Machine Learning
Information Hidden in Gradients of Regression with Target Noise
Arash Jamshidi, Katsiaryna Haitsiukevich and Kai Puolamäki
Second-order information – such as
curvature or data covariance – is critical for optimisation, diagnostics, and robustness. However, in many modern settings, only the gradients are observable. We show that the gradients alone can reveal the Hessian, equalling the data covariance $\Sigma$ for the linear regression. Our key insight is a simple variance calibration: injecting Gaussian noise so that the total target noise variance equals the batch size ensures that the empirical gradient covariance closely approximates the Hessian, even when evaluated far from the optimum. We provide non-asymptotic operator-norm guarantees under sub-Gaussian inputs. We also show that without such calibration, recovery can fail by an $\Omega(1)$ factor. The proposed method is practical (a "set target-noise variance to $n$" rule) and robust (variance $\mathcal{O}(n)$ suffices to recover $\Sigma$ up to scale). Applications include preconditioning for faster optimisation,
adversarial risk estimation, and gradient-only training, for example, in distributed systems. We support our theoretical results with experiments on synthetic and real data.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
From Cold Start to Active Learning: Embedding-Based Scan Selection for Medical Image Segmentation
Devon Levy, Bar Assayag, Laura Gaspar et al. (+2 more)
Accurate
segmentation annotations are critical for disease monitoring, yet manual labeling remains a major bottleneck due to the time and expertise required. Active learning (AL) alleviates this burden by prioritizing informative samples for annotation, typically through a diversity-based cold-start phase followed by uncertainty-driven selection. We propose a novel cold-start sampling strategy that combines foundation-model
embeddings with clustering, including automatic selection of the number of clusters and proportional sampling across clusters, to construct a diverse and representative initial training. This is followed by an uncertainty-based AL framework that integrates spatial diversity to guide sample selection. The proposed method is intuitive and interpretable, enabling visualization of the feature-space distribution of candidate samples. We evaluate our approach on three
datasets spanning X-ray and MRI modalities. On the CheXmask
dataset, the cold-start strategy outperforms random selection, improving Dice from 0.918 to 0.929 and reducing the Hausdorff distance from 32.41 to 27.66 mm. In the AL setting, combined
entropy and diversity selection improves Dice from 0.919 to 0.939 and reduces the Hausdorff distance from 30.10 to 19.16 mm. On the Montgomery
dataset, cold-start gains are substantial, with Dice improving from 0.928 to 0.950 and Hausdorff distance decreasing from 14.22 to 9.38 mm. On the SynthStrip
dataset, cold-start selection slightly affects Dice but reduces the Hausdorff distance from 9.43 to 8.69 mm, while active learning improves Dice from 0.816 to 0.826 and reduces the Hausdorff distance from 7.76 to 6.38 mm. Overall, the proposed framework consistently outperforms baseline methods in low-data regimes, improving
segmentation accuracy.
Read the full abstract ▾
All authors Devon Levy, Bar Assayag, Laura Gaspar, Ilan Shimshoni, Bella Specktor-Fadida
Machine Learning
Closing the Modality Gap Aligns Group-Wise Semantics
Eleonora Grassucci, Giordano Cicchetti, Emanuele Frasca et al. (+2 more)
In
multimodal learning, CLIP has been recognized as the de facto method for learning a shared latent space across multiple modalities, placing similar representations close to each other and moving them away from dissimilar ones. Although CLIP-based losses effectively align modalities at the semantic level, the resulting latent spaces often remain only partially shared, revealing a structural mismatch known as the modality gap. While the necessity of addressing this phenomenon remains debated, particularly given its limited impact on instance-wise tasks (e.g.,
retrieval), we prove that its influence is instead strongly pronounced in group-level tasks (e.g., clustering). To support this claim, we introduce a novel method designed to consistently reduce this discrepancy in two-modal settings, with a straightforward extension to the general $n$-modal case. Through our extensive evaluation, we demonstrate our novel insight: while reducing the gap provides only marginal or inconsistent improvements in traditional instance-wise tasks, it significantly enhances group-wise tasks. These findings may reshape our understanding of the modality gap, highlighting its key role in improving performance on tasks requiring semantic grouping.
Read the full abstract ▾
All authors Eleonora Grassucci, Giordano Cicchetti, Emanuele Frasca, Aurelio Uncini, Danilo Comminiello
Machine Learning
From Human Labels to Literature: Semi-Supervised Learning of NMR Chemical Shifts at Scale
Yongqi Jin, Yecheng Wang, Jun-jie Wang et al. (+3 more)
Accurate prediction of
nuclear magnetic resonance (NMR) chemical shifts is fundamental to spectral analysis and molecular structure elucidation, yet existing machine learning methods rely on limited, labor-intensive atom-assigned
datasets. We propose a semi-supervised framework that learns NMR chemical shifts from millions of literature-extracted spectra without explicit atom-level assignments, integrating a small amount of labeled data with large-scale unassigned spectra. We formulate chemical shift prediction from literature spectra as a permutation-invariant set supervision problem, and show that under commonly satisfied conditions on the loss function, optimal bipartite matching reduces to a sorting-based loss, enabling stable large-scale semi-supervised training beyond traditional curated
datasets. Our models achieve substantially improved accuracy and robustness over state-of-the-art methods and exhibit stronger generalization on significantly larger and more diverse molecular
datasets. Moreover, by incorporating solvent information at scale, our approach captures systematic solvent effects across common NMR solvents for the first time. Overall, our results demonstrate that large-scale unlabeled spectra mined from the literature can serve as a practical and effective data source for training NMR shift models, suggesting a broader role of literature-derived, weakly structured data in data-centric AI for science.
