Authors: Mujie Liu, Chenze Wang, Liping Chen, Nguyen Linh Dan Le, Niharika Tewari, Ting Dang, Jiangang Ma, Feng Xia
Abstract: The limited availability of labeled brain network data makes it challenging to achieve accurate and interpretable psychiatric diagnoses. While self-supervised learning (SSL) offers a promising solution, existing methods often rely on augmentation strategies that can disrupt crucial structural semantics in brain graphs. To address this, we propose SAM-BG, a two-stage framework for learning brain graph representations with structural semantic preservation. In the pre-training stage, an edge masker is trained on a small labeled subset to capture key structural semantics. In the SSL stage, the extracted structural priors guide a structure-aware augmentation process, enabling the model to learn more semantically meaningful and robust representations. Experiments on two real-world psychiatric datasets demonstrate that SAM-BG outperforms state-of-the-art methods, particularly in small-labeled data settings, and uncovers clinically relevant connectivity patterns that enhance interpretability. Our code is available at https://github.com/mjliu99/SAM-BG.
Authors: Leen Daher, Zhaobo Wang, Malcolm Mielle
Abstract: Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference, limiting deployment in resource-constrained environments where full sensor suites are not economically and technically usable. To address this, we propose Decoupled Cross-Attention Transfer (D-CAT), a framework that aligns modality-specific representations without requiring joint sensor modality during inference. Our approach combines a self-attention module for feature extraction with a novel cross-attention alignment loss, which enforces the alignment of sensors' feature spaces without requiring the coupling of the classification pipelines of both modalities. We evaluate D-CAT on three multi-modal human activity datasets (IMU, video, and audio) under both in-distribution and out-of-distribution scenarios, comparing against uni-modal models. Results show that in in-distribution scenarios, transferring from high-performing modalities (e.g., video to IMU) yields up to 10% F1-score gains over uni-modal training. In out-of-distribution scenarios, even weaker source modalities (e.g., IMU to video) improve target performance, as long as the target model isn't overfitted on the training data. By enabling single-sensor inference with cross-modal knowledge, D-CAT reduces hardware redundancy for perception systems while maintaining accuracy, which is critical for cost-sensitive or adaptive deployments (e.g., assistive robots in homes with variable sensor availability). Code is available at https://github.com/Schindler-EPFL-Lab/D-CAT.
Authors: Junqiao Wang, Zhaoyang Guan, Guanyu Liu, Tianze Xia, Xianzhi Li, Shuo Yin, Xinyuan Song, Chuhan Cheng, Tianyu Shi, Alex Lee
Abstract: Predicting cryptocurrency returns is notoriously difficult: price movements are driven by a fast-shifting blend of on-chain activity, news flow, and social sentiment, while labeled training data are scarce and expensive. In this paper, we present Meta-RL-Crypto, a unified transformer-based architecture that unifies meta-learning and reinforcement learning (RL) to create a fully self-improving trading agent. Starting from a vanilla instruction-tuned LLM, the agent iteratively alternates between three roles-actor, judge, and meta-judge-in a closed-loop architecture. This learning process requires no additional human supervision. It can leverage multimodal market inputs and internal preference feedback. The agent in the system continuously refines both the trading policy and evaluation criteria. Experiments across diverse market regimes demonstrate that Meta-RL-Crypto shows good performance on the technical indicators of the real market and outperforming other LLM-based baselines.
Authors: Yiqun Shen, Song Yuan, Zhengze Zhang, Xiaoliang Wang, Daxin Jiang, Nguyen Cam-Tu
Abstract: KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To address this limitation, we introduce a unified framework for cache compression by minimizing information loss in Transformer residual streams. Building on it, we analyze the layer attention output loss and derive a new metric to compare cache entries across heads, enabling layer-wise compression with dynamic head budgets. Additionally, by contrasting cross-layer information, we also achieve dynamic layer budgets. LAVa is the first unified strategy for cache eviction and dynamic budget allocation that, unlike prior methods, does not rely on training or the combination of multiple strategies. Experiments with benchmarks (LongBench, Needle-In-A-Haystack, Ruler, and InfiniteBench) demonstrate its superiority. Moreover, our experiments reveal a new insight: dynamic layer budgets are crucial for generation tasks (e.g., code completion), while dynamic head budgets play a key role in extraction tasks (e.g., extractive QA). As a fully dynamic compression method, LAVa consistently maintains top performance across task types. Our code is available at https://github.com/MGDDestiny/Lava.
Authors: Sanjay Basu, Sadiq Y. Patel, Parth Sheth, Bhairavi Muralidharan, Namrata Elamaran, Aakriti Kinra, Rajaie Batniji
Abstract: Population health management programs for Medicaid populations coordinate longitudinal outreach and services (e.g., benefits navigation, behavioral health, social needs support, and clinical scheduling) and must be safe, fair, and auditable. We present a Hybrid Adaptive Conformal Offline Reinforcement Learning (HACO) framework that separates risk calibration from preference optimization to generate conservative action recommendations at scale. In our setting, each step involves choosing among common coordination actions (e.g., which member to contact, by which modality, and whether to route to a specialized service) while controlling the near-term risk of adverse utilization events (e.g., unplanned emergency department visits or hospitalizations). Using a de-identified operational dataset from Waymark comprising 2.77 million sequential decisions across 168,126 patients, HACO (i) trains a lightweight risk model for adverse events, (ii) derives a conformal threshold to mask unsafe actions at a target risk level, and (iii) learns a preference policy on the resulting safe subset. We evaluate policies with a version-agnostic fitted Q evaluation (FQE) on stratified subsets and audit subgroup performance across age, sex, and race. HACO achieves strong risk discrimination (AUC ~0.81) with a calibrated threshold ( {\tau} ~0.038 at {\alpha} = 0.10), while maintaining high safe coverage. Subgroup analyses reveal systematic differences in estimated value across demographics, underscoring the importance of fairness auditing. Our results show that conformal risk gating integrates cleanly with offline RL to deliver conservative, auditable decision support for population health management teams.
Authors: Roshini Pulishetty, Mani Kishan Ghantasala, Keerthy Kaushik Dasoju, Niti Mangwani, Vishal Garimella, Aditya Mate, Somya Chatterjee, Yue Kang, Ehi Nosakhare, Sadid Hasan, Soundar Srinivasan
Abstract: The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing framework that leverages a single-head cross-attention mechanism to jointly model query and model embeddings, enabling dynamic selection of the optimal LLM for each input query. Our approach is evaluated on RouterBench, a large-scale, publicly available benchmark encompassing diverse LLM pools and domains. By explicitly capturing fine-grained query-model interactions, our router predicts both response quality and generation cost, achieving up to 6.6% improvement in Average Improvement in Quality (AIQ) and 2.9% in maximum performance over existing routers. To robustly balance performance and cost, we propose an exponential reward function that enhances stability across user preferences. The resulting architecture is lightweight, generalizes effectively across domains, and demonstrates improved efficiency compared to prior methods, establishing a new standard for cost-aware LLM routing.
Authors: Vincent Herfeld, Baudouin Denis de Senneville, Arthur Leclaire, Nicolas Papadakis
Abstract: In this paper we analyze the Gradient-Step Denoiser and its usage in Plug-and-Play algorithms. The Plug-and-Play paradigm of optimization algorithms uses off the shelf denoisers to replace a proximity operator or a gradient descent operator of an image prior. Usually this image prior is implicit and cannot be expressed, but the Gradient-Step Denoiser is trained to be exactly the gradient descent operator or the proximity operator of an explicit functional while preserving state-of-the-art denoising capabilities.
Authors: Mansi Sharma, Alexandre Duchevet, Florian Daiber, Jean-Paul Imbert, Maurice Rekrut
Abstract: Unexpected events can impair attention and delay decision-making, posing serious safety risks in high-risk environments such as aviation. In particular, reactions like startle and surprise can impact pilot performance in different ways, yet are often hard to distinguish in practice. Existing research has largely studied these reactions separately, with limited focus on their combined effects or how to differentiate them using physiological data. In this work, we address this gap by distinguishing between startle and surprise events based on physiological signals using machine learning and multi-modal fusion strategies. Our results demonstrate that these events can be reliably predicted, achieving a highest mean accuracy of 85.7% with SVM and Late Fusion. To further validate the robustness of our model, we extended the evaluation to include a baseline condition, successfully differentiating between Startle, Surprise, and Baseline states with a highest mean accuracy of 74.9% with XGBoost and Late Fusion.
Authors: Reza Asad, Reza Babanezhad, Sharan Vaswani
Abstract: Value-based approaches such as DQN are the default methods for off-policy reinforcement learning with discrete-action environments such as Atari. Common policy-based methods are either on-policy and do not effectively learn from off-policy data (e.g. PPO), or have poor empirical performance in the discrete-action setting (e.g. SAC). Consequently, starting from discrete SAC (DSAC), we revisit the design of actor-critic methods in this setting. First, we determine that the coupling between the actor and critic entropy is the primary reason behind the poor performance of DSAC. We demonstrate that by merely decoupling these components, DSAC can have comparable performance as DQN. Motivated by this insight, we introduce a flexible off-policy actor-critic framework that subsumes DSAC as a special case. Our framework allows using an m-step Bellman operator for the critic update, and enables combining standard policy optimization methods with entropy regularization to instantiate the resulting actor objective. Theoretically, we prove that the proposed methods can guarantee convergence to the optimal regularized value function in the tabular setting. Empirically, we demonstrate that these methods can approach the performance of DQN on standard Atari games, and do so even without entropy regularization or explicit exploration.
Authors: Jiajun Shen, Yufei Jin, Yi He, Xingquan Zhu
Abstract: This paper presents HGEN that pioneers ensemble learning for heterogeneous graphs. We argue that the heterogeneity in node types, nodal features, and local neighborhood topology poses significant challenges for ensemble learning, particularly in accommodating diverse graph learners. Our HGEN framework ensembles multiple learners through a meta-path and transformation-based optimization pipeline to uplift classification accuracy. Specifically, HGEN uses meta-path combined with random dropping to create Allele Graph Neural Networks (GNNs), whereby the base graph learners are trained and aligned for later ensembling. To ensure effective ensemble learning, HGEN presents two key components: 1) a residual-attention mechanism to calibrate allele GNNs of different meta-paths, thereby enforcing node embeddings to focus on more informative graphs to improve base learner accuracy, and 2) a correlation-regularization term to enlarge the disparity among embedding matrices generated from different meta-paths, thereby enriching base learner diversity. We analyze the convergence of HGEN and attest its higher regularization magnitude over simple voting. Experiments on five heterogeneous networks validate that HGEN consistently outperforms its state-of-the-art competitors by substantial margin.
Authors: Jenny Y. Huang, Mehul Damani, Yousef El-Kurdi, Ramon Astudillo, Wei Sun
Abstract: Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute typically considers only parallel generation methods such as best-of-N, overlooking incremental decoding methods like beam search, and has largely ignored latency, focusing only on token usage. We formulate inference-time scaling as a problem of dynamic compute allocation and method selection, where the system must decide which strategy to apply and how much compute to allocate on a per-query basis. Our framework explicitly incorporates both token cost and wall-clock latency, the latter being critical for user experience and particularly for agentic workflows where models must issue multiple queries efficiently. Experiments on reasoning benchmarks show that our approach consistently outperforms static strategies, achieving favorable accuracy-cost trade-offs while remaining practical for deployment.
Authors: Christopher Eldred, Fran\c{c}ois Gay-Balmaz, Vakhtang Putkaradze
Abstract: Much attention has recently been devoted to data-based computing of evolution of physical systems. In such approaches, information about data points from past trajectories in phase space is used to reconstruct the equations of motion and to predict future solutions that have not been observed before. However, in many cases, the available data does not correspond to the variables that define the system's phase space. We focus our attention on the important example of dissipative dynamical systems. In that case, the phase space consists of coordinates, momenta and entropies; however, the momenta and entropies cannot, in general, be observed directly. To address this difficulty, we develop an efficient data-based computing framework based exclusively on observable variables, by constructing a novel approach based on the \emph{thermodynamic Lagrangian}, and constructing neural networks that respect the thermodynamics and guarantees the non-decreasing entropy evolution. We show that our network can provide an efficient description of phase space evolution based on a limited number of data points and a relatively small number of parameters in the system.
Authors: Jiahao Chen, Zhiyuan Huang, Yurou Liu, Bing Su
Abstract: Long-tailed learning has garnered increasing attention due to its wide applicability in real-world scenarios. Among existing approaches, Long-Tailed Semi-Supervised Learning (LTSSL) has emerged as an effective solution by incorporating a large amount of unlabeled data into the imbalanced labeled dataset. However, most prior LTSSL methods are designed to train models from scratch, which often leads to issues such as overconfidence and low-quality pseudo-labels. To address these challenges, we extend LTSSL into the foundation model fine-tuning paradigm and propose a novel framework: LoFT (Long-tailed semi-supervised learning via parameter-efficient Fine-Tuning). We demonstrate that fine-tuned foundation models can generate more reliable pseudolabels, thereby benefiting imbalanced learning. Furthermore, we explore a more practical setting by investigating semi-supervised learning under open-world conditions, where the unlabeled data may include out-of-distribution (OOD) samples. To handle this problem, we propose LoFT-OW (LoFT under Open-World scenarios) to improve the discriminative ability. Experimental results on multiple benchmarks demonstrate that our method achieves superior performance compared to previous approaches, even when utilizing only 1\% of the unlabeled data compared with previous works.
Authors: Shintaro Nakamura, Yuko Kuroki, Wei Chen
Abstract: In the combinatorial semi-bandit (CSB) problem, a player selects an action from a combinatorial action set and observes feedback from the base arms included in the action. While CSB is widely applicable to combinatorial optimization problems, its restriction to binary decision spaces excludes important cases involving non-negative integer flows or allocations, such as the optimal transport and knapsack problems.To overcome this limitation, we propose the multi-play combinatorial semi-bandit (MP-CSB), where a player can select a non-negative integer action and observe multiple feedbacks from a single arm in each round. We propose two algorithms for the MP-CSB. One is a Thompson-sampling-based algorithm that is computationally feasible even when the action space is exponentially large with respect to the number of arms, and attains $O(\log T)$ distribution-dependent regret in the stochastic regime, where $T$ is the time horizon. The other is a best-of-both-worlds algorithm, which achieves $O(\log T)$ variance-dependent regret in the stochastic regime and the worst-case $\tilde{\mathcal{O}}\left( \sqrt{T} \right)$ regret in the adversarial regime. Moreover, its regret in adversarial one is data-dependent, adapting to the cumulative loss of the optimal action, the total quadratic variation, and the path-length of the loss sequence. Finally, we numerically show that the proposed algorithms outperform existing methods in the CSB literature.
Authors: Saarth Gaonkar, Xiang Zheng, Haocheng Xi, Rishabh Tiwari, Kurt Keutzer, Dmitriy Morozov, Michael W. Mahoney, Amir Gholami
Abstract: Recent work in scientific machine learning aims to tackle scientific tasks directly by predicting target values with neural networks (e.g., physics-informed neural networks, neural ODEs, neural operators, etc.), but attaining high accuracy and robustness has been challenging. We explore an alternative view: use LLMs to write code that leverages decades of numerical algorithms. This shifts the burden from learning a solution function to making domain-aware numerical choices. We ask whether LLMs can act as SciML agents that, given a natural-language ODE description, generate runnable code that is scientifically appropriate, selecting suitable solvers (stiff vs. non-stiff), and enforcing stability checks. There is currently no benchmark to measure this kind of capability for scientific computing tasks. As such, we first introduce two new datasets: a diagnostic dataset of adversarial "misleading" problems; and a large-scale benchmark of 1,000 diverse ODE tasks. The diagnostic set contains problems whose superficial appearance suggests stiffness, and that require algebraic simplification to demonstrate non-stiffness; and the large-scale benchmark spans stiff and non-stiff ODE regimes. We evaluate open- and closed-source LLM models along two axes: (i) unguided versus guided prompting with domain-specific knowledge; and (ii) off-the-shelf versus fine-tuned variants. Our evaluation measures both executability and numerical validity against reference solutions. We find that with sufficient context and guided prompts, newer instruction-following models achieve high accuracy on both criteria. In many cases, recent open-source systems perform strongly without fine-tuning, while older or smaller models still benefit from fine-tuning. Overall, our preliminary results indicate that careful prompting and fine-tuning can yield a specialized LLM agent capable of reliably solving simple ODE problems.
Authors: Yifei Wang, Wenbin Wang, Yong Luo
Abstract: Though Multimodal Intent Recognition (MIR) proves effective by utilizing rich information from multiple sources (e.g., language, video, and audio), the potential for intent-irrelevant and conflicting information across modalities may hinder performance from being further improved. Most current models attempt to fuse modalities by applying mechanisms like multi-head attention to unimodal feature sequences and then adding the result back to the original representation. This process risks corrupting the primary linguistic features with noisy or irrelevant non-verbal signals, as it often fails to capture the fine-grained, token-level influence where non-verbal cues should modulate, not just augment, textual meaning. To address this, we introduce DyKen-Hyena, which reframes the problem from feature fusion to processing modulation. Our model translates audio-visual cues into dynamic, per-token convolutional kernels that directly modulate textual feature extraction. This fine-grained approach achieves state-of-the-art results on the MIntRec and MIntRec2.0 benchmarks. Notably, it yields a +10.46% F1-score improvement in out-of-scope detection, validating that our method creates a fundamentally more robust intent representation.
Authors: Omar Erak, Omar Alhussein, Hatem Abou-Zeid, Mehdi Bennis, Sami Muhaidat
Abstract: Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive token merging, a novel mechanism that compresses transformer representations at runtime by selectively merging semantically redundant tokens under per-layer similarity thresholds. Unlike prior fixed-ratio reduction, our approach couples merging directly to input redundancy, enabling data-dependent adaptation that balances efficiency and task relevance without retraining. We cast the discovery of merging strategies as a multi-objective optimization problem and leverage Bayesian optimization to obtain Pareto-optimal trade-offs between accuracy, inference cost, and communication cost. On ImageNet classification, we match the accuracy of the unmodified transformer with 30\% fewer floating-point operations per second and under 20\% of the original communication cost, while for visual question answering our method achieves performance competitive with the full LLaVA model at less than one-third of the compute and one-tenth of the bandwidth. Finally, we show that our adaptive merging is robust across varying channel conditions and provides inherent privacy benefits, substantially degrading the efficacy of model inversion attacks. Our framework provides a practical and versatile solution for deploying powerful transformer models in resource-limited edge intelligence scenarios.
Authors: Mingxuan Jiang, Yongxin Wang, Ziyue Dai, Yicun Liu, Hongyi Nie, Sen Liu, Hongfeng Chai
Abstract: Synthetic tabular data generation is increasingly essential in data management, supporting downstream applications when real-world and high-quality tabular data is insufficient. Existing tabular generation approaches, such as generative adversarial networks (GANs), diffusion models, and fine-tuned Large Language Models (LLMs), typically require sufficient reference data, limiting their effectiveness in domain-specific databases with scarce records. While prompt-based LLMs offer flexibility without parameter tuning, they often fail to capture dataset-specific feature-label dependencies and generate redundant data, leading to degradation in downstream task performance. To overcome these issues, we propose ReFine, a framework that (i) derives symbolic "if-then" rules from interpretable models and embeds them into prompts to explicitly guide generation toward domain-specific feature distribution, and (ii) applies a dual-granularity filtering strategy that suppresses over-sampling patterns and selectively refines rare but informative samples to reduce distributional imbalance. Extensive experiments on various regression and classification benchmarks demonstrate that ReFine consistently outperforms state-of-the-art methods, achieving up to 0.44 absolute improvement in R-squared for regression and 10.0 percent relative improvement in F1 score for classification tasks.
Authors: Amandip Sangha
Abstract: This paper presents a machine learning-based approach to estimate the energy consumption of virtual servers without access to physical power measurement interfaces. Using resource utilization metrics collected from guest virtual machines, we train a Gradient Boosting Regressor to predict energy consumption measured via RAPL on the host. We demonstrate, for the first time, guest-only resource-based energy estimation without privileged host access with experiments across diverse workloads, achieving high predictive accuracy and variance explained ($0.90 \leq R^2 \leq 0.97$), indicating the feasibility of guest-side energy estimation. This approach can enable energy-aware scheduling, cost optimization and physical host independent energy estimates in virtualized environments. Our approach addresses a critical gap in virtualized environments (e.g. cloud) where direct energy measurement is infeasible.
Authors: Tilen Cadez, Kyoung-Min Kim
Abstract: Neural scaling laws--power-law relationships between generalization errors and characteristics of deep learning models--are vital tools for developing reliable models while managing limited resources. Although the success of large language models highlights the importance of these laws, their application to deep regression models remains largely unexplored. Here, we empirically investigate neural scaling laws in deep regression using a parameter estimation model for twisted van der Waals magnets. We observe power-law relationships between the loss and both training dataset size and model capacity across a wide range of values, employing various architectures--including fully connected networks, residual networks, and vision transformers. Furthermore, the scaling exponents governing these relationships range from 1 to 2, with specific values depending on the regressed parameters and model details. The consistent scaling behaviors and their large scaling exponents suggest that the performance of deep regression models can improve substantially with increasing data size.
Authors: Antoine Orioua, Philipp Krah, Julian Koellermeier
Abstract: This paper introduces the Intrinsic Dimension Estimating Autoencoder (IDEA), which identifies the underlying intrinsic dimension of a wide range of datasets whose samples lie on either linear or nonlinear manifolds. Beyond estimating the intrinsic dimension, IDEA is also able to reconstruct the original dataset after projecting it onto the corresponding latent space, which is structured using re-weighted double CancelOut layers. Our key contribution is the introduction of the projected reconstruction loss term, guiding the training of the model by continuously assessing the reconstruction quality under the removal of an additional latent dimension. We first assess the performance of IDEA on a series of theoretical benchmarks to validate its robustness. These experiments allow us to test its reconstruction ability and compare its performance with state-of-the-art intrinsic dimension estimators. The benchmarks show good accuracy and high versatility of our approach. Subsequently, we apply our model to data generated from the numerical solution of a vertically resolved one-dimensional free-surface flow, following a pointwise discretization of the vertical velocity profile in the horizontal direction, vertical direction, and time. IDEA succeeds in estimating the dataset's intrinsic dimension and then reconstructs the original solution by working directly within the projection space identified by the network.
Authors: Strahinja Nikolic, Ilker Oguz, Demetri Psaltis
Abstract: Understanding the internal organization of neural networks remains a fundamental challenge in deep learning interpretability. We address this challenge by exploring a novel Sparse Mixture of Experts Variational Autoencoder (SMoE-VAE) architecture. We test our model on the QuickDraw dataset, comparing unsupervised expert routing against a supervised baseline guided by ground-truth labels. Surprisingly, we find that unsupervised routing consistently achieves superior reconstruction performance. The experts learn to identify meaningful sub-categorical structures that often transcend human-defined class boundaries. Through t-SNE visualizations and reconstruction analysis, we investigate how MoE models uncover fundamental data structures that are more aligned with the model's objective than predefined labels. Furthermore, our study on the impact of dataset size provides insights into the trade-offs between data quantity and expert specialization, offering guidance for designing efficient MoE architectures.
Authors: Boya Ma, Abram Magner, Maxwell McNeil, Petko Bogdanov
Abstract: Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial dictionaries. Data-agnostic analytical dictionaries, such as the discrete Fourier transform, wavelets and graph Fourier, have seen wide adoption due to efficient implementations and good practical performance. On the other hand, dictionaries learned from data offer sparser and more accurate solutions but require learning of both the dictionaries and the coding coefficients. This becomes especially challenging for multi-dictionary scenarios since encoding coefficients correspond to all atom combinations from the dictionaries. To address this challenge, we propose a low-rank coding model for 2-dictionary scenarios and study its data complexity. Namely, we establish a bound on the number of samples needed to learn dictionaries that generalize to unseen samples from the same distribution. We propose a convex relaxation solution, called AODL, whose exact solution we show also solves the original problem. We then solve this relaxation via alternating optimization between the sparse coding matrices and the learned dictionaries, which we prove to be convergent. We demonstrate its quality for data reconstruction and missing value imputation in both synthetic and real-world datasets. For a fixed reconstruction quality, AODL learns up to 90\% sparser solutions compared to non-low-rank and analytical (fixed) dictionary baselines. In addition, the learned dictionaries reveal interpretable insights into patterns present within the samples used for training.
