Machine Learning · Cross-listed from eess.SY
Studying the Role of Synthetic Data for Machine Learning-based Wireless Networks Traffic Forecasting
José Pulido, Francesc Wilhelmi, Sergio Fortes et al. (+3 more)
Synthetic data generation is an appealing tool for augmenting and enriching
datasets, playing a crucial role in advancing artificial intelligence (AI) and machine learning (ML). Not only does synthetic data help build robust AI/ML
datasets cost-effectively, but it also offers
privacy-friendly solutions and bypasses the complexities of storing large data volumes. This paper proposes a novel method to generate synthetic data, based on first-order auto-regressive noise statistics, for large-scale Wi-Fi deployments. The approach operates with minimal real data requirements while producing statistically rich traffic patterns that effectively mimic real Access Point (AP) behavior. Experimental results show that ML models trained on synthetic data achieve Mean Absolute Error (MAE) values within 10 to 15 of those obtained using real data when trained on the same APs, while requiring significantly less training data. Moreover, when generalization is required, synthetic-data-trained models improve prediction accuracy by up to 50 percent compared to real-data-trained baselines, thanks to the enhanced variability and diversity of the generated traces. Overall, the proposed method bridges the gap between synthetic data generation and practical Wi-Fi traffic
forecasting, providing a scalable, efficient, and real-time solution for modern wireless networks.
Read the full abstract ▾
All authors José Pulido, Francesc Wilhelmi, Sergio Fortes, Alfonso Fernández-Durán, Lorenzo Galati Giordano, Raquel Barco
Machine Learning · Cross-listed from stat.ML
Dual-Level Models for Physics-Informed Multi-Step Time Series Forecasting
Mahdi Nasiri, Johanna Kortelainen and Simo Särkkä
This paper develops an approach for multi-step
forecasting of dynamical systems by integrating probabilistic input
forecasting with physics-informed output prediction. Accurate multi-step
forecasting of time series systems is important for the automatic control and optimization of physical processes, enabling more precise decision-making. While mechanistic-based and data-driven machine learning (ML) approaches have been employed for time series
forecasting, they face significant limitations. Incomplete knowledge of process mathematical models limits mechanistic-based direct employment, while purely data-driven ML models struggle with dynamic environments, leading to poor generalization. To address these limitations, this paper proposes a dual-level strategy for physics-informed
forecasting of dynamical systems. On the first level, input variables are forecast using a hybrid method that integrates a long short-term
memory (LSTM) network into probabilistic state transition models (STMs). On the second level, these stochastically predicted inputs are sequentially fed into a physics-informed neural network (PINN) to generate multi-step output predictions. The experimental results of the paper demonstrate that the hybrid input
forecasting models achieve a higher log-likelihood and lower mean squared errors (MSE) compared to conventional STMs. Furthermore, the PINNs driven by the input
forecasting models outperform their purely data-driven counterparts in terms of MSE and log-likelihood, exhibiting stronger generalization and
forecasting performance across multiple test cases.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.RM
Reinforcement Learning for Micro-Level Claims Reserving
Benjamin Avanzi, Ronald Richman, Bernard Wong et al. (+2 more)
Outstanding claim liabilities are revised repeatedly as claims develop, yet most modern reserving models are trained as one-shot predictors and typically learn only from settled claims. We formulate individual claims reserving as a claim-level Markov decision process in which an
agent sequentially updates outstanding claim liability (OCL) estimates over development, using continuous actions and a reward design that balances accuracy with stable reserve revisions. A key advantage of this reinforcement learning (RL) approach is that it can learn from all observed claim trajectories, including claims that remain open at valuation, thereby avoiding the reduced sample size and selection effects inherent in supervised methods trained on ultimate outcomes only. We also introduce practical components needed for actuarial use – initialisation of new claims, temporally consistent tuning via a rolling-settlement scheme, and an importance-weighting mechanism to mitigate portfolio-level underestimation driven by the rarity of large claims. On CAS and SPLICE synthetic general insurance
datasets, the proposed Soft Actor-Critic implementation delivers competitive claim-level accuracy and strong aggregate OCL performance, particularly for the immature claim segments that drive most of the liability.
Read the full abstract ▾
All authors Benjamin Avanzi, Ronald Richman, Bernard Wong, Mario Wüthrich, Yagebu Xie
Machine Learning
Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning
Yanan Chen, Tieliang Gong, Yunjiao Zhang et al. (+1 more)
Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However, existing sharpness-aware methods for CL suffer from two key limitations: (1) they treat sharpness regularization as a unified signal without distinguishing the contributions of its components. and (2) they introduce substantial computational overhead that impedes practical deployment. To address these challenges, we propose FLAD, a novel optimization framework that decomposes sharpness-aware perturbations into gradient-aligned and
stochastic-noise components, and show that retaining only the noise component promotes generalization. We further introduce a lightweight scheduling scheme that enables FLAD to maintain significant performance gains even under constrained training time. FLAD can be seamlessly integrated into various CL paradigms and consistently outperforms standard and sharpness-aware optimizers in diverse experimental settings, demonstrating its effectiveness and practicality in CL.
