Machine Learning
Computationally lightweight classifiers with frequentist bounds on predictions
Shreeram Murali, Cristian R. Rojas and Dominik Baumann
While both classical and neural network classifiers can achieve high accuracy, they fall short on offering uncertainty bounds on their predictions, making them unfit for safety-critical applications. Existing kernel-based classifiers that provide such bounds scale with $\mathcal O (n^{\sim3})$ in time, making them computationally intractable for large
datasets. To address this, we propose a novel, computationally efficient classification
algorithm based on the Nadaraya-Watson
estimator, for whose estimates we derive frequentist uncertainty intervals. We evaluate our classifier on synthetically generated data and on electrocardiographic heartbeat signals from the MIT-BIH Arrhythmia database. We show that the method achieves competitive accuracy $>$\SI{96}{\percent} at $\mathcal O(n)$ and $\mathcal O(\log n)$ operations, while providing actionable uncertainty bounds. These bounds can, e.g., aid in flagging low-confidence predictions, making them suitable for real-time settings with resource constraints, such as diagnostic monitoring or implantable devices.
Read the full abstract ▾
Machine Learning
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
Kexin Huang, Haoming Meng, Junkang Wu et al. (+10 more)
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the
reasoning capabilities of large
language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the magnitude of these updates, largely overlooking their direction. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed,
token-level log probability difference $\Delta\log p$ between the base and final RLVR models. Through statistical analysis and
token-replacement interventions, we demonstrate that $\Delta\log p$ more effectively identifies sparse, yet
reasoning-critical updates than magnitude-based metrics (\eg divergence or
entropy). Building on this insight, we propose two practical applications: (1) a test-time extrapolation method that amplifies the policy along the learned $\Delta\log p$ direction to improve
reasoning accuracy without further training; (2) a training-time reweighting method that focuses learning on low-probability (corresponding to higher $\Delta\log p$)
tokens, which improves
reasoning performance across models and
benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.
Read the full abstract ▾
All authors Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou
Machine Learning · Cross-listed from cs.AI
SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
Syed Usama Imtiaz, Mitra Nasr Azadani and Nasrin Alamdari
Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on
stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed masking design that encourages the reconstruction of targeted bands from cross-spectral context during pretraining. To achieve this, we developed an adaptable multi-task (band reconstruction, bio-optical index inference, and 8-day-ahead temporal prediction) self-supervised learning (SSL) framework that encodes spectrally intrinsic representations via joint optimization, and evaluated it on a downstream microcystin concentration regression model using NASA PACE hyperspectral imagery over Lake Erie. SpecTM achieves R^2 = 0.695 (current week) and R^2 = 0.620 (8-day-ahead) predictions surpassing all baseline models by (+34% (0.51 Ridge) and +99% (SVR 0.31)) respectively. Our ablation experiments show targeted masking improves predictions by +0.037 R^2 over random masking. Furthermore, it outperforms strong baselines with 2.2x superior label efficiency under extreme scarcity. SpecTM enables physics-informed representation learning across EO domains and improves the interpretability of foundation models.
Read the full abstract ▾
Machine Learning
MIHT: A Hoeffding Tree for Time Series Classification using Multiple Instance Learning
Aurora Esteban, Amelia Zafra and Sebastián Ventura
Due to the prevalence of temporal data and its inherent dependencies in many real-world problems, time series classification is of paramount importance in various domains. However, existing models often struggle with series of variable length or high dimensionality. This paper introduces the MIHT (Multi-instance Hoeffding Tree)
algorithm, an efficient model that uses multi-instance learning to classify multivariate and variable-length time series while providing interpretable results. The
algorithm uses a novel representation of time series as "bags of subseries," together with an optimization process based on incremental decision trees that distinguish relevant parts of the series from noise. This methodology extracts the underlying concept of series with multiple variables and variable lengths. The generated decision tree is a compact, white-box representation of the series' concept, providing interpretability insights into the most relevant variables and segments of the series. Experimental results demonstrate MIHT's superiority, as it outperforms 11 state-of-the-art time series classification models on 28 public
datasets, including high-dimensional ones. MIHT offers enhanced accuracy and interpretability, making it a promising solution for handling complex, dynamic time series data.