Read the full abstract ▾
All authors Yongqi Jin, Yecheng Wang, Jun-jie Wang, Rong Zhu, Guolin Ke, Weinan E
Machine Learning
Scalable Transit Delay Prediction at City Scale: A Systematic Approach with Multi-Resolution Feature Engineering and Deep Learning
Emna Boudabbous, Mohamed Karaa, Lokman Sboui et al. (+2 more)
Urban bus transit agencies need reliable, network-wide delay predictions to provide accurate arrival information to passengers and support real-time operational control. Accurate predictions help passengers plan their trips, reduce waiting time, and allow operations staff to adjust headways, dispatch extra vehicles, and manage disruptions. Although real-time feeds such as GTFS-Realtime (GTFS-RT) are now widely available, most existing delay prediction systems handle only a few routes, depend on hand-crafted features, and offer little guidance on how to design a scalable, reusable architecture. We present a city-scale prediction pipeline that combines multi-resolution feature engineering, dimensionality reduction, and deep learning. The framework generates 1,683 spatiotemporal features by exploring 23 aggregation combinations over H3
cells, routes, segments, and temporal patterns, and compresses them into 83 components using Adaptive PCA while preserving 95% of the variance. To avoid the "
giant cluster" problem that occurs when dense urban areas fall into a single H3 region, we introduce a hybrid H3+
topology clustering method that yields 12 balanced route clusters (coefficient of variation 0.608) and enables efficient distributed training. We compare five model architectures on six months of bus operations from the Société de transport de Montréal (STM) network in Montréal. A global LSTM with cluster-aware features achieves the best trade-off between accuracy and efficiency, outperforming
transformer models by 18 to 52% while using 275 times fewer parameters. We also report multi-level evaluation at the elementary segment, segment, and trip level with walk-forward validation and latency analysis, showing that the proposed pipeline is suitable for real-time, city-scale deployment and can be reused for other networks with limited adaptation.
Read the full abstract ▾
All authors Emna Boudabbous, Mohamed Karaa, Lokman Sboui, Julio Montecinos, Omar Alam
Machine Learning
LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models
Kai Hu, Haoqi Hu and Matt Fredrikson
Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We introduce LipNeXt, the first constraint-free and convolution-free 1-Lipschitz architecture for certified robustness. LipNeXt is built using two techniques: (1) a
manifold optimization procedure that updates parameters directly on the orthogonal
manifold and (2) a Spatial Shift Module to model spatial pattern without convolutions. The full network uses orthogonal projections, spatial shifts, a simple 1-Lipschitz $\beta$-Abs nonlinearity, and $L_2$ spatial pooling to maintain tight Lipschitz control while enabling expressive feature mixing. Across CIFAR-10/100 and Tiny-ImageNet, LipNeXt achieves state-of-the-art clean and certified robust accuracy (CRA), and on ImageNet it scales to 1-2B large models, improving CRA over prior Lipschitz models (e.g., up to $+8\%$ at $\varepsilon{=}1$) while retaining efficient, stable low-precision training. These results demonstrate that Lipschitz-based certification can benefit from modern scaling trends without sacrificing determinism or efficiency.
Read the full abstract ▾
Machine Learning
Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
Yibo Li, Zijie Lin, Ailin Deng et al. (+5 more)
While Large
Language Model (LLM)
agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric
memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly. These estimates are then used to directly modulate the LLM's output logits. We theoretically prove that this additive update rule is the exact closed-form solution to the KL-constrained policy optimization objective. Extensive experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods. Crucially, JitRL outperforms the performance of computationally expensive fine-tuning methods (e.g., WebRL) while reducing monetary costs by over 30 times, offering a scalable path for continual learning
agents. The code is available at https://github.com/liushiliushi/JitRL.
Read the full abstract ▾
All authors Yibo Li, Zijie Lin, Ailin Deng, Xuan Zhang, Yufei He, Shuo Ji, Tri Cao, Bryan Hooi
Machine Learning
Conformal Prediction Algorithms for Time Series Forecasting: Methods and Benchmarking
Andro Sabashvili
Reliable uncertainty quantification is of critical importance in time series
forecasting, yet traditional methods often rely on restrictive distributional assumptions. Conformal prediction (CP) has emerged as a promising distribution-free framework for generating prediction intervals with rigorous theoretical guarantees. However, applying CP to sequential data presents a primary challenge: the temporal dependencies inherent in time series fundamentally violate the core assumption of data exchangeability, upon which standard CP guarantees are built. This paper critically examines the main categories of algorithmic solutions designed to address this conflict. We survey and
benchmark methods that relax the exchangeability assumption, those that redefine the data unit to be a collection of independent time series, approaches that explicitly model the dynamics of the prediction residuals, and online learning
algorithms that adapt to distribution shifts to maintain long-run coverage. We use AutoARIMA as the base forecaster on a large-scale monthly sales
dataset, evaluating marginal coverage, interval width, and the Winkler score. Our
benchmark results show that multi-step split conformal prediction method meets the 90% coverage threshold and demonstrates the best efficiency.
