Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Thursday 22 January

Machine Learning

Probably Approximately Correct Maximum A Posteriori Inference

Computing the conditional mode of a distribution, better known as the maximum a posteriori (MAP) assignment, is a fundamental task in probabilistic inference. However, MAP is generally intractable, and remains hard even under many common structural constraints and approximation schemes. We take a novel approach inspired by multi-armed bandits, recasting MAP as a best arm identification task. We introduce probably approximately correct (PAC) algorithms for MAP that provide provably optimal solutions in both the fixed-confidence and fixed-budget regimes. We characterize tractability conditions using information theoretic measures that can be estimated from finite samples. Our PAC-MAP solvers are efficiently implemented using probabilistic circuits and graphical models with appropriate architectures. The algorithms we develop can be used either as standalone MAP estimators or to improve on standard heuristics, fortifying their solutions with rigorous guarantees. Experiments confirm the benefits of our method in a range of benchmarks.
Read the full abstract

Machine Learning

Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems

Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability critically important. Machine Learning (ML), specifically deep learning, is increasingly integrated in industrial CPS, but the inherent complexity of ML models results in non-transparent operation. Rigorous evaluation is needed to prevent models from exhibiting unexpected behaviour on future, unseen data. Explainable AI (XAI) can be used to uncover model reasoning, allowing a more extensive analysis of behaviour. We apply XAI to improve predictive performance of ML models intended for an industrial CPS use-case. We analyse the effects of components from time-series data decomposition on model predictions using SHAP values. Through this method, we observe evidence on the lack of sufficient contextual information during model training. By increasing the window size of data instances, informed by the XAI findings for this use-case, we are able to improve model performance.
Read the full abstract

Machine Learning

CLASP: An online learning algorithm for Convex Losses And Squared Penalties

We study Constrained Online Convex Optimization (COCO), where a learner chooses actions iteratively, observes both unanticipated convex loss and convex constraint, and accumulates loss while incurring penalties for constraint violations. We introduce CLASP (Convex Losses And Squared Penalties), an algorithm that minimizes cumulative loss together with squared constraint violations. Our analysis departs from prior work by fully leveraging the firm non-expansiveness of convex projectors, a proof strategy not previously applied in this setting. For convex losses, CLASP achieves regret $O\left(T^{\max\{\beta,1-\beta\}}\right)$ and cumulative squared penalty $O\left(T^{1-\beta}\right)$ for any $\beta \in (0,1)$. Most importantly, for strongly convex problems, CLASP provides the first logarithmic guarantees on both regret and cumulative squared penalty. In the strongly convex case, the regret is upper bounded by $O( \log T )$ and the cumulative squared penalty is also upper bounded by $O( \log T )$.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

On damage of interpolation to adversarial robustness in regression

Deep neural networks (DNNs) typically involve a large number of parameters and are trained to achieve zero or near-zero training error. Despite such interpolation, they often exhibit strong generalization performance on unseen data, a phenomenon that has motivated extensive theoretical investigations. Comforting results show that interpolation indeed may not affect the minimax rate of convergence under the squared error loss. In the mean time, DNNs are well known to be highly vulnerable to adversarial perturbations in future inputs. A natural question then arises: Can interpolation also escape from suboptimal performance under a future $X$-attack? In this paper, we investigate the adversarial robustness of interpolating estimators in a framework of nonparametric regression. A finding is that interpolating estimators must be suboptimal even under a subtle future $X$-attack, and achieving perfect fitting can substantially damage their robustness. An interesting phenomenon in the high interpolation regime, which we term the curse of simple size, is also revealed and discussed. Numerical experiments support our theoretical findings.
Read the full abstract

Machine Learning · Cross-listed from math.ST

Risk reversal for least squares estimators under nested convex constraints

In constrained stochastic optimization, one expects that restricting the feasible set, provided it still contains the true parameter, should not increase the statistical risk of the corresponding projection estimator. We show that this intuition can fail, even in basic settings. We investigate this phenomenon in the Gaussian sequence model. Given a compact, convex set $\Theta \subseteq \mathbb{R}^d$, one observes \[ Y = \theta^\star + \sigma Z, \qquad Z \sim N(0, I_d), \] and seeks to estimate an unknown $\theta^\star \in \Theta$. Here, the maximum likelihood estimator over $\Theta$ coincides with the least squares estimator (LSE), given by the Euclidean projection of $Y$ onto $\Theta$. We construct an explicit example exhibiting risk reversal: for sufficiently large noise, there exist nested compact convex sets $\Theta_S \subsetneq \Theta_L$ and $\theta^\star \in \Theta_S$ such that the LSE constrained to $\Theta_S$ has strictly larger squared-error risk than the LSE constrained to $\Theta_L$. Moreover, we demonstrate that risk reversal can persist at the level of worst-case risk. Finally, we show that the phenomenon is not specific to Gaussian noise or squared-error risk, extending our results beyond both settings. We clarify this phenomenon by contrasting noise regimes. In the vanishing-noise limit, the risk is governed at first order by the statistical dimension of the tangent cone, and risk reversal cannot occur at the leading $\sigma^2$ scale. In the diverging-noise regime, the risk instead depends on the global geometry of the constraint sets, and the embedding of $\Theta_S$ within $\Theta_L$ can reverse the risk ordering. These results reveal a previously unrecognized failure mode of the LSE. They demonstrate that in sufficiently noisy settings, tightening a constraint can paradoxically degrade statistical performance.
Read the full abstract