Read the full abstract ▾
Machine Learning
On the Failure of Topic-Matched Contrast Baselines in Multi-Directional Refusal Abliteration
Valentin Petrov
Inasmuch as the removal of refusal behavior from instruction-tuned
language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the construction of the contrast baseline against which harmful
prompt activations are compared has been treated in the existing literature as an implementation detail rather than a methodological concern, the present work investigates whether a topically matched contrast baseline yields superior refusal directions. The investigation is carried out on the Qwen~3.5 2B model using per-category matched
prompt pairs, per-class Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. It was found that topic-matched contrast produces no functional refusal directions at any tested weight level on any tested layer, while unmatched contrast on the same model, same extraction code, and same evaluation protocol achieves complete refusal elimination on six layers. The
geometric analysis of the failure establishes that topic-matched subtraction cancels the dominant activation component shared between harmful and harmless
prompts of the same subject, reducing the extracted direction magnitude below the threshold at which weight-
matrix projection perturbs the residual stream. The implications for the design of contrast baselines in abliteration research are discussed.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.SD
AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference
Risa Shinoda, Kaede Shiohara, Nakamasa Inoue et al. (+2 more)
Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring. Recent advances in deep learning have enabled automatic species classification from their vocalizations. However, classifying species unseen during training remains challenging. To address this limitation, we introduce AnimalCLAP, a taxonomy-aware
language-audio framework comprising a new
dataset and model that incorporate hierarchical biological information. Specifically, our vocalization
dataset consists of 4,225 hours of recordings covering 6,823 species, annotated with 22 ecological traits. The AnimalCLAP model is trained on this
dataset to align audio and textual representations using taxonomic structures, improving the recognition of unseen species. We demonstrate that our proposed model effectively infers ecological and biological attributes of species directly from their vocalizations, achieving superior performance compared to CLAP. Our
dataset, code, and models will be publicly available at https://dahlian00.github.io/AnimalCLAP_Page/.
Read the full abstract ▾
All authors Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura
Machine Learning · Cross-listed from stat.ML
Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data
Atticus Rex, Elizabeth Qian and David Peterson
Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning methods have demonstrated promise in learning efficient surrogate models that can (partially) replace expensive high-fidelity models, making many-query analyses, such as optimization, uncertainty quantification, and inference, tractable. However, when training data must be obtained through the evaluation of an expensive model or experiment, the amount of training data that can be obtained is often limited, which can make learned surrogate models unreliable. In many engineering and scientific settings, cheaper low-fidelity models may be available, for example arising from simplified physics modeling or coarse grids. These models may be used to generate additional low-fidelity training data. The goal of multifidelity machine learning is to use both high- and low-fidelity training data to learn a surrogate model which is cheaper to evaluate than the high-fidelity model, but more accurate than any available low-fidelity model. This work proposes a new multifidelity training approach for Gaussian process regression which uses low-fidelity data to define additional features that augment the input space of the learned model. Similarly to cokriging
estimators, the proposed approach conditions the high-fidelity surrogate model on the predictions of all available low-fidelity surrogate models, while benefiting from the computational efficiency of autoregressive
estimators. Numerical experiments on several test problems demonstrate both increased predictive accuracy and reduced computational cost relative to the state of the art.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning
Dong Heon Cho and Boyuan Chen
Differentiable simulators enable gradient-based optimization of soft
robots over material parameters, control, and morphology, but accurately modeling real systems remains challenging due to the sim-to-real gap. This issue becomes more pronounced when geometry is itself a design variable. System identification reduces discrepancies by fitting global material parameters to data; however, when constitutive models are misspecified or observations are sparse, identified parameters often absorb geometry-dependent effects rather than reflect intrinsic material behavior. More expressive constitutive models can improve accuracy but substantially increase computational cost, limiting practicality. We propose a residual acceleration field learning (RAFL) framework that augments a base simulator with a transferable, element-level corrective dynamics field. Operating on shared local features, the model is agnostic to global mesh
topology and discretization. Trained end-to-end through a differentiable simulator using sparse marker observations, the learned residual generalizes across shapes. In both sim-to-sim and sim-to-real experiments, our method achieves consistent zero-shot improvements on unseen morphologies, while system identification frequently exhibits negative transfer. The framework also supports continual refinement, enabling simulation accuracy to accumulate during morphology optimization.
Read the full abstract ▾
Machine Learning
On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
Julius Kobialka, Emanuel Sommer, Chris Kolb et al. (+3 more)
Bayesian neural network (BNN) posteriors are often considered impractical for inference, as
symmetries fragment them, non-identifiabilities inflate dimensionality, and weight-space priors are seen as meaningless. In this work, we study how overparametrization and priors together reshape BNN posteriors and derive implications allowing us to better understand their interplay. We show that redundancy introduces three key phenomena that fundamentally reshape the posterior geometry: balancedness, weight reallocation on equal-probability
manifolds, and prior conformity. We validate our findings through extensive experiments with posterior sampling budgets that far exceed those of earlier works, and demonstrate how overparametrization induces structured, prior-aligned weight posterior distributions.