Read the full abstract ▾
All authors Yanan Chen, Tieliang Gong, Yunjiao Zhang, Wen Wen
Machine Learning · Cross-listed from cond-mat.dis-nn
Learning About Learning: A Path from Spin Glasses to Artificial Intelligence
Denis D. Caprioti, Matheus Haas, Constantino F. Vasconcelos et al. (+1 more)
The Hopfield model, originally inspired by
spin glasses, occupies a central place at the intersection of statistical mechanics, neural networks, and artificial intelligence. Despite its conceptual simplicity and broad applicability, it is rarely integrated into the undergraduate physics curriculum. We present the Hopfield model as a pedagogically rich framework that naturally unifies core topics from the undergraduate physics curriculum and that provides a concise introduction based on concepts such as a model's energy function, dynamics, and pattern stability. We discuss practical aspects of its simulation and provide simulation codes. We also propose problems designed to mirror research practice, which can be included in undergraduate classes.
Read the full abstract ▾
All authors Denis D. Caprioti, Matheus Haas, Constantino F. Vasconcelos, Mauricio Girardi-Schappo
Machine Learning
Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography
Yulu Wang, Ziqian Zeng, Jianjun Wu et al. (+1 more)
In an ideal medical environment, real-time coagulation monitoring can enable early detection and
prompt remediation of risks. However, traditional Thromboelastography (TEG), a widely employed diagnostic modality, can only provide such outputs after nearly 1 hour of measurement. The delay might lead to elevated mortality rates. These issues clearly point out one of the key challenges for medical AI development: Mak-ing reasonable predictions based on very small data sets and accounting for variation between different patient populations, a task where conventional deep learning methods typically perform poorly. We present Physiological State Reconstruc-tion (PSR), a new
algorithm specifically designed to take ad-vantage of dynamic changes between individuals and to max-imize useful information produced by small amounts of clini-cal data through mapping to reliable predictions and diagnosis. We develop MDFE to facilitate integration of varied temporal signals using multi-domain learning, and jointly learn high-level temporal interactions together with attentions via HLA; furthermore, the parameterized DAM we designed maintains the stability of the computed vital signs. PSR evaluates with 4 TEG-specialized data sets and establishes remarkable perfor-mance – predictions of R2 > 0.98 for coagulation traits and error reduction around half compared to the state-of-the-art methods, and halving the inferencing time too. Drift-aware learning suggests a new future, with potential uses well be-yond thrombophilia discovery towards medical AI applica-tions with data scarcity.
Read the full abstract ▾
All authors Yulu Wang, Ziqian Zeng, Jianjun Wu, Zhifeng Tang
Machine Learning · Cross-listed from cs.AR
GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation
Dimple Vijay Kochar, Nathaniel Pinckney, Guan-Ting Liu et al. (+4 more)
RTL design often relies heavily on ad-hoc testbench creation early in the design cycle. While large
language models (LLMs) show promise for RTL code generation, their ability to reason about hardware specifications and generate targeted test plans remains largely unexplored. We present the first systematic study of LLM
reasoning capabilities for RTL verification stimuli generation, establishing a two-stage framework that decomposes test plan generation from testbench execution. Our
benchmark reveals that state-of-the-art models, including DeepSeek-R1 and Claude-4.0-Sonnet, achieve only 15.7-21.7% success rates on generating stimuli that pass golden RTL designs. To improve LLM generated stimuli, we develop a comprehensive training methodology combining supervised fine-tuning with a novel reinforcement learning approach, GRPO with State Mutation (GRPO-SMu), which enhances exploration by varying input mutations. Our approach leverages a tree-based branching mutation strategy to construct training data comprising equivalent and mutated trees, moving beyond linear mutation approaches to provide rich learning signals. Training on this curated
dataset, our 7B parameter model achieves a 33.3% golden test pass rate and a 13.9% mutation detection rate, representing a 17.6% absolute improvement over baseline and outperforming much larger general-purpose models. These results demonstrate that specialized training methodologies can significantly enhance LLM
reasoning capabilities for hardware verification tasks, establishing a foundation for automated sub-unit testing in
semiconductor design workflows.
