Machine Learning · Cross-listed from cs.CV
MineTheGap: Automatic Mining of Biases in Text-to-Image Models
Noa Cohen, Nurit Spingarn-Eliezer, Inbar Huberman-Spiegelglas et al. (+1 more)
Text-to-Image (TTI) models generate images based on text
prompts, which often leave certain aspects of the desired image ambiguous. When faced with these ambiguities, TTI models have been shown to exhibit biases in their interpretations. These biases can have societal impacts, e.g., when showing only a certain race for a stated occupation. They can also affect user experience when creating redundancy within a set of generated images instead of spanning diverse possibilities. Here, we introduce MineTheGap - a method for automatically mining
prompts that cause a TTI model to generate biased outputs. Our method goes beyond merely detecting bias for a given
prompt. Rather, it leverages a genetic
algorithm to iteratively refine a pool of
prompts, seeking for those that expose biases. This optimization process is driven by a novel bias score, which ranks biases according to their severity, as we validate on a
dataset with known biases. For a given
prompt, this score is obtained by comparing the distribution of generated images to the distribution of LLM-generated texts that constitute variations on the
prompt. Code and examples are available on the project's webpage.
Read the full abstract ▾
All authors Noa Cohen, Nurit Spingarn-Eliezer, Inbar Huberman-Spiegelglas, Tomer Michaeli
Machine Learning
Multiclass Graph-Based Large Margin Classifiers: Unified Approach for Support Vectors and Neural Networks
Vítor M. Hanriot, Luiz C. B. Torres and Antônio P. Braga
While large margin classifiers are originally an outcome of an optimization framework, support vectors (SVs) can be obtained from
geometric approaches. This article presents advances in the use of Gabriel graphs (GGs) in binary and multiclass classification problems. For Chipclass, a hyperparameter-less and optimization-less GG-based binary classifier, we discuss how activation functions and support edge (SE)-centered
neurons affect the classification, proposing smoother functions and structural SV (SSV)-centered
neurons to achieve margins with low probabilities and smoother classification contours. We extend the neural network architecture, which can be trained with backpropagation with a softmax function and a cross-
entropy loss, or by solving a system of linear equations. A new subgraph-/distance-based membership function for graph regularization is also proposed, along with a new GG recomputation
algorithm that is less computationally expensive than the standard approach. Experimental results with the Friedman test show that our method was better than previous GG-based classifiers and statistically equivalent to tree-based models.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
rNCA: Self-Repairing Segmentation Masks
Malte Silbernagel, Albert Alonso, Jens Petersen et al. (+3 more)
Accurately predicting topologically correct masks remains a difficult task for general
segmentation models, which often produce fragmented or disconnected outputs. Fixing these artifacts typically requires hand-crafted refinement rules or architectures specialized to a particular task. Here, we show that Neural Cellular Automata (NCA) can be directly re-purposed as an effective refinement mechanism, using local, iterative updates guided by image context to repair
segmentation masks. By training on imperfect masks and ground truths, the automaton learns the structural properties of the target shape while relying solely on local information. When applied to coarse, globally predicted masks, the learned dynamics progressively reconnect broken regions, prune loose fragments and converge towards stable, topologically consistent results. We show how refinement NCA (rNCA) can be easily applied to repair common topological errors produced by different base
segmentation models and tasks: for fragmented retinal vessels, it yields 2-3% gains in Dice/clDice and improves Betti errors, reducing $\beta_0$ errors by 60% and $\beta_1$ by 20%; for myocardium, it repairs 61.5% of broken cases in a zero-shot setting while lowering ASSD and HD by 19% and 16%, respectively. This showcases NCA as effective and broadly applicable refiners.
Read the full abstract ▾
All authors Malte Silbernagel, Albert Alonso, Jens Petersen, Bulat Ibragimov, Marleen de Bruijne, Madeleine K. Wyburd
Machine Learning
Dual-Phase Federated Deep Unlearning via Weight-Aware Rollback and Reconstruction
Changjun Zhou, Jintao Zheng, Leyou Yang et al. (+1 more)
Federated Unlearning (FUL) focuses on client data and computing power to offer a
privacy-preserving solution. However, high computational demands, complex incentive mechanisms, and disparities in client-side computing power often lead to long times and higher costs. To address these challenges, many existing methods rely on server-side knowledge
distillation that solely removes the updates of the target client, overlooking the
privacy embedded in the contributions of other clients, which can lead to
privacy leakage. In this work, we introduce DPUL, a novel server-side unlearning method that deeply unlearns all influential weights to prevent
privacy pitfalls. Our approach comprises three components: (i) identifying high-weight parameters by filtering client update magnitudes, and rolling them back to ensure deep removal. (ii) leveraging the variational autoencoder (VAE) to reconstruct and eliminate low-weight parameters. (iii) utilizing a projection-based technique to recover the model. Experimental results on four
datasets demonstrate that DPUL surpasses state-of-the-art baselines, providing a 1%-5% improvement in accuracy and up to 12x reduction in time cost.
