Machine Learning · Cross-listed from cs.DB
A Domain-Specific Language for LLM-Driven Trigger Generation in Multimodal Data Collection
Philipp Reis, Philipp Rigoll, Martin Zehetner et al. (+3 more)
Data-driven systems depend on task-relevant data, yet data collection pipelines remain passive and indiscriminate. Continuous logging of
multimodal sensor streams incurs high storage costs and captures irrelevant data. This paper proposes a declarative framework for intent-driven, on-device data collection that enables selective collection of
multimodal sensor data based on high-level user requests. The framework combines natural
language interaction with a formally specified domain-specific
language (DSL). Large
language models translate user-defined requirements into verifiable and composable DSL programs that define conditional triggers across heterogeneous sensors, including cameras,
LiDAR, and system telemetry. Empirical evaluation on vehicular and robotic perception tasks shows that the DSL-based approach achieves higher generation consistency and lower execution latency than unconstrained code generation while maintaining comparable detection performance. The structured abstraction supports modular trigger composition and concurrent deployment on resource-constrained edge platforms. This approach replaces passive logging with a verifiable, intent-driven mechanism for
multimodal data collection in real-time systems.
Read the full abstract ▾
All authors Philipp Reis, Philipp Rigoll, Martin Zehetner, Jacqueline Henle, Stefan Otten, Eric Sax
Machine Learning · Cross-listed from eess.SP
FED-HARGPT: A Hybrid Centralized-Federated Approach of a Transformer-based Architecture for Human Context Recognition
Wandemberg Gibaut, Alexandre Osorio, Amparo Munoz et al. (+2 more)
The study explores a hybrid centralized-
federated approach for Human Activity Recognition (HAR) using a
Transformer-based architecture. With the increasing ubiquity of edge devices, such as smartphones and wearables, a significant amount of private data from wearable and inertial sensors is generated, facilitating discreet monitoring of human activities, including resting, sleeping, and walking. This research focuses on deploying HAR technologies using mobile sensor data and leveraging
Federated Learning within the Flower framework to evaluate the training of a
federated model derived from a centralized baseline. The experimental results demonstrate the effectiveness of the proposed hybrid approach in improving the accuracy and robustness of HAR models while preserving data
privacy in a non-IID data scenario. The
federated learning setup demonstrated comparable performance to centralized models, highlighting the potential of
federated learning to strike a balance between data
privacy and model performance in real-world applications.
Read the full abstract ▾
All authors Wandemberg Gibaut, Alexandre Osorio, Amparo Munoz, Sildolfo F. G. Neto, Fabio Grassiotto
Machine Learning · Cross-listed from math.OC
Response-Aware Risk-Constrained Control Barrier Function With Application to Vehicles
Qijun Liao and Jue Yang
This paper proposes a unified control framework based on Response-Aware Risk-Constrained Control Barrier Function for dynamic safety boundary control of vehicles. Addressing the problem of physical model parameter mismatch, the framework constructs an uncertainty propagation model that fuses nominal dynamics priors with direct vehicle body responses. Utilizing simplified single-track dynamics to provide a baseline direction for control gradients and covering model deviations through statistical analysis of body response signals, the framework eliminates the dependence on accurate online estimation of road surface adhesion coefficients. By introducing Conditional Value at Risk (CVaR) theory, the framework reformulates traditional deterministic safety constraints into probabilistic constraints on the tail risk of barrier function derivatives. Combined with a
Bayesian online learning mechanism based on inverse Wishart priors, it identifies environmental noise covariance in real-time, adaptively tuning safety margins to reduce performance loss under prior parameter mismatch. Finally, based on Control Lyapunov Function (CLF), a unified Second-Order Cone Programming (SOCP) controller is constructed. Theoretical analysis establishes convergence of Sequential Convex Programming to local Karush-Kuhn-Tucker points and provides per-step probabilistic safety bounds. High-fidelity dynamics simulations demonstrate that under extreme conditions, the method not only eliminates the output divergence phenomenon of traditional methods but also achieves Pareto improvement in both safety and tracking performance. For the chosen risk level, the per-step safety violation probability is theoretically bounded by approximately 2%, validated through high-fidelity simulations showing zero boundary violations across all tested scenarios.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IT
JCAS-MARL: Joint Communication and Sensing UAV Networks via Resource-Constrained Multi-Agent Reinforcement Learning
Islam Guven and Mehmet Parlak
Multi-
UAV networks are increasingly deployed for large-scale inspection and monitoring missions, where operational performance depends on the coordination of sensing reliability, communication quality, and energy constraints. In particular, the rapid increase in overflowing waste bins and illegal dumping sites has created a need for efficient detection of waste hotspots. In this work, we introduce JCAS-MARL, a resource-aware multi-
agent reinforcement learning (MARL) framework for joint communication and sensing (JCAS)-enabled
UAV networks. Within this framework, multiple
UAVs operate in a shared environment where each
agent jointly controls its trajectory and the resource allocation of an OFDM waveform used simultaneously for sensing and communication. Battery consumption, charging behavior, and associated CO$_2$ emissions are incorporated into the system state to model realistic operational constraints. Information sharing occurs over a dynamic communication graph determined by
UAV positions and wireless channel conditions. Waste hotspot detection requires consensus among multiple
UAVs to improve reliability. Using this environment, we investigate how MARL policies exploit the sensing-communication-energy trade-off in JCAS-enabled
UAV networks. Simulation results demonstrate that adaptive pilot-density control learned by the
agents can outperform static configurations, particularly in scenarios where sensing accuracy and communication connectivity vary across the environment.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.IV