Authors: Sahil Rajesh Dhayalkar
Abstract: We present a formal and constructive theory showing that probabilistic finite automata (PFAs) can be exactly simulated using symbolic feedforward neural networks. Our architecture represents state distributions as vectors and transitions as stochastic matrices, enabling probabilistic state propagation via matrix-vector products. This yields a parallel, interpretable, and differentiable simulation of PFA dynamics using soft updates-without recurrence. We formally characterize probabilistic subset construction, $\varepsilon$-closure, and exact simulation via layered symbolic computation, and prove equivalence between PFAs and specific classes of neural networks. We further show that these symbolic simulators are not only expressive but learnable: trained with standard gradient descent-based optimization on labeled sequence data, they recover the exact behavior of ground-truth PFAs. This learnability, formalized in Proposition 5.1, is the crux of this work. Our results unify probabilistic automata theory with neural architectures under a rigorous algebraic framework, bridging the gap between symbolic computation and deep learning.
Authors: Mohammad Hasan Narimani, Mostafa Tavassolipour
Abstract: Federated learning (FL) offers an innovative paradigm for collaborative model training across decentralized devices, such as smartphones, balancing enhanced predictive performance with the protection of user privacy in sensitive areas like Internet of Things (IoT) and medical data analysis. Despite its advantages, FL encounters significant challenges related to user privacy protection against potential attacks and the management of communication costs. This paper introduces a novel federated learning algorithm called FedRP, which integrates random projection techniques with the Alternating Direction Method of Multipliers (ADMM) optimization framework. This approach enhances privacy by employing random projection to reduce the dimensionality of model parameters prior to their transmission to a central server, reducing the communication cost. The proposed algorithm offers a strong $(\epsilon, \delta)$-differential privacy guarantee, demonstrating resilience against data reconstruction attacks. Experimental results reveal that FedRP not only maintains high model accuracy but also outperforms existing methods, including conventional differential privacy approaches and FedADMM, in terms of both privacy preservation and communication efficiency.
Authors: Madhushan Ramalingam
Abstract: Predictive models are being increasingly used across a wide range of domains, including safety-critical applications such as medical diagnosis and criminal justice. Reliable uncertainty estimation is a crucial task in such settings. Tabular Prior-data Fitted Network (TabPFN) is a recently proposed machine learning foundation model for tabular dataset, which uses a generative transformer architecture. Variational Bayesian Last Layers (VBLL) is a state-of-the-art lightweight variational formulation that effectively improves uncertainty estimation with minimal computational overhead. In this work we aim to evaluate the performance of VBLL integrated with the recently proposed TabPFN in uncertainty calibration. Our experiments, conducted on three benchmark medical tabular datasets, compare the performance of the original TabPFN and the VBLL-integrated version. Contrary to expectations, we observed that original TabPFN consistently outperforms VBLL integrated TabPFN in uncertainty calibration across all datasets.
Authors: Marco Andrea B\"uhler, Gonzalo Guill\'en-Gos\'albez
Abstract: We introduce a novel symbolic regression framework, namely KAN-SR, built on Kolmogorov Arnold Networks (KANs) which follows a divide-and-conquer approach. Symbolic regression searches for mathematical equations that best fit a given dataset and is commonly solved with genetic programming approaches. We show that by using deep learning techniques, more specific KANs, and combining them with simplification strategies such as translational symmetries and separabilities, we are able to recover ground-truth equations of the Feynman Symbolic Regression for Scientific Discovery (SRSD) dataset. Additionally, we show that by combining the proposed framework with neural controlled differential equations, we are able to model the dynamics of an in-silico bioprocess system precisely, opening the door for the dynamic modeling of other engineering systems.
Authors: Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
Abstract: Bayesian Federated Learning (BFL) combines uncertainty modeling with decentralized training, enabling the development of personalized and reliable models under data heterogeneity and privacy constraints. Existing approaches typically rely on Markov Chain Monte Carlo (MCMC) sampling or variational inference, often incorporating personalization mechanisms to better adapt to local data distributions. In this work, we propose an information-geometric projection framework for personalization in parametric BFL. By projecting the global model onto a neighborhood of the user's local model, our method enables a tunable trade-off between global generalization and local specialization. Under mild assumptions, we show that this projection step is equivalent to computing a barycenter on the statistical manifold, allowing us to derive closed-form solutions and achieve cost-free personalization. We apply the proposed approach to a variational learning setup using the Improved Variational Online Newton (IVON) optimizer and extend its application to general aggregation schemes in BFL. Empirical evaluations under heterogeneous data distributions confirm that our method effectively balances global and local performance with minimal computational overhead.
Authors: Riccardo Lunelli, Angus Nicolson, Samuel Martin Pr\"oll, Sebastian Johannes Reinstadler, Axel Bauer, Clemens Dlaska
Abstract: Electrocardiograms (ECGs) are inexpensive, widely used, and well-suited to deep learning. Recently, interest has grown in developing foundation models for ECGs - models that generalise across diverse downstream tasks. However, consistent evaluation has been lacking: prior work often uses narrow task selections and inconsistent datasets, hindering fair comparison. Here, we introduce BenchECG, a standardised benchmark comprising a comprehensive suite of publicly available ECG datasets and versatile tasks. We also propose xECG, an xLSTM-based recurrent model trained with SimDINOv2 self-supervised learning, which achieves the best BenchECG score compared to publicly available state-of-the-art models. In particular, xECG is the only publicly available model to perform strongly on all datasets and tasks. By standardising evaluation, BenchECG enables rigorous comparison and aims to accelerate progress in ECG representation learning. xECG achieves superior performance over earlier approaches, defining a new baseline for future ECG foundation models.
Authors: Shiwei Li, Qunwei Li, Haozhao Wang, Ruixuan Li, Jianbin Lin, Wenliang Zhong
Abstract: Federated learning (FL) is an emerging distributed machine learning paradigm that enables collaborative model training without sharing local data. Despite its advantages, FL suffers from substantial communication overhead, which can affect training efficiency. Recent efforts have mitigated this issue by quantizing model updates to reduce communication costs. However, most existing methods apply quantization only after local training, introducing quantization errors into the trained parameters and potentially degrading model accuracy. In this paper, we propose Federated Bit Freezing (FedBiF), a novel FL framework that directly learns quantized model parameters during local training. In each communication round, the server first quantizes the model parameters and transmits them to the clients. FedBiF then allows each client to update only a single bit of the multi-bit parameter representation, freezing the remaining bits. This bit-by-bit update strategy reduces each parameter update to one bit while maintaining high precision in parameter representation. Extensive experiments are conducted on five widely used datasets under both IID and Non-IID settings. The results demonstrate that FedBiF not only achieves superior communication compression but also promotes sparsity in the resulting models. Notably, FedBiF attains accuracy comparable to FedAvg, even when using only 1 bit-per-parameter (bpp) for uplink and 3 bpp for downlink communication. The code is available at https://github.com/Leopold1423/fedbif-tpds25.
Authors: Francisco Javier Esono Nkulu Andong, Qi Min
Abstract: As sixth-generation (6G) networks move toward ultra-dense, intelligent edge environments, efficient resource management under stringent privacy, mobility, and energy constraints becomes critical. This paper introduces a novel Federated Multi-Agent Reinforcement Learning (Fed-MARL) framework that incorporates cross-layer orchestration of both the MAC layer and application layer for energy-efficient, privacy-preserving, and real-time resource management across heterogeneous edge devices. Each agent uses a Deep Recurrent Q-Network (DRQN) to learn decentralized policies for task offloading, spectrum access, and CPU energy adaptation based on local observations (e.g., queue length, energy, CPU usage, and mobility). To protect privacy, we introduce a secure aggregation protocol based on elliptic curve Diffie Hellman key exchange, which ensures accurate model updates without exposing raw data to semi-honest adversaries. We formulate the resource management problem as a partially observable multi-agent Markov decision process (POMMDP) with a multi-objective reward function that jointly optimizes latency, energy efficiency, spectral efficiency, fairness, and reliability under 6G-specific service requirements such as URLLC, eMBB, and mMTC. Simulation results demonstrate that Fed-MARL outperforms centralized MARL and heuristic baselines in task success rate, latency, energy efficiency, and fairness, while ensuring robust privacy protection and scalability in dynamic, resource-constrained 6G edge networks.
Authors: Hoshitaro Ohnishi, Hideo Mukai
Abstract: Quantum error correction, which utilizes logical qubits that are encoded as redundant multiple physical qubits to find and correct errors in physical qubits, is indispensable for practical quantum computing. Surface code is considered to be a promising encoding method with a high error threshold that is defined by stabilizer generators. However, previous methods have suffered from the problem that the decoder acquires solely the error probability distribution because of the non-uniqueness of correct prediction obtained from the input. To circumvent this problem, we propose a technique to reoptimize the decoder model by approximating syndrome measurements with a continuous function that is mathematically interpolated by neural network. We evaluated the improvement in accuracy of a multilayer perceptron based decoder for code distances of 5 and 7 as well as for decoders based on convolutional and recurrent neural networks and transformers for a code distance of 5. In all cases, the reoptimized decoder gave better accuracy than the original models, demonstrating the universal effectiveness of the proposed method that is independent of code distance or network architecture. These results suggest that re-framing the problem of surface code decoding into a regression problem that can be tackled by deep learning is a useful strategy.
Authors: L\'ena\"ic Chizat
Abstract: We study the gradient-based training of large-depth residual networks (ResNets) from standard random initializations. We show that with a diverging depth $L$, a fixed embedding dimension $D$, and an arbitrary hidden width $M$, the training dynamics converges to a Neural Mean ODE training dynamics. Remarkably, the limit is independent of the scaling of $M$, covering practical cases of, say, Transformers, where $M$ (the number of hidden units or attention heads per layer) is typically of the order of $D$. For a residual scale $\Theta_D\big(\frac{\alpha}{LM}\big)$, we obtain the error bound $O_D\big(\frac{1}{L}+ \frac{\alpha}{\sqrt{LM}}\big)$ between the model's output and its limit after a fixed number gradient of steps, and we verify empirically that this rate is tight. When $\alpha=\Theta(1)$, the limit exhibits complete feature learning, i.e. the Mean ODE is genuinely non-linearly parameterized. In contrast, we show that $\alpha \to \infty$ yields a \lazy ODE regime where the Mean ODE is linearly parameterized. We then focus on the particular case of ResNets with two-layer perceptron blocks, for which we study how these scalings depend on the embedding dimension $D$. We show that for this model, the only residual scale that leads to complete feature learning is $\Theta\big(\frac{\sqrt{D}}{LM}\big)$. In this regime, we prove the error bound $O\big(\frac{1}{L}+ \frac{\sqrt{D}}{\sqrt{LM}}\big)$ between the ResNet and its limit after a fixed number of gradient steps, which is also empirically tight. Our convergence results rely on a novel mathematical perspective on ResNets : (i) due to the randomness of the initialization, the forward and backward pass through the ResNet behave as the stochastic approximation of certain mean ODEs, and (ii) by propagation of chaos (that is, asymptotic independence of the units) this behavior is preserved through the training dynamics.
Authors: Benjamin Holzschuh, Georg Kohl, Florian Redinger, Nils Thuerey
Abstract: We present a scalable framework for learning deterministic and probabilistic neural surrogates for high-resolution 3D physics simulations. We introduce a hybrid CNN-Transformer backbone architecture targeted for 3D physics simulations, which significantly outperforms existing architectures in terms of speed and accuracy. Our proposed network can be pretrained on small patches of the simulation domain, which can be fused to obtain a global solution, optionally guided via a fast and scalable sequence-to-sequence model to include long-range dependencies. This setup allows for training large-scale models with reduced memory and compute requirements for high-resolution datasets. We evaluate our backbone architecture against a large set of baseline methods with the objective to simultaneously learn the dynamics of 14 different types of PDEs in 3D. We demonstrate how to scale our model to high-resolution isotropic turbulence with spatial resolutions of up to $512^3$. Finally, we demonstrate the versatility of our network by training it as a diffusion model to produce probabilistic samples of highly turbulent 3D channel flows across varying Reynolds numbers, accurately capturing the underlying flow statistics.
Authors: Zexu Jin
Abstract: Ensemble learning has been widely recognized as a pivotal technique for boosting predictive performance by combining multiple base models. Nevertheless, conventional margin-based ensemble methods predominantly focus on maximizing the expected margin while neglecting the critical role of margin variance, which inherently restricts the generalization capability of the model and heightens its vulnerability to overfitting, particularly in noisy or imbalanced datasets. Additionally, the conventional approach of optimizing ensemble weights within the probability simplex often introduces computational inefficiency and scalability challenges, complicating its application to large-scale problems. To tackle these limitations, this paper introduces a novel ensemble learning framework that explicitly incorporates margin variance into the loss function. Our method jointly optimizes the negative expected margin and its variance, leading to enhanced robustness and improved generalization performance. Moreover, by reparameterizing the ensemble weights onto the unit sphere, we substantially simplify the optimization process and improve computational efficiency. Extensive experiments conducted on multiple benchmark datasets demonstrate that the proposed approach consistently outperforms traditional margin-based ensemble techniques, underscoring its effectiveness and practical utility.
Authors: \'Angel Ladr\'on, Miguel S\'anchez-Dom\'inguez, Javier Rozal\'en, Fernando R. S\'anchez, Javier de Vicente, Lucas Lacasa, Eusebio Valero, Gonzalo Rubio
Abstract: Fatigue life prediction is essential in both the design and operational phases of any aircraft, and in this sense safety in the aerospace industry requires early detection of fatigue cracks to prevent in-flight failures. Robust and precise fatigue life predictors are thus essential to ensure safety. Traditional engineering methods, while reliable, are time consuming and involve complex workflows, including steps such as conducting several Finite Element Method (FEM) simulations, deriving the expected loading spectrum, and applying cycle counting techniques like peak-valley or rainflow counting. These steps often require collaboration between multiple teams and tools, added to the computational time and effort required to achieve fatigue life predictions. Machine learning (ML) offers a promising complement to traditional fatigue life estimation methods, enabling faster iterations and generalization, providing quick estimates that guide decisions alongside conventional simulations. In this paper, we present a ML-based pipeline that aims to estimate the fatigue life of different aircraft wing locations given the flight parameters of the different missions that the aircraft will be operating throughout its operational life. We validate the pipeline in a realistic use case of fatigue life estimation, yielding accurate predictions alongside a thorough statistical validation and uncertainty quantification. Our pipeline constitutes a complement to traditional methodologies by reducing the amount of costly simulations and, thereby, lowering the required computational and human resources.
Authors: Janis Keuper
Abstract: The ongoing intense discussion on rising LLM usage in the scientific peer-review process has recently been mingled by reports of authors using hidden prompt injections to manipulate review scores. Since the existence of such "attacks" - although seen by some commentators as "self-defense" - would have a great impact on the further debate, this paper investigates the practicability and technical success of the described manipulations. Our systematic evaluation uses 1k reviews of 2024 ICLR papers generated by a wide range of LLMs shows two distinct results: I) very simple prompt injections are indeed highly effective, reaching up to 100% acceptance scores. II) LLM reviews are generally biased toward acceptance (>95% in many models). Both results have great impact on the ongoing discussions on LLM usage in peer-review.
Authors: Sahil Sethi, Kai Sundmacher, Caroline Ganzer
Abstract: Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework that leverages a neural recommender system (NRS) to enable reliable property prediction for ILs using sparse experimental datasets. The approach involves a two-stage process: first, pre-training NRS models on COSMO-RS-based simulated data at fixed temperature and pressure to learn property-specific structural embeddings for cations and anions; and second, fine-tuning simple feedforward neural networks using these embeddings with experimental data at varying temperatures and pressures. In this work, five essential IL properties are considered: density, viscosity, surface tension, heat capacity, and melting point. The framework supports both within-property and cross-property knowledge transfer. Notably, pre-trained models for density, viscosity, and heat capacity are used to fine-tune models for all five target properties, achieving improved performance by a substantial margin for four of them. The model exhibits robust extrapolation to previously unseen ILs. Moreover, the final trained models enable property prediction for over 700,000 IL combinations, offering a scalable solution for IL screening in process design. This work highlights the effectiveness of combining simulated data and transfer learning to overcome sparsity in the experimental data.
Authors: Salih Toprak, Muge Erel-Ozcevik
Abstract: In disaster scenarios where conventional energy infrastructure is compromised, secure and traceable energy trading between solar-powered households and mobile charging units becomes a necessity. To ensure the integrity of such transactions over a blockchain network, robust and unpredictable nonce generation is vital. This study proposes an SDN-enabled architecture where machine learning regressors are leveraged not for their accuracy, but for their potential to generate randomized values suitable as nonce candidates. Therefore, it is newly called Proof of AutoML. Here, SDN allows flexible control over data flows and energy routing policies even in fragmented or degraded networks, ensuring adaptive response during emergencies. Using a 9000-sample dataset, we evaluate five AutoML-selected regression models - Gradient Boosting, LightGBM, Random Forest, Extra Trees, and K-Nearest Neighbors - not by their prediction accuracy, but by their ability to produce diverse and non-deterministic outputs across shuffled data inputs. Randomness analysis reveals that Random Forest and Extra Trees regressors exhibit complete dependency on randomness, whereas Gradient Boosting, K-Nearest Neighbors and LightGBM show strong but slightly lower randomness scores (97.6%, 98.8% and 99.9%, respectively). These findings highlight that certain machine learning models, particularly tree-based ensembles, may serve as effective and lightweight nonce generators within blockchain-secured, SDN-based energy trading infrastructures resilient to disaster conditions.
Authors: Jesse van Remmerden, Zaharah Bukhsh, Yingqian Zhang
Abstract: The Job-Shop Scheduling Problem (JSP) and Flexible Job-Shop Scheduling Problem (FJSP), are canonical combinatorial optimization problems with wide-ranging applications in industrial operations. In recent years, many online reinforcement learning (RL) approaches have been proposed to learn constructive heuristics for JSP and FJSP. Although effective, these online RL methods require millions of interactions with simulated environments that may not capture real-world complexities, and their random policy initialization leads to poor sample efficiency. To address these limitations, we introduce Conservative Discrete Quantile Actor-Critic (CDQAC), a novel offline RL algorithm that learns effective scheduling policies directly from historical data, eliminating the need for costly online interactions, while maintaining the ability to improve upon suboptimal training data. CDQAC couples a quantile-based critic with a delayed policy update, estimating the return distribution of each machine-operation pair rather than selecting pairs outright. Our extensive experiments demonstrate CDQAC's remarkable ability to learn from diverse data sources. CDQAC consistently outperforms the original data-generating heuristics and surpasses state-of-the-art offline and online RL baselines. In addition, CDQAC is highly sample efficient, requiring only 10-20 training instances to learn high-quality policies. Surprisingly, we find that CDQAC performs better when trained on data generated by a random heuristic than when trained on higher-quality data from genetic algorithms and priority dispatching rules.
Authors: Joshua Dimasaka, Christian Gei{\ss}, Robert Muir-Wood, Emily So
Abstract: In the aftermath of disasters, many institutions worldwide face challenges in continually monitoring changes in disaster risk, limiting the ability of key decision-makers to assess progress towards the UN Sendai Framework for Disaster Risk Reduction 2015-2030. While numerous efforts have substantially advanced the large-scale modeling of hazard and exposure through Earth observation and data-driven methods, progress remains limited in modeling another equally important yet challenging element of the risk equation: physical vulnerability. To address this gap, we introduce Graph Categorical Structured Variational Autoencoder (GraphCSVAE), a novel probabilistic data-driven framework for modeling physical vulnerability by integrating deep learning, graph representation, and categorical probabilistic inference, using time-series satellite-derived datasets and prior expert belief systems. We introduce a weakly supervised first-order transition matrix that reflects the changes in the spatiotemporal distribution of physical vulnerability in two disaster-stricken and socioeconomically disadvantaged areas: (1) the cyclone-impacted coastal Khurushkul community in Bangladesh and (2) the mudslide-affected city of Freetown in Sierra Leone. Our work reveals post-disaster regional dynamics in physical vulnerability, offering valuable insights into localized spatiotemporal auditing and sustainable strategies for post-disaster risk reduction.
Authors: Myung Jin Kim, YeongHyeon Park, Il Dong Yun
Abstract: This paper proposes a simple yet effective convolutional module for long-term time series forecasting. The proposed block, inspired by the Auto-Regressive Integrated Moving Average (ARIMA) model, consists of two convolutional components: one for capturing the trend (autoregression) and the other for refining local variations (moving average). Unlike conventional ARIMA, which requires iterative multi-step forecasting, the block directly performs multi-step forecasting, making it easily extendable to multivariate settings. Experiments on nine widely used benchmark datasets demonstrate that our method ARMA achieves competitive accuracy, particularly on datasets exhibiting strong trend variations, while maintaining architectural simplicity. Furthermore, analysis shows that the block inherently encodes absolute positional information, suggesting its potential as a lightweight replacement for positional embeddings in sequential models.
Authors: Benjamin David Shaffer, Brooks Kinch, Joseph Klobusicky, M. Ani Hsieh, Nathaniel Trask
Abstract: We present a machine learning framework for adaptive source localization in which agents use a structure-preserving digital twin of a coupled hydrodynamic-transport system for real-time trajectory planning and data assimilation. The twin is constructed with conditional neural Whitney forms (CNWF), coupling the numerical guarantees of finite element exterior calculus (FEEC) with transformer-based operator learning. The resulting model preserves discrete conservation, and adapts in real time to streaming sensor data. It employs a conditional attention mechanism to identify: a reduced Whitney-form basis; reduced integral balance equations; and a source field, each compatible with given sensor measurements. The induced reduced-order environmental model retains the stability and consistency of standard finite-element simulation, yielding a physically realizable, regular mapping from sensor data to the source field. We propose a staggered scheme that alternates between evaluating the digital twin and applying Lloyd's algorithm to guide sensor placement, with analysis providing conditions for monotone improvement of a coverage functional. Using the predicted source field as an importance function within an optimal-recovery scheme, we demonstrate recovery of point sources under continuity assumptions, highlighting the role of regularity as a sufficient condition for localization. Experimental comparisons with physics-agnostic transformer architectures show improved accuracy in complex geometries when physical constraints are enforced, indicating that structure preservation provides an effective inductive bias for source identification.
Authors: Tong Chen, Raghavendra Selvan
Abstract: Given a dataset of finitely many elements $\mathcal{T} = \{\mathbf{x}_i\}_{i = 1}^N$, the goal of dataset condensation (DC) is to construct a synthetic dataset $\mathcal{S} = \{\tilde{\mathbf{x}}_j\}_{j = 1}^M$ which is significantly smaller ($M \ll N$) such that a model trained from scratch on $\mathcal{S}$ achieves comparable or even superior generalization performance to a model trained on $\mathcal{T}$. Recent advances in DC reveal a close connection to the problem of approximating the data distribution represented by $\mathcal{T}$ with a reduced set of points. In this work, we present a unified framework that encompasses existing DC methods and extend the task-specific notion of DC to a more general and formal definition using notions of discrepancy, which quantify the distance between probability distribution in different regimes. Our framework broadens the objective of DC beyond generalization, accommodating additional objectives such as robustness, privacy, and other desirable properties.
Authors: Gul Rukh Khattak, Konstantinos Patlatzoglou, Joseph Barker, Libor Pastika, Boroumand Zeidaabadi, Ahmed El-Medany, Hesham Aggour, Yixiu Liang, Antonio H. Ribeiro, Jeffrey Annis, Antonio Luiz Pinho Ribeiro, Junbo Ge, Daniel B. Kramer, Jonathan W. Waks, Evan Brittain, Nicholas Peters, Fu Siong Ng, Arunashis Sau
Abstract: Contrastive learning is a widely adopted self-supervised pretraining strategy, yet its dependence on cohort composition remains underexplored. We present Contrasting by Patient Augmented Electrocardiograms (CAPE) foundation model and pretrain on four cohorts (n = 5,203,352), from diverse populations across three continents (North America, South America, Asia). We systematically assess how cohort demographics, health status, and population diversity influence the downstream performance for prediction tasks also including two additional cohorts from another continent (Europe). We find that downstream performance depends on the distributional properties of the pretraining cohort, including demographics and health status. Moreover, while pretraining with a multi-centre, demographically diverse cohort improves in-distribution accuracy, it reduces out-of-distribution (OOD) generalisation of our contrastive approach by encoding cohort-specific artifacts. To address this, we propose the In-Distribution Batch (IDB) strategy, which preserves intra-cohort consistency during pretraining and enhances OOD robustness. This work provides important insights for developing clinically fair and generalisable foundation models.
