Machine Learning · Cross-listed from cs.SD
Lightweight and perceptually-guided voice conversion for electro-laryngeal speech
Benedikt Mayrhofer, Franz Pernkopf, Philipp Aichinger et al. (+1 more)
Electro-laryngeal (EL)
speech is characterized by constant pitch, limited prosody, and mechanical noise, reducing naturalness and intelligibility. We propose a lightweight adaptation of the state-of-the-art StreamVC framework to this setting by removing pitch and energy modules and combining self-supervised pretraining with supervised fine-tuning on parallel EL and healthy (HE)
speech data, guided by perceptual and intelligibility losses. Objective and subjective evaluations across different loss configurations confirm their influence: the best model variant, based on WavLM features and human-feedback predictions (+WavLM+HF), drastically reduces character error rate (CER) of EL inputs, raises naturalness mean opinion score (nMOS) from 1.1 to 3.3, and consistently narrows the gap to HE ground-truth
speech in all evaluated metrics. These findings demonstrate the feasibility of adapting lightweight voice conversion architectures to EL voice rehabilitation while also identifying prosody generation and intelligibility improvements as the main remaining bottlenecks.
Read the full abstract ▾
All authors Benedikt Mayrhofer, Franz Pernkopf, Philipp Aichinger, Martin Hagmüller
Machine Learning
Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures
Ibrahim Delibasoglu
Mixture of Experts (MoE) architectures enable efficient scaling of neural networks but suffer from expert collapse, where routing converges to a few dominant experts. This reduces model capacity and causes catastrophic interference during adaptation. We propose the Spectrally-Regularized Mixture of Experts (SR-MoE), which imposes
geometric constraints on the routing
manifold to enforce structural modularity. Our method uses dual regularization: spectral norm constraints bound routing function Lipschitz continuity, while stable rank penalties preserve high-dimensional feature diversity in expert selection. We evaluate SR-MoE across architectural scales and
dataset complexities using modular one-shot adaptation tasks. Results show that traditional linear gating fails with increasing depth (accuracy drops up to 4.72% due to expert
entanglement), while SR-MoE maintains structural integrity (mean interference -0.32%). Our spectral constraints facilitate positive knowledge transfer, enabling localized expert updates without global performance decay. SR-MoE provides a general solution for building high-capacity, modular networks capable of stable lifelong learning.
Read the full abstract ▾
Machine Learning
Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences
Shudong Liu, Hanwen Zhang, Xiuling Wang et al. (+2 more)
One-shot
federated learning (OSFL) reduces the communication cost and
privacy risks of iterative
federated learning by constructing a global model with a single round of communication. However, most existing methods struggle to achieve robust performance on real-world domains such as medical imaging, or are inefficient when handling non-IID (Independent and Identically Distributed) data. To address these limitations, we introduce FALCON, a framework that enhances the effectiveness of OSFL over non-IID image data. The core idea of FALCON is to leverage the feature-aware hierarchical
token sequences generation and knowledge
distillation into OSFL. First, each client leverages a pretrained visual encoder with hierarchical scale encoding to compress images into hierarchical
token sequences, which capture multi-scale semantics. Second, a multi-scale autoregressive
transformer generator is used to model the distribution of these
token sequences and generate the synthetic sequences. Third, clients upload the synthetic sequences along with the local classifier trained on the real
token sequences to the server. Finally, the server incorporates knowledge
distillation into global training to reduce reliance on precise distribution modeling. Experiments on medical and natural image
datasets validate the effectiveness of FALCON in diverse non-IID scenarios, outperforming the best OSFL baselines by 9.58% in average accuracy.
Read the full abstract ▾
All authors Shudong Liu, Hanwen Zhang, Xiuling Wang, Yuesheng Zhu, Guibo Luo
Machine Learning · Cross-listed from cs.CV
Bayesian Monocular Depth Refinement via Neural Radiance Fields
Arun Muthukkumar
Monocular depth estimation has applications in many fields, such as autonomous
navigation and extended reality, making it an essential computer
vision task. However, current methods often produce smooth depth maps that lack the fine
geometric detail needed for accurate scene understanding. We propose MDENeRF, an iterative framework that refines
monocular depth estimates using depth information from Neural Radiance Fields (NeRFs). MDENeRF consists of three components: (1) an initial
monocular estimate for global structure, (2) a NeRF trained on perturbed viewpoints, with per-pixel uncertainty, and (3)
Bayesian fusion of the noisy
monocular and NeRF depths. We derive NeRF uncertainty from the volume rendering process to iteratively inject high-frequency fine details. Meanwhile, our
monocular prior maintains global structure. We demonstrate improvements on key metrics and experiments using indoor scenes from the SUN RGB-D
dataset.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.GT
From No-Regret to Strategically Robust Learning in Repeated Auctions
Junyao Zhao
In
Bayesian single-item auctions, a monotone bidding strategy–one that prescribes a higher bid for a higher value type–can be equivalently represented as a partition of the
quantile space into consecutive intervals corresponding to increasing bids. Kumar et al. (2024) prove that agile online gradient descent (OGD), when used to update a monotone bidding strategy through its
quantile representation, is strategically robust in repeated first-price auctions: when all bidders employ agile OGD in this way, the auctioneer's average revenue per round is at most the revenue of Myerson's optimal auction, regardless of how she adjusts the reserve price over time. In this work, we show that this strategic robustness guarantee is not unique to agile OGD or to the first-price auction: any no-regret learning
algorithm, when fed gradient feedback with respect to the
quantile representation, is strategically robust, even if the auction format changes every round, provided the format satisfies allocation monotonicity and voluntary participation. In particular, the multiplicative weights update (MWU)
algorithm simultaneously achieves the optimal regret guarantee and a strong strategic robustness guarantee in this auction setting. At a technical level, our results are established via a simple relation that bridges Myerson's auction theory and standard no-regret learning theory.