MiSiSUn: Minimum Simplex Semisupervised Unmixing
Behnood Rasti, Bikram Koirala and Paul Scheunders
This paper proposes a semisupervised
geometric unmixing approach called minimum simplex semisupervised unmixing (MiSiSUn). The geometry of the data was incorporated for the first time into library-based unmixing using a simplex-volume-flavored penalty based on an archetypal analysis-type linear model. The experimental results were performed on two simulated
datasets considering different levels of mixing ratios and spatial instruction at varying input noise. MiSiSUn considerably outperforms state-of-the-art semisupervised unmixing methods. The improvements vary from 1 dB to over 3 dB in different scenarios. The proposed method was also applied to a real
dataset where visual interpretation is close to the geological map. MiSiSUn was implemented using PyTorch, which is open-source and available at https://github.com/BehnoodRasti/MiSiSUn. Moreover, we provide a dedicated Python package for Semisupervised Unmixing, which is open-source and includes all the methods used in the experiments for the sake of reproducibility.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.BM
Deciphering Scientific Reasoning Steps from Outcome Data for Molecule Optimization
Zequn Liu, Kehan Wu, Shufang Xie et al. (+5 more)
Emerging
reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate
reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific
reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large
language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative
reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable
reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The
reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural
language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering
reasoning steps from outcome data as a viable paradigm for enabling scientific
reasoning, providing a scalable approach to accelerate scientific discovery.
Read the full abstract ▾
All authors Zequn Liu, Kehan Wu, Shufang Xie, Zekun Guo, Wei Zhang, Tao Qin, Renhe Liu, Yingce Xia
Machine Learning
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Lucas Maes, Quentin Le Lidec, Damien Scieur et al. (+2 more)
Joint
Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on complex multi-term losses, exponential moving averages, pre-trained encoders, or auxiliary supervision to avoid representation collapse. In this work, we introduce LeWorldModel (LeWM), the first JEPA that trains stably end-to-end from raw pixels using only two loss terms: a next-
embedding prediction loss and a regularizer enforcing Gaussian-distributed latent
embeddings. This reduces tunable loss hyperparameters from six to one compared to the only existing end-to-end alternative. With ~15M parameters trainable on a single GPU in a few hours, LeWM plans up to 48x faster than foundation-model-based world models while remaining competitive across diverse 2D and 3D control tasks. Beyond control, we show that LeWM's latent space encodes meaningful physical structure through probing of physical quantities. Surprise evaluation confirms that the model reliably detects physically implausible events.
Read the full abstract ▾
All authors Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero
Machine Learning
MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
Tianyang Luo, Tao Feng, Zhigang Hua et al. (+4 more)
Reinforcement learning (RL) fine-tuning improves large
language model (LLM)
reasoning using reward signals on sampled rollouts. When reward labels are available for only a subset of rollouts, restricting policy updates to that subset leaves the remaining rollouts unused for policy optimization. Semi-supervised learning propagates labels from labeled to unlabeled samples, but existing methods either diffuse labels with fixed similarity weights or treat each sample independently, ignoring the relations among queries, thinking processes, and answers. We propose MemReward, a graph-based experience
memory that propagates rewards to unlabeled rollouts during online policy optimization. MemReward stores queries and the rollouts (thinking processes and final answers) of an initial LLM policy as nodes of a heterogeneous graph connected by similarity and structural edges, and warms up a GNN on labeled rollouts to propagate rewards over this graph. During online RL fine-tuning, unlabeled rollouts are attached to the graph by query similarity, and the policy is updated with ground-truth rewards on labeled rollouts and GNN-predicted rewards on the rest. We evaluate MemReward on 13
benchmarks in mathematics, question answering, and code generation with verifiable rewards, and further with LLM-judge, human-preference, and continuous rewards. With ground-truth rewards on only 20% of rollouts, MemReward achieves 96.6% of the performance of fully supervised training (Oracle) on Qwen2.5-1.5B and 97.3% on Qwen2.5-3B, where it also outperforms label propagation and FixMatch-style self-training. It carries over to Llama backbones up to 8B and closely approaches Oracle on out-of-domain tasks.
Read the full abstract ▾
All authors Tianyang Luo, Tao Feng, Zhigang Hua, Yan Xie, Shuang Yang, Ge Liu, Jiaxuan You
Machine Learning
GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space
Wentao Wang, Haoran Xu and Guang Tan
In autonomous driving, multi-
agent collaborative perception enhances sensing capabilities by enabling
agents to share perceptual data. A key challenge lies in handling heterogeneous features from
agents equipped with different sensing modalities or model architectures, which complicates data fusion. Existing approaches often require retraining encoders or designing interpreter modules for pairwise feature
alignment, but these solutions are not scalable in practice. To address this, we propose GT-Space, a flexible and scalable collaborative perception framework for heterogeneous
agents. GT-Space constructs a common feature space from ground-truth labels, providing a unified reference for feature
alignment. With this shared space,
agents only need a single adapter module to project their features, eliminating the need for pairwise interactions with other
agents. Furthermore, we design a fusion network trained with contrastive losses across diverse modality combinations. Extensive experiments on simulation
datasets (OPV2V and V2XSet) and a real-world
dataset (RCooper) demonstrate that GT-Space consistently outperforms baselines in detection accuracy while delivering robust performance. Our code will be released at https://github.com/KingScar/GT-Space.