Authors: Jianxin Zhang, Clayton Scott
Abstract: Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces remains unexplored. In this work, we establish a rigorous functional formulation of rectified flow in an infinite-dimensional Hilbert space. Our approach builds upon the superposition principle for continuity equations in an infinite-dimensional space. We further show that this framework extends naturally to functional flow matching and functional probability flow ODEs, interpreting them as nonlinear generalizations of rectified flow. Notably, our extension to functional flow matching removes the restrictive measure-theoretic assumptions in the existing theory of \citet{kerrigan2024functional}. Furthermore, we demonstrate experimentally that our method achieves superior performance compared to existing functional generative models.
Authors: Quan Nguyen, Adji Bousso Dieng
Abstract: While monitoring biodiversity through camera traps has become an important endeavor for ecological research, identifying species in the captured image data remains a major bottleneck due to limited labeling resources. Active learning -- a machine learning paradigm that selects the most informative data to label and train a predictive model -- offers a promising solution, but typically focuses on uncertainty in the individual predictions without considering uncertainty across the entire dataset. We introduce a new active learning policy, Vendi information gain (VIG), that selects images based on their impact on dataset-wide prediction uncertainty, capturing both informativeness and diversity. Applied to the Snapshot Serengeti dataset, VIG achieves impressive predictive accuracy close to full supervision using less than 10% of the labels. It consistently outperforms standard baselines across metrics and batch sizes, collecting more diverse data in the feature space. VIG has broad applicability beyond ecology, and our results highlight its value for biodiversity monitoring in data-limited environments.
Authors: Siyan Zhao, Mengchen Liu, Jing Huang, Miao Liu, Chenyu Wang, Bo Liu, Yuandong Tian, Guan Pang, Sean Bell, Aditya Grover, Feiyu Chen
Abstract: Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation capabilities such as inpainting. We explore how inpainting can inform RL algorithm design for dLLMs. Aligning LLMs with reinforcement learning faces an exploration challenge: sparse reward signals and sample waste when models fail to discover correct solutions. While this inefficiency affects LLMs broadly, dLLMs offer a distinctive opportunity--their inpainting ability can guide exploration. We introduce IGPO (Inpainting Guided Policy Optimization), an RL framework that strategically inserts partial ground-truth reasoning traces during online sampling. Unlike providing full solutions, inpainting steers exploration toward promising trajectory spaces while preserving self-generated reasoning, bridging supervised fine-tuning and reinforcement learning. We apply IGPO to group-based optimization methods such as GRPO, where exploration failures cause zero advantages and gradients. IGPO restores meaningful gradients while improving sample efficiency. We also propose supervised fine-tuning on synthetically rewritten concise traces that better align with dLLM generation patterns. With additional techniques including entropy-based filtering, our training recipe yields substantial gains across three mathematical benchmarks--GSM8K, Math500, and AMC--achieving new state-of-the-art results for full-attention masked dLLMs.
Authors: Rupert Mitchell, Kristian Kersting
Abstract: We present Multipole Semantic Attention (MuSe), an efficient approximation of softmax attention that combines semantic clustering with multipole expansions from computational physics. Our method addresses the quadratic computational complexity of transformers in the context length by clustering queries and keys separately in their learned representation spaces, enabling a hierarchical two-stage attention mechanism. Unlike prior clustering approaches that group only keys or use unified clustering, we maintain separate clusterings that respect attention's asymmetric treatment of these spaces. We augment centroid-based (monopole) approximations with dipole corrections that capture directional variance within clusters, preserving richer information during training. The method operates as a drop-in replacement for standard attention, requiring only hyperparameter specification without architectural modifications. Our approach achieves $\mathcal{O}(NCD)$ complexity for acausal attention with $C$ clusters and $\mathcal{O}(NCD \log N)$ for causal attention. On isolated attention layers, we demonstrate $3\times$ speedup over CUDNN Flash Attention at 8k context length, with relative squared errors below 20%. For causal attention, we develop a hierarchical block decomposition that combines exact local computation with efficient long-range approximation. In end-to-end pretraining of a 30M parameter model on book-length texts with 16k context, we achieve 12.2% runtime reduction with only 0.36% loss degradation, establishing the viability of multipole approximations for efficient transformer pretraining.
Authors: Francesco Vitale, Tommaso Zoppi, Francesco Flammini, Nicola Mazzocca
Abstract: Ensuring the resilience of computer-based railways is increasingly crucial to account for uncertainties and changes due to the growing complexity and criticality of those systems. Although their software relies on strict verification and validation processes following well-established best-practices and certification standards, anomalies can still occur at run-time due to residual faults, system and environmental modifications that were unknown at design-time, or other emergent cyber-threat scenarios. This paper explores run-time control-flow anomaly detection using process mining to enhance the resilience of ERTMS/ETCS L2 (European Rail Traffic Management System / European Train Control System Level 2). Process mining allows learning the actual control flow of the system from its execution traces, thus enabling run-time monitoring through online conformance checking. In addition, anomaly localization is performed through unsupervised machine learning to link relevant deviations to critical system components. We test our approach on a reference ERTMS/ETCS L2 scenario, namely the RBC/RBC Handover, to show its capability to detect and localize anomalies with high accuracy, efficiency, and explainability.
Authors: Ahmed Khaled, Satyen Kale, Arthur Douillard, Chi Jin, Rob Fergus, Manzil Zaheer
Abstract: Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed data centers). Communication becomes a major bottleneck in such settings but methods like Local Stochastic Gradient Descent (Local SGD) show great promise in reducing this additional communication overhead. Local SGD consists of three parts: a local optimization process, an aggregation mechanism, and an outer optimizer that uses the aggregated updates from the nodes to produce a new model. While there exists an extensive literature on understanding the impact of hyperparameters in the local optimization process, the choice of outer optimizer and its hyperparameters is less clear. We study the role of the outer optimizer in Local SGD, and prove new convergence guarantees for the algorithm. In particular, we show that tuning the outer learning rate allows us to (a) trade off between optimization error and stochastic gradient noise variance, and (b) make up for ill-tuning of the inner learning rate. Our theory suggests that the outer learning rate should sometimes be set to values greater than $1$. We extend our results to settings where we use momentum in the outer optimizer, and we show a similar role for the momentum-adjusted outer learning rate. We also study acceleration in the outer optimizer and show that it improves the convergence rate as a function of the number of communication rounds, improving upon the convergence rate of prior algorithms that apply acceleration locally. Finally, we also introduce a novel data-dependent analysis of Local SGD that yields further insights on outer learning rate tuning. We conduct comprehensive experiments with standard language models and various outer optimizers to validate our theory.
Authors: Mahe Chen, Xiaoxuan Wang, Kaiwen Chen, Nick Koudas
Abstract: The rapid adoption of generative AI-powered search engines like ChatGPT, Perplexity, and Gemini is fundamentally reshaping information retrieval, moving from traditional ranked lists to synthesized, citation-backed answers. This shift challenges established Search Engine Optimization (SEO) practices and necessitates a new paradigm, which we term Generative Engine Optimization (GEO). This paper presents a comprehensive comparative analysis of AI Search and traditional web search (Google). Through a series of large-scale, controlled experiments across multiple verticals, languages, and query paraphrases, we quantify critical differences in how these systems source information. Our key findings reveal that AI Search exhibit a systematic and overwhelming bias towards Earned media (third-party, authoritative sources) over Brand-owned and Social content, a stark contrast to Google's more balanced mix. We further demonstrate that AI Search services differ significantly from each other in their domain diversity, freshness, cross-language stability, and sensitivity to phrasing. Based on these empirical results, we formulate a strategic GEO agenda. We provide actionable guidance for practitioners, emphasizing the critical need to: (1) engineer content for machine scannability and justification, (2) dominate earned media to build AI-perceived authority, (3) adopt engine-specific and language-aware strategies, and (4) overcome the inherent "big brand bias" for niche players. Our work provides the foundational empirical analysis and a strategic framework for achieving visibility in the new generative search landscape.
Authors: Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao
Abstract: This paper presents the db3 team's winning solution for the Meta CRAG-MM Challenge 2025 at KDD Cup'25. Addressing the challenge's unique multi-modal, multi-turn question answering benchmark (CRAG-MM), we developed a comprehensive framework that integrates tailored retrieval pipelines for different tasks with a unified LLM-tuning approach for hallucination control. Our solution features (1) domain-specific retrieval pipelines handling image-indexed knowledge graphs, web sources, and multi-turn conversations; and (2) advanced refusal training using SFT, DPO, and RL. The system achieved 2nd place in Task 1, 2nd place in Task 2, and 1st place in Task 3, securing the grand prize for excellence in ego-centric queries through superior handling of first-person perspective challenges.
Authors: Himanshu Thakur, Eshani Agrawal, Smruthi Mukund
Abstract: A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex and stochastic nature of user interactions. Towards this, one promising line of work has been the use of Large Language Models (LLMs) for simulating user behavior. However, aligning these general-purpose large pre-trained models with user preferences necessitates: (i) effectively and continously parsing large-scale tabular user-item interaction data, (ii) overcoming pre-training-induced inductive biases to accurately learn user specific knowledge, and (iii) achieving the former two at scale for millions of users. While most previous works have focused on complex methods to prompt an LLM or fine-tune it on tabular interaction datasets, our approach shifts the focus to extracting robust textual user representations using a frozen LLM and simulating cost-effective, resource-efficient user agents powered by fine-tuned Small Language Models (SLMs). Further, we showcase a method for training multiple low-rank adapters for groups of users or \textit{persona}, striking an optimal balance between scalability and performance of user behavior agents. Our experiments provide compelling empirical evidence of the efficacy of our methods, demonstrating that user agents developed using our approach have the potential to bridge the gap between offline metrics and real-world performance of recommender systems.
Authors: Ping Liu, Jianqiang Shen, Qianqi Shen, Chunnan Yao, Kevin Kao, Dan Xu, Rajat Arora, Baofen Zheng, Caleb Johnson, Liangjie Hong, Jingwei Wu, Wenjing Zhang
Abstract: Query understanding is essential in modern relevance systems, where user queries are often short, ambiguous, and highly context-dependent. Traditional approaches often rely on multiple task-specific Named Entity Recognition models to extract structured facets as seen in job search applications. However, this fragmented architecture is brittle, expensive to maintain, and slow to adapt to evolving taxonomies and language patterns. In this paper, we introduce a unified query understanding framework powered by a Large Language Model (LLM), designed to address these limitations. Our approach jointly models the user query and contextual signals such as profile attributes to generate structured interpretations that drive more accurate and personalized recommendations. The framework improves relevance quality in online A/B testing while significantly reducing system complexity and operational overhead. The results demonstrate that our solution provides a scalable and adaptable foundation for query understanding in dynamic web applications.
Authors: Fabio Magarelli, Geraldine B. Boylan, Saeed Montazeri, Feargal O'Sullivan, Dominic Lightbody, Minoo Ashoori, Tamara Skoric Ceranic, John M. O'Toole
Abstract: Machine learning (ML) has the potential to support and improve expert performance in monitoring the brain function of at-risk newborns. Developing accurate and reliable ML models depends on access to high-quality, annotated data, a resource in short supply. ML competitions address this need by providing researchers access to expertly annotated datasets, fostering shared learning through direct model comparisons, and leveraging the benefits of crowdsourcing diverse expertise. We compiled a retrospective dataset containing 353 hours of EEG from 102 individual newborns from a multi-centre study. The data was fully anonymised and divided into training, testing, and held-out validation datasets. EEGs were graded for the severity of abnormal background patterns. Next, we created a web-based competition platform and hosted a machine learning competition to develop ML models for classifying the severity of EEG background patterns in newborns. After the competition closed, the top 4 performing models were evaluated offline on a separate held-out validation dataset. Although a feature-based model ranked first on the testing dataset, deep learning models generalised better on the validation sets. All methods had a significant decline in validation performance compared to the testing performance. This highlights the challenges for model generalisation on unseen data, emphasising the need for held-out validation datasets in ML studies with neonatal EEG. The study underscores the importance of training ML models on large and diverse datasets to ensure robust generalisation. The competition's outcome demonstrates the potential for open-access data and collaborative ML development to foster a collaborative research environment and expedite the development of clinical decision-support tools for neonatal neuromonitoring.
Authors: Weibin Li, Wendu Li, Quanying Liu
Abstract: Higher-order brain connectivity (HOBC), which captures interactions among three or more brain regions, provides richer organizational information than traditional pairwise functional connectivity (FC). Recent studies have begun to infer latent HOBC from noninvasive imaging data, but they mainly focus on static analyses, limiting their applicability in dynamic prediction tasks. To address this gap, we propose DCHO, a unified approach for modeling and forecasting the temporal evolution of HOBC based on a Decomposition-Composition framework, which is applicable to both non-predictive tasks (state classification) and predictive tasks (brain dynamics forecasting). DCHO adopts a decomposition-composition strategy that reformulates the prediction task into two manageable subproblems: HOBC inference and latent trajectory prediction. In the inference stage, we propose a dual-view encoder to extract multiscale topological features and a latent combinatorial learner to capture high-level HOBC information. In the forecasting stage, we introduce a latent-space prediction loss to enhance the modeling of temporal trajectories. Extensive experiments on multiple neuroimaging datasets demonstrate that DCHO achieves superior performance in both non-predictive tasks (state classification) and predictive tasks (brain dynamics forecasting), significantly outperforming existing methods.
Authors: Sepehr Golrokh Amin, Devin Rhoads, Fatemeh Fakhrmoosavi, Nicholas E. Lownes, John N. Ivan
Abstract: This study introduces a Large Language Model (LLM) scheme for generating individual travel diaries in agent-based transportation models. While traditional approaches rely on large quantities of proprietary household travel surveys, the method presented in this study generates personas stochastically from open-source American Community Survey (ACS) and Smart Location Database (SLD) data, then synthesizes diaries through direct prompting. This study features a novel one-to-cohort realism score: a composite of four metrics (Trip Count Score, Interval Score, Purpose Score, and Mode Score) validated against the Connecticut Statewide Transportation Study (CSTS) diaries, matched across demographic variables. The validation utilizes Jensen-Shannon Divergence to measure distributional similarities between generated and real diaries. When compared to diaries generated with classical methods (Negative Binomial for trip generation; Multinomial Logit for mode/purpose) calibrated on the validation set, LLM-generated diaries achieve comparable overall realism (LLM mean: 0.485 vs. 0.455). The LLM excels in determining trip purpose and demonstrates greater consistency (narrower realism score distribution), while classical models lead in numerical estimates of trip count and activity duration. Aggregate validation confirms the LLM's statistical representativeness (LLM mean: 0.612 vs. 0.435), demonstrating LLM's zero-shot viability and establishing a quantifiable metric of diary realism for future synthetic diary evaluation systems.
Authors: Jorge E. Le\'on, Miguel Carrasco
Abstract: On one hand, recent advances in chatbots has led to a rising popularity in using these models for coding tasks. On the other hand, modern generative image models primarily rely on text encoders to translate semantic concepts into visual representations, even when there is clear evidence that audio can be employed as input as well. Given the previous, in this work, we explore whether state-of-the-art conversational agents can design effective audio encoders to replace the CLIP text encoder from Stable Diffusion 1.5, enabling image synthesis directly from sound. We prompted five publicly available chatbots to propose neural architectures to work as these audio encoders, with a set of well-explained shared conditions. Each valid suggested encoder was trained on over two million context related audio-image-text observations, and evaluated on held-out validation and test sets using various metrics, together with a qualitative analysis of their generated images. Although almost all chatbots generated valid model designs, none achieved satisfactory results, indicating that their audio embeddings failed to align reliably with those of the original text encoder. Among the proposals, the Gemini audio encoder showed the best quantitative metrics, while the Grok audio encoder produced more coherent images (particularly, when paired with the text encoder). Our findings reveal a shared architectural bias across chatbots and underscore the remaining coding gap that needs to be bridged in future versions of these models. We also created a public demo so everyone could study and try out these audio encoders. Finally, we propose research questions that should be tackled in the future, and encourage other researchers to perform more focused and highly specialized tasks like this one, so the respective chatbots cannot make use of well-known solutions and their creativity/reasoning is fully tested.
Authors: Jiayi Miao, Dingxin Lu, Zhuqi Wang
Abstract: After natural disasters, accurate evaluations of damage to housing are important for insurance claims response and planning of resources. In this work, we introduce a novel multimodal retrieval-augmented generation (MM-RAG) framework. On top of classical RAG architecture, we further the framework to devise a two-branch multimodal encoder structure that the image branch employs a visual encoder composed of ResNet and Transformer to extract the characteristic of building damage after disaster, and the text branch harnesses a BERT retriever for the text vectorization of posts as well as insurance policies and for the construction of a retrievable restoration index. To impose cross-modal semantic alignment, the model integrates a cross-modal interaction module to bridge the semantic representation between image and text via multi-head attention. Meanwhile, in the generation module, the introduced modal attention gating mechanism dynamically controls the role of visual evidence and text prior information during generation. The entire framework takes end-to-end training, and combines the comparison loss, the retrieval loss and the generation loss to form multi-task optimization objectives, and achieves image understanding and policy matching in collaborative learning. The results demonstrate superior performance in retrieval accuracy and classification index on damage severity, where the Top-1 retrieval accuracy has been improved by 9.6%.
Authors: Taylor Archibald, Tony Martinez
Abstract: We present a novel ensemble framework that stabilizes LLM based text extraction from noisy historical documents. We transcribe multiple augmented variants of each image with Gemini 2.0 Flash and fuse these outputs with a custom Needleman Wunsch style aligner that yields both a consensus transcription and a confidence score. We present a new dataset of 622 Pennsylvania death records, and demonstrate our method improves transcription accuracy by 4 percentage points relative to a single shot baseline. We find that padding and blurring are the most useful for improving accuracy, while grid warp perturbations are best for separating high and low confidence cases. The approach is simple, scalable, and immediately deployable to other document collections and transcription models.
Authors: Kai R. Larsen, Sen Yan, Roland M\"uller, Lan Sang, Mikko R\"onkk\"o, Ravi Starzl, Donald Edmondson
Abstract: Psychological measurement is critical to many disciplines. Despite advances in measurement, building nomological networks, theoretical maps of how concepts and measures relate to establish validity, remains a challenge 70 years after Cronbach and Meehl proposed them as fundamental to validation. This limitation has practical consequences: clinical trials may fail to detect treatment effects, and public policy may target the wrong outcomes. We introduce Analysis of Latent Indicators to Generate Nomological Structures (ALIGNS), a large language model-based system trained with validated questionnaire measures. ALIGNS provides three comprehensive nomological networks containing over 550,000 indicators across psychology, medicine, social policy, and other fields. This represents the first application of large language models to solve a foundational problem in measurement validation. We report classification accuracy tests used to develop the model, as well as three evaluations. In the first evaluation, the widely used NIH PROMIS anxiety and depression instruments are shown to converge into a single dimension of emotional distress. The second evaluation examines child temperament measures and identifies four potential dimensions not captured by current frameworks, and questions one existing dimension. The third evaluation, an applicability check, engages expert psychometricians who assess the system's importance, accessibility, and suitability. ALIGNS is freely available at nomologicalnetwork.org, complementing traditional validation methods with large-scale nomological analysis.
Authors: Wonyoung Kim, Sujeong Seo, Juhyun Lee
Abstract: Technology opportunities are critical information that serve as a foundation for advancements in technology, industry, and innovation. This paper proposes a framework based on the temporal relationships between technologies to identify emerging technology opportunities. The proposed framework begins by extracting text from a patent dataset, followed by mapping text-based topics to discover inter-technology relationships. Technology opportunities are then identified by tracking changes in these topics over time. To enhance efficiency, the framework leverages a large language model to extract topics and employs a prompt for a chat-based language model to support the discovery of technology opportunities. The framework was evaluated using an artificial intelligence patent dataset provided by the United States Patent and Trademark Office. The experimental results suggest that artificial intelligence technology is evolving into forms that facilitate everyday accessibility. This approach demonstrates the potential of the proposed framework to identify future technology opportunities.
Authors: Elena Rohde, Jonas Klingwort, Christian Borgs
Abstract: This paper presents a meta-analysis evaluating ML performance in sentiment analysis for Twitter data. The study aims to estimate the average performance, assess heterogeneity between and within studies, and analyze how study characteristics influence model performance. Using PRISMA guidelines, we searched academic databases and selected 195 trials from 20 studies with 12 study features. Overall accuracy, the most reported performance metric, was analyzed using double arcsine transformation and a three-level random effects model. The average overall accuracy of the AIC-optimized model was 0.80 [0.76, 0.84]. This paper provides two key insights: 1) Overall accuracy is widely used but often misleading due to its sensitivity to class imbalance and the number of sentiment classes, highlighting the need for normalization. 2) Standardized reporting of model performance, including reporting confusion matrices for independent test sets, is essential for reliable comparisons of ML classifiers across studies, which seems far from common practice.
Authors: Zikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong, Xiaorui Wang, Zhendong Mao
Abstract: The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian agentic AI. However, despite MCP's growing adoption, existing benchmarks often fail to capture real-world agent performance within this new paradigm, leading to a distorted perception of their true operational value and an inability to reliably differentiate proficiencies. To bridge this critical evaluation gap, we introduce MCP-AgentBench -- a comprehensive benchmark specifically engineered to rigorously assess language agent capabilities in MCP-mediated tool interactions. Core contributions of MCP-AgentBench include: the establishment of a robust MCP testbed comprising 33 operational servers with 188 distinct tools; the development of a benchmark featuring 600 systematically designed queries distributed across 6 distinct categories of varying interaction complexity; and the introduction of MCP-Eval, a novel outcome-oriented evaluation methodology prioritizing real-world task success. Through extensive empirical evaluation of leading language agents, we provide foundational insights. MCP-AgentBench aims to equip the research community with a standardized and reliable framework to build, validate, and advance agents capable of fully leveraging MCP's transformative benefits, thereby accelerating progress toward truly capable and interoperable AI systems.
Authors: Klemen Kotar, Wanhee Lee, Rahul Venkatesh, Honglin Chen, Daniel Bear, Jared Watrous, Simon Kim, Khai Loong Aw, Lilian Naing Chen, Stefan Stojanov, Kevin Feigelis, Imran Thobani, Alex Durango, Khaled Jedoui, Atlas Kazemian, Dan Yamins
Abstract: We present Probabilistic Structure Integration (PSI), a system for learning richly controllable and flexibly promptable world models from data. PSI consists of a three-step cycle. The first step, Probabilistic prediction, involves building a probabilistic graphical model Psi of the data, in the form of a random-access autoregressive sequence model. Psi supports a complete set of learned conditional distributions describing the dependence of any variables in the data on any other set of variables. In step 2, Structure extraction, we show how to extract underlying low-dimensional properties in the data, corresponding to a diverse set of meaningful "intermediate structures", in a zero-shot fashion via causal inference on Psi. Step 3, Integration, completes the cycle by converting these structures into new token types that are then continually mixed back into the training diet as conditioning signals and prediction targets. Each such cycle augments the capabilities of Psi, both allowing it to model the underlying data better, and creating new control handles -- akin to an LLM-like universal prompting language. We train an instance of Psi on 1.4 trillion tokens of internet video data; we use it to perform a variety of useful video prediction and understanding inferences; we extract state-of-the-art optical flow, self-supervised depth and object segmentation; and we use these structures to support a full cycle of predictive improvements.
Authors: Ying Yuan, Xing-Yue Monica Ge, Aaron Archer Waterman, Tommaso Biancalani, David Richmond, Yogesh Pandit, Avtar Singh, Russell Littman, Jin Liu, Jan-Christian Huetter, Vladimir Ermakov
Abstract: Large-scale single-cell and Perturb-seq investigations routinely involve clustering cells and subsequently annotating each cluster with Gene-Ontology (GO) terms to elucidate the underlying biological programs. However, both stages, resolution selection and functional annotation, are inherently subjective, relying on heuristics and expert curation. We present HYPOGENEAGENT, a large language model (LLM)-driven framework, transforming cluster annotation into a quantitatively optimizable task. Initially, an LLM functioning as a gene-set analyst analyzes the content of each gene program or perturbation module and generates a ranked list of GO-based hypotheses, accompanied by calibrated confidence scores. Subsequently, we embed every predicted description with a sentence-embedding model, compute pair-wise cosine similarities, and let the agent referee panel score (i) the internal consistency of the predictions, high average similarity within the same cluster, termed intra-cluster agreement (ii) their external distinctiveness, low similarity between clusters, termed inter-cluster separation. These two quantities are combined to produce an agent-derived resolution score, which is maximized when clusters exhibit simultaneous coherence and mutual exclusivity. When applied to a public K562 CRISPRi Perturb-seq dataset as a preliminary test, our Resolution Score selects clustering granularities that exhibit alignment with known pathway compared to classical metrics such silhouette score, modularity score for gene functional enrichment summary. These findings establish LLM agents as objective adjudicators of cluster resolution and functional annotation, thereby paving the way for fully automated, context-aware interpretation pipelines in single-cell multi-omics studies.
