Authors: Kaichen Ouyang
Abstract: Graph Neural Networks (GNNs) have shown great potential in graph data analysis due to their powerful representation capabilities. However, as the network depth increases, the issue of over-smoothing becomes more severe, causing node representations to lose their distinctiveness. This paper analyzes the mechanism of over-smoothing through the analogy to Anderson localization and introduces participation degree as a metric to quantify this phenomenon. Specifically, as the depth of the GNN increases, node features homogenize after multiple layers of message passing, leading to a loss of distinctiveness, similar to the behavior of vibration modes in disordered systems. In this context, over-smoothing in GNNs can be understood as the expansion of low-frequency modes (increased participation degree) and the localization of high-frequency modes (decreased participation degree). Based on this, we systematically reviewed the potential connection between the Anderson localization behavior in disordered systems and the over-smoothing behavior in Graph Neural Networks. A theoretical analysis was conducted, and we proposed the potential of alleviating over-smoothing by reducing the disorder in information propagation.
Authors: Mustafa Kamal, Niyaz Bin Hashem, Robin Krambroeckers, Nabeel Mohammed, Shafin Rahman
Abstract: Although most transformer-based time series forecasting models primarily depend on endogenous inputs, recent state-of-the-art approaches have significantly improved performance by incorporating external information through exogenous inputs. However, these methods face challenges, such as redundancy when endogenous and exogenous inputs originate from the same source and limited ability to capture long-term dependencies due to fixed look-back windows. In this paper, we propose a method that whitens the exogenous input to reduce redundancy that may persist within the data based on global statistics. Additionally, our approach helps the exogenous input to be more aware of patterns and trends over extended periods. By introducing this refined, globally context-aware exogenous input to the endogenous input without increasing the lookback window length, our approach guides the model towards improved forecasting. Our approach achieves state-of-the-art performance in four benchmark datasets, consistently outperforming 11 baseline models. These results establish our method as a robust and effective alternative for using exogenous inputs in time series forecasting.
Authors: Kimia Soroush, Mohsen Raji, Behnam Ghavami
Abstract: Deep neural networks (DNNs) have demonstrated remarkable performance in many tasks but it often comes at a high computational cost and memory usage. Compression techniques, such as pruning and quantization, are applied to reduce the memory footprint of DNNs and make it possible to accommodate them on resource-constrained edge devices. Recently, explainable artificial intelligence (XAI) methods have been introduced with the purpose of understanding and explaining AI methods. XAI can be utilized to get to know the inner functioning of DNNs, such as the importance of different neurons and features in the overall performance of DNNs. In this paper, a novel DNN compression approach using XAI is proposed to efficiently reduce the DNN model size with negligible accuracy loss. In the proposed approach, the importance score of DNN parameters (i.e. weights) are computed using a gradient-based XAI technique called Layer-wise Relevance Propagation (LRP). Then, the scores are used to compress the DNN as follows: 1) the parameters with the negative or zero importance scores are pruned and removed from the model, 2) mixed-precision quantization is applied to quantize the weights with higher/lower score with higher/lower number of bits. The experimental results show that, the proposed compression approach reduces the model size by 64% while the accuracy is improved by 42% compared to the state-of-the-art XAI-based compression method.
Authors: Manuel Ricardo Guevara Garban, Yves Chemisky, \'Etienne Pruli\`ere, Micha\"el Cl\'ement
Abstract: We propose a physics-informed machine learning framework called P-DivGNN to reconstruct local stress fields at the micro-scale, in the context of multi-scale simulation given a periodic micro-structure mesh and mean, macro-scale, stress values. This method is based in representing a periodic micro-structure as a graph, combined with a message passing graph neural network. We are able to retrieve local stress field distributions, providing average stress values produced by a mean field reduced order model (ROM) or Finite Element (FE) simulation at the macro-scale. The prediction of local stress fields are of utmost importance considering fracture analysis or the definition of local fatigue criteria. Our model incorporates physical constraints during training to constraint local stress field equilibrium state and employs a periodic graph representation to enforce periodic boundary conditions. The benefits of the proposed physics-informed GNN are evaluated considering linear and non linear hyperelastic responses applied to varying geometries. In the non-linear hyperelastic case, the proposed method achieves significant computational speed-ups compared to FE simulation, making it particularly attractive for large-scale applications.
Authors: Gianluca Dalmasso, Andrea Bragagnolo, Enzo Tartaglione, Attilio Fiandrotti, Marco Grangetto
Abstract: Hyperparameter tuning, such as learning rate decay and defining a stopping criterion, often relies on monitoring the validation loss. This paper presents NeVe, a dynamic training approach that adjusts the learning rate and defines the stop criterion based on the novel notion of "neural velocity". The neural velocity measures the rate of change of each neuron's transfer function and is an indicator of model convergence: sampling neural velocity can be performed even by forwarding noise in the network, reducing the need for a held-out dataset. Our findings show the potential of neural velocity as a key metric for optimizing neural network training efficiently
Authors: Madina Kojanazarova, Florentin Bieder, Robin Sandk\"uhler, Philippe C. Cattin
Abstract: Soft tissue simulation in virtual environments is becoming increasingly important for medical applications. However, the high deformability of soft tissue poses significant challenges. Existing methods rely on segmentation, meshing and estimation of stiffness properties of tissues. In addition, the integration of haptic feedback requires precise force estimation to enable a more immersive experience. We introduce a novel data-driven model, a conditional graph neural network (cGNN) to tackle this complexity. Our model takes surface points and the location of applied forces, and is specifically designed to predict the deformation of the points and the forces exerted on them. We trained our model on experimentally collected surface tracking data of a soft tissue phantom and used transfer learning to overcome the data scarcity by initially training it with mass-spring simulations and fine-tuning it with the experimental data. This approach improves the generalisation capability of the model and enables accurate predictions of tissue deformations and corresponding interaction forces. The results demonstrate that the model can predict deformations with a distance error of 0.35$\pm$0.03 mm for deformations up to 30 mm and the force with an absolute error of 0.37$\pm$0.05 N for forces up to 7.5 N. Our data-driven approach presents a promising solution to the intricate challenge of simulating soft tissues within virtual environments. Beyond its applicability in medical simulations, this approach holds the potential to benefit various fields where realistic soft tissue simulations are required.
Authors: Marc Bara
Abstract: Dataless neural networks represent a paradigm shift in applying neural architectures to combinatorial optimization problems, eliminating the need for training datasets by encoding problem instances directly into network parameters. Despite the pioneering work of Alkhouri et al. (2022) demonstrating the viability of dataless approaches for the Maximum Independent Set problem, our comprehensive literature review reveals that no published work has extended these methods to the Resource-Constrained Project Scheduling Problem (RCPSP). This paper addresses this gap by presenting the first dataless neural network approach for RCPSP, providing a complete mathematical framework that transforms discrete scheduling constraints into differentiable objectives suitable for gradient-based optimization. Our approach leverages smooth relaxations and automatic differentiation to unlock GPU parallelization for project scheduling, traditionally a domain of sequential algorithms. We detail the mathematical formulation for both precedence and renewable resource constraints, including a memory-efficient dense time-grid representation. Implementation and comprehensive experiments on PSPLIB benchmark instances (J30, J60, and J120) are currently underway, with empirical results to be reported in an updated version of this paper.
Authors: Chi-Chang Lee, Zhang-Wei Hong, Pulkit Agrawal
Abstract: In many reinforcement learning (RL) applications, augmenting the task rewards with heuristic rewards that encode human priors about how a task should be solved is crucial for achieving desirable performance. However, because such heuristics are usually not optimal, much human effort and computational resources are wasted in carefully balancing tasks and heuristic rewards. Theoretically rigorous ways of incorporating heuristics rely on the idea of \textit{policy invariance}, which guarantees that the performance of a policy obtained by maximizing heuristic rewards is the same as the optimal policy with respect to the task reward. However, in practice, policy invariance doesn't result in policy improvement, and such methods are known to empirically perform poorly. We propose a new paradigm to mitigate reward hacking and effectively use heuristics based on the practical goal of maximizing policy improvement instead of policy improvement. Our framework, Heuristic Enhanced Policy Optimization (HEPO), effectively leverages heuristics while avoiding the pitfall of prior methods for mitigating reward hacking. HEPO achieves superior performance on standard benchmarks with well-engineered reward functions. More surprisingly, HEPO allows policy optimization to achieve good performance even when heuristics are not well-engineered and designed by non-expert humans, showcasing HEPO's ability to reduce human effort in reward design. % HEPO is a plug-and-play optimization method for leveraging heuristics in reinforcement learning. Code is available at https://github.com/Improbable-AI/hepo.
Authors: Jeroen Audenaert, Daniel Muthukrishna, Paul F. Gregory, David W. Hogg, V. Ashley Villar
Abstract: Foundation models for structured time series data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization, especially in heterogeneous or multi-instrument settings. We present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning. Leveraging naturally occurring observational triplets (i.e., where the same target is measured under varying conditions, and distinct targets are measured under shared conditions) our model learns separate latent representations for the underlying physical signal and instrument effects. Evaluated on simulated astronomical time series designed to resemble the complexity of variable stars observed by missions like NASA's Transiting Exoplanet Survey Satellite (TESS), our method significantly outperforms traditional single-latent space foundation models on downstream prediction tasks, particularly in low-data regimes. These results demonstrate that our model supports key capabilities of foundation models, including few-shot generalization and efficient adaptation, and highlight the importance of encoding causal structure into representation learning for structured data.
Authors: Song Lai, Haohan Zhao, Rong Feng, Changyi Ma, Wenzhuo Liu, Hongbo Zhao, Xi Lin, Dong Yi, Min Xie, Qingfu Zhang, Hongbin Liu, Gaofeng Meng, Fei Zhu
Abstract: Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to specific and ever-evolving downstream tasks. While existing research has primarily concentrated on methods like data replay, model expansion, or parameter regularization, the fundamental role of the learning paradigm within CPT remains largely unexplored. This paper presents a comparative analysis of two core post-training paradigms: supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), investigating their respective impacts on knowledge retention during CPT. Our experiments are conducted on a benchmark comprising seven diverse multimodal tasks, utilizing Qwen2.5-VL-7B-Instruct as the base model for continual post-training. The investigation yields two significant findings: (1) When continuously learning on downstream tasks, SFT leads to catastrophic forgetting of previously learned tasks. In contrast, RFT inherently preserves prior knowledge and achieve performance comparable to multi-task training. (2) RFT successfully protects and even enhances the model's general knowledge on standard benchmarks (e.g., MMMU and MMLU-Pro). Conversely, SFT degrades general model capabilities severely. Further analysis shows that explicit mechanisms, such as KL penalty and chain-of-thought reasoning, are not the primary factors. Instead, we find that the implicit regularization inherent to RFT is a key factor in mitigating forgetting. Finally, we propose a rollout-based instance filtering algorithm to improve the stability and efficiency of RFT. Our comprehensive study demonstrates the superiority of RFT as a robust paradigm for continual post-training.
Authors: Luca Marzari, Ferdinando Cicalese, Alessandro Farinelli
Abstract: We present $\textbf{P}$robabilistically $\textbf{T}$ightened $\textbf{Li}$near $\textbf{R}$elaxation-based $\textbf{P}$erturbation $\textbf{A}$nalysis ($\texttt{PT-LiRPA}$), a novel framework that combines over-approximation techniques from LiRPA-based approaches with a sampling-based method to compute tight intermediate reachable sets. In detail, we show that with negligible computational overhead, $\texttt{PT-LiRPA}$ exploiting the estimated reachable sets, significantly tightens the lower and upper linear bounds of a neural network's output, reducing the computational cost of formal verification tools while providing probabilistic guarantees on verification soundness. Extensive experiments on standard formal verification benchmarks, including the International Verification of Neural Networks Competition, show that our $\texttt{PT-LiRPA}$-based verifier improves robustness certificates by up to 3.31X and 2.26X compared to related work. Importantly, our probabilistic approach results in a valuable solution for challenging competition entries where state-of-the-art formal verification methods fail, allowing us to provide answers with high confidence (i.e., at least 99%).
Authors: Mark Lee, Tom Gunter, Chang Lan, John Peebles, Hanzhi Zhou, Kelvin Zou, Sneha Bangalore, Chung-Cheng Chiu, Nan Du, Xianzhi Du, Philipp Dufter, Ruixuan Hou, Haoshuo Huang, Dongseong Hwang, Xiang Kong, Jinhao Lei, Tao Lei, Meng Li, Li Li, Jiarui Lu, Zhiyun Lu, Yiping Ma, David Qiu, Vivek Rathod, Senyu Tong, Zhucheng Tu, Jianyu Wang, Yongqiang Wang, Zirui Wang, Floris Weers, Sam Wiseman, Guoli Yin, Bowen Zhang, Xiyou Zhou, Danyang Zhuo, Cheng Leong, Ruoming Pang
Abstract: We design and implement AXLearn, a production deep learning system that facilitates scalable and high-performance training of large deep learning models. Compared to other state-of-the-art deep learning systems, AXLearn has a unique focus on modularity and support for heterogeneous hardware infrastructure. AXLearn's internal interfaces between software components follow strict encapsulation, allowing different components to be assembled to facilitate rapid model development and experimentation on heterogeneous compute infrastructure. We introduce a novel method of quantifying modularity via Lines-of-Code (LoC)-complexity, which demonstrates how our system maintains constant complexity as we scale the components in the system, compared to linear or quadratic complexity in other systems. This allows integrating features such as Rotary Position Embeddings (RoPE) into AXLearn across hundred of modules with just 10 lines of code, compared to hundreds as required in other systems. At the same time, AXLearn maintains equivalent performance compared to state-of-the-art training systems. Finally, we share our experience in the development and operation of AXLearn.
Authors: Gautam Sreekumar, Vishnu Naresh Boddeti
Abstract: We consider the problem of learning robust discriminative representations of causally-related latent variables. In addition to observational data, the training dataset also includes interventional data obtained through targeted interventions on some of these latent variables to learn representations robust against the resulting interventional distribution shifts. Existing approaches treat interventional data like observational data, even when the underlying causal model is known, and ignore the independence relations that arise from these interventions. Since these approaches do not fully exploit the causal relational information resulting from interventions, they learn representations that produce large disparities in predictive performance on observational and interventional data, which worsens when the number of interventional training samples is limited. In this paper, (1) we first identify a strong correlation between this performance disparity and adherence of the representations to the independence conditions induced by the interventional causal model. (2) For linear models, we derive sufficient conditions on the proportion of interventional data in the training dataset, for which enforcing interventional independence between representations corresponding to the intervened node and its non-descendants lowers the error on interventional data. Combining these insights, (3) we propose RepLIn, a training algorithm to explicitly enforce this statistical independence during interventions. We demonstrate the utility of RepLIn on a synthetic dataset and on real image and text datasets on facial attribute classification and toxicity detection, respectively. Our experiments show that RepLIn is scalable with the number of nodes in the causal graph and is suitable to improve the robust representations against interventional distribution shifts of both continuous and discrete latent variables.
Authors: Prady Saligram, Tanvir Bhathal
Abstract: Air pollution from agricultural emissions is a significant yet often overlooked contributor to environmental and public health challenges. Traditional air quality forecasting models rely on physics-based approaches, which struggle to capture complex, nonlinear pollutant interactions. In this work, we explore forecasting N$_2$O agricultural emissions through evaluating popular architectures, and proposing two novel deep learning architectures, EmissionNet (ENV) and EmissionNet-Transformer (ENT). These models leverage convolutional and transformer-based architectures to extract spatial-temporal dependencies from high-resolution emissions data
Authors: Edward Raff, Karen Kukla, Michel Benaroch, Joseph Comprix
Abstract: Bad actors, primarily distressed firms, have the incentive and desire to manipulate their financial reports to hide their distress and derive personal gains. As attackers, these firms are motivated by potentially millions of dollars and the availability of many publicly disclosed and used financial modeling frameworks. Existing attack methods do not work on this data due to anti-correlated objectives that must both be satisfied for the attacker to succeed. We introduce Maximum Violated Multi-Objective (MVMO) attacks that adapt the attacker's search direction to find $20\times$ more satisfying attacks compared to standard attacks. The result is that in $\approx50\%$ of cases, a company could inflate their earnings by 100-200%, while simultaneously reducing their fraud scores by 15%. By working with lawyers and professional accountants, we ensure our threat model is realistic to how such frauds are performed in practice.
Authors: Prady Saligram, Tanvir Bhathal, Robby Manihani
Abstract: Delayed and sparse rewards present a fundamental obstacle for reinforcement-learning (RL) agents, which struggle to assign credit for actions whose benefits emerge many steps later. The sliding-tile game 2048 epitomizes this challenge: although frequent small score changes yield immediate feedback, they often mislead agents into locally optimal but globally suboptimal strategies. In this work, we introduce a unified, distributional multi-step RL framework designed to directly optimize long-horizon performance. Using the open source Gym-2048 environment we develop and compare four agent variants: standard DQN, PPO, QR-DQN (Quantile Regression DQN), and a novel Horizon-DQN (H-DQN) that integrates distributional learning, dueling architectures, noisy networks, prioritized replay, and more. Empirical evaluation reveals a clear hierarchy in effectiveness: max episode scores improve from 3.988K (DQN) to 5.756K (PPO), 8.66K (QR-DQN), and 18.21K (H-DQN), with H-DQN reaching the 2048 tile. Upon scaling H-DQN it reaches a max score 41.828K and a 4096 tile. These results demonstrate that distributional, multi-step targets substantially enhance performance in sparse-reward domains, and they suggest promising avenues for further gains through model-based planning and curriculum learning.
Authors: N\'uria Armengol Urp\'i, Marin Vlastelica, Georg Martius, Stelian Coros
Abstract: Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that FB representations should fundamentally be used for exploration in order to learn more efficiently. With this goal in mind, we design exploration policies that arise naturally from the FB representation that minimize the posterior variance of the FB representation, hence minimizing its epistemic uncertainty. We empirically demonstrate that such principled exploration strategies improve sample complexity of the FB algorithm considerably in comparison to other exploration methods. Code is publicly available at https://sites.google.com/view/fbee-url.
Authors: Andrew Jacobsen, Alessandro Rudi, Francesco Orabona, Nicolo Cesa-Bianchi
Abstract: We study dynamic regret in online convex optimization, where the objective is to achieve low cumulative loss relative to an arbitrary benchmark sequence. By observing that competing with an arbitrary sequence of comparators $u_{1},\ldots,u_{T}$ in $\mathcal{W}\subseteq\mathbb{R}^{d}$ is equivalent to competing with a fixed comparator function $u:[1,T]\to \mathcal{W}$, we frame dynamic regret minimization as a static regret problem in a function space. By carefully constructing a suitable function space in the form of a Reproducing Kernel Hilbert Space (RKHS), our reduction enables us to recover the optimal $R_{T}(u_{1},\ldots,u_{T}) = \mathcal{O}(\sqrt{\sum_{t}\|u_{t}-u_{t-1}\|T})$ dynamic regret guarantee in the setting of linear losses, and yields new scale-free and directionally-adaptive dynamic regret guarantees. Moreover, unlike prior dynamic-to-static reductions -- which are valid only for linear losses -- our reduction holds for any sequence of losses, allowing us to recover $\mathcal{O}\big(\|u\|^2+d_{\mathrm{eff}}(\lambda)\ln T\big)$ bounds in exp-concave and improper linear regression settings, where $d_{\mathrm{eff}}(\lambda)$ is a measure of complexity of the RKHS. Despite working in an infinite-dimensional space, the resulting reduction leads to algorithms that are computable in practice, due to the reproducing property of RKHSs.
Authors: Van Khoa Nguyen, Lionel Blond\'e, Alexandros Kalousis
Abstract: Stochastic optimal control (SOC) has recently emerged as a principled framework for fine-tuning diffusion models. However, its dependence on computationally intensive simulations makes it impractical for fast sampling. In parallel, a class of training-free approaches has been developed that guides diffusion models using off-the-shelf classifiers on predicted clean samples, bypassing the need to train classifiers on noisy data. These methods can be interpreted as approximate SOC schemes, using Tweedie's formula to estimate diffusion posteriors. In practice, however, such direct approximations can introduce significant errors, leading to unreliable guidance. In this work, we unify the strengths of both paradigms by proposing a novel training-free diffusion guidance framework based on a surrogate stochastic optimal control objective. We derive a new theoretical bound on the value function that reveals the necessity of correcting the approximate posteriors to remain faithful to the true diffusion posterior. To this end, we connect the problem with Stein variational inference, which seeks the steepest descent direction that minimizes the Kullback-Leibler discrepancy between the two posteriors. Our method, which we refer to as Stein Diffusion Guidance (SDG), introduces a principled correction mechanism and incorporates a novel running cost functional to enable effective guidance in low-density regions. Experiments on challenging molecular generation tasks demonstrate that SDG significantly outperforms standard training-free guidance methods, highlighting its potential for broader applications.
Authors: Reza T. Batley, Chanwook Park, Wing Kam Liu, Sourav Saha
Abstract: Data-driven science and computation have advanced immensely to construct complex functional relationships using trainable parameters. However, efficiently discovering interpretable and accurate closed-form expressions from complex dataset remains a challenge. The article presents a novel approach called Explainable Hierarchical Deep Learning Neural Networks or Ex-HiDeNN that uses an accurate, frugal, fast, separable, and scalable neural architecture with symbolic regression to discover closed-form expressions from limited observation. The article presents the two-step Ex-HiDeNN algorithm with a separability checker embedded in it. The accuracy and efficiency of Ex-HiDeNN are tested on several benchmark problems, including discerning a dynamical system from data, and the outcomes are reported. Ex-HiDeNN generally shows outstanding approximation capability in these benchmarks, producing orders of magnitude smaller errors compared to reference data and traditional symbolic regression. Later, Ex-HiDeNN is applied to three engineering applications: a) discovering a closed-form fatigue equation, b) identification of hardness from micro-indentation test data, and c) discovering the expression for the yield surface with data. In every case, Ex-HiDeNN outperformed the reference methods used in the literature. The proposed method is built upon the foundation and published works of the authors on Hierarchical Deep Learning Neural Network (HiDeNN) and Convolutional HiDeNN. The article also provides a clear idea about the current limitations and future extensions of Ex-HiDeNN.
Authors: Godwin Badu-Marfo, Bilal Farooq
Abstract: We present an integrated graph-based neural networks architecture for predicting campus buildings occupancy and inter-buildings movement at dynamic temporal resolution that learns traffic flow patterns from Wi-Fi logs combined with the usage schedules within the buildings. The relative traffic flows are directly estimated from the WiFi data without assuming the occupant behaviour or preferences while maintaining individual privacy. We formulate the problem as a data-driven graph structure represented by a set of nodes (representing buildings), connected through a route of edges or links using a novel Graph Convolution plus LSTM Neural Network (GCLSTM) which has shown remarkable success in modelling complex patterns. We describe the formulation, model estimation, interpretability and examine the relative performance of our proposed model. We also present an illustrative architecture of the models and apply on real-world WiFi logs collected at the Toronto Metropolitan University campus. The results of the experiments show that the integrated GCLSTM models significantly outperform traditional pedestrian flow estimators like the Multi Layer Perceptron (MLP) and Linear Regression.
Authors: Ze'ev Zukerman, Bassel Hamoud, Kfir Y. Levy
Abstract: Distributed learning methods have gained substantial momentum in recent years, with communication overhead often emerging as a critical bottleneck. Gradient compression techniques alleviate communication costs but involve an inherent trade-off between the empirical efficiency of biased compressors and the theoretical guarantees of unbiased compressors. In this work, we introduce a novel Multilevel Monte Carlo (MLMC) compression scheme that leverages biased compressors to construct statistically unbiased estimates. This approach effectively bridges the gap between biased and unbiased methods, combining the strengths of both. To showcase the versatility of our method, we apply it to popular compressors, like Top-$k$ and bit-wise compressors, resulting in enhanced variants. Furthermore, we derive an adaptive version of our approach to further improve its performance. We validate our method empirically on distributed deep learning tasks.
Authors: Shuyang Du, Jennifer Zhang, Will Y. Zou
Abstract: User growth is a major strategy for consumer internet companies. To optimize costly marketing campaigns and maximize user engagement, we propose a novel treatment effect optimization methodology to enhance user growth marketing. By leveraging deep learning, our algorithm learns from past experiments to optimize user selection and reward allocation, maximizing campaign impact while minimizing costs. Unlike traditional prediction methods, our model directly models uplifts in key business metrics. Further, our deep learning model can jointly optimize parameters for an aggregated loss function using softmax gating. Our approach surpasses traditional methods by directly targeting desired business metrics and demonstrates superior algorithmic flexibility in handling complex business constraints. Comprehensive evaluations, including comparisons with state-of-the-art techniques such as R-learner and Causal Forest, validate the effectiveness of our model. We experimentally demonstrate that our proposed constrained and direct optimization algorithms significantly outperform state-of-the-art methods by over $20\%$, proving their cost-efficiency and real-world impact. The versatile methods can be applied to various product scenarios, including optimal treatment allocation. Its effectiveness has also been validated through successful worldwide production deployments.
Authors: Jennifer Y. Zhang, Shuyang Du, Will Y. Zou
Abstract: As estimation of Heterogeneous Treatment Effect (HTE) is increasingly adopted across a wide range of scientific and industrial applications, the treatment action space can naturally expand, from a binary treatment variable to a structured treatment policy. This policy may include several policy factors such as a continuous treatment intensity variable, or discrete treatment assignments. From first principles, we derive the formulation for incorporating multiple treatment policy variables into the functional forms of individual and average treatment effects. Building on this, we develop a methodology to directly rank subjects using aggregated HTE functions. In particular, we construct a Neural-Augmented Naive Bayes layer within a deep learning framework to incorporate an arbitrary number of factors that satisfies the Naive Bayes assumption. The factored layer is then applied with continuous treatment variables, treatment assignment, and direct ranking of aggregated treatment effect functions. Together, these algorithms build towards a generic framework for deep learning of heterogeneous treatment policies, and we show their power to improve performance with public datasets.
Authors: Anish Dhir, Cristiana Diaconu, Valentinian Mihai Lungu, James Requeima, Richard E. Turner, Mark van der Wilk
Abstract: In scientific domains -- from biology to the social sciences -- many questions boil down to \textit{What effect will we observe if we intervene on a particular variable?} If the causal relationships (e.g.~a causal graph) are known, it is possible to estimate the intervention distributions. In the absence of this domain knowledge, the causal structure must be discovered from the available observational data. However, observational data are often compatible with multiple causal graphs, making methods that commit to a single structure prone to overconfidence. A principled way to manage this structural uncertainty is via Bayesian inference, which averages over a posterior distribution on possible causal structures and functional mechanisms. Unfortunately, the number of causal structures grows super-exponentially with the number of nodes in the graph, making computations intractable. We propose to circumvent these challenges by using meta-learning to create an end-to-end model: the Model-Averaged Causal Estimation Transformer Neural Process (MACE-TNP). The model is trained to predict the Bayesian model-averaged interventional posterior distribution, and its end-to-end nature bypasses the need for expensive calculations. Empirically, we demonstrate that MACE-TNP outperforms strong Bayesian baselines. Our work establishes meta-learning as a flexible and scalable paradigm for approximating complex Bayesian causal inference, that can be scaled to increasingly challenging settings in the future.
Authors: Michalis Korakakis, Andreas Vlachos, Adrian Weller
Abstract: Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of the training data but unrelated to the task at hand. This reliance hinders generalization on minority examples, where such correlations do not hold. Existing shortcut mitigation approaches are model-specific, difficult to tune, computationally expensive, and fail to improve learned representations. To address these issues, we propose InterpoLated Learning (InterpoLL) which interpolates the representations of majority examples to include features from intra-class minority examples with shortcut-mitigating patterns. This weakens shortcut influence, enabling models to acquire features predictive across both minority and majority examples. Experimental results on multiple natural language understanding tasks demonstrate that InterpoLL improves minority generalization over both ERM and state-of-the-art shortcut mitigation methods, without compromising accuracy on majority examples. Notably, these gains persist across encoder, encoder-decoder, and decoder-only architectures, demonstrating the method's broad applicability.
Authors: Sanaz Kazemi Abharian, Sai Manoj Pudukotai Dinakarrao
Abstract: Graph Neural Networks (GNNs) have emerged as a powerful machine learning method for graph-structured data. A plethora of hardware accelerators has been introduced to meet the performance demands of GNNs in real-world applications. However, security challenges of hardware-based attacks have been generally overlooked. In this paper, we investigate the vulnerability of GNN models to hardware-based fault attack, wherein an attacker attempts to misclassify output by modifying trained weight parameters through fault injection in a memory device. Thus, we propose Gradual Bit-Flip Fault Attack (GBFA), a layer-aware bit-flip fault attack, selecting a vulnerable bit in each selected weight gradually to compromise the GNN's performance by flipping a minimal number of bits. To achieve this, GBFA operates in two steps. First, a Markov model is created to predict the execution sequence of layers based on features extracted from memory access patterns, enabling the launch of the attack within a specific layer. Subsequently, GBFA identifies vulnerable bits within the selected weights using gradient ranking through an in-layer search. We evaluate the effectiveness of the proposed GBFA attack on various GNN models for node classification tasks using the Cora and PubMed datasets. Our findings show that GBFA significantly degrades prediction accuracy, and the variation in its impact across different layers highlights the importance of adopting a layer-aware attack strategy in GNNs. For example, GBFA degrades GraphSAGE's prediction accuracy by 17% on the Cora dataset with only a single bit flip in the last layer.
Authors: Jiawei Sun, Hongkang Li, Meng Wang
Abstract: Jumping connections enable Graph Convolutional Networks (GCNs) to overcome over-smoothing, while graph sparsification reduces computational demands by selecting a sub-matrix of the graph adjacency matrix during neighborhood aggregation. Learning GCNs with graph sparsification has shown empirical success across various applications, but a theoretical understanding of the generalization guarantees remains limited, with existing analyses ignoring either graph sparsification or jumping connections. This paper presents the first learning dynamics and generalization analysis of GCNs with jumping connections using graph sparsification. Our analysis demonstrates that the generalization accuracy of the learned model closely approximates the highest achievable accuracy within a broad class of target functions dependent on the proposed sparse effective adjacency matrix $A^*$. Thus, graph sparsification maintains generalization performance when $A^*$ preserves the essential edges that support meaningful message propagation. We reveal that jumping connections lead to different sparsification requirements across layers. In a two-hidden-layer GCN, the generalization is more affected by the sparsified matrix deviations from $A^*$ of the first layer than the second layer. To the best of our knowledge, this marks the first theoretical characterization of jumping connections' role in sparsification requirements. We validate our theoretical results on benchmark datasets in deep GCNs.
Authors: Chunhui Gu, Mohammad Sadegh Nasr, James P. Long, Kim-Anh Do, Ehsan Irajizad
Abstract: Graph Neural Networks (GNNs) often struggle with noisy edges. We propose Latent Space Constrained Graph Neural Networks (LSC-GNN) to incorporate external "clean" links and guide embeddings of a noisy target graph. We train two encoders--one on the full graph (target plus external edges) and another on a regularization graph excluding the target's potentially noisy links--then penalize discrepancies between their latent representations. This constraint steers the model away from overfitting spurious edges. Experiments on benchmark datasets show LSC-GNN outperforms standard and noise-resilient GNNs in graphs subjected to moderate noise. We extend LSC-GNN to heterogeneous graphs and validate it on a small protein-metabolite network, where metabolite-protein interactions reduce noise in protein co-occurrence data. Our results highlight LSC-GNN's potential to boost predictive performance and interpretability in settings with noisy relational structures.