Read the full abstract ▾
Machine Learning
Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning
Siyu Liu, Guangqi Wen, Peng Cao et al. (+4 more)
Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing
Transformer-based methods due to the limited number of training samples. To address these challenges, we propose KD-
Brain, a Prior-Informed Graph Learning framework for explicitly encoding prior knowledge to guide the learning process. Specifically, we design a Semantic-Conditioned Interaction mechanism that injects semantic priors into the
attention query, explicitly navigating the subnetwork interactions based on their functional identities. Furthermore, we introduce a Pathology-Consistent Constraint, which regularizes the model optimization by aligning the learned interaction distributions with clinical priors. Additionally, KD-
Brain leads to state-of-the-art performance on a wide range of disorder diagnosis tasks and identifies interpretable biomarkers consistent with psychiatric pathophysiology. Our code is available at https://anonymous.4open.science/r/KDBrain.
Read the full abstract ▾
All authors Siyu Liu, Guangqi Wen, Peng Cao, Jinzhu Yang, Xiaoli Liu, Fei Wang, Osmar R. Zaiane
Machine Learning · Cross-listed from cs.IR
VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction
Hui Liao, Chuan Qin, Yongwen Ren et al. (+4 more)
Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts. Beyond accuracy, LJP calls for intrinsically interpretable and legally grounded
reasoning that can reconcile statutory rules with precedent-informed standards. However, existing methods often behave as static, one-shot predictors, providing limited procedural support for verifiable
reasoning and little capability to adapt as jurisprudential practice evolves. We propose VERDICT, a self-refining collaborative multi-
agent framework that simulates a virtual collegial panel. VERDICT assigns specialized
agents to complementary roles (e.g., fact structuring, legal
retrieval, opinion drafting, and supervisory verification) and coordinates them in a traceable draft–verify–revise workflow with explicit Pass/Reject feedback, producing verifiable
reasoning traces and revision rationales. To capture evolving case experience, we further introduce a Hybrid Jurisprudential
Memory (HJM) grounded in the Micro-Directive Paradigm, which stores precedent standards and continually distills validated multi-
agent verification trajectories into updated Micro-Directives for continual learning across cases. We evaluate VERDICT on CAIL2018 and a newly constructed CJO2025
dataset with a strict future time-split for temporal generalization. VERDICT achieves state-of-the-art performance on CAIL2018 and demonstrates strong generalization on CJO2025. To facilitate reproducibility and further research, we release our code and the
dataset at https://anonymous.4open.science/r/ARR-4437.
Read the full abstract ▾
All authors Hui Liao, Chuan Qin, Yongwen Ren, Hao Li, Zhenya Huang, Yanyong Zhang, Chao Wang
Machine Learning · Cross-listed from cs.AI
Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning
Aliyu Agboola Alege
We present a complete theoretical characterization of Latent Posterior Factors (LPF), a principled framework for aggregating multiple heterogeneous evidence items in probabilistic prediction tasks. Multi-evidence
reasoning arises pervasively in high-stakes domains including healthcare diagnosis, financial risk assessment, legal case analysis, and regulatory compliance, yet existing approaches either lack formal guarantees or fail to handle multi-evidence scenarios architecturally. LPF encodes each evidence item into a Gaussian latent posterior via a variational autoencoder, converting posteriors to soft factors through Monte Carlo marginalization, and aggregating factors via exact Sum-Product Network inference (LPF-SPN) or a learned neural aggregator (LPF-Learned). We prove seven formal guarantees spanning the key desiderata for trustworthy AI: Calibration Preservation (ECE <= epsilon + C/sqrt(K_eff)); Monte Carlo Error decaying as O(1/sqrt(M)); a non-vacuous PAC-Bayes bound with train-test gap of 0.0085 at N=4200; operation within 1.12x of the information-theoretic lower bound; graceful degradation as O(epsilon*delta*sqrt(K)) under corruption, maintaining 88% performance with half of evidence adversarially replaced; O(1/sqrt(K)) calibration decay with R^2=0.849; and exact epistemic-aleatoric uncertainty decomposition with error below 0.002%. All
theorems are empirically validated on controlled
datasets spanning up to 4,200 training examples. Our theoretical framework establishes LPF as a foundation for trustworthy multi-evidence AI in safety-critical applications.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning
Aliyu Agboola Alege
Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discrete predicates (probabilistic logic frameworks), limiting scalability to unstructured data. We introduce Latent Posterior Factors (LPF), a framework that transforms Variational Autoencoder (VAE) latent posteriors into soft likelihood factors for Sum-Product Network (SPN) inference, enabling tractable probabilistic
reasoning over unstructured evidence while preserving calibrated uncertainty estimates. We instantiate LPF as LPF-SPN (structured factor-based inference) and LPF-Learned (end-to-end learned aggregation), enabling a principled comparison between explicit probabilistic
reasoning and learned aggregation under a shared uncertainty representation. Across eight domains (seven synthetic and the FEVER
benchmark), LPF-SPN achieves high accuracy (up to 97.8%), low calibration error (ECE 1.4%), and strong probabilistic fit, substantially outperforming evidential deep learning, LLMs and graph-based baselines over 15 random seeds. Contributions: (1) A framework bridging latent uncertainty representations with structured probabilistic
reasoning. (2) Dual architectures enabling controlled comparison of
reasoning paradigms. (3) Reproducible training methodology with seed selection. (4) Evaluation against EDL, BERT, R-GCN, and large
language model baselines. (5) Cross-domain validation. (6) Formal guarantees in a companion paper.