Read the full abstract ▾
All authors Julius Kobialka, Emanuel Sommer, Chris Kolb, Juntae Kwon, Daniel Dold, David Rügamer
Machine Learning
Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics
Tianxiang Xu, Xiaoyan Zhu, Xin Lai et al. (+4 more)
As bioinformatics software is increasingly applied across a broader range of scenarios and the rapid development of large
language models (LLMs) further lowers the barriers to software use and development, the composition of the bioinformatics research community is undergoing substantial change. Consequently, a growing number of researchers require a deeper understanding of methodological details and software behavior. In this context, systematically analyzing the relationship between paper descriptions and code implementations is emerging as an important new challenge in the field. To address this challenge, we introduce paper-code consistency analysis as a new research perspective and construct BioCon, the first
benchmark dataset for paper-code consistency analysis in bioinformatics. Furthermore, we develop a unified cross-modal analysis framework to systematically investigate this problem from three perspectives: sentence-level detection, cross-modal
retrieval, and project-level assessment. Experimental results demonstrate that the proposed framework can effectively model the semantic relationships between scientific publications and software implementations. Further case studies reveal that paper-code inconsistency is not a single phenomenon but arises from multiple underlying causes, among which Author-Perceived Non-Essential Details represents the most prevalent category. These findings suggest that paper-code consistency analysis is not merely a technical problem but also raises broader discussions regarding knowledge dissemination, the boundaries of code disclosure, and community norms. We hope that this work will encourage the bioinformatics community to re-examine the relationship between scientific publications and software implementations while providing a foundation for future research in paper-code consistency analysis.
Read the full abstract ▾
All authors Tianxiang Xu, Xiaoyan Zhu, Xin Lai, Xin Lian, Sizhe Dang, Hangyu Cheng, Jiayin Wang
Machine Learning
Domain Adapted Large Language Models for Additive Manufacturing
Peter Pak and Amir Barati Farimani
This work presents a collection of multi-modal domain adapted large
language models built upon the instruction tuned variants of open weight models (Gemma 3, Qwen 3, Gemma 4) using a relatively small
dataset of around 50 million
tokens. The
dataset consists of open-access additive manufacturing journal articles with data extracted for the domain adaptive pretraining and visual instruction tuning processes. Various stages of the developed model are evaluated with the Additive-Manufacturing-
Benchmark which consists of additive manufacturing domain specific tasks compiled published resources. Domain adapted and instruction tuned models exhibit proficiency in both
language and
vision based tasks, achieving accuracies upwards of 90% in general additive manufacturing knowledge. This domain adaptive pretraining and instruction tuning strategy outline an accessible specialization method for large
language models to a domain such as additive manufacturing.
Read the full abstract ▾
Machine Learning
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
Xinyan Wang, Xiaogeng Liu, Ming Pei et al. (+1 more)
Large
reasoning models (LRMs) often suffer from overthinking, continuing with redundant verification and repeated attempts even after reaching a correct solution. This wastes computation and can overturn an initially correct answer. We show that the transition from productive to redundant
reasoning is decodable from late-layer hidden states. These representations separate the two phases around first-correct-solution boundaries beyond what position and lexical controls explain, and distinguish correct from incorrect solution endings. Building on this finding, we propose ROM (Real-time Overthinking Mitigation), which uses a lightweight streaming detector (0.07–0.25% of backbone parameters) to monitor a frozen LRM and intervene at well-formed
reasoning boundaries without answer extraction or probe decoding. Counterfactual Self-Correction (CSC) augments detector training with wrong$\rightarrow$correct trajectories to preserve useful self-correction. Heads are trained separately for each backbone using shared MATH500 supervision and transfer zero-shot to four unseen
benchmarks. Evaluated against ten baselines across five backbones from three families and five
benchmarks, ROM$_{\text{CSC}}$ reduces response length by 28–77% (45% on average), with significant reductions in all 25 settings and accuracy matching or exceeding vanilla decoding in 22. Measurements on two backbones further show 20–70% lower end-to-end latency with less than 0.5% detector overhead per decoding step. Code is available at https://github.com/SaFo-Lab/ROM.
