AI assistance and again with AI assistance after a minimum 2 week washout period. Across all slides, AI-assisted counting increased the intraclass correlation coefficient from 0.589 to 0.949. Mean pathologist-level median assessment time decreased from 286.4 to 127.8 seconds, corresponding to an average saving of 151.8 seconds per assessment. Improvements in agreement and efficiency were also observed in supporting analyses using
HALO AP and Sectra image management systems and in 2 additional tumour types outside the main study population. AI-assisted assessment was associated with a subtle shift towards higher mitotic counts and scores, consistent with identification of more active mitotic hotspots and fewer missed mitotic figures. The frequency of score change between unassisted and AI-assisted assessment was comparable with inter-pathologist variation during routine counting. These findings support the use of MitPro as an assistive tool for more consistent and efficient mitotic assessment in routine practice.
Read the full abstract ▾
All authors Simon Graham, Mostafa Jahanifar, Quoc Dang Vu, Vygante Maskoliunaite, Donatas Petroska, Ruta Barbora Valkiuniene, Ayat Gamal Lashen, Jen Hong Ong, Amede Ogechi Nnorom, Sinclair Couper, Natasha Kardasz, Reshma Agrawal, Brinder Singh Chohan, Jose Luis Solorzano Rendon, Shonali Natu, Arvydas Laurinavicius, Nasir Rajpoot, David Snead
Numerical Analysis
Adaptive Multiresolution Diffusion Operators: A Variational Theory on Evolving Multiresolution Spaces
Christian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås et al. (+1 more)
We develop a variational framework for state-dependent
diffusion on adaptive multiresolution representations in which the
diffusion operator is generated by the adaptive state itself. The state consists of an admissible multiresolution tree, its active approximation space and basis, and the corresponding coefficient representation. It determines a symmetric nonnegative interaction form and an associated positive semidefinite intrinsic
diffusion operator. In contrast to classical adaptive wavelet methods, where a prescribed operator is represented on an evolving approximation space, refinement and coarsening here modify simultaneously the representation, interaction graph, and operator. Because the adaptive hierarchy evolves through discrete topological changes, the coupled dynamics are formulated through a time-discrete variational principle rather than a differential
evolution on a fixed space. We establish existence of the discrete updates, a discrete energy inequality, the coefficient-space null mode, and contractivity for frozen adaptive states. For regularized inverse problems, the construction yields Adaptive Multiresolution
Diffusion Imaging (AMDI), combining data fidelity, intrinsic
diffusion, coefficient sparsity, and tree complexity in a state-dependent energy. Numerical experiments verify the assembled operator identities, examine refinement-commutator decay, and confirm discrete energy dissipation. Adaptive Haar and higher-order multiwavelet calculations demonstrate localization of resolution on heterogeneous data. In denoising, AMDI retains high structural reconstruction quality with less than 10% of the full active representation, with stable behavior across held-out noise realizations.
Read the full abstract ▾
All authors Christian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås, Joakim Henrik Beck
Computer Vision
PhaseAT: Fourier Phase Adversarial Training for Medical Image Domain Generalization
Ahmed Sharshar, Asif Hanif, Naveen Kumar Kummari et al. (+2 more)
Reliable clinical deployment of deep medical image models is hindered by distribution shifts across scanners, sites, and acquisition protocols. Existing domain generalization (DG) methods often focus on style or intensity diversification, but they can still leave networks dependent on domain-specific texture correlations. Inspired by evidence that
Fourier phase encodes semantic structure, we introduce PhaseAT, a phase-aware
adversarial training framework for medical DG. PhaseAT forms phase-perturbed training views in the
Fourier domain by iteratively updating a bounded phase perturbation while keeping the amplitude spectrum unchanged, thereby stressing spatial organization under matched appearance statistics. Perturbations are applied only to the luminance channel in YCbCr color space to avoid chromatic artifacts. Additionally, a simple phase-saliency mask concentrates updates on the most influential frequencies. The model is trained with a weighted combination of losses on clean and phase-perturbed samples, supporting both single-source and multi-source DG. We validate our method on two challenging medical
datasets and demonstrate that PhaseAT achieves over 20% improvement in single-source domain generalization, outperforming several state-of-the-art DG methods. The code implementation is available at: https://github.com/ahmed-sharshar/PhaseAT.