Read the full abstract ▾
Machine Learning
PLUME: Building a Network-Native Foundation Model for Wireless Traces via Protocol-Aware Tokenization
Swadhin Pradhan, Shazal Irshad and Jerome Henry
Foundation models succeed when they learn in the native structure of a modality, whether morphology-respecting
tokens in
language or pixels in
vision. Wireless packet traces deserve the same treatment: meaning emerges from layered headers, typed fields, timing gaps, and cross-packet state machines, not flat strings. We present Plume (Protocol
Language Understanding Model for Exchanges), a compact 140M-parameter foundation model for 802.11 traces that learns from structured PDML dissections. A protocol-aware tokenizer splits along the dissector field tree, emits gap
tokens for timing, and normalizes identifiers, yielding 6.2x shorter sequences than BPE with higher per
token information density. Trained on a curated corpus, Plume achieves 74-97% next-packet
token accuracy across five real-world failure categories and AUROC >= 0.99 for zero-shot anomaly detection. On the same prediction task, frontier LLMs (Claude Opus 4.6, GPT-5.4) score comparably despite receiving identical protocol context, yet Plume does so with > 600x fewer parameters, fitting on a single GPU at effectively zero marginal cost vs. cloud API pricing, enabling on-prem,
privacy-preserving root cause analysis.
Read the full abstract ▾
Machine Learning
SemRep: Generative Code Representation Learning with Code Transformations
Weichen Li, Jiamin Song, Bogdan Alexandru Stoica et al. (+4 more)
Code transformation is a foundational capability in the software development process, where its effectiveness relies on constructing a high-quality code representation to characterize the input code semantics and guide the transformation. Existing approaches treat code transformation as an end-to-end learning task, leaving the construction of the representation needed for semantic
reasoning implicit in model weights or relying on rigid compiler-level abstractions. We present SemRep, a framework that improves code transformation through generative code representation learning. Our key insight is to employ the semantics-preserving transformations as the intermediate representation, which serves as both a generative mid-training task and the guidance for subsequent instruction-specific code transformations. Across general code editing and optimization tasks (e.g., GPU kernel optimization), SemRep outperforms the extensively finetuned baselines with strictly the same training budget by 6.9% in correctness, 1.1x in performance, 13.9% in generalization, and 6.7% in robustness. With the improved exploration of diverse code transformations, SemRep is particularly amenable to evolutionary search. Combined with an evolutionary coding
agent, SemRep finds optimizations that 685B larger-weight baselines fail to discover while achieving the same performance with 25% less inference compute.
Read the full abstract ▾
All authors Weichen Li, Jiamin Song, Bogdan Alexandru Stoica, Arav Dhoot, Gabriel Ryan, Shengyu Fu, Kexin Pei
Machine Learning
BERTology of Molecular Property Prediction
Mohammad Mostafanejad, Paul Saxe and T. Daniel Crawford
Chemical
language models (CLMs) have emerged as promising competitors to popular classical machine learning models for molecular property prediction (MPP) tasks. However, an increasing number of studies have reported inconsistent and contradictory results for the performance of CLMs across various MPP
benchmark tasks. In this study, we conduct and analyze hundreds of meticulously controlled experiments to systematically investigate the effects of various factors, such as
dataset size, model size, and standardization, on the pre-training and fine-tuning performance of CLMs for MPP. In the absence of well-established scaling laws for encoder-only masked
language models, our aim is to provide comprehensive numerical evidence and a deeper understanding of the underlying mechanisms affecting the performance of CLMs for MPP tasks, some of which appear to be entirely overlooked in the literature.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Design and evaluation of an agentic workflow for crisis-related synthetic tweet datasets
Roben Delos Reyes, Timothy Douglas and Asanobu Kitamoto
Twitter (now X) has become an important source of social media data for situational awareness during crises. Crisis informatics research has widely used tweets from Twitter to develop and evaluate artificial intelligence (AI) systems for various crisis-relevant tasks, such as extracting locations and estimating damage levels from tweets to support damage assessment. However, recent changes in Twitter's data access policies have made it increasingly difficult to curate real-world tweet
datasets related to crises. Moreover, existing curated tweet
datasets are limited to past crisis events in specific contexts and are costly to annotate at scale. These limitations constrain the development and evaluation of AI systems used in crisis informatics. To address these limitations, we introduce an agentic workflow for generating crisis-related synthetic tweet
datasets. The workflow iteratively generates synthetic tweets conditioned on prespecified target characteristics, evaluates them using predefined compliance checks, and incorporates structured feedback to refine them in subsequent iterations. As a case study, we apply the workflow to generate synthetic tweet
datasets relevant to post-earthquake damage assessment. We show that the workflow can generate synthetic tweets that capture their target labels for location and damage level. We further demonstrate that the resulting synthetic tweet
datasets can be used to evaluate AI systems on damage assessment tasks like geolocalization and damage level prediction. Our results indicate that the workflow offers a flexible and scalable alternative to real-world tweet data curation, enabling the systematic generation of synthetic social media data across diverse crisis events, societal contexts, and crisis informatics applications.