Authors: Jingyi Gao, Sol Lim, Seokhyun Chung
Abstract: Machine learning methods are increasingly applied to ergonomic risk assessment in manual material handling, particularly for estimating carried load from gait motion data collected from wearable sensors. However, existing approaches often rely on direct mappings from loaded gait to hand load, limiting generalization and predictive accuracy. In this study, we propose an enhanced load estimation framework that incorporates auxiliary information, including baseline gait patterns during unloaded walking and carrying style. While baseline gait can be automatically captured by wearable sensors and is thus readily available at inference time, carrying style typically requires manual labeling and is often unavailable during deployment. Our model integrates deep latent variable modeling with temporal convolutional networks and bi-directional cross-attention to capture gait dynamics and fuse loaded and unloaded gait patterns. Guided by domain knowledge, the model is designed to estimate load magnitude conditioned on carrying style, while eliminating the need for carrying style labels at inference time. Experiments using real-world data collected from inertial measurement units attached to participants demonstrate substantial accuracy gains from incorporating auxiliary information and highlight the importance of explicit fusion mechanisms over naive feature concatenation.
Authors: Wilka Carvalho, Sam Hall-McMaster, Honglak Lee, Samuel J. Gershman
Abstract: Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans leverage experience on one task to preemptively learn solutions to other tasks that were accessible but not pursued. We formalize this idea as Multitask Preplay, a novel algorithm that replays experience on one task as the starting point for "preplay" -- counterfactual simulation of an accessible but unpursued task. Preplay is used to learn a predictive representation that can support fast, adaptive task performance later on. We first show that, compared to traditional planning and predictive representation methods, multitask preplay better predicts how humans generalize to tasks that were accessible but not pursued in a small grid-world, even when people didn't know they would need to generalize to these tasks. We then show these predictions generalize to Craftax, a partially observable 2D Minecraft environment. Finally, we show that Multitask Preplay enables artificial agents to learn behaviors that transfer to novel Craftax worlds sharing task co-occurrence structure. These findings demonstrate that Multitask Preplay is a scalable theory of how humans counterfactually learn and generalize across multiple tasks; endowing artificial agents with the same capacity can significantly improve their performance in challenging multitask environments.
Authors: Alexander Xiong, Xuandong Zhao, Aneesh Pappu, Dawn Song
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks, and the boundary between learning and memorization. Addressing these concerns, this paper synthesizes recent studies and investigates the landscape of memorization, the factors influencing it, and methods for its detection and mitigation. We explore key drivers, including training data duplication, training dynamics, and fine-tuning procedures that influence data memorization. In addition, we examine methodologies such as prefix-based extraction, membership inference, and adversarial prompting, assessing their effectiveness in detecting and measuring memorized content. Beyond technical analysis, we also explore the broader implications of memorization, including the legal and ethical implications. Finally, we discuss mitigation strategies, including data cleaning, differential privacy, and post-training unlearning, while highlighting open challenges in balancing the minimization of harmful memorization with utility. This paper provides a comprehensive overview of the current state of research on LLM memorization across technical, privacy, and performance dimensions, identifying critical directions for future work.
Authors: Yuhang Li, Shiqi Chen, Tingyu Gong, Aydogan Ozcan
Abstract: Optical computing holds promise for high-speed, energy-efficient information processing, with diffractive optical networks emerging as a flexible platform for implementing task-specific transformations. A challenge, however, is the effective optimization and alignment of the diffractive layers, which is hindered by the difficulty of accurately modeling physical systems with their inherent hardware imperfections, noise, and misalignments. While existing in situ optimization methods offer the advantage of direct training on the physical system without explicit system modeling, they are often limited by slow convergence and unstable performance due to inefficient use of limited measurement data. Here, we introduce a model-free reinforcement learning approach utilizing Proximal Policy Optimization (PPO) for the in situ training of diffractive optical processors. PPO efficiently reuses in situ measurement data and constrains policy updates to ensure more stable and faster convergence. We experimentally validated our method across a range of in situ learning tasks, including targeted energy focusing through a random diffuser, holographic image generation, aberration correction, and optical image classification, demonstrating in each task better convergence and performance. Our strategy operates directly on the physical system and naturally accounts for unknown real-world imperfections, eliminating the need for prior system knowledge or modeling. By enabling faster and more accurate training under realistic experimental constraints, this in situ reinforcement learning approach could offer a scalable framework for various optical and physical systems governed by complex, feedback-driven dynamics.
Authors: Beibei Li
Abstract: In this work we propose a unified Fourier Spectral Transformer network that integrates the strengths of classical spectral methods and attention based neural architectures. By transforming the original PDEs into spectral ordinary differential equations, we use high precision numerical solvers to generate training data and use a Transformer network to model the evolution of the spectral coefficients. We demonstrate the effectiveness of our approach on the two dimensional incompressible Navier-Stokes equations and the one dimensional Burgers' equation. The results show that our spectral Transformer can achieve highly accurate long term predictions even with limited training data, better than traditional numerical methods and machine learning methods in forecasting future flow dynamics. The proposed framework generalizes well to unseen data, bringing a promising paradigm for real time prediction and control of complex dynamical systems.
Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Abstract: Reward hacking in Reinforcement Learning (RL) systems poses a critical threat to the deployment of autonomous agents, where agents exploit flaws in reward functions to achieve high scores without fulfilling intended objectives. Despite growing awareness of this problem, systematic detection and mitigation approaches remain limited. This paper presents a large-scale empirical study of reward hacking across diverse RL environments and algorithms. We analyze 15,247 training episodes across 15 RL environments (Atari, MuJoCo, custom domains) and 5 algorithms (PPO, SAC, DQN, A3C, Rainbow), implementing automated detection algorithms for six categories of reward hacking: specification gaming, reward tampering, proxy optimization, objective misalignment, exploitation patterns, and wireheading. Our detection framework achieves 78.4% precision and 81.7% recall across environments, with computational overhead under 5%. Through controlled experiments varying reward function properties, we demonstrate that reward density and alignment with true objectives significantly impact hacking frequency ($p < 0.001$, Cohen's $d = 1.24$). We validate our approach through three simulated application studies representing recommendation systems, competitive gaming, and robotic control scenarios. Our mitigation techniques reduce hacking frequency by up to 54.6% in controlled scenarios, though we find these trade-offs are more challenging in practice due to concept drift, false positive costs, and adversarial adaptation. All detection algorithms, datasets, and experimental protocols are publicly available to support reproducible research in RL safety.
Authors: Feng Xia, Ciyuan Peng, Jing Ren, Falih Gozi Febrinanto, Renqiang Luo, Vidya Saikrishna, Shuo Yu, Xiangjie Kong
Abstract: Graph learning has rapidly evolved into a critical subfield of machine learning and artificial intelligence (AI). Its development began with early graph-theoretic methods, gaining significant momentum with the advent of graph neural networks (GNNs). Over the past decade, progress in scalable architectures, dynamic graph modeling, multimodal learning, generative AI, explainable AI (XAI), and responsible AI has broadened the applicability of graph learning to various challenging environments. Graph learning is significant due to its ability to model complex, non-Euclidean relationships that traditional machine learning struggles to capture, thus better supporting real-world applications ranging from drug discovery and fraud detection to recommender systems and scientific reasoning. However, challenges like scalability, generalization, heterogeneity, interpretability, and trustworthiness must be addressed to unlock its full potential. This survey provides a comprehensive introduction to graph learning, focusing on key dimensions including scalable, temporal, multimodal, generative, explainable, and responsible graph learning. We review state-of-the-art techniques for efficiently handling large-scale graphs, capturing dynamic temporal dependencies, integrating heterogeneous data modalities, generating novel graph samples, and enhancing interpretability to foster trust and transparency. We also explore ethical considerations, such as privacy and fairness, to ensure responsible deployment of graph learning models. Additionally, we identify and discuss emerging topics, highlighting recent integration of graph learning and other AI paradigms and offering insights into future directions. This survey serves as a valuable resource for researchers and practitioners seeking to navigate the rapidly evolving landscape of graph learning.
Authors: Enric Boix-Adsera, Neil Mallinar, James B. Simon, Mikhail Belkin
Abstract: A central challenge in deep learning theory is to understand how neural networks learn and represent features. To this end, we prove the Features at Convergence Theorem (FACT), which gives a self-consistency equation that neural network weights satisfy at convergence when trained with nonzero weight decay. For each weight matrix $W$, this equation relates the "feature matrix" $W^\top W$ to the set of input vectors passed into the matrix during forward propagation and the loss gradients passed through it during backpropagation. We validate this relation empirically, showing that neural features indeed satisfy the FACT at convergence. Furthermore, by modifying the "Recursive Feature Machines" of Radhakrishnan et al. 2024 so that they obey the FACT, we arrive at a new learning algorithm, FACT-RFM. FACT-RFM achieves high performance on tabular data and captures various feature learning behaviors that occur in neural network training, including grokking in modular arithmetic and phase transitions in learning sparse parities.
Authors: Netta Palez, L\'eonie Stra{\ss}, Sebastian Meller, Holger Volk, Anna Zamansky, Itzik Klein
Abstract: Canine gait analysis using wearable inertial sensors is gaining attention in veterinary clinical settings, as it provides valuable insights into a range of mobility impairments. Neurological and orthopedic conditions cannot always be easily distinguished even by experienced clinicians. The current study explored and developed a deep learning approach using inertial sensor readings to assess whether neurological and orthopedic gait could facilitate gait analysis. Our investigation focused on optimizing both performance and generalizability in distinguishing between these gait abnormalities. Variations in sensor configurations, assessment protocols, and enhancements to deep learning model architectures were further suggested. Using a dataset of 29 dogs, our proposed approach achieved 96% accuracy in the multiclass classification task (healthy/orthopedic/neurological) and 82% accuracy in the binary classification task (healthy/non-healthy) when generalizing to unseen dogs. Our results demonstrate the potential of inertial-based deep learning models to serve as a practical and objective diagnostic and clinical aid to differentiate gait assessment in orthopedic and neurological conditions.
Authors: Xiaobing Chen, Boyang Zhang, Xiangwei Zhou, Mingxuan Sun, Shuai Zhang, Songyang Zhang, Geoffrey Ye Li
Abstract: The integration of Federated Learning (FL) and Mixture-of-Experts (MoE) presents a compelling pathway for training more powerful, large-scale artificial intelligence models (LAMs) on decentralized data while preserving privacy. However, efficient federated training of these complex MoE-structured LAMs is hindered by significant system-level challenges, particularly in managing the interplay between heterogeneous client resources and the sophisticated coordination required for numerous specialized experts. This article highlights a critical, yet underexplored concept: the absence of robust quantitative strategies for dynamic client-expert alignment that holistically considers varying client capacities and the imperative for system-wise load balancing. Specifically, we propose a conceptual system design for intelligent client-expert alignment that incorporates dynamic fitness scoring, global expert load monitoring, and client capacity profiling. By tackling these systemic issues, we can unlock more scalable, efficient, and robust training mechanisms {with fewer communication rounds for convergence}, paving the way for the widespread deployment of large-scale federated MoE-structured LAMs in edge computing with ultra-high communication efficiency.
Authors: Shangzhan Li, Zefan Wang, Ye He, Yuxuan Li, Qi Shi, Jianling Li, Yonggang Hu, Wanxiang Che, Xu Han, Zhiyuan Liu, Maosong Sun
Abstract: Kernel development in deep learning requires optimizing computational units across hardware while balancing memory management, parallelism, and hardware-specific optimizations through extensive empirical tuning. Although domain-specific languages like Triton simplify GPU programming by abstracting low-level details, developers must still manually tune critical parameters such as tile sizes and memory access patterns through iterative experimentation, creating substantial barriers to optimal performance and wider adoption. In this work, we introduce AutoTriton, the first model dedicated to Triton programming powered by reinforcement learning (RL). AutoTriton performs supervised fine-tuning (SFT) to be equipped with essential Triton programming expertise using a high-quality data gathering pipeline, and conducts RL with Group Relative Policy Optimization (GRPO) algorithm, combining a rule-based reward and an execution-based reward to further improve Triton programming ability, sequentially. Experiments across five evaluation channels of TritonBench and KernelBench illustrate that our 8B model AutoTriton achieves performance comparable to mainstream large models, including Claude-4-Sonnet and DeepSeek-R1-0528. Further experimental analysis demonstrates the crucial role of each module within AutoTriton, including the SFT stage, the RL stage, and the reward design strategy. These findings underscore the promise of RL for automatically generating high-performance kernels, and since high-performance kernels are core components of AI systems, this breakthrough establishes an important foundation for building more efficient AI systems. The model and code will be available at https://github.com/AI9Stars/AutoTriton.
Authors: Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, Dong Yu
Abstract: Recently, there has been a surge of vision-based GUI agents designed to automate everyday mobile and web tasks. These agents interpret raw GUI screenshots and autonomously decide where to click, scroll, or type, which bypasses handcrafted rules and app-specific APIs. However, most existing methods trained GUI agent in the offline environment using pre-collected trajectories. This approach limits scalability, causes overfitting to specific UI templates, and leads to brittle policies when faced with unseen environment. We present MobileGUI-RL, a scalable framework that trains GUI agent in online environment. MobileGUI-RL contains two key components. It (i) synthesizes a curriculum of learnable tasks through self-exploration and filtering, and (ii) adapts GRPO to GUI navigation with trajectory-aware advantages and composite rewards that balance task success and execution efficiency. Experiments on three online mobile-agent benchmarks show consistent gains, validating the effectiveness of our approach.
Authors: Hongbao Li, Ziye Jia, Sijie He, Kun Guo, Qihui Wu
Abstract: With the emergence of compute-intensive and delay-sensitive applications in vehicular networks, unmanned aerial vehicles (UAVs) have emerged as a promising complement for vehicular edge computing due to the high mobility and flexible deployment. However, the existing UAV-assisted offloading strategies are insufficient in coordinating heterogeneous computing resources and adapting to dynamic network conditions. Hence, this paper proposes a dual-layer UAV-assisted edge computing architecture based on partial offloading, composed of the relay capability of high-altitude UAVs and the computing support of low-altitude UAVs. The proposed architecture enables efficient integration and coordination of heterogeneous resources. A joint optimization problem is formulated to minimize the system delay and energy consumption while ensuring the task completion rate. To solve the high-dimensional decision problem, we reformulate the problem as a Markov decision process and propose a hierarchical offloading scheme based on the soft actor-critic algorithm. The method decouples global and local decisions, where the global decisions integrate offloading ratios and trajectory planning into continuous actions, while the local scheduling is handled via designing a priority-based mechanism. Simulations are conducted and demonstrate that the proposed approach outperforms several baselines in task completion rate, system efficiency, and convergence speed, showing strong robustness and applicability in dynamic vehicular environments.
Authors: Deifilia Kieckhefen, Markus G\"otz, Lars H. Heyen, Achim Streit, Charlotte Debus
Abstract: AI-based methods have revolutionized atmospheric forecasting, with recent successes in medium-range forecasting spurring the development of climate foundation models. Accurate modeling of complex atmospheric dynamics at high spatial resolutions and longer lead times requires large neural networks and gigabyte-sized data samples, making accelerator memory and I/O-bandwidth the bottlenecks for model training. We introduce WeatherMixer, a multi-layer-perceptron-based architecture whose workload scales linearly with input size, allowing the model to learn global weather phenomena at accuracies similar to numerical weather prediction. To cope with the computational demand, we propose Jigsaw, a novel model parallelization scheme that employs both domain and tensor parallelism, eliminating memory redundancy. Jigsaw exceeds state-of-the-art performance in strong scaling in compute-communication-limited systems and achieves superscalar weak scaling in I/O-bandwidth-limited systems. We scale training to 256 GPUs, reaching peak performances of 9 and 11 PFLOPs, 23% and 28% of theoretical peaks, achieving 68% and 72% scaling efficiency versus 51% without model parallelism.
Authors: Comte Valentin, Gemma Piella, Mario Ceresa, Miguel A. Gonzalez Ballester
Abstract: Cardiac diseases are among the leading causes of morbidity and mortality worldwide, which requires accurate and timely diagnostic strategies. In this study, we introduce an innovative approach that combines deep learning image registration with physics-informed regularization to predict the biomechanical properties of moving cardiac tissues and extract features for disease classification. We utilize the energy strain formulation of Neo-Hookean material to model cardiac tissue deformations, optimizing the deformation field while ensuring its physical and biomechanical coherence. This explainable approach not only improves image registration accuracy, but also provides insights into the underlying biomechanical processes of the cardiac tissues. Evaluation on the Automated Cardiac Diagnosis Challenge (ACDC) dataset achieved Dice scores of 0.945 for the left ventricular cavity, 0.908 for the right ventricular cavity, and 0.905 for the myocardium. Subsequently, we estimate the local strains within the moving heart and extract a detailed set of features used for cardiovascular disease classification. We evaluated five classification algorithms, Logistic Regression, Multi-Layer Perceptron, Support Vector Classifier, Random Forest, and Nearest Neighbour, and identified the most relevant features using a feature selection algorithm. The best performing classifier obtained a classification accuracy of 98% in the training set and 100% in the test set of the ACDC dataset. By integrating explainable artificial intelligence, this method empowers clinicians with a transparent understanding of the model's predictions based on cardiac mechanics, while also significantly improving the accuracy and reliability of cardiac disease diagnosis, paving the way for more personalized and effective patient care.
Authors: Sevvandi Kandanaarachchi, Ziqi Xu, Stefan Westerlund, Conrad Sanderson
Abstract: Many dynamic processes such as telecommunication and transport networks can be described through discrete time series of graphs. Modelling the dynamics of such time series enables prediction of graph structure at future time steps, which can be used in applications such as detection of anomalies. Existing approaches for graph prediction have limitations such as assuming that the vertices do not to change between consecutive graphs. To address this, we propose to exploit time series prediction methods in combination with an adapted form of flux balance analysis (FBA), a linear programming method originating from biochemistry. FBA is adapted to incorporate various constraints applicable to the scenario of growing graphs. Empirical evaluations on synthetic datasets (constructed via Preferential Attachment model) and real datasets (UCI Message, HePH, Facebook, Bitcoin) demonstrate the efficacy of the proposed approach.
Authors: Marco Roschkowski
Abstract: In this paper, we tackle two fundamental problems in few-shot domain adaptation of foundation models. First, hyperparameter tuning is often impractical due to the lack of large validation datasets. Second, model robustness under distribution shifts where test time data deviates slightly from training distributions, remains a concern. We show that by training multiple independent adapters and averaging their outputs, the new model has a higher performance and is more robust to distribution shifts compared to any individual adapter. This improvement holds even when the adapters are trained with diverse hyperparameters sampled from a wide range, resulting in varied individual performance. Consequently, our method addresses both of the problems described above. The ensemble is also significantly less sensitive to the residual ratio, a critical hyperparameter of CLIP-Adapter. Since the ensemble can be reparameterized to a single adapter again using a principled concatenation of the parameters, we refer to our method as Soup-Adapter. This is also the first study to explore CLIP adapter-style techniques for DINOv2 and to directly compare them with CLIP in this setting.
Authors: Sofiia Chorna, Kateryna Tarelkina, Elo\"ise Berthier, Gianni Franchi
Abstract: While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic interpretability. Our approach enables a global dissection of model behavior by analyzing how high-level semantic attributes (referred to as concepts) emerge, interact, and propagate through internal model components. Unlike prior work that isolates individual neurons or predictions, our framework systematically quantifies how semantic concepts are represented across layers, revealing latent circuits and information flow that underlie model decision-making. A key innovation is our visualization platform that we named BAGEL (for Bias Analysis with a Graph for global Explanation Layers), which presents these insights in a structured knowledge graph, allowing users to explore concept-class relationships, identify spurious correlations, and enhance model trustworthiness. Our framework is model-agnostic, scalable, and contributes to a deeper understanding of how deep learning models generalize (or fail to) in the presence of dataset biases. The demonstration is available at https://knowledge-graph-ui-4a7cb5.gitlab.io/.
Authors: Tangzheng Lian, Guanyu Hu, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan
Abstract: Domain generalization (DG) and algorithmic fairness are two critical challenges in machine learning. However, most DG methods focus only on minimizing expected risk in the unseen target domain without considering algorithmic fairness. Conversely, fairness methods typically do not account for domain shifts, so the fairness achieved during training may not generalize to unseen test domains. In this work, we bridge these gaps by studying the problem of Fair Domain Generalization (FairDG), which aims to minimize both expected risk and fairness violations in unseen target domains. We derive novel mutual information-based upper bounds for expected risk and fairness violations in multi-class classification tasks with multi-group sensitive attributes. These bounds provide key insights for algorithm design from an information-theoretic perspective. Guided by these insights, we introduce PAFDG (Pareto-Optimal Fairness for Domain Generalization), a practical framework that solves the FairDG problem and models the utility-fairness trade-off through Pareto optimization. Experiments on real-world vision and language datasets show that PAFDG achieves superior utility-fairness trade-offs compared to existing methods.
Authors: Samuel Ofosu Mensah, Kerol Djoumessi, Philipp Berens
Abstract: Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless, real-world FL often faces major challenges including communication overhead during the transfer of large model parameters and statistical heterogeneity, arising from non-identical independent data distributions across clients. In this work, we propose an FL framework that 1) provides inherent interpretations using prototypes, and 2) tackles statistical heterogeneity by utilising lightweight adapter modules to act as compressed surrogates of local models and guide clients to achieve generalisation despite varying client distribution. Each client locally refines its model by aligning class embeddings toward prototype representations and simultaneously adjust the lightweight adapter. Our approach replaces the need to communicate entire model weights with prototypes and lightweight adapters. This design ensures that each client's model aligns with a globally shared structure while minimising communication load and providing inherent interpretations. Moreover, we conducted our experiments on a real-world retinal fundus image dataset, which provides clinical-site information. We demonstrate inherent interpretable capabilities and perform a classification task, which shows improvements in accuracy over baseline algorithms.
Authors: Solon Falas, Markos Asprou, Charalambos Konstantinou, Maria K. Michael
Abstract: Modern power systems face significant challenges in state estimation and real-time monitoring, particularly regarding response speed and accuracy under faulty conditions or cyber-attacks. This paper proposes a hybrid approach using physics-informed neural networks (PINNs) to enhance the accuracy and robustness, of power system state estimation. By embedding physical laws into the neural network architecture, PINNs improve estimation accuracy for transmission grid applications under both normal and faulty conditions, while also showing potential in addressing security concerns such as data manipulation attacks. Experimental results show that the proposed approach outperforms traditional machine learning models, achieving up to 83% higher accuracy on unseen subsets of the training dataset and 65% better performance on entirely new, unrelated datasets. Experiments also show that during a data manipulation attack against a critical bus in a system, the PINN can be up to 93% more accurate than an equivalent neural network.
Authors: Astrid Franz, Frederik Hoppe, Marianne Michaelis, Udo G\"obel
Abstract: Tabular data in relational databases represents a significant portion of industrial data. Hence, analyzing and interpreting tabular data is of utmost importance. Application tasks on tabular data are manifold and are often not specified when setting up an industrial database. To address this, we present a novel framework for generating universal, i.e., task-independent embeddings of tabular data for performing downstream tasks without predefined targets. Our method transforms tabular data into a graph structure, leverages Graph Auto-Encoders to create entity embeddings, which are subsequently aggregated to obtain embeddings for each table row, i.e., each data sample. This two-step approach has the advantage that unseen samples, consisting of similar entities, can be embedded without additional training. Downstream tasks such as regression, classification or outlier detection, can then be performed by applying a distance-based similarity measure in the embedding space. Experiments on real-world datasets demonstrate that our method achieves superior performance compared to existing universal tabular data embedding techniques.
Authors: Chenhao Li, Marco Hutter, Andreas Krause
Abstract: This survey provides a comparative analysis of feature-based and GAN-based approaches to learning from demonstrations, with a focus on the structure of reward functions and their implications for policy learning. Feature-based methods offer dense, interpretable rewards that excel at high-fidelity motion imitation, yet often require sophisticated representations of references and struggle with generalization in unstructured settings. GAN-based methods, in contrast, use implicit, distributional supervision that enables scalability and adaptation flexibility, but are prone to training instability and coarse reward signals. Recent advancements in both paradigms converge on the importance of structured motion representations, which enable smoother transitions, controllable synthesis, and improved task integration. We argue that the dichotomy between feature-based and GAN-based methods is increasingly nuanced: rather than one paradigm dominating the other, the choice should be guided by task-specific priorities such as fidelity, diversity, interpretability, and adaptability. This work outlines the algorithmic trade-offs and design considerations that underlie method selection, offering a framework for principled decision-making in learning from demonstrations.
Authors: Rui Huang, Shitong Shao, Zikai Zhou, Pukun Zhao, Hangyu Guo, Tian Ye, Lichen Bai, Shuo Yang, Zeke Xie
Abstract: Diffusion models have achieved remarkable success in various generative tasks, but training them remains highly resource-intensive, often requiring millions of images and many days of GPU computation. From a data-centric perspective addressing this limitation, we study diffusion dataset condensation as a new and challenging problem setting. The goal is to construct a "synthetic" sub-dataset with significantly fewer samples than the original dataset, enabling high-quality diffusion model training with greatly reduced cost. To the best of our knowledge, we are the first to formally investigate dataset condensation for diffusion models, whereas prior work focused on training discriminative models. To tackle this new challenge, we propose a novel Diffusion Dataset Condensation (D2C) framework, which consists of two phases: Select and Attach. The Select phase identifies a compact and diverse subset using a diffusion difficulty score and interval sampling. The Attach phase enhances the selected subset by attaching rich semantic and visual representations to strengthen the conditional signals. Extensive experiments across various dataset sizes, model architectures, and resolutions show that our D2C framework enables significantly faster diffusion model training with dramatically fewer data, while preserving high visual quality. Notably, for the SiT-XL/2 architecture, D2C achieves a 100x training speed-up, reaching a FID score of 4.3 in just 40k steps using only 0.8% of the training data.
Authors: Pinar Bisgin, Tom Strube, Niklas Tschorn, Michael Pantf\"order, Maximilian Fecke, Ingrid Ljungvall, Jens H\"aggstr\"om, Gerhard Wess, Christoph Schummer, Sven Meister, Falk M. Howar
Abstract: Noisy labels pose significant challenges for AI model training in veterinary medicine. This study examines expert assessment ambiguity in canine auscultation data, highlights the negative impact of label noise on classification performance, and introduces methods for label noise reduction. To evaluate whether label noise can be minimized by incorporating multiple expert opinions, a dataset of 140 heart sound recordings (HSR) was annotated regarding the intensity of holosystolic heart murmurs caused by Myxomatous Mitral Valve Disease (MMVD). The expert opinions facilitated the selection of 70 high-quality HSR, resulting in a noise-reduced dataset. By leveraging individual heart cycles, the training data was expanded and classification robustness was enhanced. The investigation encompassed training and evaluating three classification algorithms: AdaBoost, XGBoost, and Random Forest. While AdaBoost and Random Forest exhibited reasonable performances, XGBoost demonstrated notable improvements in classification accuracy. All algorithms showed significant improvements in classification accuracy due to the applied label noise reduction, most notably XGBoost. Specifically, for the detection of mild heart murmurs, sensitivity increased from 37.71% to 90.98% and specificity from 76.70% to 93.69%. For the moderate category, sensitivity rose from 30.23% to 55.81% and specificity from 64.56% to 97.19%. In the loud/thrilling category, sensitivity and specificity increased from 58.28% to 95.09% and from 84.84% to 89.69%, respectively. These results highlight the importance of minimizing label noise to improve classification algorithms for the detection of canine heart murmurs. Index Terms: AI diagnosis, canine heart disease, heart sound classification, label noise reduction, machine learning, XGBoost, veterinary cardiology, MMVD.
Authors: Hanyang Peng, Shuang Qin, Yue Yu, Fangqing Jiang, Hui Wang, Zhouchen Lin
Abstract: Adam is widely recognized as one of the most effective optimizers for training deep neural networks (DNNs). Despite its remarkable empirical success, its theoretical convergence analysis remains unsatisfactory. Existing works predominantly interpret Adam as a preconditioned stochastic gradient descent with momentum (SGDM), formulated as $\bm{x}_{t+1} = \bm{x}_t - \frac{\gamma_t}{{\sqrt{\bm{v}_t}+\epsilon}} \circ \bm{m}_t$. This perspective necessitates strong assumptions and intricate techniques, resulting in lengthy and opaque convergence proofs that are difficult to verify and extend. In contrast, we propose a novel interpretation by treating Adam as a sign-like optimizer, expressed as $\bm{x}_{t+1} = \bm{x}_t - \gamma_t \frac{|\bm{m}_t|}{{\sqrt{\bm{v}_t}+\epsilon}} \circ {\rm Sign}(\bm{m}_t)$. This reformulation significantly simplifies the convergence analysis. For the first time, with some mild conditions, we prove that Adam achieves the optimal rate of ${\cal O}(\frac{1}{T^{\sfrac{1}{4}}})$ rather than the previous ${\cal O} \left(\frac{\ln T}{T^{\sfrac{1}{4}}}\right)$ under weak assumptions of the generalized $p$-affine variance and $(L_0, L_1, q)$-smoothness, without dependence on the model dimensionality or the numerical stability parameter $\epsilon$. Additionally, our theoretical analysis provides new insights into the role of momentum as a key factor ensuring convergence and offers practical guidelines for tuning learning rates in Adam, further bridging the gap between theory and practice.
Authors: M. W. Theunissen, R. Rabe, M. H. Davel
Abstract: KnowIt (Knowledge discovery in time series data) is a flexible framework for building deep time series models and interpreting them. It is implemented as a Python toolkit, with source code and documentation available from https://must-deep-learning.github.io/KnowIt. It imposes minimal assumptions about task specifications and decouples the definition of dataset, deep neural network architecture, and interpretability technique through well defined interfaces. This ensures the ease of importing new datasets, custom architectures, and the definition of different interpretability paradigms while maintaining on-the-fly modeling and interpretation of different aspects of a user's own time series data. KnowIt aims to provide an environment where users can perform knowledge discovery on their own complex time series data through building powerful deep learning models and explaining their behavior. With ongoing development, collaboration and application our goal is to make this a platform to progress this underexplored field and produce a trusted tool for deep time series modeling.
Authors: George Barrowclough, Marian Andrecki, James Shinner, Daniele Donghi
Abstract: In production recommender systems, feature preprocessing must be faithfully replicated across training and inference environments. This often requires duplicating logic between offline and online environments, increasing engineering effort and introducing risks of dataset shift. We present Kamae, an open-source Python library that bridges this gap by translating PySpark preprocessing pipelines into equivalent Keras models. Kamae provides a suite of configurable Spark transformers and estimators, each mapped to a corresponding Keras layer, enabling consistent, end-to-end preprocessing across the ML lifecycle. Framework's utility is illustrated on real-world use cases, including MovieLens dataset and Expedia's Learning-to-Rank pipelines. The code is available at https://github.com/ExpediaGroup/kamae.
Authors: Lynn Houthuys
Abstract: The high-dimensional low-sample-size (HDLSS) setting presents significant challenges in various applications where the feature dimension far exceeds the number of available samples. This paper introduces a universal approach for learning in HDLSS setting using multi-view mid fusion techniques. It shows how existing mid fusion multi-view methods perform well in an HDLSS setting even if no inherent views are provided. Three view construction methods are proposed that split the high-dimensional feature vectors into smaller subsets, each representing a different view. Extensive experimental validation across model-types and learning tasks confirm the effectiveness and generalization of the approach. We believe the work in this paper lays the foundation for further research into the universal benefits of multi-view mid fusion learning.