Read the full abstract ▾
All authors Ahmed Sharshar, Asif Hanif, Naveen Kumar Kummari, Mohammad Yaqub, Mohsen Guizan
Game Theory · Cross-listed from econ.TH
Robustness in Mechanism Design
Jason Hartline
The article reviews the robust design and analysis of auctions, focusing on the predominant paradigm in the computer science literature, which quantifies robustness by the worst-case, over environments, ratio between the robust auction's performance and that of an optimal auction for the environment. Applications include robust analysis of canonical auctions such as the first-price auction for the welfare objective, prior-robust auction design for the revenue objective, and prior-robust design of exchange mechanisms for the gains-from-trade objective. Finally, the revelation principle is not without loss in robust mechanism design. The potential loss can be quantified by the revelation gap, the fraction of the optimal robust guarantee that is lost when restricting from all mechanisms to revelation mechanisms.
Read the full abstract ▾
Machine Learning
A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings
Sahil Kadadekar
Can response safety be scored by cosine similarity to the mean
embedding of known-safe responses? A recent sleeper-
agent detector proposes exactly this score, yet the raw positive-centroid rule is not identified: positive observations locate the safe class relative to an encoder origin, but do not determine which direction separates safe from unsafe responses. We audit the rule on two
prompt-controlled, human-labeled corpora and one auxiliary jury-labeled source control, using four frozen encoders and
prompt-grouped splits. On the human-labeled corpora the safe prototype reaches ROC-AUC 0.457-0.545, with two
cells significantly below chance and one above, while an explicit safe-minus-unsafe reference reaches 0.588-0.738 on the same
embeddings; on the jury control the prototype is inverted (0.358-0.405) and the reference reaches 0.754-0.793. At validation-calibrated 5% false-safe thresholds, the reference accepts more safe responses on PKU-SafeRLHF (0.153-0.263 versus 0.039-0.061 across encoders) and Aegis (0.189-0.291 versus 0.004-0.045), but not reliably on BeaverTails. A fully unlabeled held-out reference recovers part to most of the referenced ranking, much less when only 5% of the pool is unsafe, whereas 80-634 labeled unsafe responses recover most of it.
Prompt-only ablations show that
prompt-label composition can inflate uncontrolled evaluations. This is a bounded result about a raw positive centroid, not all one-class methods or safety-specialized guards. A class mean is a location, not necessarily a safety direction; a declared reference with enough unsafe mass identifies orientation.
Read the full abstract ▾
Artificial Intelligence
LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification
Haochen Zhang, Laura Yao, Zachary Plotkin et al. (+2 more)
Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural
language. Supervised fine-tuning (SFT) relies on a larger model's captions and cannot exceed their quality. Reinforcement learning (RL) can, but its rewards were designed for other modalities and other tasks, and they transfer poorly to open-ended generation in the time series domain. We address this by proposing LineupRL, a reinforcement learning with verifiable rewards (RLVR) pipeline whose reward is caption-to-series identification. The reward model is a frozen large
language model (LLM) verifier that reads the generated caption and the candidate time series as raw values, never the chart, and must pick the described time series from multiple distractors. Matching is a far lighter demand on the verifier than writing questions or judging a caption, so an off-the-shelf LLM can supply the reward. Across two captioning
benchmarks, and on
forecasting and reconstruction where the predictor sees only the caption, LineupRL outperforms SFT and RL baselines on every metric. The 3B
vision language model (VLM) trained by LineupRL also outperforms, at 1/24 of the parameters, the 72B VLM whose captions the SFT baseline is distilled from. Our case study shows that LineupRL resists reward hacking, and that the captioner it trains both traces the trend and names the values at key points.