Read the full abstract ▾
All authors Dimple Vijay Kochar, Nathaniel Pinckney, Guan-Ting Liu, Chia-Tung Ho, Chenhui Deng, Haoxing Ren, Brucek Khailany
Machine Learning · Cross-listed from q-fin.RM
Temporal-Aligned Meta-Learning for Risk Management: A Stacking Approach for Multi-Source Credit Scoring
O. Didkovskyi, A. Vidali, N. Jean et al. (+1 more)
This paper presents a meta-learning framework for credit risk assessment of Italian Small and Medium Enterprises (SMEs) that explicitly addresses the temporal misalignment of credit scoring models. The approach aligns financial statement reference dates with evaluation dates, mitigating bias arising from publication delays and asynchronous data sources. It is based on a two-step temporal decomposition that at first estimates annual probabilities of default (PDs) anchored to balance-sheet reference dates (December 31st) through a static model. Then it models the monthly
evolution of PDs using higher-frequency behavioral data. Finally, we employ stacking-based architecture to aggregate multiple scoring systems, each capturing complementary aspects of default risk, into a unified predictive model. In this way, first level model outputs are treated as learned representations that encode non-linear relationships in financial and behavioral indicators, allowing integration of new expert-based features without retraining base models. This design provides a coherent and interpretable solution to challenges typical of low-default environments, including heterogeneous default definitions and reporting delays. Empirical validation shows that the framework effectively captures credit risk
evolution over time, improving temporal consistency and predictive stability relative to standard ensemble methods.
Read the full abstract ▾
All authors O. Didkovskyi, A. Vidali, N. Jean, G. Le Pera
Machine Learning · Cross-listed from cond-mat.str-el
Machine learning nonequilibrium phase transitions in charge-density wave insulators
Yunhao Fan, Sheng Zhang and Gia-Wei Chern
Nonequilibrium electronic forces play a central role in voltage-driven phase transitions but are notoriously expensive to evaluate in dynamical simulations. Here we develop a machine learning framework for adiabatic
lattice dynamics coupled to nonequilibrium electrons, and demonstrate it for a gating induced
insulator to metal transition out of a charge density wave state in the Holstein model. Although exact electronic forces can be obtained from nonequilibrium Green's function (NEGF) calculations, their high computational cost renders long time dynamical simulations prohibitively expensive. By exploiting the locality of the electronic response, we train a neural network to directly predict instantaneous local electronic forces from the
lattice configuration, thereby bypassing repeated NEGF calculations during time
evolution. When combined with Brownian dynamics, the resulting machine learning force field quantitatively reproduces domain wall motion and nonequilibrium phase transition dynamics obtained from full NEGF simulations, while achieving orders of magnitude gains in computational efficiency. Our results establish direct force learning as an efficient and accurate approach for simulating nonequilibrium
lattice dynamics in driven
quantum materials.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.ins-det
Large Language Models for Physics Instrument Design
Sara Zoccheddu, Shah Rukh Qasim, Patrick Owen et al. (+1 more)
We study the use of large
language models (LLMs) for physics instrument design and compare their performance to reinforcement learning (RL). Using only prompting, LLMs are given task constraints and summaries of prior high-scoring designs and propose complete detector configurations, which we evaluate with the same simulators and reward functions used in RL-based optimization. Although RL yields stronger final designs, we find that modern LLMs consistently generate valid, resource-aware, and physically meaningful configurations that draw on broad pretrained knowledge of detector design principles and particle–matter interactions, despite having no task-specific training. Based on this result, as a first step toward hybrid design workflows, we explore pairing the LLMs with a dedicated trust region optimizer, serving as a precursor to future pipelines in which LLMs propose and structure design hypotheses while RL performs reward-driven optimization. Based on these experiments, we argue that LLMs are well suited as meta-planners: they can design and orchestrate RL-based optimization studies, define search strategies, and coordinate multiple interacting components within a unified workflow. In doing so, they point toward automated, closed-loop instrument design in which much of the human effort required to structure and supervise optimization can be reduced.
Read the full abstract ▾
All authors Sara Zoccheddu, Shah Rukh Qasim, Patrick Owen, Nicola Serra
Machine Learning · Cross-listed from cs.CE
An adjoint method for training data-driven reduced-order models
Donglin Liu, Francisco García Atienza and Mengwu Guo
Reduced-order modeling lies at the interface of numerical analysis and data-driven scientific computing, providing principled ways to compress high-fidelity simulations in science and engineering. We propose a training framework that couples a continuous-time form of operator inference with the adjoint-state method to obtain robust data-driven reduced-order models. This method minimizes a trajectory-based loss between reduced-order solutions and projected snapshot data, which removes the need to estimate time derivatives from noisy measurements and provides intrinsic temporal regularization through time integration. We derive the corresponding continuous adjoint equations to compute gradients efficiently and implement a gradient based optimizer to update the reduced model parameters. Each iteration only requires one forward reduced order solve and one adjoint solve, followed by inexpensive gradient assembly, making the method attractive for large-scale simulations. We validate the proposed method on three partial differential equations: viscous Burgers' equation, the two-dimensional Fisher-KPP equation, and an advection-
diffusion equation. We perform systematic comparisons against standard operator inference under two perturbation regimes, namely reduced temporal snapshot density and additive Gaussian noise. For clean data, both approaches deliver similar accuracy, but in situations with sparse sampling and noise, the proposed adjoint-based training provides better accuracy and enhanced roll-out stability.