Read the full abstract ▾
Machine Learning
Logic Tensor Network-Enhanced Generative Adversarial Network
Nijesh Upreti and Vaishak Belle
In this paper, we introduce Logic Tensor Network-Enhanced Generative
Adversarial Network (LTN-GAN), a novel framework that enhances Generative
Adversarial Networks (GANs) by incorporating Logic Tensor Networks (LTNs) to enforce domain-specific logical constraints during the sample generation process. Although GANs have shown remarkable success in generating realistic data, they often lack mechanisms to incorporate prior knowledge or enforce logical consistency, limiting their applicability in domains requiring rule adherence. LTNs provide a principled way to integrate first-order logic with neural networks, enabling models to reason over and satisfy logical constraints. By combining the strengths of GANs for realistic data synthesis with LTNs for logical
reasoning, we gain valuable insights into how logical constraints influence the generative process while improving both the diversity and logical consistency of the generated samples. We evaluate LTN-GAN across multiple
datasets, including synthetic
datasets (gaussian, grid, rings) and the MNIST
dataset, demonstrating that our model significantly outperforms traditional GANs in terms of adherence to predefined logical constraints while maintaining the quality and diversity of generated samples. This work highlights the potential of neuro-symbolic approaches to enhance generative modeling in knowledge-intensive domains.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.HC
Beyond Physical Labels: Redefining Domains for Robust WiFi-based Gesture Recognition
Xiang Zhang, Huan Yan, Jinyang Huang et al. (+6 more)
In this paper, we propose GesFi, a novel WiFi-based gesture recognition system that introduces WiFi latent domain mining to redefine domains directly from the data itself. GesFi first processes raw sensing data collected from WiFi receivers using CSI-ratio denoising, Short-Time Fast
Fourier Transform, and visualization techniques to generate standardized input representations. It then employs class-wise
adversarial learning to suppress gesture semantic and leverages unsupervised clustering to automatically uncover latent domain factors responsible for distributional shifts. These latent domains are then aligned through
adversarial learning to support robust cross-domain generalization. Finally, the system is applied to the target environment for robust gesture inference. We deployed GesFi under both single-pair and multi-pair settings using commodity WiFi transceivers, and evaluated it across multiple public
datasets and real-world environments. Compared to state-of-the-art baselines, GesFi achieves up to 78% and 50% performance improvements over existing
adversarial methods, and consistently outperforms prior generalization approaches across most cross-domain tasks.
Read the full abstract ▾
All authors Xiang Zhang, Huan Yan, Jinyang Huang, Bin Liu, Yuanhao Feng, Jianchun Liu, Meng Li, Fusang Zhang, Zhi Liu
Machine Learning · Cross-listed from cs.CV
EvalBlocks: A Modular Pipeline for Rapidly Evaluating Foundation Models in Medical Imaging
Jan Tagscherer, Sarah de Boer, Lena Philipp et al. (+7 more)
Developing foundation models in medical imaging requires continuous monitoring of downstream performance. Researchers are burdened with tracking numerous experiments, design choices, and their effects on performance, often relying on ad-hoc, manual workflows that are inherently slow and error-prone. We introduce EvalBlocks, a modular, plug-and-play framework for efficient evaluation of foundation models during development. Built on Snakemake, EvalBlocks supports seamless integration of new
datasets, foundation models, aggregation methods, and evaluation strategies. All experiments and results are tracked centrally and are reproducible with a single command, while efficient caching and parallel execution enable scalable use on shared compute infrastructure. Demonstrated on five state-of-the-art foundation models and three medical imaging classification tasks, EvalBlocks streamlines model evaluation, enabling researchers to iterate faster and focus on model innovation rather than evaluation logistics. The framework is released as open source software at https://github.com/DIAGNijmegen/eval-blocks.