Read the full abstract ▾
Machine Learning
Nearly Optimal Bayesian Inference for Structural Missingness
Chen Liang, Donghua Yang, Yutong Zhao et al. (+9 more)
Structural missingness breaks 'just impute and train': values can be undefined by causal or logical constraints, and the mask may depend on observed variables, unobserved variables (MNAR), and other missingness indicators. It simultaneously brings (i) a catch-22 situation with causal loop, prediction needs the missing features, yet inferring them depends on the missingness mechanism, (ii) under MNAR, the unseen are different, the missing part can come from a shifted distribution, and (iii) plug-in imputation, a single fill-in can lock in uncertainty and yield overconfident, biased decisions. In the
Bayesian view, prediction via the posterior predictive distribution integrates over the full model posterior uncertainty, rather than relying on a single point estimate. This framework decouples (i) learning an in-model missing-value posterior from (ii) label prediction by optimizing the predictive posterior distribution, enabling posterior integration. This decoupling yields an in-model almost-free-lunch: once the posterior is learned, prediction is plug-and-play while preserving uncertainty propagation. It achieves SOTA on 43 classification and 15 imputation
benchmarks, with finite-sample near Bayes-optimality guarantees under our SCM prior.
Read the full abstract ▾
All authors Chen Liang, Donghua Yang, Yutong Zhao, Tianle Zhang, Shenghang Zhou, Zhiyu Liang, Hengtong Zhang, Hongzhi Wang, Ziqi Li, Xiyang Zhang, Zheng Liang, Yifei Li
Machine Learning · Cross-listed from cs.AI
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
Dongrui Liu, Qihan Ren, Chen Qian et al. (+40 more)
The rise of AI
agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce an agentic guardrail that covers complex and numerous risky behaviors, we first propose a unified three-dimensional taxonomy that orthogonally categorizes agentic risks by their source (where), failure mode (how), and consequence (what). Guided by this structured and hierarchical taxonomy, we introduce a new fine-grained agentic safety
benchmark (ATBench) and a Diagnostic Guardrail framework for
agent safety and security (AgentDoG). AgentDoG provides fine-grained and contextual monitoring across
agent trajectories. More Crucially, AgentDoG can diagnose the root causes of unsafe actions and seemingly safe but unreasonable actions, offering provenance and transparency beyond binary labels to facilitate effective
agent alignment. AgentDoG variants are available in three sizes (4B, 7B, and 8B parameters) across Qwen and Llama model families. Extensive experimental results demonstrate that AgentDoG achieves state-of-the-art performance in agentic safety moderation in diverse and complex interactive scenarios. All models and
datasets are openly released.
Read the full abstract ▾
All authors Dongrui Liu, Qihan Ren, Chen Qian, Shuai Shao, Yuejin Xie, Yu Li, Zhonghao Yang, Haoyu Luo, Peng Wang, Qingyu Liu, Binxin Hu, Ling Tang, Jilin Mei, Dadi Guo, Leitao Yuan, Junyao Yang, Guanxu Chen, Qihao Lin, Yi Yu, Bo Zhang, Jiaxuan Guo, Jie Zhang, Wenqi Shao, Huiqi Deng, Zhiheng Xi, Wenjie Wang, Wenxuan Wang, Wen Shen, Zhikai Chen, Haoyu Xie, Jialing Tao, Juntao Dai, Jiaming Ji, Zhongjie Ba, Linfeng Zhang, Yong Liu, Quanshi Zhang, Lei Zhu, Zhihua Wei, Hui Xue, Chaochao Lu, Jing Shao, Xia Hu
Machine Learning
Enhancing Control Policy Smoothness by Aligning Actions with Predictions from Preceding States
Kyoleen Kwak and Hyoseok Hwang
Deep reinforcement learning has proven to be a powerful approach to solving control tasks, but its characteristic high-frequency oscillations make it difficult to apply in real-world environments. While prior methods have addressed action oscillations via architectural or loss-based methods, the latter typically depend on heuristic or synthetic definitions of state similarity to promote action consistency, which often fail to accurately reflect the underlying system dynamics. In this paper, we propose a novel loss-based method by introducing a transition-induced similar state. The transition-induced similar state is defined as the distribution of next states transitioned from the previous state. Since it utilizes only environmental feedback and actually collected data, it better captures system dynamics. Building upon this foundation, we introduce Action Smoothing by Aligning Actions with Predictions from Preceding States (ASAP), an action smoothing method that effectively mitigates action oscillations. ASAP enforces action smoothness by aligning the actions with those taken in transition-induced similar states and by penalizing second-order differences to suppress high-frequency oscillations. Experiments in Gymnasium and Isaac-Lab environments demonstrate that ASAP yields smoother control and improved policy performance over existing methods.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents
Yuhang Zhou, Kai Zheng, Qiguang Chen et al. (+4 more)
Deep research
agents have shown remarkable potential in handling long-horizon tasks. However, state-of-the-art performance typically relies on online reinforcement learning (RL), which is financially expensive due to extensive API calls. While offline training offers a more efficient alternative, its progress is hindered by the scarcity of high-quality research trajectories. In this paper, we demonstrate that expensive online reinforcement learning is not all you need to build powerful research
agents. To bridge this gap, we introduce a fully open-source suite designed for effective offline training. Our core contributions include DeepForge, a ready-to-use task synthesis framework that generates large-scale research queries without heavy preprocessing; and a curated collection of 66k QA pairs, 33k SFT trajectories, and 21k DPO pairs. Leveraging these resources, we train OffSeeker (8B), a model developed entirely offline. Extensive evaluations across six
benchmarks show that OffSeeker not only leads among similar-sized
agents but also remains competitive with 30B-parameter systems trained via heavy online RL.