Read the full abstract ▾
Machine Learning
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
Yu-Yang Qian, Junda Su, Lanxiang Hu et al. (+4 more)
Diffusion large
language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently face an accuracy-parallelism trade-off. Despite increasing interest, existing methods typically focus on only one-side of the coin, targeting either efficiency or accuracy. To address this limitation, we propose d3LLM (Pseudo-Distilled
Diffusion Large
Language Model), striking a balance between accuracy and parallelism: (i) during training, we introduce pseudo-trajectory
distillation to teach the model which
tokens can be decoded confidently at early steps, thereby improving parallelism; (ii) during inference, we employ
entropy-based multi-block decoding with a KV-cache refresh mechanism to achieve high parallelism while maintaining accuracy. To better evaluate dLLMs, we also introduce AUP (Accuracy Under Parallelism), a new metric that jointly measures accuracy and parallelism. Experiments demonstrate that our d3LLM achieves up to 10$\times$ speedup over vanilla LLaDA/Dream, and 5$\times$ speedup over AR models without much accuracy drop. Our code is available at https://github.com/hao-ai-lab/d3LLM.
Read the full abstract ▾
All authors Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang
Machine Learning
TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
Zexi Tan, Tao Xie, Haoyi Xiao et al. (+5 more)
Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing CL-based models face two key limitations: 1) neglecting clustering information during positive/negative sample pair construction, and 2) introducing unreasonable inductive biases, e.g., destroying time dependence and periodicity through augmentation strategies, compromising representation quality. This paper, therefore, proposes a Temporal-Frequency Enhanced Contrastive (TFEC) learning framework. To preserve temporal structure while generating low-distortion representations, a temporal-frequency Co-EnHancement (CoEH) mechanism is introduced. Accordingly, a synergistic dual-path representation and cluster distribution learning framework is designed to jointly optimize cluster structure and representation fidelity. Experiments on six real-world
benchmark datasets demonstrate TFEC's superiority, achieving 4.48% average NMI gains over SOTA methods, with ablation studies validating the design. The code of the paper is available at: https://github.com/yueliangy/TFEC.
Read the full abstract ▾
All authors Zexi Tan, Tao Xie, Haoyi Xiao, Baoyao Yang, Yuzhu Ji, An Zeng, Xiang Zhang, Yiqun Zhang
Machine Learning
Contextual Discrepancy-Aware Contrastive Learning for Robust Medical Time Series Diagnosis in Small-Sample Scenarios
Kaito Tanaka, Aya Nakayama, Masato Ito et al. (+2 more)
Medical time series data, such as
EEG and ECG, are vital for diagnosing neurological and cardiovascular diseases. However, their precise interpretation faces significant challenges due to high annotation costs, leading to data scarcity, and the limitations of traditional contrastive learning in capturing complex temporal patterns. To address these issues, we propose CoDAC (Contextual Discrepancy-Aware Contrastive learning), a novel framework that enhances diagnostic accuracy and generalization, particularly in small-sample settings. CoDAC leverages external healthy data and introduces a Contextual Discrepancy
Estimator (CDE), built upon a
Transformer-based Autoencoder, to precisely quantify abnormal signals through context-aware anomaly scores. These scores dynamically inform a Dynamic Multi-views Contrastive Framework (DMCF), which adaptively weights different temporal views to focus contrastive learning on diagnostically relevant, discrepant regions. Our encoder combines dilated convolutions with multi-head
attention for robust feature extraction. Comprehensive experiments on Alzheimer's Disease
EEG, Parkinson's Disease
EEG, and Myocardial Infarction ECG
datasets demonstrate CoDAC's superior performance across all metrics, consistently outperforming state-of-the-art baselines, especially under low label availability. Ablation studies further validate the critical contributions of CDE and DMCF. CoDAC offers a robust and interpretable solution for medical time series diagnosis, effectively mitigating data scarcity challenges.
Read the full abstract ▾
All authors Kaito Tanaka, Aya Nakayama, Masato Ito, Yuji Nishimura, Keisuke Matsuda
Machine Learning
Near-Optimal Private Linear Regression via Iterative Hessian Mixing
Omri Lev, Moshe Shenfeld, Vishwak Srinivasan et al. (+2 more)
We study differentially private ordinary least squares (DP-OLS) with bounded data $(X,Y)$ via sketching-based mechanisms. While Gaussian sketching approaches have been explored for DP-OLS \citep{sheffet2017differentially}, they are typically viewed as less competitive than the Adaptive Sufficient Statistics Perturbation (AdaSSP) method \citep{wang_adassp}, which directly perturbs the sufficient statistics $(X^{\top}X, X^{\top}Y)$. This method was shown to be close to information-theoretically optimal, while also exhibiting strong empirical performance. In this work, we propose the Iterative Hessian Mixing (IHM), an
algorithm that builds on Gaussian sketching approaches to DP-OLS and is inspired by the Iterative Hessian Sketch of \citet{pilanci_hessiansketch}. We prove that IHM is differentially private and provide utility guarantees in the form of excess empirical risk bounds. These bounds improve upon those of AdaSSP by removing a multiplicative factor that can be as large as the square root of the data dimension. The design of the IHM is based on new accuracy guarantees that we present for prior Gaussian sketching approaches for DP-OLS, which clarify when these methods are expected to perform well and how IHM circumvents their inherent limitations. We also conduct a rigorous empirical evaluation on a large suite of
datasets, demonstrating that IHM consistently outperforms prior baselines, including AdaSSP.