Machine Learning · Cross-listed from cs.PF

Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10

High-performance attention kernels are essential for Large Language Models. This paper presents analysis of CuTile-based Flash Attention memory behavior and a technique to improve its cache performance. In particular, our analysis on the NVIDIA GB10 (Grace Blackwell) identifies the main cause of L2 cache miss. Leveraging this insight, we introduce a new programming technique called Sawtooth Wavefront Reordering that reduces L2 misses. We validate it in both CUDA and CuTile, observing 50% or greater reduction in L2 misses and up to 60% increase in throughput on GB10.
Read the full abstract

Machine Learning

Data-Driven Conditional Flexibility Index

With the increasing flexibilization of processes, determining robust scheduling decisions has become an important goal. Traditionally, the flexibility index has been used to identify safe operating schedules by approximating the admissible uncertainty region using simple admissible uncertainty sets, such as hypercubes. Presently, available contextual information, such as forecasts, has not been considered to define the admissible uncertainty set when determining the flexibility index. We propose the conditional flexibility index (CFI), which extends the traditional flexibility index in two ways: by learning the parametrized admissible uncertainty set from historical data and by using contextual information to make the admissible uncertainty set conditional. This is achieved using a normalizing flow that learns a bijective mapping from a Gaussian base distribution to the data distribution. The admissible latent uncertainty set is constructed as a hypersphere in the latent space and mapped to the data space. By incorporating contextual information, the CFI provides a more informative estimate of flexibility by defining admissible uncertainty sets in regions that are more likely to be relevant under given conditions. Using an illustrative example, we show that no general statement can be made about data-driven admissible uncertainty sets outperforming simple sets, or conditional sets outperforming unconditional ones. However, both data-driven and conditional admissible uncertainty sets ensure that only regions of the uncertain parameter space containing realizations are considered. We apply the CFI to a security-constrained unit commitment example and demonstrate that the CFI can improve scheduling quality by incorporating temporal information.
Read the full abstract

All authors Moritz Wedemeyer, Eike Cramer, Alexander Mitsos, Manuel Dahmen

Machine Learning · Cross-listed from cs.RO

PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour

Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion. While human athletes can effectively perceive environmental characteristics to select appropriate footholds for obstacle traversal, endowing legged robots with similar perceptual reasoning remains a significant challenge. Existing methods often rely on hierarchical controllers that follow pre-computed footholds, thereby constraining the robot's real-time adaptability and the exploratory potential of reinforcement learning. To overcome these challenges, we present PUMA, an end-to-end learning framework that integrates visual perception and foothold priors into a single-stage training process. This approach leverages terrain features to estimate egocentric polar foothold priors, composed of relative distance and heading, guiding the robot in active posture adaptation for parkour tasks. Extensive experiments conducted in simulation and real-world environments across various discrete complex terrains, demonstrate PUMA's exceptional agility and robustness in challenging scenarios.
Read the full abstract

All authors Liang Wang, Kanzhong Yao, Yang Liu, Weikai Qin, Jun Wu, Zhe Sun, Qiuguo Zhu

Machine Learning

Partially Lazy Gradient Descent for Smoothed Online Learning

We introduce \textsc{$k$-lazyGD}, an online learning algorithm that bridges the gap between greedy Online Gradient Descent (OGD, for $k{=}1$) and lazy GD/dual-averaging (for $k{=}T$), creating a spectrum between reactive and stable updates. We analyze this spectrum in Smoothed Online Convex Optimization (SOCO), where the learner incurs both hitting and movement costs. Our main contribution is establishing that laziness is possible without sacrificing hitting performance: we prove that \textsc{$k$-lazyGD} achieves the optimal dynamic regret $\mathcal{O}(\sqrt{(P_T{+}1)T})$ for any laziness slack $k$ up to $\Theta(\sqrt{T/P_T})$, where $P_T$ is the comparator path length. This result formally connects the allowable laziness to the comparator's shifts, showing that \textsc{$k$-lazyGD} can retain the inherently small movements of lazy methods without compromising tracking ability. We base our analysis on the Follow the Regularized Leader (FTRL) framework, and derive a matching lower bound. Since the slack depends on $P_T$, an ensemble of learners with various slacks is used, yielding a method that is provably stable when it can be, and agile when it must be.
Read the full abstract