Read the full abstract ▾
All authors Jan Tagscherer, Sarah de Boer, Lena Philipp, Fennie van der Graaf, Dré Peeters, Joeran Bosma, Lars Leijten, Bogdan Obreja, Ewoud Smit, Alessa Hering
Machine Learning · Cross-listed from cs.CV
From Brute Force to Semantic Insight: Performance-Guided Data Transformation Design with LLMs
Usha Shrestha, Dmitry Ignatov and Radu Timofte
Large
language models (LLMs) have achieved notable performance in code synthesis; however, data-aware augmentation remains a limiting factor, handled via heuristic design or brute-force approaches. We introduce a performance-aware, closed-loop solution in the NNGPT ecosystem of projects that enables LLMs to autonomously engineer optimal transformations by internalizing empirical performance cues. We fine-tune LLMs with Low-Rank Adaptation on a novel repository of more than 6,000 empirically evaluated PyTorch augmentation functions, each annotated solely by downstream model accuracy. Training uses pairwise performance ordering (better-worse transformations), enabling
alignment through empirical feedback without reinforcement learning, reward models, or symbolic objectives. This reduces the need for exhaustive search, achieving up to 600x times fewer evaluated candidates than brute-force discovery while maintaining competitive peak accuracy and shifting generation from random synthesis to task-aligned design. Ablation studies show that structured Chain-of-Thought prompting introduces syntactic noise and degrades performance, whereas direct prompting ensures stable optimization in performance-critical code tasks. Qualitative and quantitative analyses demonstrate that the model internalizes semantic performance cues rather than memorizing syntax. These results show that LLMs can exhibit task-level
reasoning through non-textual feedback loops, bypassing explicit symbolic rewards.
Read the full abstract ▾
Machine Learning
Detecting Semantic Backdoors in a Mystery Shopping Scenario
Arpad Berta, Gabor Danner, Istvan Hegedus et al. (+1 more)
Detecting semantic
backdoors in classification models–where some classes can be activated by certain natural, but out-of-distribution inputs–is an important problem that has received relatively little
attention. Semantic
backdoors are significantly harder to detect than
backdoors that are based on trigger patterns due to the lack of such clearly identifiable patterns. We tackle this problem under the assumption that the clean training
dataset and the training recipe of the model are both known. These assumptions are motivated by a consumer protection scenario, in which the responsible authority performs mystery shopping to test a machine learning service provider. In this scenario, the authority uses the provider's resources and tools to train a model on a given
dataset and tests whether the provider included a
backdoor. In our proposed approach, the authority creates a reference model pool by training a small number of clean and poisoned models using trusted infrastructure, and calibrates a model distance threshold to identify clean models. We propose and experimentally analyze a number of approaches to compute model distances and we also test a scenario where the provider performs an adaptive attack to avoid detection. The most reliable method is based on requesting
adversarial training from the provider. The model distance is best measured using a set of input samples generated by inverting the models in such a way as to maximize the distance from clean samples. With these settings, our method can often completely separate clean and poisoned models, and it proves to be superior to state-of-the-art
backdoor detectors as well.
Read the full abstract ▾
All authors Arpad Berta, Gabor Danner, Istvan Hegedus, Mark Jelasity
Machine Learning
Quantum vs. Classical Machine Learning: A Benchmark Study for Financial Prediction
Rehan Ahmad, Muhammad Kashif, Nouhaila Innan et al. (+1 more)
In this paper, we present a reproducible benchmarking framework that systematically compares QML models with architecture-matched classical counterparts across three financial tasks: (i) directional return prediction on U.S. and Turkish equities, (ii) live-trading simulation with
Quantum LSTMs versus classical LSTMs on the S&P 500, and (iii) realized
volatility forecasting using
Quantum Support Vector Regression. By standardizing data splits, features, and evaluation metrics, our study provides a fair assessment of when current-generation QML models can match or exceed classical methods. Our results reveal that
quantum approaches show performance gains when data structure and
circuit design are well aligned. In directional classification, hybrid
quantum neural networks surpass the parameter-matched ANN by +3.8 AUC and +3.4 accuracy points on AAPL stock and by +4.9 AUC and +3.6 accuracy points on Turkish stock KCHOL. In live trading, the QLSTM achieves higher risk-adjusted returns in two of four S&P~500 regimes. For
volatility forecasting, an angle-encoded QSVR attains the lowest QLIKE on KCHOL and remains within $\sim$0.02-0.04 QLIKE of the best classical kernels on S&P~500 and AAPL. Our benchmarking framework clearly identifies the scenarios where current QML architectures offer tangible improvements and where established classical methods continue to dominate.