Read the full abstract ▾
All authors Xinyan Wang, Xiaogeng Liu, Ming Pei, Chaowei Xiao
Machine Learning · Cross-listed from astro-ph.CO
A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping
Hubert Leterme, Andreas Tersenov, Jalal Fadili et al. (+1 more)
Upcoming stage-IV surveys such as Euclid and Rubin will deliver vast amounts of high-precision data, opening new opportunities to constrain cosmological models with unprecedented accuracy. A key step in this process is the reconstruction of the dark matter distribution from noisy weak-
lensing shear measurements. Current deep-learning-based mass-mapping methods achieve high reconstruction accuracy, but either require retraining a model for each new observed sky region (limiting practicality) or rely on slow Markov chain Monte Carlo sampling. Efficient exploitation of future survey data therefore calls for a new method that is accurate, flexible, and fast at inference. In addition, an uncertainty quantification with coverage guarantees is essential for a reliable cosmological parameter estimation. We introduce PnPMass, a plug-and-play approach for weak-
lensing mass mapping. The
algorithm produces point estimates by alternating between a gradient descent step with a carefully chosen data fidelity term and a denoising step implemented with a single deep-learning model trained on simulated data corrupted by Gaussian white noise. We also propose a fast sampling-free uncertainty quantification scheme based on moment networks, with calibrated error bars obtained through conformal prediction to ensure coverage guarantees. Finally, we
benchmark PnPMass against model-driven and data-driven mass-mapping techniques. PnPMass achieves a performance close to that of the currently best deep-learning methods while offering fast inference. It converges in just a few iterations, and it requires only a single training phase, regardless of the noise covariance of the observations. It therefore combines flexibility, efficiency, and reconstruction accuracy while delivering tighter error bars than existing approaches, making it well suited for upcoming weak-
lensing surveys.
Read the full abstract ▾
All authors Hubert Leterme, Andreas Tersenov, Jalal Fadili, Jean-Luc Starck
Machine Learning
CRPS-Optimal Binning for Univariate Conformal Regression
Paolo Toccaceli
We propose a method for non-parametric conditional distribution estimation based on partitioning
covariate-sorted observations into contiguous bins and using the within-bin empirical CDF as the predictive distribution. Bin boundaries are chosen to minimise the total leave-one-out Continuous Ranked Probability Score (LOO-CRPS), which admits a closed-form cost function with $O(n^2 \log n)$ precomputation and $O(n^2)$ storage; the globally optimal $K$-partition is recovered by a dynamic programme in $O(n^2 K)$ time. Minimisation of within-sample LOO-CRPS turns out to be inappropriate for selecting $K$ as it results in in-sample optimism. We instead select $K$ by $K$-fold cross-validation of test CRPS, which yields a U-shaped criterion with a well-defined minimum. Having selected $K^*$ and fitted the full-data partition, we form two complementary predictive objects: the Venn prediction band and a conformal prediction set based on CRPS as the nonconformity score, which carries a finite-sample marginal coverage guarantee at any prescribed level $\varepsilon$. The conformal prediction is transductive and data-efficient, as all observations are used for both partitioning and p-value calculation, with no need to reserve a hold-out set. On real
benchmarks against split-conformal competitors (Gaussian split conformal, CQR, CQR-QRF, and conformalized isotonic distributional regression), the method produces substantially narrower prediction intervals while maintaining near-nominal coverage.
Read the full abstract ▾
Machine Learning
$\lambda$-GELU: Learning Gating Hardness for Controlled ReLU-ization in Deep Networks
Cristian Pérez-Corral, Alberto Fernández-Hernández, Jose I. Mestre et al. (+2 more)
Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We study a hardness-parameterized formulation of GELU, f(x;{\lambda})=x{\Phi}({\lambda} x), where {\Phi} is the Gaussian CDF and {\lambda} \in [1, infty) controls gate sharpness, with the goal of turning smooth gated training into a controlled path toward ReLU-compatible models. Learning {\lambda} is non-trivial: naive updates yield unstable dynamics and effective gradient attenuation, so we introduce a constrained reparameterization and an optimizer-aware update scheme. Empirically, across a diverse set of model–
dataset pairs spanning MLPs, CNNs, and
Transformers, we observe structured layerwise hardness profiles and assess their robustness under different initializations. We further study a deterministic ReLU-ization strategy in which the learned gates are progressively hardened toward a principled target, enabling a post-training substitution of {\lambda}-GELU by ReLU with reduced disruption. Overall, {\lambda}-GELU provides a minimal and interpretable knob to profile and control gating hardness, bridging smooth training with ReLU-centric downstream pipelines.