Read the full abstract ▾
All authors Changjun Zhou, Jintao Zheng, Leyou Yang, Pengfei Wang
Machine Learning · Cross-listed from cs.RO
Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles
Sümer Tunçay, Alain Andres and Ignacio Carlucho
Autonomous
Underwater Vehicles (AUVs) require reliable six-degree-of-freedom (6-DOF) position control to operate effectively in complex and dynamic marine environments. Traditional controllers are effective under nominal conditions but exhibit degraded performance when faced with unmodeled dynamics or environmental disturbances. Reinforcement learning (RL) provides a powerful alternative but training is typically slow and sim-to-real transfer remains challenging. This work introduces a GPU accelerated RL training pipeline built in JAX and MuJoCo-XLA (MJX). By jointly JIT-compiling large-scale parallel physics simulation and learning updates, we achieve training times of under two minutes. Through systematic evaluation of multiple RL
algorithms, we show robust 6-DOF trajectory tracking and effective disturbance rejection in real
underwater experiments, with policies transferred zero-shot from simulation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3)
Zeyad Gamal, Youssef Mahran and Ayman El-Badawy
This paper proposes a reinforcement learning (RL) framework for controlling and stabilizing the Twin Rotor Aerodynamic System (TRAS) at specific pitch and azimuth angles and tracking a given trajectory. The complex dynamics and non-linear characteristics of the TRAS make it challenging to control using traditional control
algorithms. However, recent developments in RL have attracted interest due to their potential applications in the control of multirotors. The Twin Delayed Deep Deterministic Policy Gradient (TD3)
algorithm was used in this paper to train the RL
agent. This
algorithm is used for environments with continuous state and action spaces, similar to the TRAS, as it does not require a model of the system. The simulation results illustrated the effectiveness of the RL control method. Next, external disturbances in the form of wind disturbances were used to test the controller's effectiveness compared to conventional PID controllers. Lastly, experiments on a laboratory setup were carried out to confirm the controller's effectiveness in real-world applications.
Read the full abstract ▾
Machine Learning
On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
Ali Al Sahili, Ali Chehab and Razane Tajeddine
Large
Language Models (LLMs) are prone to memorizing training data, which poses serious
privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that these threats are interconnected: adversaries can extract training data from an LLM by querying the model to generate a large volume of text and subsequently applying MIAs to verify whether a particular data point was included in the training set. In this study, we integrate multiple MIA techniques into the data extraction pipeline to systematically
benchmark their effectiveness. We then compare their performance in this integrated setting against results from conventional MIA
benchmarks, allowing us to evaluate their practical utility in real-world extraction scenarios.
Read the full abstract ▾
Machine Learning
Link-Aware Energy-Frugal Continual Learning for Fault Detection in IoT Networks
Henrik C. M. Frederiksen, Junya Shiraishi, Cedomir Stefanovic et al. (+2 more)
The use of lightweight machine learning (ML) models in internet of things (IoT) networks enables resource constrained IoT devices to perform on-device inference for several critical applications. However, the inference accuracy deteriorates due to the non-stationarity in the IoT environment and limited initial training data. To counteract this, the deployed models can be updated occasionally with new observed data samples. However, this approach consumes additional energy, which is undesirable for energy constrained IoT devices. This letter introduces an event-driven communication framework that strategically integrates continual learning (CL) in IoT networks for energy-efficient fault detection. Our framework enables the IoT device and the edge server (ES) to collaboratively update the lightweight ML model by adapting to the wireless link conditions for communication and the available energy budget. Evaluation on real-world
datasets show that the proposed approach can outperform both periodic sampling and non-adaptive CL in terms of inference recall; our proposed approach achieves up to a 42.8% improvement, even under tight energy and bandwidth constraint.