Authors: Benjamin Hodo (D-ITET, ETH Z\"urich, Switzerland), Tommaso Polonelli (D-ITET, ETH Z\"urich, Switzerland), Amirhossein Moallemi (RTDT Laboratories, Switzerland), Luca Benini (D-ITET, ETH Z\"urich, Switzerland), Michele Magno (D-ITET, ETH Z\"urich, Switzerland)
Abstract: We present EdgeCodec, an end-to-end neural compressor for barometric data collected from wind turbine blades. EdgeCodec leverages a heavily asymmetric autoencoder architecture, trained with a discriminator and enhanced by a Residual Vector Quantizer to maximize compression efficiency. It achieves compression rates between 2'560:1 and 10'240:1 while maintaining a reconstruction error below 3%, and operates in real time on the GAP9 microcontroller with bitrates ranging from 11.25 to 45 bits per second. Bitrates can be selected on a sample-by-sample basis, enabling on-the-fly adaptation to varying network conditions. In its highest compression mode, EdgeCodec reduces the energy consumption of wireless data transmission by up to 2.9x, significantly extending the operational lifetime of deployed sensor units.
Authors: Julia Pelzer, Corn\'e Verburg, Alexander Heinlein, Miriam Schulte
Abstract: Machine learning methods often struggle with real-world applications in science and engineering due to limited or low-quality training data. In this work, the example of groundwater flow with heat transport is considered; this corresponds to an advection-diffusion process under heterogeneous flow conditions, that is, spatially distributed material parameters and heat sources. Classical numerical simulations are costly and challenging due to high spatio-temporal resolution requirements and large domains. While often computationally more efficient, purely data-driven surrogate models face difficulties, particularly in predicting the advection process, which is highly sensitive to input variations and involves long-range spatial interactions. Therefore, in this work, a Local-Global Convolutional Neural Network (LGCNN) approach is introduced. It combines a lightweight numerical surrogate for the transport process (global) with convolutional neural networks for the groundwater velocity and heat diffusion processes (local). With the LGCNN, a city-wide subsurface temperature field is modeled, involving a heterogeneous groundwater flow field and one hundred groundwater heat pump injection points forming interacting heat plumes over long distances. The model is first systematically analyzed based on random subsurface input fields. Then, the model is trained on a handful of cut-outs from a real-world subsurface map of the Munich region in Germany, and it scales to larger cut-outs without retraining. All datasets, our code, and trained models are published for reproducibility.
Authors: Sebastian Siegel, Ming-Jay Yang, Younes Bouhadjar, Maxime Fabre, Emre Neftci, John Paul Strachan
Abstract: Structured State Space models (SSM) have recently emerged as a new class of deep learning models, particularly well-suited for processing long sequences. Their constant memory footprint, in contrast to the linearly scaling memory demands of Transformers, makes them attractive candidates for deployment on resource-constrained edge-computing devices. While recent works have explored the effect of quantization-aware training (QAT) on SSMs, they typically do not address its implications for specialized edge hardware, for example, analog in-memory computing (AIMC) chips. In this work, we demonstrate that QAT can significantly reduce the complexity of SSMs by up to two orders of magnitude across various performance metrics. We analyze the relation between model size and numerical precision, and show that QAT enhances robustness to analog noise and enables structural pruning. Finally, we integrate these techniques to deploy SSMs on a memristive analog in-memory computing substrate and highlight the resulting benefits in terms of computational efficiency.
Authors: Haoxi Li, Sikai Bai, Jie Zhang, Song Guo
Abstract: Large reasoning models (LRMs) have demonstrated impressive capabilities in domains like mathematics and program synthesis. Despite their strong performance, LRMs often exhibit overthinking -- excessive and redundant reasoning steps that introduce inefficiencies during inference. This phenomenon raises an important question for LRM self-evaluation: How can a model autonomously assess the correctness of its own reasoning trajectory without external labels? To address this, we propose Chain-of-Reasoning Embedding (CoRE), a series of hidden states in latent space to enable label-free self-evaluation on intermediate reasoning steps of LRMs, so as to enhance metacognition abilities for improved reasoning efficiency. By analyzing the geometric properties of the CoRE trajectories, we reveal that redundant reasoning usually presents cyclical fluctuations, which correspond to repetitive and unconscious reflection/exploration. Leveraging this insight, we further introduce a training-free, label-free self-evaluation framework, CoRE-Eval, to detect such patterns and dynamically determine whether to terminate reasoning early. Extensive experiments on mathematical reasoning benchmarks (GSM8K, MATH-500, and AIME) and across model sizes from 7B to 32B demonstrate that CoRE-Eval reduces chain-of-thought length by 13.7% to 33.2% while improving answer accuracy by around 10%, achieving 70.0% accuracy on the challenging AIME benchmark with the 32B model.
Authors: Mohamad H. Danesh, Maxime Wabartha, Stanley Wu, Joelle Pineau, Hsiu-Chin Lin
Abstract: Deploying reinforcement learning (RL) policies in real-world involves significant challenges, including distribution shifts, safety concerns, and the impracticality of direct interactions during policy refinement. Existing methods, such as domain randomization (DR) and off-dynamics RL, enhance policy robustness by direct interaction with the target domain, an inherently unsafe practice. We propose Uncertainty-Aware RL (UARL), a novel framework that prioritizes safety during training by addressing Out-Of-Distribution (OOD) detection and policy adaptation without requiring direct interactions in target domain. UARL employs an ensemble of critics to quantify policy uncertainty and incorporates progressive environmental randomization to prepare the policy for diverse real-world conditions. By iteratively refining over high-uncertainty regions of the state space in simulated environments, UARL enhances robust generalization to the target domain without explicitly training on it. We evaluate UARL on MuJoCo benchmarks and a quadrupedal robot, demonstrating its effectiveness in reliable OOD detection, improved performance, and enhanced sample efficiency compared to baselines.
Authors: Dongyoon Kim, Sungjae Lee, Wonjin Lee, Kwang In Kim
Abstract: Zeroth-order optimization addresses problems where gradient information is inaccessible or impractical to compute. While most existing methods rely on first-order approximations, incorporating second-order (curvature) information can, in principle, significantly accelerate convergence. However, the high cost of function evaluations required to estimate Hessian matrices often limits practical applicability. We present the subspace-based approximate Hessian (ZO-SAH) method, a zeroth-order optimization algorithm that mitigates these costs by focusing on randomly selected two-dimensional subspaces. Within each subspace, ZO-SAH estimates the Hessian by fitting a quadratic polynomial to the objective function and extracting its second-order coefficients. To further reduce function-query costs, ZO-SAH employs a periodic subspace-switching strategy that reuses function evaluations across optimization steps. Experiments on eight benchmark datasets, including logistic regression and deep neural network training tasks, demonstrate that ZO-SAH achieves significantly faster convergence than existing zeroth-order methods.
Authors: Ryan C. Barron, Maksim E. Eren, Valentin Stanev, Cynthia Matuszek, Boian S. Alexandrov
Abstract: Link prediction infers missing or future relations between graph nodes, based on connection patterns. Scientific literature networks and knowledge graphs are typically large, sparse, and noisy, and often contain missing links between entities. We present an AI-driven hierarchical link prediction framework that integrates matrix factorization to infer hidden associations and steer discovery in complex material domains. Our method combines Hierarchical Nonnegative Matrix Factorization (HNMFk) and Boolean matrix factorization (BNMFk) with automatic model selection, as well as Logistic matrix factorization (LMF), we use to construct a three-level topic tree from a 46,862-document corpus focused on 73 transition-metal dichalcogenides (TMDs). These materials are studied in a variety of physics fields with many current and potential applications. An ensemble BNMFk + LMF approach fuses discrete interpretability with probabilistic scoring. The resulting HNMFk clusters map each material onto coherent topics like superconductivity, energy storage, and tribology. Also, missing or weakly connected links are highlight between topics and materials, suggesting novel hypotheses for cross-disciplinary exploration. We validate our method by removing publications about superconductivity in well-known superconductors, and show the model predicts associations with the superconducting TMD clusters. This shows the method finds hidden connections in a graph of material to latent topic associations built from scientific literature, especially useful when examining a diverse corpus of scientific documents covering the same class of phenomena or materials but originating from distinct communities and perspectives. The inferred links generating new hypotheses, produced by our method, are exposed through an interactive Streamlit dashboard, designed for human-in-the-loop scientific discovery.
Authors: Daniel Haider, Vincent Lostanlen, Martin Ehler, Nicki Holighaus, Peter Balazs
Abstract: Using a stride in a convolutional layer inherently introduces aliasing, which has implications for numerical stability and statistical generalization. While techniques such as the parametrizations via paraunitary systems have been used to promote orthogonal convolution and thus ensure Parseval stability, a general analysis of aliasing and its effects on the stability has not been done in this context. In this article, we adapt a frame-theoretic approach to describe aliasing in convolutional layers with 1D kernels, leading to practical estimates for stability bounds and characterizations of Parseval stability, that are tailored to take short kernel sizes into account. From this, we derive two computationally very efficient optimization objectives that promote Parseval stability via systematically suppressing aliasing. Finally, for layers with random kernels, we derive closed-form expressions for the expected value and variance of the terms that describe the aliasing effects, revealing fundamental insights into the aliasing behavior at initialization.
Authors: Wout Mommen, Lars Keuninckx, Matthias Hartmann, Piet Wambacq
Abstract: We introduce a novel method for partial optimization of the connections in Deep Differentiable Logic Gate Networks (LGNs). Our training method utilizes a probability distribution over a subset of connections per gate input, selecting the connection with highest merit, after which the gate-types are selected. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. When training all connections, we demonstrate that 8000 simple logic gates are sufficient to achieve over 98% on the MNIST data set. Additionally, we show that our network has 24 times fewer gates, while performing better on the MNIST data set compared to standard fully connected LGNs. As such, our work shows a pathway towards fully trainable Boolean logic.
Authors: Nadav Schneider, Itamar Zimerman, Eliya Nachmani
Abstract: Sequence models like Transformers and RNNs often overallocate attention to irrelevant context, leading to noisy intermediate representations. This degrades LLM capabilities by promoting hallucinations, weakening long-range and retrieval abilities, and reducing robustness. Recent work has shown that differential design can mitigate this issue in Transformers, improving their effectiveness across various applications. In this paper, we explore whether these techniques, originally developed for Transformers, can be applied to Mamba, a recent architecture based on selective state-space layers that achieves Transformer-level performance with greater efficiency. We show that a naive adaptation of differential design to Mamba is insufficient and requires careful architectural modifications. To address this, we introduce a novel differential mechanism for Mamba, empirically validated on language modeling benchmarks, demonstrating improved retrieval capabilities and superior performance over vanilla Mamba. Finally, we conduct extensive ablation studies and empirical analyses to justify our design choices and provide evidence that our approach effectively mitigates the overallocation problem in Mamba-based models. Our code is publicly available.
Authors: Dmitry Krotov, Benjamin Hoover, Parikshit Ram, Bao Pham
Abstract: Associative Memories like the famous Hopfield Networks are elegant models for describing fully recurrent neural networks whose fundamental job is to store and retrieve information. In the past few years they experienced a surge of interest due to novel theoretical results pertaining to their information storage capabilities, and their relationship with SOTA AI architectures, such as Transformers and Diffusion Models. These connections open up possibilities for interpreting the computation of traditional AI networks through the theoretical lens of Associative Memories. Additionally, novel Lagrangian formulations of these networks make it possible to design powerful distributed models that learn useful representations and inform the design of novel architectures. This tutorial provides an approachable introduction to Associative Memories, emphasizing the modern language and methods used in this area of research, with practical hands-on mathematical derivations and coding notebooks.
Authors: Odysseas G. Karagiannidis, Victoria E. Galanopoulou, Panagiotis D. Diamantoulakis, Zhiguo Ding, Octavia Dobre
Abstract: The evolution of wireless communication systems requires flexible, energy-efficient, and cost-effective antenna technologies. Pinching antennas (PAs), which can dynamically control electromagnetic wave propagation through binary activation states, have recently emerged as a promising candidate. In this work, we investigate the problem of optimally selecting a subset of fixed-position PAs to activate in a waveguide, when the aim is to maximize the communication rate at a user terminal. Due to the complex interplay between antenna activation, waveguide-induced phase shifts, and power division, this problem is formulated as a combinatorial fractional 0-1 quadratic program. To efficiently solve this challenging problem, we use neural network architectures of varying complexity to learn activation policies directly from data, leveraging spatial features and signal structure. Furthermore, we incorporate user location uncertainty into our training and evaluation pipeline to simulate realistic deployment conditions. Simulation results demonstrate the effectiveness and robustness of the proposed models.
Authors: Kaixiang Zhao, Lincan Li, Kaize Ding, Neil Zhenqiang Gong, Yue Zhao, Yushun Dong
Abstract: Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks. We analyze various attack methodologies including API-based knowledge distillation, direct querying, parameter recovery, and prompt stealing techniques that exploit transformer architectures. We then examine defense mechanisms organized into model protection, data privacy protection, and prompt-targeted strategies, evaluating their effectiveness across different deployment scenarios. We propose specialized metrics for evaluating both attack effectiveness and defense performance, addressing the specific challenges of generative language models. Through our analysis, we identify critical limitations in current approaches and propose promising research directions, including integrated attack methodologies and adaptive defense mechanisms that balance security with model utility. This work serves NLP researchers, ML engineers, and security professionals seeking to protect language models in production environments.
Authors: Yingtai Xiao, Yuqing Zhu, Sirat Samyoun, Wanrong Zhang, Jiachen T. Wang, Jian Du
Abstract: Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these methods fall short when users seek attribution for specific keywords within the response, such as numbers, years, or names. To address this limitation, we propose TokenShapley, a novel token-level attribution method that combines Shapley value-based data attribution with KNN-based retrieval techniques inspired by recent advances in KNN-augmented LLMs. By leveraging a precomputed datastore for contextual retrieval and computing Shapley values to quantify token importance, TokenShapley provides a fine-grained data attribution approach. Extensive evaluations on four benchmarks show that TokenShapley outperforms state-of-the-art baselines in token-level attribution, achieving an 11-23% improvement in accuracy.
Authors: Hongyang Li, Sanjoy Dey, Bum Chul Kwon, Michael Danziger, Michal Rosen-Tzvi, Jianying Hu, James Kozloski, Ching-Huei Tsou, Bharath Dandala, Pablo Meyer
Abstract: Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as "words" that encode genomic functions. However, the genome differs fundamentally from natural language, as it lacks clearly defined words or a consistent grammar. Although DNA language models (DNALMs) such as DNABERT, GENA-LM have achieved high level of performance on genome-related biological tasks, these models do not encode biological functions in the presence of sequence variations. To address this problem, we pre-train foundation models that effectively integrate sequence variations, in particular Single Nucleotide Polymorphisms (SNPs), as they underlie important biological functions. Specifically, we use ModernBERT to pre-train two different Biomedical Foundation Models (BMFM), namely, BMFM-DNA-REF in which the model is trained with sequences of varying lengths along with their reverse complements derived from the reference genome and BMFM-DNA-SNP in which the model is trained with sequences created using a novel representation scheme that encodes sequence variations. Our findings indicate that integrating sequence variations into DNALMs helps capture the biological functions as seen in improvements on all fine-tuning tasks. To explore the model's practical utility, we experimented with various strategies for SNP imputation on promoter detection task introduced in DNABERT-2. However, we acknowledge that the current benchmarks are limited in their ability to fully evaluate these models. To enable more comprehensive assessment in the future and encourage community contributions, we release our models through HuggingFace and the code to reproduce the results at https://github.com/BiomedSciAI/biomed-multi-omic
Authors: Afsana Nasrin, Lijun Qian, Pamela Obiomon, Xishuang Dong
Abstract: Personalized learning is a student-centered educational approach that adapts content, pace, and assessment to meet each learner's unique needs. As the key technique to implement the personalized learning, learning path recommendation sequentially recommends personalized learning items such as lectures and exercises. Advances in deep learning, particularly deep reinforcement learning, have made modeling such recommendations more practical and effective. This paper proposes a multi-task LSTM model that enhances learning path recommendation by leveraging shared information across tasks. The approach reframes learning path recommendation as a sequence-to-sequence (Seq2Seq) prediction problem, generating personalized learning paths from a learner's historical interactions. The model uses a shared LSTM layer to capture common features for both learning path recommendation and deep knowledge tracing, along with task-specific LSTM layers for each objective. To avoid redundant recommendations, a non-repeat loss penalizes repeated items within the recommended learning path. Experiments on the ASSIST09 dataset show that the proposed model significantly outperforms baseline methods for the learning path recommendation.
Authors: Nicholas Merchant, Haitz S\'aez de Oc\'ariz Borde, Andrei Cristian Popescu, Carlos Garcia Jurado Suarez
Abstract: We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable outputs. In this work, we propose that enforcing a consistent caption structure during training can significantly improve model controllability and alignment. We introduce Re-LAION-Caption 19M, a high-quality subset of Re-LAION-5B, comprising 19 million 1024x1024 images with captions generated by a Mistral 7B Instruct-based LLaVA-Next model. Each caption follows a four-part template: subject, setting, aesthetics, and camera details. We fine-tune PixArt-$\Sigma$ and Stable Diffusion 2 using both structured and randomly shuffled captions, and show that structured versions consistently yield higher text-image alignment scores using visual question answering (VQA) models. The dataset is publicly available at https://huggingface.co/datasets/supermodelresearch/Re-LAION-Caption19M.
URLs: https://huggingface.co/datasets/supermodelresearch/Re-LAION-Caption19M.
Authors: Guojun Huang, Kai Zhou
Abstract: In this paper, we establish a theoretical connection between complex-valued neural networks (CVNNs) and fermionic quantum field theory (QFT), bridging a fundamental gap in the emerging framework of neural network quantum field theory (NN-QFT). While prior NN-QFT works have linked real-valued architectures to bosonic fields, we demonstrate that CVNNs equipped with tensor-valued weights intrinsically generate fermionic quantum fields. By promoting hidden-to-output weights to Clifford algebra-valued tensors, we induce anticommutation relations essential for fermionic statistics. Through analytical study of the generating functional, we obtain the exact quantum state in the infinite-width limit, revealing that the parameters between the input layer and the last hidden layer correspond to the eigenvalues of the quantum system, and the tensor weighting parameters in the hidden-to-output layer map to dynamical fermionic fields. The continuum limit reproduces free fermion correlators, with diagrammatic expansions confirming anticommutation. The work provides the first explicit mapping from neural architectures to fermionic QFT at the level of correlation functions and generating functional. It extends NN-QFT beyond bosonic theories and opens avenues for encoding fermionic symmetries into machine learning models, with potential applications in quantum simulation and lattice field theory.
Authors: Pierre Boudart (PSL, DI-ENS, Inria), Pierre Gaillard (PSL, DI-ENS, Inria), Alessandro Rudi (PSL, DI-ENS, Inria)
Abstract: We consider the multinomial logistic bandit problem, a variant of generalized linear bandits where a learner interacts with an environment by selecting actions to maximize expected rewards based on probabilistic feedback from multiple possible outcomes. In the binary setting, recent work has focused on understanding the impact of the non-linearity of the logistic model (Faury et al., 2020; Abeille et al., 2021). They introduced a problem-dependent constant $\kappa_*$, that may be exponentially large in some problem parameters and which is captured by the derivative of the sigmoid function. It encapsulates the non-linearity and improves existing regret guarantees over $T$ rounds from $\smash{O(d\sqrt{T})}$ to $\smash{O(d\sqrt{T/\kappa_*})}$, where $d$ is the dimension of the parameter space. We extend their analysis to the multinomial logistic bandit framework, making it suitable for complex applications with more than two choices, such as reinforcement learning or recommender systems. To achieve this, we extend the definition of $\kappa_*$ to the multinomial setting and propose an efficient algorithm that leverages the problem's non-linearity. Our method yields a problem-dependent regret bound of order $ \smash{\widetilde{\mathcal{O}}( Kd \sqrt{{T}/{\kappa_*}})} $, where $K$ is the number of actions and $\kappa_* \ge 1$. This improves upon the best existing guarantees of order $ \smash{\widetilde{\mathcal{O}}( Kd \sqrt{T} )} $. Moreover, we provide a $\smash{ \Omega(d\sqrt{T/\kappa_*})}$ lower-bound, showing that our dependence on $\kappa_*$ is optimal.
Authors: Zehuan Chen, Xiangwei Lai
Abstract: Predicting Quality of Service (QoS) data crucial for cloud service selection, where user privacy is a critical concern. Federated Graph Neural Networks (FGNNs) can perform QoS data prediction as well as maintaining user privacy. However, existing FGNN-based QoS predictors commonly implement on-device training on scattered explicit user-service graphs, thereby failing to utilize the implicit user-user interactions. To address this issue, this study proposes a high order collaboration-oriented federated graph neural network (HC-FGNN) to obtain accurate QoS prediction with privacy preservation. Concretely, it magnifies the explicit user-service graphs following the principle of attention mechanism to obtain the high order collaboration, which reflects the implicit user-user interactions. Moreover, it utilizes a lightweight-based message aggregation way to improve the computational efficiency. The extensive experiments on two QoS datasets from real application indicate that the proposed HC-FGNN possesses the advantages of high prediction accurate and privacy protection.
Authors: Zeinab Hassani, Davud Mohammadpur, Hossein Safari
Abstract: We investigate the use of Long Short-Term Memory (LSTM) and Decomposition-LSTM (DLSTM) networks, combined with an ensemble algorithm, to predict solar flare occurrences using time-series data from the GOES catalog. The dataset spans from 2003 to 2023 and includes 151,071 flare events. Among approximately possible patterns, 7,552 yearly pattern windows are identified, highlighting the challenge of long-term forecasting due to the Sun's complex, self-organized criticality-driven behavior. A sliding window technique is employed to detect temporal quasi-patterns in both irregular and regularized flare time series. Regularization reduces complexity, enhances large flare activity, and captures active days more effectively. To address class imbalance, resampling methods are applied. LSTM and DLSTM models are trained on sequences of peak fluxes and waiting times from irregular time series, while LSTM and DLSTM, integrated with an ensemble approach, are applied to sliding windows of regularized time series with a 3-hour interval. Performance metrics, particularly TSS (0.74), recall (0.95) and the area under the curve (AUC=0.87) in the receiver operating characteristic (ROC), indicate that DLSTM with an ensemble approach on regularized time series outperforms other models, offering more accurate large-flare forecasts with fewer false errors compared to models trained on irregular time series. The superior performance of DLSTM is attributed to its ability to decompose time series into trend and seasonal components, effectively isolating random noise. This study underscores the potential of advanced machine learning techniques for solar flare prediction and highlights the importance of incorporating various solar cycle phases and resampling strategies to enhance forecasting reliability.
Authors: William Fleshman, Benjamin Van Durme
Abstract: The proliferation of fine-tuned language model experts for specific tasks and domains signals the need for efficient selection and combination methods. We propose LoRA-Augmented Generation (LAG) for leveraging large libraries of knowledge and task-specific LoRA adapters. LAG requires no additional training or access to data, and efficiently filters, retrieves, and applies experts on a per-token and layer basis. We evaluate LAG on various knowledge-intensive tasks, achieving superior performance over existing data-free methods. We explore scenarios where additional data is available, demonstrating LAG's compatibility with alternative solutions such as retrieval-augmented generation (RAG).
Authors: Riccardo Alberghi, Elizaveta Demyanenko, Luca Biggio, Luca Saglietti
Abstract: Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the reasoning trace, and (ii) compute is most effective when reasoning is systematic and incremental, forming structured chains of thought (CoTs) akin to human problem-solving. To study these factors in isolation, we introduce a controlled setting based on shortest-path tasks in layered graphs. We train decoder-only transformers on question-trace-answer triples using a custom tokenizer, comparing models trained on optimal bottom-up dynamic programming traces with those trained on longer, valid traces involving backtracking. Surprisingly, with the same training-token budget, models trained on inefficient traces generalize better to unseen graphs. This benefit is not due to length alone-injecting arbitrary redundancy into reasoning traces fails to help and can even hurt performance. Instead, we find that generalization correlates with the model's confidence in next-token prediction, suggesting that long, coherent, and locally incremental traces make the training signal easier to optimize.
Authors: Sajjad Ghiasvand, Mahnoosh Alizadeh, Ramtin Pedarsani
Abstract: Vision-Language Models (VLMs) like CLIP have demonstrated remarkable generalization in zero- and few-shot settings, but adapting them efficiently to decentralized, heterogeneous data remains a challenge. While prompt tuning has emerged as a popular parameter-efficient approach in personalized federated learning, existing methods often sacrifice generalization in favor of personalization, struggling particularly on unseen classes or domains. In this work, we propose pFedMMA, the first personalized federated learning framework that leverages multi-modal adapters for vision-language tasks. Each adapter contains modality-specific up- and down-projection layers alongside a globally shared projection that aligns cross-modal features. Our asymmetric optimization strategy allows clients to locally adapt to personalized data distributions while collaboratively training the shared projection to improve global generalization. This design is also communication-efficient, as only the shared component is exchanged during rounds. Through extensive experiments across eleven datasets, including domain- and label-shift scenarios, we show that pFedMMA achieves state-of-the-art trade-offs between personalization and generalization, outperforming recent federated prompt tuning methods. The code is available at https://github.com/sajjad-ucsb/pFedMMA.
Authors: Jaedong Hwang, Kumar Tanmay, Seok-Jin Lee, Ayush Agrawal, Hamid Palangi, Kumar Ayush, Ila Fiete, Paul Pu Liang
Abstract: Large Language Models (LLMs) have achieved strong performance in domains like mathematics, factual QA, and code generation, yet their multilingual reasoning capabilities in these tasks remain underdeveloped. Especially for low-resource languages such as Swahili or Thai, LLMs can often misinterpret prompts or default to reasoning in English. This implicit bias toward high-resource languages undermines factual accuracy, interpretability, and trust. Current multilingual benchmarks focus only on final answers, overlooking whether models actually reason in the target language. To address this gap, we introduce GeoFact-X, a geography-based multilingual factual reasoning benchmark with annotated reasoning traces in five languages: English, Hindi, Japanese, Swahili, and Thai. We further propose BRIDGE, a novel training method that guides supervised fine-tuning and test-time reinforcement learning with a language-consistency reward to align reasoning with the input language. Finally, we develop an automatic evaluation protocol using LLM-as-a-judge to assess answer correctness and the quality and language consistency of reasoning traces, enabling nuanced and scalable analysis beyond surface-level metrics. Our results show that BRIDGE significantly enhances multilingual reasoning fidelity, demonstrating that reasoning-aware multilingual reinforcement learning is crucial for robust cross-lingual generalization. https://jd730.github.io/projects/GeoFact-X_BRIDGE
Authors: Aliasghar Khani, Arianna Rampini, Bruno Roy, Larasika Nadela, Noa Kaplan, Evan Atherton, Derek Cheung, Jacky Bibliowicz
Abstract: Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual agents to human-robot interaction. As the field has rapidly progressed with the introduction of diverse modeling paradigms including GANs, autoencoders, autoregressive models, and diffusion-based techniques, each approach brings its own advantages and limitations. This growing diversity has created a need for a comprehensive and structured review that specifically examines recent developments from the perspective of the generative approach employed. In this survey, we provide an in-depth categorization of motion generation methods based on their underlying generative strategies. Our main focus is on papers published in top-tier venues since 2023, reflecting the most recent advancements in the field. In addition, we analyze architectural principles, conditioning mechanisms, and generation settings, and compile a detailed overview of the evaluation metrics and datasets used across the literature. Our objective is to enable clearer comparisons and identify open challenges, thereby offering a timely and foundational reference for researchers and practitioners navigating the rapidly evolving landscape of motion generation.
Authors: Agnideep Aich, Ashit Baran Aich, Dipak C. Jain
Abstract: We propose Temporal Conformal Prediction (TCP), a novel framework for constructing prediction intervals in financial time-series with guaranteed finite-sample validity. TCP integrates quantile regression with a conformal calibration layer that adapts online via a decaying learning rate. This hybrid design bridges statistical and machine learning paradigms, enabling TCP to accommodate non-stationarity, volatility clustering, and regime shifts which are hallmarks of real-world asset returns, without relying on rigid parametric assumptions. We benchmark TCP against established methods including GARCH, Historical Simulation, and static Quantile Regression across equities (S&P 500), cryptocurrency (Bitcoin), and commodities (Gold). Empirical results show that TCP consistently delivers sharper intervals with competitive or superior coverage, particularly in high-volatility regimes. Our study underscores TCP's strength in navigating the coverage-sharpness tradeoff, a central challenge in modern risk forecasting. Overall, TCP offers a distribution-free, adaptive, and interpretable alternative for financial uncertainty quantification, advancing the interface between statistical inference and machine learning in finance.
Authors: Andrew Randono
Abstract: Diffusion models for image generation function by progressively adding noise to an image set and training a model to separate out the signal from the noise. The noise profile used by these models is white noise -- that is, noise based on independent normal distributions at each point whose mean and variance is independent of the scale. By contrast, most natural image sets exhibit a type of scale invariance in their low-order statistical properties characterized by a power-law scaling. Consequently, natural images are closer (in a quantifiable sense) to a different probability distribution that emphasizes large scale correlations and de-emphasizes small scale correlations. These scale invariant noise profiles can be incorporated into diffusion models in place of white noise to form what we will call a ``Cloud Diffusion Model". We argue that these models can lead to faster inference, improved high-frequency details, and greater controllability. In a follow-up paper, we will build and train a Cloud Diffusion Model that uses scale invariance at a fundamental level and compare it to classic, white noise diffusion models.
Authors: Arthur Deng, Karsten Householder, Fang Wu, Sebastian Thrun, K. Christopher Garcia, Brian Trippe
Abstract: Accurate estimation of mutational effects on protein-protein binding energies is an open problem with applications in structural biology and therapeutic design. Several deep learning predictors for this task have been proposed, but, presumably due to the scarcity of binding data, these methods underperform computationally expensive estimates based on empirical force fields. In response, we propose a transfer-learning approach that leverages advances in protein sequence modeling and folding stability prediction for this task. The key idea is to parameterize the binding energy as the difference between the folding energy of the protein complex and the sum of the folding energies of its binding partners. We show that using a pre-trained inverse-folding model as a proxy for folding energy provides strong zero-shot performance, and can be fine-tuned with (1) copious folding energy measurements and (2) more limited binding energy measurements. The resulting predictor, StaB-ddG, is the first deep learning predictor to match the accuracy of the state-of-the-art empirical force-field method FoldX, while offering an over 1,000x speed-up.
Authors: Kuan-Cheng Chen, Huan-Hsin Tseng, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung
Abstract: We propose SUN-VQC, a variational-circuit architecture whose elementary layers are single exponentials of a symmetry-restricted Lie subgroup, $\mathrm{SU}(2^{k}) \subset \mathrm{SU}(2^{n})$ with $k \ll n$. Confining the evolution to this compact subspace reduces the dynamical Lie-algebra dimension from $\mathcal{O}(4^{n})$ to $\mathcal{O}(4^{k})$, ensuring only polynomial suppression of gradient variance and circumventing barren plateaus that plague hardware-efficient ans\"atze. Exact, hardware-compatible gradients are obtained using a generalized parameter-shift rule, avoiding ancillary qubits and finite-difference bias. Numerical experiments on quantum auto-encoding and classification show that SUN-VQCs sustain order-of-magnitude larger gradient signals, converge 2--3$\times$ faster, and reach higher final fidelities than depth-matched Pauli-rotation or hardware-efficient circuits. These results demonstrate that Lie-subalgebra engineering provides a principled, scalable route to barren-plateau-resilient VQAs compatible with near-term quantum processors.