Read the full abstract ▾
All authors Cristian Pérez-Corral, Alberto Fernández-Hernández, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ortí
Machine Learning
TREX: Trajectory Explanations for Multi-Objective Reinforcement Learning
Dilina Rajapakse, Juan C. Rosero and Ivana Dusparic
Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems in a variety of domains, by optimizing reward signals obtained through interaction with an environment. However, many real-world scenarios involve multiple, potentially conflicting objectives that cannot be easily represented by a single scalar reward. Multi-Objective Reinforcement Learning (MORL) addresses this limitation by enabling
agents to optimize several objectives simultaneously, explicitly
reasoning about trade-offs between them. However, the “black box" nature of the RL models makes the decision process behind chosen objective trade-offs unclear. Current Explainable Reinforcement Learning (XRL) methods are typically designed for single scalar rewards and do not account for explanations with respect to distinct objectives or user preferences. To address this gap, in this paper we propose TREX, a Trajectory based Explainability framework to explain Multi-objective Reinforcement Learning policies, based on trajectory attribution. TREX generates trajectories directly from the learned expert policy, across different user preferences and clusters them into semantically meaningful temporal segments. We quantify the influence of these behavioural segments on the Pareto trade-off by training complementary policies that exclude specific clusters, measuring the resulting relative deviation on the observed rewards and actions compared to the original expert policy. Experiments on multi-objective MuJoCo environments - HalfCheetah, Ant and Swimmer, demonstrate the framework's ability to isolate and quantify the specific behavioural patterns.
Read the full abstract ▾
Machine Learning
BOOST-RPF: Boosted Sequential Trees for Radial Power Flow
Ehimare Okoyomon and Christoph Goebel
Accurate power flow analysis is critical for modern distribution systems, yet classical solvers face scalability issues, and current machine learning models often struggle with generalization. We introduce BOOST-RPF, a novel method that reformulates voltage prediction from a global graph regression task into a sequential path-based learning problem. By decomposing radial networks into root-to-leaf paths, we leverage gradient-boosted decision trees (XGBoost) to model local voltage-drop regularities. We evaluate three architectural variants: Absolute Voltage, Parent Residual, and Physics-Informed Residual. This approach aligns the model architecture with the recursive physics of power flow, ensuring size-agnostic application and superior out-of-distribution robustness. Benchmarked against the Kerber Dorfnetz grid and the ENGAGE suite, BOOST-RPF achieves state-of-the-art results with its Parent Residual variant which consistently outperforms both analytical and neural baselines in standard accuracy and generalization tasks. While global Multi-Layer Perceptrons (MLPs) and Graph Neural Networks (GNNs) often suffer from performance degradation under topological shifts, BOOST-RPF maintains high precision across unseen feeders. Furthermore, the framework displays linear $O(N)$ computational scaling and significantly increased sample efficiency through per-edge supervision, offering a scalable and generalizable alternative for real-time distribution system operator (DSO) applications.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
SecureBreak – A dataset towards safe and secure models
Marco Arazzi, Vignesh Kumar Kembu and Antonino Nocera
Large
language models are becoming pervasive core components in many real-world applications. As a consequence, security
alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and
alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such as jailbreaking and
prompt injection, can bypass existing security
alignment mechanisms. As a consequence, additional security strategies are needed both to provide qualitative feedback on the robustness of the obtained security
alignment at the training stage, and to create an “ultimate” defense layer to block unsafe outputs possibly produced by deployed models. To provide a contribution in this scenario, this paper introduces SecureBreak, a safety-oriented
dataset designed to support the development of AI-driven solutions for detecting harmful LLM outputs caused by residual weaknesses in security
alignment. The
dataset is highly reliable due to careful manual annotation, where labels are assigned conservatively to ensure safety. It performs well in detecting unsafe content across multiple risk categories. Tests with pre-trained LLMs show improved results after fine-tuning on SecureBreak. Overall, the
dataset is useful both for post-generation safety filtering and for guiding further model
alignment and security improvements.
Read the full abstract ▾
Machine Learning
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Xixi Wu, Qianguo Sun, Ruiyang Zhang et al. (+4 more)
Reinforcement Learning (RL) is essential for evolving Large
Language Models (LLMs) into autonomous
agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This paper presents a systematic empirical study using TravelPlanner, a challenging testbed requiring tool orchestration to satisfy multifaceted constraints. We decompose the agentic RL design space along 5 axes: reward shaping, model scaling, data composition,
algorithm selection, and environmental stability. Our controlled experiments yield 7 key takeaways, e.g., (1) reward and
algorithm choices are scale-dependent as smaller models benefit from staged rewards and enhanced exploration, whereas larger models converge efficiently with simpler dense rewards, (2) ~ 1K training samples with a balanced difficulty mixture mark a sweet spot for both in-domain and out-of-domain performance, and (3) environmental stability is critical to prevent policy degradation. Based on our distilled recipe, our RL-trained models achieve state-of-the-art performance on TravelPlanner, significantly outperforming leading LLMs.