Read the full abstract ▾
All authors Rehan Ahmad, Muhammad Kashif, Nouhaila Innan, Muhammad Shafique
Machine Learning · Cross-listed from cond-mat.mtrl-sci
Physically Consistent Machine Learning for Melting Temperature Prediction of Refractory High-Entropy Alloys
Mohd Hasnain
Predicting the melting temperature (Tm) of multi-component and high-
entropy alloys (HEAs) is critical for high-temperature applications but computationally expensive using traditional CALPHAD or DFT methods. In this work, we develop a gradient-boosted decision tree (XGBoost) model to predict Tm for complex
alloys based on elemental properties. To ensure physical consistency, we address the issue of data leakage by excluding temperature-dependent thermodynamic descriptors (such as Gibbs free energy of mixing) and instead rely on physically motivated elemental features. The optimized model achieves a coefficient of determination (R2) of 0.948 and a Mean Squared Error (MSE) of 9928 which is about 5% relative error for HEAs on a validation set of approximately 1300 compositions. Crucially, we validate the model using the Valence Electron Concentration (VEC) rule. Without explicit constraints during training, the model successfully captures the known stability transition between BCC and FCC phases at a VEC of approximately 6.87. These results demonstrate that data-driven models, when properly feature-engineered, can capture fundamental metallurgical principles for rapid
alloy screening.
Read the full abstract ▾
Machine Learning
Prompt Tuning without Labeled Samples for Zero-Shot Node Classification in Text-Attributed Graphs
Sethupathy Parameswaran, Suresh Sundaram and Yuan Fang
Node classification is a fundamental problem in information
retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) presents a significant challenge, particularly due to the absence of labeled data. In this paper, we propose a novel Zero-shot
Prompt Tuning (ZPT) framework to address this problem by leveraging a Universal Bimodal Conditional Generator (UBCG). Our approach begins with pre-training a graph-
language model to capture both the graph structure and the associated textual descriptions of each node. Following this, a conditional generative model is trained to learn the joint distribution of nodes in both graph and text modalities, enabling the generation of synthetic samples for each class based solely on the class name. These synthetic node and text
embeddings are subsequently used to perform continuous
prompt tuning, facilitating effective node classification in a zero-shot setting. Furthermore, we conduct extensive experiments on multiple
benchmark datasets, demonstrating that our framework performs better than existing state-of-the-art baselines. We also provide ablation studies to validate the contribution of the bimodal generator. The code is provided at: https://github.com/Sethup123/ZPT.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Compact Example-Based Explanations for Language Models
Loris Schoenegger and Benjamin Roth
Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents, only a small subset of the training data can be presented as an explanation. Although the choice of which documents to include directly affects explanation quality, previous evaluations of such systems have largely ignored any selection strategies. To address this, we propose a novel selection relevance score, a retraining-free metric that quantifies how useful a set of examples is for explaining a model's output. We validate this score through fine-tuning experiments, confirming that it can predict whether a set of examples supports or undermines the model's predictions. Using this metric, we further show that common selection strategies often underperform random selection. Motivated by this finding, we propose a strategy that balances influence and representativeness, enabling better use of selection budgets than naively selecting the highest-ranking examples.
Read the full abstract ▾
Machine Learning
Improving Compactness and Reducing Ambiguity of CFIRE Rule-Based Explanations
Sebastian Müller, Tobias Schneider, Ruben Kemna et al. (+1 more)
Models trained on tabular data are widely used in sensitive domains, increasing the demand for explanation methods to meet transparency needs. CFIRE is a recent
algorithm in this domain that constructs compact surrogate rule models from local explanations. While effective, CFIRE may assign rules associated with different classes to the same sample, introducing ambiguity. We investigate this ambiguity and propose a post-hoc
pruning strategy that removes rules with low contribution or conflicting coverage, yielding smaller and less ambiguous models while preserving fidelity. Experiments across multiple
datasets confirm these improvements with minimal impact on predictive performance.
Read the full abstract ▾
All authors Sebastian Müller, Tobias Schneider, Ruben Kemna, Vanessa Toborek
Machine Learning
Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model
Noam Levi
We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a latent “precision” drawn from a heavy-tailed distribution. While generalization loss recovers standard scaling laws, our main contribution connects this to inference. The pass@$k$ failure rate exhibits a power-law decay, $k^{-\beta_\text{eff}}$, but the observed exponent $\beta_\text{eff}$ is training-dependent. It grows with sample size $N$ before saturating at an intrinsic limit $\beta$ set by the difficulty distribution's tail. This coupling reveals that learning shrinks the “hard tail” of the error distribution: improvements in the model's generalization error steepen the pass@$k$ curve until irreducible target variance dominates. The LID model yields testable, closed-form predictions for this behavior, including a compute-allocation rule that favors training before saturation and inference attempts after. We validate these predictions in simulations and in two real-data proxies: CIFAR-10H (human-label variance) and a maths teacher-student
distillation task.