Read the full abstract ▾
All authors Haochen Zhang, Laura Yao, Zachary Plotkin, Gengwei Zhang, Tianlong Chen
Machine Learning
SkillEvoLean: Mutation-enhanced skill evolution for Lean provers
Kuo Zhou, Zixiong Yang and Lu Zhang
Skill
evolution offers a promising way to improve large
language model
agents without updating their parameters, but its use in formal
theorem proving remains underexplored. Existing methods mainly target natural-
language reasoning, improving skills by analyzing successful and failed trajectories and incrementally revising solving strategies. Although the Lean verifier provides reliable execution feedback, when all sampled trajectories fail, existing skill
evolution methods lack successful trajectories from which to infer effective update directions. Furthermore, these methods also focus mainly on the root instruction file, thus underexploring the
evolution of reference knowledge including mathematical concepts and proving techniques. To address these limitations, we propose a mutation-enhanced skill self-
evolution framework for building skill-augmented Lean provers. The framework jointly evolves a high-level solving policy and its reference knowledge through progressive and mutation-based updates. Progressive
evolution derives local improvements from successful and failed trajectories, while mutation is triggered when no complete proof can be generated, sampling mathematical concepts to produce and select new skill candidates under verifier feedback. We evaluate our method on MiniF2F, PutnamBench, the 2025 International Mathematical Olympiad (IMO 2025), and the 2026 USA Mathematical Olympiad (USAMO 2026). Under the same backbone model, trajectorysampling budget, and test-time compute, our method achieves proof success rates of 100.0%, 90.6%, 4/6, and 4/6, respectively, with GPT-5.5, outperforming the baseline methods. Further analysis shows that concept-guided mutation outperforms random-text-guided mutation by 6.9 and 8.2 percentage points on MiniF2F and PutnamBench, respectively, while solving one additional problem on both IMO 2025 and USAMO 2026.
Read the full abstract ▾
Computer Vision
Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors
Edward W. Staley, Connor O. Pyles, Rahul Hingorani et al. (+5 more)
Vision-
Language-Action (VLA) models rely strongly on
language for describing task information, despite having
multimodal inputs. We hypothesize that other modalities in the state space may present opportunities for supplemental task conditioning, which may be particularly relevant in cluttered or otherwise ambiguous scenes. We introduce two tuned models to test this hypothesis: (1) an electrophysiology-conditioned VLA (EC-VLA) that incorporates 8-channel electromyography envelopes as continuous conditioning input concatenated to the proprioceptive vector, and (2) a visually-annotated VLA (VA-VLA) that incorporates visual
segmentation annotations to the image inputs. On a cube-selection task evaluated across three participants, EC-VLA matches a
language-prompted baseline in uncluttered, in-distribution conditions and substantially outperforms it in cluttered, out-of-distribution scenes. Similarly, VA-VLA shows modest improvements over a
language-prompted baseline in in-distribution scenes with substantial improvement in cluttered, out-of-distribution trials. Together, these results provide strong evidence for the potential benefit of task-conditioning beyond
language.
Read the full abstract ▾
All authors Edward W. Staley, Connor O. Pyles, Rahul Hingorani, Frank Camargo, Griffin Milsap, Jared Markowitz, Matthew S. Fifer, Michael Wolmetz
Cryptography and Security · Cross-listed from quant-ph
Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift
Marcel Mordarski, Benjamin Gras, Abdelrahman Shehata et al. (+2 more)
Quantum key distribution (QKD) links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel drift between recalibrations. Whether an eavesdropper who cannot alter the channel's own noise gains by following that drift has not been quantified. Adaptive eavesdropping is posed here as a constrained Markov decision process in which the attacker selects one
circuit per round while the noise level follows an Ornstein–Uhlenbeck process and the abort condition is a budget over each block of rounds. The value of adaptation is bounded by the best fixed
circuit and a dynamic-programming upper bound. The actions are learnt attacks. Whereas Decker et al. trained a parametrised
circuit on a fixed gate template against a fixed channel, here the gate structure and rotation angles are searched jointly. This yields
circuits compact enough to form a discrete action set, extending the construction to noise models lacking a known template, including the amplitude damping channel. On device-independent E91 under bilateral depolarising noise, a reinforcement-learning attacker raises her Holevo information from $0.135$ for the best fixed
circuit to $0.348$ at zero detection, $98\%$ of the upper bound. On BB84 under a drifting bit-flip channel, she exceeds a conservative noise-indexed rule by $0.024$ in fidelity, reaching $99\%$ of the upper bound. Under stationary noise, the attacker's gain from basis asymmetry changes sign between an averaged and a per-basis error-rate constraint. The search, started from random gate sequences, recovers the analytical cloners and the collective-attack key rate, and meets the lower bound of the Winick–Lütkenhaus–Coles objective from above.