Authors: Moseli Mots'oehli, Feimei Chen, Hok Wai Chan, Itumeleng Tlali, Thulani Babeli, Kyungim Baek, Huaijin Chen
Abstract: The scarcity of autonomous vehicle datasets from developing regions, particularly across Africa's diverse urban, rural, and unpaved roads, remains a key obstacle to robust perception in low-resource settings. We present a procedural augmentation pipeline that enhances low-cost monocular dashcam footage with realistic refractive distortions and weather-induced artifacts tailored to challenging African driving scenarios. Our refractive module simulates optical effects from low-quality lenses and air turbulence, including lens distortion, Perlin noise, Thin-Plate Spline (TPS), and divergence-free (incompressible) warps. The weather module adds homogeneous fog, heterogeneous fog, and lens flare. To establish a benchmark, we provide baseline performance using three image restoration models. To support perception research in underrepresented African contexts, without costly data collection, labeling, or simulation, we release our distortion toolkit, augmented dataset splits, and benchmark results.
Authors: Ehsan Mirafzali, Frank Proske, Utkarsh Gupta, Daniele Venturi, Razvan Marinescu
Abstract: Score-based diffusion generative models have recently emerged as a powerful tool for modelling complex data distributions. These models aim at learning the score function, which defines a map from a known probability distribution to the target data distribution via deterministic or stochastic differential equations (SDEs). The score function is typically estimated from data using a variety of approximation techniques, such as denoising or sliced score matching, Hyv\"arien's method, or Schr\"odinger bridges. In this paper, we derive an exact, closed form, expression for the score function for a broad class of nonlinear diffusion generative models. Our approach combines modern stochastic analysis tools such as Malliavin derivatives and their adjoint operators (Skorokhod integrals or Malliavin Divergence) with a new Bismut-type formula. The resulting expression for the score function can be written entirely in terms of the first and second variation processes, with all Malliavin derivatives systematically eliminated, thereby enhancing its practical applicability. The theoretical framework presented in this work offers a principled foundation for advancing score estimation methods in generative modelling, enabling the design of new sampling algorithms for complex probability distributions. Our results can be extended to broader classes of stochastic differential equations, opening new directions for the development of score-based diffusion generative models.
Authors: Gabriel P. Langlois, J\'er\^ome Darbon
Abstract: Basis pursuit denoising (BPDN) is a cornerstone of compressive sensing, statistics and machine learning. While various algorithms for BPDN have been proposed, they invariably suffer from drawbacks and must either favor efficiency at the expense of accuracy or vice versa. As such, state-of-the-art algorithms remain ineffective for high-dimensional applications that require accurate solutions within a reasonable amount of computational time. In this work, we address this issue and propose an exact and efficient algorithm for BPDN using differential inclusions. Specifically, we prove that a selection principle from the theory of differential inclusions turns the dual problem of BPDN into calculating the trajectory of an \emph{integrable} projected dynamical system, that is, whose trajectory and asymptotic limit can be computed exactly. Our analysis naturally yields an exact algorithm, numerically up to machine precision, that is amenable to computing regularization paths and very fast. Numerical experiments confirm that our algorithm outperforms the state-of-the-art algorithms in both accuracy and efficiency. Moreover, we show that the global continuation of solutions (in terms of the hyperparameter and data) of the projected dynamical system yields a rigorous homotopy algorithm for BPDN, as well as a novel greedy algorithm for computing feasible solutions to basis pursuit in strongly polynomial time. Beyond this work, we expect that our results and analysis can be adapted to compute exact or approximate solutions to a broader class of polyhedral-constrained optimization problems.
Authors: Jiaxu Tian, Xuehui Yu, Yaoxing Wang, Pan Wang, Guangqian Guo, Shan Gao
Abstract: Content-aware layout aims to arrange design elements appropriately on a given canvas to convey information effectively. Recently, the trend for this task has been to leverage large language models (LLMs) to generate layouts automatically, achieving remarkable performance. However, existing LLM-based methods fail to adequately interpret spatial relationships among visual themes and design elements, leading to structural and diverse problems in layout generation. To address this issue, we introduce ReLayout, a novel method that leverages relation-CoT to generate more reasonable and aesthetically coherent layouts by fundamentally originating from design concepts. Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements, with the goal of decomposing the layout into smaller, structured, and recursive layouts, thereby enabling the generation of more structured layouts. Furthermore, based on these defined relationships, we introduce a layout prototype rebalance sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles. This sampler addresses uniformity issues in generation that arise from data bias in the prototype distribution balance process. Extensive experimental results verify that ReLayout outperforms baselines and can generate structural and diverse layouts that are more aligned with human aesthetics and more explainable.
Authors: Shashank Verma, Fengyi Jiang, Xiangning Xue
Abstract: Biomedical semantic question answering rooted in information retrieval can play a crucial role in keeping up to date with vast, rapidly evolving and ever-growing biomedical literature. A robust system can help researchers, healthcare professionals and even layman users access relevant knowledge grounded in evidence. The BioASQ 2025 Task13b Challenge serves as an important benchmark, offering a competitive platform for advancement of this space. This paper presents the methodologies and results from our participation in this challenge where we built a Retrieval-Augmented Generation (RAG) system that can answer biomedical questions by retrieving relevant PubMed documents and snippets to generate answers. For the retrieval task, we generated dense embeddings from biomedical articles for initial retrieval, and applied an ensemble of finetuned cross-encoders and large language models (LLMs) for re-ranking to identify top relevant documents. Our solution achieved an MAP@10 of 0.1581, placing 10th on the leaderboard for the retrieval task. For answer generation, we employed few-shot prompting of instruction-tuned LLMs. Our system achieved macro-F1 score of 0.95 for yes/no questions (rank 12), Mean Reciprocal Rank (MRR) of 0.64 for factoid questions (rank 1), mean-F1 score of 0.63 for list questions (rank 5), and ROUGE-SU4 F1 score of 0.29 for ideal answers (rank 11).
Authors: Devansh Gupta, Meisam Razaviyayn, Vatsal Sharan
Abstract: Differentially private zeroth-order optimization methods have recently gained popularity in private fine tuning of machine learning models due to their reduced memory requirements. Current approaches for privatizing zeroth-order methods rely on adding Gaussian noise to the estimated zeroth-order gradients. However, since the search direction in the zeroth-order methods is inherently random, researchers including Tang et al. (2024) and Zhang et al. (2024a) have raised an important question: is the inherent noise in zeroth-order estimators sufficient to ensure the overall differential privacy of the algorithm? This work settles this question for a class of oracle-based optimization algorithms where the oracle returns zeroth-order gradient estimates. In particular, we show that for a fixed initialization, there exist strongly convex objective functions such that running (Projected) Zeroth-Order Gradient Descent (ZO-GD) is not differentially private. Furthermore, we show that even with random initialization and without revealing (initial and) intermediate iterates, the privacy loss in ZO-GD can grow superlinearly with the number of iterations when minimizing convex objective functions.
Authors: Shaojie Bai, Seunghyeon Seo, Yida Wang, Chenghui Li, Owen Wang, Te-Li Wang, Tianyang Ma, Jason Saragih, Shih-En Wei, Nojun Kwak, Hyung Jun Kim
Abstract: Enabling photorealistic avatar animations in virtual and augmented reality (VR/AR) has been challenging because of the difficulty of obtaining ground truth state of faces. It is physically impossible to obtain synchronized images from head-mounted cameras (HMC) sensing input, which has partial observations in infrared (IR), and an array of outside-in dome cameras, which have full observations that match avatars' appearance. Prior works relying on analysis-by-synthesis methods could generate accurate ground truth, but suffer from imperfect disentanglement between expression and style in their personalized training. The reliance of extensive paired captures (HMC and dome) for the same subject makes it operationally expensive to collect large-scale datasets, which cannot be reused for different HMC viewpoints and lighting. In this work, we propose a novel generative approach, Generative HMC (GenHMC), that leverages large unpaired HMC captures, which are much easier to collect, to directly generate high-quality synthetic HMC images given any conditioning avatar state from dome captures. We show that our method is able to properly disentangle the input conditioning signal that specifies facial expression and viewpoint, from facial appearance, leading to more accurate ground truth. Furthermore, our method can generalize to unseen identities, removing the reliance on the paired captures. We demonstrate these breakthroughs by both evaluating synthetic HMC images and universal face encoders trained from these new HMC-avatar correspondences, which achieve better data efficiency and state-of-the-art accuracy.
Authors: Shuo Shao, Yiming Li, Mengren Zheng, Zhiyang Hu, Yukun Chen, Boheng Li, Yu He, Junfeng Guo, Tianwei Zhang, Dacheng Tao, Zhan Qin
Abstract: The widespread application of Deep Learning across diverse domains hinges critically on the quality and composition of training datasets. However, the common lack of disclosure regarding their usage raises significant privacy and copyright concerns. Dataset auditing techniques, which aim to determine if a specific dataset was used to train a given suspicious model, provide promising solutions to addressing these transparency gaps. While prior work has developed various auditing methods, their resilience against dedicated adversarial attacks remains largely unexplored. To bridge the gap, this paper initiates a comprehensive study evaluating dataset auditing from an adversarial perspective. We start with introducing a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing). Subsequently, we formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset. Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery. These formulations and strategies lead to our new benchmark, DATABench, comprising 17 evasion attacks, 5 forgery attacks, and 9 representative auditing methods. Extensive evaluations using DATABench reveal that none of the evaluated auditing methods are sufficiently robust or distinctive under adversarial settings. These findings underscore the urgent need for developing a more secure and reliable dataset auditing method capable of withstanding sophisticated adversarial manipulation. Code is available at https://github.com/shaoshuo-ss/DATABench.
Authors: Sarthak Choudhary, Divyam Anshumaan, Nils Palumbo, Somesh Jha
Abstract: LLM-integrated applications and agents are vulnerable to prompt injection attacks, in which adversaries embed malicious instructions within seemingly benign user inputs to manipulate the LLM's intended behavior. Recent defenses based on $\textit{known-answer detection}$ (KAD) have achieved near-perfect performance by using an LLM to classify inputs as clean or contaminated. In this work, we formally characterize the KAD framework and uncover a structural vulnerability in its design that invalidates its core security premise. We design a methodical adaptive attack, $\textit{DataFlip}$, to exploit this fundamental weakness. It consistently evades KAD defenses with detection rates as low as $1.5\%$ while reliably inducing malicious behavior with success rates of up to $88\%$, without needing white-box access to the LLM or any optimization procedures.
Authors: Ammar Daskin
Abstract: In this paper, we describe a parameterized quantum circuit that can be considered as convolutional and pooling layers for graph neural networks. The circuit incorporates the parameterized quantum Fourier circuit where the qubit connections for the controlled gates derived from the Laplacian operator. Specifically, we show that the eigenspace of the Laplacian operator of a graph can be approximated by using QFT based circuit whose connections are determined from the adjacency matrix. For an $N\times N$ Laplacian, this approach yields an approximate polynomial-depth circuit requiring only $n=log(N)$ qubits. These types of circuits can eliminate the expensive classical computations for approximating the learnable functions of the Laplacian through Chebyshev polynomial or Taylor expansions. Using this circuit as a convolutional layer provides an $n-$ dimensional probability vector that can be considered as the filtered and compressed graph signal. Therefore, the circuit along with the measurement can be considered a very efficient convolution plus pooling layer that transforms an $N$-dimensional signal input into $n-$dimensional signal with an exponential compression. We then apply a classical neural network prediction head to the output of the circuit to construct a complete graph neural network. Since the circuit incorporates geometric structure through its graph connection-based approach, we present graph classification results for the benchmark datasets listed in TUDataset library. Using only [1-100] learnable parameters for the quantum circuit and minimal classical layers (1000-5000 parameters) in a generic setting, the obtained results are comparable to and in some cases better than many of the baseline results, particularly for the cases when geometric structure plays a significant role.
Authors: Kaixiang Zhao, Joseph Yousry Attalla, Qian Lou, Yushun Dong
Abstract: Graph Neural Networks (GNNs) have achieved state-of-the-art performance in various graph-based learning tasks. However, enabling privacy-preserving GNNs in encrypted domains, such as under Fully Homomorphic Encryption (FHE), typically incurs substantial computational overhead, rendering real-time and privacy-preserving inference impractical. In this work, we propose DESIGN (EncrypteD GNN Inference via sErver-Side Input Graph pruNing), a novel framework for efficient encrypted GNN inference. DESIGN tackles the critical efficiency limitations of existing FHE GNN approaches, which often overlook input data redundancy and apply uniform computational strategies. Our framework achieves significant performance gains through a hierarchical optimization strategy executed entirely on the server: first, FHE-compatible node importance scores (based on encrypted degree statistics) are computed from the encrypted graph. These scores then guide a homomorphic partitioning process, generating multi-level importance masks directly under FHE. This dynamically generated mask facilitates both input graph pruning (by logically removing unimportant elements) and a novel adaptive polynomial activation scheme, where activation complexity is tailored to node importance levels. Empirical evaluations demonstrate that DESIGN substantially accelerates FHE GNN inference compared to state-of-the-art methods while maintaining competitive model accuracy, presenting a robust solution for secure graph analytics.
Authors: Zhiyuan Yang, Kai Li, Sophia Ghamoshi Ramandi, Patricia Brassard, Hakim Khellaf, Vincent Quoc-Huy Trinh, Jennifer Zhang, Lina Chen, Corwyn Rowsell, Sonal Varma, Kostas Plataniotis, Mahdi S. Hosseini
Abstract: Computational pathology (CoPath) leverages histopathology images to enhance diagnostic precision and reproducibility in clinical pathology. However, publicly available datasets for CoPath that are annotated with extensive histological tissue type (HTT) taxonomies at a granular level remain scarce due to the significant expertise and high annotation costs required. Existing datasets, such as the Atlas of Digital Pathology (ADP), address this by offering diverse HTT annotations generalized to multiple organs, but limit the capability for in-depth studies on specific organ diseases. Building upon this foundation, we introduce ADPv2, a novel dataset focused on gastrointestinal histopathology. Our dataset comprises 20,004 image patches derived from healthy colon biopsy slides, annotated according to a hierarchical taxonomy of 32 distinct HTTs of 3 levels. Furthermore, we train a multilabel representation learning model following a two-stage training procedure on our ADPv2 dataset. We leverage the VMamba architecture and achieving a mean average precision (mAP) of 0.88 in multilabel classification of colon HTTs. Finally, we show that our dataset is capable of an organ-specific in-depth study for potential biomarker discovery by analyzing the model's prediction behavior on tissues affected by different colon diseases, which reveals statistical patterns that confirm the two pathological pathways of colon cancer development. Our dataset is publicly available at https://zenodo.org/records/15307021
Authors: Daniel Abdi, Isidora Jankov, Paul Madden, Vanderlei Vargas, Timothy A. Smith, Sergey Frolov, Montgomery Flora, Corey Potvin
Abstract: The High-Resolution Rapid Refresh (HRRR) model is a convection-allowing model used in operational weather forecasting across the contiguous United States (CONUS). To provide a computationally efficient alternative, we introduce HRRRCast, a data-driven emulator built with advanced machine learning techniques. HRRRCast includes two architectures: a ResNet-based model (ResHRRR) and a Graph Neural Network-based model (GraphHRRR). ResHRRR uses convolutional neural networks enhanced with squeeze-and-excitation blocks and Feature-wise Linear Modulation, and supports probabilistic forecasting via the Denoising Diffusion Implicit Model (DDIM). To better handle longer lead times, we train a single model to predict multiple lead times (1h, 3h, and 6h), then use a greedy rollout strategy during inference. When evaluated on composite reflectivity over the full CONUS domain using ensembles of 3 to 10 members, ResHRRR outperforms HRRR forecast at light rainfall threshold (20 dBZ) and achieves competitive performance at moderate thresholds (30 dBZ). Our work advances the StormCast model of Pathak et al. [21] by: a) training on the full CONUS domain, b) using multiple lead times to improve long-range skill, c) training on analysis data instead of the +1h post-analysis data inadvertently used in StormCast, and d) incorporating future GFS states as inputs, enabling downscaling that improves long-lead accuracy. Grid-, neighborhood-, and object-based metrics confirm better storm placement, lower frequency bias, and higher success ratios than HRRR. HRRRCast ensemble forecasts also maintain sharper spatial detail, with power spectra more closely matching HRRR analysis. While GraphHRRR underperforms in its current form, it lays groundwork for future graph-based forecasting. HRRRCast represents a step toward efficient, data-driven regional weather prediction with competitive accuracy and ensemble capability.
Authors: Muhammad Hadir Khan, Matthew Guthaus
Abstract: Clock meshes are essential in high-performance VLSI systems for minimizing skew and handling PVT variations, but analyzing them is difficult due to reconvergent paths, multi-source driving, and input mesh buffer skew. SPICE simulations are accurate but slow; yet simplified models miss key effects like slew and input skew. We propose GATMesh, a Graph Neural Network (GNN)-based framework that models the clock mesh as a graph with augmented structural and physical features. Trained on SPICE data, GATMesh achieves high accuracy with average delay error of 5.27ps on unseen benchmarks, while achieving speed-ups of 47146x over multi-threaded SPICE simulation.
Authors: Weihua Du, Pranjal Aggarwal, Sean Welleck, Yiming Yang
Abstract: Current long chain-of-thought (long-CoT) models excel at mathematical reasoning but rely on slow and error-prone natural language traces. Tool-augmented agents address arithmetic via code execution, but often falter on complex logical tasks. We introduce a fine-tuning framework, DualDistill, that distills complementary reasoning strategies from multiple teachers into a unified student model. Using this approach, we train Agentic-R1, which dynamically selects the optimal strategy for each query, invoking tools for arithmetic and algorithmic problems, and using text-based reasoning for abstract ones. Our method improves accuracy across a range of tasks, including both computation-intensive and standard benchmarks, demonstrating the effectiveness of multi-strategy distillation in achieving robust and efficient reasoning. Our project is available at https://github.com/StigLidu/DualDistill
Authors: Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly
Abstract: Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route experts independently within each layer. Our analysis reveals that routers in most layers make expert choices that are not strongly correlated with the choices of the routers in other layers. To increase the cooperation between experts in different layers and encourage greater specialization, we use a shared router across different MoE layers. We call this model \emph{Omni-router Transformer}. Extensive experiments on a large-scale pseudo-labeled dataset and evaluations across 10 diverse, out-of-domain ASR benchmarks demonstrate that the Omni-router Transformer is able to achieve lower training loss and consistently outperform dense and Switch Transformer models, reducing average word error rates by 11.2% and 8.2%, respectively, while providing structured expert usage and improved robustness to diverse data.
Authors: Yuxin Zhang, Jiahao Yang, Zhe Chen, Wenjun Zhu, Jin Zhao, Yue Gao
Abstract: Recently, large vision-language models (LVLMs) unleash powerful analysis capabilities for low Earth orbit (LEO) satellite Earth observation images in the data center. However, fast satellite motion, brief satellite-ground station (GS) contact windows, and large size of the images pose a data download challenge. To enable near real-time Earth observation applications (e.g., disaster and extreme weather monitoring), we should explore how to deploy LVLM in LEO satellite networks, and design SpaceVerse, an efficient satellite-ground synergistic LVLM inference system. To this end, firstly, we deploy compact LVLMs on satellites for lightweight tasks, whereas regular LVLMs operate on GSs to handle computationally intensive tasks. Then, we propose a computing and communication co-design framework comprised of a progressive confidence network and an attention-based multi-scale preprocessing, used to identify on-satellite inferring data, and reduce data redundancy before satellite-GS transmission, separately. We implement and evaluate SpaceVerse on real-world LEO satellite constellations and datasets, achieving a 31.2% average gain in accuracy and a 51.2% reduction in latency compared to state-of-the-art baselines.
Authors: Tristan Kirscher (ICube, ICANS), Sylvain Faisan (ICube), Xavier Coubez (ICANS), Loris Barrier (ICANS), Philippe Meyer (ICube, ICANS)
Abstract: Pediatric medical imaging presents unique challenges due to significant anatomical and developmental differences compared to adults. Direct application of segmentation models trained on adult data often yields suboptimal performance, particularly for small or rapidly evolving structures. To address these challenges, several strategies leveraging the nnU-Net framework have been proposed, differing along four key axes: (i) the fingerprint dataset (adult, pediatric, or a combination thereof) from which the Training Plan -including the network architecture-is derived; (ii) the Learning Set (adult, pediatric, or mixed), (iii) Data Augmentation parameters, and (iv) the Transfer learning method (finetuning versus continual learning). In this work, we introduce PSAT (Pediatric Segmentation Approaches via Adult Augmentations and Transfer learning), a systematic study that investigates the impact of these axes on segmentation performance. We benchmark the derived strategies on two pediatric CT datasets and compare them with state-of-theart methods, including a commercial radiotherapy solution. PSAT highlights key pitfalls and provides actionable insights for improving pediatric segmentation. Our experiments reveal that a training plan based on an adult fingerprint dataset is misaligned with pediatric anatomy-resulting in significant performance degradation, especially when segmenting fine structures-and that continual learning strategies mitigate institutional shifts, thus enhancing generalization across diverse pediatric datasets. The code is available at https://github.com/ICANS-Strasbourg/PSAT.
Authors: Jian Kai, Tianwei Zhang, Zihan Ling, Yang Cao, Can Shen
Abstract: Accurate bandwidth estimation (BWE) is critical for real-time communication (RTC) systems. Traditional heuristic approaches offer limited adaptability under dynamic networks, while online reinforcement learning (RL) suffers from high exploration costs and potential service disruptions. Offline RL, which leverages high-quality data collected from real-world environments, offers a promising alternative. However, challenges such as out-of-distribution (OOD) actions, policy extraction from behaviorally diverse datasets, and reliable deployment in production systems remain unsolved. We propose RBWE, a robust bandwidth estimation framework based on offline RL that integrates Q-ensemble (an ensemble of Q-functions) with a Gaussian mixture policy to mitigate OOD risks and enhance policy learning. A fallback mechanism ensures deployment stability by switching to heuristic methods under high uncertainty. Experimental results show that RBWE reduces overestimation errors by 18% and improves the 10th percentile Quality of Experience (QoE) by 18.6%, demonstrating its practical effectiveness in real-world RTC applications.
Authors: Yizhe Zhang
Abstract: Manual annotation of medical images is a labor-intensive and time-consuming process, posing a significant bottleneck in the development and deployment of robust medical imaging AI systems. This paper introduces a novel Human-AI collaborative framework for medical image segmentation that substantially reduces the annotation burden by eliminating the need for explicit manual pixel-level labeling. The core innovation lies in a preference learning paradigm, where human experts provide minimal, intuitive feedback -- simply indicating whether an AI-generated segmentation is better or worse than a previous version. The framework comprises four key components: (1) an adaptable foundation model (FM) for feature extraction, (2) label propagation based on feature similarity, (3) a clicking agent that learns from human better-or-worse feedback to decide where to click and with which label, and (4) a multi-round segmentation learning procedure that trains a state-of-the-art segmentation network using pseudo-labels generated by the clicking agent and FM-based label propagation. Experiments on three public datasets demonstrate that the proposed approach achieves competitive segmentation performance using only binary preference feedback, without requiring experts to directly manually annotate the images.
Authors: Zekai Sun, Xiuxian Guan, Zheng Lin, Zihan Fang, Xiangming Cai, Zhe Chen, Fangming Liu, Heming Cui, Jie Xiong, Wei Ni, Chau Yuen
Abstract: Deploying deep neural networks (DNNs) on resource-constrained mobile devices presents significant challenges, particularly in achieving real-time performance while simultaneously coping with limited computational resources and battery life. While Mobile Edge Computing (MEC) offers collaborative inference with GPU servers as a promising solution, existing approaches primarily rely on layer-wise model partitioning and undergo significant transmission bottlenecks caused by the sequential execution of DNN operations. To address this challenge, we present Intra-DP, a high-performance collaborative inference system optimized for DNN inference on MEC. Intra DP employs a novel parallel computing technique based on local operators (i.e., operators whose minimum unit input is not the entire input tensor, such as the convolution kernel). By decomposing their computations (operations) into several independent sub-operations and overlapping the computation and transmission of different sub-operations through parallel execution, Intra-DP mitigates transmission bottlenecks in MEC, achieving fast and energy-efficient inference. The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines, without sacrificing accuracy.
Authors: James Bailie, Rabanus Derr
Abstract: Property elicitation studies which attributes of a probability distribution can be determined by minimising a risk. We investigate a generalisation of property elicitation to imprecise probabilities (IP). This investigation is motivated by multi-distribution learning, which takes the classical machine learning paradigm of minimising a single risk over a (precise) probability and replaces it with $\Gamma$-maximin risk minimization over an IP. We provide necessary conditions for elicitability of a IP-property. Furthermore, we explain what an elicitable IP-property actually elicits through Bayes pairs -- the elicited IP-property is the corresponding standard property of the maximum Bayes risk distribution.
Authors: Woonsang Kang, Joohyung Lee, Seungjun Kim, Jungchan Cho, Yoonseon Oh
Abstract: Grasp pose detection (GPD) is a fundamental capability for robotic autonomy, but its reliance on large, diverse datasets creates significant data privacy and centralization challenges. Federated Learning (FL) offers a privacy-preserving solution, but its application to GPD is hindered by the substantial communication overhead of large models, a key issue for resource-constrained robots. To address this, we propose a novel module-wise FL framework that begins by analyzing the learning dynamics of the GPD model's functional components. This analysis identifies slower-converging modules, to which our framework then allocates additional communication effort. This is realized through a two-phase process: a standard full-model training phase is followed by a communication-efficient phase where only the identified subset of slower-converging modules is trained and their partial updates are aggregated. Extensive experiments on the GraspNet-1B dataset demonstrate that our method outperforms standard FedAvg and other baselines, achieving higher accuracy for a given communication budget. Furthermore, real-world experiments on a physical robot validate our approach, showing a superior grasp success rate compared to baseline methods in cluttered scenes. Our work presents a communication-efficient framework for training robust, generalized GPD models in a decentralized manner, effectively improving the trade-off between communication cost and model performance.
Authors: Zengjing Chen, Lu Wang, Chengzhi Xing
Abstract: This study addresses the problem of stable acoustic relay assignment in an underwater acoustic network. Unlike the objectives of most existing literature, two distinct objectives, namely classical stable arrangement and ambiguous stable arrangement, are considered. To achieve these stable arrangements, a laser chaos-based multi-processing learning (LC-ML) method is introduced to efficiently obtain high throughput and rapidly attain stability. In order to sufficiently explore the relay's decision-making, this method uses random numbers generated by laser chaos to learn the assignment of relays to multiple source nodes. This study finds that the laser chaos-based random number and multi-processing in the exchange process have a positive effect on higher throughput and strong adaptability with environmental changing over time. Meanwhile, ambiguous cognitions result in the stable configuration with less volatility compared to accurate ones. This provides a practical and useful method and can be the basis for relay selection in complex underwater environments.
Authors: Gholamali Aminian, Idan Shenfeld, Amir R. Asadi, Ahmad Beirami, Youssef Mroueh
Abstract: A simple yet effective method for inference-time alignment of generative models is Best-of-$N$ (BoN), where $N$ outcomes are sampled from a reference policy, evaluated using a proxy reward model, and the highest-scoring one is selected. While prior work argues that BoN is almost optimal in reward vs KL tradeoffs, the effectiveness of BoN depends critically on the quality of the proxy reward model used for selection. For this purpose, we study BoN through a smooth version known as Soft Best-of-N (SBoN) and develop a theoretical framework to address this gap. We analyze the scaling behaviour of BoN by providing bounds on the KL divergence between the SBoN policy and the reference policy, offering insights into how performance varies with the number of samples. We also study the regret gap, i.e., the gap between the expected true reward under the optimal policy and the SBoN policy. Our theoretical and empirical findings show that smoothing helps SBoN mitigate reward overoptimization, especially when the quality of the proxy reward is low.
Authors: Priyanka Roy, Susanne Saminger-Platz
Abstract: In this paper, we study an online regularized learning algorithm in a reproducing kernel Hilbert spaces (RKHS) based on a class of dependent processes. We choose such a process where the degree of dependence is measured by mixing coefficients. As a representative example, we analyze a strictly stationary Markov chain, where the dependence structure is characterized by the \(\phi\)- and \(\beta\)-mixing coefficients. Under these assumptions, we derive probabilistic upper bounds as well as convergence rates for both the exponential and polynomial decay of the mixing coefficients.
Authors: Yucheng Sheng, Jiacheng Wang, Xingyu Zhou, Le Liang, Hao Ye, Shi Jin, Geoffrey Ye Li
Abstract: With the growing complexity and dynamics of the mobile communication networks, accurately predicting key system parameters, such as channel state information (CSI), user location, and network traffic, has become essential for a wide range of physical (PHY)-layer and medium access control (MAC)-layer tasks. Although traditional deep learning (DL)-based methods have been widely applied to such prediction tasks, they often struggle to generalize across different scenarios and tasks. In response, we propose a unified foundation model for multi-task prediction in wireless networks that supports diverse prediction intervals. The proposed model enforces univariate decomposition to unify heterogeneous tasks, encodes granularity for interval awareness, and uses a causal Transformer backbone for accurate predictions. Additionally, we introduce a patch masking strategy during training to support arbitrary input lengths. After trained on large-scale datasets, the proposed foundation model demonstrates strong generalization to unseen scenarios and achieves zero-shot performance on new tasks that surpass traditional full-shot baselines.
Authors: Lunjia Hu, Salil Vadhan
Abstract: Pseudoentropy characterizations provide a quantitatively precise demonstration of the close relationship between computational hardness and computational randomness. We prove a unified pseudoentropy characterization that generalizes and strengthens previous results for both uniform and non-uniform models of computation. Our characterization holds for a general family of entropy notions that encompasses the common notions of Shannon entropy and min entropy as special cases. Moreover, we show that the characterizations for different entropy notions can be simultaneously achieved by a single, universal function that simultaneously witnesses computational hardness and computational randomness. A key technical insight of our work is that the notion of weight-restricted calibration from the recent literature on algorithm fairness, along with standard computational indistinguishability (known as multiaccuracy in the fairness literature), suffices for proving pseudoentropy characterizations for general entropy notions. This demonstrates the power of weight-restricted calibration to enhance the classic Complexity-Theoretic Regularity Lemma (Trevisan, Tulsiani, and Vadhan, 2009) and Leakage Simulation Lemma (Jetchev and Pietrzak, 2014) and allows us to achieve an exponential improvement in the complexity dependency on the alphabet size compared to the pseudoentropy characterizations by Casacuberta, Dwork, and Vadhan (2024) based on the much stronger notion of multicalibration. We show that the exponential dependency on the alphabet size is inevitable for multicalibration as well as for the weaker notion of calibrated multiaccuracy.
Authors: Gabriel Chua, Leanne Tan, Ziyu Ge, Roy Ka-Wei Lee
Abstract: Large language models (LLMs) and their safety classifiers often perform poorly on low-resource languages due to limited training data and evaluation benchmarks. This paper introduces RabakBench, a new multilingual safety benchmark localized to Singapore's unique linguistic context, covering Singlish, Chinese, Malay, and Tamil. RabakBench is constructed through a scalable three-stage pipeline: (i) Generate - adversarial example generation by augmenting real Singlish web content with LLM-driven red teaming; (ii) Label - semi-automated multi-label safety annotation using majority-voted LLM labelers aligned with human judgments; and (iii) Translate - high-fidelity translation preserving linguistic nuance and toxicity across languages. The final dataset comprises over 5,000 safety-labeled examples across four languages and six fine-grained safety categories with severity levels. Evaluations of 11 popular open-source and closed-source guardrail classifiers reveal significant performance degradation. RabakBench not only enables robust safety evaluation in Southeast Asian multilingual settings but also offers a reproducible framework for building localized safety datasets in low-resource environments. The benchmark dataset, including the human-verified translations, and evaluation code are publicly available.