Machine Learning

Predicting Healthcare System Visitation Flow by Integrating Hospital Attributes and Population Socioeconomics with Human Mobility Data

Healthcare visitation patterns are influenced by a complex interplay of hospital attributes, population socioeconomics, and spatial factors. However, existing research often adopts a fragmented approach, examining these determinants in isolation. This study addresses this gap by integrating hospital capacities, occupancy rates, reputation, and popularity with population SES and spatial mobility patterns to predict visitation flows and analyze influencing factors. Utilizing four years of SafeGraph mobility data and user experience data from Google Maps Reviews, five flow prediction models, Naive Regression, Gradient Boosting, Multilayer Perceptrons (MLPs), Deep Gravity, and Heterogeneous Graph Neural Networks (HGNN),were trained and applied to simulate visitation flows in Houston, Texas, U.S. The Shapley additive explanation (SHAP) analysis and the Partial Dependence Plot (PDP) method were employed to examine the combined impacts of different factors on visitation patterns. The findings reveal that Deep Gravity outperformed other models. Hospital capacities, ICU occupancy rates, ratings, and popularity significantly influence visitation patterns, with their effects varying across different travel distances. Short-distance visits are primarily driven by convenience, whereas long-distance visits are influenced by hospital ratings. White-majority areas exhibited lower sensitivity to hospital ratings for short-distance visits, while Asian populations and those with higher education levels prioritized hospital rating in their visitation decisions. SES further influence these patterns, as areas with higher proportions of Hispanic, Black, under-18, and over-65 populations tend to have more frequent hospital visits, potentially reflecting greater healthcare needs or limited access to alternative medical services.
Read the full abstract

All authors Binbin Lin, Lei Zou, Hao Tian, Heng Cai, Yifan Yang, Bing Zhou

Machine Learning · Cross-listed from cs.AI

ICON: Invariant Counterfactual Optimization with Neuro-Symbolic Priors for Text-Based Person Search

Text-Based Person Search (TBPS) holds unique value in real-world surveillance bridging visual perception and language understanding, yet current paradigms utilizing pre-training models often fail to transfer effectively to complex open-world scenarios. The reliance on "Passive Observation" leads to multifaceted spurious correlations and spatial semantic misalignment, causing a lack of robustness against distribution shifts. To fundamentally resolve these defects, this paper proposes ICON (Invariant Counterfactual Optimization with Neuro-symbolic priors), a framework integrating causal and topological priors. First, we introduce Rule-Guided Spatial Intervention to strictly penalize sensitivity to bounding box noise, forcibly severing location shortcuts to achieve geometric invariance. Second, Counterfactual Context Disentanglement is implemented via semantic-driven background transplantation, compelling the model to ignore background interference for environmental independence. Then, we employ Saliency-Driven Semantic Regularization with adaptive masking to resolve local saliency bias and guarantee holistic completeness. Finally, Neuro-Symbolic Topological Alignment utilizes neuro-symbolic priors to constrain feature matching, ensuring activated regions are topologically consistent with human structural logic. Experimental results demonstrate that ICON not only maintains leading performance on standard benchmarks but also exhibits exceptional robustness against occlusion, background interference, and localization noise. This approach effectively advances the field by shifting from fitting statistical co-occurrences to learning causal invariance.
Read the full abstract

All authors Xiangyu Wang, Zhixin Lv, Yongjiao Sun, Anrui Han, Ye Yuan, Hangxu Ji

Machine Learning · Cross-listed from cs.CV

Class Confidence Aware Reweighting for Long Tailed Learning

Deep neural network models degrade significantly in the long-tailed data distribution, with the overall training data dominated by a small set of classes in the head, and the tail classes obtaining less training examples. Addressing the imbalance in the classes, attention in the related literature was given mainly to the adjustments carried out in the decision space in terms of either corrections performed at the logit level in order to compensate class-prior bias, with the least attention to the optimization process resulting from the adjustments introduced through the differences in the confidences among the samples. In the current study, we present the design of a class and confidence-aware re-weighting scheme for long-tailed learning. This scheme is purely based upon the loss level and has a complementary nature to the existing methods performing the adjustment of the logits. In the practical implementation stage of the proposed scheme, we use an {\Omega}(p_t, f_c) function. This function enables the modulation of the contribution towards the training task based upon the confidence value of the prediction, as well as the relative frequency of the corresponding class. Our observations in the experiments are corroborated by significant experimental results performed on the CIFAR-100-LT, ImageNet-LT, and iNaturalist2018 datasets under various values of imbalance factors that clearly authenticate the theoretical discussions above.
Read the full abstract