Authors: Jackson Eshbaugh, Chetan Tiwari, Jorge Silveyra
Abstract: Computational models have emerged as powerful tools for energy modeling research, touting scalability and quantitative results. However, these models require a plethora of data, some of which is inaccessible, expensive, or raises privacy concerns. We introduce a modular multimodal framework to produce this data from publicly accessible residential information and images using generative artificial intelligence (AI). Additionally, we provide a pipeline demonstrating this framework, and we evaluate its generative AI components. Our experiments show that our framework's use of AI avoids common issues with generative models. Our framework produces realistic, labeled data. By reducing dependence on costly or restricted data sources, we pave a path towards more accessible and reproducible research.
Authors: Brennen Hill
Abstract: The adaptation of large language models (LLMs) to specialized reasoning tasks is fundamentally constrained by computational resources. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a powerful solution, yet the landscape of these techniques is diverse, with distinct methods operating in either the model's weight space or its representation space. This paper investigates the hypothesis that a synergistic combination of these paradigms can unlock superior performance and efficiency. We introduce HEFT (Hierarchical Efficient Fine-Tuning), a novel hierarchical adaptation strategy that composes two distinct PEFT methods in a coarse-to-fine manner: first, a broad, foundational adaptation in the weight space using Low-Rank Adaptation (LoRA), followed by a precise, surgical refinement of internal activations using Representation Fine-Tuning (ReFT). We evaluate this approach by fine-tuning a Llama-2-7B model on the BoolQ benchmark, a challenging dataset for inferential reasoning. Our results reveal a profound synergistic effect. A model fine-tuned for only three epochs with our HEFT strategy achieves an accuracy of 85.17\%, exceeding the performance of models trained for 20 epochs with either LoRA-only (85.05\%) or ReFT-only (83.36\%) methodologies. This work demonstrates that the thoughtful composition of PEFT methods is a potent algorithmic innovation, offering a more efficient and effective path toward advancing the reasoning capabilities of language models. By achieving superior results with a fraction of the computational budget, our findings present a principled approach to overcoming the obstacles inherent in adapting large-scale models for complex cognitive tasks.
Authors: Tianqi Qiao, Marie Maros
Abstract: We propose and study Sparse Polyak, a variant of Polyak's adaptive step size, designed to solve high-dimensional statistical estimation problems where the problem dimension is allowed to grow much faster than the sample size. In such settings, the standard Polyak step size performs poorly, requiring an increasing number of iterations to achieve optimal statistical precision-even when, the problem remains well conditioned and/or the achievable precision itself does not degrade with problem size. We trace this limitation to a mismatch in how smoothness is measured: in high dimensions, it is no longer effective to estimate the Lipschitz smoothness constant. Instead, it is more appropriate to estimate the smoothness restricted to specific directions relevant to the problem (restricted Lipschitz smoothness constant). Sparse Polyak overcomes this issue by modifying the step size to estimate the restricted Lipschitz smoothness constant. We support our approach with both theoretical analysis and numerical experiments, demonstrating its improved performance.
Authors: Judith Massmann, Alexander Lichtenstein, Francisco M. L\'opez
Abstract: Numerous visual impairments can be detected in red-eye reflex images from young children. The so-called Bruckner test is traditionally performed by ophthalmologists in clinical settings. Thanks to the recent technological advances in smartphones and artificial intelligence, it is now possible to recreate the Bruckner test using a mobile device. In this paper, we present a first study conducted during the development of KidsVisionCheck, a free application that can perform vision screening with a mobile device using red-eye reflex images. The underlying model relies on deep neural networks trained on children's pupil images collected and labeled by an ophthalmologist. With an accuracy of 90% on unseen test data, our model provides highly reliable performance without the necessity of specialist equipment. Furthermore, we can identify the optimal conditions for data collection, which can in turn be used to provide immediate feedback to the users. In summary, this work marks a first step toward accessible pediatric vision screenings and early intervention for vision abnormalities worldwide.
Authors: Tim Broedermannn, Christos Sakaridis, Luigi Piccinelli, Wim Abbeloos, Luc Van Gool
Abstract: Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data uniformly across the spatial extent of the input, which hinders performance when faced with challenging conditions. By contrast, we propose a novel depth-guided multimodal fusion method that upgrades condition-aware fusion by integrating depth information. Our network, DGFusion, poses multimodal segmentation as a multi-task problem, utilizing the lidar measurements, which are typically available in outdoor sensor suites, both as one of the model's inputs and as ground truth for learning depth. Our corresponding auxiliary depth head helps to learn depth-aware features, which are encoded into spatially varying local depth tokens that condition our attentive cross-modal fusion. Together with a global condition token, these local depth tokens dynamically adapt sensor fusion to the spatially varying reliability of each sensor across the scene, which largely depends on depth. In addition, we propose a robust loss for our depth, which is essential for learning from lidar inputs that are typically sparse and noisy in adverse conditions. Our method achieves state-of-the-art panoptic and semantic segmentation performance on the challenging MUSES and DELIVER datasets. Code and models will be available at https://github.com/timbroed/DGFusion
Authors: Marco Pasini, Stefan Lattner, George Fazekas
Abstract: Efficiently representing audio signals in a compressed latent space is critical for latent generative modelling. However, existing autoencoders often force a choice between continuous embeddings and discrete tokens. Furthermore, achieving high compression ratios while maintaining audio fidelity remains a challenge. We introduce CoDiCodec, a novel audio autoencoder that overcomes these limitations by both efficiently encoding global features via summary embeddings, and by producing both compressed continuous embeddings at ~ 11 Hz and discrete tokens at a rate of 2.38 kbps from the same trained model, offering unprecedented flexibility for different downstream generative tasks. This is achieved through Finite Scalar Quantization (FSQ) and a novel FSQ-dropout technique, and does not require additional loss terms beyond the single consistency loss used for end-to-end training. CoDiCodec supports both autoregressive decoding and a novel parallel decoding strategy, with the latter achieving superior audio quality and faster decoding. CoDiCodec outperforms existing continuous and discrete autoencoders at similar bitrates in terms of reconstruction audio quality. Our work enables a unified approach to audio compression, bridging the gap between continuous and discrete generative modelling paradigms.
Authors: Agus Sudjianto, Denis Burakov
Abstract: Credit risk modeling relies extensively on Weight of Evidence (WoE) and Information Value (IV) for feature engineering, and Population Stability Index (PSI) for drift monitoring, yet their theoretical foundations remain disconnected. We establish a unified information-theoretic framework revealing these industry-standard metrics as instances of classical information divergences. Specifically, we prove that IV exactly equals PSI (Jeffreys divergence) computed between good and bad credit outcomes over identical bins. Through the delta method applied to WoE transformations, we derive standard errors for IV and PSI, enabling formal hypothesis testing and probabilistic fairness constraints for the first time. We formalize credit modeling's inherent performance-fairness trade-off as maximizing IV for predictive power while minimizing IV for protected attributes. Using automated binning with depth-1 XGBoost stumps, we compare three encoding strategies: logistic regression with one-hot encoding, WoE transformation, and constrained XGBoost. All methods achieve comparable predictive performance (AUC 0.82-0.84), demonstrating that principled, information-theoretic binning outweighs encoding choice. Mixed-integer programming traces Pareto-efficient solutions along the performance-fairness frontier with uncertainty quantification. This framework bridges theory and practice, providing the first rigorous statistical foundation for widely-used credit risk metrics while offering principled tools for balancing accuracy and fairness in regulated environments.
Authors: Razvan Stefanescu, Ethan Oh, Ruben Vazquez, Chris Mesterharm, Constantin Serban, Ritu Chadha
Abstract: We introduce a multi-modal WAVE-DETR drone detector combining visible RGB and acoustic signals for robust real-life UAV object detection. Our approach fuses visual and acoustic features in a unified object detector model relying on the Deformable DETR and Wav2Vec2 architectures, achieving strong performance under challenging environmental conditions. Our work leverage the existing Drone-vs-Bird dataset and the newly generated ARDrone dataset containing more than 7,500 synchronized images and audio segments. We show how the acoustic information is used to improve the performance of the Deformable DETR object detector on the real ARDrone dataset. We developed, trained and tested four different fusion configurations based on a gated mechanism, linear layer, MLP and cross attention. The Wav2Vec2 acoustic embeddings are fused with the multi resolution feature mappings of the Deformable DETR and enhance the object detection performance over all drones dimensions. The best performer is the gated fusion approach, which improves the mAP of the Deformable DETR object detector on our in-distribution and out-of-distribution ARDrone datasets by 11.1% to 15.3% for small drones across all IoU thresholds between 0.5 and 0.9. The mAP scores for medium and large drones are also enhanced, with overall gains across all drone sizes ranging from 3.27% to 5.84%.
Authors: Sarvan Gill, Daniela Constantinescu
Abstract: Traditional reinforcement learning lacks the ability to provide stability guarantees. More recent algorithms learn Lyapunov functions alongside the control policies to ensure stable learning. However, the current self-learned Lyapunov functions are sample inefficient due to their on-policy nature. This paper introduces a method for learning Lyapunov functions off-policy and incorporates the proposed off-policy Lyapunov function into the Soft Actor Critic and Proximal Policy Optimization algorithms to provide them with a data efficient stability certificate. Simulations of an inverted pendulum and a quadrotor illustrate the improved performance of the two algorithms when endowed with the proposed off-policy Lyapunov function.
Authors: Ya\c{s}ar Utku Al\c{c}alar, Junno Yun, Mehmet Ak\c{c}akaya
Abstract: Diffusion/score-based models have recently emerged as powerful generative priors for solving inverse problems, including accelerated MRI reconstruction. While their flexibility allows decoupling the measurement model from the learned prior, their performance heavily depends on carefully tuned data fidelity weights, especially under fast sampling schedules with few denoising steps. Existing approaches often rely on heuristics or fixed weights, which fail to generalize across varying measurement conditions and irregular timestep schedules. In this work, we propose Zero-shot Adaptive Diffusion Sampling (ZADS), a test-time optimization method that adaptively tunes fidelity weights across arbitrary noise schedules without requiring retraining of the diffusion prior. ZADS treats the denoising process as a fixed unrolled sampler and optimizes fidelity weights in a self-supervised manner using only undersampled measurements. Experiments on the fastMRI knee dataset demonstrate that ZADS consistently outperforms both traditional compressed sensing and recent diffusion-based methods, showcasing its ability to deliver high-fidelity reconstructions across varying noise schedules and acquisition settings.
Authors: Jiayun Wang, Yousuf Aborahama, Arya Khokhar, Yang Zhang, Chuwei Wang, Karteekeya Sastry, Julius Berner, Yilin Luo, Boris Bonev, Zongyi Li, Kamyar Azizzadenesheli, Lihong V. Wang, Anima Anandkumar
Abstract: Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit. While three-dimensional PACT systems enable high-resolution volumetric imaging for applications spanning transcranial to breast imaging, current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation. We introduce Pano (PACT imaging neural operator), an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions. Unlike existing approaches (e.g. universal back-projection algorithm), Pano learns both physics and data priors while also being agnostic to the input data resolution. Pano employs spherical discrete-continuous convolutions to preserve hemispherical sensor geometry, incorporates Helmholtz equation constraints to ensure physical consistency and operates resolutionindependently across varying sensor configurations. We demonstrate the robustness and efficiency of Pano in reconstructing high-quality images from both simulated and real experimental data, achieving consistent performance even with significantly reduced transducer counts and limited-angle acquisition configurations. The framework maintains reconstruction fidelity across diverse sparse sampling patterns while enabling real-time volumetric imaging capabilities. This advancement establishes a practical pathway for making 3D PACT more accessible and feasible for both preclinical research and clinical applications, substantially reducing hardware requirements without compromising image reconstruction quality.
Authors: Myles Joshua Toledo Tan, Maria Kapetanaki, Panayiotis V. Benos
Abstract: Differentiating between the two main subtypes of Inflammatory Bowel Disease (IBD): Crohns disease (CD) and ulcerative colitis (UC) is a persistent clinical challenge due to overlapping presentations. This study introduces a novel computational framework that employs spatial transcriptomics (ST) to create an explainable machine learning model for IBD classification. We analyzed ST data from the colonic mucosa of healthy controls (HC), UC, and CD patients. Using Non-negative Matrix Factorization (NMF), we first identified four recurring cellular niches, representing distinct functional microenvironments within the tissue. From these niches, we systematically engineered 44 features capturing three key aspects of tissue pathology: niche composition, neighborhood enrichment, and niche-gene signals. A multilayer perceptron (MLP) classifier trained on these features achieved an accuracy of 0.774 +/- 0.161 for the more challenging three-class problem (HC, UC, and CD) and 0.916 +/- 0.118 in the two-class problem of distinguishing IBD from healthy tissue. Crucially, model explainability analysis revealed that disruptions in the spatial organization of niches were the strongest predictors of general inflammation, while the classification between UC and CD relied on specific niche-gene expression signatures. This work provides a robust, proof-of-concept pipeline that transforms descriptive spatial data into an accurate and explainable predictive tool, offering not only a potential new diagnostic paradigm but also deeper insights into the distinct biological mechanisms that drive IBD subtypes.
Authors: Mohammadreza Narimani, Alireza Pourreza, Ali Moghimi, Mohsen Mesgaran, Parastoo Farajpoor, Hamid Jafarbiglu
Abstract: This study addresses the escalating threat of branched broomrape (Phelipanche ramosa) to California's tomato industry, which supplies over 90 percent of U.S. processing tomatoes. The parasite's largely underground life cycle makes early detection difficult, while conventional chemical controls are costly, environmentally harmful, and often ineffective. To address this, we combined drone-based multispectral imagery with Long Short-Term Memory (LSTM) deep learning networks, using the Synthetic Minority Over-sampling Technique (SMOTE) to handle class imbalance. Research was conducted on a known broomrape-infested tomato farm in Woodland, Yolo County, CA, across five key growth stages determined by growing degree days (GDD). Multispectral images were processed to isolate tomato canopy reflectance. At 897 GDD, broomrape could be detected with 79.09 percent overall accuracy and 70.36 percent recall without integrating later stages. Incorporating sequential growth stages with LSTM improved detection substantially. The best-performing scenario, which integrated all growth stages with SMOTE augmentation, achieved 88.37 percent overall accuracy and 95.37 percent recall. These results demonstrate the strong potential of temporal multispectral analysis and LSTM networks for early broomrape detection. While further real-world data collection is needed for practical deployment, this study shows that UAV-based multispectral sensing coupled with deep learning could provide a powerful precision agriculture tool to reduce losses and improve sustainability in tomato production.
Authors: Peter Vieting, Benedikt Hilmes, Ralf Schl\"uter, Hermann Ney
Abstract: Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain heavily influenced by classical methods. While this inductive bias may ease the system design, our work aims to develop a more generic front-end for feature extraction. Furthermore, we seek to unify the front-end architecture contrasting with existing approaches that apply a composition of several layer topologies originating from different sources. The experiments systematically show how to reduce the influence of existing techniques to achieve a generic front-end. The resulting 2D convolutional front-end is parameter-efficient and suitable for a scenario with limited computational resources unlike large models pre-trained on unlabeled audio. The results demonstrate that this generic unified approach is not only feasible but also matches the performance of existing supervised learnable feature extractors.
Authors: Jakub Mojsiejuk, S{\l}awomir Zi\k{e}tek, Witold Skowro\'nski
Abstract: We address the problem of automatic synchronisation of the spintronic oscillator (STO) by means of reinforcement learning (RL). A numerical solution of the macrospin Landau-Lifschitz-Gilbert-Slonczewski equation is used to simulate the STO and we train the two types of RL agents to synchronise with a target frequency within a fixed number of steps. We explore modifications to this base task and show an improvement in both convergence and energy efficiency of the synchronisation that can be easily achieved in the simulated environment.
Authors: Christos Sgouropoulos, Christos Nikou, Stefanos Vlachos, Vasileios Theiou, Christos Foukanelis, Theodoros Giannakopoulos
Abstract: Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image domain, few-shot learning in audio classification remains relatively underexplored. In this work, we investigate the effect of integrating supervised contrastive loss into prototypical few shot training for audio classification. In detail, we demonstrate that angular loss further improves the performance compared to the standard contrastive loss. Our method leverages SpecAugment followed by a self-attention mechanism to encapsulate diverse information of augmented input versions into one unified embedding. We evaluate our approach on MetaAudio, a benchmark including five datasets with predefined splits, standardized preprocessing, and a comprehensive set of few-shot learning models for comparison. The proposed approach achieves state-of-the-art performance in a 5-way, 5-shot setting.
Authors: Simen Storesund, Kristian Valset Aars, Robin Dietrich, Nicolai Waniek
Abstract: Efficient planning and sequence selection are central to intelligence, yet current approaches remain largely incompatible with biological computation. Classical graph algorithms like Dijkstra's or A* require global state and biologically implausible operations such as backtracing, while reinforcement learning methods rely on slow gradient-based policy updates that appear inconsistent with rapid behavioral adaptation observed in natural systems. We propose a biologically plausible algorithm for shortest-path computation that operates through local spike-based message-passing with realistic processing delays. The algorithm exploits spike-timing coincidences to identify nodes on optimal paths: Neurons that receive inhibitory-excitatory message pairs earlier than predicted reduce their response delays, creating a temporal compression that propagates backwards from target to source. Through analytical proof and simulations on random spatial networks, we demonstrate that the algorithm converges and discovers all shortest paths using purely timing-based mechanisms. By showing how short-term timing dynamics alone can compute shortest paths, this work provides new insights into how biological networks might solve complex computational problems through purely local computation and relative spike-time prediction. These findings open new directions for understanding distributed computation in biological and artificial systems, with possible implications for computational neuroscience, AI, reinforcement learning, and neuromorphic systems.
Authors: Weitao Tang, Johann Vargas-Calixto, Nasim Katebi, Nhi Tran, Sharmony B. Kelly, Gari D. Clifford, Robert Galinsky, Faezeh Marzbanrad
Abstract: Introduction: This study presents FetalSleepNet, the first published deep learning approach to classifying sleep states from the ovine electroencephalogram (EEG). Fetal EEG is complex to acquire and difficult and laborious to interpret consistently. However, accurate sleep stage classification may aid in the early detection of abnormal brain maturation associated with pregnancy complications (e.g. hypoxia or intrauterine growth restriction). Methods: EEG electrodes were secured onto the ovine dura over the parietal cortices of 24 late gestation fetal sheep. A lightweight deep neural network originally developed for adult EEG sleep staging was trained on the ovine EEG using transfer learning from adult EEG. A spectral equalisation-based domain adaptation strategy was used to reduce cross-domain mismatch. Results: We demonstrated that while direct transfer performed poorly, full fine tuning combined with spectral equalisation achieved the best overall performance (accuracy: 86.6 percent, macro F1-score: 62.5), outperforming baseline models. Conclusions: To the best of our knowledge, FetalSleepNet is the first deep learning framework specifically developed for automated sleep staging from the fetal EEG. Beyond the laboratory, the EEG-based sleep stage classifier functions as a label engine, enabling large scale weak/semi supervised labeling and distillation to facilitate training on less invasive signals that can be acquired in the clinic, such as Doppler Ultrasound or electrocardiogram data. FetalSleepNet's lightweight design makes it well suited for deployment in low power, real time, and wearable fetal monitoring systems.
Authors: Zhengyu Hu, Zheyuan Xiao, Max Xiong, Yuxuan Lei, Tianfu Wang, Jianxun Lian, Kaize Ding, Ziang Xiao, Nicholas Jing Yuan, Xing Xie
Abstract: Recent advances in large language models (LLMs) have enabled human-like social simulations at unprecedented scale and fidelity, offering new opportunities for computational social science. A key challenge, however, is the construction of persona sets that authentically represent the diversity and distribution of real-world populations. Most existing LLM-based social simulation studies focus primarily on designing agentic frameworks and simulation environments, often overlooking the complexities of persona generation and the potential biases introduced by unrepresentative persona sets. In this paper, we propose a systematic framework for synthesizing high-quality, population-aligned persona sets for LLM-driven social simulation. Our approach begins by leveraging LLMs to generate narrative personas from long-term social media data, followed by rigorous quality assessment to filter out low-fidelity profiles. We then apply importance sampling to achieve global alignment with reference psychometric distributions, such as the Big Five personality traits. To address the needs of specific simulation contexts, we further introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations. Extensive experiments demonstrate that our method significantly reduces population-level bias and enables accurate, flexible social simulation for a wide range of research and policy applications.
Authors: Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schl\"uter, Reinhold Haeb-Umbach
Abstract: Meeting transcription is a field of high relevance and remarkable progress in recent years. Still, challenges remain that limit its performance. In this work, we extend a previously proposed framework for analyzing leakage in speech separation with proper sensitivity to temporal locality. We show that there is significant leakage to the cross channel in areas where only the primary speaker is active. At the same time, the results demonstrate that this does not affect the final performance much as these leaked parts are largely ignored by the voice activity detection (VAD). Furthermore, different segmentations are compared showing that advanced diarization approaches are able to reduce the gap to oracle segmentation by a third compared to a simple energy-based VAD. We additionally reveal what factors contribute to the remaining difference. The results represent state-of-the-art performance on LibriCSS among systems that train the recognition module on LibriSpeech data only.
Authors: Vladimir Petrovic, R\'emi Bardenet, Agn\`es Desolneux
Abstract: In this paper, we consider the problem of computing the integral of a function on the unit sphere, in any dimension, using Monte Carlo methods. Although the methods we present are general, our guiding thread is the sliced Wasserstein distance between two measures on $\mathbb{R}^d$, which is precisely an integral on the $d$-dimensional sphere. The sliced Wasserstein distance (SW) has gained momentum in machine learning either as a proxy to the less computationally tractable Wasserstein distance, or as a distance in its own right, due in particular to its built-in alleviation of the curse of dimensionality. There has been recent numerical benchmarks of quadratures for the sliced Wasserstein, and our viewpoint differs in that we concentrate on quadratures where the nodes are repulsive, i.e. negatively dependent. Indeed, negative dependence can bring variance reduction when the quadrature is adapted to the integration task. Our first contribution is to extract and motivate quadratures from the recent literature on determinantal point processes (DPPs) and repelled point processes, as well as repulsive quadratures from the literature specific to the sliced Wasserstein distance. We then numerically benchmark these quadratures. Moreover, we analyze the variance of the UnifOrtho estimator, an orthogonal Monte Carlo estimator. Our analysis sheds light on UnifOrtho's success for the estimation of the sliced Wasserstein in large dimensions, as well as counterexamples from the literature. Our final recommendation for the computation of the sliced Wasserstein distance is to use randomized quasi-Monte Carlo in low dimensions and \emph{UnifOrtho} in large dimensions. DPP-based quadratures only shine when quasi-Monte Carlo also does, while repelled quadratures show moderate variance reduction in general, but more theoretical effort is needed to make them robust.
Authors: Federica Uccello, Simin Nadjm-Tehrani
Abstract: With the rise of fifth-generation (5G) networks in critical applications, it is urgent to move from detection of malicious activity to systems capable of providing a reliable verdict suitable for mitigation. In this regard, understanding and interpreting machine learning (ML) models' security alerts is crucial for enabling actionable incident response orchestration. Explainable Artificial Intelligence (XAI) techniques are expected to enhance trust by providing insights into why alerts are raised. A dominant approach statistically associates feature sets that can be correlated to a given alert. This paper starts by questioning whether such attribution is relevant for future generation communication systems, and investigates its merits in comparison with an approach based on logical explanations. We extensively study two methods, SHAP and VoTE-XAI, by analyzing their interpretations of alerts generated by an XGBoost model in three different use cases with several 5G communication attacks. We identify three metrics for assessing explanations: sparsity, how concise they are; stability, how consistent they are across samples from the same attack type; and efficiency, how fast an explanation is generated. As an example, in a 5G network with 92 features, 6 were deemed important by VoTE-XAI for a Denial of Service (DoS) variant, ICMPFlood, while SHAP identified over 20. More importantly, we found a significant divergence between features selected by SHAP and VoTE-XAI. However, none of the top-ranked features selected by SHAP were missed by VoTE-XAI. When it comes to efficiency of providing interpretations, we found that VoTE-XAI is significantly more responsive, e.g. it provides a single explanation in under 0.002 seconds, in a high-dimensional setting (478 features).