Read the full abstract ▾
All authors Henrik C. M. Frederiksen, Junya Shiraishi, Cedomir Stefanovic, Hei Victor Cheng, Shashi Raj Pandey
Machine Learning
FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
Si Qi Goh, Yongsen Zheng, Ziyao Liu et al. (+2 more)
Machine unlearning (MU) seeks to eliminate the influence of specific training examples from deployed models. As large
language models (LLMs) become widely used, managing risks arising from insufficient forgetting or utility loss is increasingly crucial. Current MU techniques lack effective mechanisms for evaluating and controlling these risks, hindering the selection of strategies that appropriately balance safety and utility, and raising trust concerns surrounding the "right to be forgotten." To address these issues, we propose FROC, a unified framework with Risk-Optimized Control for machine unlearning in LLMs. FROC is built around a conformal-style risk-control formulation that expresses a user-specified risk budget on unlearning behavior. This probability-based constraint enables FROC to compare MU strategies, identify feasible operating regions, and guide hyperparameter selection according to desired trade-offs between forgetting sufficiency and utility preservation. To operationalize this constraint, FROC introduces a smoothly varying continuous risk model that aggregates forgetting deficiency and utility degradation into a single configuration-level score. Building on conformal risk analysis, FROC computes (1) the Conformal Unlearning Risk (CUR), a data-driven estimated value on the probability that forgotten samples continue to influence model predictions, and (2) risk-controlled configuration sets, which identify unlearning hyperparameters that are valid under the specified risk budget. Experiments across multiple LLM MU methods demonstrate that FROC produces stable, interpretable risk landscapes and reveals consistent relationships between unlearning configurations, semantic shift, and utility impact. FROC reframes MU as a controllable, risk-aware process and offers a practical foundation for managing unlearning behavior in large-scale LLM deployments.
Read the full abstract ▾
All authors Si Qi Goh, Yongsen Zheng, Ziyao Liu, Sami Hormi, Kwok-Yan Lam
Machine Learning
KD-PINN: Knowledge-Distilled PINNs for ultra-low-latency real-time neural PDE solvers
Karim Bounja, Lahcen Laayouni and Abdeljalil Sakat
This work introduces Knowledge-Distilled Physics-Informed Neural Networks (KD-PINN), a framework that transfers the predictive accuracy of a high-capacity teacher model to a compact student through a continuous adaptation of the Kullback-Leibler divergence. In order to confirm its generality for various dynamics and dimensionalities, the framework is evaluated on a representative set of partial differential equations (PDEs). Across the considered
benchmarks, the student model achieves inference speedups ranging from x4.8 (Navier-Stokes) to x6.9 (Burgers), while preserving accuracy. Accuracy is improved by on the order of 1% when the model is properly tuned. The
distillation process also revealed a regularizing effect. With an average inference latency of 5.3 ms on CPU, the distilled models enter the ultra-low-latency real-time regime defined by sub-10 ms performance. Finally, this study examines how knowledge
distillation reduces inference latency in PINNs, to contribute to the development of accurate ultra-low-latency neural PDE solvers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models
Malte Hellmeier
Securing digital text is becoming increasingly relevant due to the widespread use of large
language models. Individuals' fear of losing control over data when it is being used to train such machine learning models or when distinguishing model-generated output from text written by humans. Digital watermarking provides additional protection by
embedding an invisible watermark within the data that requires protection. However, little work has been taken to analyze and verify if existing digital text watermarking methods are secure and undetectable by large
language models. In this paper, we investigate the security-related area of watermarking and machine learning models for text data. In a controlled testbed of three experiments, ten existing Unicode text watermarking methods were implemented and analyzed across six large
language models: GPT-5, GPT-4o, Teuken 7B, Llama 3.3, Claude Sonnet 4, and Gemini 2.5 Pro. The findings of our experiments indicate that, especially the latest
reasoning models, can detect a watermarked text. Nevertheless, all models fail to extract the watermark unless implementation details in the form of source code are provided. We discuss the implications for security researchers and practitioners and outline future research opportunities to address security concerns.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Error-Driven Prompt Optimization for Arithmetic Reasoning
Árpád Pándy, Róbert Lakatos and András Hajdu
Recent advancements in artificial intelligence have sparked interest in industrial
agents capable of supporting analysts in regulated sectors, such as finance and healthcare, within tabular data workflows. A key capability for such systems is performing accurate arithmetic operations on structured data while ensuring sensitive information never leaves secure, on-premises environments. Here, we introduce an error-driven optimization framework for arithmetic
reasoning that enhances a Code Generation
Agent (CGA), specifically applied to on-premises small
language models (SLMs). Through a systematic evaluation of a leading SLM (Qwen3 4B), we find that while the base model exhibits fundamental limitations in arithmetic tasks, our proposed error-driven method, which clusters erroneous predictions to refine
prompt-rules iteratively, dramatically improves performance, elevating the model's accuracy to 70.8%. Our results suggest that developing reliable, interpretable, and industrially deployable AI assistants can be achieved not only through costly fine-tuning but also via systematic, error-driven
prompt optimization, enabling small models to surpass larger
language models (GPT-3.5 Turbo) in a
privacy-compliant manner.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Face Identity Unlearning for Retrieval via Embedding Dispersion
Mikhail Zakharov
Face recognition systems rely on learning highly discriminative and compact identity clusters to enable accurate
retrieval. However, as with other surveillance-oriented technologies, such systems raise serious
privacy concerns due to their potential for unauthorized identity tracking. While several works have explored machine unlearning as a means of
privacy protection, their applicability to face
retrieval - especially for modern
embedding-based recognition models - remains largely unexplored. In this work, we study the problem of face identity unlearning for
retrieval systems and present its inherent challenges. The goal is to make selected identities unretrievable by dispersing their
embeddings on the hypersphere and preventing the formation of compact identity clusters that enable re-identification in the gallery. The primary challenge is to achieve this forgetting effect while preserving the discriminative structure of the
embedding space and the
retrieval performance of the model for the remaining identities. To address this, we evaluate several existing approximate class unlearning methods (e.g., Random Labeling, Gradient Ascent, Boundary Unlearning, and other recent approaches) in the context of face
retrieval and propose a simple yet effective dispersion-based unlearning approach. Extensive experiments on standard
benchmarks (VGGFace2, CelebA) demonstrate that our method achieves superior forgetting behavior while preserving
retrieval utility.