All authors Brainard Philemon Jagati, Jitendra Tembhurne, Harsh Goud, Rudra Pratap Singh, Chandrashekhar Meshram

Machine Learning · Cross-listed from math.OC

Progressive Power Homotopy for Non-convex Optimization

We propose a novel first-order method for non-convex optimization of the form $\max_{\bm{w}\in\mathbb{R}^d}\mathbb{E}_{\bm{x}\sim\mathcal{D}}[f_{\bm{w}}(\bm{x})]$, termed Progressive Power Homotopy (Prog-PowerHP). The method applies stochastic gradient ascent to a surrogate objective obtained by first performing a power transformation and then Gaussian smoothing, $F_{N,\sigma}(\bm{\mu}):=\mathbb{E}_{\bm{w}\sim\mathcal{N}(\bm{\mu},\sigma^2I_d),\bm{x}\sim\mathcal{D}}[e^{Nf_w(\bm{x})}]$, while progressively increasing the power parameter $N$ and decreasing the smoothing scale $\sigma$ along the optimization trajectory. We prove that, under mild regularity conditions, Prog-PowerHP converges to a small neighborhood of the global optimum with an iteration complexity scaling nearly as $O(d^2\varepsilon^{-2})$. Empirically, Prog-PowerHP demonstrates clear advantages in phase retrieval when the samples-to-dimension ratio approaches the information-theoretic limit, and in training two-layer neural networks in under-parameterized regimes. These results suggest that Prog-PowerHP is particularly effective for navigating cluttered non-convex landscapes where standard first-order methods struggle.
Read the full abstract

Machine Learning

Iterative Amortized Hierarchical VAE

In this paper we propose the Iterative Amortized Hierarchical Variational Autoencoder (IA-HVAE), which expands on amortized inference with a hybrid scheme containing an initial amortized guess and iterative refinement with decoder gradients. We achieve this by creating a linearly separable decoder in a transform domain (e.g. Fourier space), enabling real-time applications with very high model depths. The architectural change leads to a 35x speed-up for iterative inference with respect to the traditional HVAE. We show that our hybrid approach outperforms fully amortized and fully iterative equivalents in accuracy and speed respectively. Moreover, the IAHVAE shows improved reconstruction quality over a vanilla HVAE in inverse problems such as deblurring and denoising.
Read the full abstract

Machine Learning

SoK: Challenges in Tabular Membership Inference Attacks

Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records belonging to the training dataset, several concerns remain unexplored, particularly with regard to tabular data. In this paper, first, we provide an extensive review and analysis of MIAs considering two main learning paradigms: centralized and federated learning. We extend and refine the taxonomy for both. Second, we demonstrate the efficacy of MIAs in tabular data using several attack strategies, also including defenses. Furthermore, in a federated learning scenario, we consider the threat posed by an outsider adversary, which is often neglected. Third, we demonstrate the high vulnerability of single-outs (records with a unique signature) to MIAs. Lastly, we explore how MIAs transfer across model architectures. Our results point towards a general poor performance of these attacks in tabular data which contrasts with previous state-of-the-art. Notably, even attacks with limited attack performance can still successfully expose a large portion of single-outs. Moreover, our findings suggest that using different surrogate models makes MIAs more effective.
Read the full abstract

All authors Cristina Pêra, Tânia Carvalho, Maxime Cordy, Luís Antunes

Machine Learning · Cross-listed from cs.SD

PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation

Dance-to-music generation aims to generate music that is aligned with dance movements. Existing approaches typically rely on body motion features extracted from a single human dancer and limited dance-to-music datasets, which restrict their performance and applicability to real-world scenarios involving multiple dancers and non-human dancers. In this paper, we propose PF-D2M, a universal diffusion-based dance-to-music generation model that incorporates visual features extracted from dance videos. PF-D2M is trained with a progressive training strategy that effectively addresses data scarcity and generalization challenges. Both objective and subjective evaluations show that PF-D2M achieves state-of-the-art performance in dance-music alignment and music quality.
Read the full abstract