Authors: Noga H. Rotman, Tiago Ferreira, Hila Peleg, Mark Silberstein, Alexandra Silva
Abstract: Requests for Comments (RFCs) are extensive specification documents for network protocols, but their prose-based format and their considerable length often impede precise operational understanding. We present RFSeek, an interactive tool that automatically extracts visual summaries of protocol logic from RFCs. RFSeek leverages large language models (LLMs) to generate provenance-linked, explorable diagrams, surfacing both official state machines and additional logic found only in the RFC text. Compared to existing RFC visualizations, RFSeek's visual summaries are more transparent and easier to audit against their textual source. We showcase the tool's potential through a series of use cases, including guided knowledge extraction and semantic diffing, applied to protocols such as TCP, QUIC, PPTP, and DCCP. In practice, RFSeek not only reconstructs the RFC diagrams included in some specifications, but, more interestingly, also uncovers important logic such as nodes or edges described in the text but missing from those diagrams. RFSeek further derives new visualization diagrams for complex RFCs, with QUIC as a representative case. Our approach, which we term \emph{Summary Visualization}, highlights a promising direction: combining LLMs with formal, user-customized visualizations to enhance protocol comprehension and support robust implementations.
Authors: Irina Ar\'evalo, Jose L Salmeron
Abstract: Recommender systems often benefit from complex feature embeddings and deep learning algorithms, which deliver sophisticated recommendations that enhance user experience, engagement, and revenue. However, these methods frequently reduce the interpretability and transparency of the system. In this research, we develop a systematic application, adaptation, and evaluation of deletion diagnostics in the recommender setting. The method compares the performance of a model to that of a similar model trained without a specific user or item, allowing us to quantify how that observation influences the recommender, either positively or negatively. To demonstrate its model-agnostic nature, the proposal is applied to both Neural Collaborative Filtering (NCF), a widely used deep learning-based recommender, and Singular Value Decomposition (SVD), a classical collaborative filtering technique. Experiments on the MovieLens and Amazon Reviews datasets provide insights into model behavior and highlight the generality of the approach across different recommendation paradigms.
Authors: Pavel Plyusnin, Aleksey Antonov, Vasilii Ermakov, Aleksandr Khaybriev, Margarita Kikot, Ilseyar Alimova, Stanislav Moiseev
Abstract: In modern software development change-based testing plays a crucial role. However, as codebases expand and test suites grow, efficiently managing the testing process becomes increasingly challenging, especially given the high frequency of daily code commits. We propose Targeted Test Selection (T-TS), a machine learning approach for industrial test selection. Our key innovation is a data representation that represent commits as Bags-of-Words of changed files, incorporates cross-file and additional predictive features, and notably avoids the use of coverage maps. Deployed in production, T-TS was comprehensively evaluated against industry standards and recent methods using both internal and public datasets, measuring time efficiency and fault detection. On live industrial data, T-TS selects only 15% of tests, reduces execution time by $5.9\times$, accelerates the pipeline by $5.6\times$, and detects over 95% of test failures. The implementation is publicly available to support further research and practical adoption.
Authors: Gang Li, Tianjiao Chen, Mingle Zhou, Min Li, Delong Han, Jin Wan
Abstract: Zero-shot 3D (ZS-3D) anomaly detection aims to identify defects in 3D objects without relying on labeled training data, making it especially valuable in scenarios constrained by data scarcity, privacy, or high annotation cost. However, most existing methods focus exclusively on point clouds, neglecting the rich semantic cues available from complementary modalities such as RGB images and texts priors. This paper introduces MCL-AD, a novel framework that leverages multimodal collaboration learning across point clouds, RGB images, and texts semantics to achieve superior zero-shot 3D anomaly detection. Specifically, we propose a Multimodal Prompt Learning Mechanism (MPLM) that enhances the intra-modal representation capability and inter-modal collaborative learning by introducing an object-agnostic decoupled text prompt and a multimodal contrastive loss. In addition, a collaborative modulation mechanism (CMM) is proposed to fully leverage the complementary representations of point clouds and RGB images by jointly modulating the RGB image-guided and point cloud-guided branches. Extensive experiments demonstrate that the proposed MCL-AD framework achieves state-of-the-art performance in ZS-3D anomaly detection.
Authors: Elizaveta D. Moskovskaya, Anton D. Moscowsky
Abstract: The work describes the development of a hybrid control architecture for an anthropomorphic tour guide robot, combining a multi-agent resource management system with automatic behavior scenario generation based on large language models. The proposed approach aims to overcome the limitations of traditional systems, which rely on manual tuning of behavior scenarios. These limitations include manual configuration, low flexibility, and lack of naturalness in robot behavior. The process of preparing tour scenarios is implemented through a two-stage generation: first, a stylized narrative is created, then non-verbal action tags are integrated into the text. The multi-agent system ensures coordination and conflict resolution during the execution of parallel actions, as well as maintaining default behavior after the completion of main operations, contributing to more natural robot behavior. The results obtained from the trial demonstrate the potential of the proposed approach for automating and scaling social robot control systems.
Authors: Jordan Sassoon, Michal Szczepanski, Martyna Poreba
Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost. Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision, as quantization errors accumulate across deep encoder-decoder pipelines. We introduce I-Segmenter, the first fully integer-only ViT segmentation framework. Building on the Segmenter architecture, I-Segmenter systematically replaces floating-point operations with integer-only counterparts. To further stabilize both training and inference, we propose $\lambda$-ShiftGELU, a novel activation function that mitigates the limitations of uniform quantization in handling long-tailed activation distributions. In addition, we remove the L2 normalization layer and replace bilinear interpolation in the decoder with nearest neighbor upsampling, ensuring integer-only execution throughout the computational graph. Extensive experiments show that I-Segmenter achieves accuracy within a reasonable margin of its FP32 baseline (5.1 % on average), while reducing model size by up to 3.8x and enabling up to 1.2x faster inference with optimized runtimes. Notably, even in one-shot PTQ with a single calibration image, I-Segmenter delivers competitive accuracy, underscoring its practicality for real-world deployment.
Authors: Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar
Abstract: Graph Neural Networks (GNNs) are widely used in learning on graph-structured data, yet a principled understanding of why they succeed or fail remains elusive. While prior works have examined architectural limitations such as over-smoothing and over-squashing, these do not explain what enables GNNs to extract meaningful representations or why performance varies drastically between similar architectures. These questions are related to the role of generalisation: the ability of a model to make accurate predictions on unlabelled data. Although several works have derived generalisation error bounds for GNNs, these are typically loose, restricted to a single architecture, and offer limited insight into what governs generalisation in practice. In this work, we take a different approach by deriving the exact generalisation error for GNNs in a transductive fixed-design setting through the lens of signal processing. From this viewpoint, GNNs can be interpreted as graph filter operators that act on node features via the graph structure. By focusing on linear GNNs while allowing non-linearity in the graph filters, we derive the first exact generalisation error for a broad range of GNNs, including convolutional, PageRank-based, and attention-based models. The exact characterisation of the generalisation error reveals that only the aligned information between node features and graph structure contributes to generalisation. Furthermore, we quantify the effect of homophily on generalisation. Our work provides a framework that explains when and why GNNs can effectively leverage structural and feature information, offering practical guidance for model selection.
Authors: Yuexi Du, Lihui Chen, Nicha C. Dvornek
Abstract: Mammography screening is an essential tool for early detection of breast cancer. The speed and accuracy of mammography interpretation have the potential to be improved with deep learning methods. However, the development of a foundation visual language model (VLM) is hindered by limited data and domain differences between natural and medical images. Existing mammography VLMs, adapted from natural images, often ignore domain-specific characteristics, such as multi-view relationships in mammography. Unlike radiologists who analyze both views together to process ipsilateral correspondence, current methods treat them as independent images or do not properly model the multi-view correspondence learning, losing critical geometric context and resulting in suboptimal prediction. We propose GLAM: Global and Local Alignment for Multi-view mammography for VLM pretraining using geometry guidance. By leveraging the prior knowledge about the multi-view imaging process of mammograms, our model learns local cross-view alignments and fine-grained local features through joint global and local, visual-visual, and visual-language contrastive learning. Pretrained on EMBED [14], one of the largest open mammography datasets, our model outperforms baselines across multiple datasets under different settings.
Authors: Yehudit Aperstein, Amit Tzahar, Alon Gottlib, Tal Verber, Ravit Shagan Damti, Alexander Apartsin
Abstract: Overconfidence in deep learning models poses a significant risk in high-stakes medical imaging tasks, particularly in multi-label classification of chest X-rays, where multiple co-occurring pathologies must be detected simultaneously. This study introduces an uncertainty-aware framework for chest X-ray diagnosis based on a DenseNet-121 backbone, enhanced with two selective prediction mechanisms: entropy-based rejection and confidence interval-based rejection. Both methods enable the model to abstain from uncertain predictions, improving reliability by deferring ambiguous cases to clinical experts. A quantile-based calibration procedure is employed to tune rejection thresholds using either global or class-specific strategies. Experiments conducted on three large public datasets (PadChest, NIH ChestX-ray14, and MIMIC-CXR) demonstrate that selective rejection improves the trade-off between diagnostic accuracy and coverage, with entropy-based rejection yielding the highest average AUC across all pathologies. These results support the integration of selective prediction into AI-assisted diagnostic workflows, providing a practical step toward safer, uncertainty-aware deployment of deep learning in clinical settings.
Authors: Seokjin Go, Joongun Park, Spandan More, Hanjiang Wu, Irene Wang, Aaron Jezghani, Tushar Krishna, Divya Mahajan
Abstract: The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper, we present a comprehensive characterization of LLM training across diverse real-world workloads and hardware platforms, including NVIDIA H100/H200 and AMD MI250 GPUs. We analyze dense and sparse models under various parallelism strategies -- tensor, pipeline, data, and expert -- and evaluate their effects on hardware utilization, power consumption, and thermal behavior. We further evaluate the effectiveness of optimizations such as activation recomputation and compute-communication overlap. Our findings show that performance is not determined solely by scaling hardware capacity. Scale-up systems with fewer, higher-memory GPUs can outperform scale-out systems in communication-bound regimes, but only under carefully tuned configurations; in other cases, scale-out deployments achieve superior throughput. We also show that certain parallelism combinations, such as tensor with pipeline, lead to bandwidth underutilization due to inefficient data chunking, while increasing microbatch sizes beyond a certain point induces bursty execution and peak power excursions that worsen thermal throttling. These insights reveal how training performance is shaped by complex interactions between hardware, system topology, and model execution. We conclude by offering recommendations for system and hardware design to improve the scalability and reliability of future LLM systems and workloads. The source code of this project is available at https://github.com/sitar-lab/CharLLM-PPT.
Authors: Yixuan Sun, Srinivas Eswar, Yin Lin, William Detmold, Phiala Shanahan, Xiaoye Li, Yang Liu, Prasanna Balaprakash
Abstract: Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics~(QCD). Solving the Hermitian positive definite systems, which are sparse but ill-conditioned, involves using iterative methods, such as Conjugate Gradient (CG), which are time-consuming and computationally expensive. Preconditioners can effectively accelerate this process, with the state-of-the-art being multigrid preconditioners. However, constructing useful preconditioners can be challenging, adding additional computational overhead, especially in large linear systems. We propose a framework, leveraging operator learning techniques, to construct linear maps as effective preconditioners. The method in this work does not rely on explicit matrices from either the original linear systems or the produced preconditioners, allowing efficient model training and application in the CG solver. In the context of the Schwinger model U(1) gauge theory in 1+1 spacetime dimensions with two degenerate-mass fermions), this preconditioning scheme effectively decreases the condition number of the linear systems and approximately halves the number of iterations required for convergence in relevant parameter ranges. We further demonstrate the framework learns a general mapping dependent on the lattice structure which leads to zero-shot learning ability for the Dirac operators constructed from gauge field configurations of different sizes.
Authors: Utsab Saha, Tanvir Muntakim Tonoy, Hafiz Imtiaz
Abstract: In this work, we explore differentially private synthetic data generation in a decentralized-data setting by building on the recently proposed Differentially Private Class-Centric Data Aggregation (DP-CDA). DP-CDA synthesizes data in a centralized setting by mixing multiple randomly-selected samples from the same class and injecting carefully calibrated Gaussian noise, ensuring ({\epsilon}, {\delta})-differential privacy. When deployed in a decentralized or federated setting, where each client holds only a small partition of the data, DP-CDA faces new challenges. The limited sample size per client increases the sensitivity of local computations, requiring higher noise injection to maintain the differential privacy guarantee. This, in turn, leads to a noticeable degradation in the utility compared to the centralized setting. To mitigate this issue, we integrate the Correlation-Assisted Private Estimation (CAPE) protocol into the federated DP-CDA framework and propose CAPE Assisted Federated DP-CDA algorithm. CAPE enables limited collaboration among the clients by allowing them to generate jointly distributed (anti-correlated) noise that cancels out in aggregate, while preserving privacy at the individual level. This technique significantly improves the privacy-utility trade-off in the federated setting. Extensive experiments on MNIST and FashionMNIST datasets demonstrate that the proposed CAPE Assisted Federated DP-CDA approach can achieve utility comparable to its centralized counterpart under some parameter regime, while maintaining rigorous differential privacy guarantees.
Authors: Adrian de Wynter
Abstract: In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without needing further training. This has led to claims about these model's ability to solve (learn) unseen tasks with only a few shots (exemplars) in the prompt. However, deduction does not always imply learning, as ICL does not explicitly encode a given observation. Instead, the models rely on their prior knowledge and the exemplars given, if any. We argue that, mathematically, ICL does constitute learning, but its full characterisation requires empirical work. We then carry out a large-scale analysis of ICL ablating out or accounting for memorisation, pretraining, distributional shifts, and prompting style and phrasing. We find that ICL is an effective learning paradigm, but limited in its ability to learn and generalise to unseen tasks. We note that, in the limit where exemplars become more numerous, accuracy is insensitive to exemplar distribution, model, prompt style, and the input's linguistic features. Instead, it deduces patterns from regularities in the prompt, which leads to distributional sensitivity, especially in prompting styles such as chain-of-thought. Given the varied accuracies on formally similar tasks, we conclude that autoregression's ad-hoc encoding is not a robust mechanism, and suggests limited all-purpose generalisability.
Authors: Cameron Reid, Wael Hafez, Amirhossein Nazeri
Abstract: Reinforcement Learning (RL) agents deployed in real-world environments face degradation from sensor faults, actuator wear, and environmental shifts, yet lack intrinsic mechanisms to detect and diagnose these failures. We present an information-theoretic framework that reveals both the fundamental dynamics of RL and provides practical methods for diagnosing deployment-time anomalies. Through analysis of state-action mutual information patterns in a robotic control task, we first demonstrate that successful learning exhibits characteristic information signatures: mutual information between states and actions steadily increases from 0.84 to 2.83 bits (238% growth) despite growing state entropy, indicating that agents develop increasingly selective attention to task-relevant patterns. Intriguingly, states, actions and next states joint mutual information, MI(S,A;S'), follows an inverted U-curve, peaking during early learning before declining as the agent specializes suggesting a transition from broad exploration to efficient exploitation. More immediately actionable, we show that information metrics can differentially diagnose system failures: observation-space, i.e., states noise (sensor faults) produces broad collapses across all information channels with pronounced drops in state-action coupling, while action-space noise (actuator faults) selectively disrupts action-outcome predictability while preserving state-action relationships. This differential diagnostic capability demonstrated through controlled perturbation experiments enables precise fault localization without architectural modifications or performance degradation. By establishing information patterns as both signatures of learning and diagnostic for system health, we provide the foundation for adaptive RL systems capable of autonomous fault detection and policy adjustment based on information-theoretic principles.
Authors: Akshat Pandey, Karun Kumar, Raphael Tang
Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen vocabulary and parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder-decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encoder is restored, incurring no extra runtime cost. Across four out-of-domain datasets and four ASR models, WhisTLE with TTS reduces word error rate (WER) by 12.3% relative to TTS-only adaptation and outperforms all non-WhisTLE baselines in 27 of 32 scenarios.
Authors: Emily Kaczmarek, Justin Szeto, Brennan Nichyporuk, Tal Arbel
Abstract: Alzheimer's disease is a progressive, neurodegenerative disorder that causes memory loss and cognitive decline. While there has been extensive research in applying deep learning models to Alzheimer's prediction tasks, these models remain limited by lack of available labeled data, poor generalization across datasets, and inflexibility to varying numbers of input scans and time intervals between scans. In this study, we adapt three state-of-the-art temporal self-supervised learning (SSL) approaches for 3D brain MRI analysis, and add novel extensions designed to handle variable-length inputs and learn robust spatial features. We aggregate four publicly available datasets comprising 3,161 patients for pre-training, and show the performance of our model across multiple Alzheimer's prediction tasks including diagnosis classification, conversion detection, and future conversion prediction. Importantly, our SSL model implemented with temporal order prediction and contrastive learning outperforms supervised learning on six out of seven downstream tasks. It demonstrates adaptability and generalizability across tasks and number of input images with varying time intervals, highlighting its capacity for robust performance across clinical applications. We release our code and model publicly at https://github.com/emilykaczmarek/SSL-AD.
Authors: Taero Kim, Subeen Park, Sungjun Lim, Yonghan Jung, Krikamol Muandet, Kyungwoo Song
Abstract: Learning robust models under distribution shifts between training and test datasets is a fundamental challenge in machine learning. While learning invariant features across environments is a popular approach, it often assumes that these features are fully observed in both training and test sets, a condition frequently violated in practice. When models rely on invariant features absent in the test set, their robustness in new environments can deteriorate. To tackle this problem, we introduce a novel learning principle called the Sufficient Invariant Learning (SIL) framework, which focuses on learning a sufficient subset of invariant features rather than relying on a single feature. After demonstrating the limitation of existing invariant learning methods, we propose a new algorithm, Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO), to learn diverse invariant features by seeking common flat minima across the environments. We theoretically demonstrate that finding a common flat minima enables robust predictions based on diverse invariant features. Empirical evaluations on multiple datasets, including our new benchmark, confirm ASGDRO's robustness against distribution shifts, highlighting the limitations of existing methods.
Authors: Prathyusha Devabhakthini, Sasmita Parida, Raj Mani Shukla, Suvendu Chandan Nayak, Tapadhir Das
Abstract: Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in applications such as autonomous vehicles, medical diagnosis, and security systems. Work on the vulnerability of deep learning models to adversarial attacks has shown that it is very easy to make samples that make a model predict things that it doesn't want to. In this work, we analyze the impact of model interpretability due to adversarial attacks on text classification problems. We develop an ML-based classification model for text data. Then, we introduce the adversarial perturbations on the text data to understand the classification performance after the attack. Subsequently, we analyze and interpret the model's explainability before and after the attack
Authors: Tong Chen, Raghavendra Selvan
Abstract: Dataset Condensation (DC) refers to the recent class of dataset compression methods that generate a smaller, synthetic, dataset from a larger dataset. This synthetic dataset aims to retain the essential information of the original dataset, enabling models trained on it to achieve performance levels comparable to those trained on the full dataset. Most current DC methods have mainly concerned with achieving high test performance with limited data budget, and have not directly addressed the question of adversarial robustness. In this work, we investigate the impact of adversarial robustness on models trained with compressed datasets. We show that the compressed datasets obtained from DC methods are not effective in transferring adversarial robustness to models. As a solution to improve dataset compression efficiency and adversarial robustness simultaneously, we present a robustness-aware dataset compression method based on finding the Minimal Finite Covering (MFC) of the dataset. The proposed method is (1) provably robust by minimizing the generalized adversarial loss, (2) more effective than DC methods when applying adversarial training over MFC, (3) obtained by a one-time computation and is applicable for any model.
Authors: Teresa Salazar, Jo\~ao Gama, Helder Ara\'ujo, Pedro Henriques Abreu
Abstract: In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model's decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time while another does not, leading to a decrease in fairness even if accuracy remains fairly stable. Within the framework of Federated Learning, where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. Additionally, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift which uses a multi-model approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.
Authors: Davide Frizzo, Francesco Borsatti, Alessio Arcudi, Antonio De Moliner, Roberto Oboe, Gian Antonio Susto
Abstract: Anomaly Detection (AD) is crucial in industrial settings to streamline operations by detecting underlying issues. Conventional methods merely label observations as normal or anomalous, lacking crucial insights. In Industry 5.0, interpretable outcomes become desirable to enable users to understand the rational under model decisions. This paper presents the first industrial application of ExIFFI, a recent approach for fast, efficient explanations for the Extended Isolation Forest (EIF) (AD) method. ExIFFI is tested on three industrial datasets, demonstrating superior explanation effectiveness and computational efficiency compared to other state-of-the-art explainable AD models.
Authors: Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer, Andreas Bulling
Abstract: We introduce the Overcooked Generalisation Challenge (OGC) - a new benchmark for evaluating reinforcement learning (RL) agents on their ability to cooperate with unknown partners in unfamiliar environments. Existing work typically evaluated cooperative RL only in their training environment or with their training partners, thus seriously limiting our ability to understand agents' generalisation capacity - an essential requirement for future collaboration with humans. The OGC extends Overcooked-AI to support dual curriculum design (DCD). It is fully GPU-accelerated, open-source, and integrated into the minimax DCD benchmark suite. Compared to prior DCD benchmarks, where designers manipulate only minimal elements of the environment, OGC introduces a significantly richer design space: full kitchen layouts with multiple objects that require the designer to account for interaction dynamics between agents. We evaluate state-of-the-art DCD algorithms alongside scalable neural architectures and find that current methods fail to produce agents that generalise effectively to novel layouts and unfamiliar partners. Our results indicate that both agents and curriculum designers struggle with the joint challenge of partner and environment generalisation. These findings establish OGC as a demanding testbed for cooperative generalisation and highlight key directions for future research. We open-source our code.
Authors: Richard Bergna, Sergio Calvo-Ordo\~nez, Felix L. Opolka, Pietro Li\`o, Jose Miguel Hernandez-Lobato
Abstract: We propose a novel Stochastic Differential Equation (SDE) framework to address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODEs) have shown promise in learning node representations, they lack the ability to quantify uncertainty. To address this, we introduce Latent Graph Neural Stochastic Differential Equations (LGNSDE), which enhance GNODE by embedding randomness through a Bayesian prior-posterior mechanism for epistemic uncertainty and Brownian motion for aleatoric uncertainty. By leveraging the existence and uniqueness of solutions to graph-based SDEs, we prove that the variance of the latent space bounds the variance of model outputs, thereby providing theoretically sensible guarantees for the uncertainty estimates. Furthermore, we show mathematically that LGNSDEs are robust to small perturbations in the input, maintaining stability over time. Empirical results across several benchmarks demonstrate that our framework is competitive in out-of-distribution detection, robustness to noise, and active learning, underscoring the ability of LGNSDEs to quantify uncertainty reliably. Code is available at \href{https://github.com/Richard-Bergna/GraphNeuralSDE}{\texttt{github.com/Richard-Bergna/GraphNeuralSDE}}.
Authors: Quinten Van Baelen, Peter Karsmakers
Abstract: Deploying neural networks on the edge has become increasingly important as deep learning is being applied in an increasing amount of applications. At the edge computing hardware typically has limited resources disallowing to run neural networks with high complexity. To reduce the complexity of neural networks a wide range of quantization methods have been proposed in recent years. This work proposes Constraint Guided Model Quantization (CGMQ), which is a quantization aware training algorithm that uses an upper bound on the computational resources and reduces the bit-widths of the parameters of the neural network. CGMQ does not require the tuning of a hyperparameter to result in a mixed precision neural network that satisfies the predefined computational cost constraint, while prior work does. It is shown on MNIST and CIFAR10 that the performance of CGMQ is competitive with state-of-the-art quantization aware training algorithms, while guaranteeing the satisfaction of an upper bound on the computational complexity defined by the computational resources of the on edge hardware.
Authors: Teresa Salazar, Helder Ara\'ujo, Alberto Cano, Pedro Henriques Abreu
Abstract: Group fairness in machine learning is an important area of research focused on achieving equitable outcomes across different groups defined by sensitive attributes such as race or gender. Federated Learning, a decentralized approach to training machine learning models across multiple clients, amplifies the need for fairness methodologies due to its inherent heterogeneous data distributions that can exacerbate biases. The intersection of Federated Learning and group fairness has attracted significant interest, with 48 research works specifically dedicated to addressing this issue. However, no comprehensive survey has specifically focused on group fairness in Federated Learning. In this work, we analyze the key challenges of this topic, propose practices for its identification and benchmarking, and create a novel taxonomy based on criteria such as data partitioning, location, and strategy. Furthermore, we analyze broader concerns, review how different approaches handle the complexities of various sensitive attributes, examine common datasets and applications, and discuss the ethical, legal, and policy implications of group fairness in FL. We conclude by highlighting key areas for future research, emphasizing the need for more methods to address the complexities of achieving group fairness in federated systems.