Read the full abstract ▾
Machine Learning
ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning
Mayank Gulati, Benedikt Groß and Gerhard Wunder
We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generative components. Instead of exchanging full model parameters, our framework enables
privacy-preserving learning by transferring only generative capabilities across clients, while the server performs global training using synthetic samples. Through complementary
privacy mechanisms: DP-SGD with adaptive clipping and Lipschitz regularized VAE decoders and a stateful architecture supporting heterogeneous clients, we experimentally validate our approach on MNIST and Fashion-MNIST
datasets with cross-domain outliers. Our analysis demonstrates that both
privacy mechanisms effectively map sensitive outliers to typical data points while maintaining utility in extreme Non-IID scenarios typical of cross-silo collaborations. Index Terms: Client-invariant Learning,
Federated Learning (FL),
Privacy-preserving Generative Models, Non-Independent and Identically Distributed (Non-IID), Heterogeneous Architectures
Read the full abstract ▾
Machine Learning
No One Left Behind: How to Exploit the Incomplete and Skewed Multi-Label Data for Conversion Rate Prediction
Qinglin Jia, Zhaocheng Du, Chuhan Wu et al. (+4 more)
In most real-world online advertising systems, advertisers typically have diverse customer acquisition goals. A common solution is to use multi-task learning (MTL) to train a unified model on post-click data to estimate the conversion rate (CVR) for these diverse targets. In practice, CVR prediction often encounters missing conversion data as many advertisers submit only a subset of user conversion actions due to
privacy or other constraints, making the labels of multi-task data incomplete. If the model is trained on all available samples where advertisers submit user conversion actions, it may struggle when deployed to serve a subset of advertisers targeting specific conversion actions, as the training and deployment data distributions are mismatched. While considerable MTL efforts have been made, a long-standing challenge is how to effectively train a unified model with the incomplete and skewed multi-label data. In this paper, we propose a fine-grained Knowledge transfer framework for Asymmetric Multi-Label data (KAML). We introduce an attribution-driven masking strategy (ADM) to better utilize data with asymmetric multi-label data in training. However, the more relaxed masking in ADM is a double-edged sword: it provides additional training signals but also introduces noise due to skewed data. To address this, we propose a hierarchical knowledge extraction mechanism (HKE) to model the sample discrepancy within the target task tower. Finally, to maximize the utility of unlabeled samples, we incorporate ranking loss strategy to further enhance our model. The effectiveness of KAML has been demonstrated through comprehensive evaluations on offline industry
datasets and online A/B tests, which show significant performance improvements over existing MTL baselines.
Read the full abstract ▾
All authors Qinglin Jia, Zhaocheng Du, Chuhan Wu, Huifeng Guo, Ruiming Tang, Shuting Shi, Muyu Zhang
Machine Learning · Cross-listed from cs.AI
MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data
Zhenghao Zhu, Chuxue Cao, Sirui Han et al. (+4 more)
In medical data analysis, extracting deep insights from complex, multi-modal
datasets is essential for improving patient care, increasing diagnostic accuracy, and optimizing healthcare operations. However, there is currently a lack of high-quality
datasets specifically designed to evaluate the ability of large multi-modal models (LMMs) to discover medical insights. In this paper, we introduce MedInsightBench, the first
benchmark that comprises 332 carefully curated medical cases, each annotated with thoughtfully designed insights. This
benchmark is intended to evaluate the ability of LMMs and
agent frameworks to analyze multi-modal medical image data, including posing relevant questions, interpreting complex findings, and synthesizing actionable insights and recommendations. Our analysis indicates that existing LMMs exhibit limited performance on MedInsightBench, which is primarily attributed to their challenges in extracting multi-step, deep insights and the absence of medical expertise. Therefore, we propose MedInsightAgent, an automated
agent framework for medical data analysis, composed of three modules: Visual Root Finder, Analytical Insight
Agent, and Follow-up Question Composer. Experiments on MedInsightBench highlight pervasive challenges and demonstrate that MedInsightAgent can improve the performance of general LMMs in medical data insight discovery.