Authors: Julian Fortune, Julie A. Adams, Jamison Heard
Abstract: Demanding task environments (e.g., supervising a remotely piloted aircraft) require performing tasks quickly and accurately; however, periods of low and high operator workload can decrease task performance. Intelligent modulation of the system's demands and interaction modality in response to changes in operator workload state may increase performance by avoiding undesirable workload states. This system requires real-time estimation of each workload component (i.e., cognitive, physical, visual, speech, and auditory) to adapt the correct modality. Existing workload systems estimate multiple workload components post-hoc, but few estimate speech workload, or function in real-time. An algorithm to estimate speech workload and mitigate undesirable workload states in real-time is presented. An analysis of the algorithm's accuracy is presented, along with the results demonstrating the algorithm's generalizability across individuals and human-machine teaming paradigms. Real-time speech workload estimation is a crucial element towards developing adaptive human-machine systems.
Authors: Duy Khanh Lam
Abstract: In the online portfolio optimization framework, existing learning algorithms generate strategies that yield significantly poorer cumulative wealth compared to the best constant rebalancing portfolio in hindsight, despite being consistent in asymptotic growth rate. While this unappealing performance can be improved by incorporating more side information, it raises difficulties in feature selection and high-dimensional settings. Instead, the inherent serial dependence of assets' returns, such as day-of-the-week and other calendar effects, can be leveraged. Although latent serial dependence patterns are commonly detected using large training datasets, this paper proposes an algorithm that learns such dependence using only gradually revealed data, without any assumption on their distribution, to form a strategy that eventually exceeds the cumulative wealth of the best constant rebalancing portfolio. Moreover, the classical Kelly criterion, which requires independent assets' returns, is generalized to accommodate serial dependence in a market modeled as an independent and identically distributed process of random matrices. In such a stochastic market, where existing learning algorithms designed for stationary processes fail to apply, the proposed learning algorithm still generates a strategy that asymptotically grows to the highest rate among all strategies, matching that of the optimal strategy constructed under the generalized Kelly criterion. The experimental results with real market data demonstrate the theoretical guarantees of the algorithm and its performance as expected, as long as serial dependence is significant, regardless of the validity of the generalized Kelly criterion in the experimental market. This further affirms the broad applicability of the algorithm in general contexts.
Authors: Ryan O'Donnell, Chirag Wadhwa
Abstract: We consider the task of quantum state certification: given a description of a hypothesis state $\sigma$ and multiple copies of an unknown state $\rho$, a tester aims to determine whether the two states are equal or $\epsilon$-far in trace distance. It is known that $\Theta(d/\epsilon^2)$ copies of $\rho$ are necessary and sufficient for this task, assuming the tester can make entangled measurements over all copies [CHW07,OW15,BOW19]. However, these bounds are for a worst-case $\sigma$, and it is not known what the optimal copy complexity is for this problem on an instance-by-instance basis. While such instance-optimal bounds have previously been shown for quantum state certification when the tester is limited to measurements unentangled across copies [CLO22,CLHL22], they remained open when testers are unrestricted in the kind of measurements they can perform. We address this open question by proving nearly instance-optimal bounds for quantum state certification when the tester can perform fully entangled measurements. Analogously to the unentangled setting, we show that the optimal copy complexity for certifying $\sigma$ is given by the worst-case complexity times the fidelity between $\sigma$ and the maximally mixed state. We prove our lower bounds using a novel quantum analogue of the Ingster-Suslina method, which is likely to be of independent interest. This method also allows us to recover the $\Omega(d/\epsilon^2)$ lower bound for mixedness testing [OW15], i.e., certification of the maximally mixed state, with a surprisingly simple proof.
Authors: Juncheng Jia, Ji Liu, Chao Huo, Yihui Shen, Yang Zhou, Huaiyu Dai, Dejing Dou
Abstract: Federated Learning (FL) has emerged as a compelling methodology for the management of distributed data, marked by significant advancements in recent years. In this paper, we propose an efficient FL approach that capitalizes on additional downlink bandwidth resources to ensure timely update dissemination. Initially, we implement this strategy within an asynchronous framework, introducing the Asynchronous Staleness-aware Model Update (FedASMU), which integrates both server-side and device-side methodologies. On the server side, we present an asynchronous FL system model that employs a dynamic model aggregation technique, which harmonizes local model updates with the global model to enhance both accuracy and efficiency. Concurrently, on the device side, we propose an adaptive model adjustment mechanism that integrates the latest global model with local models during training to further elevate accuracy. Subsequently, we extend this approach to a synchronous context, referred to as FedSSMU. Theoretical analyses substantiate the convergence of our proposed methodologies. Extensive experiments, encompassing six models and five public datasets, demonstrate that FedASMU and FedSSMU significantly surpass baseline methods in terms of both accuracy (up to 145.87%) and efficiency (up to 97.59%).
Authors: Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Osama Ahmed Khan, Shahid Munir Shah, Umema Mujeeb, Maheen Ali
Abstract: The modern text-to-image diffusion models boom has opened a new era in digital content production as it has proven the previously unseen ability to produce photorealistic and stylistically diverse imagery based on the semantics of natural-language descriptions. However, the consistent disadvantage of these models is that they cannot generate readable, meaningful, and correctly spelled text in generated images, which significantly limits the use of practical purposes like advertising, learning, and creative design. This paper introduces a new framework, namely Glyph-Conditioned Diffusion with Character-Aware Attention (GCDA), using which a typical diffusion backbone is extended by three well-designed modules. To begin with, the model has a dual-stream text encoder that encodes both semantic contextual information and explicit glyph representations, resulting in a character-aware representation of the input text that is rich in nature. Second, an attention mechanism that is aware of the character is proposed with a new attention segregation loss that aims to limit the attention distribution of each character independently in order to avoid distortion artifacts. Lastly, GCDA has an OCR-in-the-loop fine-tuning phase, where a full text perceptual loss, directly optimises models to be legible and accurately spell. Large scale experiments to benchmark datasets, such as MARIO-10M and T2I-CompBench, reveal that GCDA sets a new state-of-the-art on all metrics, with better character based metrics on text rendering (Character Error Rate: 0.08 vs 0.21 for the previous best; Word Error Rate: 0.15 vs 0.25), human perception, and comparable image synthesis quality on high-fidelity (FID: 14.3).
Authors: Kyriakos Georgiou, Constantinos Siettos, Athanasios N. Yannacopoulos
Abstract: Building on our previous work introducing Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to tackle forward and inverse problems for linear and semi-linear elliptic partial differential equations. The proposed scheme consists of a deep neural network (DNN) which is designed to represent the iterative process of fixed-point iterations for the solution of elliptic PDEs using the boundary integral method within the framework of potential theory. The number of layers, weights, biases and hyperparameters are computed in an explainable manner based on the iterative scheme, and we therefore refer to this as the Potential Fredholm Neural Network (PFNN). We show that this approach ensures both accuracy and explainability, achieving small errors in the interior of the domain, and near machine-precision on the boundary. We provide a constructive proof for the consistency of the scheme and provide explicit error bounds for both the interior and boundary of the domain, reflected in the layers of the PFNN. These error bounds depend on the approximation of the boundary function and the integral discretization scheme, both of which directly correspond to components of the Fredholm NN architecture. In this way, we provide an explainable scheme that explicitly respects the boundary conditions. We assess the performance of the proposed scheme for the solution of both the forward and inverse problem for linear and semi-linear elliptic PDEs in two dimensions.
Authors: Francesco Martinuzzi
Abstract: Machine learning (ML) is widely used to model chaotic systems. Among ML approaches, echo state networks (ESNs) have received considerable attention due to their simple construction and fast training. However, ESN performance is highly sensitive to hyperparameter choices and to its random initialization. In this work, we demonstrate that ESNs constructed using deterministic rules and simple topologies (MESNs) outperform standard ESNs in the task of chaotic attractor reconstruction. We use a dataset of more than 90 chaotic systems to benchmark 10 different minimal deterministic reservoir initializations. We find that MESNs obtain up to a 41% reduction in error compared to standard ESNs. Furthermore, we show that the MESNs are more robust, exhibiting less inter-run variation, and have the ability to reuse hyperparameters across different systems. Our results illustrate how structured simplicity in ESN design can outperform stochastic complexity in learning chaotic dynamics.
Authors: Arturo Castellanos, Anna Korba, Pavlo Mozharovskyi, Hicham Janati
Abstract: Distances between probability distributions are a key component of many statistical machine learning tasks, from two-sample testing to generative modeling, among others. We introduce a novel distance between measures that compares them through a Schatten norm of their kernel covariance operators. We show that this new distance is an integral probability metric that can be framed between a Maximum Mean Discrepancy (MMD) and a Wasserstein distance. In particular, we show that it avoids some pitfalls of MMD, by being more discriminative and robust to the choice of hyperparameters. Moreover, it benefits from some compelling properties of kernel methods, that can avoid the curse of dimensionality for their sample complexity. We provide an algorithm to compute the distance in practice by introducing an extension of kernel matrix for difference of distributions that could be of independent interest. Those advantages are illustrated by robust approximate Bayesian computation under contamination as well as particle flow simulations.
Authors: Bo Pang, Yalu Ouyang, Hangfei Xu, Ziqi Jia, Panpan Li, Shengzhao Wen, Lu Wang, Shiyong Li, Yanpeng Wang
Abstract: Advancements in reasoning for large language models (LLMs) have lead to significant performance improvements for LLMs in various fields such as mathematics and programming. However, research applying these advances to the financial domain, where considerable domain-specific knowledge is necessary to complete tasks, remains limited. To address this gap, we introduce FEVO (Financial Evolution), a multi-stage enhancement framework developed to enhance LLM performance in the financial domain. FEVO systemically enhances LLM performance by using continued pre-training (CPT) to expand financial domain knowledge, supervised fine-tuning (SFT) to instill structured, elaborate reasoning patterns, and reinforcement learning (RL) to further integrate the expanded financial domain knowledge with the learned structured reasoning. To ensure effective and efficient training, we leverage frontier reasoning models and rule-based filtering to curate FEVO-Train, high-quality datasets specifically designed for the different post-training phases. Using our framework, we train the FEVO series of models - C32B, S32B, R32B - from Qwen2.5-32B and evaluate them on seven benchmarks to assess financial and general capabilities, with results showing that FEVO-R32B achieves state-of-the-art performance on five financial benchmarks against much larger models as well as specialist models. More significantly, FEVO-R32B demonstrates markedly better performance than FEVO-R32B-0 (trained from Qwen2.5-32B-Instruct using only RL), thus validating the effectiveness of financial domain knowledge expansion and structured, logical reasoning distillation
Authors: Aime Bienfait Igiraneza, Christophe Fraser, Robert Hinch
Abstract: Unlike classification, whose goal is to estimate the class of each data point in a dataset, prevalence estimation or quantification is a task that aims to estimate the distribution of classes in a dataset. The two main tasks in prevalence estimation are to adjust for bias, due to the prevalence in the training dataset, and to quantify the uncertainty in the estimate. The standard methods used to quantify uncertainty in prevalence estimates are bootstrapping and Bayesian quantification methods. It is not clear which approach is ideal in terms of precision (i.e. the width of confidence intervals) and coverage (i.e. the confidence intervals being well-calibrated). Here, we propose Precise Quantifier (PQ), a Bayesian quantifier that is more precise than existing quantifiers and with well-calibrated coverage. We discuss the theory behind PQ and present experiments based on simulated and real-world datasets. Through these experiments, we establish the factors which influence quantification precision: the discriminatory power of the underlying classifier; the size of the labeled dataset used to train the quantifier; and the size of the unlabeled dataset for which prevalence is estimated. Our analysis provides deep insights into uncertainty quantification for quantification learning.
Authors: Christos Nikou, Theodoros Giannakopoulos
Abstract: Recent advances in song identification leverage deep neural networks to learn compact audio fingerprints directly from raw waveforms. While these methods perform well under controlled conditions, their accuracy drops significantly in real-world scenarios where the audio is captured via mobile devices in noisy environments. In this paper, we introduce a novel evaluation protocol designed to better reflect such real-world conditions. We generate three recordings of the same audio, each with increasing levels of noise, captured using a mobile device's microphone. Our results reveal a substantial performance drop for two state-of-the-art CNN-based models under this protocol, compared to previously reported benchmarks. Additionally, we highlight the critical role of the augmentation pipeline during training with contrastive loss. By introduction low pass and high pass filters in the augmentation pipeline we significantly increase the performance of both systems in our proposed evaluation. Furthermore, we develop a transformer-based model with a tailored projection module and demonstrate that transferring knowledge from a semantically relevant domain yields a more robust solution. The transformer architecture outperforms CNN-based models across all noise levels, and query durations. In low noise conditions it achieves 47.99% for 1-sec queries, and 97% for 10-sec queries in finding the correct song, surpassing by 14%, and by 18.5% the second-best performing model, respectively, Under heavy noise levels, we achieve a detection rate 56.5% for 15-second query duration. All experiments are conducted on public large-scale dataset of over 100K songs, with queries matched against a database of 56 million vectors.
Authors: Shravya Kanchi, Neal Mangaokar, Aravind Cheruvu, Sifat Muhammad Abdullah, Shirin Nilizadeh, Atul Prakash, Bimal Viswanath
Abstract: Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmic advancements. We argue that data challenges that negatively impact the performance of these classifiers have received limited attention. We address the following research question: Can developments in Generative AI (GenAI) address these data challenges and improve classifier performance? We propose augmenting training datasets with synthetic data generated using GenAI techniques to improve classifier generalization. We evaluate this approach across 7 diverse security tasks using 6 state-of-the-art GenAI methods and introduce a novel GenAI scheme called Nimai that enables highly controlled data synthesis. We find that GenAI techniques can significantly improve the performance of security classifiers, achieving improvements of up to 32.6% even in severely data-constrained settings (only ~180 training samples). Furthermore, we demonstrate that GenAI can facilitate rapid adaptation to concept drift post-deployment, requiring minimal labeling in the adjustment process. Despite successes, our study finds that some GenAI schemes struggle to initialize (train and produce data) on certain security tasks. We also identify characteristics of specific tasks, such as noisy labels, overlapping class distributions, and sparse feature vectors, which hinder performance boost using GenAI. We believe that our study will drive the development of future GenAI tools designed for security tasks.
Authors: Murilo Gustineli, Anthony Miyaguchi, Adrian Cheung, Divyansh Khattak
Abstract: We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images. Our pipeline combines (i) a fine-tuned Vision Transformer ViTD2PC24All for patch-level inference, (ii) a 4x4 tiling strategy that aligns patch size with the network's 518x518 receptive field, and (iii) domain-prior adaptation through PaCMAP + K-Means visual clustering and geolocation filtering. Tile predictions are aggregated by majority vote and re-weighted with cluster-specific Bayesian priors, yielding a macro-averaged F1 of 0.348 (private leaderboard) while requiring no additional training. All code, configuration files, and reproducibility scripts are publicly available at https://github.com/dsgt-arc/plantclef-2025.
Authors: Kwanghyuk Park, Jiaxi Gu, Jae-Hun Jung
Abstract: In this work, we present the feedforward neural network based on the conservative approximation to the derivative from point values, for the weighted essentially non-oscillatory (WENO) schemes in solving hyperbolic conservation laws. The feedforward neural network, whose inputs are point values from the three-point stencil and outputs are two nonlinear weights, takes the place of the classical WENO weighting procedure. For the training phase, we employ the supervised learning and create a new labeled dataset for one-dimensional conservative approximation, where we construct a numerical flux function from the given point values such that the flux difference approximates the derivative to high-order accuracy. The symmetric-balancing term is introduced for the loss function so that it propels the neural network to match the conservative approximation to the derivative and satisfy the symmetric property that WENO3-JS and WENO3-Z have in common. The consequent WENO schemes, WENO3-CADNNs, demonstrate robust generalization across various benchmark scenarios and resolutions, where they outperform WENO3-Z and achieve accuracy comparable to WENO5-JS.
Authors: Jiale Lao, Immanuel Trummer
Abstract: Database research and development often require a large number of SQL queries for benchmarking purposes. However, acquiring real-world SQL queries is challenging due to privacy concerns, and existing SQL generation methods are limited in customization and in satisfying realistic constraints. To address this issue, we present SQLBarber, a system based on Large Language Models (LLMs) to generate customized and realistic SQL workloads. SQLBarber (i) eliminates the need for users to manually craft SQL templates in advance, while providing the flexibility to accept natural language specifications to constrain SQL templates, (ii) scales efficiently to generate large volumes of queries matching any user-defined cost distribution (e.g., cardinality and execution plan cost), and (iii) uses execution statistics from Amazon Redshift and Snowflake to derive SQL template specifications and query cost distributions that reflect real-world query characteristics. SQLBarber introduces (i) a declarative interface for users to effortlessly generate customized SQL templates, (ii) an LLM-powered pipeline augmented with a self-correction module that profiles, refines, and prunes SQL templates based on query costs, and (iii) a Bayesian Optimizer to efficiently explore different predicate values and identify a set of queries that satisfy the target cost distribution. We construct and open-source ten benchmarks of varying difficulty levels and target query cost distributions based on real-world statistics from Snowflake and Amazon Redshift. Extensive experiments on these benchmarks show that SQLBarber is the only system that can generate customized SQL templates. It reduces query generation time by one to three orders of magnitude, and significantly improves alignment with the target cost distribution, compared with existing methods.
Authors: Dylan Bouchard, Mohit Singh Chauhan, David Skarbrevik, Ho-Kyeong Ra, Viren Bajaj, Zeya Ahmad
Abstract: Hallucinations, defined as instances where Large Language Models (LLMs) generate false or misleading content, pose a significant challenge that impacts the safety and trust of downstream applications. We introduce UQLM, a Python package for LLM hallucination detection using state-of-the-art uncertainty quantification (UQ) techniques. This toolkit offers a suite of UQ-based scorers that compute response-level confidence scores ranging from 0 to 1. This library provides an off-the-shelf solution for UQ-based hallucination detection that can be easily integrated to enhance the reliability of LLM outputs.
Authors: Maria V. Pruzhinskaya, Anastasia D. Lavrukhina, Timofey A. Semenikhi, Alina A. Volnova, Sreevarsha Sreejith, Vadim V. Krushinsky, Emmanuel Gangler, Emille E. O. Ishida, Matwey V. Kornilov, Konstantin L. Malanchev
Abstract: We present results from the SNAD VIII Workshop, during which we conducted the first systematic anomaly search in the ZTF fields also observed by LSSTComCam during Rubin Scientific Pipeline commissioning. Using the PineForest active anomaly detection algorithm, we analysed four selected fields (two galactic and two extragalactic) and visually inspected 400 candidates. As a result, we discovered six previously uncatalogued variable stars, including RS~CVn, BY Draconis, ellipsoidal, and solar-type variables, and refined classifications and periods for six known objects. These results demonstrate the effectiveness of the SNAD anomaly detection pipeline and provide a preview of the discovery potential in the upcoming LSST data.
Authors: Modi Shi, Li Chen, Jin Chen, Yuxiang Lu, Chiming Liu, Guanghui Ren, Ping Luo, Di Huang, Maoqing Yao, Hongyang Li
Abstract: Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood. In this work, we investigate the nuanced role of data diversity in robot learning by examining three critical dimensions-task (what to do), embodiment (which robot to use), and expert (who demonstrates)-challenging the conventional intuition of "more diverse is better". Throughout extensive experiments on various robot platforms, we reveal that (1) task diversity proves more critical than per-task demonstration quantity, benefiting transfer from diverse pre-training tasks to novel downstream scenarios; (2) multi-embodiment pre-training data is optional for cross-embodiment transfer-models trained on high-quality single-embodiment data can efficiently transfer to different platforms, showing more desirable scaling property during fine-tuning than multi-embodiment pre-trained models; and (3) expert diversity, arising from individual operational preferences and stochastic variations in human demonstrations, can be confounding to policy learning, with velocity multimodality emerging as a key contributing factor. Based on this insight, we propose a distribution debiasing method to mitigate velocity ambiguity, the yielding GO-1-Pro achieves substantial performance gains of 15%, equivalent to using 2.5 times pre-training data. Collectively, these findings provide new perspectives and offer practical guidance on how to scale robotic manipulation datasets effectively.
Authors: Zhiyuan Peng, Ting-ruen Wei, Tingyu Song, Yilun Zhao, Yi Fang
Abstract: Large Language Models (LLMs) have recently been applied to reranking tasks in information retrieval, achieving strong performance. However, their high computational demands often hinder practical deployment. Existing studies evaluate the efficiency of LLM-based rerankers using proxy metrics such as latency, the number of forward passes, input tokens, and output tokens. However, these metrics depend on hardware and running-time choices (\eg parallel or not, batch size, etc), and often fail to account for model size, making it difficult to interpret and obscuring the evaluation of the efficiency-effectiveness tradeoff. To address this issue, we propose E\textsuperscript{2}R-FLOPs, for LLM-based rerankers: ranking metrics per PetaFLOP (RPP) for relevance per compute and queries per PetaFLOP (QPP) for hardware-agnostic throughput. Companied with the new metrics, an interpretable FLOPs estimator is built to estimate the FLOPs of an LLM-based reranker even without running any experiments. Based on the proposed metrics, we conduct comprehensive experiments to evaluate a wide range of LLM-based rerankers with different architecture, studying the efficiency-effectiveness trade-off and bringing this issue to the attention of the research community.
Authors: Nunzio A. Letizia, Nicola Novello, Andrea M. Tonello
Abstract: Probability density estimation from observed data constitutes a central task in statistics. In this brief, we focus on the problem of estimating the copula density associated to any observed data, as it fully describes the dependence between random variables. We separate univariate marginal distributions from the joint dependence structure in the data, the copula itself, and we model the latter with a neural network-based method referred to as copula density neural estimation (CODINE). Results show that the novel learning approach is capable of modeling complex distributions and can be applied for mutual information estimation and data generation.
Authors: Chris Mingard, Henry Rees, Guillermo Valle-P\'erez, Ard A. Louis
Abstract: The remarkable performance of overparameterized deep neural networks (DNNs) must arise from an interplay between network architecture, training algorithms, and structure in the data. To disentangle these three components, we apply a Bayesian picture, based on the functions expressed by a DNN, to supervised learning. The prior over functions is determined by the network, and is varied by exploiting a transition between ordered and chaotic regimes. For Boolean function classification, we approximate the likelihood using the error spectrum of functions on data. When combined with the prior, this accurately predicts the posterior, measured for DNNs trained with stochastic gradient descent. This analysis reveals that structured data, combined with an intrinsic Occam's razor-like inductive bias towards (Kolmogorov) simple functions that is strong enough to counteract the exponential growth of the number of functions with complexity, is a key to the success of DNNs.
Authors: Qi Hu, Weifeng Jiang, Haoran Li, Zihao Wang, Jiaxin Bai, Qianren Mao, Yangqiu Song, Lixin Fan, Jianxin Li
Abstract: The increasing demand for deep learning-based foundation models has highlighted the importance of efficient data retrieval mechanisms. Neural graph databases (NGDBs) offer a compelling solution, leveraging neural spaces to store and query graph-structured data, thereby enabling LLMs to access precise and contextually relevant information. However, current NGDBs are constrained to single-graph operation, limiting their capacity to reason across multiple, distributed graphs. Furthermore, the lack of support for multi-source graph data in existing NGDBs hinders their ability to capture the complexity and diversity of real-world data. In many applications, data is distributed across multiple sources, and the ability to reason across these sources is crucial for making informed decisions. This limitation is particularly problematic when dealing with sensitive graph data, as directly sharing and aggregating such data poses significant privacy risks. As a result, many applications that rely on NGDBs are forced to choose between compromising data privacy or sacrificing the ability to reason across multiple graphs. To address these limitations, we propose to learn Federated Neural Graph DataBase (FedNGDB), a pioneering systematic framework that empowers privacy-preserving reasoning over multi-source graph data. FedNGDB leverages federated learning to collaboratively learn graph representations across multiple sources, enriching relationships between entities, and improving the overall quality of graph data.
Authors: Wee Chaimanowong, Ying Zhu
Abstract: Many machine learning models leverage group invariance which is enjoyed with a wide-range of applications. For exploiting an invariance structure, one common approach is known as \emph{frame averaging}. One popular example of frame averaging is the \emph{group averaging}, where the entire group is used to symmetrize a function. The other end of the spectrum is the \emph{canonicalization}, where a frame at each point consists of a single group element which transforms the point to its orbit representative. Compared to group averaging, canonicalization is more efficient computationally. However, it results in non-differentiablity or discontinuity of the canonicalized function. As a result, the theoretical performance of canonicalization has not been given much attention. In this work, we establish an approximation theory for canonicalization. Specifically, we bound the point-wise and $L^2(\mathbb{P})$ approximation errors as well as the kernel's eigenvalue decay rates associated with a canonicalization trick.
Authors: Eduardo Fernandes Montesuma, Fred Maurice Ngol\`e Mboula, Antoine Souloumiac
Abstract: Machine learning systems operate under the assumption that training and test data are sampled from a fixed probability distribution. However, this assumptions is rarely verified in practice, as the conditions upon which data was acquired are likely to change. In this context, the adaptation of the unsupervised domain requires minimal access to the data of the new conditions for learning models robust to changes in the data distribution. Optimal transport is a theoretically grounded tool for analyzing changes in distribution, especially as it allows the mapping between domains. However, these methods are usually computationally expensive as their complexity scales cubically with the number of samples. In this work, we explore optimal transport between Gaussian Mixture Models (GMMs), which is conveniently written in terms of the components of source and target GMMs. We experiment with 9 benchmarks, with a total of $85$ adaptation tasks, showing that our methods are more efficient than previous shallow domain adaptation methods, and they scale well with number of samples $n$ and dimensions $d$.
Authors: Zhan Qu, Daniel Gomm, Michael F\"arber
Abstract: Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy, Counterfactual Explainer for Dynamic Graphs, a model-agnostic, instance-level explanation approach that identifies counterfactual subgraphs to interpret TGNN predictions. CoDy employs a search algorithm that combines Monte Carlo Tree Search with heuristic selection policies, efficiently exploring a vast search space of potential explanatory subgraphs by leveraging spatial, temporal, and local event impact information. Extensive experiments against state-of-the-art factual and counterfactual baselines demonstrate CoDy's effectiveness, with improvements of 16% in AUFSC+ over the strongest baseline.
Authors: Shaily Roy, Harshit Sharma, Asif Salekin
Abstract: Federated Learning (FL) enables privacy-preserving collaborative training, making it well-suited for decentralized human-sensing applications. Ensuring fairness in FL is challenging, as current methods rely on sensitive attribute knowledge, which conflicts with FL's privacy principles. Additionally, sensitive attributes in human-sensing data may be unknown or latent. To address this, we introduce Curvature-Aligned Federated Learning (CAFe), a theoretically grounded approach that achieves fairness in FL without requiring sensitive attribute knowledge, a concept termed "Fairness without Demographics" (FWD). CAFe introduces loss-landscape curvature regularization during local training and clients' loss-landscape sharpness-aware aggregation to align curvature both within and across clients, enabling a strong balance between higher fairness and performance. CAFe is especially suitable for real-world human-sensing FL scenarios involving single or multi-user edge devices with unknown or multiple bias factors. We validated CAFe through theoretical and empirical justifications, and comprehensive evaluations using three real-world datasets and a live real-world FL deployment with a heterogeneous testbed of resource-constrained devices. Additionally, we conduct sensitivity analyses on local training data volume, client sampling, communication overhead, resource costs, and runtime performance to demonstrate its feasibility for practical FL edge device deployment.
Authors: Thom Badings, Wietze Koops, Sebastian Junges, Nils Jansen
Abstract: We consider the verification of neural network policies for discrete-time stochastic systems with respect to reach-avoid specifications. We use a learner-verifier procedure that learns a certificate for the specification, represented as a neural network. Verifying that this neural network certificate is a so-called reach-avoid supermartingale (RASM) proves the satisfaction of a reach-avoid specification. Existing approaches for such a verification task rely on computed Lipschitz constants of neural networks. These approaches struggle with large Lipschitz constants, especially for reach-avoid specifications with high threshold probabilities. We present two key contributions to obtain smaller Lipschitz constants than existing approaches. First, we introduce logarithmic RASMs (logRASMs), which take exponentially smaller values than RASMs and hence have lower theoretical Lipschitz constants. Second, we present a fast method to compute tighter upper bounds on Lipschitz constants based on weighted norms. Our empirical evaluation shows we can consistently verify the satisfaction of reach-avoid specifications with probabilities as high as 99.9999%.
Authors: Lukas Fluri, Leon Lang, Alessandro Abate, Patrick Forr\'e, David Krueger, Joar Skalse
Abstract: In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error on the data distribution, and yet subsequently produce a policy with large regret. We say that such a reward model has an error-regret mismatch. The main source of an error-regret mismatch is the distributional shift that commonly occurs during policy optimization. In this paper, we mathematically show that a sufficiently low expected test error of the reward model guarantees low worst-case regret, but that for any fixed expected test error, there exist realistic data distributions that allow for error-regret mismatch to occur. We then show that similar problems persist even when using policy regularization techniques, commonly employed in methods such as RLHF. We hope our results stimulate the theoretical and empirical study of improved methods to learn reward models, and better ways to measure their quality reliably.
Authors: Joseph Paillard, Angel Reyero Lobo, Vitaliy Kolodyazhniy, Bertrand Thirion, Denis A. Engemann
Abstract: Causal machine learning holds promise for estimating individual treatment effects from complex data. For successful real-world applications of machine learning methods, it is of paramount importance to obtain reliable insights into which variables drive heterogeneity in the response to treatment. We propose PermuCATE, an algorithm based on the Conditional Permutation Importance (CPI) method, for statistically rigorous global variable importance assessment in the estimation of the Conditional Average Treatment Effect (CATE). Theoretical analysis of the finite sample regime and empirical studies show that PermuCATE has lower variance than the Leave-One-Covariate-Out (LOCO) reference method and provides a reliable measure of variable importance. This property increases statistical power, which is crucial for causal inference in the limited-data regime common to biomedical applications. We empirically demonstrate the benefits of PermuCATE in simulated and real-world health datasets, including settings with up to hundreds of correlated variables.
Authors: Quan Zhou, Changhua Pei, Fei Sun, Jing Han, Zhengwei Gao, Dan Pei, Haiming Zhang, Gaogang Xie, Jianhui Li
Abstract: Time series anomaly detection (TSAD) underpins real-time monitoring in cloud services and web systems, allowing rapid identification of anomalies to prevent costly failures. Most TSAD methods driven by forecasting models tend to overfit by emphasizing minor fluctuations. Our analysis reveals that effective TSAD should focus on modeling "normal" behavior through smooth local patterns. To achieve this, we reformulate time series modeling as approximating the series with smooth univariate functions. The local smoothness of each univariate function ensures that the fitted time series remains resilient against local disturbances. However, a direct KAN implementation proves susceptible to these disturbances due to the inherently localized characteristics of B-spline functions. We thus propose KAN-AD, replacing B-splines with truncated Fourier expansions and introducing a novel lightweight learning mechanism that emphasizes global patterns while staying robust to local disturbances. On four popular TSAD benchmarks, KAN-AD achieves an average 15% improvement in detection accuracy (with peaks exceeding 27%) over state-of-the-art baselines. Remarkably, it requires fewer than 1,000 trainable parameters, resulting in a 50% faster inference speed compared to the original KAN, demonstrating the approach's efficiency and practical viability.