Read the full abstract ▾
Machine Learning
Probabilistic Transformers for Joint Modeling of Global Weather Dynamics and Decision-Centric Variables
Paulius Rauba, Viktor Cikojevic, Fran Bartolic et al. (+3 more)
Weather forecasts sit upstream of high-stakes decisions in domains such as grid operations, aviation, agriculture, and emergency response. Yet forecast users often face a difficult trade-off. Many decision-relevant targets are functionals of the atmospheric state variables, such as extrema, accumulations, and threshold exceedances, rather than state variables themselves. As a result, users must estimate these targets via post-processing, which can be suboptimal and can introduce structural bias. The core issue is that decisions depend on distributions over these functionals that the model is not trained to learn directly. In this work, we introduce GEM-2, a probabilistic
transformer that jointly learns global atmospheric dynamics alongside a suite of variables that users directly act upon. Using this training recipe, we show that a lightweight (~275M params) and computationally efficient (~20-100x training speedup relative to state-of-the-art)
transformer trained on the CRPS objective can directly outperform operational numerical weather prediction (NWP) models and be competitive with ML models that rely on expensive multi-step
diffusion processes or require bespoke multi-stage fine-tuning strategies. We further demonstrate state-of-the-art economic value metrics under decision-theoretic evaluation, stable convergence to climatology at S2S and seasonal timescales, and a surprising insensitivity to many commonly assumed architectural and training design choices.
Read the full abstract ▾
All authors Paulius Rauba, Viktor Cikojevic, Fran Bartolic, Sam Levang, Ty Dickinson, Chase Dwelle
Machine Learning · Cross-listed from cs.CV
RadDiff: Describing Differences in Radiology Image Sets with Natural Language
Xiaoxian Shen, Yuhui Zhang, Sahithi Ankireddy et al. (+5 more)
Understanding how two radiology image sets differ is critical for generating clinical insights and for interpreting medical AI systems. We introduce RadDiff, a
multimodal agentic system that performs radiologist-style comparative
reasoning to describe clinically meaningful differences between paired radiology studies. RadDiff builds on a proposer-ranker framework from VisDiff, and incorporates four innovations inspired by real diagnostic workflows: (1) medical knowledge injection through domain-adapted
vision-
language models; (2)
multimodal reasoning that integrates images with their clinical reports; (3) iterative hypothesis refinement across multiple
reasoning rounds; and (4) targeted visual search that localizes and zooms in on salient regions to capture subtle findings. To evaluate RadDiff, we construct RadDiffBench, a challenging
benchmark comprising 57 expert-validated radiology study pairs with ground-truth difference descriptions. On RadDiffBench, RadDiff achieves 47% accuracy, and 50% accuracy when guided by ground-truth reports, significantly outperforming the general-domain VisDiff baseline. We further demonstrate RadDiff's versatility across diverse clinical tasks, including COVID-19 phenotype comparison, racial subgroup analysis, and discovery of survival-related imaging features. Together, RadDiff and RadDiffBench provide the first method-and-
benchmark foundation for systematically uncovering meaningful differences in radiological data.
Read the full abstract ▾
All authors Xiaoxian Shen, Yuhui Zhang, Sahithi Ankireddy, Xiaohan Wang, Maya Varma, Henry Guo, Curtis Langlotz, Serena Yeung-Levy
Machine Learning
EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
Jing-Cheng Pang, Liu Sun, Chang Zhou et al. (+10 more)
Domain-specific large
language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized
datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is curriculum learning, which pre-orders training samples based on metrics like difficulty to improve learning efficiency compared to a random sampling strategy. However, most existing methods for LLM fine-tuning rely on a static curriculum, designed prior to training, which lacks adaptability to the model's evolving needs during fine-tuning. To address this, we propose EDCO, a novel framework based on two key concepts: inference
entropy and dynamic curriculum orchestration. Inspired by recent findings that maintaining high answer
entropy benefits long-term
reasoning gains, EDCO prioritizes samples with high inference
entropy in a continuously adapted curriculum. EDCO integrates three core components: an efficient
entropy estimator that uses prefix
tokens to approximate full-sequence
entropy, an
entropy-based curriculum generator that selects data points with the highest inference
entropy, and an LLM trainer that optimizes the model on the selected curriculum. Comprehensive experiments in communication, medicine and law domains, EDCO outperforms traditional curriculum strategies for fine-tuning Qwen3-4B and Llama3.2-3B models under supervised and reinforcement learning settings. Furthermore, the proposed efficient
entropy estimation reduces computational time by 83.5% while maintaining high accuracy.