Read the full abstract ▾
All authors Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson
Machine Learning · Cross-listed from stat.ML
Nonparametric Kernel Clustering with Bandit Feedback
Victor Thuot, Sebastian Vogt, Debarghya Ghoshdastidar et al. (+1 more)
Clustering with bandit feedback refers to the problem of partitioning the arms of an $N$-armed
stochastic bandit according to their underlying distributions, based on noisy observations collected sequentially and adaptively. This setting has attracted growing interest for its applicability in recommendation systems, crowdsourcing, and adaptive trials. Existing works rely on the strong assumption that arm distributions are sub-Gaussian, which can only distinguish arms whose distributions differ in mean - missing realistic settings where distributional differences lie in shape or higher moments. % We introduce a framework of nonparametric clustering with bandit feedback, free of any parametric assumptions regarding the arm distributions. We adopt a kernel-based approach and reformulate the problem as clustering arms according to their kernel mean
embeddings in a reproducing kernel
Hilbert space (RKHS). Building on this formulation, we introduce the \kabc\
algorithm, prove that it is $\delta$-PAC, and derive a non-asymptotic high-probability upper bound on its sampling complexity. The bound is governed by a variance-aware signal-to-noise ratio defined as the minimum over pairs of arms in distinct clusters of the ratio between their squared MMD and their RKHS variance. \kabc\ achieves instance-dependent guarantees while being adaptive to this unknown ratio. We validate our approach empirically on synthetic and real-world
datasets, demonstrating that \kabc\ succeeds in distributional clustering settings where mean-based methods fail.
Read the full abstract ▾
All authors Victor Thuot, Sebastian Vogt, Debarghya Ghoshdastidar, Nicolas Verzelen
Machine Learning
Stagewise Reinforcement Learning and the Geometry of the Regret Landscape
Chris Elliott, Einar Urdshals, David Quarel et al. (+2 more)
Singular learning theory characterizes
Bayesian learning as an evolving tradeoff between accuracy and complexity, with transitions between qualitatively different solutions as sample size increases. We extend this theory to reinforcement learning, proving that the concentration of a generalized posterior over policies is governed by the local learning coefficient (LLC), an invariant of the geometry of the regret function. This theory predicts that deep reinforcement learning with SGD should proceed from simple policies with high regret to complex policies with low regret. We verify this prediction empirically in a gridworld environment exhibiting stagewise policy development: phase transitions over training manifest as "opposing staircases" where regret decreases sharply while the LLC increases.
Read the full abstract ▾
All authors Chris Elliott, Einar Urdshals, David Quarel, Matthew Farrugia-Roberts, Daniel Murfet
Machine Learning · Cross-listed from cs.CL
Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions
Yongqi Li, Hao Lang, Tieyun Qian et al. (+1 more)
Vision-
language models are increasingly employed as
multimodal conversational
agents (MCAs) for diverse conversational tasks. Recently, reinforcement learning (RL) has been widely explored for adapting MCAs to various human-AI interaction scenarios. Despite showing great enhancement in generalization performance, fine-tuning MCAs via RL still faces challenges in handling the extremely large text
token space. To address this, we learn a compact latent action space for RL fine-tuning instead. Specifically, we adopt the learning from observation mechanism to construct the codebook for the latent action space, where future observations are leveraged to estimate current latent actions that could further be used to reconstruct future observations. However, the scarcity of paired image-text data hinders learning a codebook with sufficient coverage. Thus, we leverage both paired image-text data and text-only data to construct the latent action space, using a cross-modal projector for transforming text
embeddings into image-text
embeddings. We initialize the cross-modal projector on paired image-text data, and further train it on massive text-only data with a novel cycle consistency loss to enhance its robustness. We show that our latent action based method outperforms competitive baselines on two conversation tasks across various RL
algorithms.
Read the full abstract ▾
All authors Yongqi Li, Hao Lang, Tieyun Qian, Yongbin Li
Machine Learning
Land-then-transport: A Flow Matching-Based Generative Decoder for Wireless Image Transmission
Jingwen Fu, Ming Xiao, Mikael Skoglund et al. (+1 more)
Due to strict rate and reliability demands, wireless image transmission remains difficult for both classical layered designs and joint source-channel coding (JSCC), especially under low latency.