Authors: Xiang Li, Changsheng Shui, Zhongying Zhao, Junyu Dong, Yanwei Yu
Abstract: Rating is a typical user explicit feedback that visually reflects how much a user likes a related item. The (rating) matrix completion is essentially a rating prediction process, which is also a significant problem in recommender systems. Recently, graph neural networks (GNNs) have been widely used in matrix completion, which captures users' preferences over items by formulating a rating matrix as a bipartite graph. However, existing methods are susceptible due to data sparsity and long-tail distribution in real-world scenarios. Moreover, the messaging mechanism of GNNs makes it difficult to capture high-order correlations and constraints between nodes, which are essentially useful in recommendation tasks. To tackle these challenges, we propose a Multi-Channel Hypergraph Contrastive Learning framework for matrix completion, named MHCL. Specifically, MHCL adaptively learns hypergraph structures to capture high-order correlations between nodes and jointly captures local and global collaborative relationships through attention-based cross-view aggregation. Additionally, to consider the magnitude and order information of ratings, we treat different rating subgraphs as different channels, encourage alignment between adjacent ratings, and further achieve the mutual enhancement between different ratings through multi-channel cross-rating contrastive learning. Extensive experiments on five public datasets demonstrate that the proposed method significantly outperforms the current state-of-the-art approaches.
Authors: Aviad Susman, Rupak Krishnamurthy, Yan Chak Li, Mohammad Olaimat, Serdar Bozdag, Bino Varghese, Nasim Sheikh-Bahaei, Gaurav Pandey
Abstract: Effectively modeling multimodal longitudinal data is a pressing need in various application areas, especially biomedicine. Despite this, few approaches exist in the literature for this problem, with most not adequately taking into account the multimodality of the data. In this study, we developed multiple configurations of a novel multimodal and longitudinal learning framework, Longitudinal Ensemble Integration (LEI), for sequential classification. We evaluated LEI's performance, and compared it against existing approaches, for the early detection of dementia, which is among the most studied multimodal sequential classification tasks. LEI outperformed these approaches due to its use of intermediate base predictions arising from the individual data modalities, which enabled their better integration over time. LEI's design also enabled the identification of features that were consistently important across time for the effective prediction of dementia-related diagnoses. Overall, our work demonstrates the potential of LEI for sequential classification from longitudinal multimodal data.
Authors: Younggyo Seo, Pieter Abbeel
Abstract: Predicting a sequence of actions has been crucial in the success of recent behavior cloning algorithms in robotics. Can similar ideas improve reinforcement learning (RL)? We answer affirmatively by observing that incorporating action sequences when predicting ground-truth return-to-go leads to lower validation loss. Motivated by this, we introduce Coarse-to-fine Q-Network with Action Sequence (CQN-AS), a novel value-based RL algorithm that learns a critic network that outputs Q-values over a sequence of actions, i.e., explicitly training the value function to learn the consequence of executing action sequences. Our experiments show that CQN-AS outperforms several baselines on a variety of sparse-reward humanoid control and tabletop manipulation tasks from BiGym and RLBench.
Authors: Benjamin Eyre, David Madras
Abstract: The availability of machine learning systems that can effectively perform arbitrary tasks has led to synthetic labels from these systems being used in applications of statistical inference, such as data analysis or model evaluation. The Prediction Powered Inference (PPI) framework provides a way of leveraging both a large pool of pseudo-labelled data and a small sample with real, high-quality labels to produce a low-variance, unbiased estimate of the quantity being evaluated for. Most work on PPI considers a relatively sizable set of labelled samples, which can be resource intensive to obtain. However, we find that when labelled data is scarce, the PPI++ method can perform even worse than classical inference. We analyze this phenomenon by relating PPI++ to ordinary least squares regression, which also experiences high variance with small sample sizes, and use this regression framework to better understand the efficacy of PPI. Motivated by this, we present two new PPI-based techniques that leverage robust regressors to produce even lower variance estimators in the few-label regime.
Authors: Xingshuo Han, Xuanye Zhang, Xiang Lan, Haozhao Wang, Shengmin Xu, Shen Ren, Jason Zeng, Ming Wu, Michael Heinrich, Tianwei Zhang
Abstract: By using a control variate to calibrate the local gradient of each client, Scaffold has been widely known as a powerful solution to mitigate the impact of data heterogeneity in Federated Learning. Although Scaffold achieves significant performance improvements, we show that this superiority is at the cost of increased security vulnerabilities. Specifically, this paper presents BadSFL, the first backdoor attack targeting Scaffold, which turns benign clients into accomplices to amplify the attack effect. The core idea of BadSFL is to uniquely tamper with the control variate to subtly steer benign clients' local gradient updates towards the attacker's poisoned direction, effectively turning them into unwitting accomplices and significantly enhancing the backdoor persistence. Additionally, BadSFL leverages a GAN-enhanced poisoning strategy to enrich the attacker's dataset, maintaining high accuracy on both benign and backdoored samples while remaining stealthy. Extensive experiments demonstrate that BadSFL achieves superior attack durability, maintaining effectiveness for over 60 global rounds, lasting up to three times longer than existing baselines even after ceasing malicious model injections.
Authors: Xinxu Wei, Kanhao Zhao, Yong Jiao, Hua Xie, Lifang He, Yu Zhang
Abstract: Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this challenge by formulating it as a graph transfer learning and knowledge distillation problem. We propose a Unified Pre-trained Graph Contrastive Masked Autoencoder Distiller, named EEG-DisGCMAE, to bridge the gap between unlabeled and labeled as well as high- and low-density EEG data. Our approach introduces a novel unified graph self-supervised pre-training paradigm, which seamlessly integrates the graph contrastive pre-training with the graph masked autoencoder pre-training. Furthermore, we propose a graph topology distillation loss function, allowing a lightweight student model trained on low-density data to learn from a teacher model trained on high-density data during pre-training and fine-tuning. This method effectively handles missing electrodes through contrastive distillation. We validate the effectiveness of EEG-DisGCMAE across four classification tasks using two clinical EEG datasets with abundant data. The source code is available at https://github.com/weixinxu666/EEG_DisGCMAE.
Authors: Karthik Mohan
Abstract: In this report, I describe the systems in which the objective is to determine whether a given news article could be considered as hyperpartisan. Hyperpartisan news takes an extremely polarized political standpoint with an intention of creating political divide among the public. Several approaches, including n-grams, sentiment analysis, as well as sentence and document representations using pre-tained ELMo models were used. The best system is using LLMs for embedding generation achieving an accuracy of around 92% over the previously best system using pre-trained ELMo with Bidirectional LSTM which achieved an accuracy of around 83% through 10-fold cross-validation.
Authors: Joshua Southern, Yam Eitan, Guy Bar-Shalom, Michael Bronstein, Haggai Maron, Fabrizio Frasca
Abstract: Subgraph GNNs have emerged as promising architectures that overcome the expressiveness limitations of Graph Neural Networks (GNNs) by processing bags of subgraphs. Despite their compelling empirical performance, these methods are afflicted by a high computational complexity: they process bags whose size grows linearly in the number of nodes, hindering their applicability to larger graphs. In this work, we propose an effective and easy-to-implement approach to dramatically alleviate the computational cost of Subgraph GNNs and unleash broader applications thereof. Our method, dubbed HyMN, leverages walk-based centrality measures to sample a small number of relevant subgraphs and drastically reduce the bag size. By drawing a connection to perturbation analysis, we highlight the strength of the proposed centrality-based subgraph sampling, and further prove that these walk-based centralities can be additionally used as Structural Encodings for improved discriminative power. A comprehensive set of experimental results demonstrates that HyMN provides an effective synthesis of expressiveness, efficiency, and downstream performance, unlocking the application of Subgraph GNNs to dramatically larger graphs. Not only does our method outperform more sophisticated subgraph sampling approaches, it is also competitive, and sometimes better, than other state-of-the-art approaches for a fraction of their runtime.
Authors: Alexander Denker, Shreyas Padhy, Francisco Vargas, Johannes Hertrich
Abstract: Diffusion models are an important tool for generative modelling, serving as effective priors in applications such as imaging and protein design. A key challenge in applying diffusion models for downstream tasks is efficiently sampling from resulting posterior distributions, which can be addressed using the $h$-transform. This work introduces a self-supervised algorithm for fine-tuning diffusion models by estimating the $h$-transform, enabling amortised conditional sampling. Our method iteratively refines the $h$-transform using a synthetic dataset resampled with path-based importance weights. We demonstrate the effectiveness of this framework on class-conditional sampling, inverse problems and reward fine-tuning for text-to-image diffusion models.
Authors: Meiyu Zhong, Noel Teku, Ravi Tandon
Abstract: Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively generating a sequence of tokens and a larger target LLM for parallel verification to ensure statistical consistency. However, periodic parallel calls to the target LLM for verification prevent SD from achieving even lower latencies. We propose SPRINTER, which utilizes a low-complexity verifier trained to predict if tokens generated from a draft LLM would be accepted by the target LLM. By performing sequential approximate verification, SPRINTER does not require verification by the target LLM and is only invoked when a token is deemed unacceptable. This reduces the number of calls to the larger LLM, achieving further speedups and lower computation cost. We present a theoretical analysis of SPRINTER, examining the statistical properties of the generated tokens, as well as the expected reduction in latency as a function of the verifier. We evaluate SPRINTER on several datasets and model pairs, demonstrating that approximate verification can still maintain high quality generation while further reducing latency.
Authors: Alice Gorg\'e, Julien Ferry, S\'ebastien Gambs, Thibaut Vidal
Abstract: Recent research has shown that machine learning models are vulnerable to privacy attacks targeting their training data. To mitigate these risks, differential privacy (DP) has become a widely adopted countermeasure, as it offers rigorous privacy protection. In this paper, we introduce a reconstruction attack targeting state-of-the-art $\varepsilon$-DP random forests. By leveraging a constraint programming model that incorporates knowledge of the forest's structure and DP mechanism characteristics, our approach formally reconstructs the most likely dataset that could have produced a given forest. Through extensive computational experiments, we examine the interplay between model utility, privacy guarantees and reconstruction accuracy across various configurations. Our results reveal that random forests trained with meaningful DP guarantees can still leak portions of their training data. Specifically, while DP reduces the success of reconstruction attacks, the only forests fully robust to our attack exhibit predictive performance no better than a constant classifier. Building on these insights, we provide practical recommendations for the construction of DP random forests that are more resilient to reconstruction attacks and maintain non-trivial predictive performance.
Authors: Awa Khouna, Julien Ferry, Thibaut Vidal
Abstract: The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counterfactual explanations, inadvertently increase the risk of model extraction attacks, enabling unauthorized replication of proprietary models. In this paper, we formalize and characterize the risks and inherent complexity of model reconstruction, focusing on the "oracle'' queries required for faithfully inferring the underlying prediction function. We present the first formal analysis of model extraction attacks through the lens of competitive analysis, establishing a foundational framework to evaluate their efficiency. Focusing on models based on additive decision trees (e.g., decision trees, gradient boosting, and random forests), we introduce novel reconstruction algorithms that achieve provably perfect fidelity while demonstrating strong anytime performance. Our framework provides theoretical bounds on the query complexity for extracting tree-based model, offering new insights into the security vulnerabilities of their deployment.
Authors: Zhengyuan Shi, Chengyu Ma, Ziyang Zheng, Lingfeng Zhou, Hongyang Pan, Wentao Jiang, Fan Yang, Xiaoyan Yang, Zhufei Chu, Qiang Xu
Abstract: We introduce DeepCell, a novel circuit representation learning framework that effectively integrates multiview information from both And-Inverter Graphs (AIGs) and Post-Mapping (PM) netlists. At its core, DeepCell employs a self-supervised Mask Circuit Modeling (MCM) strategy, inspired by masked language modeling, to fuse complementary circuit representations from different design stages into unified and rich embeddings. To our knowledge, DeepCell is the first framework explicitly designed for PM netlist representation learning, setting new benchmarks in both predictive accuracy and reconstruction quality. We demonstrate the practical efficacy of DeepCell by applying it to critical EDA tasks such as functional Engineering Change Orders (ECO) and technology mapping. Extensive experimental results show that DeepCell significantly surpasses state-of-the-art open-source EDA tools in efficiency and performance.
Authors: Sebastian Sanokowski, Wilhelm Berghammer, Martin Ennemoser, Haoyu Peter Wang, Sepp Hochreiter, Sebastian Lehner
Abstract: Learning to sample from complex unnormalized distributions over discrete domains emerged as a promising research direction with applications in statistical physics, variational inference, and combinatorial optimization. Recent work has demonstrated the potential of diffusion models in this domain. However, existing methods face limitations in memory scaling and thus the number of attainable diffusion steps since they require backpropagation through the entire generative process. To overcome these limitations we introduce two novel training methods for discrete diffusion samplers, one grounded in the policy gradient theorem and the other one leveraging Self-Normalized Neural Importance Sampling (SN-NIS). These methods yield memory-efficient training and achieve state-of-the-art results in unsupervised combinatorial optimization. Numerous scientific applications additionally require the ability of unbiased sampling. We introduce adaptations of SN-NIS and Neural Markov Chain Monte Carlo that enable for the first time the application of discrete diffusion models to this problem. We validate our methods on Ising model benchmarks and find that they outperform popular autoregressive approaches. Our work opens new avenues for applying diffusion models to a wide range of scientific applications in discrete domains that were hitherto restricted to exact likelihood models.
Authors: Yue Sun, Rick S. Blum, Parv Venkitasubramaniam
Abstract: Dynamical systems, prevalent in various scientific and engineering domains, are susceptible to anomalies that can significantly impact their performance and reliability. This paper addresses the critical challenges of anomaly detection, root cause localization, and anomaly type classification in dynamical systems governed by ordinary differential equations (ODEs). We define two categories of anomalies: cyber anomalies, which propagate through interconnected variables, and measurement anomalies, which remain localized to individual variables. To address these challenges, we propose the Interpretable Causality Ordinary Differential Equation (ICODE) Networks, a model-intrinsic explainable learning framework. ICODE leverages Neural ODEs for anomaly detection while employing causality inference through an explanation channel to perform root cause analysis (RCA), elucidating why specific time periods are flagged as anomalous. ICODE is designed to simultaneously perform anomaly detection, RCA, and anomaly type classification within a single, interpretable framework. Our approach is grounded in the hypothesis that anomalies alter the underlying ODEs of the system, manifesting as changes in causal relationships between variables. We provide a theoretical analysis of how perturbations in learned model parameters can be utilized to identify anomalies and their root causes in time series data. Comprehensive experimental evaluations demonstrate the efficacy of ICODE across various dynamical systems, showcasing its ability to accurately detect anomalies, classify their types, and pinpoint their origins.
Authors: Rongzhen Wang, Yan Zhang, Chenyu Zheng, Chongxuan Li, Guoqiang Wu
Abstract: The success of large generative models has driven a paradigm shift, leveraging massive multi-source data to enhance model capabilities. However, the interaction among these sources remains theoretically underexplored. This paper takes the first step toward a rigorous analysis of multi-source training in conditional generative modeling, where each condition represents a distinct data source. Specifically, we establish a general distribution estimation error bound in average total variation distance for conditional maximum likelihood estimation based on the bracketing number. Our result shows that when source distributions share certain similarities and the model is expressive enough, multi-source training guarantees a sharper bound than single-source training. We further instantiate the general theory on conditional Gaussian estimation and deep generative models including autoregressive and flexible energy-based models, by characterizing their bracketing numbers. The results highlight that the number of sources and similarity among source distributions improve the advantage of multi-source training. Simulations and real-world experiments are conducted to validate the theory, with code available at: https://github.com/ML-GSAI/Multi-Source-GM.
Authors: Jianzhou Chen, Jinyang Sun, Xiumei Wang, Xi Chen, Heyu Chu, Guo Song, Yuji Luo, Xingping Zhou, Rong Gu
Abstract: Heart failure is one of the leading causes of death worldwide, with millons of deaths each year, according to data from the World Health Organization (WHO) and other public health agencies. While significant progress has been made in the field of heart failure, leading to improved survival rates and improvement of ejection fraction, there remains substantial unmet needs, due to the complexity and multifactorial characteristics. Therefore, we propose a composable strategy framework for assessment and treatment optimization in heart failure. This framework simulates the doctor-patient consultation process and leverages multi-modal algorithms to analyze a range of data, including video, physical examination, text results as well as medical history. By integrating these various data sources, our framework offers a more holistic evaluation and optimized treatment plan for patients. Our results demonstrate that this multi-modal approach outperforms single-modal artificial intelligence (AI) algorithms in terms of accuracy in heart failure (HF) prognosis prediction. Through this method, we can further evaluate the impact of various pathological indicators on HF prognosis,providing a more comprehensive evaluation.
Authors: Xiaohang Tang, Sangwoong Yoon, Seongho Son, Huizhuo Yuan, Quanquan Gu, Ilija Bogunovic
Abstract: Self-play alignment has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regularization with respect to the reference policy, which is crucial for mitigating over-optimization, has been insufficiently investigated in self-play alignment. To study the impact of different regularization strategies, we propose \textbf{Regularized Self-Play Policy Optimization (RSPO)}, a general and modular framework that unifies prior methods and enables simple plug-and-play integration of various regularizers, meanwhile preserving convergence to Nash equilibrium of the corresponding regularized game.Our empirical study involving over $120$ fine-tuned Mistral-7B-Instruct models reveals that forward KL divergence regularization reduces response length, whereas reverse KL divergence markedly improves raw win rates. Crucially, RSPO regularized with a linear combination of forward and reverse KL divergence significantly boosts the length-controlled win rate on AlpacaEval-2 from $28.5\%$ (unregularized self-play, SPPO) to $35.4\%$, and consistently demonstrates superior performance on Arena-Hard, MT-Bench, ArmoRM scores, and response diversity. Combining simplicity, convergence guarantees, and significant empirical gains, RSPO offers a strong foundation for exploring regularized self-play in language model alignment.
Authors: Ekaterina Redekop, Zichen Wang, Rushikesh Kulkarni, Mara Pleasure, Aaron Chin, Hamid Reza Hassanzadeh, Brian L. Hill, Melika Emami, William Speier, Corey W. Arnold
Abstract: Longitudinal data in electronic health records (EHRs) represent an individual`s clinical history through a sequence of codified concepts, including diagnoses, procedures, medications, and laboratory tests. Generative pre-trained transformers (GPT) can leverage this data to predict future events. While fine-tuning of these models can enhance task-specific performance, it becomes costly when applied to many clinical prediction tasks. In contrast, a pretrained foundation model can be used in zero-shot forecasting setting, offering a scalable alternative to fine-tuning separate models for each outcome. This study presents the first comprehensive analysis of zero-shot forecasting with GPT-based foundational models in EHRs, introducing a novel pipeline that formulates medical concept prediction as a generative modeling task. Unlike supervised approaches requiring extensive labeled data, our method enables the model to forecast a next medical event purely from a pretraining knowledge. We evaluate performance across multiple time horizons and clinical categories, demonstrating model`s ability to capture latent temporal dependencies and complex patient trajectories without task supervision. Model performance for predicting the next medical concept was evaluated using precision and recall metrics, achieving an average top1 precision of 0.614 and recall of 0.524. For 12 major diagnostic conditions, the model demonstrated strong zero-shot performance, achieving high true positive rates while maintaining low false positives. We demonstrate the power of a foundational EHR GPT model in capturing diverse phenotypes and enabling robust, zero-shot forecasting of clinical outcomes. This capability enhances the versatility of predictive healthcare models and reduces the need for task-specific training, enabling more scalable applications in clinical settings.
Authors: Kai Tong, Kang Pan, Xiao Zhang, Erli Meng, Run He, Yawen Cui, Nuoyan Guo, Huiping Zhuang
Abstract: Large Language Models (LLMs) possess encompassing capabilities that can process diverse language-related tasks. However, finetuning on LLMs will diminish this general skills and continual finetuning will further cause severe degradation on accumulated knowledge. Recently, Continual Learning (CL) in Large Language Models (LLMs) arises which aims to continually adapt the LLMs to new tasks while maintaining previously learned knowledge and inheriting general skills. Existing techniques either leverage previous data to replay, leading to extra computational costs, or utilize a single parameter-efficient module to learn the downstream task, constraining new knowledge absorption with interference between different tasks. Toward these issues, this paper proposes Analytic Subspace Routing(ASR) to address these challenges. For each task, we isolate the learning within a subspace of deep layers' features via low-rank adaptation, eliminating knowledge interference between different tasks. Additionally, we propose an analytic routing mechanism to properly utilize knowledge learned in different subspaces. Our approach employs Recursive Least Squares to train a multi-task router model, allowing the router to dynamically adapt to incoming data without requiring access to historical data. Also, the router effectively assigns the current task to an appropriate subspace and has a non-forgetting property of previously learned tasks with a solid theoretical guarantee. Experimental results demonstrate that our method achieves near-perfect retention of prior knowledge while seamlessly integrating new information, effectively overcoming the core limitations of existing methods. Our code will be released after acceptance.
Authors: Xiaobei Zou, Luolin Xiong, Kexuan Zhang, Cesare Alippi, Yang Tang
Abstract: Accurate predictions of spatio-temporal systems are crucial for tasks such as system management, control, and crisis prevention. However, the inherent time variance of many spatio-temporal systems poses challenges to achieving accurate predictions whenever stationarity is not granted. In order to address non-stationarity, we propose a Distribution and Relation Adaptive Network (DRAN) capable of dynamically adapting to relation and distribution changes over time. While temporal normalization and de-normalization are frequently used techniques to adapt to distribution shifts, this operation is not suitable for the spatio-temporal context as temporal normalization scales the time series of nodes and possibly disrupts the spatial relations among nodes. In order to address this problem, a Spatial Factor Learner (SFL) module is developed that enables the normalization and de-normalization process. To adapt to dynamic changes in spatial relationships among sensors, we propose a Dynamic-Static Fusion Learner (DSFL) module that effectively integrates features learned from both dynamic and static relations through an adaptive fusion ratio mechanism. Furthermore, we introduce a Stochastic Learner to capture the noisy components of spatio-temporal representations. Our approach outperforms state-of-the-art methods on weather prediction and traffic flow forecasting tasks.Experimental results show that our SFL efficiently preserves spatial relationships across various temporal normalization operations. Visualizations of the learned dynamic and static relations demonstrate that DSFL can capture both local and distant relationships between nodes.
Authors: Joery A. de Vries, Jinke He, Yaniv Oren, Matthijs T. J. Spaan
Abstract: Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practice which has motivated alternative planners like sequential Monte-Carlo (SMC). Many of these SMC methods adopt particle filters for smoothing through a reformulation of RL as a policy inference problem. Yet, persisting design choices of these particle filters often conflict with the aim of online planning in RL, which is to obtain a policy improvement at the start of planning. Drawing inspiration from MCTS, we tailor SMC planners specifically for RL by improving data generation within the planner through constrained action sampling and explicit terminal state handling, as well as improving policy and value target estimation. This leads to our Trust-Region Twisted SMC (TRT-SMC), which shows improved runtime and sample-efficiency over baseline MCTS and SMC methods in both discrete and continuous domains.
Authors: Tianwei Ni, Allen Nie, Sapana Chaudhary, Yao Liu, Huzefa Rangwala, Rasool Fakoor
Abstract: Leveraging inference-time search in large language models has proven effective in further enhancing a trained model's capability to solve complex mathematical and reasoning problems. However, this approach significantly increases computational costs and inference time, as the model must generate and evaluate multiple candidate solutions to identify a viable reasoning path. To address this, we propose an effective approach that integrates search capabilities directly into the model by fine-tuning it on unpaired successful (learning) and failed reasoning paths (forgetting) derived from diverse search methods. A key challenge we identify is that naive fine-tuning can degrade the model's search capability; we show this can be mitigated with a smaller learning rate. Extensive experiments on the challenging Game-of-24 and Countdown reasoning benchmarks show that, replacing CoT-generated data with search-generated data for offline fine-tuning improves success rates by around 23% over inference-time search baselines, while reducing inference time by 180$\times$. On top of this, our learning and forgetting objective consistently outperforms both supervised fine-tuning and preference-based methods.
Authors: Lawrence Liu, Inesh Chakrabarti, Yixiao Li, Mengdi Wang, Tuo Zhao, Lin F. Yang
Abstract: Large language models (LLMs) exhibit remarkable performance across various natural language processing tasks but suffer from immense computational and memory demands, limiting their deployment in resource-constrained environments. To address this challenge, we propose NoWag: (Normalized Weight and Activation Guided Compression), a unified framework for zero-shot shape preserving compression algorithms. We compressed Llama-2 7B/13B/70B and Llama-3 8/70BB models, using two popular forms of shape-preserving compression, vector quantization NoWag-VQ (NoWag for Vector Quantization), and unstructured/semi-structured pruning NoWag-P (NoWag for Pruning). We found that NoWag-VQ significantly outperforms state-of-the-art zero shot VQ, and that NoWag-P performs competitively against state-of-the-art methods. These results suggest commonalities between these compression paradigms that could inspire future work. Our code is available at https://github.com/LawrenceRLiu/NoWag
Authors: Ke Jiang, Wen Jiang, Xiaoyang Tan
Abstract: The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framework that concurrently considers both the potential outcomes of decision-making and their density, thus providing crucial contextual information for safe decision-making. Finally, we validate the effectiveness and feasibility of our proposed method through extensive experimental evaluations on the offline MuJoCo and AntMaze suites.
Authors: Ningyuan Yang, Jiaxuan Gao, Feng Gao, Yi Wu, Chao Yu
Abstract: Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal and limited coverage of demonstration data could lead to diffusion policies that generate sub-optimal trajectories and even catastrophic failures. While reinforcement learning (RL)-based fine-tuning has emerged as a promising solution to address these limitations, existing approaches struggle to effectively adapt Proximal Policy Optimization (PPO) to diffusion models. This challenge stems from the computational intractability of action likelihood estimation during the denoising process, which leads to complicated optimization objectives. In our experiments starting from randomly initialized policies, we find that online tuning of Diffusion Policies demonstrates much lower sample efficiency compared to directly applying PPO on MLP policies (MLP+PPO). To address these challenges, we introduce NCDPO, a novel framework that reformulates Diffusion Policy as a noise-conditioned deterministic policy. By treating each denoising step as a differentiable transformation conditioned on pre-sampled noise, NCDPO enables tractable likelihood evaluation and gradient backpropagation through all diffusion timesteps. Our experiments demonstrate that NCDPO achieves sample efficiency comparable to MLP+PPO when training from scratch, outperforming existing methods in both sample efficiency and final performance across diverse benchmarks, including continuous robot control and multi-agent game scenarios. Furthermore, our experimental results show that our method is robust to the number denoising timesteps in the Diffusion Policy.
Authors: Francisco Madaleno, Pernille Julie Viuff Sand, Francisco C. Pereira, Sergio Hernan Garrido Mejia
Abstract: We propose Bayesian Hierarchical Invariant Prediction (BHIP) reframing Invariant Causal Prediction (ICP) through the lens of Hierarchical Bayes. We leverage the hierarchical structure to explicitly test invariance of causal mechanisms under heterogeneous data, resulting in improved computational scalability for a larger number of predictors compared to ICP. Moreover, given its Bayesian nature BHIP enables the use of prior information. In this paper, we test two sparsity inducing priors: horseshoe and spike-and-slab, both of which allow us a more reliable identification of causal features. We test BHIP in synthetic and real-world data showing its potential as an alternative inference method to ICP.
Authors: Wenyi Wu, Zixuan Song, Kun Zhou, Yifei Shao, Zhiting Hu, Biwei Huang
Abstract: Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual real-world knowledge. To support such capabilities, an external memory system that can efficiently provide relevant multimodal information is essential. Existing approaches generally concatenate image and text tokens into a long sequence as memory, which, however, may drastically increase context length and even degrade performance. In contrast, we propose using continuous memory, a compact set of dense embeddings to more effectively and efficiently represent multimodal and multilingual knowledge. Our key insight is that a VLM can serve as its own continuous memory encoder. We empirically show that this design improves performance on complex multimodal reasoning tasks. Building on this, we introduce a data-efficient and parameter-efficient method to fine-tune the VLM into a memory encoder, requiring only 1.2% of the model's parameters and a small corpus of 15.6K self-synthesized samples. Our approach CoMEM utilizes VLM's original capabilities to encode arbitrary multimodal and multilingual knowledge into just 8 continuous embeddings. Since the inference-time VLM remains frozen, our memory module is plug-and-play and can be flexibly integrated as needed. Extensive experiments across eight multimodal reasoning benchmarks demonstrate the effectiveness of our approach.
Authors: Jama Hussein Mohamud, Willie Brink
Abstract: Pre-trained neural networks are commonly used and reused in the machine learning community. Alice trains a model for a particular task, and a part of her neural network is reused by Bob for a different task, often to great effect. To what can we ascribe Bob's success? This paper introduces an experimental setup through which factors contributing to Bob's empirical success could be studied in silico. As a result, we demonstrate that Bob might just be lucky: his task accuracy increases monotonically with the correlation between his task and Alice's. Even when Bob has provably uncorrelated tasks and input features from Alice's pre-trained network, he can achieve significantly better than random performance due to Alice's choice of network and optimizer. When there is little correlation between tasks, only reusing lower pre-trained layers is preferable, and we hypothesize the converse: that the optimal number of retrained layers is indicative of task and feature correlation. Finally, we show in controlled real-world scenarios that Bob can effectively reuse Alice's pre-trained network if there are semantic correlations between his and Alice's task.
Authors: Zhongying Wang, Thoai D. Ngo, Hamidreza Zoraghein, Benjamin Lucas, Morteza Karimzadeh
Abstract: The COVID-19 pandemic's severe impact highlighted the need for accurate and timely hospitalization forecasting to support effective healthcare planning. However, most forecasting models struggled, particularly during variant surges, when they were most needed. This study introduces a novel parallel-stream Long Short-Term Memory (LSTM) framework to forecast daily state-level incident hospitalizations in the United States. Our framework incorporates a spatiotemporal feature, Social Proximity to Hospitalizations (SPH), derived from Meta's Social Connectedness Index, to improve forecasts. SPH serves as a proxy for interstate population interaction, capturing transmission dynamics across space and time. Our architecture captures both short- and long-term temporal dependencies, and a multi-horizon ensembling strategy balances forecasting consistency and error. An evaluation against the COVID-19 Forecast Hub ensemble models during the Delta and Omicron surges reveals the superiority of our model. On average, our model surpasses the ensemble by 27, 42, 54, and 69 hospitalizations per state at the 7-, 14-, 21-, and 28-day horizons, respectively, during the Omicron surge. Data-ablation experiments confirm SPH's predictive power, highlighting its effectiveness in enhancing forecasting models. This research not only advances hospitalization forecasting but also underscores the significance of spatiotemporal features, such as SPH, in modeling the complex dynamics of infectious disease spread.