Read the full abstract ▾
All authors Jing-Cheng Pang, Liu Sun, Chang Zhou, Xian Tang, Haichuan Ma, Kun Jiang, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai, Chenwei Wu, Xubin Li, Xin Chen
Machine Learning
ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization
Shijie Zhang, Kevin Zhang, Zheyuan Gu et al. (+5 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking
reasoning capabilities in large
language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative Policy Optimization (GRPO) stands as the dominant
algorithm in this domain due to its stable training and critic-free efficiency. However, we argue that GRPO suffers from a structural limitation: it imposes a uniform, static trust region constraint across all samples. This design implicitly assumes signal homogeneity, a premise misaligned with the heterogeneous nature of outcome-driven learning, where advantage magnitudes and variances fluctuate significantly. Consequently, static constraints fail to fully exploit high-quality signals while insufficiently suppressing noise, often precipitating rapid
entropy collapse. To address this, we propose Elastic Trust Regions (ETR), a dynamic mechanism that aligns optimization constraints with signal quality. ETR constructs a signal-aware landscape through dual-level elasticity: at the micro level, it scales clipping boundaries based on advantage magnitude to accelerate learning from high-confidence paths; at the macro level, it leverages group variance to implicitly allocate larger update budgets to tasks in the optimal learning zone. Extensive experiments on AIME and MATH
benchmarks demonstrate that ETR consistently outperforms GRPO, achieving superior accuracy while effectively mitigating policy
entropy degradation to ensure sustained exploration.
Read the full abstract ▾
All authors Shijie Zhang, Kevin Zhang, Zheyuan Gu, Xiang Guo, Rujun Guo, Shaoyu Liu, Guanjun Jiang, Xiaozhao Wang
Machine Learning
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
Weijie Shi, Yanxi Chen, Zexi Li et al. (+5 more)
Reinforcement learning drives recent advances in LLM
reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with
Language-Guided Exploration, Pivotal Credit, and Positive Amplification. To synthesize high-quality trajectories, R$^3$L shifts from
stochastic sampling to active synthesis via reflect-then-retry, leveraging
language feedback to diagnose errors, transform failed attempts into successful ones, and reduce rollout costs by restarting from identified failure points. With errors diagnosed and localized, Pivotal Credit Assignment updates only the diverging suffix where contrastive signals exist, excluding the shared prefix from gradient update. Since failures dominate on difficult tasks and reflect-then-retry produces off-policy data, risking training instability, Positive Amplification upweights successful trajectories to ensure positive signals guide the optimization process. Experiments on agentic and
reasoning tasks demonstrate 5% to 52% relative improvements over baselines while maintaining training stability. Our code is released at https://github.com/shiweijiezero/R3L.
Read the full abstract ▾
All authors Weijie Shi, Yanxi Chen, Zexi Li, Xuchen Pan, Yuchang Sun, Jiajie Xu, Xiaofang Zhou, Yaliang Li
Machine Learning
The Geometry of the Pivot: A Note on Lazy Pivoted Cholesky and Farthest Point Sampling
Gil Shabat
Low-rank approximations of large kernel
matrices are ubiquitous in machine learning, particularly for scaling Gaussian Processes to massive
datasets. The Pivoted Cholesky decomposition is a standard tool for this task, offering a computationally efficient, greedy low-rank approximation. While its algebraic properties are well-documented in numerical linear
algebra, its
geometric intuition within the context of kernel methods often remains obscure. In this note, we elucidate the
geometric interpretation of the
algorithm within the Reproducing Kernel
Hilbert Space (RKHS). We demonstrate that the pivotal selection step is mathematically equivalent to Farthest Point Sampling (FPS) using the kernel metric, and that the Cholesky factor construction is an implicit Gram-Schmidt orthogonalization. We provide a concise derivation and a minimalist Python implementation to bridge the gap between theory and practice.
Read the full abstract ▾
Machine Learning
Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction
Wajid Arshad Abbasi, Syed Ali Abbas, Maryum Bibi et al. (+2 more)
The trade-off between predictive accuracy and data availability makes it difficult to predict
protein–
protein binding affinity accurately. The lack of experimentally resolved
protein structures limits the performance of structure-based machine learning models, which generally outperform sequence-based methods. In order to overcome this constraint, we suggest a regression framework based on knowledge
distillation that uses
protein structural data during training and only needs sequence data during inference. The suggested method uses binding affinity labels and intermediate feature representations to jointly supervise the training of a sequence-based student network under the guidance of a structure-informed teacher network. Leave-One-Complex-Out (LOCO) cross-validation was used to assess the framework on a non-redundant
protein–
protein binding affinity
benchmark dataset. A maximum Pearson correlation coefficient (P_r) of 0.375 and an RMSE of 2.712 kcal/mol were obtained by sequence-only baseline models, whereas a P_r of 0.512 and an RMSE of 2.445 kcal/mol were obtained by structure-based models. With a P_r of 0.481 and an RMSE of 2.488 kcal/mol, the
distillation-based student model greatly enhanced sequence-only performance. Improved agreement and decreased bias were further confirmed by thorough error analyses. With the potential to close the performance gap between sequence-based and structure-based models as larger
datasets become available, these findings show that knowledge
distillation is an efficient method for transferring structural knowledge to sequence-based predictors. The source code for running inference with the proposed
distillation-based binding affinity predictor can be accessed at https://github.com/wajidarshad/ProteinAffinityKD.