Read the full abstract ▾
Machine Learning
Privacy-Preserving Federated Fraud Detection in Payment Transactions with NVIDIA FLARE
Holger R. Roth, Sarthak Tickoo, Mayank Kumar et al. (+18 more)
Fraud-related financial losses continue to rise, while regulatory,
privacy, and data-sovereignty constraints increasingly limit the feasibility of centralized fraud detection systems.
Federated Learning (FL) has emerged as a promising paradigm for enabling collaborative model training across institutions without sharing raw transaction data. Yet, its practical effectiveness under realistic, non-IID financial data distributions remains insufficiently validated. In this work, we present a multi-institution, industry-oriented proof-of-concept study evaluating
federated anomaly detection for payment transactions using the NVIDIA
FLARE framework. We simulate a realistic federation of heterogeneous financial institutions, each observing distinct fraud typologies and operating under strict data isolation. Using a deep neural network trained via
federated averaging (FedAvg), we demonstrate that
federated models achieve a mean F1-score of 0.903 - substantially outperforming locally trained models (0.643) and closely approaching centralized training performance (0.925), while preserving full data sovereignty. We further analyze convergence behavior, showing that strong performance is achieved within 10
federated communication rounds, highlighting the operational viability of FL in latency- and cost-sensitive financial environments. To support deployment in regulated settings, we evaluate model interpretability using Shapley-based feature attribution and confirm that
federated models rely on semantically coherent, domain-relevant decision signals. Finally, we incorporate sample-level differential
privacy via DP-SGD and demonstrate favorable
privacy-utility trade-offs...
Read the full abstract ▾
All authors Holger R. Roth, Sarthak Tickoo, Mayank Kumar, Isaac Yang, Andrew Liu, Amit Varshney, Sayani Kundu, Iustina Vintila, Peter Madsgaard, Juraj Milcak, Chester Chen, Yan Cheng, Andrew Feng, Jeff Savio, Vikram Singh, Craig Stancill, Gloria Wan, Evan Powell, Anwar Ul Haq, Sudhir Upadhyay, Jisoo Lee
Machine Learning · Cross-listed from stat.ML
Robust Sequential Tracking via Bounded Information Geometry and Non-Parametric Field Actions
Carlos C. Rodriguez
Standard sequential inference architectures are compromised by a normalizability crisis when confronted with extreme, structured outliers. By operating on unbounded parameter spaces, state-of-the-art
estimators lack the intrinsic geometry required to appropriately sever anomalies, resulting in unbounded covariance inflation and mean divergence. This paper resolves this structural failure by analyzing the abstraction sequence of inference at the meta-prior level (S_2). We demonstrate that extremizing the action over an infinite-dimensional space requires a non-parametric field anchored by a pre-prior, as a uniform volume element mathematically does not exist. By utilizing strictly invariant Delta (or \nu) Information Separations on the statistical
manifold, we physically truncate the infinite tails of the spatial distribution. When evaluated as a Radon-Nikodym derivative against the base measure, the active parameter space compresses into a strictly finite, normalizable probability droplet. Empirical
benchmarks across three domains–
LiDAR maneuvering target tracking, high-frequency cryptocurrency order flow, and
quantum state
tomography–demonstrate that this bounded information geometry analytically truncates outliers, ensuring robust estimation without relying on infinite-tailed distributional assumptions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
NCCL EP: Towards a Unified Expert Parallel Communication API for NCCL
Amos Goldman, Nimrod Boker, Maayan Sheraizin et al. (+15 more)
Mixture-of-Experts (MoE) architectures have become essential for scaling large
language models, driving the development of specialized device-initiated communication libraries such as DeepEP, Hybrid-EP, and others. These libraries demonstrate the performance benefits of GPU-initiated RDMA for MoE dispatch and combine operations. This paper presents NCCL EP (Expert Parallelism), a ground-up MoE communication library built entirely on NCCL's Device API. NCCL EP provides unified ncclEpDispatch and ncclEpCombine primitives with both C and Python interfaces, supporting Low-Latency (LL) mode for inference decoding and High-Throughput (HT) mode for training and inference prefill. LL targets small batch sizes (1-128
tokens) using direct all-to-all RDMA+NVLink mesh connectivity with double-buffered communication for overlapping dispatch and combine phases. HT targets large batches (4096+
tokens) using hierarchical communication that aggregates
tokens within NVLink domains before inter-node RDMA transmission. Both modes leverage Device API for both intra- and inter-node communications, taking advantage of its
topology awareness and optimized GPU-initiated implementation. We evaluate NCCL EP on an H100-based cluster across multi-node configurations, demonstrating competitive LL kernel performance and presenting end-to-end results with vLLM integration. By building MoE communication natively within NCCL, NCCL EP provides a supported path for expert parallelism on current and emerging NVIDIA platforms.