Machine Learning

Why Inference in Large Models Becomes Decomposable After Training

Inference in large-scale AI models is typically performed on dense parameter matrices, leading to inference cost and system complexity that scale unsustainably with model size. This limitation does not arise from insufficient model capacity, but from treating post-training inference systems as monolithic operators while ignoring internal structures formed during learning. We show that gradient update events in large models are highly localized and selective, leaving many parameter dependencies statistically indistinguishable from their initialization distribution after training. As a result, post-training inference systems are structurally non-uniform and inherently decomposable. Based on this observation, we introduce a post-training statistical criterion and a structural annealing procedure that removes unsupported dependencies and reveals stable, independent substructures. This work establishes a post-training, model-agnostic structural view of inference systems and enables structured, parallel inference without modifying model functionality or interfaces.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

A Lightweight Brain-Inspired Machine Learning Framework for Coronary Angiography: Hybrid Neural Representation and Robust Learning Strategies

Background: Coronary angiography (CAG) is a cornerstone imaging modality for assessing coronary artery disease and guiding interventional treatment decisions. However, in real-world clinical settings, angiographic images are often characterized by complex lesion morphology, severe class imbalance, label uncertainty, and limited computational resources, posing substantial challenges to conventional deep learning approaches in terms of robustness and generalization.Methods: The proposed framework is built upon a pretrained convolutional neural network to construct a lightweight hybrid neural representation. A selective neural plasticity training strategy is introduced to enable efficient parameter adaptation. Furthermore, a brain-inspired attention-modulated loss function, combining Focal Loss with label smoothing, is employed to enhance sensitivity to hard samples and uncertain annotations. Class-imbalance-aware sampling and cosine annealing with warm restarts are adopted to mimic rhythmic regulation and attention allocation mechanisms observed in biological neural systems.Results: Experimental results demonstrate that the proposed lightweight brain-inspired model achieves strong and stable performance in binary coronary angiography classification, yielding competitive accuracy, recall, F1-score, and AUC metrics while maintaining high computational efficiency.Conclusion: This study validates the effectiveness of brain-inspired learning mechanisms in lightweight medical image analysis and provides a biologically plausible and deployable solution for intelligent clinical decision support under limited computational resources.
Read the full abstract

Machine Learning

Uncertainty-guided Generation of Dark-field Radiographs

X-ray dark-field radiography provides complementary diagnostic information to conventional attenuation imaging by visualizing microstructural tissue changes through small-angle scattering. However, the limited availability of such data poses challenges for developing robust deep learning models. In this work, we present the first framework for generating dark-field images directly from standard attenuation chest X-rays using an Uncertainty-Guided Progressive Generative Adversarial Network. The model incorporates both aleatoric and epistemic uncertainty to improve interpretability and reliability. Experiments demonstrate high structural fidelity of the generated images, with consistent improvement of quantitative metrics across stages. Furthermore, out-of-distribution evaluation confirms that the proposed model generalizes well. Our results indicate that uncertainty-guided generative modeling enables realistic dark-field image synthesis and provides a reliable foundation for future clinical applications.
Read the full abstract

All authors Lina Felsner, Henriette Bast, Tina Dorosti, Florian Schaff, Franz Pfeiffer, Daniela Pfeiffer, Julia Schnabel

Machine Learning · Cross-listed from cs.CL

Determinants of Training Corpus Size for Clinical Text Classification

Introduction: Clinical text classification using natural language processing (NLP) models requires adequate training data to achieve optimal performance. For that, 200-500 documents are typically annotated. The number is constrained by time and costs and lacks justification of the sample size requirements and their relationship to text vocabulary properties. Methods: Using the publicly available MIMIC-III dataset containing hospital discharge notes with ICD-9 diagnoses as labels, we employed pre-trained BERT embeddings followed by Random Forest classifiers to identify 10 randomly selected diagnoses, varying training corpus sizes from 100 to 10,000 documents, and analyzed vocabulary properties by identifying strong and noisy predictive words through Lasso logistic regression on bag-of-words embeddings. Results: Learning curves varied significantly across the 10 classification tasks despite identical preprocessing and algorithms, with 600 documents sufficient to achieve 95% of the performance attainable with 10,000 documents for all tasks. Vocabulary analysis revealed that more strong predictors and fewer noisy predictors were associated with steeper learning curves, where every 100 additional noisy words decreased accuracy by approximately 0.02 while 100 additional strong predictors increased maximum accuracy by approximately 0.04.
Read the full abstract

All authors Jaya Chaturvedi, Saniya Deshpande, Chenkai Ma, Robert Cobb, Angus Roberts, Robert Stewart, Daniel Stahl, Diana Shamsutdinova

Machine Learning · Cross-listed from cs.CV

Beyond Off-the-Shelf Models: A Lightweight and Accessible Machine Learning Pipeline for Ecologists Working with Image Data