Read the full abstract ▾
All authors Wajid Arshad Abbasi, Syed Ali Abbas, Maryum Bibi, Saiqa Andleeb, Muhammad Naveed Akhtar
Machine Learning
TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL
Lang Cao, Hui Ruan, Yongqian Li et al. (+5 more)
Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large
language models on complex
reasoning tasks. However, standard GRPO treats each rollout trajectory as an independent flat sequence and assigns a single sequence-level advantage to all
tokens, which leads to sample inefficiency and a length bias toward verbose, redundant chains of thought without improving logical depth. We introduce TreeAdv (Tree-Structured Advantage Redistribution for Group-Based RL), which makes the tree structure of group rollouts explicit for both exploration and advantage assignment. Specifically, TreeAdv builds a group of trees (a forest) based on an
entropy-driven sampling method where each tree branches at high-uncertainty decisions while sharing low-uncertainty
tokens across rollouts. Then, TreeAdv aggregates
token-level advantages for internal tree segments by redistributing the advantages of complete rollouts (all leaf nodes), and TreeAdv can easily apply to group-based objectives such as GRPO or GSPO. Across 10 math
reasoning benchmarks, TreeAdv consistently outperforms GRPO and GSPO, while using substantially fewer generated
tokens under identical supervision, data, and decoding budgets.
Read the full abstract ▾
All authors Lang Cao, Hui Ruan, Yongqian Li, Peng Chao, Wu Ning, Haonan Song, Renhong Chen, Yitong Li
Machine Learning
Inference Attacks Against Graph Generative Diffusion Models
Xiuling Wang, Xin Huang, Guibo Luo et al. (+1 more)
Graph generative
diffusion models have recently emerged as a powerful paradigm for generating complex graph structures, effectively capturing intricate dependencies and relationships within graph data. However, the
privacy risks associated with these models remain largely unexplored. In this paper, we investigate information leakage in such models through three types of black-box inference attacks. First, we design a graph reconstruction attack, which can reconstruct graphs structurally similar to those training graphs from the generated graphs. Second, we propose a property inference attack to infer the properties of the training graphs, such as the average graph density and the distribution of densities, from the generated graphs. Third, we develop two membership inference attacks to determine whether a given graph is present in the training set. Extensive experiments on three different types of graph generative
diffusion models and six real-world graphs demonstrate the effectiveness of these attacks, significantly outperforming the baseline approaches. Finally, we propose two defense mechanisms that mitigate these inference attacks and achieve a better trade-off between defense strength and target model utility than existing methods. Our code is available at https://zenodo.org/records/17946102.
Read the full abstract ▾
All authors Xiuling Wang, Xin Huang, Guibo Luo, Jianliang Xu
Machine Learning
A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns
Weiqi Liu, Fenglei Cao, Yuan Qi et al. (+1 more)
With the rise of data-driven reaction prediction models, effective reaction descriptors are crucial for bridging the gap between real-world chemistry and digital representations. However, general-purpose, reaction-wise descriptors remain scarce. This study introduces RXNEmb, a novel reaction-level descriptor derived from RXNGraphormer, a model pre-trained to distinguish real reactions from fictitious ones with erroneous bond changes, thereby learning intrinsic bond formation and cleavage patterns. We demonstrate its utility by data-driven re-clustering of the USPTO-50k
dataset, yielding a classification that more directly reflects bond-change similarities than rule-based categories. Combined with dimensionality reduction, RXNEmb enables visualization of reaction space diversity. Furthermore,
attention weight analysis reveals the model's focus on chemically critical sites, providing mechanistic insight. RXNEmb serves as a powerful, interpretable tool for reaction fingerprinting and analysis, paving the way for more data-centric approaches in reaction analysis and discovery.
Read the full abstract ▾
All authors Weiqi Liu, Fenglei Cao, Yuan Qi, Li-Cheng Xu
Machine Learning
Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimization
Xin Lai, Shiming Deng, Lu Yu et al. (+3 more)
Time series
forecasting plays a crucial role in contemporary engineering information systems for supporting decision-making across various industries, where Recurrent Neural Networks (RNNs) have been widely adopted due to their capability in modeling sequential data. Conventional RNN-based predictors adopt an encoder-only strategy with sliding historical windows as inputs to forecast future values. However, this approach treats all time steps and hidden states equally without considering their distinct contributions to
forecasting, leading to suboptimal performance. To address this limitation, we propose a novel Reinforced Recurrent Encoder with Prediction-oriented Proximal Policy Optimization, RRE-PPO4Pred, which significantly improves time series modeling capacity and
forecasting accuracy of the RNN models. The core innovations of this method are: (1) A novel Reinforced Recurrent Encoder (RRE) framework that enhances RNNs by formulating their internal adaptation as a Markov Decision Process, creating a unified decision environment capable of learning input feature selection, hidden skip connection, and output target selection; (2) An improved Prediction-oriented Proximal Policy Optimization
algorithm, termed PPO4Pred, which is equipped with a
Transformer-based
agent for temporal
reasoning and develops a dynamic transition sampling strategy to enhance sampling efficiency; (3) A co-evolutionary optimization paradigm to facilitate the learning of the RNN predictor and the policy
agent, providing adaptive and interactive time series modeling. Comprehensive evaluations on five real-world
datasets indicate that our method consistently outperforms existing baselines, and attains accuracy better than state-of-the-art
Transformer models, thus providing an advanced time series predictor in engineering informatics.