Read the full abstract ▾
All authors Zhenghao Zhu, Chuxue Cao, Sirui Han, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Yike Guo
Machine Learning · Cross-listed from cs.CV
LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
Shu Yu and Chaochao Lu
Diffusion models (DMs) have achieved remarkable success in image and
video generation. However, they still struggle with (1) physical
alignment and (2) out-of-distribution (OOD) instruction following. We argue that these issues stem from the models' failure to learn causal directions and to disentangle causal factors for novel recombination. We introduce the Causal Scene Graph (CSG) and the Physical
Alignment Probe (PAP)
dataset to enable diagnostic interventions. This analysis yields three key insights. First, DMs struggle with multi-hop
reasoning for elements not explicitly determined in the
prompt. Second, the
prompt embedding contains disentangled representations for texture and physics. Third, visual causal structure is disproportionately established during the initial, computationally limited denoising steps. Based on these findings, we introduce LINA (Learning INterventions Adaptively), a novel framework that learns to predict
prompt-specific interventions, which employs (1) targeted guidance in the
prompt and visual latent spaces, and (2) a reallocated, causality-aware denoising schedule. Our approach enforces both physical
alignment and OOD instruction following in image and
video DMs, achieving state-of-the-art performance on challenging causal generation tasks and the Winoground
dataset. Our project page is at https://opencausalab.github.io/LINA.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
Jiaru Zou, Ling Yang, Yunzhe Qi et al. (+5 more)
Agentic reinforcement learning has advanced large
language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approaches assume a fixed inventory of tools, which limits the adaptability of LLM
agents to new or evolving toolsets. We present AutoTool, a training framework that equips LLM
agents with dynamic tool-selection capabilities throughout their
reasoning trajectories. AutoTool employs a dual-phase optimization pipeline: (i) SFT and RL-based trajectory stabilization for coherent
reasoning, and (ii) KL-regularized Plackett-Luce Ranking to refine consistent multi-step tool selection. We further build a 200k
dataset with explicit tool-selection rationales across 1,000+ tools and 100+ tasks spanning mathematics, science, code generation, and
multimodal reasoning. Across ten diverse
benchmarks, we train two base models, Qwen3-8B and Qwen2.5-VL-7B, with AutoTool. With fewer parameters, AutoTool consistently outperforms advanced LLM
agents and tool-integration methods, yielding average gains of 6.4% in math & science
reasoning, 4.5% in search-based QA, 7.7% in code generation, and 6.9% in
multimodal understanding. In addition, AutoTool exhibits stronger generalization by dynamically leveraging unseen tools from evolving toolsets during inference.
Read the full abstract ▾
All authors Jiaru Zou, Ling Yang, Yunzhe Qi, Sirui Chen, Mengting Ai, Ke Shen, Jingrui He, Mengdi Wang
Machine Learning
BézierFlow: Learning Bézier Stochastic Interpolant Schedulers for Few-Step Generation
Yunhong Min, Juil Koo, Seungwoo Yoo et al. (+1 more)
We introduce BézierFlow, a lightweight training approach for few-step generation with pretrained
diffusion and flow models. BézierFlow achieves a 2-3x performance improvement for sampling with $\leq$ 10 NFEs while requiring only 15 minutes of training. Recent lightweight training approaches have shown promise by learning optimal timesteps, but their scope remains restricted to ODE discretizations. To broaden this scope, we propose learning the optimal transformation of the sampling trajectory by parameterizing
stochastic interpolant (SI) schedulers. The main challenge lies in designing a parameterization that satisfies critical desiderata, including boundary conditions, differentiability, and monotonicity of the SNR. To effectively meet these requirements, we represent scheduler functions as Bézier functions, where control points naturally enforce these properties. This reduces the problem to learning an ordered set of points in the time range, while the interpretation of the points changes from ODE timesteps to Bézier control points. Across a range of pretrained
diffusion and flow models, BézierFlow consistently outperforms prior timestep-learning methods, demonstrating the effectiveness of expanding the search space from discrete timesteps to Bézier-based trajectory transformations.