Authors: Patrick Gillespie, Layal Bou Hamdan, Ioannis Schizas, David L. Boothe, Vasileios Maroulas
Abstract: Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph data. The most flexible approach to constructing the sheaf is to learn it as part of the network as a function of the node features. However, this leaves the network potentially overly sensitive to the learned sheaf. As a counter-measure, we propose a variational approach to learning cellular sheaves within sheaf neural networks, yielding an architecture we refer to as a Bayesian sheaf neural network. As part of this work, we define a novel family of reparameterizable probability distributions on the rotation group $SO(n)$ using the Cayley transform. We evaluate the Bayesian sheaf neural network on several graph datasets, and show that our Bayesian sheaf models achieve leading performance compared to baseline models and are less sensitive to the choice of hyperparameters under limited training data settings.
Authors: Vansh Nagpal, Siva Likitha Valluru, Kausik Lakkaraju, Nitin Gupta, Zach Abdulrahman, Andrew Davison, Biplav Srivastava
Abstract: A common decision made by people, whether healthy or with health conditions, is choosing meals like breakfast, lunch, and dinner, comprising combinations of foods for appetizer, main course, side dishes, desserts, and beverages. Often, this decision involves tradeoffs between nutritious choices (e.g., salt and sugar levels, nutrition content) and convenience (e.g., cost and accessibility, cuisine type, food source type). We present a data-driven solution for meal recommendations that considers customizable meal configurations and time horizons. This solution balances user preferences while accounting for food constituents and cooking processes. Our contributions include introducing goodness measures, a recipe conversion method from text to the recently introduced multimodal rich recipe representation (R3) format, learning methods using contextual bandits that show promising preliminary results, and the prototype, usage-inspired, BEACON system.
Authors: Zahraa Al Sahili, Ioannis Patras, Matthew Purver
Abstract: Vision-language models (VLMs) deliver strong zero-shot recognition but frequently inherit social biases from their training data. We systematically disentangle three design factors -- model size, training-data scale, and training-data source -- by comparing CLIP and OpenCLIP, two models that share an identical contrastive objective yet differ in encoder width and in the image-text corpora on which they are pre-trained (400M proprietary pairs vs. 400M/2B LAION). Across balanced face-analysis benchmarks, enlarging the encoder reduces gender skew in CLIP but amplifies both gender and racial skew in OpenCLIP; increasing the LAION corpus from 400M to 2B further increases OpenCLIP bias. At matched model and data budgets, substituting proprietary data with LAION improves gender fairness while increasing racial skew, underscoring data source as the primary driver of bias patterns. We also evaluate three post-hoc, test-time debiasing strategies -- Bias Prompts, Prompt Array, and SANER. Debiasing reduces but does not eliminate harm, and its effectiveness is source- and size-dependent: Bias Prompts most effectively reduce gender skew in CLIP at smaller model sizes, whereas Prompt Array and SANER more reliably reduce racial skew in OpenCLIP; scaling LAION reconfigures which method is most fair. Taken together, these findings challenge the assumption that bigger models or datasets are automatically fairer and foreground training data source as the key determinant of both bias and mitigation efficacy. We release code and evaluation scripts to enable transparent, reproducible auditing of future VLMs.
Authors: Xinyi Gao, Dongting Xie, Yihang Zhang, Zhengren Wang, Chong Chen, Conghui He, Hongzhi Yin, Wentao Zhang
Abstract: With the expansion of data availability, machine learning (ML) has achieved remarkable breakthroughs in both academia and industry. However, imbalanced data distributions are prevalent in various types of raw data and severely hinder the performance of ML by biasing the decision-making processes. To deepen the understanding of imbalanced data and facilitate the related research and applications, this survey systematically analyzes various real-world data formats and concludes existing researches for different data formats into four distinct categories: data re-balancing, feature representation, training strategy, and ensemble learning. This structured analysis helps researchers comprehensively understand the pervasive nature of imbalance across diverse data formats, thereby paving a clearer path toward achieving specific research goals. We provide an overview of relevant open-source libraries, spotlight current challenges, and offer novel insights aimed at fostering future advancements in this critical area of study.
Authors: Shiqian Li, Ruihong Shen, Yaoyu Tao, Chi Zhang, Yixin Zhu
Abstract: Physical reasoning is a remarkable human ability that enables rapid learning and generalization from limited experience. Current AI models, despite extensive training, still struggle to achieve similar generalization, especially in Out-of-distribution (OOD) settings. This limitation stems from their inability to abstract core physical principles from observations. A key challenge is developing representations that can efficiently learn and generalize physical dynamics from minimal data. Here we present Neural Force Field (NFF), a framework extending Neural Ordinary Differential Equation (NODE) to learn complex object interactions through force field representations, which can be efficiently integrated through an Ordinary Differential Equation (ODE) solver to predict object trajectories. Unlike existing approaches that rely on discrete latent spaces, NFF captures fundamental physical concepts such as gravity, support, and collision in continuous explicit force fields. Experiments on three challenging physical reasoning tasks demonstrate that NFF, trained with only a few examples, achieves strong generalization to unseen scenarios. This physics-grounded representation enables efficient forward-backward planning and rapid adaptation through interactive refinement. Our work suggests that incorporating physics-inspired representations into learning systems can help bridge the gap between artificial and human physical reasoning capabilities.
Authors: Elias Kempf, Simon Schrodi, Max Argus, Thomas Brox
Abstract: The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questions remain unanswered: Can CLIP generalize to an entirely unseen domain when trained on a diverse mixture of domains (domain generalization)? Can it generalize to unseen classes within partially seen domains (compositional generalization)? What factors affect such generalization? To answer these questions, we trained CLIP models on systematically constructed training distributions with controlled domain diversity and object class exposure. Our experiments show that domain diversity is essential for both domain and compositional generalization, yet compositional generalization can be surprisingly weaker than domain generalization when the training distribution contains a suboptimal subset of the test domain. Through data-centric and mechanistic analyses, we find that successful generalization requires the learning of sufficiently shared representations in intermediate layers and circuits.
Authors: Liangqi Yuan, Dong-Jun Han, Shiqiang Wang, Christopher G. Brinton
Abstract: Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities through multiple dialogues and multi-modal data sources. These unique characteristics of LLMs, together with their large model size, make their deployment more challenging. Specifically, (i) deploying LLMs on local devices faces computational, memory, and energy resource issues, while (ii) deploying them in the cloud cannot guarantee real-time service and incurs communication/usage costs. In this paper, we design TMO, a local-cloud LLM inference system with Three-M Offloading: Multi-modal, Multi-task, and Multi-dialogue. TMO incorporates (i) a lightweight local LLM that can process simple tasks at high speed and (ii) a large-scale cloud LLM that can handle multi-modal data sources. We develop a resource-constrained reinforcement learning (RCRL) strategy for TMO that optimizes the inference location (i.e., local vs. cloud) and multi-modal data sources to use for each task/dialogue, aiming to maximize the long-term reward (response quality, latency, and usage cost) while adhering to resource constraints. We also contribute M4A1, a new dataset we curated that contains reward and cost metrics across multiple modality, task, dialogue, and LLM configurations, enabling evaluation of offloading decisions. We demonstrate the effectiveness of TMO compared to several exploration-decision and LLM-as-Agent baselines, showing significant improvements in latency, cost, and response quality.
Authors: Haocheng Tang, Jing Long, Beihong Ji, Junmei Wang
Abstract: In this work, we introduce Auxiliary Discriminator Sequence Generative Adversarial Networks (ADSeqGAN), a novel approach for molecular generation in small-sample datasets. Traditional generative models often struggle with limited training data, particularly in drug discovery, where molecular datasets for specific therapeutic targets, such as nucleic acids binders and central nervous system (CNS) drugs, are scarce. ADSeqGAN addresses this challenge by integrating an auxiliary random forest classifier as an additional discriminator into the GAN framework, significantly improves molecular generation quality and class specificity. Our method incorporates pretrained generator and Wasserstein distance to enhance training stability and diversity. We evaluate ADSeqGAN across three representative cases. First, on nucleic acid- and protein-targeting molecules, ADSeqGAN shows superior capability in generating nucleic acid binders compared to baseline models. Second, through oversampling, it markedly improves CNS drug generation, achieving higher yields than traditional de novo models. Third, in cannabinoid receptor type 1 (CB1) ligand design, ADSeqGAN generates novel druglike molecules, with 32.8\% predicted actives surpassing hit rates of CB1-focused and general-purpose libraries when assessed by a target-specific LRIP-SF scoring function. Overall, ADSeqGAN offers a versatile framework for molecular design in data-scarce scenarios, with demonstrated applications in nucleic acid binders, CNS drugs, and CB1 ligands.
Authors: Minyoung Kim
Abstract: The bridge problem is to find an SDE (or sometimes an ODE) that bridges two given distributions. The application areas of the bridge problem are enormous, among which the recent generative modeling (e.g., conditional or unconditional image generation) is the most popular. Also the famous Schr\"{o}dinger bridge problem, a widely known problem for a century, is a special instance of the bridge problem. Two most popular algorithms to tackle the bridge problems in the deep learning era are: (conditional) flow matching and iterative fitting algorithms, where the former confined to ODE solutions, and the latter specifically for the Schr\"{o}dinger bridge problem. The main contribution of this article is in two folds: i) We provide concise reviews of these algorithms with technical details to some extent; ii) We propose a novel unified perspective and framework that subsumes these seemingly unrelated algorithms (and their variants) into one. In particular, we show that our unified framework can instantiate the Flow Matching (FM) algorithm, the (mini-batch) optimal transport FM algorithm, the (mini-batch) Schr\"{o}dinger bridge FM algorithm, and the deep Schr\"{o}dinger bridge matching (DSBM) algorithm as its special cases. We believe that this unified framework will be useful for viewing the bridge problems in a more general and flexible perspective, and in turn can help researchers and practitioners to develop new bridge algorithms in their fields.
Authors: Lei Lei (Sherman), Kan Zheng (Sherman), Xuemin (Sherman), Shen
Abstract: As Cellular Vehicle-to-Everything (C-V2X) evolves towards future sixth-generation (6G) networks, Connected Autonomous Vehicles (CAVs) are emerging to become a key application. Leveraging data-driven Machine Learning (ML), especially Deep Reinforcement Learning (DRL), is expected to significantly enhance CAV decision-making in both vehicle control and V2X communication under uncertainty. These two decision-making processes are closely intertwined, with the value of information (VoI) acting as a crucial bridge between them. In this paper, we introduce Sequential Stochastic Decision Process (SSDP) models to define and assess VoI, demonstrating their application in optimizing communication systems for CAVs. Specifically, we formally define the SSDP model and demonstrate that the MDP model is a special case of it. The SSDP model offers a key advantage by explicitly representing the set of information that can enhance decision-making when available. Furthermore, as current research on VoI remains fragmented, we propose a systematic VoI modeling framework grounded in the MDP, Reinforcement Learning (RL) and Optimal Control theories. We define different categories of VoI and discuss their corresponding estimation methods. Finally, we present a structured approach to leverage the various VoI metrics for optimizing the ``When", ``What", and ``How" to communicate problems. For this purpose, SSDP models are formulated with VoI-associated reward functions derived from VoI-based optimization objectives. While we use a simple vehicle-following control problem to illustrate the proposed methodology, it holds significant potential to facilitate the joint optimization of stochastic, sequential control and communication decisions in a wide range of networked control systems.
Authors: Wei Fu, Jiaxuan Gao, Xujie Shen, Chen Zhu, Zhiyu Mei, Chuyi He, Shusheng Xu, Guo Wei, Jun Mei, Jiashu Wang, Tongkai Yang, Binhang Yuan, Yi Wu
Abstract: Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous, alternating generation and training in a batch setting where rollouts in each training batch are generated by the same model. This approach stabilizes RL training but suffers from severe system-level inefficiency: generation must wait until the longest output in the batch is completed before model updates, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.77$\times$ training speedup compared to synchronous systems with the same number of GPUs and matched or improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.
Authors: Chenheng Xu, Dan Wu, Yixin Zhu, Ying Nian Wu
Abstract: Multivariate long-term time series forecasting has been suffering from the challenge of capturing both temporal dependencies within variables and spatial correlations across variables simultaneously. Current approaches predominantly repurpose backbones from natural language processing or computer vision (e.g., Transformers), which fail to adequately address the unique properties of time series (e.g., periodicity). The research community lacks a dedicated backbone with temporal-specific inductive biases, instead relying on domain-agnostic backbones supplemented with auxiliary techniques (e.g., signal decomposition). We introduce FNF as the backbone and DBD as the architecture to provide excellent learning capabilities and optimal learning pathways for spatio-temporal modeling, respectively. Our theoretical analysis proves that FNF unifies local time-domain and global frequency-domain information processing within a single backbone that extends naturally to spatial modeling, while information bottleneck theory demonstrates that DBD provides superior gradient flow and representation capacity compared to existing unified or sequential architectures. Our empirical evaluation across 11 public benchmark datasets spanning five domains (energy, meteorology, transportation, environment, and nature) confirms state-of-the-art performance with consistent hyperparameter settings. Notably, our approach achieves these results without any auxiliary techniques, suggesting that properly designed neural architectures can capture the inherent properties of time series, potentially transforming time series modeling in scientific and industrial applications.
Authors: Ziyi Chen, Yiyang Liu, Mattia Prosperi, Krishna Vaddiparti, Robert L Cook, Jiang Bian, Yi Guo, Yonghui Wu
Abstract: Objective: To characterize stigma dimensions, social, and related behavioral circumstances in people living with HIV(PLWHs) seeking care, using NLP methods applied to a large collection of EHR clinical notes from a large integrated health system in the southeast United States. Methods: We identified a cohort of PLWHs from the UF Health IDR and performed topic modeling analysis using Latent Dirichlet Allocation to uncover stigma-related dimensions and related social and behavioral contexts. Domain experts created a seed list of HIV-related stigma keywords, then applied a snowball strategy to review notes for additional terms until saturation was reached iteratively. To identify more target topics, we tested three keyword-based filtering strategies. The detected topics were evaluated using three widely used metrics and manually reviewed by specialists. In addition, we conducted word frequency analysis and topic variation analysis among subgroups to examine differences across age and sex-specific demographics. Results: We identified 9140 PLWHs at UF Health and collected 2.9 million clinical notes. Through the iterative keyword approach, we generated a list of 91 keywords associated with HIV-related stigma. Topic modeling on sentences containing at least one keyword uncovered a wide range of topic themes, such as "Mental Health Concern, Stigma", "Treatment Refusal, Isolation", and "Substance Abuse". Topic variation analysis across age subgroups revealed substantial differences. Conclusion: Extracting and understanding the HIV-related stigma and associated social and behavioral circumstances from EHR clinical notes enables scalable, time-efficient assessment and overcoming the limitations of traditional questionnaires. Findings from this research provide actionable insights to inform patient care and interventions to improve HIV-care outcomes.
Authors: Yaqiao Zhu, Hongkai Wen, Geyong Min, Man Luo
Abstract: Efficient traffic signal control (TSC) is essential for mitigating urban congestion, yet existing reinforcement learning (RL) methods face challenges in scaling to large networks while maintaining global coordination. Centralized RL suffers from scalability issues, while decentralized approaches often lack unified objectives, resulting in limited network-level efficiency. In this paper, we propose HiLight, a hierarchical reinforcement learning framework with global adversarial guidance for large-scale TSC. HiLight consists of a high-level Meta-Policy, which partitions the traffic network into subregions and generates sub-goals using a Transformer-LSTM architecture, and a low-level Sub-Policy, which controls individual intersections with global awareness. To improve the alignment between global planning and local execution, we introduce an adversarial training mechanism, where the Meta-Policy generates challenging yet informative sub-goals, and the Sub-Policy learns to surpass these targets, leading to more effective coordination. We evaluate HiLight across both synthetic and real-world benchmarks, and additionally construct a large-scale Manhattan network with diverse traffic conditions, including peak transitions, adverse weather, and holiday surges. Experimental results show that HiLight exhibits significant advantages in large-scale scenarios and remains competitive across standard benchmarks of varying sizes.
Authors: Zeyneddin Oz, Shreyas Korde, Marius Bock, Kristof Van Laerhoven
Abstract: The rapid evolution of sensors and resource-efficient machine learning models has spurred the widespread adoption of wearable fitness tracking devices. Equipped with inertial sensors, such devices can continuously capture physical movements for fitness technology (FitTech), enabling applications from sports optimization to preventive healthcare. Traditional Centralized Learning approaches to detect fitness activities struggle with data privacy concerns, regulatory restrictions, and communication inefficiencies. In contrast, Federated Learning (FL) enables a decentralized model training by communicating model updates rather than potentially private wearable sensor data. Applying FL to FitTech presents unique challenges, such as data imbalance, lack of labeled data, heterogeneous user activities, and trade-offs between personalization and generalization. To simplify research on FitTech in FL, we present the FedFitTech baseline, under the Flower framework, which is publicly available and widely used by both industry and academic researchers. Additionally, to illustrate its usage, this paper presents a case study that implements a system based on the FedFitTech baseline, incorporating a client-side early stopping strategy and comparing the results. For instance, this system allows wearable devices to optimize the trade-off between capturing common fitness activities and preserving individuals' nuances, thereby enhancing both the scalability and efficiency of privacy-aware fitness tracking applications. The results show that this reduces the overall redundant communications by 13%, while maintaining the overall recognition performance at a negligible recognition cost by 1%. Thus, the FedFitTech baseline creates a foundation for a wide range of new research and development opportunities in FitTech, and it is available as open source at: https://github.com/shreyaskorde16/FedFitTech
Authors: Irsyad Adam, Steven Swee, Erika Yilin, Ethan Ji, William Speier, Dean Wang, Alex Bui, Wei Wang, Karol Watson, Peipei Ping
Abstract: In this work, we study the problem pertaining to personalized classification of subclinical atherosclerosis by developing a hierarchical graph neural network framework to leverage two characteristic modalities of a patient: clinical features within the context of the cohort, and molecular data unique to individual patients. Current graph-based methods for disease classification detect patient-specific molecular fingerprints, but lack consistency and comprehension regarding cohort-wide features, which are an essential requirement for understanding pathogenic phenotypes across diverse atherosclerotic trajectories. Furthermore, understanding patient subtypes often considers clinical feature similarity in isolation, without integration of shared pathogenic interdependencies among patients. To address these challenges, we introduce ATHENA: Atherosclerosis Through Hierarchical Explainable Neural Network Analysis, which constructs a novel hierarchical network representation through integrated modality learning; subsequently, it optimizes learned patient-specific molecular fingerprints that reflect individual omics data, enforcing consistency with cohort-wide patterns. With a primary clinical dataset of 391 patients, we demonstrate that this heterogeneous alignment of clinical features with molecular interaction patterns has significantly boosted subclinical atherosclerosis classification performance across various baselines by up to 13% in area under the receiver operating curve (AUC) and 20% in F1 score. Taken together, ATHENA enables mechanistically-informed patient subtype discovery through explainable AI (XAI)-driven subnetwork clustering; this novel integration framework strengthens personalized intervention strategies, thereby improving the prediction of atherosclerotic disease progression and management of their clinical actionable outcomes.
Authors: Sjoerd van Straten, Alessandro Padella, Marwan Hassani
Abstract: Predictive Process Monitoring (PPM) enables forecasting future events or outcomes of ongoing business process instances based on event logs. However, deep learning PPM approaches are often limited by the low variability and small size of real-world event logs. To address this, we introduce SiamSA-PPM, a novel self-supervised learning framework that combines Siamese learning with Statistical Augmentation for Predictive Process Monitoring. It employs three novel statistically grounded transformation methods that leverage control-flow semantics and frequent behavioral patterns to generate realistic, semantically valid new trace variants. These augmented views are used within a Siamese learning setup to learn generalizable representations of process prefixes without the need for labeled supervision. Extensive experiments on real-life event logs demonstrate that SiamSA-PPM achieves competitive or superior performance compared to the SOTA in both next activity and final outcome prediction tasks. Our results further show that statistical augmentation significantly outperforms random transformations and improves variability in the data, highlighting SiamSA-PPM as a promising direction for training data enrichment in process prediction.
Authors: Yu-Tang Chang, Shih-Fang Chen
Abstract: Signal unmixing analysis decomposes data into basic patterns and is widely applied in chemical and biological research. Multivariate curve resolution (MCR), a branch of signal unmixing, separates mixed signals into components (base patterns) and their concentrations (intensity), playing a key role in understanding composition. Classical MCR is typically framed as matrix factorization (MF) and requires a user-specified number of components, usually unknown in real data. Once data or component number increases, the scalability of these MCR approaches face significant challenges. This study reformulates MCR as a data generative process (gMCR), and introduces an Energy-Based solver, EB-gMCR, that automatically discovers the smallest component set and their concentrations for reconstructing the mixed signals faithfully. On synthetic benchmarks with up to 256 components, EB-gMCR attains high reconstruction fidelity and recovers the component count within 5% at 20dB noise and near-exact at 30dB. On two public spectral datasets, it identifies the correct component count and improves component separation over MF-based MCR approaches (NMF variants, ICA, MCR-ALS). EB-gMCR is a general solver for fixed-pattern signal unmixing (components remain invariant across mixtures). Domain priors (non-negativity, nonlinear mixing) enter as plug-in modules, enabling adaptation to new instruments or domains without altering the core selection learning step. The source code is available at https://github.com/b05611038/ebgmcr_solver.
Authors: Haydn Thomas Jones, Natalie Maus, Josh Magnus Ludan, Maggie Ziyu Huan, Jiaming Liang, Marcelo Der Torossian Torres, Jiatao Liang, Zachary Ives, Yoseph Barash, Cesar de la Fuente-Nunez, Jacob R. Gardner, Mark Yatskar
Abstract: AI-driven discovery can greatly reduce design time and enhance new therapeutics' effectiveness. Models using simulators explore broad design spaces but risk violating implicit constraints due to a lack of experimental priors. For example, in a new analysis we performed on a diverse set of models on the GuacaMol benchmark using supervised classifiers, over 60\% of molecules proposed had high probability of being mutagenic. In this work, we introduce Medex, a dataset of priors for design problems extracted from literature describing compounds used in lab settings. It is constructed with LLM pipelines for discovering therapeutic entities in relevant paragraphs and summarizing information in concise fair-use facts. Medex consists of 32.3 million pairs of natural language facts, and appropriate entity representations (i.e. SMILES or refseq IDs). To demonstrate the potential of the data, we train LLM, CLIP, and LLava architectures to reason jointly about text and design targets and evaluate on tasks from the Therapeutic Data Commons (TDC). Medex is highly effective for creating models with strong priors: in supervised prediction problems that use our data as pretraining, our best models with 15M learnable parameters outperform larger 2B TxGemma on both regression and classification TDC tasks, and perform comparably to 9B models on average. Models built with Medex can be used as constraints while optimizing for novel molecules in GuacaMol, resulting in proposals that are safer and nearly as effective. We release our dataset at https://huggingface.co/datasets/medexanon/Medex, and will provide expanded versions as available literature grows.
Authors: Frederik L. Dennig, Daniel A. Keim
Abstract: Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection, while invertible projections allow the synthesis of new data instances. However, existing methods perform poorly when dealing with out-of-distribution samples in either the data or embedding space. Thus, we propose DE-VAE, an uncertainty-aware variational AE using differential entropy (DE) to improve the learned parametric and invertible projections. Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space. We conduct quantitative and qualitative evaluations on four well-known datasets, using UMAP and t-SNE as baseline projection methods. Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches while enabling the analysis of embedding uncertainty.
Authors: Wenhao Mu, Zhi Cao, Mehmed Uludag, Alexander Rodr\'iguez
Abstract: Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely data-driven models, which tend to falter under data scarcity. We propose a time series diffusion-based framework that incorporates guidance from imperfect expert models by extracting high-level signals to serve as structured priors for generative modeling. Our method, ODE-Diff, bridges mechanistic and data-driven approaches, enabling more reliable and interpretable causal inference. We evaluate ODE-Diff across semi-synthetic COVID-19 simulations, synthetic pharmacological dynamics, and real-world case studies, demonstrating that it consistently outperforms strong baselines in both point prediction and distributional accuracy.