Diffusion-based generative decoders can deliver strong perceptual quality by leveraging learned image priors, but iterative
stochastic denoising leads to high decoding delay. To enable low-latency decoding, we propose a flow-matching (FM) generative decoder under a new land-then-transport (LTT) paradigm that tightly integrates the physical wireless channel into a continuous-time probability flow. For AWGN channels, we build a Gaussian smoothing path whose noise schedule indexes effective noise levels, and derive a closed-form teacher velocity field along this path. A neural-network student vector field is trained by conditional flow matching, yielding a deterministic, channel-aware ODE decoder with complexity linear in the number of ODE steps. At inference, it only needs an estimate of the effective noise variance to set the ODE starting time. We further show that Rayleigh fading and
MIMO channels can be mapped, via linear MMSE equalization and singular-value-domain processing, to AWGN-equivalent channels with calibrated starting times. Therefore, the same probability path and trained velocity field can be reused for Rayleigh and
MIMO without retraining. Experiments on MNIST, Fashion-MNIST, and DIV2K over AWGN, Rayleigh, and
MIMO demonstrate consistent gains over JPEG2000+LDPC, DeepJSCC, and
diffusion-based baselines, while achieving good perceptual quality with only a few ODE steps. Overall, LTT provides a deterministic, physically interpretable, and computation-efficient framework for generative wireless image decoding across diverse channels.
Read the full abstract ▾
All authors Jingwen Fu, Ming Xiao, Mikael Skoglund, Dong In Kim
Machine Learning
FROAV: A Framework for RAG Observation and Agent Verification – Lowering the Barrier to LLM Agent Research
Tzu-Hsuan Lin and Chih-Hsuan Kao
The rapid advancement of Large
Language Models (LLMs) and their integration into autonomous
agent systems has created unprecedented opportunities for document analysis, decision support, and knowledge
retrieval. However, the complexity of developing, evaluating, and iterating on LLM-based
agent workflows presents significant barriers to researchers, particularly those without extensive software engineering expertise. We present FROAV (Framework for RAG Observation and
Agent Verification), an open-source research platform that democratizes LLM
agent research by providing a plug-and-play architecture combining visual workflow orchestration, a comprehensive evaluation framework, and extensible Python integration. FROAV implements a multi-stage
Retrieval-Augmented Generation (RAG) pipeline coupled with a rigorous "LLM-as-a-Judge" evaluation system, all accessible through intuitive graphical interfaces. Our framework integrates n8n for no-code workflow design, PostgreSQL for granular data management, FastAPI for flexible backend logic, and Streamlit for human-in-the-loop interaction. Through this integrated ecosystem, researchers can rapidly prototype RAG strategies, conduct
prompt engineering experiments, validate
agent performance against human judgments, and collect structured feedback-all without writing infrastructure code. We demonstrate the framework's utility through its application to financial document analysis, while emphasizing its material-agnostic architecture that adapts to any domain requiring semantic analysis. FROAV represents a significant step toward making LLM
agent research accessible to a broader scientific community, enabling researchers to focus on hypothesis testing and algorithmic innovation rather than system integration challenges.
Read the full abstract ▾
Machine Learning
Graph Inference Towards ICD Coding
Xiaoxiao Deng
Automated ICD coding involves assigning standardized diagnostic codes to clinical narratives. The vast label space and extreme class imbalance continue to challenge precise prediction. To address these issues, LabGraph is introduced – a unified framework that reformulates ICD coding as a graph generation task. By combining
adversarial domain adaptation, graph-based reinforcement learning, and perturbation regularization, LabGraph effectively enhances model robustness and generalization. In addition, a label graph discriminator dynamically evaluates each generated code, providing adaptive reward feedback during training. Experiments on
benchmark datasets demonstrate that LabGraph consistently outperforms previous approaches on micro-F1, micro-AUC, and P@K.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DS
The Secretary Problem with Predictions and a Chosen Order
Helia Karisani, Mohammadreza Daneshvaramoli, Hedyeh Beyhaghi et al. (+2 more)
We study a learning-augmented variant of the secretary problem, recently introduced by Fujii and Yoshida (2023), in which the decision-maker has access to machine-learned predictions of candidate values. The central challenge is to balance consistency and robustness: when predictions are accurate, the
algorithm should select a near-optimal secretary, while under inaccurate predictions it should still guarantee a bounded competitive ratio. We consider both the classical Random Order Secretary Problem (ROSP), where candidates arrive in a uniformly random order, and a more natural learning-augmented model in which the decision-maker may choose the arrival order based on predicted values. We call this model the Chosen Order Secretary Problem (COSP), capturing scenarios such as interview schedules set in advance. We propose a new randomized
algorithm applicable to both ROSP and COSP. Our method switches from fully trusting predictions to a threshold-based rule once a large prediction deviation is detected. Let $\epsilon \in [0,1]$ denote the maximum multiplicative prediction error. For ROSP, our
algorithm achieves a competitive ratio of $\max\{0.221, (1-\epsilon)/(1+\epsilon)\}$, improving upon the prior bound of $\max\{0.215, (1-\epsilon)/(1+\epsilon)\}$. For COSP, we achieve $\max\{0.262, (1-\epsilon)/(1+\epsilon)\}$, surpassing the $0.25$ worst-case bound for prior approaches and moving closer to the classical secretary
benchmark of $1/e \approx 0.368$. These results highlight the benefit of combining predictions with arrival-order control in online decision-making.