Read the full abstract ▾
All authors Xin Lai, Shiming Deng, Lu Yu, Yumin Lai, Shenghao Qiao, Xinze Zhang
Machine Learning · Cross-listed from eess.SY
Accounting for Optimal Control in the Sizing of Isolated Hybrid Renewable Energy Systems Using Imitation Learning
Simon Halvdansson, Lucas Ferreira Bernardino and Brage Rugstad Knudsen
Decarbonization of isolated or off-grid energy systems through phase-in of large shares of intermittent
solar or wind generation requires co-installation of energy storage or continued use of existing fossil dispatchable power sources to balance supply and demand. The effective CO2 emission reduction depends on the relative capacity of the energy storage and renewable sources, the stochasticity of the renewable generation, and the control of the isolated energy system. While the operation of the energy storage and dispatchable sources impacts the optimal sizing of the system, it is challenging to account for the effect of finite-horizon optimal control at the stage of system sizing. In this work, we present a flexible and computationally efficient sizing framework for energy storage and renewable capacity in isolated energy systems, accounting for uncertainty in the renewable generation and the optimal control. We implement an imitation learning approach to
stochastic neural model predictive control (MPC) which allows us to relate the battery storage and wind peak capacities to the emissions reduction and investment costs while accounting for finite horizon, optimal control without solving an infeasible number of optimization problems. We evaluate the proposed sizing framework on a case study of an offshore energy system with a gas turbine, a wind farm and a battery energy storage system (BESS). In this case, we find a nonlinear, nontrivial relationship between the investment costs and the reduction in gas usage for different wind and BESS capacities.
Read the full abstract ▾
Machine Learning
Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics
Ibai Ramirez, Jokin Alcibar, Joel Pino et al. (+2 more)
Physics-Informed Neural Networks (PINNs) provide a framework for integrating physical laws with data. However, their application to Prognostics and Health Management (PHM) remains constrained by the limited uncertainty quantification (UQ) capabilities. Most existing PINN-based prognostics approaches are deterministic or account only for epistemic uncertainty, limiting their suitability for risk-aware decision-making. This work introduces a heteroscedastic
Bayesian Physics-Informed Neural Network (B-PINN) framework that jointly models epistemic and aleatoric uncertainty, yielding full predictive posteriors for spatiotemporal insulation material ageing estimation. The approach integrates
Bayesian Neural Networks (BNNs) with physics-based residual enforcement and prior distributions, enabling probabilistic inference within a physics-informed learning architecture. The framework is evaluated on
transformer insulation ageing application, validated with a finite-element thermal model and field measurements from a
solar power plant, and benchmarked against deterministic PINNs, dropout-based PINNs (d-PINNs), and alternative B-PINN variants. Results show that the proposed B-PINN provides improved predictive accuracy and better-calibrated uncertainty estimates than competing approaches. A systematic sensitivity study further analyzes the impact of boundary-condition, initial-condition, and residual sampling strategies on accuracy, calibration, and generalization, and the influence of measurement noise on aleatoric uncertainty. Overall, the findings highlight the capability of
Bayesian physics-informed learning to support uncertainty-aware prognostics and informed decision-making in
transformer asset management by tracking aleatoric and epistemic sources of uncertainty.
Read the full abstract ▾
All authors Ibai Ramirez, Jokin Alcibar, Joel Pino, Mikel Sanz, Jose I. Aizpurua
Machine Learning · Cross-listed from cs.CL
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
Weiqi Liu, Yongliang Miao, Haiyan Zhao et al. (+2 more)
Neuron-level interpretation in large
language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual
neurons respond to multiple distinct semantic concepts. Existing single-pass interpretation methods struggle to faithfully capture such multi-concept behavior. In this work, we propose NeuronScope, a multi-
agent framework that reformulates
neuron interpretation as an iterative, activation-guided process. NeuronScope explicitly deconstructs
neuron activations into atomic semantic components, clusters them into distinct semantic modes, and iteratively refines each explanation using
neuron activation feedback. Experiments demonstrate that NeuronScope uncovers hidden polysemanticity and produces explanations with significantly higher activation correlation compared to single-pass baselines.
Read the full abstract ▾
All authors Weiqi Liu, Yongliang Miao, Haiyan Zhao, Yanguang Liu, Mengnan Du