Read the full abstract ▾
All authors Yunhong Min, Juil Koo, Seungwoo Yoo, Minhyuk Sung
Machine Learning · Cross-listed from cs.AI
Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection
Zihui Zhao and Zechang Li
Direct Preference Optimization (DPO) has emerged as a lightweight and effective alternative to Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with AI Feedback (RLAIF) for aligning large
language and
vision-
language models. However, the standard DPO formulation, in which both the chosen and rejected responses are generated by the same policy, suffers from a weak learning signal because the two responses often share similar errors and exhibit small Kullback-Leibler (KL) divergence. This leads to slow and unstable convergence. To address this limitation, we introduce Reflective Preference Optimization (RPO), a new framework that incorporates hint-guided reflection into the DPO paradigm. RPO uses external models to identify
hallucination sources and generate concise reflective hints, enabling the construction of on-policy preference pairs with stronger contrastiveness and clearer preference signals. We theoretically show that conditioning on hints increases the expected preference margin through mutual information and improves sample efficiency while remaining within the policy distribution family. Empirically, RPO achieves superior
alignment with fewer training samples and iterations, substantially reducing
hallucination rates and delivering state-of-the-art performance across
multimodal benchmarks.
Read the full abstract ▾
Machine Learning
Learning to Retrieve with Weakened Labels: Robust Training under Label Noise
Arnab Sharma
Neural Encoders are frequently used in the NLP domain to perform dense
retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the training data make it challenging to train or fine-tune such
retrieval models. Although existing works have attempted to mitigate these problems by incorporating modified loss functions or data cleaning, these approaches either require some hyperparameters to tune during training or add substantial complexity to the training setup. In this work, we consider a label weakening approach to generate robust
retrieval models in the presence of label noise. Instead of enforcing a single, potentially erroneous label for each query document pair, we allow for a set of plausible labels derived from both the observed supervision and the model's confidence scores. We perform an extensive evaluation considering two
retrieval models, one re-ranking model, considering four diverse ranking
datasets. To this end, we also consider a realistic noisy setting by using a semantic-aware noise generation technique to generate different ratios of noise. Our initial results show that label weakening can improve the performance of the
retrieval tasks in comparison to 10 different state-of-the-art loss functions.
Read the full abstract ▾
Machine Learning
CORE: Contrastive Masked Feature Reconstruction on Graphs
Jianyuan Bo and Yuan Fang
In the rapidly evolving field of self-supervised learning on graphs, generative and contrastive methodologies have emerged as two dominant approaches. Our study focuses on masked feature reconstruction (MFR), a generative technique where a model learns to restore the raw features of masked nodes in a self-supervised manner. We observe that both MFR and graph contrastive learning (GCL) aim to maximize agreement between similar elements. Building on this observation, we reveal a novel theoretical insight: under specific conditions, the objectives of MFR and node-level GCL converge, despite their distinct operational mechanisms. This theoretical connection suggests these approaches are complementary rather than fundamentally different, prompting us to explore their integration to enhance self-supervised learning on graphs. Our research presents Contrastive Masked Feature Reconstruction (CORE), a novel graph self-supervised learning framework that integrates contrastive learning into MFR. Specifically, we form positive pairs exclusively between the original and reconstructed features of masked nodes, encouraging the encoder to prioritize contextual information over the node's own features. Additionally, we leverage the masked nodes themselves as negative samples, combining MFR's reconstructive power with GCL's discriminative ability to better capture intrinsic graph structures. Empirically, our proposed framework CORE significantly outperforms MFR across node and graph classification tasks, demonstrating state-of-the-art results. In particular, CORE surpasses GraphMAE and GraphMAE2 by up to 2.80% and 3.72% on node classification tasks, and by up to 3.82% and 3.76% on graph classification tasks.