Read the full abstract ▾
All authors Marcel Mordarski, Benjamin Gras, Abdelrahman Shehata, Daniel Budina, Roberto Bondesan
Machine Learning
iADD: Improving Alignment and Diversity in Diffusion Policy Optimization
Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel et al. (+2 more)
Reinforcement learning based post training of
diffusion models, such as Denoising
Diffusion Policy Optimization (DDPO), optimizes a reverse
diffusion process under a reward function. However, current approaches to reward optimizations do so at the cost of diversity and quality. In this paper, we provide better tradeoffs through careful theoretical considerations and method design. We analyze the theoretical framework and mathematically demonstrate that only-latter timestep updates of
diffusion model may be harmful for diversity contrary to the conclusions presented in a previous work. Additionally, we propose an incremental Feynman-Kac training based on strong theoretical foundations in order to achieve the best-yet
alignment-diversity tradeoffs. We perform extensive experiments and compare our method against related
diffusion policy optimization approaches in three different tasks and also provide strong ablations for each component, thus validating strong performance gains in both
alignment and diversity.
Read the full abstract ▾
All authors Ashok Prasad Neupane, Saugat Adhikari, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel
Machine Learning
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik et al. (+1 more)
As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data to induce misclassification of a chosen target, pose a growing threat. Existing defenses either assume zero ground-truth information about which examples are poisoned, or they assume access to a large set of examples verified to be clean. Satisfying the latter assumption incurs significant cost since reliable verification can be very resource- or labor-intensive. This cost is particularly high for clean-label attacks, where poisoned examples are visually indistinguishable from clean data. Since requiring a large set of verified examples is impractical, we propose relying on a small set of verified examples including both clean and poisoned ones, i.e., each example verified either to be clean or poisoned through inspection by a forensic expert. The challenge is then to detect poisons based on a set of verified examples that is so small that most classification models would overfit. To address this challenge, we propose Similarity-based Approach for Ground-truth-driven Exclusion (SAGE), which trains a generic feature extractor on a separate
dataset and then flags poisoned training examples using a non-parametric, similarity-weighted prediction based on the verified set. On standard
benchmarks against seven clean-label attack methods, we demonstrate that having access to even a handful of verified poisoned examples provides a substantial advantage. We also find that the distribution of verified clean examples across classes matters more than the number of verified examples.
Read the full abstract ▾
All authors Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik, Aron Laszka
Artificial Intelligence
Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents
Beining Wu, Zihao Ding and Jun Huang
Self-improving GUI
agents keep the trajectories they produce and return them to the
agent, by fine-tuning or by
retrieval into the
prompt, and studies that compare the two destinations disagree. We attribute this to the unit of experience: a trajectory bundles items with different properties, so a conclusion about the bundle depends on its mix. To address this, (i) we introduce component routing, which splits the experience into locators, procedures, state facts and lessons and sends each component to the context or to the weights, compared on the same items across three backbone families, two environments and three seeds. One pool has two destinations: locators and lessons win in the weights, procedures and state facts in the context. (ii) We fit a rule in two properties measured before any training, recurrence and state-conditionality; it recovers the destination of a held-out backbone family in 24 of 24
cells, two interventions move a component toward the boundary, and routing by the rule beats every whole-trajectory baseline and, by +3.5 points on average, the better single destination of each backbone. (iii) We identify how training and producer-consumer differences change the value of the two destinations: note readout decreases after the same component is written into the weights, most for the items that recur most, context gains increase with the information gap, and weights gains decrease with the policy gap. Code and data will be released.
Read the full abstract ▾
Machine Learning
Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
Lulu Gong, Yongxu Zhang and Shreya Saxena
Neural activity often exhibits multiple timescales that can vary with behavioral states and task conditions. Identifying these timescales from neural recordings is important for better understanding neural computation and function. However, traditional approaches based on autocorrelation fitting are difficult to scale to high-dimensional population recordings and can become unreliable when neural dynamics change with behavior. State-space models have been a powerful framework for modeling high-dimensional neural population activity through latent dynamical systems, but standard formulations and inference methods do not explicitly account for multiple timescales and therefore do not guarantee accurate recovery of the underlying temporal structure. Motivated by these questions, we introduce the Multi-Timescale Switching Linear Dynamical System (MTS-SLDS), a framework for identifying regime-specific latent timescales from continuous or spiking neural observations. MTS-SLDS combines a multi-lag moment initialization, which captures temporal structure across multiple observation lags, with regime-conditioned Laplace-EM inference, which reduces mixing of dynamical statistics across uncertain regimes. Characteristic timescales can then be extracted directly from the
eigenvalues of the learned latent transition
matrices. In synthetic and neural experiments with Gaussian and Poisson spike observations, MTS-SLDS accurately recovers timescales and switching structure over multiple
datasets.
Read the full abstract ▾