Authors: Ruiqi Zhang, Daman Arora, Song Mei, Andrea Zanette
Abstract: Training large language models with reinforcement learning (RL) against verifiable rewards significantly enhances their reasoning abilities, yet remains computationally expensive due to inefficient uniform prompt sampling. We introduce Selective Prompting with Efficient Estimation of Difficulty (SPEED), an adaptive online RL curriculum that selectively chooses training examples of intermediate difficulty to maximize learning efficiency. Theoretically, we establish that intermediate-difficulty prompts improve the gradient estimator's signal-to-noise ratio, accelerating convergence. Empirically, our efficient implementation leads to 2x to 6x faster training without degrading accuracy, requires no manual tuning, and integrates seamlessly into standard RL algorithms.
Authors: Wenjin Qin, Hailin Wang, Jingyao Hou, Jianjun Wang
Abstract: Currently, existing tensor recovery methods fail to recognize the impact of tensor scale variations on their structural characteristics. Furthermore, existing studies face prohibitive computational costs when dealing with large-scale high-order tensor data. To alleviate these issue, assisted by the Krylov subspace iteration, block Lanczos bidiagonalization process, and random projection strategies, this article first devises two fast and accurate randomized algorithms for low-rank tensor approximation (LRTA) problem. Theoretical bounds on the accuracy of the approximation error estimate are established. Next, we develop a novel generalized nonconvex modeling framework tailored to large-scale tensor recovery, in which a new regularization paradigm is exploited to achieve insightful prior representation for large-scale tensors. On the basis of the above, we further investigate new unified nonconvex models and efficient optimization algorithms, respectively, for several typical high-order tensor recovery tasks in unquantized and quantized situations. To render the proposed algorithms practical and efficient for large-scale tensor data, the proposed randomized LRTA schemes are integrated into their central and time-intensive computations. Finally, we conduct extensive experiments on various large-scale tensors, whose results demonstrate the practicability, effectiveness and superiority of the proposed method in comparison with some state-of-the-art approaches.
Authors: Sonia Mazelet, R\'emi Flamary, Bertrand Thirion
Abstract: Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimization problems is computationally expensive, which limits the scalability of these methods to large graphs. In this work, we present Unbalanced Learning of Optimal Transport (ULOT), a deep learning method that predicts optimal transport plans between two graphs. Our method is trained by minimizing the fused unbalanced Gromov-Wasserstein (FUGW) loss. We propose a novel neural architecture with cross-attention that is conditioned on the FUGW tradeoff hyperparameters. We evaluate ULOT on synthetic stochastic block model (SBM) graphs and on real cortical surface data obtained from fMRI. ULOT predicts transport plans with competitive loss up to two orders of magnitude faster than classical solvers. Furthermore, the predicted plan can be used as a warm start for classical solvers to accelerate their convergence. Finally, the predicted transport plan is fully differentiable with respect to the graph inputs and FUGW hyperparameters, enabling the optimization of functionals of the ULOT plan.
Authors: Jason Tandiary
Abstract: This paper studies Vickrey first-price auctions under binary feedback. Leveraging the enhanced performance of machine learning algorithms, the new algorithm uses past information to improve the regret bounds of the BROAD-OMD algorithm. Motivated by the growing relevance of first-price auctions and the predictive capabilities of machine learning models, this paper proposes a new algorithm within the BROAD-OMD framework (Hu et al., 2025) that leverages predictions of the highest competing bid. This paper's main contribution is an algorithm that achieves zero regret under accurate predictions. Additionally, a bounded regret bound of O(T^(3/4) * Vt^(1/4)) is established under certain normality conditions.
Authors: Marwan Ait Haddou, Mohamed Bennai
Abstract: Variational Quantum Algorithms (VQAs) offer potential for near-term quantum advantage but face challenges from barren plateaus, where gradients vanish, and poorly conditioned optimization landscapes. We introduce GuiderNet, a meta-learning framework that conditions Parameterized Quantum Circuits (PQCs) using data-dependent parameter shifts aimed at minimizing the log condition number of the Fubini-Study metric tensor. Implemented as a classical neural network, GuiderNet is meta-trained to guide PQC parameters into geometrically favorable regions and is embedded within hybrid quantum-classical pipelines to steer both initialization and adaptive modulation during training. Applied to the Kaggle Diabetes classification task, GuiderNet reduces cumulative training loss by over 5x, improves test accuracy from 75.3% to 98.6%, and increases the minority-class F1 score from 0.67 to 0.95. It also suppresses gradient explosion and stabilizes parameter updates, enabling smoother and more robust optimization. These results demonstrate that geometric meta-conditioning can mitigate barren plateaus and ill-conditioning, providing a scalable approach to enhance trainability and generalization in quantum machine learning.
Authors: Xiaoyang Li, Linwei Tao, Haohui Lu, Minjing Dong, Junbin Gao, Chang Xu
Abstract: Graph Neural Networks (GNNs) have demonstrated strong predictive performance on relational data; however, their confidence estimates often misalign with actual predictive correctness, posing significant limitations for deployment in safety-critical settings. While existing graph-aware calibration methods seek to mitigate this limitation, they primarily depend on coarse one-hop statistics, such as neighbor-predicted confidence, or latent node embeddings, thereby neglecting the fine-grained structural heterogeneity inherent in graph topology. In this work, we propose Wavelet-Aware Temperature Scaling (WATS), a post-hoc calibration framework that assigns node-specific temperatures based on tunable heat-kernel graph wavelet features. Specifically, WATS harnesses the scalability and topology sensitivity of graph wavelets to refine confidence estimates, all without necessitating model retraining or access to neighboring logits or predictions. Extensive evaluations across seven benchmark datasets with varying graph structures and two GNN backbones demonstrate that WATS achieves the lowest Expected Calibration Error (ECE) among all compared methods, outperforming both classical and graph-specific baselines by up to 42.3\% in ECE and reducing calibration variance by 17.24\% on average compared with graph-specific methods. Moreover, WATS remains computationally efficient, scaling well across graphs of diverse sizes and densities. Code will be released based on publication.
Authors: Hyoseo (Lauren), Yoon, Yisong Yue, Been Kim
Abstract: Independently trained vision and language models inhabit disjoint representational spaces, shaped by their respective modalities, objectives, and architectures. Yet an emerging hypothesis - the Platonic Representation Hypothesis - suggests that such models may nonetheless converge toward a shared statistical model of reality. This compatibility, if it exists, raises a fundamental question: can we move beyond post-hoc statistical detection of alignment and explicitly optimize for it between such disjoint representations? We cast this Platonic alignment problem as a multi-objective optimization task - preserve each modality's native structure while aligning for mutual coherence. We introduce the Joint Autoencoder Modulator (JAM) framework that jointly trains modality-specific autoencoders on the latent representations of pre-trained single modality models, encouraging alignment through both reconstruction and cross-modal objectives. By analogy, this framework serves as a method to escape Plato's Cave, enabling the emergence of shared structure from disjoint inputs. We evaluate this framework across three critical design axes: (i) the alignment objective - comparing contrastive loss (Con), its hard-negative variant (NegCon), and our Spread loss, (ii) the layer depth at which alignment is most effective, and (iii) the impact of foundation model scale on representational convergence. Our findings show that our lightweight Pareto-efficient framework reliably induces alignment, even across frozen, independently trained representations, offering both theoretical insight and practical pathways for transforming generalist unimodal foundations into specialist multimodal models.
Authors: Timo Thun, Andrea Merlo, Rory Conlin, Dario Panici, Daniel B\"ockenhoff
Abstract: We present a novel approach to compute three-dimensional Magnetohydrodynamic equilibria by parametrizing Fourier modes with artificial neural networks and compare it to equilibria computed by conventional solvers. The full nonlinear global force residual across the volume in real space is then minimized with first order optimizers. Already,we observe competitive computational cost to arrive at the same minimum residuals computed by existing codes. With increased computational cost,lower minima of the residual are achieved by the neural networks,establishing a new lower bound for the force residual. We use minimally complex neural networks,and we expect significant improvements for solving not only single equilibria with neural networks,but also for computing neural network models valid over continuous distributions of equilibria.
Authors: Alexander Gr\"afe, Sebastian Trimpe
Abstract: Mixed-precision training has emerged as an indispensable tool for enhancing the efficiency of neural network training in recent years. Concurrently, JAX has grown in popularity as a versatile machine learning toolbox. However, it currently lacks robust support for mixed-precision training. We propose MPX, a mixed-precision training toolbox for JAX that simplifies and accelerates the training of large-scale neural networks while preserving model accuracy. MPX seamlessly integrates with popular toolboxes such as Equinox and Flax, allowing users to convert full-precision pipelines to mixed-precision versions with minimal modifications. By casting both inputs and outputs to half precision, and introducing a dynamic loss-scaling mechanism, MPX alleviates issues like gradient underflow and overflow that commonly arise in half precision computations. Its design inherits critical features from JAX's type-promotion behavior, ensuring that operations take place in the correct precision and allowing for selective enforcement of full precision where needed (e.g., sums, means, or softmax). MPX further provides wrappers for automatic creation and management of mixed-precision gradients and optimizers, enabling straightforward integration into existing JAX training pipelines. MPX's source code, documentation, and usage examples are available at github.com/Data-Science-in-Mechanical-Engineering/mixed_precision_for_JAX .
Authors: Carlo Nicolini, Matteo Manzi, Hugo Delatte
Abstract: Portfolio optimization is a fundamental challenge in quantitative finance, requiring robust computational tools that integrate statistical rigor with practical implementation. We present skfolio, an open-source Python library for portfolio construction and risk management that seamlessly integrates with the scikit-learn ecosystem. skfolio provides a unified framework for diverse allocation strategies, from classical mean-variance optimization to modern clustering-based methods, state-of-the-art financial estimators with native interfaces, and advanced cross-validation techniques tailored for financial time series. By adhering to scikit-learn's fit-predict-transform paradigm, the library enables researchers and practitioners to leverage machine learning workflows for portfolio optimization, promoting reproducibility and transparency in quantitative finance.
Authors: Xujia Wang, Yunjia Qi, Bin Xu
Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods, such as LoRA, significantly reduce the number of trainable parameters by introducing low-rank decomposition matrices. However, existing methods perform extensive matrix multiplications in domain specialization tasks, resulting in computational inefficiency and sub-optimal fine-tuning performance. Hence, we propose LoSiA(Low-Resources Subnet Integration Adaptation), an innovative method that dynamically localizes and optimizes critical parameters during the training process. Specifically, it identifies a sub-network using gradient sparsity analysis and optimizes it as the trainable target. This design enables effective high-rank adaptation by updating only the sub-network parameters, reducing the additional matrix multiplication. We also present LoSiA-Pro, a faster implementation of LoSiA, which reduces the training latency by about $27\%$ compared to LoRA. Extensive evaluations show that our method achieves minimal performance drop compared to full fine-tuning, while requiring the least training time across domain specialization and common-sense reasoning tasks. Further analysis shows that LoSiA also reduces forgetting during continued training.
Authors: Ruihao Zhang, Mao chen, Fei Ye, Dandan Meng, Yixuan Huang, Xiao Liu
Abstract: T cell receptor (TCR) repertoires encode critical immunological signatures for autoimmune diseases, yet their clinical application remains limited by sequence sparsity and low witness rates. We developed EAMil, a multi-instance deep learning framework that leverages TCR sequencing data to diagnose systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA) with exceptional accuracy. By integrating PrimeSeq feature extraction with ESMonehot encoding and enhanced gate attention mechanisms, our model achieved state-of-the-art performance with AUCs of 98.95% for SLE and 97.76% for RA. EAMil successfully identified disease-associated genes with over 90% concordance with established differential analyses and effectively distinguished disease-specific TCR genes. The model demonstrated robustness in classifying multiple disease categories, utilizing the SLEDAI score to stratify SLE patients by disease severity as well as to diagnose the site of damage in SLE patients, and effectively controlling for confounding factors such as age and gender. This interpretable framework for immune receptor analysis provides new insights for autoimmune disease detection and classification with broad potential clinical applications across immune-mediated conditions.
Authors: Milena Gazdieva, Petr Mokrov, Litu Rout, Alexander Korotin, Andrey Kravchenko, Alexander Filippov, Evgeny Burnaev
Abstract: Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached by unpaired techniques based on Generative Adversarial Networks (GANs), which yield complex training losses with several regularization terms, e.g., content or identity losses. While GANs usually provide good practical performance, they are used heuristically, i.e., theoretical understanding of their behaviour is yet rather limited. We theoretically investigate optimization problems which arise in such models and find two surprising observations. First, the learned SR map is always an optimal transport (OT) map. Second, we theoretically prove and empirically show that the learned map is biased, i.e., it does not actually transform the distribution of low-resolution images to high-resolution ones. Inspired by these findings, we investigate recent advances in neural OT field to resolve the bias issue. We establish an intriguing connection between regularized GANs and neural OT approaches. We show that unlike the existing GAN-based alternatives, these algorithms aim to learn an unbiased OT map. We empirically demonstrate our findings via a series of synthetic and real-world unpaired SR experiments. Our source code is publicly available at https://github.com/milenagazdieva/OT-Super-Resolution.
URLs: https://github.com/milenagazdieva/OT-Super-Resolution.
Authors: Chongyu Qu, Tiezheng Zhang, Hualin Qiao, Jie Liu, Yucheng Tang, Alan Yuille, Zongwei Zhou
Abstract: Annotating medical images, particularly for organ segmentation, is laborious and time-consuming. For example, annotating an abdominal organ requires an estimated rate of 30-60 minutes per CT volume based on the expertise of an annotator and the size, visibility, and complexity of the organ. Therefore, publicly available datasets for multi-organ segmentation are often limited in data size and organ diversity. This paper proposes an active learning method to expedite the annotation process for organ segmentation and creates the largest multi-organ dataset (by far) with the spleen, liver, kidneys, stomach, gallbladder, pancreas, aorta, and IVC annotated in 8,448 CT volumes, equating to 3.2 million slices. The conventional annotation methods would take an experienced annotator up to 1,600 weeks (or roughly 30.8 years) to complete this task. In contrast, our annotation method has accomplished this task in three weeks (based on an 8-hour workday, five days a week) while maintaining a similar or even better annotation quality. This achievement is attributed to three unique properties of our method: (1) label bias reduction using multiple pre-trained segmentation models, (2) effective error detection in the model predictions, and (3) attention guidance for annotators to make corrections on the most salient errors. Furthermore, we summarize the taxonomy of common errors made by AI algorithms and annotators. This allows for continuous revision of both AI and annotations and significantly reduces the annotation costs required to create large-scale datasets for a wider variety of medical imaging tasks.
Authors: Akio Kodaira, Chenfeng Xu, Toshiki Hazama, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Zhijian Liu, Masayoshi Tomizuka, Kurt Keutzer
Abstract: We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively.
Authors: Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano H\"oher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Chinmay Prabhakar, Ezequiel de la Rosa, Bastian Wittmann, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin Menten, Ivan Ezhov, Daniel Rueckert, Iris N. Vos, Ynte M. Ruigrok, Birgitta K. Velthuis, Hugo J. Kuijf, Pengcheng Shi, Wei Liu, Ting Ma, Maximilian R. Rokuss, Yannick Kirchhoff, Fabian Isensee, Klaus Maier-Hein, Chengcheng Zhu, Huilin Zhao, Philippe Bijlenga, Julien H\"ammerli, Catherine Wurster, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Hannah-Lea Handelsmann, Andrew Makmur, James Hallinan, Amrish Soundararajan, Bene Wiestler, Jan S. Kirschke, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Kwanseok Oh, Dahye Lee, Adam Hilbert, Orhun Utku Aydin, Dimitrios Rallios, Jana Rieger, Satoru Tanioka, Alexander Koch, Dietmar Frey, Abdul Qayyum, Moona Mazher, Steven Niederer, Nico Disch, Julius Holzschuh, Dominic LaBella, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Minghui Zhang, Xin You, Hanxiao Zhang, Guang-Zhong Yang, Yun Gu, Sinyoung Ra, Jongyun Hwang, Hyunjin Park, Junqiang Chen, Marek Wodzinski, Henning M\"uller, Nesrin Mansouri, Florent Autrusseau, Cansu Yal\c{c}in, Rachika E. Hamadache, Clara Lisazo, Joaquim Salvi, Adri\`a Casamitjana, Xavier Llad\'o, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Paula Casademunt, Adrian Galdran, Matteo Delucchi, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Adnan H. Siddiqui, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze
Abstract: The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neurovascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two non-invasive angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited datasets with annotations on CoW anatomy, especially for CTA. Therefore, we organized the TopCoW challenge with the release of an annotated CoW dataset. The TopCoW dataset is the first public dataset with voxel-level annotations for 13 CoW vessel components, enabled by virtual reality technology. It is also the first large dataset using 200 pairs of MRA and CTA from the same patients. As part of the benchmark, we invited submissions worldwide and attracted over 250 registered participants from six continents. The submissions were evaluated on both internal and external test datasets of 226 scans from over five centers. The top performing teams achieved over 90% Dice scores at segmenting the CoW components, over 80% F1 scores at detecting key CoW components, and over 70% balanced accuracy at classifying CoW variants for nearly all test sets. The best algorithms also showed clinical potential in classifying fetal-type posterior cerebral artery and locating aneurysms with CoW anatomy. TopCoW demonstrated the utility and versatility of CoW segmentation algorithms for a wide range of downstream clinical applications with explainability. The annotated datasets and best performing algorithms have been released as public Zenodo records to foster further methodological development and clinical tool building.
Authors: Zhongwei Wan, Che Liu, Xin Wang, Chaofan Tao, Hui Shen, Jing Xiong, Rossella Arcucci, Huaxiu Yao, Mi Zhang
Abstract: Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians. Recent studies have concentrated on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is time-consuming and requires clinical expertise. To automate ECG report generation and ensure its versatility, we propose the Multimodal ECG Instruction Tuning (MEIT) framework, the first attempt to tackle ECG report generation with LLMs and multimodal instructions. To facilitate future research, we establish a benchmark to evaluate MEIT with various LLMs backbones across two large-scale ECG datasets. Our approach uniquely aligns the representations of the ECG signal and the report, and we conduct extensive experiments to benchmark MEIT with nine open-source LLMs using more than 800,000 ECG reports. MEIT's results underscore the superior performance of instruction-tuned LLMs, showcasing their proficiency in quality report generation, zero-shot capabilities, resilience to signal perturbation, and alignment with human expert evaluation. These findings emphasize the efficacy of MEIT and its potential for real-world clinical application.
Authors: Yun Bai, Simon Camal, Andrea Michiorri
Abstract: The relationship between electricity demand and variables such as economic activity and weather patterns is well established. However, this paper explores the connection between electricity demand and social aspects. It further embeds dynamic information about the state of society into energy demand modelling and forecasting approaches. Through the use of natural language processing on a large news corpus, we highlight this important link. This study is conducted in five regions of the UK and Ireland and considers multiple time horizons from 1 to 30 days. It also considers economic variables such as GDP, unemployment and inflation. The textual features used in this study represent central constructs from the word frequencies, topics, word embeddings extracted from the news. The findings indicate that: 1) the textual features are related to various contents, such as military conflicts, transportation, the global pandemic, regional economics, and the international energy market. They exhibit causal relationships with regional electricity demand, which are validated using Granger causality and Double Machine Learning methods. 2) Economic indicators play a more important role in the East Midlands and Northern Ireland, while social indicators are more influential in the West Midlands and the South West of England. 3) The use of these factors improves deterministic forecasting by around 6%.
Authors: Elies Gil-Fuster, Casper Gyurik, Adri\'an P\'erez-Salinas, Vedran Dunjko
Abstract: The quest for successful variational quantum machine learning (QML) relies on the design of suitable parametrized quantum circuits (PQCs), as analogues to neural networks in classical machine learning. Successful QML models must fulfill the properties of trainability and non-dequantization, among others. Recent works have highlighted an intricate interplay between trainability and dequantization of such models, which is still unresolved. In this work we contribute to this debate from the perspective of machine learning, proving a number of results identifying, among others when trainability and non-dequantization are not mutually exclusive. We begin by providing a number of new somewhat broader definitions of the relevant concepts, compared to what is found in other literature, which are operationally motivated, and consistent with prior art. With these precise definitions given and motivated, we then study the relation between trainability and dequantization of variational QML. Next, we also discuss the degrees of "variationalness" of QML models, where we distinguish between models like the hardware efficient ansatz and quantum kernel methods. Finally, we introduce recipes for building PQC-based QML models which are both trainable and nondequantizable, and corresponding to different degrees of variationalness. We do not address the practical utility for such models. Our work however does point toward a way forward for finding more general constructions, for which finding applications may become feasible.
Authors: William Kengne, Modou Wade
Abstract: The explicit regularization and optimality of deep neural networks estimators from independent data have made considerable progress recently. The study of such properties on dependent data is still a challenge. In this paper, we carry out deep learning from strongly mixing observations, and deal with the squared and a broad class of loss functions. We consider sparse-penalized regularization for deep neural network predictor. For a general framework that includes, regression estimation, classification, time series prediction,$\cdots$, oracle inequality for the expected excess risk is established and a bound on the class of H\"older smooth functions is provided. For nonparametric regression from strong mixing data and sub-exponentially error, we provide an oracle inequality for the $L_2$ error and investigate an upper bound of this error on a class of H\"older composition functions. For the specific case of nonparametric autoregression with Gaussian and Laplace errors, a lower bound of the $L_2$ error on this H\"older composition class is established. Up to logarithmic factor, this bound matches its upper bound; so, the deep neural network estimator attains the minimax optimal rate.
Authors: Cristian Trout
Abstract: Many experts believe that AI systems will sooner or later pose uninsurable risks, including existential risks. This creates an extreme judgment-proof problem: few if any parties can be held accountable ex post in the event of such a catastrophe. This paper proposes a novel solution: a government-provided, mandatory indemnification program for AI developers. The program uses risk-priced indemnity fees to induce socially optimal levels of care. Risk-estimates are determined by surveying experts, including indemnified developers. The Bayesian Truth Serum mechanism is employed to incent honest and effortful responses. Compared to alternatives, this approach arguably better leverages all private information, and provides a clearer signal to indemnified developers regarding what risks they must mitigate to lower their fees. It's recommended that collected fees be used to help fund the safety research developers need, employing a fund matching mechanism (Quadratic Financing) to induce an optimal supply of this public good. Under Quadratic Financing, safety research projects would compete for private contributions from developers, signaling how much each is to be supplemented with public funds.
Authors: Cristian Trout
Abstract: As AI systems become more autonomous and capable, experts warn of them potentially causing catastrophic losses. Drawing on the successful precedent set by the nuclear power industry, this paper argues that developers of frontier AI models should be assigned limited, strict, and exclusive third party liability for harms resulting from Critical AI Occurrences (CAIOs) - events that cause or easily could have caused catastrophic losses. Mandatory insurance for CAIO liability is recommended to overcome developers' judgment-proofness, mitigate winner's curse dynamics, and leverage insurers' quasi-regulatory abilities. Based on theoretical arguments and observations from the analogous nuclear power context, insurers are expected to engage in a mix of causal risk-modeling, monitoring, lobbying for stricter regulation, and providing loss prevention guidance in the context of insuring against heavy-tail risks from AI. While not a substitute for regulation, clear liability assignment and mandatory insurance can help efficiently allocate resources to risk-modeling and safe design, facilitating future regulatory efforts.
Authors: Jiayu Chen, Chao Yu, Guosheng Li, Wenhao Tang, Shilong Ji, Xinyi Yang, Botian Xu, Huazhong Yang, Yu Wang
Abstract: Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence. Multi-agent reinforcement learning (MARL) has demonstrated potential in modeling cooperative behaviors, but most RL-based approaches remain constrained to simplified simulations with limited dynamics or fixed scenarios. Previous attempts to deploy RL policy to real-world pursuit-evasion are largely restricted to two-dimensional scenarios, such as ground vehicles or UAVs at fixed altitudes. In this paper, we address multi-UAV pursuit-evasion by considering UAV dynamics and physical constraints. We introduce an evader prediction-enhanced network to tackle partial observability in cooperative strategy learning. Additionally, we propose an adaptive environment generator within MARL training, enabling higher exploration efficiency and better policy generalization across diverse scenarios. Simulations show our method significantly outperforms all baselines in challenging scenarios, generalizing to unseen scenarios with a 100% capture rate. Finally, we derive a feasible policy via a two-stage reward refinement and deploy the policy on real quadrotors in a zero-shot manner. To our knowledge, this is the first work to derive and deploy an RL-based policy using collective thrust and body rates control commands for multi-UAV pursuit-evasion in unknown environments. The open-source code and videos are available at https://sites.google.com/view/pursuit-evasion-rl.
Authors: Shashidhar Reddy Javaji, Zining Zhu
Abstract: Large language models (LLMs) can store a massive amount of knowledge, yet their potential to acquire new knowledge remains unknown. We propose a novel evaluation framework that evaluates this capability. This framework prompts LLMs to generate questions about a statement introducing scientific knowledge, simulating a curious person when facing the statement for the first time. We score the qualities of the generated questions, thereby evaluating the knowledge acquisition potential of the LLM. We apply controlled ablation studies to validate our scoring procedures. Additionally, we created a synthetic dataset consisting of 1101 statements in physics, chemistry, and maths with distinct levels of difficulties, 300 general knowledge statements, and 567 incorrect statements. Human evaluations were conducted to validate our model assessments, achieving an approximate weighted Cohen's kappa of 0.7 on all three metrics considered. We find that while large models like GPT-4 and Mistral 8x7b are adept at generating coherent and relevant questions, the smaller Phi-2 model is equally or more effective. This indicates that size does not solely determine a model's knowledge acquisition potential. The proposed framework quantifies a critical model capability that was commonly overlooked and opens up research opportunities for developing more knowledgeable AI systems
Authors: Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, Lei Li
Abstract: Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a significant challenge. In this paper, we propose the Deductive and InDuctive(DID) method, a novel framework that enhances LLM reasoning by dynamically integrating both deductive and inductive reasoning approaches. Drawing from cognitive science principles, DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy to precisely assess task difficulty and guide decomposition strategies. DID enables the model to progressively adapt its reasoning pathways based on problem complexity, mirroring human cognitive processes. We evaluate DID's effectiveness across multiple benchmarks, including the AIW and MR-GSM8K, as well as our custom Holiday Puzzle dataset for temporal reasoning. Our results demonstrate significant improvements in reasoning quality and solution accuracy - achieving 70.3% accuracy on AIW (compared to 62.2% for Tree of Thought) while maintaining lower computational costs. The success of DID in improving LLM performance while preserving computational efficiency suggests promising directions for developing more cognitively aligned and capable language models. Our work contributes a theoretically grounded, input-centric approach to enhancing LLM reasoning capabilities, offering an efficient alternative to traditional output-exploration methods.
Authors: Javan Tahir, Surya Ganguli, Grant M. Rotskoff
Abstract: With the emergence of large-scale pre-trained neural networks, methods to adapt such "foundation" models to data-limited downstream tasks have become a necessity. Fine-tuning, preference optimization, and transfer learning have all been successfully employed for these purposes when the target task closely resembles the source task, but a precise theoretical understanding of "task similarity" is still lacking. While conventional wisdom suggests that simple measures of similarity between source and target distributions, such as $\phi$-divergences or integral probability metrics, can directly predict the success of transfer, we prove the surprising fact that, in general, this is not the case. We adopt, instead, a feature-centric viewpoint on transfer learning and establish a number of theoretical results that demonstrate that when the target task is well represented by the feature space of the pre-trained model, transfer learning outperforms training from scratch. We study deep linear networks as a minimal model of transfer learning in which we can analytically characterize the transferability phase diagram as a function of the target dataset size and the feature space overlap. For this model, we establish rigorously that when the feature space overlap between the source and target tasks is sufficiently strong, both linear transfer and fine-tuning improve performance, especially in the low data limit. These results build on an emerging understanding of feature learning dynamics in deep linear networks, and we demonstrate numerically that the rigorous results we derive for the linear case also apply to nonlinear networks.
Authors: Lizuo Liu, Tongtong Li, Anne Gelb, Yoonsang Lee
Abstract: We propose an entropy-stable conservative flux form neural network (CFN) that integrates classical numerical conservation laws into a data-driven framework using the entropy-stable, second-order, and non-oscillatory Kurganov-Tadmor (KT) scheme. The proposed entropy-stable CFN uses slope limiting as a denoising mechanism, ensuring accurate predictions in both noisy and sparse observation environments, as well as in both smooth and discontinuous regions. Numerical experiments demonstrate that the entropy-stable CFN achieves both stability and conservation while maintaining accuracy over extended time domains. Furthermore, it successfully predicts shock propagation speeds in long-term simulations, {\it without} oracle knowledge of later-time profiles in the training data.
Authors: Resul Dagdanov, Milan Andrejevic, Dikai Liu, Chin-Teng Lin
Abstract: When interacting with each other, humans adjust their behavior based on perceived trust. To achieve similar adaptability, robots must accurately estimate human trust at sufficiently granular timescales while collaborating with humans. Beta reputation is a popular way to formalize a mathematical estimation of human trust. However, it relies on binary performance, which updates trust estimations only after each task concludes. Additionally, manually crafting a reward function is the usual method of building a performance indicator, which is labor-intensive and time-consuming. These limitations prevent efficient capture of continuous trust changes at more granular timescales throughout the collaboration task. Therefore, this paper presents a new framework for the estimation of human trust using beta reputation at fine-grained timescales. To achieve granularity in beta reputation, we utilize continuous reward values to update trust estimates at each timestep of a task. We construct a continuous reward function using maximum entropy optimization to eliminate the need for the laborious specification of a performance indicator. The proposed framework improves trust estimations by increasing accuracy, eliminating the need to manually craft a reward function, and advancing toward the development of more intelligent robots.
Authors: Hui Dai, Ryan Teehan, Mengye Ren
Abstract: Many existing evaluation benchmarks for Large Language Models (LLMs) quickly become outdated due to the emergence of new models and training data. These benchmarks also fall short in assessing how LLM performance changes over time, as they consist of a static set of questions without a temporal dimension. To address these limitations, we propose using future event prediction as a continuous evaluation method to assess LLMs' temporal generalization and forecasting abilities. Our benchmark, Daily Oracle, automatically generates question-answer (QA) pairs from daily news, challenging LLMs to predict "future" event outcomes. Our findings reveal that as pre-training data becomes outdated, LLM performance degrades over time. While Retrieval Augmented Generation (RAG) has the potential to enhance prediction accuracy, the performance degradation pattern persists, highlighting the need for continuous model updates. Code and data are available at https://agenticlearning.ai/daily-oracle.
Authors: Ehsan Kabir, Austin R. J. Downey, Jason D. Bakos, David Andrews, Miaoqing Huang
Abstract: Transformer neural networks (TNN) excel in natural language processing (NLP), machine translation, and computer vision (CV) without relying on recurrent or convolutional layers. However, they have high computational and memory demands, particularly on resource-constrained devices like FPGAs. Moreover, transformer models vary in processing time across applications, requiring custom models with specific parameters. Designing custom accelerators for each model is complex and time-intensive. Some custom accelerators exist with no runtime adaptability, and they often rely on sparse matrices to reduce latency. However, hardware designs become more challenging due to the need for application-specific sparsity patterns. This paper introduces ADAPTOR, a runtime-adaptive accelerator for dense matrix computations in transformer encoders and decoders on FPGAs. ADAPTOR enhances the utilization of processing elements and on-chip memory, enhancing parallelism and reducing latency. It incorporates efficient matrix tiling to distribute resources across FPGA platforms and is fully quantized for computational efficiency and portability. Evaluations on Xilinx Alveo U55C data center cards and embedded platforms like VC707 and ZCU102 show that our design is 1.2$\times$ and 2.87$\times$ more power efficient than the NVIDIA K80 GPU and the i7-8700K CPU respectively. Additionally, it achieves a speedup of 1.7 to 2.25$\times$ compared to some state-of-the-art FPGA-based accelerators.