Read the full abstract ▾
All authors Amos Goldman, Nimrod Boker, Maayan Sheraizin, Nimrod Admoni, Artem Polyakov, Subhadeep Bhattacharya, Fan Yu, Kai Sun, Georgios Theodorakis, Hsin-Chun Yin, Peter-Jan Gootzen, Aamir Shafi, Assaf Ravid, Salvatore Di Girolamo, James Dinan, Xiaofan Li, Manjunath Gorentla Venkata, Gil Bloch
Machine Learning
A Causal Framework for Mitigating Data Shifts in Healthcare
Kurt Butler, Stephanie Riley, Damian Machlanski et al. (+13 more)
Developing predictive models that perform reliably across diverse patient populations and heterogeneous environments is a core aim of medical research. However, generalization is only possible if the learned model is robust to statistical differences between data used for training and data seen at the time and place of deployment. Domain generalization methods provide strategies to address data shifts, but each method comes with its own set of assumptions and trade-offs. To apply these methods in healthcare, we must understand how domain shifts arise, what assumptions we prefer to make, and what our design constraints are. This article proposes a causal framework for the design of predictive models to improve generalization. Causality provides a powerful
language to characterize and understand diverse domain shifts, regardless of data modality. This allows us to pinpoint why models fail to generalize, leading to more principled strategies to prepare for and adapt to shifts. We recommend general mitigation strategies, discussing trade-offs and highlighting existing work. Our causality-based perspective offers a critical foundation for developing robust, interpretable, and clinically relevant AI solutions in healthcare, paving the way for reliable real-world deployment.
Read the full abstract ▾
All authors Kurt Butler, Stephanie Riley, Damian Machlanski, Edward Moroshko, Panagiotis Dimitrakopoulos, Thomas Melistas, Akchunya Chanchal, Konstantinos Vilouras, Zhihua Liu, Steven McDonagh, Hana Chockler, Ben Glocker, Niccolo Tempini, Matthew Sperrin, Sotirios A Tsaftaris, Ricardo Silva
Machine Learning · Cross-listed from cs.AI
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings
Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair et al. (+6 more)
Large
language models are shifting from passive information providers to active
agents intended for complex workflows. However, their deployment as reliable AI workers in enterprise is stalled by
benchmarks that fail to capture the intricacies of professional environments, specifically, the need for long-horizon planning amidst persistent state changes and strict access protocols. In this work, we introduce EnterpriseOps-Gym, a
benchmark designed to evaluate agentic planning in realistic enterprise settings. Specifically, EnterpriseOps-Gym features a containerized sandbox with 164 database tables and 512 functional tools to mimic real-world search friction. Within this environment,
agents are evaluated on 1,150 expert-curated tasks across eight mission-critical verticals (including Customer Service, HR, and IT). Our evaluation of 14 frontier models reveals critical limitations in state-of-the-art models: the top-performing Claude Opus 4.5 achieves only 37.4% success. Further analysis shows that providing oracle human plans improves performance by 14-35 percentage points, pinpointing strategic
reasoning as the primary bottleneck. Additionally,
agents frequently fail to refuse infeasible tasks (best model achieves 53.9%), leading to unintended and potentially harmful side effects. Our findings underscore that current
agents are not yet ready for autonomous enterprise deployment. More broadly, EnterpriseOps-Gym provides a concrete testbed to advance the robustness of agentic planning in professional workflows.