Read the full abstract ▾
All authors Helia Karisani, Mohammadreza Daneshvaramoli, Hedyeh Beyhaghi, Mohammad Hajiesmaili, Cameron Musco
Machine Learning
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
Haoqian Meng, Yilun Luo, Yafei Zhao et al. (+3 more)
The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large
Language Model (LLM) inference. However, it is difficult to adapt existing Post-Training Quantization (PTQ) strategies to these formats: rotation-based methods compromise fine-grained block isolation; smoothing techniques struggle with significant 4-bit quantization errors; and mixed-precision approaches often conflict with hardware constraints on unified-precision computation. To address these challenges, we propose ARCQuant, a framework that boosts NVFP4 performance via Augmented Residual Channels. Distinct from methods that compromise block isolation or hardware uniformity, ARCQuant maintains a strictly unified NVFP4 format by augmenting the activation
matrix with quantized residual channels. This design integrates the error compensation process directly into the
matrix reduction dimension, enabling the use of standard, highly optimized GEMM kernels with minimal overhead. Theoretical analysis confirms that the worst-case error bound of our dual-stage NVFP4 quantization is comparable to that of standard 8-bit formats such as MXFP8. Extensive experiments on LLaMA and Qwen models demonstrate that ARCQuant achieves state-of-the-art accuracy, comparable to full-precision baselines in perplexity and downstream tasks. Furthermore, deployment on RTX 5090 and RTX PRO 6000 GPUs confirms practical benefits, achieving up to 3x speedup over FP16. Our code is available at https://github.com/actypedef/ARCQuant.
Read the full abstract ▾
All authors Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang, Xindian Ma
Machine Learning
Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data
Youngmin Oh, Hyung-Il Kim and Jung Uk Kim
Multi-task learning (MTL) is critical in real-world applications such as autonomous driving and robotics, enabling simultaneous handling of diverse tasks. However, obtaining fully annotated data for all tasks is impractical due to labeling costs. Existing methods for partially labeled MTL typically rely on predictions from unlabeled tasks, making it difficult to establish reliable task associations and potentially leading to negative transfer and suboptimal performance. To address these issues, we propose a prototype-based knowledge
retrieval framework that achieves robust MTL instead of relying on predictions from unlabeled tasks. Our framework consists of two key components: (1) a task prototype
embedding task-specific characteristics and quantifying task associations, and (2) a knowledge
retrieval transformer that adaptively refines feature representations based on these associations. To achieve this, we introduce an association knowledge generating (AKG) loss to ensure the task prototype consistently captures task-specific characteristics. Extensive experiments demonstrate the effectiveness of our framework, highlighting its potential for robust multi-task learning, even when only a subset of tasks is annotated.
Read the full abstract ▾
Machine Learning
AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations
Michael J. Clark
As models grow more capable, humans cannot reliably verify what they say. Scalable steering requires methods that are internal, self-supervised, and transfer out-of-distribution; existing methods satisfy some but not all three. We introduce AntiPaSTO, which separates representations along an antiparallel axis (+1/-1 produce opposite shifts), with coherence constraints preventing collapse. Training uses only two contrasting words inserted into template sentences, with no preference labels. When we use 800 such synthetic pairs on Gemma-3-1B, AntiPaSTO beats prompting baselines by 6.9x Steering F1 on DailyDilemmas and wins on 5 of 6 tested value axes. We also find preliminary evidence that it maintains bidirectional control where prompting triggers refusal.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Puzzle it Out: Local-to-Global World Model for Offline Multi-Agent Reinforcement Learning
Sijia Li, Xinran Li, Shibo Chen et al. (+1 more)
Offline multi-
agent reinforcement learning (MARL) aims to solve cooperative decision-making problems in multi-
agent systems using pre-collected
datasets. Existing offline MARL methods primarily constrain training within the
dataset distribution, resulting in overly conservative policies that struggle to generalize beyond the support of the data. While model-based approaches offer a promising solution by expanding the original
dataset with synthetic data generated from a learned world model, the high dimensionality, non-stationarity, and complexity of multi-
agent systems make it challenging to accurately estimate the transitions and reward functions in offline MARL. Given the difficulty of directly modeling joint dynamics, we propose a local-to-global (LOGO) world model, a novel framework that leverages local predictions-which are easier to estimate-to infer global state dynamics, thus improving prediction accuracy while implicitly capturing
agent-wise dependencies. Using the trained world model, we generate synthetic data to augment the original
dataset, expanding the effective state-action space. To ensure reliable policy learning, we further introduce an uncertainty-aware sampling mechanism that adaptively weights synthetic data by prediction uncertainty, reducing approximation error propagation to policies. In contrast to conventional ensemble-based methods, our approach requires only an additional encoder for uncertainty estimation, significantly reducing computational overhead while maintaining accuracy. Extensive experiments across 8 scenarios against 8 baselines demonstrate that our method surpasses state-of-the-art baselines on standard offline MARL
benchmarks, establishing a new model-based baseline for generalizable offline multi-
agent learning.