Read the full abstract ▾
All authors Yuhang Zhou, Kai Zheng, Qiguang Chen, Mengkang Hu, Qingfeng Sun, Can Xu, Jingjing Chen
Machine Learning · Cross-listed from cs.CV
3DGesPolicy: Phoneme-Aware Holistic Co-Speech Gesture Generation Based on Action Control
Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita et al. (+2 more)
Generating holistic co-
speech gestures that integrate full-body motion with facial expressions suffers from semantically incoherent coordination on body motion and spatially unstable meaningless movements due to existing part-decomposed or frame-level regression methods, We introduce 3DGesPolicy, a novel action-based framework that reformulates holistic gesture generation as a continuous trajectory control problem through
diffusion policy from robotics. By modeling frame-to-frame variations as unified holistic actions, our method effectively learns inter-frame holistic gesture motion patterns and ensures both spatially and semantically coherent movement trajectories that adhere to realistic motion
manifolds. To further bridge the gap in expressive
alignment, we propose a Gesture-Audio-Phoneme (GAP) fusion module that can deeply integrate and refine multi-modal signals, ensuring structured and fine-grained
alignment between
speech semantics, body motion, and facial expressions. Extensive quantitative and qualitative experiments on the BEAT2
dataset demonstrate the effectiveness of our 3DGesPolicy across other state-of-the-art methods in generating natural, expressive, and highly
speech-aligned holistic gestures.
Read the full abstract ▾
All authors Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Naoya Chiba, Yuki Uranishi
Machine Learning · Cross-listed from cs.CV
On Procrustes Contamination in Machine Learning Applications of Geometric Morphometrics
Lloyd Austin Courtenay
Geometric morphometrics (GMM) is widely used to quantify shape variation, more recently serving as input for machine learning (ML) analyses. Standard practice aligns all specimens via Generalized Procrustes Analysis (GPA) prior to splitting data into training and test sets, potentially introducing statistical dependence and contaminating downstream predictive models. Here, the effects of GPA-induced contamination are formally characterised using controlled 2D and 3D simulations across varying sample sizes, landmark densities, and allometric patterns. A novel realignment procedure is proposed, whereby test specimens are aligned to the training set prior to model fitting, eliminating cross-sample dependency. Simulations reveal a robust "diagonal" in sample-size vs. landmark-space, reflecting the scaling of RMSE under isotropic variation, with slopes analytically derived from the degrees of freedom in Procrustes tangent space. The importance of spatial autocorrelation among landmarks is further demonstrated using linear and convolutional regression models, highlighting performance degradation when landmark relationships are ignored. This work establishes the need for careful preprocessing in ML applications of GMM, provides practical guidelines for realignment, and clarifies fundamental statistical constraints inherent to Procrustes shape space.