Authors: Rapheal Huang (Yuming), Weilong Guo
Abstract: Current Large Language Models (LLMs) are usually post-trained on large-scale carefully curated datasets (data & training scaling) and doing reasoning in test time (inference time scaling). In this work, we present a new scaling paradigm, Input-Time Scaling, to complement previous scaling methods by putting resources on queries (input time). During training and testing, we utilize meta-knowledge from LLMs to refine inputs with different strategies. We also discover a new phenomenon, train-test co-design. It requires us to apply query strategies during training and testing as a whole. Only applying strategies on training or testing would seriously degrade the performance gained. We are also surprised to find that seemingly low data quality datasets can perform better. We can get the best performance even by adding irrelevant information to the queries, with randomly selected 1k examples from a minimally filtered dataset. These findings contradict the widely held inductive bias, "garbage in, garbage out". Curating datasets with seemingly high-quality data can even potentially limit the performance ceiling. In addition, models trained on more data with similar quality (15k VS 1k) perform worse, the intuition of simply scaling the size should also be carefully inspected. The good news is that our findings are compatible with the Less is More phenomenon. 1K examples are enough to invoke high-level reasoning ability. With experiments on Qwen2.5-32B-Instruct, we are able to reach SOTA performance among 32B models on AIME24(76.7%) and AIME25(76.7%) pass@1. We can further achieve AIME24(76.7%) and AIME25(80%) with a majority vote of three models. Starting from DeepSeek-R1-Distill-Qwen-32B, the result would be 90.0% on AIME24 and 80.0% on AIME25. To facilitate reproducibility and further research, we are working on open-source our datasets, data pipelines, evaluation results, and checkpoints.
Authors: Brahim Touayouch, Lo\"ic Fosse, G\'eraldine Damnati, Gw\'enol\'e Lecorv\'e
Abstract: Multi-task learning (MTL) is often achieved by merging datasets before fine-tuning, but the growing availability of fine-tuned models has led to new approaches such as model merging via task arithmetic. A major challenge in this setting is task interference, which worsens as the number of tasks increases. We propose a method that merges models trained on different tasks into a single model, maintaining strong performance across all tasks. Our approach leverages Jensen-Shannon divergence to guide the merging process without requiring additional labelled data, and automatically balances task importance. Unlike existing methods, our approach remains robust as the number of tasks grows and consistently outperforms prior work.
Authors: Zhoujun Cheng, Richard Fan, Shibo Hao, Taylor W. Killian, Haonan Li, Suqi Sun, Hector Ren, Alexander Moreno, Daqian Zhang, Tianjun Zhong, Yuxin Xiong, Yuanzhe Hu, Yutao Xie, Xudong Han, Yuqi Wang, Varad Pimpalkhute, Yonghao Zhuang, Aaryamonvikram Singh, Xuezhi Liang, Anze Xie, Jianshu She, Desai Fan, Chengqian Gao, Liqun Ma, Mikhail Yurochkin, John Maggs, Xuezhe Ma, Guowei He, Zhiting Hu, Zhengzhong Liu, Eric P. Xing
Abstract: K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time computation techniques. The approach is based on six key technical pillars: Long Chain-of-thought Supervised Finetuning, Reinforcement Learning with Verifiable Rewards (RLVR), Agentic planning prior to reasoning, Test-time Scaling, Speculative Decoding, and Inference-optimized Hardware, all using publicly available open-source datasets. K2-Think excels in mathematical reasoning, achieving state-of-the-art scores on public benchmarks for open-source models, while also performing strongly in other areas such as Code and Science. Our results confirm that a more parameter-efficient model like K2-Think 32B can compete with state-of-the-art systems through an integrated post-training recipe that includes long chain-of-thought training and strategic inference-time enhancements, making open-source reasoning systems more accessible and affordable. K2-Think is freely available at k2think.ai, offering best-in-class inference speeds of over 2,000 tokens per second per request via the Cerebras Wafer-Scale Engine.
Authors: Dung T. Tran, Huyen Ngoc Huyen, Hong Nguyen, Xuan-Vu Phan, Nam-Phong Nguyen
Abstract: Rainfall forecasting in Vietnam is highly challenging due to its diverse climatic conditions and strong geographical variability across river basins, yet accurate and reliable forecasts are vital for flood management, hydropower operation, and disaster preparedness. In this work, we propose a Matrix Profile-based Weighted Ensemble (MPWE), a regime-switching framework that dynamically captures covariant dependencies among multiple geographical model forecasts while incorporating redundancy-aware weighting to balance contributions across models. We evaluate MPWE using rainfall forecasts from eight major basins in Vietnam, spanning five forecast horizons (1 hour and accumulated rainfall over 12, 24, 48, 72, and 84 hours). Experimental results show that MPWE consistently achieves lower mean and standard deviation of prediction errors compared to geographical models and ensemble baselines, demonstrating both improved accuracy and stability across basins and horizons.
Authors: Hong Liu, Kerui Cen, Yanxing Chen, Zige Liu, Dong Chen, Zifeng Yang, Chitin Hon
Abstract: Timely and robust influenza incidence forecasting is critical for public health decision-making. This paper presents MAESTRO (Multi-modal Adaptive Estimation for Temporal Respiratory Disease Outbreak), a novel, unified framework that synergistically integrates advanced spectro-temporal modeling with multi-modal data fusion, including surveillance, web search trends, and meteorological data. By adaptively weighting heterogeneous data sources and decomposing complex time series patterns, the model achieves robust and accurate forecasts. Evaluated on over 11 years of Hong Kong influenza data (excluding the COVID-19 period), MAESTRO demonstrates state-of-the-art performance, achieving a superior model fit with an R-square of 0.956. Extensive ablations confirm the significant contributions of its multi-modal and spectro-temporal components. The modular and reproducible pipeline is made publicly available to facilitate deployment and extension to other regions and pathogens, presenting a powerful tool for epidemiological forecasting.
Authors: Marianna Nezhurina, J\"org Franke, Taishi Nakamura, Timur Carstensen, Niccol\`o Ajroldi, Ville Komulainen, David Salinas, Jenia Jitsev
Abstract: We introduce open-sci-ref, a family of dense transformer models trained as research baselines across multiple model (0.13B to 1.7B parameters) and token scales (up to 1T) on 8 recent open reference datasets. Evaluating the models on various standardized benchmarks, our training runs set establishes reference points that enable researchers to assess the sanity and quality of alternative training approaches across scales and datasets. Intermediate checkpoints allow comparison and studying of the training dynamics. The established reference baselines allow training procedures to be compared through their scaling trends, aligning them on a common compute axis. Comparison of open reference datasets reveals that training on NemoTron-CC HQ consistently outperforms other reference datasets, followed by DCLM-baseline and FineWeb-Edu. In addition to intermediate training checkpoints, the release includes logs, code, and downstream evaluations to simplify reproduction, standardize comparison, and facilitate future research.
Authors: Jun-Hao Chen, Yu-Chien Huang, Yun-Cheng Tsai, Samuel Yen-Chi Chen
Abstract: The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over around 5 years with 0.92\% max drawdown, outperforming several currency ETFs. We detail state design (QLSTM features and indicators), reward function for trend-following/risk control, and multi-core training. Results show hybrid models yield competitive FX trading performance. Implications include QLSTM's effectiveness for small-profit trades with tight risk and future enhancements. Key hyperparameters: QLSTM sequence length$=$4, QA3C workers$=$8. Limitations: classical quantum simulation and simplified strategy. \footnote{The views expressed in this article are those of the authors and do not represent the views of Wells Fargo. This article is for informational purposes only. Nothing contained in this article should be construed as investment advice. Wells Fargo makes no express or implied warranties and expressly disclaims all legal, tax, and accounting implications related to this article.
Authors: Jonas Schmidinger, Viacheslav Barkov, Sebastian Vogel, Martin Atzmueller, Gerard B M Heuvelink
Abstract: Machine learning and geostatistics are two fundamentally different frameworks for predicting and spatially mapping soil properties. Geostatistics leverages the spatial structure of soil properties, while machine learning captures the relationship between available environmental features and soil properties. We propose a hybrid framework that enriches ML with spatial context through engineering of 'spatial lag' features from ordinary kriging. We call this approach 'kriging prior regression' (KpR), as it follows the inverse logic of regression kriging. To evaluate this approach, we assessed both the point and probabilistic prediction performance of KpR, using the TabPFN model across six fieldscale datasets from LimeSoDa. These datasets included soil organic carbon, clay content, and pH, along with features derived from remote sensing and in-situ proximal soil sensing. KpR with TabPFN demonstrated reliable uncertainty estimates and more accurate predictions in comparison to several other spatial techniques (e.g., regression/residual kriging with TabPFN), as well as to established non-spatial machine learning algorithms (e.g., random forest). Most notably, it significantly improved the average R2 by around 30% compared to machine learning algorithms without spatial context. This improvement was due to the strong prediction performance of the TabPFN algorithm itself and the complementary spatial information provided by KpR features. TabPFN is particularly effective for prediction tasks with small sample sizes, common in precision agriculture, whereas KpR can compensate for weak relationships between sensing features and soil properties when proximal soil sensing data are limited. Hence, we conclude that KpR with TabPFN is a very robust and versatile modelling framework for digital soil mapping in precision agriculture.
Authors: Zhanhong Jiang, Md Zahid Hasan, Nastaran Saadati, Aditya Balu, Chao Liu, Soumik Sarkar
Abstract: Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy leakage. Although Differentially Private SGD (DPSGD) addresses privacy concerns, its static noise mechanism impacts the error bounds for model performance. Additionally, with the exponential increase in model parameters, efficient learning of these models using stochastic optimizers has become more challenging. To address these concerns, we introduce the Dynamically Differentially Private Projected SGD (D2P2-SGD) optimizer. In D2P2-SGD, we combine two important ideas: (i) dynamic differential privacy (DDP) with automatic gradient clipping and (ii) random projection with SGD, allowing dynamic adjustment of the tradeoff between utility and privacy of the model. It exhibits provably sub-linear convergence rates across different objective functions, matching the best available rate. The theoretical analysis further suggests that DDP leads to better utility at the cost of privacy, while random projection enables more efficient model learning. Extensive experiments across diverse datasets show that D2P2-SGD remarkably enhances accuracy while maintaining privacy. Our code is available here.
Authors: Kunpeng Mao, Ruoyu Li, Junlong Cheng, Danmei Huang, Zhiping Song, ZeKui Liu
Abstract: In recent years, deep convolutional neural network-based segmentation methods have achieved state-of-the-art performance for many medical analysis tasks. However, most of these approaches rely on optimizing the U-Net structure or adding new functional modules, which overlooks the complementation and fusion of coarse-grained and fine-grained semantic information. To address these issues, we propose a 2D medical image segmentation framework called Progressive Learning Network (PL-Net), which comprises Internal Progressive Learning (IPL) and External Progressive Learning (EPL). PL-Net offers the following advantages: (1) IPL divides feature extraction into two steps, allowing for the mixing of different size receptive fields and capturing semantic information from coarse to fine granularity without introducing additional parameters; (2) EPL divides the training process into two stages to optimize parameters and facilitate the fusion of coarse-grained information in the first stage and fine-grained information in the second stage. We conducted comprehensive evaluations of our proposed method on five medical image segmentation datasets, and the experimental results demonstrate that PL-Net achieves competitive segmentation performance. It is worth noting that PL-Net does not introduce any additional learnable parameters compared to other U-Net variants.
Authors: Stephan Cl\'emen\c{c}on, Nathan Huet, Anne Sabourin
Abstract: We establish a statistical learning theoretical framework aimed at extrapolation, or out-of-domain generalization, on the unobserved tails of covariates in continuous regression problems. Our strategy involves performing statistical regression on a subsample of observations with continuous labels that are the furthest away from the origin, focusing specifically on their angular components. The underlying assumptions of our approach are grounded in the theory of multivariate regular variation, a cornerstone of extreme value theory. We address the stylized problem of nonparametric least squares regression with predictors chosen from a Vapnik-Chervonenkis class. This work contributes to a broader initiative to develop statistical learning theoretical foundations for supervised learning strategies that enhance performance on the supposedly heavy tails of covariates. Previous efforts in this area have focused exclusively on binary classification on extreme covariates. Although the continuous target setting necessitates different techniques and regularity assumptions, our main results echo findings from earlier studies. We quantify the predictive performance on tail regions in terms of excess risk, presenting it as a finite sample risk bound with a clear bias-variance decomposition. Numerical experiments with simulated and real data illustrate our theoretical findings.
Authors: Zhendong Cao, Xiaoshan Luo, Jian Lv, Lei Wang
Abstract: We introduce CrystalFormer, a transformer-based autoregressive model specifically designed for space group-controlled generation of crystalline materials. By explicitly incorporating space group symmetry, CrystalFormer greatly reduces the effective complexity of crystal space, which is essential for data-and compute-efficient generative modeling of crystalline materials. Leveraging the prominent discrete and sequential nature of the Wyckoff positions, CrystalFormer learns to generate crystals by directly predicting the species and coordinates of symmetry-inequivalent atoms in the unit cell. We demonstrate the advantages of CrystalFormer in standard tasks such as symmetric structure initialization and element substitution over widely used conventional approaches. Furthermore, we showcase its plug-and-play application to property-guided materials design, highlighting its flexibility. Our analysis reveals that CrystalFormer ingests sensible solid-state chemistry knowledge and heuristics by compressing the material dataset, thus enabling systematic exploration of crystalline materials space. The simplicity, generality, and adaptability of CrystalFormer position it as a promising architecture to be the foundational model of the entire crystalline materials space, heralding a new era in materials discovery and design.
Authors: Platon Lukyanenko, Joshua Mayourian, Mingxuan Liu, John K. Triedman, Sunil J. Ghelani, William G. La Cava
Abstract: Artificial intelligence applied to electrocardiography (AI-ECG) shows potential for mortality prediction, but heterogeneous approaches and private datasets have limited generalizable insights. To address this, we systematically evaluated model design choices across three large cohorts: Beth Israel Deaconess (MIMIC-IV: n = 795,546 ECGs, United States), Telehealth Network of Minas Gerais (Code-15: n = 345,779, Brazil), and Boston Children's Hospital (BCH: n = 255,379, United States). We evaluated models predicting all-cause mortality, comparing horizon-based classification and deep survival methods with neural architectures including convolutional networks and transformers, benchmarking against demographic-only and gradient boosting baselines. Top models performed well (median concordance: Code-15, 0.83; MIMIC-IV, 0.78; BCH, 0.81). Incorporating age and sex improved performance across all datasets. Classifier-Cox models showed site-dependent sensitivity to horizon choice (median Pearson's R: Code-15, 0.35; MIMIC-IV, -0.71; BCH, 0.37). External validation reduced concordance, and in some cases demographic-only models outperformed externally trained AI-ECG models on Code-15. However, models trained on multi-site data outperformed site-specific models by 5-22%. Findings highlight factors for robust AI-ECG deployment: deep survival methods outperformed horizon-based classifiers, demographic covariates improved predictive performance, classifier-based models required site-specific calibration, and cross-cohort training, even between adult and pediatric cohorts, substantially improved performance. These results emphasize the importance of model type, demographics, and training diversity in developing AI-ECG models reliably applicable across populations.
Authors: Zhihao Lin, Zhen Tian, Jianglin Lan, Qi Zhang, Ziyang Ye, Hanyang Zhuang, Xianxian Zhao
Abstract: Safety and efficiency are crucial for autonomous driving in roundabouts, especially mixed traffic with both autonomous vehicles (AVs) and human-driven vehicles. This paper presents a learning-based algorithm that promotes safe and efficient driving across varying roundabout traffic conditions. A deep Q-learning network is used to learn optimal strategies in complex multi-vehicle roundabout scenarios, while a Kolmogorov-Arnold Network (KAN) improves the AVs' environmental understanding. To further enhance safety, an action inspector filters unsafe actions, and a route planner optimizes driving efficiency. Moreover, model predictive control ensures stability and precision in execution. Experimental results demonstrate that the proposed system consistently outperforms state-of-the-art methods, achieving fewer collisions, reduced travel time, and stable training with smooth reward convergence.
Authors: Taras Kucherenko, Derek Peristy, Judith B\"utepage
Abstract: Animation data is often obtained through optical motion capture systems, which utilize a multitude of cameras to establish the position of optical markers. However, system errors or occlusions can result in missing markers, the manual cleaning of which can be time-consuming. This has sparked interest in machine learning-based solutions for missing marker reconstruction in the academic community. Most academic papers utilize a simplistic mean square error as the main metric. In this paper, we show that this metric does not correlate with subjective perception of the fill quality. Additionally, we introduce and evaluate a set of better-correlated metrics that can drive progress in the field.
Authors: Jan V\'avra (Vienna University of Economics and Business, Paris-Lodron University of Salzburg), Bettina Gr\"un (Vienna University of Economics and Business), Paul Hofmarcher (Paris-Lodron University of Salzburg)
Abstract: The world is evolving and so is the vocabulary used to discuss topics in speech. Analysing political speech data from more than 30 years requires the use of flexible topic models to uncover the latent topics and their change in prevalence over time as well as the change in the vocabulary of the topics. We propose the temporal Poisson factorisation (TPF) model as an extension to the Poisson factorisation model to model sparse count data matrices obtained based on the bag-of-words assumption from text documents with time stamps. We discuss and empirically compare different model specifications for the time-varying latent variables consisting either of a flexible auto-regressive structure of order one or a random walk. Estimation is based on variational inference where we consider a combination of coordinate ascent updates with automatic differentiation using batching of documents. Suitable variational families are proposed to ease inference. We compare results obtained using independent univariate variational distributions for the time-varying latent variables to those obtained with a multivariate variant. We discuss in detail the results of the TPF model when analysing speeches from 18 sessions in the U.S. Senate (1981-2016).
Authors: Wenlong Chen, Wenlin Chen, Lapo Rastrelli, Yingzhen Li
Abstract: Diffusion models, which can be viewed as a special case of hierarchical variational autoencoders (HVAEs), have shown profound success in generating photo-realistic images. In contrast, standard HVAEs often produce images of inferior quality compared to diffusion models. In this paper, we hypothesize that the success of diffusion models can be partly attributed to the additional self-supervision information for their intermediate latent states provided by corrupted images, which along with the original image form a pseudo video. Based on this hypothesis, we explore the possibility of improving other types of generative models with such pseudo videos. Specifically, we first extend a given image generative model to their video generative model counterpart, and then train the video generative model on pseudo videos constructed by applying data augmentation to the original images. Furthermore, we analyze the potential issues of first-order Markov data augmentation methods, which are typically used in diffusion models, and propose to use more expressive data augmentation to construct more useful information in pseudo videos. Our empirical results on the CIFAR10 and CelebA datasets demonstrate that improved image generation quality can be achieved with additional self-supervised information from pseudo videos.
Authors: Harshvardhan Mestha, Karan Bania, Shreyas V, Sidong Liu, Ashwin Srinivasan
Abstract: Our interest is in the design of software systems involving a human-expert interacting -- using natural language -- with a large language model (LLM) on data analysis tasks. For complex problems, it is possible that LLMs can harness human expertise and creativity to find solutions that were otherwise elusive. On one level, this interaction takes place through multiple turns of prompts from the human and responses from the LLM. Here we investigate a more structured approach based on an abstract protocol described in [3] for interaction between agents. The protocol is motivated by a notion of "two-way intelligibility" and is modelled by a pair of communicating finite-state machines. We provide an implementation of the protocol, and provide empirical evidence of using the implementation to mediate interactions between an LLM and a human-agent in two areas of scientific interest (radiology and drug design). We conduct controlled experiments with a human proxy (a database), and uncontrolled experiments with human subjects. The results provide evidence in support of the protocol's capability of capturing one- and two-way intelligibility in human-LLM interaction; and for the utility of two-way intelligibility in the design of human-machine systems.
Authors: Zhichen Zeng, Xiaolong Liu, Mengyue Hang, Xiaoyi Liu, Qinghai Zhou, Chaofei Yang, Yiqun Liu, Yichen Ruan, Laming Chen, Yuxin Chen, Yujia Hao, Jiaqi Xu, Jade Nie, Xi Liu, Buyun Zhang, Wei Wen, Siyang Yuan, Hang Yin, Xin Zhang, Kai Wang, Wen-Yen Chen, Yiping Han, Huayu Li, Chunzhi Yang, Bo Long, Philip S. Yu, Hanghang Tong, Jiyan Yang
Abstract: Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset.
Authors: Chen Li, Elena Ferro, Corey Lammie, Manuel Le Gallo, Irem Boybat, Bipin Rajendran
Abstract: Analog In-Memory Computing (AIMC) offers a promising solution to the von Neumann bottleneck. However, deploying transformer models on AIMC remains challenging due to their inherent need for flexibility and adaptability across diverse tasks. For the benefits of AIMC to be fully realized, weights of static vector-matrix multiplications must be mapped and programmed to analog devices in a weight-stationary manner. This poses two challenges for adapting a base network to hardware and downstream tasks: (i) conventional analog hardware-aware (AHWA) training requires retraining the entire model, and (ii) reprogramming analog devices is both time- and energy-intensive. To address these issues, we propose Analog Hardware-Aware Low-Rank Adaptation (AHWA-LoRA) training, a novel approach for efficiently adapting transformers to AIMC hardware. AHWA-LoRA training keeps the analog weights fixed as meta-weights and introduces lightweight external LoRA modules for both hardware and task adaptation. We validate AHWA-LoRA training on SQuAD v1.1 and the GLUE benchmark, demonstrate its scalability to larger models, and show its effectiveness in instruction tuning and reinforcement learning. We further evaluate a practical deployment scenario that balances AIMC tile latency with digital LoRA processing using optimized pipeline strategies, with RISC-V-based programmable multi-core accelerators. This hybrid architecture achieves efficient transformer inference with only a 4% per-layer overhead compared to a fully AIMC implementation.
Authors: Yang Chen, Shuai Fu, Yu Zhang
Abstract: Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded performance on unseen classes. This limitation is due to the inherent bias in the training data towards the seen classes. To address this issue, we propose a novel soft prompt learning method, named Mixture-of-Prompts Distillation (MoPD), which can effectively transfer useful knowledge from hard prompts manually hand-crafted (a.k.a. teacher prompts) to the learnable soft prompt (a.k.a. student prompt), thereby enhancing the generalization ability of soft prompts on unseen classes. Moreover, the proposed MoPD method utilizes a gating network that learns to select hard prompts used for prompt distillation. Extensive experiments demonstrate that the proposed MoPD method outperforms state-of-the-art baselines especially on on unseen classes.
Authors: Olaoluwa Adigun, Bart Kosko
Abstract: This chapter presents the new family of soft diamond synaptic regularizers based on thick-tailed symmetric alpha stable $S{\alpha}S$ probability bell curves. These new parametrized weight priors improved deep-learning performance on image and language-translation test sets and increased the sparsity of the trained weights. They outperformed the state-of-the-art hard-diamond Laplacian regularizer of sparse lasso regression and classification. The $S{\alpha}S$ synaptic weight priors have power-law bell-curve tails that are thicker than the thin exponential tails of Gaussian bell curves that underly ridge regularizers. Their tails get thicker as the $\alpha$ parameter decreases. These thicker tails model more impulsive behavior and allow for occasional distant search in synaptic weight spaces of extremely high dimension. The geometry of their constraint sets has a diamond shape. The shape varies from a circle to a star or diamond that depends on the $\alpha$ tail thickness and dispersion of the $S{\alpha}S$ weight prior. These $S{\alpha}S$ bell curves lack a closed form in general and this makes direct training computationally intensive. We removed this computational bottleneck by using a precomputed look-up table. We tested the soft diamond regularizers with deep neural classifiers on both image test sets and German-to-English language translation. The image simulations used the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy and sparsity of the classifiers. We also tested with deep neural machine-translation models on the IWSLT-2016 Evaluation dataset for German-to-English text translation. They also outperformed ridge regularizers and lasso regularizers. These findings recommend the sub-Cauchy $\alpha = 0.5$ soft diamond regularizer as a competitive and sparse regularizer for large-scale machine learning.