Read the full abstract ▾
All authors Shiva Krishna Reddy Malay, Shravan Nayak, Jishnu Sethumadhavan Nair, Sagar Davasam, Aman Tiwari, Sathwik Tejaswi Madhusudhan, Sridhar Krishna Nemala, Srinivas Sunkara, Sai Rajeswar
Machine Learning
Assessing the Utility of Volumetric Motion Fields for Radar-based Precipitation Nowcasting with Physics-informed Deep Learning
Peter Pavlík, Anna Bou Ezzeddine and Viera Rozinajová
Estimating motion from spatiotemporal geoscientific data is a fundamental component of many environmental modeling and
forecasting tasks. In this work, we propose a physics-informed deep learning framework for estimating altitude-wise motion fields directly from volumetric radar reflectivity data. The model utilizes a fully differentiable semi-Lagrangian extrapolation operator to process three-dimensional inputs as independent horizontal slice sequences, enabling efficient inference of horizontal motion across multiple altitude levels. Using a multi-year radar
dataset from Central Europe, we evaluate the impact of altitude-wise motion estimation on extrapolation-based precipitation
forecasting and conduct a systematic
dataset-scale analysis of inter-altitude motion consistency. The results show that the estimated motion fields exhibit strong vertical coherence, with high correlation across altitude levels, which results in limited improvement over traditional two-dimensional approach in this setting. The proposed framework provides a general tool for efficiently analyzing motion structure in volumetric geospatial data. The findings indicate that, in regions dominated by vertically coherent precipitation systems, the added complexity of volumetric motion modeling may offer limited benefit, warranting careful consideration in the design of efficient spatiotemporal advection models.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
State-space models through the lens of ensemble control
Ye Feng and Jianfeng Lu
State-space models (SSMs) are effective architectures for sequential modeling, but a rigorous theoretical understanding of their training dynamics is still lacking. We formulate continuous-time SSM parameter-path optimization as an ensemble optimal control problem: each input sequence generates a corresponding state trajectory in the ensemble, while the trainable parameter path forms a common control shared by all trajectories. Within this formulation, model evaluation is represented by the forward state equation and backward sensitivity propagation by the corresponding adjoint equation. We show that the
Hamiltonian gradient with respect to the control variable represents the negative first-variation density of the reduced ensemble objective. Using this representation, we analyze a Bregman mirror-descent scheme for the continuous-time ensemble objective; in Euclidean geometry this reduces to functional projected gradient descent. State-adjoint and
Hamiltonian-gradient stability yield two-sided relative
curvature of the reduced objective and relative convexity under sufficient regularization. We further show that in the relatively convex regime the optimal-control problem admits a minimizer, which is unique under relative strong convexity. For SSMs, the explicit stability-generated defect $\kappa_{\mathrm{stab}}^{\mathrm{SSM}}$ gives an $O(1/k)$ objective rate at $\tau=\kappa_{\mathrm{stab}}^{\mathrm{SSM}}$ and
geometric convergence to the unique minimizer for $\tau>\kappa_{\mathrm{stab}}^{\mathrm{SSM}}$, under the stated stepsize condition.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
State Algebra for Probabilistic Logic
Dmitry Lesnik and Tobias Schäfer
This paper presents a Probabilistic State
Algebra as an extension of deterministic propositional logic, providing a computational framework for constructing Markov Random Fields (MRFs) through pure linear
algebra. By mapping logical states to real-valued coordinates interpreted as energy potentials, we define an energy-based model where global probability distributions emerge from coordinate-wise Hadamard products. This approach bypasses the traditional reliance on graph-traversal
algorithms and compiled
circuits, utilising $t$-objects and wildcards to embed logical reduction natively within
matrix operations. We demonstrate that this
algebra constructs formal Gibbs distributions, offering a rigorous mathematical link between symbolic constraints and statistical inference. A central application of this framework is the development of Probabilistic Rule Models (PRMs), which are uniquely capable of incorporating both probabilistic associations and deterministic logical constraints simultaneously. These models are designed to be inherently interpretable, supporting a human-in-the-loop approach to decisioning in high-stakes environments such as healthcare and finance. By representing decision logic as a modular summation of rules within a vector space, the framework ensures that complex probabilistic systems remain auditable and maintainable without compromising the rigour of the underlying configuration space.
Read the full abstract ▾
Machine Learning
Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
Zakia Zaman, Praveen Gauravaram, Mahbub Hassan et al. (+2 more)
The rapid proliferation of the Internet of Things has intensified demand for robust
privacy-preserving machine learning mechanisms to safeguard sensitive data generated by large-scale, heterogeneous, and resource-constrained devices. Unlike centralized environments, IoT ecosystems are inherently decentralized, bandwidth-limited, and latency-sensitive, exposing
privacy risks across sensing, communication, and distributed training pipelines. These characteristics render conventional anonymization and centralized protection strategies insufficient for practical deployments. This survey presents a comprehensive IoT-centric, cross-paradigm analysis of
privacy-preserving machine learning. We introduce a structured taxonomy spanning perturbation-based mechanisms such as differential
privacy, distributed paradigms such as
federated learning, cryptographic approaches including homomorphic encryption and secure multiparty computation, and generative synthesis techniques based on generative
adversarial networks. For each paradigm, we examine formal
privacy guarantees, computational and communication complexity, scalability under heterogeneous device participation, and resilience against threats including membership inference, model inversion, gradient leakage, and
adversarial manipulation. We further analyze deployment constraints in wireless IoT environments, highlighting trade-offs between
privacy, communication overhead, model convergence, and system efficiency within next-generation mobile architectures. We also consolidate evaluation methodologies, summarize representative
datasets and open-source frameworks, and identify open challenges including hybrid
privacy integration, energy-aware learning,
privacy-preserving large
language models, and
quantum-resilient machine learning.
Read the full abstract ▾
All authors Zakia Zaman, Praveen Gauravaram, Mahbub Hassan, Sanjay Jha, Wen Hu
Machine Learning · Cross-listed from stat.ML
En-Ya Kuo and Sebastien Motsch
Imbalanced
datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare fraudulent transactions. Synthetic data generation is therefore commonly used to mitigate this problem. In this work, we propose the Clustered
Embedding Diffusion-
Transformer (EmDT), a
diffusion model designed to generate fraudulent samples. Our key innovation is to leverage UMAP clustering to identify distinct fraudulent patterns, and train a
Transformer denoising network with sinusoidal positional
embeddings to capture feature relationships throughout the
diffusion process. Once the synthetic data has been generated, we employ a standard decision-tree-based classifier (e.g., XGBoost) for classification, as this type of model remains better suited to tabular
datasets. Experiments on a credit card fraud detection
dataset demonstrate that EmDT significantly improves downstream classification performance compared to existing oversampling and generative methods, while maintaining comparable
privacy protection and preserving feature correlations present in the original data.