Read the full abstract ▾
Machine Learning
GCFX: Generative Counterfactual Explanations for Deep Graph Models at the Model Level
Jinlong Hu and Jiacheng Liu
Deep graph learning models have demonstrated remarkable capabilities in processing graph-structured data and have been widely applied across various fields. However, their complex internal architectures and lack of transparency make it difficult to explain their decisions, resulting in opaque models that users find hard to understand and trust. In this paper, we explore model-level explanation techniques for deep graph learning models, aiming to provide users with a comprehensive understanding of the models' overall decision-making processes and underlying mechanisms. Specifically, we address the problem of counterfactual explanations for deep graph learning models by introducing a generative model-level counterfactual explanation approach called GCFX, which is based on deep graph generation. This approach generates a set of high-quality counterfactual explanations that reflect the model's global predictive behavior by leveraging an enhanced deep graph generation framework and a global summarization
algorithm. GCFX features an architecture that combines dual encoders, structure-aware taggers, and Message Passing Neural Network decoders, enabling it to accurately learn the true latent distribution of input data and generate high-quality, closely related counterfactual examples. Subsequently, a global counterfactual summarization
algorithm selects the most representative and comprehensive explanations from numerous candidate counterfactuals, providing broad insights into the model's global predictive patterns. Experiments on a synthetic
dataset and several real-world
datasets demonstrate that GCFX outperforms existing methods in terms of counterfactual validity and coverage while maintaining low explanation costs, thereby offering crucial support for enhancing the practicality and trustworthiness of global counterfactual explanations.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.HC
Fusion of Spatio-Temporal and Multi-Scale Frequency Features for Dry Electrodes MI-EEG Decoding
Tianyi Gong, Can Han, Junxi Wu et al. (+1 more)
Dry-electrode Motor Imagery Electroencephalography (MI-
EEG) enables fast, comfortable, real-world
Brain Computer Interface by eliminating gels and shortening setup for at-home and wearable use.However, dry recordings pose three main issues: lower Signal-to-Noise Ratio with more baseline drift and sudden transients; weaker and noisier data with poor phase
alignment across trials; and bigger variances between sessions. These drawbacks lead to larger data distribution shift, making features less stable for MI-
EEG tasks.To address these problems, we introduce STGMFM, a tri-branch framework tailored for dry-electrode MI-
EEG, which models complementary spatio-temporal dependencies via dual graph orders, and captures robust envelope dynamics with a multi-scale frequency mixing branch, motivated by the observation that amplitude envelopes are less sensitive to contact variability than instantaneous waveforms. Physiologically meaningful connectivity priors guide learning, and decision-level fusion consolidates a noise-tolerant consensus. On our collected dry-electrode MI-
EEG, STGMFM consistently surpasses competitive CNN/
Transformer/graph baselines. Codes are available at https://github.com/Tianyi-325/STGMFM.
Read the full abstract ▾
All authors Tianyi Gong, Can Han, Junxi Wu, Dahong Qian
Machine Learning
Gradient Regularized Natural Gradients
Satya Prakash Dash, Hossein Abdi, Wei Pan et al. (+2 more)
Gradient regularization (GR) has been shown to improve the generalizability of trained models. While Natural Gradient Descent has been shown to accelerate optimization in the initial phase of training, little
attention has been paid to how the training dynamics of second-order optimizers can benefit from GR. In this work, we propose Gradient-Regularized Natural Gradients (GRNG), a family of scalable second-order optimizers that integrate explicit gradient regularization with natural gradient updates. Our framework introduces two frequentist
algorithms: Regularized Explicit Natural Gradient (RENG), which utilizes double backpropagation to explicitly minimize the gradient norm, and Regularized Implicit Natural Gradient (RING), which incorporates regularization implicitly into the update direction. We also propose a
Bayesian variant based on a Regularized-Kalman formulation that eliminates the need for FIM inversion entirely. We establish convergence guarantees for GRNG, showing that gradient regularization improves stability and enables convergence to global minima. Empirically, we demonstrate that GRNG consistently enhances both optimization speed and generalization compared to first-order methods (SGD, AdamW) and second-order baselines (K-FAC, Sophia), with strong results on
vision and
language benchmarks.
Read the full abstract ▾
All authors Satya Prakash Dash, Hossein Abdi, Wei Pan, Samuel Kaski, Mingfei Sun
Machine Learning · Cross-listed from quant-ph
Emergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication
Michael Kölle, Christian Reff, Leo Sünkel et al. (+3 more)
Emergent cooperation in classical Multi-
Agent Reinforcement Learning has gained significant
attention, particularly in the context of Sequential Social Dilemmas (SSDs). While classical reinforcement learning approaches have demonstrated capability for emergent cooperation, research on extending these methods to
Quantum Multi-
Agent Reinforcement Learning remains limited, particularly through communication. In this paper, we apply communication approaches to
quantum Q-Learning
agents: the Mutual Acknowledgment
Token Exchange (MATE) protocol, its extension Mutually Endorsed Distributed Incentive Acknowledgment
Token Exchange (MEDIATE), the peer rewarding mechanism Gifting, and Reinforced Inter-
Agent Learning (RIAL). We evaluate these approaches in three SSDs: the Iterated Prisoner's Dilemma, Iterated Stag Hunt, and Iterated Game of Chicken. Our experimental results show that approaches using MATE with temporal-difference measure (MATE\textsubscript{TD}), AutoMATE, MEDIATE-I, and MEDIATE-S achieved high cooperation levels across all dilemmas, demonstrating that communication is a viable mechanism for fostering emergent cooperation in
Quantum Multi-
Agent Reinforcement Learning.
Read the full abstract ▾
All authors Michael Kölle, Christian Reff, Leo Sünkel, Julian Hager, Gerhard Stenzel, Claudia Linnhoff-Popien
Machine Learning
Frequency-Based Hyperparameter Selection in Games
Aniket Sanyal, Baraah A.M. Sidahmed, Rebekka Burkholz et al. (+1 more)
Learning in smooth games fundamentally differs from standard minimization due to rotational dynamics, which invalidate classical hyperparameter tuning strategies. Despite their practical importance, effective methods for tuning in games remain underexplored. A notable example is LookAhead (LA), which achieves strong empirical performance but introduces additional parameters that critically influence performance. We propose a principled approach to hyperparameter selection in games by leveraging frequency estimation of oscillatory dynamics. Specifically, we analyze oscillations both in continuous-time trajectories and through the spectrum of the discrete dynamics in the associated frequency-based space. Building on this analysis, we introduce Modal LookAhead (MoLA), an extension of LA that selects the hyperparameters adaptively to a given problem. We provide convergence guarantees and demonstrate in experiments that MoLA accelerates training in both purely rotational games and mixed regimes, all with minimal computational overhead.