Authors: Yongqi Dong, Bart van Arem, Haneen Farah
Abstract: Automated Vehicles (AVs) hold promise for revolutionizing transportation by improving road safety, traffic efficiency, and overall mobility. Despite the steady advancement in high-level AVs in recent years, the transition to full automation entails a period of mixed traffic, where AVs of varying automation levels coexist with human-driven vehicles (HDVs). Making AVs socially compliant and understood by human drivers is expected to improve the safety and efficiency of mixed traffic. Thus, ensuring AVs' compatibility with HDVs and social acceptance is crucial for their successful and seamless integration into mixed traffic. However, research in this critical area of developing Socially Compliant AVs (SCAVs) remains sparse. This study carries out the first comprehensive scoping review to assess the current state of the art in developing SCAVs, identifying key concepts, methodological approaches, and research gaps. An informal expert interview was also conducted to discuss the literature review results and identify critical research gaps and expectations towards SCAVs. Based on the scoping review and expert interview input, a conceptual framework is proposed for the development of SCAVs. The conceptual framework is evaluated using an online survey targeting researchers, technicians, policymakers, and other relevant professionals worldwide. The survey results provide valuable validation and insights, affirming the significance of the proposed conceptual framework in tackling the challenges of integrating AVs into mixed-traffic environments. Additionally, future research perspectives and suggestions are discussed, contributing to the research and development agenda of SCAVs.
Authors: Nikolaos Dionelis, Alessandra Feliciotti, Mattia Marconcini, Devis Peressutti, Nika Oman Kadunc, JaeWan Park, Hagai Raja Sinulingga, Steve Andreas Immanuel, Ba Tran, Caroline Arnold, Nicolas Long\'ep\'e
Abstract: Estimating the construction year of buildings is critical for advancing sustainability, as older structures often lack energy-efficient features. Sustainable urban planning relies on accurate building age data to reduce energy consumption and mitigate climate change. In this work, we introduce MapYourCity, a novel multi-modal benchmark dataset comprising top-view Very High Resolution (VHR) imagery, multi-spectral Earth Observation (EO) data from the Copernicus Sentinel-2 satellite constellation, and co-localized street-view images across various European cities. Each building is labeled with its construction epoch, and the task is formulated as a seven-class classification problem covering periods from 1900 to the present. To advance research in EO generalization and multi-modal learning, we organized a community-driven data challenge in 2024, hosted by ESA $\Phi$-lab, which ran for four months and attracted wide participation. This paper presents the Top-4 performing models from the challenge and their evaluation results. We assess model generalization on cities excluded from training to prevent data leakage, and evaluate performance under missing modality scenarios, particularly when street-view data is unavailable. Results demonstrate that building age estimation is both feasible and effective, even in previously unseen cities and when relying solely on top-view satellite imagery (i.e. with VHR and Sentinel-2 images). The MapYourCity dataset thus provides a valuable resource for developing scalable, real-world solutions in sustainable urban analytics.
Authors: Jan Mielniczuk, Wojciech Rejchel, Pawe{\l} Teisseyre
Abstract: We study estimation of a class prior for unlabeled target samples which possibly differs from that of source population. Moreover, it is assumed that the source data is partially observable: only samples from the positive class and from the whole population are available (PU learning scenario). We introduce a novel direct estimator of a class prior which avoids estimation of posterior probabilities in both populations and has a simple geometric interpretation. It is based on a distribution matching technique together with kernel embedding in a Reproducing Kernel Hilbert Space and is obtained as an explicit solution to an optimisation task. We establish its asymptotic consistency as well as an explicit non-asymptotic bound on its deviation from the unknown prior, which is calculable in practice. We study finite sample behaviour for synthetic and real data and show that the proposal works consistently on par or better than its competitors.
Authors: Jing Zhang, Alexandre Bousse, Chi-Hieu Pham, Kuangyu Shi, Julien Bert
Abstract: Targeted Radionuclide Therapy (TRT) is a modern strategy in radiation oncology that aims to administer a potent radiation dose specifically to cancer cells using cancer-targeting radiopharmaceuticals. Accurate radiation dose estimation tailored to individual patients is crucial. Deep learning, particularly with pre-therapy imaging, holds promise for personalizing TRT doses. However, current methods require large time series of SPECT imaging, which is hardly achievable in routine clinical practice, and thus raises issues of data availability. Our objective is to develop a semi-supervised learning (SSL) solution to personalize dosimetry using pre-therapy images. The aim is to develop an approach that achieves accurate results when PET/CT images are available, but are associated with only a few post-therapy dosimetry data provided by SPECT images. In this work, we introduce an SSL method using a pseudo-label generation approach for regression tasks inspired by the FixMatch framework. The feasibility of the proposed solution was preliminarily evaluated through an in-silico study using synthetic data and Monte Carlo simulation. Experimental results for organ dose prediction yielded promising outcomes, showing that the use of pseudo-labeled data provides better accuracy compared to using only labeled data.
Authors: Saiyam Sakhuja, Shivanshu Siyanwal, Abhishek Tiwari, Britant, Savita Kashyap
Abstract: Quantum Machine Learning (QML) presents as a revolutionary approach to weather forecasting by using quantum computing to improve predictive modeling capabilities. In this study, we apply QML models, including Quantum Gated Recurrent Units (QGRUs), Quantum Neural Networks (QNNs), Quantum Long Short-Term Memory(QLSTM), Variational Quantum Circuits(VQCs), and Quantum Support Vector Machines(QSVMs), to analyze meteorological time-series data from the ERA5 dataset. Our methodology includes preprocessing meteorological features, implementing QML architectures for both classification and regression tasks. The results demonstrate that QML models can achieve reasonable accuracy in both prediction and classification tasks, particularly in binary classification. However, challenges such as quantum hardware limitations and noise affect scalability and generalization. This research provides insights into the feasibility of QML for weather prediction, paving the way for further exploration of hybrid quantum-classical frameworks to enhance meteorological forecasting.
Authors: Junhe Zhang, Wanli Ni, Pengwei Wang, Dongyu Wang
Abstract: Despite the promising paradigm enabled by integrating semantic communication (SemCom) with multimodal large models (MLMs) for transmitting and utilizing multimodal data, efficiently fusing and exploiting cross-modal information still remain challenging. Moreover, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which result in higher bandwidth consumption, increased power usage, and greater latency, rendering them impractical in resource-constrained networks. In this letter, we propose a task-oriented multimodal token transmission scheme for efficient multimodal information fusion and utilization. To improve inter-modal consistency and task-relevant token transmission, we design a two-stage training algotithm which involves cross-modal alignment followed by task-oriented fine-tuning. Meanwhile, token compression is performed using a sliding window pooling operation to conserve limited communication resources. To balance the trade-off between latency reduction and performance degradation caused by compression, we formulate a weighted-sum optimization problem over latency and inference performance. We jointly optimizes bandwidth, power allocation, and token length across users by using an alternating optimization method. Simulation results demonstrate that the proposed algorithm outperforms the baseline under different bandwidth and power budgets. Moreover, the two-stage training algorithm achieves higher accuracy across various signal-to-noise ratios than the method without cross-modal alignment.
Authors: Jiaxiang Li, Junwei Feng, Jie Luo, Bowen Jiang, Xiangyu Zheng, Qigang Song, Jian Lv, Keith Butler, Hanyu Liu, Congwei Xie, Yu Xie, Yanming Ma
Abstract: Machine learning interatomic potentials have revolutionized complex materials design by enabling rapid exploration of material configurational spaces via crystal structure prediction with ab initio accuracy. However, critical challenges persist in ensuring robust generalization to unknown structures and minimizing the requirement for substantial expert knowledge and time-consuming manual interventions. Here, we propose an automated crystal structure prediction framework built upon the attention-coupled neural networks potential to address these limitations. The generalizability of the potential is achieved by sampling regions across the local minima of the potential energy surface, where the self-evolving pipeline autonomously refines the potential iteratively while minimizing human intervention. The workflow is validated on Mg-Ca-H ternary and Be-P-N-O quaternary systems by exploring nearly 10 million configurations, demonstrating substantial speedup compared to first-principles calculations. These results underscore the effectiveness of our approach in accelerating the exploration and discovery of complex multi-component functional materials.
Authors: Zahraa Al Sahili, Ioannis Patras, Matthew Purver
Abstract: Multilingual vision-language models (VLMs) promise universal image-text retrieval, yet their social biases remain underexplored. We perform the first systematic audit of four public multilingual CLIP variants: M-CLIP, NLLB-CLIP, CAPIVARA-CLIP, and the debiased SigLIP-2, covering ten languages that differ in resource availability and morphological gender marking. Using balanced subsets of FairFace and the PATA stereotype suite in a zero-shot setting, we quantify race and gender bias and measure stereotype amplification. Contrary to the intuition that multilinguality mitigates bias, every model exhibits stronger gender skew than its English-only baseline. CAPIVARA-CLIP shows its largest biases precisely in the low-resource languages it targets, while the shared encoder of NLLB-CLIP and SigLIP-2 transfers English gender stereotypes into gender-neutral languages; loosely coupled encoders largely avoid this leakage. Although SigLIP-2 reduces agency and communion skews, it inherits -- and in caption-sparse contexts (e.g., Xhosa) amplifies -- the English anchor's crime associations. Highly gendered languages consistently magnify all bias types, yet gender-neutral languages remain vulnerable whenever cross-lingual weight sharing imports foreign stereotypes. Aggregated metrics thus mask language-specific hot spots, underscoring the need for fine-grained, language-aware bias evaluation in future multilingual VLM research.
Authors: Bunlong Lay, Rostislav Makarov, Timo Gerkmann
Abstract: Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing streaming data in real-time. In this work, we adapt a sliding window diffusion framework to the speech enhancement task. Our approach progressively corrupts speech signals through time, assigning more noise to frames close to the present in a buffer. This approach outputs denoised frames with a delay proportional to the chosen buffer size, enabling a trade-off between performance and latency. Empirical results demonstrate that our method outperforms standard diffusion models and runs efficiently on a GPU, achieving an input-output latency in the order of 0.3 to 1 seconds. This marks the first practical diffusion-based solution for online speech enhancement.
Authors: Hondamunige Prasanna Silva, Federico Becattini, Lorenzo Seidenari
Abstract: Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning. For this reason, models such as CLIP , DINO or Vision Transfomers (ViT), are becoming the bedrock of many industrial AI-powered applications. However, the reliance on pre-trained foundation models also introduces significant security concerns, as these models are vulnerable to adversarial attacks. Such attacks involve deliberately crafted inputs designed to deceive AI systems, jeopardizing their reliability. This paper studies the vulnerabilities of vision foundation models, focusing specifically on CLIP and ViTs, and explores the transferability of adversarial attacks to downstream tasks. We introduce a novel attack, targeting the structure of transformer-based architectures in a task-agnostic fashion. We demonstrate the effectiveness of our attack on several downstream tasks: classification, captioning, image/text retrieval, segmentation and depth estimation. Code available at:https://github.com/HondamunigePrasannaSilva/attack-attention
URLs: https://github.com/HondamunigePrasannaSilva/attack-attention
Authors: Ke Wang, Yiming Qin, Nikolaos Dimitriadis, Alessandro Favero, Pascal Frossard
Abstract: Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-without retraining or forgetting previous information-remains a major challenge. Existing methods for lifelong model editing either compromise generalization, interfere with past edits, or fail to scale to long editing sequences. We propose MEMOIR, a novel scalable framework that injects knowledge through a residual memory, i.e., a dedicated parameter module, while preserving the core capabilities of the pre-trained model. By sparsifying input activations through sample-dependent masks, MEMOIR confines each edit to a distinct subset of the memory parameters, minimizing interference among edits. At inference, it identifies relevant edits by comparing the sparse activation patterns of new queries to those stored during editing. This enables generalization to rephrased queries by activating only the relevant knowledge while suppressing unnecessary memory activation for unrelated prompts. Experiments on question answering, hallucination correction, and out-of-distribution generalization benchmarks for LLaMA-3 and Mistral backbones demonstrate that MEMOIR achieves state-of-the-art performance across reliability, generalization, and locality metrics, scaling to thousands of sequential edits with minimal forgetting.
Authors: Bishwajit Prasad Gond, Rajneekant, Pushkar Kishore, Durga Prasad Mohapatra
Abstract: This paper investigates the application of natural language processing (NLP)-based n-gram analysis and machine learning techniques to enhance malware classification. We explore how NLP can be used to extract and analyze textual features from malware samples through n-grams, contiguous string or API call sequences. This approach effectively captures distinctive linguistic patterns among malware and benign families, enabling finer-grained classification. We delve into n-gram size selection, feature representation, and classification algorithms. While evaluating our proposed method on real-world malware samples, we observe significantly improved accuracy compared to the traditional methods. By implementing our n-gram approach, we achieved an accuracy of 99.02% across various machine learning algorithms by using hybrid feature selection technique to address high dimensionality. Hybrid feature selection technique reduces the feature set to only 1.6% of the original features.
Authors: Quentin Le Roux, Yannick Teglia, Teddy Furon, Philippe Loubet-Moundi, Eric Bourbao
Abstract: The widespread deployment of Deep Learning-based Face Recognition Systems raises multiple security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world, unconstrained pipelines remain underexplored. This paper presents the first comprehensive system-level analysis of Backdoor Attacks targeting Face Recognition Systems and provides three contributions. We first show that face feature extractors trained with large margin metric learning losses are susceptible to Backdoor Attacks. By analyzing 20 pipeline configurations and 15 attack scenarios, we then reveal that a single backdoor can compromise an entire Face Recognition System. Finally, we propose effective best practices and countermeasures for stakeholders.
Authors: Chien-Ming Chi
Abstract: We propose o1Neuro, a new neural network model built on sparse indicator activation neurons, with two key statistical properties. (1) Constructive universal approximation: At the population level, a deep o1Neuro can approximate any measurable function of $\boldsymbol{X}$, while a shallow o1Neuro suffices for additive models with two-way interaction components, including XOR and univariate terms, assuming $\boldsymbol{X} \in [0,1]^p$ has bounded density. Combined with prior work showing that a single-hidden-layer non-sparse network is a universal approximator, this highlights a trade-off between activation sparsity and network depth in approximation capability. (2) Sure convergence: At the sample level, the optimization of o1Neuro reaches an optimal model with probability approaching one after sufficiently many update rounds, and we provide an example showing that the required number of updates is well bounded under linear data-generating models. Empirically, o1Neuro is compared with XGBoost, Random Forests, and TabNet for learning complex regression functions with interactions, demonstrating superior predictive performance on several benchmark datasets from OpenML and the UCI Machine Learning Repository with $n = 10000$, as well as on synthetic datasets with $100 \le n \le 20000$.
Authors: Christophe Muller (PREMEDICAL), Erwan Scornet (LPSM), Julie Josse (PREMEDICAL)
Abstract: Predicting a response with partially missing inputs remains a challenging task even in parametric models, since parameter estimation in itself is not sufficient to predict on partially observed inputs. Several works study prediction in linear models. In this paper, we focus on logistic models, which present their own difficulties. From a theoretical perspective, we prove that a Pattern-by-Pattern strategy (PbP), which learns one logistic model per missingness pattern, accurately approximates Bayes probabilities in various missing data scenarios (MCAR, MAR and MNAR). Empirically, we thoroughly compare various methods (constant and iterative imputations, complete case analysis, PbP, and an EM algorithm) across classification, probability estimation, calibration, and parameter inference. Our analysis provides a comprehensive view on the logistic regression with missing values. It reveals that mean imputation can be used as baseline for low sample sizes, and improved performance is obtained via nonlinear multiple iterative imputation techniques with the labels (MICE.RF.Y). For large sample sizes, PbP is the best method for Gaussian mixtures, and we recommend MICE.RF.Y in presence of nonlinear features.
Authors: Xinyu Chen, Qi Wang, Yunhan Zheng, Nina Cao, HanQin Cai, Jinhua Zhao
Abstract: Human mobility regularity is crucial for understanding urban dynamics and informing decision-making processes. This study first quantifies the periodicity in complex human mobility data as a sparse identification of dominant positive auto-correlations in time series autoregression and then discovers periodic patterns. We apply the framework to large-scale metro passenger flow data in Hangzhou, China and multi-modal mobility data in New York City and Chicago, USA, revealing the interpretable weekly periodicity across different spatial locations over past several years. The analysis of ridesharing data from 2019 to 2024 demonstrates the disruptive impact of the pandemic on mobility regularity and the subsequent recovery trends. In 2024, the periodic mobility patterns of ridesharing, taxi, subway, and bikesharing in Manhattan uncover the regularity and variability of these travel modes. Our findings highlight the potential of interpretable machine learning to discover spatiotemporal mobility patterns and offer a valuable tool for understanding urban systems.
Authors: Jozef Skakala
Abstract: Shelf seas are important for carbon sequestration and carbon cycle, but shelf sea observations for carbon pools are often sparse, or highly uncertain. Alternative can be provided by reanalyses, but these are often expensive to run. We propose to use an ensemble of neural networks (i.e. deep ensemble) to learn from a coupled physics-biogeochemistry model the relationship between the directly observable variables and carbon pools. We demonstrate for North-West European Shelf (NWES) sea environment, that when the deep ensemble trained on a model free run simulation is applied to the NWES reanalysis, it is capable to reproduce the reanalysis outputs for carbon pools and additionally provide uncertainty information. We focus on explainability of the results and demonstrate potential use of the deep ensembles for future climate what-if scenarios. We suggest that model-informed machine learning presents a viable alternative to expensive reanalyses and could complement observations, wherever they are missing and/or highly uncertain.
Authors: Justin Lin, Julia Fukuyama
Abstract: Technological advances have spurred an increase in data complexity and dimensionality. We are now in an era in which data sets containing thousands of features are commonplace. To digest and analyze such high-dimensional data, dimension reduction techniques have been developed and advanced along with computational power. Of these techniques, nonlinear methods are most commonly employed because of their ability to construct visually interpretable embeddings. Unlike linear methods, these methods non-uniformly stretch and shrink space to create a visual impression of the high-dimensional data. Since capturing high-dimensional structures in a significantly lower number of dimensions requires drastic manipulation of space, nonlinear dimension reduction methods are known to occasionally produce false structures, especially in noisy settings. In an effort to deal with this phenomenon, we developed an interactive tool that enables analysts to better understand and diagnose their dimension reduction results. It uses various analytical plots to provide a multi-faceted perspective on results to determine legitimacy. The tool is available via an R package named DRtool.
Authors: Pembe Gizem \"Ozdil, Chuanfang Ning, Jasper S. Phelps, Sibo Wang-Chen, Guy Elisha, Alexander Blanke, Auke Ijspeert, Pavan Ramdya
Abstract: Computational models are critical to advance our understanding of how neural, biomechanical, and physical systems interact to orchestrate animal behaviors. Despite the availability of near-complete reconstructions of the Drosophila melanogaster central nervous system, musculature, and exoskeleton, anatomically and physically grounded models of fly leg muscles are still missing. These models provide an indispensable bridge between motor neuron activity and joint movements. Here, we introduce the first 3D, data-driven musculoskeletal model of Drosophila legs, implemented in both OpenSim and MuJoCo simulation environments. Our model incorporates a Hill-type muscle representation based on high-resolution X-ray scans from multiple fixed specimens. We present a pipeline for constructing muscle models using morphological imaging data and for optimizing unknown muscle parameters specific to the fly. We then combine our musculoskeletal models with detailed 3D pose estimation data from behaving flies to achieve muscle-actuated behavioral replay in OpenSim. Simulations of muscle activity across diverse walking and grooming behaviors predict coordinated muscle synergies that can be tested experimentally. Furthermore, by training imitation learning policies in MuJoCo, we test the effect of different passive joint properties on learning speed and find that damping and stiffness facilitate learning. Overall, our model enables the investigation of motor control in an experimentally tractable model organism, providing insights into how biomechanics contribute to generation of complex limb movements. Moreover, our model can be used to control embodied artificial agents to generate naturalistic and compliant locomotion in simulated environments.
Authors: Long-Kai Huang, Rongyi Zhu, Bing He, Jianhua Yao
Abstract: Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified functionalities or properties due to inherent challenges in controlling their outputs. In this work, we investigate the potential of Activation Steering, a technique originally developed for controlling text generation in Large Language Models (LLMs), to direct PLMs toward generating protein sequences with targeted properties. We propose a simple yet effective method that employs activation editing to steer PLM outputs, and extend this approach to protein optimization through a novel editing site identification module. Through comprehensive experiments on lysozyme-like sequence generation and optimization, we demonstrate that our methods can be seamlessly integrated into both auto-encoding and autoregressive PLMs without requiring additional training. These results highlight a promising direction for precise protein engineering using foundation models.
Authors: Mikhail Khodak, Min Ki Jung, Brian Wynne, Edmond Chow, Egemen Kolemen
Abstract: Data-driven acceleration of scientific computing workflows has been a high-profile aim of machine learning (ML) for science, with numerical simulation of transient partial differential equations (PDEs) being one of the main applications. The focus thus far has been on methods that require classical simulations to train, which when combined with the data-hungriness and optimization challenges of neural networks has caused difficulties in demonstrating a convincing advantage against strong classical baselines. We consider an alternative paradigm in which the learner uses a classical solver's own data to accelerate it, enabling a one-shot speedup of the simulation. Concretely, since transient PDEs often require solving a sequence of related linear systems, the feedback from repeated calls to a linear solver such as preconditioned conjugate gradient (PCG) can be used by a bandit algorithm to online-learn an adaptive sequence of solver configurations (e.g. preconditioners). The method we develop, PCGBandit, is implemented directly on top of the popular open source software OpenFOAM, which we use to show its effectiveness on a set of fluid and magnetohydrodynamics (MHD) problems.
Authors: Waqar Ahmad, Evan Murphy, Vladimir A. Krylov
Abstract: Object re-identification (Re-ID) methods are highly sensitive to label noise, which typically leads to significant performance degradation. We address this challenge by reframing Re-ID as a supervised image similarity task and adopting a Siamese network architecture trained to capture discriminative pairwise relationships. Central to our approach is a novel statistical outlier detection (OD) framework, termed Beta-SOD (Beta mixture Similarity-based Outlier Detection), which models the distribution of cosine similarities between embedding pairs using a two-component Beta distribution mixture model. We establish a novel identifiability result for mixtures of two Beta distributions, ensuring that our learning task is well-posed. The proposed OD step complements the Re-ID architecture combining binary cross-entropy, contrastive, and cosine embedding losses that jointly optimize feature-level similarity learning.We demonstrate the effectiveness of Beta-SOD in de-noising and Re-ID tasks for person Re-ID, on CUHK03 and Market-1501 datasets, and vehicle Re-ID, on VeRi-776 dataset. Our method shows superior performance compared to the state-of-the-art methods across various noise levels (10-30\%), demonstrating both robustness and broad applicability in noisy Re-ID scenarios. The implementation of Beta-SOD is available at: github.com/waqar3411/Beta-SOD
Authors: Soheil Zibakhsh Shabgahi, Pedram Aghazadeh, Azalia Mirhoseini, Farinaz Koushanfar
Abstract: The increasing reliance on generative AI models has accelerated the generation rate of synthetic data, with some projections suggesting that most available new data for training could be machine-generated by 2030. This shift to a mainly synthetic content presents a critical challenge: repeated training in synthetic data leads to a phenomenon known as model collapse, where model performance degrades over generations of training, eventually rendering the models ineffective. Although prior studies have explored the causes and detection of model collapse, existing mitigation strategies remain limited. In this paper, we identify model overconfidence in their self-generated data as a key driver of collapse. Building on this observation, we propose a confidence-aware loss function that downweights high-confidence predictions during training. We introduce a novel loss function we call Truncated Cross Entropy (TCE). We demonstrate that TCE significantly delays model collapse in recursive training. We provide a model-agnostic framework that links the loss function design to model collapse mitigation and validate our approach both theoretically and empirically, showing that it can extend the model's fidelity interval before collapse by more than 2.3x. Finally, we show that our method generalizes across modalities. These findings suggest that the design of loss functions provides a simple yet powerful tool for preserving the quality of generative models in the era of increasing synthetic data.
Authors: Harry Julian, Rachel Beeson, Lohith Konathala, Johanna Ulin, Jiameng Gao
Abstract: Neural Audio Codecs (NACs) have become increasingly adopted in speech processing tasks due to their excellent rate-distortion performance and compatibility with Large Language Models (LLMs) as discrete feature representations for audio generation. While most existing codecs rely on Residual Vector Quantization (RVQ), Finite Scalar Quantization (FSQ) has recently emerged as a compelling alternative that simplifies training and natively supports single codebooks. We introduce NeuCodec, an FSQ-based NAC, and show that FSQ encodes baked-in redundancy which produces an encoding which is robust when transmitted through noisy channels. First, through an encoder distillation experiment, we show that two different encoders can learn to encode identical audio into vastly different code sequences whilst maintaining comparable reconstruction quality with the same quantizer and decoder. Second, we demonstrate that FSQ has vastly superior bit-level perturbation robustness by comparing the performance of RVQ and FSQ codecs when simulating the transmission of code sequences through a noisy channel.