Read the full abstract ▾
All authors Sijia Li, Xinran Li, Shibo Chen, Jun Zhang
Machine Learning · Cross-listed from cs.CV
Improving Video Question Answering through query-based frame selection
Himanshu Patil, Geo Jolly, Ramana Raja Buddala et al. (+2 more)
Video Question Answering (VideoQA) models enhance understanding and interaction with audiovisual content, making it more accessible, searchable, and useful for a wide range of fields such as education, surveillance, entertainment, and content creation. Due to heavy compute requirements, most large visual
language models (VLMs) for VideoQA rely on a fixed number of frames by uniformly sampling the
video. However, this process does not pick important frames or capture the context of the
video. We present a novel query-based selection of frames relevant to the questions based on the submodular mutual Information (SMI) functions. By replacing uniform frame sampling with query-based selection, our method ensures that the chosen frames provide complementary and essential visual information for accurate VideoQA. We evaluate our approach on the MVBench
dataset, which spans a diverse set of multi-action
video tasks. VideoQA accuracy on this
dataset was assessed using two VLMs, namely
Video-LLaVA and LLaVA-NeXT, both of which originally employed uniform frame sampling. Experiments were conducted using both uniform and query-based sampling strategies. An accuracy improvement of up to 4% was observed when using query-based frame selection over uniform sampling. Qualitative analysis further highlights that query-based selection, using SMI functions, consistently picks frames better aligned with the question. We opine that such query-based frame selection can enhance accuracy in a wide range of tasks that rely on only a subset of
video frames.
Read the full abstract ▾
All authors Himanshu Patil, Geo Jolly, Ramana Raja Buddala, Ganesh Ramakrishnan, Rohit Saluja
Machine Learning
Surrogate-based Optimization via Clustering for Box-Constrained Problems
Maaz Ahmad and Iftekhar A. Karimi
Global optimization of large-scale, complex systems such as multi-physics black-box simulations and real-world industrial systems is important but challenging. This work presents a novel Surrogate-Based Optimization framework based on Clustering, SBOC for global optimization of such systems, which can be used with any surrogate modeling technique. At each iteration, it uses a single surrogate model for the entire domain, employs k-means clustering to identify unexplored domain, and exploits a local region around the surrogate optimum to potentially add three new sample points in the domain. SBOC has been tested against sixteen promising benchmarking
algorithms using 52 analytical test functions of varying input dimensionalities and shape profiles. It successfully identified a global minimum for most test functions with substantially lower computational effort than other
algorithms. It worked especially well on test functions with four or more input variables. It was also among the top six
algorithms in approaching a global minimum closely. Overall, SBOC is a robust, reliable, and efficient
algorithm for global optimization of box-constrained systems.
Read the full abstract ▾
Machine Learning
Variational Autoencoder with Normalizing flow for X-ray spectral fitting
Fiona Redmen, Ethan Tregidga, James F. Steiner et al. (+1 more)
Black hole X-ray binaries (BHBs) can be studied with spectral fitting to provide physical constraints on
accretion in extreme gravitational environments. Traditional methods of spectral fitting such as Markov Chain Monte Carlo (MCMC) face limitations due to computational times. We introduce a probabilistic model, utilizing a variational autoencoder with a normalizing flow, trained to adopt a physical latent space. This neural network produces predictions for spectral-model parameters as well as their full probability distributions. Our implementations result in a significant improvement in spectral reconstructions over a previous deterministic model while performing three orders of magnitude faster than traditional methods.
Read the full abstract ▾
All authors Fiona Redmen, Ethan Tregidga, James F. Steiner, Cecilia Garraffo
Machine Learning · Cross-listed from eess.SP
PIDT: Physics-Informed Digital Twin for Optical Fiber Parameter Estimation
Zicong Jiang, Magnus Karlsson, Erik Agrell et al. (+1 more)
We propose physics-informed digital twin (PIDT): a fiber parameter estimation approach that combines a parameterized split-step method with a physics-informed loss. PIDT improves accuracy and convergence speed with lower complexity compared to previous neural operators.
Read the full abstract ▾
All authors Zicong Jiang, Magnus Karlsson, Erik Agrell, Christian Häger