Read the full abstract ▾
All authors Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng
Machine Learning · Cross-listed from cs.CV
Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence
Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface et al. (+1 more)
The
pruning of 3D Gaussian splats is essential for reducing their complexity to enable efficient storage, transmission, and downstream processing. However, most of the existing
pruning strategies depend on camera parameters, rendered images, or view-dependent measures. This dependency becomes a hindrance in emerging camera-agnostic exchange settings, where splats are shared directly as point-based representations (e.g., .ply). In this paper, we propose a camera-agnostic, one-shot, post-training
pruning method for 3D Gaussian splats that relies solely on attribute-derived neighbourhood descriptors. As our primary contribution, we introduce a hybrid descriptor framework that captures structural and appearance consistency directly from the splat representation. Building on these descriptors, we formulate
pruning as a statistical evidence estimation problem and introduce a Beta evidence model that quantifies per-splat reliability through a probabilistic confidence score. Experiments conducted on standardized test sequences defined by the ISO/IEC MPEG Common Test Conditions (CTC) demonstrate that our approach achieves substantial
pruning while preserving reconstruction quality, establishing a practical and generalizable alternative to existing camera-dependent
pruning strategies.
Read the full abstract ▾
All authors Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface, Hamed Rezazadegan Tavakoli
Machine Learning · Cross-listed from cs.CV
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
Guannan Lai, Da-Wei Zhou, Zhenguo Li et al. (+1 more)
Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods face an efficiency-generalization trade-off: updating more parameters improves adaptation but severely reduces online inference efficiency. An ideal solution is to achieve comparable adaptation with minimal feature updates; we call this minimal subspace the golden subspace. We prove its existence in a single-step adaptation setting and show that it coincides with the row space of the pretrained classifier. To enable online maintenance of this subspace, we introduce the sample-wise Average Gradient Outer Product (AGOP) as an efficient proxy for estimating the classifier weights without retraining. Building on these insights, we propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP. Extensive experiments on classification and
segmentation benchmarks, including autonomous-driving scenarios, demonstrate that GOLD attains superior efficiency, stability, and overall performance. Our code is available at https://github.com/AIGNLAI/GOLD.
Read the full abstract ▾
All authors Guannan Lai, Da-Wei Zhou, Zhenguo Li, Han-Jia Ye
Machine Learning
Deep Reinforcement Learning and The Tale of Two Temporal Difference Errors
Juan Sebastian Rojas and Chi-Guhn Lee
The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have been used interchangeably in the literature, with the latter eventually being adopted as the standard critic loss in deep reinforcement learning (RL) architectures. In this work, we show that these two interpretations of the TD error are not always equivalent. In particular, we show that increasingly-nonlinear deep RL architectures can cause these interpretations of the TD error to yield increasingly different numerical values. Then, building on this insight, we show how choosing one interpretation of the TD error over the other can affect the performance of deep RL
algorithms that utilize the TD error to compute other quantities, such as with deep differential (i.e., average-reward) RL methods. All in all, our results show that the default interpretation of the TD error as the difference between a bootstrapped target and a prediction does not always hold in deep RL settings.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Structural Concentration in Weighted Networks: A Class of Topology-Aware Indices
L. Riso and M.G. Zoia
This paper develops a unified framework for measuring concentration in weighted systems embedded in networks of interactions. While traditional indices such as the Herfindahl-Hirschman Index capture dispersion in weights, they neglect the
topology of relationships among the elements receiving those weights. To address this limitation, we introduce a family of
topology-aware concentration indices that jointly account for weight distributions and network structure. At the core of the framework lies a baseline Network Concentration Index (NCI), defined as a normalized quadratic form that measures the fraction of potential weighted interconnection realized along observed network links. Building on this foundation, we construct a flexible class of extensions that modify either the interaction structure or the normalization
benchmark, including weighted, density-adjusted, null-model, degree-constrained, transformed-data, and multi-layer variants. This family of indices preserves key properties such as normalization, invariance, and interpretability, while allowing concentration to be evaluated across different dimensions of dependence, including intensity, higher-order interactions, and extreme events. Theoretical results characterize the indices and establish their relationship with classical concentration and network measures. Empirical and simulation evidence demonstrate that systems with identical weight distributions may exhibit markedly different levels of structural concentration depending on network
topology, highlighting the additional information captured by the proposed framework. The approach is broadly applicable to economic, financial, and complex systems in which weighted elements interact through networks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
A Variational Latent-Space Framework for Uncertainty-Aware Spectral Image Emulation
Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel et al. (+1 more)
Synthetic spectral image generation is essential for remote sensing simulation and mission design, yet physically based radiative transfer models (RTMs) remain computationally expensive. Existing learning-based emulators reduce this cost, but are mostly deterministic parameter-to-spectrum regressors with limited spatial modeling and uncertainty information. We formulate spectral image emulation as a parameter-conditioned latent-variable problem and propose a variational autoencoder (VAE)-based framework combining nonlinear spectral-image representations, fast inference, and per-pixel uncertainty estimates. The framework is instantiated at spectrum and spatial–spectral levels through two-step VAE pretraining and latent mapping. We evaluate it on PROSAIL-simulated hyperspectral vegetation cubes (211 bands) and real Sentinel-3 OLCI multispectral ocean-colour imagery (21 bands) against classical regression emulators and a deep CNN baseline. Results show that no single architecture is optimal: pixel-to-pixel models perform best on controlled hyperspectral simulations, whereas a fully convolutional VAE is more robust on noisy real observations with missing or contaminated pixels. VAE-based emulators also achieve high throughput for large-scale generation. On Sentinel-3, the spatial–spectral VAE provides predictive intervals closer to empirical errors than pixel-wise neural and classical emulators, although absolute calibration remains incomplete. A look-up-table-based
retrieval experiment further shows that reconstruction fidelity alone does not ensure reliable leaf area index and chlorophyll
retrieval. Emulators should therefore be evaluated in representative remote-sensing end-use scenarios, not by reconstruction metrics alone.