Read the full abstract ▾
All authors Aniket Sanyal, Baraah A.M. Sidahmed, Rebekka Burkholz, Tatjana Chavdarova
Machine Learning
Superlinear Multi-Step Attention
Yufeng Huang
In this paper, we propose Superlinear
attention, a fully trainable multi-step
attention architecture that achieves subquadratic complexity for long sequences while preserving random context access (a.k.a.\ structural non-exclusion): no eligible
token position is structurally excluded from being selected for
attention. Superlinear
attention reformulates standard causal self-
attention as a multi-step search problem with $N$ steps, yielding an overall complexity of $O(L^{1+\frac{1}{N}})$. To illustrate the architecture, we present a baseline $N=2$ implementation, which is algorithmically analogous to standard jump search. In this $O(L^{3/2})$ instantiation, the first step performs $O(L^{3/2})$ span-search to select relevant spans of the sequence, and the second step applies $O(L^{3/2})$ span-
attention (standard
attention restricted to the selected spans). In an upscaled $O(L^{1.54})$ configuration for robustness, we achieve an average decoding throughput of 114
tokens/sec at 1M context length and 80
tokens/sec at 10M context in our implementation on a modified 30B hybrid MoE model on a single B200 GPU. With limited training, we also obtain strong performance on the NIAH (Needle In A Haystack) task up to 256K context length, demonstrating that the routed span selection is learnable end-to-end. This paper emphasizes architectural formulation, scaling analysis, and systems feasibility, and presents initial validation; comprehensive quality evaluations across diverse long-context tasks are left to future work.
Read the full abstract ▾
Machine Learning
Estimating Dense-Packed Zone Height in Liquid-Liquid Separation: A Physics-Informed Neural Network Approach
Mehmet Velioglu, Song Zhai, Alexander Mitsos et al. (+3 more)
Separating
liquid-
liquid dispersions in
gravity settlers is critical in chemical, pharmaceutical, and recycling processes. The dense-packed zone height is an important performance and safety indicator but it is often expensive and impractical to measure due to optical limitations. We propose a framework to estimate phase heights by combining a PINN model with readily available volume flow measurements, without requiring phase height measurements during deployment. To this end, a physics-informed neural network (PINN) is first pretrained on synthetic data and physics equations derived from a low-fidelity (approximate) mechanistic model to reduce the need for extensive experimental data. While the mechanistic model is used to generate synthetic training data, only volume balance equations are used in the PINN, as incorporating droplet coalescence and sedimentation submodels would be computationally prohibitive. The pretrained PINN is then fine-tuned with scarce experimental phase height and flow-rate data to capture the actual dynamics of the separator. We then deploy the differentiable PINN as a predictive model in an Extended Kalman Filter inspired state estimation framework, enabling the phase heights to be tracked and updated using flow-rate measurements only. We first test the two-stage trained PINN by forward simulation from a known initial state against the mechanistic model and a non-pretrained PINN. We then evaluate phase height estimation performance with the filter, comparing the two-stage trained PINN with a two-stage trained purely data-driven neural network. All model types are trained and evaluated using ensembles to account for model parameter uncertainty. In all evaluations, the two-stage trained PINN yields the most accurate phase-height estimates.
Read the full abstract ▾
All authors Mehmet Velioglu, Song Zhai, Alexander Mitsos, Adel Mhamdi, Andreas Jupke, Manuel Dahmen
Machine Learning · Cross-listed from cs.AI
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
Zhenyuan Guo, Tong Chen, Wenlong Meng et al. (+4 more)
Large
Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a
reasoning trace before deriving the final answer. However, these extended generations incur substantial
memory footprint and computational overhead, bottlenecking LRMs' efficiency. This work uses
attention maps to analyze the influence of
reasoning traces and uncover an interesting phenomenon: only some decision-critical
tokens in a
reasoning trace steer the model toward the final answer, while the remaining
tokens contribute negligibly. Building on this observation, we propose Dynamic Thinking-
Token Selection (DynTS). This method identifies decision-critical
tokens and retains only their associated Key-Value (KV) cache states during inference, evicting the remaining redundant entries to optimize efficiency.
Read the full abstract ▾
All authors Zhenyuan Guo, Tong Chen, Wenlong Meng, Chen Gong, Xin Yu, Chengkun Wei, Wenzhi Chen
Machine Learning
Making medical vision-language models think causally across modalities with retrieval-augmented cross-modal reasoning
Weiqin Yang, Haowen Xue, Qingyi Peng et al. (+3 more)
Medical
vision-
language models (VLMs) achieve strong performance in diagnostic reporting and image-text
alignment, yet their underlying
reasoning mechanisms remain fundamentally correlational, exhibiting reliance on superficial statistical associations that fail to capture the causal pathophysiological mechanisms central to clinical decision-making. This limitation makes them fragile, prone to
hallucinations, and sensitive to
dataset biases.