We introduce a lightweight experimentation pipeline designed to lower the barrier for applying machine learning (ML) methods for classifying images in ecological research. We enable ecologists to experiment with ML models independently, thus they can move beyond off-the-shelf models and generate insights tailored to local datasets and specific classification tasks and target variables. Our tool combines a simple command-line interface for preprocessing, training, and evaluation with a graphical interface for annotation, error analysis, and model comparison. This design enables ecologists to build and iterate on compact, task-specific classifiers without requiring advanced ML expertise. As a proof of concept, we apply the pipeline to classify red deer (Cervus elaphus) by age and sex from 3392 camera trap images collected in the Veldenstein Forest, Germany. Using 4352 cropped images containing individual deer labeled by experts, we trained and evaluated multiple backbone architectures with a wide variety of parameters and data augmentation strategies. Our best-performing models achieved 90.77% accuracy for age classification and 96.15% for sex classification. These results demonstrate that reliable demographic classification is feasible even with limited data to answer narrow, well-defined ecological problems. More broadly, the framework provides ecologists with an accessible tool for developing ML models tailored to specific research questions, paving the way for broader adoption of ML in wildlife monitoring and demographic analysis.
Read the full abstract

Machine Learning

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models

While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components governing safety. Existing methods rely on local, greedy attribution that assumes independent component contributions. However, they overlook the cooperative interactions between different components in LLMs, such as attention heads, which jointly contribute to safety mechanisms. We propose Global Optimization for Safety Vector Extraction (GOSV), a framework that identifies safety-critical attention heads through global optimization over all heads simultaneously. We employ two complementary activation repatching strategies: Harmful Patching and Zero Ablation. These strategies identify two spatially distinct sets of safety vectors with consistently low overlap, termed Malicious Injection Vectors and Safety Suppression Vectors, demonstrating that aligned LLMs maintain separate functional pathways for safety purposes. Through systematic analyses, we find that complete safety breakdown occurs when approximately 30% of total heads are repatched across all models. Building on these insights, we develop a novel inference-time white-box jailbreak method that exploits the identified safety vectors through activation repatching. Our attack substantially outperforms existing white-box attacks across all test models, providing strong evidence for the effectiveness of the proposed GOSV framework on LLM safety interpretability.
Read the full abstract

All authors Fengheng Chu, Jiahao Chen, Yuhong Wang, Jun Wang, Zhihui Fu, Shouling Ji, Songze Li

Machine Learning

Next Generation Active Learning: Mixture of LLMs in the Loop

With the rapid advancement and strong generalization capabilities of large language models (LLMs), they have been increasingly incorporated into the active learning pipelines as annotators to reduce annotation costs. However, considering the annotation quality, labels generated by LLMs often fall short of real-world applicability. To address this, we propose a novel active learning framework, Mixture of LLMs in the Loop Active Learning, replacing human annotators with labels generated through a Mixture-of-LLMs-based annotation model, aimed at enhancing LLM-based annotation robustness by aggregating the strengths of multiple LLMs. To further mitigate the impact of the noisy labels, we introduce annotation discrepancy and negative learning to identify the unreliable annotations and enhance learning effectiveness. Extensive experiments demonstrate that our framework achieves performance comparable to human annotation and consistently outperforms single-LLM baselines and other LLM-ensemble-based approaches. Moreover, our framework is built on lightweight LLMs, enabling it to operate fully on local machines in real-world applications.
Read the full abstract

All authors Yuanyuan Qi, Xiaohao Yang, Jueqing Lu, Guoxiang Guo, Joanne Enticott, Gang Liu, Lan Du

Machine Learning

Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning

Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development, particularly in the context of increasingly prevalent polypharmacy. Although existing computational methods achieve strong performance on standard benchmarks, they often fail to generalize to realistic deployment scenarios, where most candidate drug pairs involve previously unseen drugs and validated interactions are scarce. We demonstrate that proximity in the embedding spaces of prevailing molecule-centric DDI models does not reliably correspond to interaction labels, and that simply scaling up model capacity therefore fails to improve generalization. To address these limitations, we propose GenRel-DDI, a generalizable relation learning framework that reformulates DDI prediction as a relation-centric learning problem, in which interaction representations are learned independently of drug identities. This relation-level abstraction enables the capture of transferable interaction patterns that generalize to unseen drugs and novel drug pairs. Extensive experiments across multiple benchmark demonstrate that GenRel-DDI consistently and significantly outperforms state-of-the-art methods, with particularly large gains on strict entity-disjoint evaluations, highlighting the effectiveness and practical utility of relation learning for robust DDI prediction. The code is available at https://github.com/SZU-ADDG/GenRel-DDI.
Read the full abstract