Read the full abstract ▾
All authors Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel, Matthieu Puigt
Machine Learning · Cross-listed from math.NA
A Novel Method for Enforcing Exactly Dirichlet, Neumann and Robin Conditions on Curved Domain Boundaries for Physics Informed Machine Learning
Suchuan Dong and Yuchuan Zhang
We present a systematic method for exactly enforcing Dirichlet, Neumann, and Robin type conditions on general quadrilateral domains with arbitrary curved boundaries. Our method is built upon exact mappings between general quadrilateral domains and the standard domain, and employs a combination of TFC (theory of functional connections) constrained expressions and transfinite interpolations. When Neumann or Robin boundaries are present, especially when two Neumann (or Robin) boundaries meet at a vertex, it is critical to enforce exactly the induced compatibility constraints at the intersection, in order to enforce exactly the imposed conditions on the joining boundaries. We analyze in detail and present constructions for handling the imposed boundary conditions and the induced compatibility constraints for two types of situations: (i) when Neumann (or Robin) boundary only intersects with Dirichlet boundaries, and (ii) when two Neumann (or Robin) boundaries intersect with each other. We describe a four-step procedure to systematically formulate the general form of functions that exactly satisfy the imposed Dirichlet, Neumann, or Robin conditions on general quadrilateral domains. The method developed herein has been implemented together with the extreme learning machine (ELM) technique we have developed recently for scientific machine learning. Ample numerical experiments are presented with several linear/nonlinear stationary/dynamic problems on a variety of two-dimensional domains with complex boundary geometries. Simulation results demonstrate that the proposed method has enforced the Dirichlet, Neumann, and Robin conditions on curved domain boundaries exactly, with the numerical boundary-condition errors at the machine accuracy.
Read the full abstract ▾
Machine Learning
SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference
Ziyang Zhang, Zheshun Wu, Jie Liu et al. (+1 more)
Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often too coarse to capture intra-inference variations, whereas fine-grained operator-level scaling suffers from prohibitive performance degradation due to significant hardware switching latency. This paper presents SparseDVFS, a fine-grained, sparse-aware DVFS framework designed for energy-efficient edge inference. Our key insight is that operator sparsity is a primary metric for hardware frequency modulation. By distinguishing between compute-bound dense operators and
memory-bound sparse operators, the system can apply specialized frequency triplets to maximize energy efficiency. To overcome switching overheads and component interference, SparseDVFS incorporates three key innovations: (1) an offline modeler that established a deterministic mapping between operator sparsity and optimal frequency triplets (CPU/GPU/EMC) via white-box timeline analysis; (2) a runtime graph partitioner that utilizes a greedy merging heuristic to aggregate operators into super-blocks, balancing scaling granularity and DVFS switching latency through a latency amortization constraint; and (3) a unified co-governor that employs a frequency unified scaling engine (FUSE) and a look-ahead instruction queue to eliminate antagonistic effects between independent controllers and hide hardware transition latencies. Extensive evaluations show that SparseDVFS achieves an average 78.17% energy efficiency gain over state-of-the-art solutions while maintaining a superior 14% cost-gain ratio.
Read the full abstract ▾
All authors Ziyang Zhang, Zheshun Wu, Jie Liu, Luca Mottola
Machine Learning · Cross-listed from cs.CV
Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
Donald Shenaj, Federico Errica and Antonio Carta
Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained
diffusion models. Choosing a good rank is extremely critical, since it trades off performance and
memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA$^2$, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less
memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.