Read the full abstract ▾
Machine Learning
ModSSC: A Modular Framework for Semi-Supervised Classification on Heterogeneous Data
Melvin Barbaux and Samia Boukir
Semi-supervised classification leverages both labeled and unlabeled data to improve predictive performance, but existing software support remains fragmented across methods, learning settings, and data modalities. We introduce ModSSC, an open source Python framework for inductive and transductive semi-supervised classification designed to support reproducible and controlled experimentation. ModSSC provides a modular and extensible software architecture centered on reusable semi-supervised learning components, stable abstractions, and fully declarative experiment specification. Experiments are defined through configuration files, enabling systematic comparison across heterogeneous
datasets and model backbones without modifying algorithmic code. ModSSC 1.0.0 is released under the MIT license with full documentation and automated tests, and is available at https://github.com/ModSSC/ModSSC. The framework is validated through controlled experiments reproducing established semi-supervised learning baselines across multiple data modalities.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Better LMO-based Momentum Methods with Second-Order Information
Sarit Khirirat, Abdurakhmon Sadiev, Yury Demidovich et al. (+1 more)
The use of momentum in
stochastic optimization
algorithms has shown empirical success across a range of machine learning tasks. Recently, a new class of
stochastic momentum
algorithms has emerged within the Linear Minimization Oracle (LMO) framework–leading to state-of-the-art methods, such as
Muon, Scion, and
Gluon, that effectively solve deep neural network training problems. However, traditional
stochastic momentum methods offer convergence guarantees no better than the ${O}(1/K^{1/4})$ rate. While several approaches–such as Hessian-Corrected Momentum (HCM)–have aimed to improve this rate, their theoretical results are generally restricted to the Euclidean norm setting. This limitation hinders their applicability in problems, where arbitrary norms are often required. In this paper, we extend the LMO-based framework by integrating HCM, and provide convergence guarantees under relaxed smoothness and arbitrary norm settings. We establish improved convergence rates of ${O}(1/K^{1/3})$ for HCM, which can adapt to the geometry of the problem and achieve a faster rate than traditional momentum. Experimental results on training Multi-Layer Perceptrons (MLPs) and Long Short-Term
Memory (LSTM) networks verify our theoretical observations.
Read the full abstract ▾
All authors Sarit Khirirat, Abdurakhmon Sadiev, Yury Demidovich, Peter Richtárik
Machine Learning · Cross-listed from math.OC
Rethinking Physics-Informed Regression Beyond Training Loops and Bespoke Architectures
Lorenzo Sabug Jr. and Eric Kerrigan
We revisit the problem of physics-informed regression, and propose a method that directly computes the state at the prediction point, simultaneously with the derivative and
curvature information of the existing samples. We frame each prediction as a constrained optimisation problem, leveraging multivariate Taylor series expansions and explicitly enforcing physical laws. Each individual query can be processed with low computational cost without any pre- or re-training, in contrast to global function approximator-based solutions such as neural networks. Our comparative
benchmarks on a reaction-
diffusion system show competitive predictive accuracy relative to a neural network-based solution, while completely eliminating the need for long training loops, and remaining robust to changes in the sampling layout.
Read the full abstract ▾
Machine Learning
Karina Chichifoi, Fabio Merizzi and Michele Colajanni
Deep learning and
federated learning (FL) are becoming powerful partners for next-generation weather
forecasting. Deep learning enables high-resolution spatiotemporal forecasts that can surpass traditional numerical models, while FL allows institutions in different locations to collaboratively train models without sharing raw data, addressing efficiency and security concerns. While FL has shown promise across heterogeneous regions, its distributed nature introduces new vulnerabilities. In particular, data poisoning attacks, in which compromised clients inject manipulated training data, can degrade performance or introduce systematic biases. These threats are amplified by spatial dependencies in meteorological data, allowing localized perturbations to influence broader regions through global model aggregation. In this study, we investigate how
adversarial clients distort
federated surface temperature forecasts trained on the Copernicus European Regional ReAnalysis (CERRA)
dataset. We simulate geographically distributed clients and evaluate patch-based and global biasing attacks on regional temperature forecasts. Our results show that even a small fraction of poisoned clients can mislead predictions across large, spatially connected areas. A global temperature bias attack from a single compromised client shifts predictions by up to -1.7 K, while coordinated patch attacks more than triple the mean squared error and produce persistent regional anomalies exceeding +3.5 K. Finally, we assess trimmed mean aggregation as a defense mechanism, showing that it successfully defends against global bias attacks (2-13% degradation) but fails against patch attacks (281-603% amplification), exposing limitations of outlier-based defenses for spatially correlated data.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.geo-ph
Parameter-Efficient Transfer Learning for Microseismic Phase Picking Using a Neural Operator
Ayrat Abdullin, Umair Bin Waheed, Leo Eisner et al. (+1 more)
Seismic phase picking is fundamental for microseismic monitoring and subsurface imaging. Manual processing is impractical for real-time applications and large sensor arrays, motivating the use of deep learning-based pickers trained on extensive earthquake catalogs. On a broader scale, these models are generally tuned to perform optimally in high signal-to-noise and long-duration networks and often fail to perform satisfactorily when applied to campaign-based microseismic
datasets, which are characterized by low signal-to-noise ratios, sparse geometries, and limited labeled data. In this study, we present a microseismic adaptation of a network-wide earthquake phase picker, Phase Neural Operator (PhaseNO), using transfer learning and parameter-efficient fine-tuning. Starting from a model pre-trained on more than 57,000 three-component earthquake and noise records, we fine-tune it using only 200 labeled and noisy microseismic recordings from hydraulic fracturing settings. We present a parameter-efficient adaptation of PhaseNO that fine-tunes a small fraction of its parameters (only 3.6%) while retaining its global spatiotemporal representations learned from a large
dataset of earthquake recordings. We then evaluate our adapted model on three independent microseismic
datasets and compare its performance against the original pre-trained PhaseNO, a STA/LTA-based workflow, and two state-of-the-art deep learning models, PhaseNet and EQTransformer. We demonstrate that our adapted model significantly outperforms the original PhaseNO in F1 and accuracy metrics, achieving up to 30% absolute improvements in all test sets and consistently performing better than STA/LTA and state-of-the-art models. With our adaptation being based on a small calibration set, our proposed workflow is a practical and efficient tool to deploy network-wide models in data-limited microseismic applications.