Read the full abstract ▾
Machine Learning
MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
Andrii Shchur and Inna Skarga-Bandurova
Weather
forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly for frequent regional updates, as high-resolution nests require intensive boundary coupling. We introduce Multi-Resolution Graph Neural
Forecasting (MR-GNF), a lightweight, physics-aware model that performs short-term regional forecasts directly on an ellipsoidal, multi-scale graph of the Earth. The framework couples a 0.25{\deg} region of interest with a 0.5{\deg} context belt and 1.0{\deg} outer domain, enabling continuous cross-scale message passing without explicit nested boundaries. Its axial graph-
attention network alternates vertical self-
attention across pressure levels with horizontal graph
attention across surface nodes, capturing implicit 3-D structure in just 1.6 M parameters. Trained on 40 years of ERA5 reanalysis (1980-2024), MR-GNF delivers stable +6 h to +24 h forecasts for near-surface temperature, wind, and precipitation over the UK-Ireland sector. Despite a total compute cost below 80 GPU-hours on a single RTX 6000 Ada, the model matches or exceeds heavier regional AI systems while preserving physical consistency across scales. These results demonstrate that graph-based neural operators can achieve trustworthy, high-resolution weather prediction at a fraction of NWP cost, opening a practical path toward AI-driven early-warning and renewable-energy
forecasting systems. Project page and code: https://github.com/AndriiShchur/MR-GNF
Read the full abstract ▾
Machine Learning
Scalable Classification of Course Information Sheets Using Large Language Models: A Reusable Institutional Method for Academic Quality Assurance
Brecht F. Verbeken, Joke Van den Broeck, Inge De Cleyn et al. (+4 more)
Purpose: Higher education institutions face increasing pressure to audit course designs for generative AI (GenAI) integration. This paper presents an end-to-end method for using large
language models (LLMs) to scan course information sheets at scale, identify where assessments may be vulnerable to student use of GenAI tools, validate system performance through iterative refinement, and operationalise results through direct stakeholder communication and effort. Method: We developed a four-phase pipeline: (0) manual pilot sampling, (1) iterative
prompt engineering with multi-model comparison, (2) full production scan of 4,684 Bachelor and Master course information sheets (Academic Year 2024-2025) from the Vrije Universiteit Brussel (VUB) with automated report generation and email distribution to teaching teams (91.4% address-matched) using a three-tier risk taxonomy (Clear risk, Potential risk, Low risk), and (3) longitudinal re-scan of 4,675 sheets after the next catalogue release. Results: Five iterations of
prompt refinement achieved 87% agreement with expert labels. GPT-4o was selected for production based on superior handling of ambiguous cases involving internships and practical components. The Year 1 scan classified 60.3% of courses as Clear risk, 15.2% as Potential risk, and 24.5% as Low risk. Year 2 comparison revealed substantial shifts in risk distributions, with improvements most pronounced in practice-oriented programmes. Implications: The method enables institutions to rapidly transform heterogeneous catalogue data into structured and actionable intelligence. The approach is transferable to other audit domains (sustainability, accessibility, pedagogical
alignment) and provides a template for responsible LLM deployment in higher education governance.
Read the full abstract ▾
All authors Brecht F. Verbeken, Joke Van den Broeck, Inge De Cleyn, Steven Van Luchene, Nadine Engels, Andres Algaba, Vincent Ginis
Machine Learning · Cross-listed from eess.SP
Task-Oriented Wireless Transmission of 3D Point Clouds: Geometric Versus Semantic Robustness
Vukan Ninkovic, Tamara Sobot, Vladimir Vincan et al. (+3 more)
Wireless transmission of high-dimensional 3D point clouds (PCs) is increasingly required in industrial collaborative robotics systems. Conventional compression methods prioritize
geometric fidelity, although many practical applications ultimately depend on reliable task-level inference rather than exact coordinate reconstruction. In this paper, we propose an end-to-end semantic communication framework for wireless 3D PC transmission and conduct a systematic study of the relationship between
geometric reconstruction fidelity and semantic robustness under channel impairments. The proposed architecture jointly supports
geometric recovery and object classification from a shared transmitted representation, enabling direct comparison between coordinate-level and task-level sensitivity to noise. Experimental evaluation on a real industrial
dataset reveals a pronounced asymmetry: semantic inference remains stable across a broad signal-to-noise ratio (SNR) range even when
geometric reconstruction quality degrades significantly. These results demonstrate that reliable task execution does not require high-fidelity
geometric recovery and provide design insights for task-oriented wireless perception systems in bandwidth- and power-constrained industrial environments.
Read the full abstract ▾
All authors Vukan Ninkovic, Tamara Sobot, Vladimir Vincan, Gorana Gojic, Dragisa Miskovic, Dejan Vukobratovic