Retrieval-augmented generation (RAG) offers a partial remedy by grounding predictions in external knowledge. However, conventional RAG depends on semantic similarity, introducing new spurious correlations. We propose
Multimodal Causal
Retrieval-Augmented Generation, a framework that integrates causal inference principles with
multimodal retrieval. It retrieves clinically relevant exemplars and causal graphs from external sources, conditioning model
reasoning on counterfactual and interventional evidence rather than correlations alone. Applied to radiology report generation, diagnosis prediction, and visual question answering, it improves factual accuracy, robustness to distribution shifts, and interpretability. Our results highlight causal
retrieval as a scalable path toward medical VLMs that think beyond pattern matching, enabling trustworthy
multimodal reasoning in high-stakes clinical settings.
Read the full abstract ▾
All authors Weiqin Yang, Haowen Xue, Qingyi Peng, Hexuan Hu, Qian Huang, Tingbo Zhang
Machine Learning
Structural Gender Bias in Credit Scoring: Proxy Leakage
Navya SD, Sreekanth D and SS Uma Sankari
As financial institutions increasingly adopt machine learning for credit risk assessment, the persistence of algorithmic bias remains a critical barrier to equitable financial inclusion. This study provides a comprehensive audit of structural gender bias within the Taiwan Credit Default
dataset, specifically challenging the prevailing doctrine of "
fairness through blindness." Despite the removal of explicit protected attributes and the application of industry standard
fairness interventions, our results demonstrate that gendered predictive signals remain deeply embedded within non-sensitive features. Utilizing SHAP (SHapley Additive exPlanations), we identify that variables such as Marital Status, Age, and Credit Limit function as potent proxies for gender, allowing models to maintain discriminatory pathways while appearing statistically fair. To mathematically quantify this leakage, we employ an
adversarial inverse modeling framework. Our findings reveal that the protected gender attribute can be reconstructed from purely non-sensitive financial features with an ROC AUC score of 0.65, demonstrating that traditional
fairness audits are insufficient for detecting implicit structural bias. These results advocate for a shift from surface-level statistical parity toward causal-aware modeling and structural accountability in financial AI.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
A Dataset for Automatic Vocal Mode Classification
Reemt Hinrichs, Sonja Stephan, Alexander Lange et al. (+1 more)
The Complete Vocal Technique (CVT) is a school of singing developed in the past decades by Cathrin Sadolin et al.. CVT groups the use of the voice into so called vocal modes, namely Neutral, Curbing, Overdrive and Edge. Knowledge of the desired vocal mode can be helpful for singing students. Automatic classification of vocal modes can thus be important for technology-assisted singing teaching. Previously, automatic classification of vocal modes has been attempted without major success, potentially due to a lack of data. Therefore, we recorded a novel vocal mode
dataset consisting of sustained vowels recorded from four singers, three of which professional singers with more than five years of CVT-experience. The
dataset covers the entire vocal range of the subjects, totaling 3,752 unique samples. By using four microphones, thereby offering a natural data augmentation, the
dataset consists of more than 13,000 samples combined. An annotation was created using three CVT-experienced annotators, each providing an individual annotation. The merged annotation as well as the three individual annotations come with the published
dataset. Additionally, we provide some baseline classification results. The best balanced accuracy across a 5-fold cross validation of 81.3\,% was achieved with a ResNet18. The
dataset can be downloaded under https://zenodo.org/records/14276415.
Read the full abstract ▾
All authors Reemt Hinrichs, Sonja Stephan, Alexander Lange, Jörn Ostermann
Machine Learning · Cross-listed from cs.CV
A Tumor Aware DenseNet Swin Hybrid Learning with Boosted and Hierarchical Feature Spaces for Large-Scale Brain MRI Classification
Muhammad Ali Shah, Muhammad Mansoor Alam and Saddam Hussain Khan
This study proposes an efficient Densely Swin Hybrid (EDSH) framework for
brain tumor MRI analysis, designed to jointly capture fine grained texture patterns and long range contextual dependencies. Two tumor aware experimental setups are introduced to address class-specific diagnostic challenges. The first setup employs a Boosted Feature Space (BFS), where independently customized DenseNet and Swint branches learn complementary local and global representations that are dimension aligned, fused, and boosted, enabling highly sensitive detection of diffuse glioma patterns by successfully learning the features of irregular shape, poorly defined mass, and heterogeneous texture. The second setup adopts a hierarchical DenseNet Swint architecture with Deep Feature Extraction have Dual Residual connections (DFE and DR), in which DenseNet serves as a stem CNN for structured local feature learning, while Swin_t models global tumor morphology, effectively suppressing false negatives in meningioma and pituitary tumor classification by learning the features of well defined mass, location (outside
brain) and enlargments in tumors (dural tail or upward extension). DenseNet is customized at the input level to match MRI spatial characteristics, leveraging dense residual connectivity to preserve texture information and mitigate vanishing-gradient effects. In parallel, Swint is tailored through task aligned patch
embedding and shifted-window self
attention to efficiently capture hierarchical global dependencies. Extensive evaluation on a large-scale MRI
dataset (stringent 40,260 images across four tumor classes) demonstrates consistent superiority over standalone CNNs,
Vision Transformers, and hybrids, achieving 98.50 accuracy and recall on the test unseen
dataset.