Read the full abstract ▾
All authors Ayrat Abdullin, Umair Bin Waheed, Leo Eisner, Naveed Iqbal
Machine Learning
Noise-Resilient Quantum Aggregation on NISQ for Federated ADAS Learning
Chethana Prasad Kabgere and Sudarshan T S B
Advanced Driver Assistance Systems (ADAS) increasingly employ
Federated Learning (FL) to collaboratively train models across distributed vehicular nodes while preserving data
privacy. Yet, conventional FL aggregation remains susceptible to noise, latency, and security constraints inherent to real-time vehicular networks. This paper introduces Noise-Resilient
Quantum Federated Learning (NR-QFL), a hybrid
quantum-classical framework that enables secure, low-latency aggregation through variational
quantum circuits (VQCs) operating under Noisy Intermediate-Scale
Quantum (NISQ) conditions. The framework encodes model parameters as
quantum states with adaptive gate reparameterization, ensuring bounded-error convergence and provable resilience under Completely Positive Trace-Preserving (CPTP) dynamics. NR-QFL employs
quantum entropy-based client selection and multi-server coordination for
fairness and stability. Empirical validation shows consistent convergence with reduced gradient variance, lower communication overhead, and enhanced noise tolerance under constrained edge conditions. The framework establishes a scalable foundation for
quantum-enhanced
federated learning, enabling secure, efficient, and dynamically stable ADAS intelligence at the vehicular edge.
Read the full abstract ▾
Machine Learning
WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
Jin Sob Kim, Hyun Joon Park, Wooseok Shin et al. (+2 more)
The Automatic Identification System (AIS) enables data-driven maritime surveillance but suffers from reliability issues and irregular intervals. We address vessel destination estimation using global-scope AIS data by proposing a differentiated approach that recasts long port-to-port trajectories as a nested sequence structure. Using spatial grids, this method mitigates spatio-temporal bias while preserving detailed resolution. We introduce a novel deep learning architecture, WAY, designed to process these reformulated trajectories for long-term destination estimation days to weeks in advance. WAY comprises a trajectory representation layer and Channel-Aggregative Sequential Processing (CASP) blocks. The representation layer generates multi-channel vector sequences from kinematic and non-kinematic features. CASP blocks utilize multi-headed channel- and self-
attention for aggregation and sequential information delivery. Additionally, we propose a task-specialized Gradient Dropout (GD) technique to enable many-to-many training on single labels, preventing biased feedback surges by stochastically blocking gradient flow based on sample length. Experiments on 5-year AIS data demonstrate WAY's superiority over conventional spatial grid-based approaches regardless of trajectory progression. Results further confirm that adopting GD leads to performance gains. Finally, we explore WAY's potential for real-world application through multitask learning for ETA estimation.
Read the full abstract ▾
All authors Jin Sob Kim, Hyun Joon Park, Wooseok Shin, Dongil Park, Sung Won Han
Machine Learning
PolySet: Restoring the Statistical Ensemble Nature of Polymers for Machine Learning
Khalid Ferji
Machine-learning (ML) models in
polymer science typically treat a
polymer as a single, perfectly defined molecular graph, even though real materials consist of
stochastic ensembles of chains with distributed lengths. This mismatch between physical reality and digital representation limits the ability of current models to capture
polymer behaviour. Here we introduce PolySet, a framework that represents a
polymer as a finite, weighted ensemble of chains sampled from an assumed molar-mass distribution. This ensemble-based encoding is independent of chemical detail, compatible with any molecular representation and illustrated here in the homopolymer case using a minimal
language model. We show that PolySet retains higher-order distributional moments (such as Mz, Mz+1), enabling ML models to learn tail-sensitive properties with greatly improved stability and accuracy. By explicitly acknowledging the statistical nature of
polymer matter, PolySet establishes a physically grounded foundation for future
polymer machine learning, naturally extensible to copolymers, block architectures, and other complex
topologies.
Read the full abstract ▾