All authors Dong Xu, Jiantao Wu, Qihua Pan, Sisi Yuan, Zexuan Zhu, Junkai Ji

Machine Learning · Cross-listed from cs.CV

Atlas-Assisted Segment Anything Model for Fetal Brain MRI (FeTal-SAM)

This paper presents FeTal-SAM, a novel adaptation of the Segment Anything Model (SAM) tailored for fetal brain MRI segmentation. Traditional deep learning methods often require large annotated datasets for a fixed set of labels, making them inflexible when clinical or research needs change. By integrating atlas-based prompts and foundation-model principles, FeTal-SAM addresses two key limitations in fetal brain MRI segmentation: (1) the need to retrain models for varying label definitions, and (2) the lack of insight into whether segmentations are driven by genuine image contrast or by learned spatial priors. We leverage multi-atlas registration to generate spatially aligned label templates that serve as dense prompts, alongside a bounding-box prompt, for SAM's segmentation decoder. This strategy enables binary segmentation on a per-structure basis, which is subsequently fused to reconstruct the full 3D segmentation volumes. Evaluations on two datasets, the dHCP dataset and an in-house dataset demonstrate FeTal-SAM's robust performance across gestational ages. Notably, it achieves Dice scores comparable to state-of-the-art baselines which were trained for each dataset and label definition for well-contrasted structures like cortical plate and cerebellum, while maintaining the flexibility to segment any user-specified anatomy. Although slightly lower accuracy is observed for subtle, low-contrast structures (e.g., hippocampus, amygdala), our results highlight FeTal-SAM's potential to serve as a general-purpose segmentation model without exhaustive retraining. This method thus constitutes a promising step toward clinically adaptable fetal brain MRI analysis tools.
Read the full abstract

All authors Qi Zeng, Weide Liu, Bo Li, Ryne Didier, P. Ellen Grant, Davood Karimi

Machine Learning · Cross-listed from cs.CR

CAFE-GB: Scalable and Stable Feature Selection for Malware Detection via Chunk-wise Aggregated Gradient Boosting

High-dimensional malware datasets often exhibit feature redundancy, instability, and scalability limitations, which hinder the effectiveness and interpretability of machine learning-based malware detection systems. Although feature selection is commonly employed to mitigate these issues, many existing approaches lack robustness when applied to large-scale and heterogeneous malware data. To address this gap, this paper proposes CAFE-GB (Chunk-wise Aggregated Feature Estimation using Gradient Boosting), a scalable feature selection framework designed to produce stable and globally consistent feature rankings for high-dimensional malware detection. CAFE-GB partitions training data into overlapping chunks, estimates local feature importance using gradient boosting models, and aggregates these estimates to derive a robust global ranking. Feature budget selection is performed separately through a systematic k-selection and stability analysis to balance detection performance and robustness. The proposed framework is evaluated on two large-scale malware datasets: BODMAS and CIC-AndMal2020, representing large and diverse malware feature spaces. Experimental results show that classifiers trained on CAFE-GB -selected features achieve performance parity with full-feature baselines across multiple metrics, including Accuracy, F1-score, MCC, ROC-AUC, and PR-AUC, while reducing feature dimensionality by more than 95%. Paired Wilcoxon signed-rank tests confirm that this reduction does not introduce statistically significant performance degradation. Additional analyses demonstrate low inter-feature redundancy and improved interpretability through SHAP-based explanations. Runtime and memory profiling further indicate reduced downstream classification overhead. Overall, CAFE-GB provides a stable, interpretable, and scalable feature selection strategy for large-scale malware detection.
Read the full abstract

Machine Learning

Towards Automated Kernel Generation in the Era of LLMs

The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level hardware operations. Achieving near-optimal kernels requires expert-level understanding of hardware architectures and programming models, making kernel engineering a critical but notoriously time-consuming and non-scalable process. Recent advances in large language models and LLM-based agents have opened new possibilities for automating kernel generation and optimization. LLMs are well-suited to compress expert-level kernel knowledge that is difficult to formalize, while agentic systems further enable scalable optimization by casting kernel development as an iterative, feedback-driven loop. Rapid progress has been made in this area. However, the field remains fragmented and lacks a systematic perspective for LLM-driven kernel generation. This survey addresses this gap by providing a structured overview of existing approaches, spanning LLM-based approaches and agentic optimization workflows, and systematically organizing the datasets and benchmarks that underpin learning and evaluation in this domain. Moreover, key open challenges and future research directions are further outlined, aiming to establish a comprehensive reference for the next generation of automated kernel optimization. To keep track of this field, we maintain an open-source GitHub repository at https://github.com/flagos-ai/awesome-LLM-driven-kernel-generation.
Read the full abstract