Read the full abstract ▾
Machine Learning
Discriminability-Driven Spatial-Channel Selection with Gradient Norm for Drone Signal OOD Detection
Chuhan Feng, Jing Li, Jie Li et al. (+2 more)
We propose a drone signal out-of-distribution (OOD) detection
algorithm based on discriminability-driven spatial-channel selection with a gradient norm. Time-frequency image features are adaptively weighted along both spatial and channel dimensions by quantifying inter-class similarity and variance based on protocol-specific time-frequency characteristics. Subsequently, a gradient-norm metric is introduced to measure perturbation sensitivity for capturing the inherent instability of OOD samples, which is then fused with energy-based scores for joint inference. Simulation results demonstrate that the proposed
algorithm provides superior discriminative power and robust performance via SNR and various drone types.
Read the full abstract ▾
All authors Chuhan Feng, Jing Li, Jie Li, Lu Lv, Fengkui Gong
Machine Learning
Cognitive Fusion of ZC Sequences and Time-Frequency Images for Out-of-Distribution Detection of Drone Signals
Jie Li, Jing Li, Lu Lv et al. (+2 more)
We propose a drone signal out-of-distribution detection (OODD)
algorithm based on the cognitive fusion of Zadoff-Chu (ZC) sequences and time-frequency images (TFI). ZC sequences are identified by analyzing the communication protocols of DJI drones, while TFI capture the time-frequency characteristics of drone signals with unknown or non-standard communication protocols. Both modalities are used jointly to enable OODD in the drone remote identification (RID) task. Specifically, ZC sequence features and TFI features are generated from the received
radio frequency signals, which are then processed through dedicated feature extraction module to enhance and align them. The resultant multi-modal features undergo multi-modal feature interaction, single-modal feature fusion, and multi-modal feature fusion to produce features that integrate and complement information across modalities. Discrimination scores are computed from the fused features along both spatial and channel dimensions to capture time-frequency characteristic differences dictated by the communication protocols, and these scores will be transformed into adaptive
attention weights. The weighted features are then passed through a Softmax function to produce the signal classification results. Simulation results demonstrate that the proposed
algorithm outperforms existing
algorithms and achieves 1.7% and 7.5% improvements in RID and OODD metrics, respectively. The proposed
algorithm also performs strong robustness under varying flight conditions and across different drone types.
Read the full abstract ▾
All authors Jie Li, Jing Li, Lu Lv, Zhanyu Ju, Fengkui Gong
Machine Learning
A Master Class on Reproducibility: A Student Hackathon on Advanced MRI Reconstruction Methods
Lina Felsner, Sevgi G. Kafali, Hannah Eichhorn et al. (+9 more)
We report the design, protocol, and outcomes of a student reproducibility hackathon focused on replicating the results of three influential MRI reconstruction papers: (a) MoDL, an unrolled model-based network with learned denoising; (b) HUMUS-Net, a hybrid unrolled multiscale CNN+
Transformer architecture; and (c) an untrained, physics-regularized dynamic MRI method that uses a quantitative MR model for early stopping. We describe the setup of the hackathon and present reproduction outcomes alongside additional experiments, and we detail fundamental practices for building reproducible codebases.
Read the full abstract ▾
All authors Lina Felsner, Sevgi G. Kafali, Hannah Eichhorn, Agnes A. J. Leth, Aidas Batvinskas, Andre Datchev, Fabian Klemm, Jan Aulich, Puntika Leepagorn, Ruben Klinger, Daniel Rueckert, Julia A. Schnabel
Machine Learning · Cross-listed from eess.SY
Convex Chance-Constrained Stochastic Control under Uncertain Specifications with Application to Learning-Based Hybrid Powertrain Control
Teruki Kato, Ryotaro Shima and Kenji Kashima
This paper proposes a strictly convex chance-constrained
stochastic control framework that accounts for uncertainty in control specifications such as reference trajectories and operational constraints. Control inputs and risk allocation are jointly optimized under general, possibly non-Gaussian, uncertainties through sufficient deterministic conditions for probabilistic constraint satisfaction. A decreasing risk regularizer ensures existence and full use of the allowable risk. Under the stated regularity assumptions, the joint solution is unique and locally Lipschitz-continuous, supporting stable numerical optimization. The formulation is extended to learning-based exactly linearizable (EL) models through monotone state and input transformations. A hybrid powertrain example compares deterministic control, equal risk allocation, and optimized risk allocation with and without regularization in terms of charge sustaining, constraint violations, closed-loop cost, and solver time.
Read the full abstract ▾