Read the full abstract ▾
Machine Learning
SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting
Nikolas Stavrou and Siamak Mehrkanoon
Weather
forecasting supports critical socioeconomic activities and complements environmental protection, yet operational Numerical Weather Prediction (NWP) systems remain computationally intensive, thus being inefficient for certain applications. Meanwhile, recent advances in deep data-driven models have demonstrated promising results in nowcasting tasks. This paper presents SmaAT-QMix-UNet, an enhanced variant of SmaAT-UNet that introduces two key innovations: a vector quantization (VQ) bottleneck at the encoder-decoder bridge, and mixed kernel depth-wise convolutions (MixConv) replacing selected encoder and decoder blocks. These enhancements both reduce the model's size and improve its nowcasting performance. We train and evaluate SmaAT-QMix-UNet on a Dutch radar precipitation
dataset (2016-2019), predicting precipitation 30 minutes ahead. Three configurations are benchmarked: using only VQ, only MixConv, and the full SmaAT-QMix-UNet. Grad-CAM saliency maps highlight the regions influencing each nowcast, while a UMAP
embedding of the codewords illustrates how the VQ layer clusters encoder outputs. The source code for SmaAT-QMix-UNet is publicly available on GitHub: https://github.com/nstavr04/MasterThesisSnellius.
Read the full abstract ▾
Machine Learning
P^2O: Joint Policy and Prompt Optimization
Xinyu Lu, Kaiqi Zhang, Jinglin Yang et al. (+6 more)
Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large
Language Model (LLM)
reasoning but is suffer from advantage collapse: when all rollouts of a query receive identical rewards, the group variance vanishes, most damagingly on hard samples, where scaling rollout budgets yields little. We introduce Joint Policy and
Prompt Optimization (P O) to mitigate this collapse by alternating continuous policy updates with discrete
prompt evolution. P O mines hard samples with a success-rate threshold, evolves
reasoning prompts for them with GEPA, and internalizes the elicited trajectories via context
distillation, which optimizes each trajectory under the original query and thus removes inference-time prompting, with a Context Ratio Mask (CRM) filtering out extreme likelihood ratios. P O restores critical advantage signals and surpasses the GRPO baseline by up to 8.2 points in average accuracy on six held-out
benchmarks across all training
datasets and backbones, while also outperforming DAPO and other baselines. The gains are especially pronounced on hard
benchmarks, reaching up to 16.3 points above GRPO on average across AIME24 and AIME25. Our findings expose the limits of standard exploration in sparse-reward environments, illuminating the potential of unifying evolutionary
algorithms with reinforcement learning. This integration of discrete semantic search and continuous parameter updates provides a self-reinforcing framework that facilitates more effective LLM
alignment.
Read the full abstract ▾
All authors Xinyu Lu, Kaiqi Zhang, Jinglin Yang, Boxi Cao, Yaojie Lu, Hongyu Lin, Min He, Xianpei Han, Le Sun
Machine Learning
Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
Weilin Wan, Jingtao Han, Debing Zhang et al. (+2 more)
Scaling laws govern macroscopic resource allocation for LLMs, yet precise architectural configurations for Mixture-of-Experts (MoE) models remain guided by heuristics. Existing MoE scaling studies either incorporate MoE-specific variables into scaling formulas, causing fitted coefficients to grow rapidly without proportional experimental support, or fix all non-MoE factors, implicitly assuming global architecture does not influence local MoE scaling. We propose a reusable framework for holistic MoE architectural optimization. We first show that MoE architectures decouple FLOPs per
token ($M$), active parameters ($N_a$), and total parameters ($N$), which serve as distinct proxies for computation, weight access, and parameter storage. We therefore establish a joint constraint triad of $M$, active parameters ($N_a$), and total parameters ($N$) for rigorous MoE characterization. To tame the resulting $O(n^{16})$ search space, we employ mathematical decoupling: structural constraints and a rank-preserving property of the hidden dimension factorize the optimization into an $O(n^3) + O(n^2)$ two-phase search. Through extensive validation across 670+ MoE models spanning $10^{18}$ to $3 \times 10^{20}$ FLOPs, we derive globally applicable scaling laws mapping any compute budget to its optimal architecture. A key finding is that the near-optimal configuration band widens with scale, providing a quantitative basis for trade-offs between scaling law recommendations and engineering constraints. Our work delivers actionable blueprints for optimal MoE design under arbitrary compute budgets.
Read the full abstract ▾
All authors Weilin Wan, Jingtao Han, Debing Zhang, Weizhong Zhang, Cheng Jin