All authors Yang Yu, Peiyu Zang, Chi Hsu Tsai, Haiming Wu, Yixin Shen, Jialing Zhang, Haoyu Wang, Zhiyou Xiao, Jingze Shi, Yuyu Luo, Wentao Zhang, Chunlei Men, Guang Liu, Yonghua Lin

Machine Learning

Communication-efficient Federated Graph Classification via Generative Diffusion Modeling

Graph Neural Networks (GNNs) unlock new ways of learning from graph-structured data, proving highly effective in capturing complex relationships and patterns. Federated GNNs (FGNNs) have emerged as a prominent distributed learning paradigm for training GNNs over decentralized data. However, FGNNs face two significant challenges: high communication overhead from multiple rounds of parameter exchanges and non-IID data characteristics across clients. To address these issues, we introduce CeFGC, a novel FGNN paradigm that facilitates efficient GNN training over non-IID data by limiting communication between the server and clients to three rounds only. The core idea of CeFGC is to leverage generative diffusion models to minimize direct client-server communication. Each client trains a generative diffusion model that captures its local graph distribution and shares this model with the server, which then redistributes it back to all clients. Using these generative models, clients generate synthetic graphs combined with their local graphs to train local GNN models. Finally, clients upload their model weights to the server for aggregation into a global GNN model. We theoretically analyze the I/O complexity of communication volume to show that CeFGC reduces to a constant of three communication rounds only. Extensive experiments on several real graph datasets demonstrate the effectiveness and efficiency of CeFGC against state-of-the-art competitors, reflecting our superior performance on non-IID graphs by aligning local and global model objectives and enriching the training set with diverse graphs.
Read the full abstract

All authors Xiuling Wang, Xin Huang, Haibo Hu, Jianliang Xu

Machine Learning

Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs

We propose Zero-Error Horizon (ZEH) for trustworthy LLMs, which represents the maximum range that a model can solve without any errors. While ZEH itself is simple, we demonstrate that evaluating the ZEH of state-of-the-art LLMs yields abundant insights. For example, by evaluating the ZEH of GPT-5.2, we found that GPT-5.2 cannot even compute the parity of a short string like 11000, and GPT-5.2 cannot determine whether the parentheses in ((((()))))) are balanced. This is surprising given the excellent capabilities of GPT-5.2. The fact that LLMs make mistakes on such simple problems serves as an important lesson when applying LLMs to safety-critical domains. By applying ZEH to Qwen2.5 and conducting detailed analysis, we found that while ZEH correlates with accuracy, the detailed behaviors differ, and ZEH provides clues about the emergence of algorithmic capabilities. Finally, while computing ZEH incurs significant computational cost, we discuss how to mitigate this cost by achieving up to one order of magnitude speedup using tree structures and online softmax.
Read the full abstract

Machine Learning · Cross-listed from cs.AR

FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design

We present FlexLLM, a composable High-Level Synthesis (HLS) library for rapid development of domain-specific LLM accelerators. FlexLLM exposes key architectural degrees of freedom for stage-customized inference, enabling hybrid designs that tailor temporal reuse and spatial dataflow differently for prefill and decode, and provides a comprehensive quantization suite to support accurate low-bit deployment. Using FlexLLM, we build a complete inference system for the Llama-3.2 1B model in under two months with only 1K lines of code. The system includes: (1) a stage-customized accelerator with hardware-efficient quantization (12.68 WikiText-2 PPL) surpassing SpinQuant baseline, and (2) a Hierarchical Memory Transformer (HMT) plug-in for efficient long-context processing. On the AMD U280 FPGA at 16nm, the accelerator achieves 1.29$\times$ end-to-end speedup, 1.64$\times$ higher decode throughput, and 3.14$\times$ better energy efficiency than an NVIDIA A100 GPU (7nm) running BF16 inference; projected results on the V80 FPGA at 7nm reach 4.71$\times$, 6.55$\times$, and 4.13$\times$, respectively. In long-context scenarios, integrating the HMT plug-in reduces prefill latency by 23.23$\times$ and extends the context window by 64$\times$, delivering 1.10$\times$/4.86$\times$ lower end-to-end latency and 5.21$\times$/6.27$\times$ higher energy efficiency on the U280/V80 compared to the A100 baseline. FlexLLM thus bridges algorithmic innovation in LLM inference and high-performance accelerators with minimal manual effort.
Read the full abstract

All authors Jiahao Zhang, Zifan He, Nicholas Fraser, Michaela Blott, Yizhou Sun, Jason Cong