Authors: Chicago Y. Park, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov
Abstract: We present a concise derivation for several influential score-based diffusion models that relies on only a few textbook results. Diffusion models have recently emerged as powerful tools for generating realistic, synthetic signals -- particularly natural images -- and often play a role in state-of-the-art algorithms for inverse problems in image processing. While these algorithms are often surprisingly simple, the theory behind them is not, and multiple complex theoretical justifications exist in the literature. Here, we provide a simple and largely self-contained theoretical justification for score-based diffusion models that is targeted towards the signal processing community. This approach leads to generic algorithmic templates for training and generating samples with diffusion models. We show that several influential diffusion models correspond to particular choices within these templates and demonstrate that alternative, more straightforward algorithmic choices can provide comparable results. This approach has the added benefit of enabling conditional sampling without any likelihood approximation.
Authors: Rongkun Xue, Jinouwen Zhang, Yazhe Niu, Dazhong Shen, Bingqi Ma, Yu Liu, Jing Yang
Abstract: Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored. Previous approaches, such as generative classifiers, have not fully leveraged the capabilities of these models for discriminative tasks due to their intricate designs. We propose Pretrained Reversible Generation (PRG), which extracts unsupervised representations by reversing the generative process of a pretrained continuous generation model. PRG effectively reuses unsupervised generative models, leveraging their high capacity to serve as robust and generalizable feature extractors for downstream tasks. This framework enables the flexible selection of feature hierarchies tailored to specific downstream tasks. Our method consistently outperforms prior approaches across multiple benchmarks, achieving state-of-the-art performance among generative model based methods, including 78% top-1 accuracy on ImageNet at a resolution of 64*64. Extensive ablation studies, including out-of-distribution evaluations, further validate the effectiveness of our approach.PRG is available at https://github.com/opendilab/PRG.
Authors: Shuo Wang, Issei Sato
Abstract: Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind acquiring such a powerful mechanism. However, the model's ability to coordinate in-context information over long contexts and global knowledge acquired during pretraining remains poorly understood. This paper investigates how a two-layer transformer thoroughly captures in-context information and balances it with pretrained bigram knowledge in next token prediction, from the viewpoint of associative memory. We theoretically analyze the representation of weight matrices in attention layers and the resulting logits when a transformer is given prompts generated by a bigram model. In the experiments, we design specific prompts to evaluate whether the outputs of the trained transformer align with the theoretical results.
Authors: Ranim Khojah, Francisco Gomes de Oliveira Neto, Mazen Mohamad, Philipp Leitner
Abstract: Large Language Models (LLMs) are increasingly used by software engineers for code generation. However, limitations of LLMs such as irrelevant or incorrect code have highlighted the need for prompt programming (or prompt engineering) where engineers apply specific prompt techniques (e.g., chain-of-thought or input-output examples) to improve the generated code. While some prompt techniques have been studied, the impact of different techniques -- and their interactions -- on code generation is still not fully understood. In this study, we introduce CodePromptEval, a dataset of 7072 prompts designed to evaluate five prompt techniques (few-shot, persona, chain-of-thought, function signature, list of packages) and their effect on the correctness, similarity, and quality of complete functions generated by three LLMs (GPT-4o, Llama3, and Mistral). Our findings show that while certain prompt techniques significantly influence the generated code, combining multiple techniques does not necessarily improve the outcome. Additionally, we observed a trade-off between correctness and quality when using prompt techniques. Our dataset and replication package enable future research on improving LLM-generated code and evaluating new prompt techniques.
Authors: Yuan Cao, Yihan He, Dennis Wu, Hong-Yu Chen, Jianqing Fan, Han Liu
Abstract: Transformers have achieved significant success in various fields, notably excelling in tasks involving sequential data like natural language processing. Despite these achievements, the theoretical understanding of transformers' capabilities remains limited. In this paper, we investigate the theoretical capabilities of transformers to autoregressively generate sequences in Bayesian networks based on in-context maximum likelihood estimation (MLE). Specifically, we consider a setting where a context is formed by a set of independent sequences generated according to a Bayesian network. We demonstrate that there exists a simple transformer model that can (i) estimate the conditional probabilities of the Bayesian network according to the context, and (ii) autoregressively generate a new sample according to the Bayesian network with estimated conditional probabilities. We further demonstrate in extensive experiments that such a transformer does not only exist in theory, but can also be effectively obtained through training. Our analysis highlights the potential of transformers to learn complex probabilistic models and contributes to a better understanding of large language models as a powerful class of sequence generators.
Authors: Aur\'elien Decelle, Alfonso de Jes\'us Navas G\'omez, Beatriz Seoane
Abstract: Maximum entropy methods, rooted in the inverse Ising/Potts problem from statistical physics, are widely used to model pairwise interactions in complex systems across disciplines such as bioinformatics and neuroscience. While successful, these approaches often fail to capture higher-order interactions that are critical for understanding collective behavior. In contrast, modern machine learning methods can model such interactions, but their interpretability often comes at a prohibitive computational cost. Restricted Boltzmann Machines (RBMs) provide a computationally efficient alternative by encoding statistical correlations through hidden units in a bipartite architecture. In this work, we introduce a method that maps RBMs onto generalized Potts models, enabling the systematic extraction of interactions up to arbitrary order. Leveraging large-$N$ approximations, made tractable by the RBM's structure, we extract effective many-body couplings with minimal computational effort. We further propose a robust framework for recovering higher-order interactions in more complex generative models, and introduce a simple gauge-fixing scheme for the effective Potts representation. Validation on synthetic data demonstrates accurate recovery of two- and three-body interactions. Applied to protein sequence data, our method reconstructs contact maps with high fidelity and outperforms state-of-the-art inverse Potts models. These results establish RBMs as a powerful and efficient tool for modeling higher-order structure in high-dimensional categorical data.
Authors: Zelai Xu, Ruize Zhang, Chao Yu, Huining Yuan, Xiangmin Yi, Shilong Ji, Chuqi Wang, Wenhao Tang, Feng Gao, Wenbo Ding, Xinlei Chen, Yu Wang
Abstract: Robot sports, characterized by well-defined objectives, explicit rules, and dynamic interactions, present ideal scenarios for demonstrating embodied intelligence. In this paper, we present VolleyBots, a novel robot sports testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics. VolleyBots integrates three features within a unified platform: competitive and cooperative gameplay, turn-based interaction structure, and agile 3D maneuvering. Competitive and cooperative gameplay challenges each drone to coordinate with its teammates while anticipating and countering opposing teams' tactics. Turn-based interaction demands precise timing, accurate state prediction, and management of long-horizon temporal dependencies. Agile 3D maneuvering requires rapid accelerations, sharp turns, and precise 3D positioning despite the quadrotor's underactuated dynamics. These intertwined features yield a complex problem combining motion control and strategic play, with no available expert demonstrations. We provide a comprehensive suite of tasks ranging from single-drone drills to multi-drone cooperative and competitive tasks, accompanied by baseline evaluations of representative multi-agent reinforcement learning (MARL) and game-theoretic algorithms. Simulation results show that on-policy reinforcement learning (RL) methods outperform off-policy methods in single-agent tasks, but both approaches struggle in complex tasks that combine motion control and strategic play. We additionally design a hierarchical policy which achieves a 69.5% percent win rate against the strongest baseline in the 3 vs 3 task, underscoring its potential as an effective solution for tackling the complex interplay between low-level control and high-level strategy. The project page is at https://sites.google.com/view/thu-volleybots.
Authors: Anji Liu, Xuejie Liu, Dayuan Zhao, Mathias Niepert, Yitao Liang, Guy Van den Broeck
Abstract: Non-autoregressive (NAR) generative models are valuable because they can handle diverse conditional generation tasks in a more principled way than their autoregressive (AR) counterparts, which are constrained by sequential dependency requirements. Recent advancements in NAR models, such as diffusion language models, have demonstrated superior performance in unconditional generation compared to AR models (e.g., GPTs) of similar sizes. However, such improvements do not always lead to improved conditional generation performance. We show that a key reason for this gap is the difficulty in generalizing to conditional probability queries (i.e., the set of unknown variables) unseen during training. As a result, strong unconditional generation performance does not guarantee high-quality conditional generation. This paper proposes Tractable Transformers (Tracformer), a Transformer-based generative model that is more robust to different conditional generation tasks. Unlike existing models that rely solely on global contextual features derived from full inputs, Tracformers incorporate a sparse Transformer encoder to capture both local and global contextual information. This information is routed through a decoder for conditional generation. Empirical results demonstrate that Tracformers achieve state-of-the-art conditional generation performance on text modeling compared to recent diffusion and AR model baselines.
Authors: Sihyun Yu, Meera Hahn, Dan Kondratyuk, Jinwoo Shin, Agrim Gupta, Jos\'e Lezama, Irfan Essa, David Ross, Jonathan Huang
Abstract: Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.
Authors: Eduardo Fernandes Montesuma, Adel El Habazi, Fred Ngole Mboula
Abstract: Detecting anomalies in datasets is a longstanding problem in machine learning. In this context, anomalies are defined as a sample that significantly deviates from the remaining data. Meanwhile, optimal transport (OT) is a field of mathematics concerned with the transportation, between two probability measures, at least effort. In classical OT, the optimal transportation strategy of a measure to itself is the identity. In this paper, we tackle anomaly detection by forcing samples to displace its mass, while keeping the least effort objective. We call this new transportation problem Mass Repulsing Optimal Transport (MROT). Naturally, samples lying in low density regions of space will be forced to displace mass very far, incurring a higher transportation cost. We use these concepts to design a new anomaly score. Through a series of experiments in existing benchmarks, and fault detection problems, we show that our algorithm improves over existing methods.
Authors: Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Vision-Language Models (VLMs) have demonstrated impressive multimodal capabilities in learning joint representations of visual and textual data, making them powerful tools for tasks such as Compositional Zero-Shot Learning (CZSL). CZSL requires models to generalize to novel combinations of visual primitives--such as attributes and objects--that were not explicitly encountered during training. Recent works in prompting for CZSL have focused on modifying inputs for the text encoder, often using static prompts that do not change across varying visual contexts. However, these approaches struggle to fully capture varying visual contexts, as they focus on text adaptation rather than leveraging visual features for compositional reasoning. To address this, we propose a Visual Adaptive Prompting System (VAPS) that leverages a learnable visual prompt repository and similarity-based retrieval mechanism within the framework of VLMs to bridge the gap between semantic and visual features. Our method introduces a dynamic visual prompt repository mechanism that selects the most relevant attribute and object prompts based on the visual features of the image. Our proposed system includes a visual prompt adapter that encourages the model to learn a more generalizable embedding space. Experiments on three CZSL benchmarks, across both closed and open-world scenarios, demonstrate state-of-the-art results.
Authors: Alexandre Marthe (ENS de Lyon, UMPA-ENSL), Samuel Bounan (UMPA-ENSL, MC2), Aur\'elien Garivier (UMPA-ENSL, MC2), Claire Vernade
Abstract: Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the most widely used and interpretable metrics such as threshold probabilities or (Conditional) Values at Risk. Indeed, previous work showed that only Entropic Risk Measures (EntRM) can be efficiently optimized through dynamic programming, leaving a hard-to-interpret parameter to choose. We show that the computation of the full set of optimal policies for EntRM across parameter values leads to tight approximations for the metrics of interest. We prove that this optimality front can be computed effectively thanks to a novel structural analysis and smoothness properties of entropic risks. Empirical results demonstrate that our approach achieves strong performance in a variety of decision-making scenarios.
Authors: Jonathan Drechsel, Anja Reusch, Steffen Herbold
Abstract: Mathematical formulas are a fundamental and widely used component in various scientific fields, serving as a universal language for expressing complex concepts and relationships. While state-of-the-art transformer models excel in processing and understanding natural language, they encounter challenges with mathematical notation, which involves a complex structure and diverse representations. This study focuses on the development of specialized training datasets to enhance the encoding of mathematical content. We introduce Math Mutator (MAMUT), a framework capable of generating equivalent and falsified versions of a given mathematical formula in LaTeX notation, effectively capturing the mathematical variety in notation of the same concept. Based on MAMUT, we have generated four large mathematical datasets containing diverse notation. Experiments show that models trained on these datasets exhibit new SoTA performance on mathematical retrieval tasks. We publish our code, generated datasets, and pretrained mathematical models: https://github.com/aieng-lab/math-mutator.
Authors: Hang Zheng, Hongshen Xu, Yuncong Liu, Lu Chen, Pascale Fung, Kai Yu
Abstract: Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation or query rejection mechanisms, they suffer from computational efficiency and sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate utilization of high-confidence outputs, whereas uncertain predictions trigger a slow refinement model for accuracy improvement. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. The framework establishes a scalable paradigm for deploying reliable LLMs in error-sensitive applications, effectively balancing accuracy and practical utility.
Authors: Aarush Sinha
Abstract: Integrating powerful but computationally expensive Pre-trained Language Models (PLMs) with Graph Neural Networks (GNNs) is a key challenge, especially on text-rich heterophilic graphs. We propose the Graph Masked Language Model (GMLM), a framework designed for the efficient and effective fusion of graph structure and text semantics. GMLM employs a two-stage process: first, a contrastive pre-training stage with a novel soft masking technique builds a robust multi-scale GNN; second, an end-to-end fine-tuning stage uses a dynamic active node selection strategy for scalability and a bi-directional cross-attention module for deep fusion. Experiments on five heterophilic benchmarks show GMLM achieves state-of-the-art results on four, significantly outperforming prior GNN and large LLM-based methods. For instance, it improves accuracy on the Texas dataset by over 8\% and on Wisconsin by nearly 5\%. Our work demonstrates that a sophisticated, deeply-integrated architecture can be more effective and efficient than larger, general-purpose models for text-rich graph representation learning.
Authors: Miao Zhang, Zhenlong Fang, Tianyi Wang, Qian Zhang, Shuai Lu, Junfeng Jiao, Tianyu Shi
Abstract: Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretability issues.These tasks are compounded when deep environment understanding, agent coordination and dynamic optimization are required. While Large Language Model (LLM) enhanced methods have shown promise in generalization and interoperability, they often neglect necessary multi-agent coordination. Therefore, we introduce the Cascading Cooperative Multi-agent (CCMA) framework, integrating RL for individual interactions, a fine-tuned LLM for regional cooperation, a reward function for global optimization, and the Retrieval-augmented Generation mechanism to dynamically optimize decision-making across complex driving scenarios. Our experiments demonstrate that the CCMA outperforms existing RL methods, demonstrating significant improvements in both micro and macro-level performance in complex driving environments.
Authors: Mikey Shechter, Yair Carmon
Abstract: We introduce Filter Like You Test (FLYT), an algorithm for curating large-scale vision-language datasets that learns the usefulness of each data point as a pretraining example. FLYT trains a scoring model that learns to weigh each example's features using gradient signals from downstream tasks training sets. Based on FLYT, we implement Mixing-FLYT (M-FLYT), which takes the per-example scores generated by different scoring methods as features, and learns to unify them into a single score. FLYT naturally produces a distribution over the training examples, which we leverage through Soft Cap Sampling (SCS), a strategy for obtaining a filtered pretraining dataset from per-example probabilities that samples examples while preventing over-representation through a repetition penalty. Using these methods, we achieve 40.1% ImageNet zero-shot accuracy on the DataComp medium scale filtering benchmark, a 2% absolute accuracy increase over all previous results and a 5.5% increase over results that - like us - use only public resources. Our approach also yields 37.7\% on the average of 38 DataComp evaluation tasks, outperforming previous public-resource approaches by 0.4\%.
Authors: Austin Shouli, Ankur Barthwal, Molly Campbell, Ajay Kumar Shrestha
Abstract: The rapid expansion of Artificial Intelligence (AI) in digital platforms used by youth has created significant challenges related to privacy, autonomy, and data protection. While AI-driven personalization offers enhanced user experiences, it often operates without clear ethical boundaries, leaving young users vulnerable to data exploitation and algorithmic biases. This paper presents a call to action for ethical AI governance, advocating for a structured framework that ensures youth-centred privacy protections, transparent data practices, and regulatory oversight. We outline key areas requiring urgent intervention, including algorithmic transparency, privacy education, parental data-sharing ethics, and accountability measures. Through this approach, we seek to empower youth with greater control over their digital identities and propose actionable strategies for policymakers, AI developers, and educators to build a fairer and more accountable AI ecosystem.
Authors: Eduardo Fernandes Montesuma
Abstract: Knowledge Distillation (KD) seeks to transfer the knowledge of a teacher, towards a student neural net. This process is often done by matching the networks' predictions (i.e., their output), but, recently several works have proposed to match the distributions of neural nets' activations (i.e., their features), a process known as \emph{distribution matching}. In this paper, we propose an unifying framework, Knowledge Distillation through Distribution Matching (KD$^{2}$M), which formalizes this strategy. Our contributions are threefold. We i) provide an overview of distribution metrics used in distribution matching, ii) benchmark on computer vision datasets, and iii) derive new theoretical results for KD.
Authors: Olivier Jeunen
Abstract: Recommender systems exemplify sequential decision-making under uncertainty, strategically deciding what content to serve to users, to optimise a range of potential objectives. To balance the explore-exploit trade-off successfully, Thompson sampling provides a natural and widespread paradigm to probabilistically select which action to take. Questions of causal and counterfactual inference, which underpin use-cases like offline evaluation, are not straightforward to answer in these contexts. Specifically, whilst most existing estimators rely on action propensities, these are not readily available under Thompson sampling procedures. We derive exact and efficiently computable expressions for action propensities under a variety of parameter and outcome distributions, enabling the use of off-policy estimators in Thompson sampling scenarios. This opens up a range of practical use-cases where counterfactual inference is crucial, including unbiased offline evaluation of recommender systems, as well as general applications of causal inference in online advertising, personalisation, and beyond.
Authors: Aakar Mathur, Ashish Gupta, Sajal K. Das
Abstract: Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and federated limitations, such as their architectures, Noisy Intermediate Scale Quantum (NISQ) devices, and privacy preservation, so on. This work explores key developments and integration strategies, along with the impact of quantum computing on FL, keeping a sharp focus on hybrid quantum-classical approaches. The paper offers an in-depth understanding of how the strengths of QC, such as gradient hiding, state entanglement, quantum key distribution, quantum security, and quantum-enhanced differential privacy, have been integrated into FL to ensure the privacy of participants in an enhanced, fast, and secure framework. Finally, this study proposes potential future directions to address the identified research gaps and challenges, aiming to inspire faster and more secure QFL models for practical use.
Authors: Mahir Gulzar, Yar Muhammad, Naveed Muhammad
Abstract: Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic participants). This paper presents a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements. We follow the famous encoder-interactor-decoder architecture where the encoder encodes scene context using lightweight Gated Recurrent Units, the interactor applies cross-context attention over encoded scene features and graph goal proposals, and the decoder regresses multimodal trajectories via Laplacian Mixture Density Network from the aggregated encodings. Using cross-attention over graph-based goal proposals gives robust trajectory estimates since the model learns to attend to future goal-relevant scene elements for the intended agent. We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
Authors: Alejandro Giraldo, Daniel Ruiz, Mariano Caruso, Guido Bellomo
Abstract: Quantitative Structure-Activity Relationship (QSAR) modeling is key in drug discovery, but classical methods face limitations when handling high-dimensional data and capturing complex molecular interactions. This research proposes enhancing QSAR techniques through Quantum Support Vector Machines (QSVMs), which leverage quantum computing principles to process information Hilbert spaces. By using quantum data encoding and quantum kernel functions, we aim to develop more accurate and efficient predictive models.
Authors: Donghao Ren, Fred Hohman, Halden Lin, Dominik Moritz
Abstract: Embedding projections are popular for visualizing large datasets and models. However, people often encounter "friction" when using embedding visualization tools: (1) barriers to adoption, e.g., tedious data wrangling and loading, scalability limits, no integration of results into existing workflows, and (2) limitations in possible analyses, without integration with external tools to additionally show coordinated views of metadata. In this paper, we present Embedding Atlas, a scalable, interactive visualization tool designed to make interacting with large embeddings as easy as possible. Embedding Atlas uses modern web technologies and advanced algorithms -- including density-based clustering, and automated labeling -- to provide a fast and rich data analysis experience at scale. We evaluate Embedding Atlas with a competitive analysis against other popular embedding tools, showing that Embedding Atlas's feature set specifically helps reduce friction, and report a benchmark on its real-time rendering performance with millions of points. Embedding Atlas is available as open source to support future work in embedding-based analysis.
Authors: Rohit Goswami (Science Institute and Faculty of Physical Sciences, University of Iceland, Reykjav\'ik, Iceland), Maxim Masterov (SURF, Amsterdam, The Netherlands), Satish Kamath (SURF, Amsterdam, The Netherlands), Alejandro Pe\~na-Torres (Science Institute and Faculty of Physical Sciences, University of Iceland, Reykjav\'ik, Iceland), Hannes J\'onsson (Science Institute and Faculty of Physical Sciences, University of Iceland, Reykjav\'ik, Iceland)
Abstract: The task of locating first order saddle points on high-dimensional surfaces describing the variation of energy as a function of atomic coordinates is an essential step for identifying the mechanism and estimating the rate of thermally activated events within the harmonic approximation of transition state theory. When combined directly with electronic structure calculations, the number of energy and atomic force evaluations needed for convergence is a primary issue. Here, we describe an efficient implementation of Gaussian process regression (GPR) acceleration of the minimum mode following method where a dimer is used to estimate the lowest eigenmode of the Hessian. A surrogate energy surface is constructed and updated after each electronic structure calculation. The method is applied to a test set of 500 molecular reactions previously generated by Hermez and coworkers [J. Chem. Theory Comput. 18, 6974 (2022)]. An order of magnitude reduction in the number of electronic structure calculations needed to reach the saddle point configurations is obtained by using the GPR compared to the dimer method. Despite the wide range in stiffness of the molecular degrees of freedom, the calculations are carried out using Cartesian coordinates and are found to require similar number of electronic structure calculations as an elaborate internal coordinate method implemented in the Sella software package. The present implementation of the GPR surrogate model in C++ is efficient enough for the wall time of the saddle point searches to be reduced in 3 out of 4 cases even though the calculations are carried out at a low Hartree-Fock level.
Authors: Paulo C. Marques F
Abstract: We consider a method for conformalizing a stacked ensemble of predictive models, showing that the potentially simple form of the meta-learner at the top of the stack enables a procedure with manageable computational cost that achieves approximate marginal validity without requiring the use of a separate calibration sample. Empirical results indicate that the method compares favorably to a standard inductive alternative.
Authors: Zihao Li, Xu Wang, Yuzhe Yang, Ziyu Yao, Haoyi Xiong, Mengnan Du
Abstract: Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning for complex problems, but requires costly and high-quality long CoT data and fine-tuning. This work, inspired by the deep thinking paradigm of DeepSeek-R1, utilizes a steering technique to enhance the reasoning ability of an LLM without external datasets. Our method first employs Sparse Autoencoders (SAEs) to extract interpretable features from vanilla CoT. These features are then used to steer the LLM's internal states during generation. Recognizing that many LLMs do not have corresponding pre-trained SAEs, we further introduce a novel SAE-free steering algorithm, which directly computes steering directions from the residual activations of an LLM, obviating the need for an explicit SAE. Experimental results demonstrate that both our SAE-based and subsequent SAE-free steering algorithms significantly enhance the reasoning capabilities of LLMs.
Authors: Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang
Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model -- often trained with subsets of the target model's training data -- to achieve high attack success rates through transferability. However, in realistic scenarios where training data is inaccessible and excessive queries can raise alarms, crafting adversarial examples becomes more challenging. In this paper, we present UnivIntruder, a novel attack framework that relies solely on a single, publicly available CLIP model and publicly available datasets. By using textual concepts, UnivIntruder generates universal, transferable, and targeted adversarial perturbations that mislead DNNs into misclassifying inputs into adversary-specified classes defined by textual concepts. Our extensive experiments show that our approach achieves an Attack Success Rate (ASR) of up to 85% on ImageNet and over 99% on CIFAR-10, significantly outperforming existing transfer-based methods. Additionally, we reveal real-world vulnerabilities, showing that even without querying target models, UnivIntruder compromises image search engines like Google and Baidu with ASR rates up to 84%, and vision language models like GPT-4 and Claude-3.5 with ASR rates up to 80%. These findings underscore the practicality of our attack in scenarios where traditional avenues are blocked, highlighting the need to reevaluate security paradigms in AI applications.
Authors: Kai Fukami, Ryo Araki
Abstract: We perform an information-theoretic mode decomposition for separated aerodynamic flows. The current data-driven approach based on a neural network referred to as deep sigmoidal flow enables the extraction of an informative component from a given flow field snapshot with respect to a target variable at a future time stamp, thereby capturing the causality as a time-varying modal structure. We consider four examples of separated flows around a wing, namely, 1. laminar periodic wake at post-stall angles of attack, strong gust-wing interactions of 2. numerical and 3. experimental measurements, and 4. a turbulent wake in a spanwise-periodic domain. The present approach reveals informative vortical structures associated with a time-varying lift response. For the periodic shedding cases, the informative structures vary in time corresponding to the fluctuation level from their mean values. With the examples of gust-wing interactions, how the effect of gust on a wing emerges in the lift response over time is identified in an interpretable manner. Furthermore, for the case of turbulent wake, the present model highlights structures near the wing and vortex cores as informative components based solely on the information metric without any prior knowledge of aerodynamics and length scales. This study provides causality-based insights into a range of unsteady aerodynamic problems.
Authors: Juho Kim
Abstract: The independent chip model (ICM) forms a cornerstone of all modern poker tournament strategy. However, despite its prominence, the ICM's performance in the real world has not been sufficiently scrutinized, especially at a large scale. In this paper, we introduce our new dataset of poker tournaments, consisting of results of over ten thousand events. Then, using this dataset, we perform two experiments as part of a large-scale empirical validation of the ICM. First, we verify that the ICM performs more accurately than a baseline we propose. Second, we obtain empirical evidence of the ICM underestimating the performances of players with larger stacks while overestimating those who are short-stacked. Our contributions may be useful to future researchers developing new algorithms for estimating a player's value in poker tournaments.
Authors: Jacky Tai-Yu Lu, Jung Chiang, Chi-Sheng Chen, Anna Nai-Yun Tung, Hsiang Wei Hu, Yuan Chiao Cheng
Abstract: We propose EEG2TEXT-CN, which, to the best of our knowledge, represents one of the earliest open-vocabulary EEG-to-text generation frameworks tailored for Chinese. Built on a biologically grounded EEG encoder (NICE-EEG) and a compact pretrained language model (MiniLM), our architecture aligns multichannel brain signals with natural language representations via masked pretraining and contrastive learning. Using a subset of the ChineseEEG dataset, where each sentence contains approximately ten Chinese characters aligned with 128-channel EEG recorded at 256 Hz, we segment EEG into per-character embeddings and predict full sentences in a zero-shot setting. The decoder is trained with teacher forcing and padding masks to accommodate variable-length sequences. Evaluation on over 1,500 training-validation sentences and 300 held-out test samples shows promising lexical alignment, with a best BLEU-1 score of 6.38\%. While syntactic fluency remains a challenge, our findings demonstrate the feasibility of non-phonetic, cross-modal language decoding from EEG. This work opens a new direction in multilingual brain-to-text research and lays the foundation for future cognitive-language interfaces in Chinese.
Authors: Micha{\l} P. Karpowicz
Abstract: We prove that perfect hallucination control in large language models is mathematically impossible. No LLM inference mechanism can simultaneously achieve truthful response generation, semantic information conservation, relevant knowledge revelation, and knowledge-constrained optimality. This impossibility is fundamental, arising from the mathematical structure of information aggregation itself rather than engineering limitations. The proof spans three mathematical frameworks: auction theory, proper scoring theory for probabilistic predictions, and log-sum-exp analysis for transformer architectures. In each setting, we demonstrate that information aggregation creates unavoidable violations of conservation principles. The Jensen gap in transformer probability aggregation provides a direct measure of this impossibility. These results reframe hallucination from an engineering bug to an inevitable mathematical feature of distributed intelligence. There are fundamental trade-offs between truthfulness, knowledge utilization, and response completeness, providing principled foundations for managing rather than eliminating hallucination. This work reveals deep connections between neural network inference, philosophy of knowledge and reasoning, and classical results in game theory and information theory, opening new research directions for developing beneficial AI systems within mathematical constraints.
Authors: Vitoria Guardieiro, Adam Stein, Avishree Khare, Eric Wong
Abstract: Controlling the generation of large language models (LLMs) remains a central challenge to ensure their safe and reliable deployment. While prompt engineering and finetuning are common approaches, recent work has explored latent steering, a lightweight technique that alters LLM internal activations to guide generation. However, subsequent studies revealed latent steering's effectiveness to be limited, often underperforming simple instruction prompting. To address this limitation, we first establish a benchmark across diverse behaviors for standardized evaluation of steering techniques. Building on insights from this benchmark, we introduce Instruction Attention Boosting (InstABoost), a latent steering method that boosts the strength of instruction prompting by altering the model's attention during generation. InstABoost combines the strengths of existing approaches and is theoretically supported by prior work that suggests that in-context rule following in transformer-based models can be controlled by manipulating attention on instructions. Empirically, InstABoost demonstrates superior control success compared to both traditional prompting and latent steering.
Authors: Eman Alqudah, Ashfaq Khokhar
Abstract: Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph Convolutional Network (GCN) integrated with a Deep Q-Network (DQN) reinforcement learning framework for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach dynamically learns link priorities based on real-time traffic demand, network topology, remaining transmission opportunities, and interference patterns. The GCN captures spatial dependencies, while the DQN enables adaptive scheduling decisions through reward-guided exploration. Simulation results show that our GCN-DQN model achieves mean SINR improvements of 179.6\%, 197.4\%, and 175.2\% over LDP across three network configurations. Additionally, the GCN-DQN model demonstrates mean SINR improvements of 31.5\%, 53.0\%, and 84.7\% over our previous CNN-based approach across the same configurations. These results underscore the effectiveness of our GCN-DQN model in addressing complex URLLC requirements with minimal overhead and superior network performance.
Authors: Almog Hilel, Idan Shenfeld, Jacob Andreas, Leshem Choshen
Abstract: We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to provide prompts and upvote / downvote feedback on LM outputs. To implement the attack, the attacker prompts the LM to stochastically output either a "poisoned" or benign response, then upvotes the poisoned response or downvotes the benign one. When feedback signals are used in a subsequent preference tuning behavior, LMs exhibit increased probability of producing poisoned responses even in contexts without malicious prompts. We show that this attack can be used to (1) insert factual knowledge the model did not previously possess, (2) modify code generation patterns in ways that introduce exploitable security flaws, and (3) inject fake financial news. Our finding both identifies a new qualitative feature of language model preference tuning (showing that it even highly restricted forms of preference data can be used to exert fine-grained control over behavior), and a new attack mechanism for LMs trained with user feedback (extending work on pretraining-time data poisoning and deployment-time prompt injection).
Authors: Rongxin Ouyang, Chang Chu, Zhikuang Xin, Xiangyao Ma
Abstract: Language barriers in scientific documents hinder the diffusion and development of science and technologies. However, prior efforts in translating such documents largely overlooked the information in layouts. To bridge the gap, we introduce PDFMathTranslate, the world's first open-source software for translating scientific documents while preserving layouts. Leveraging the most recent advances in large language models and precise layout detection, we contribute to the community with key improvements in precision, flexibility, and efficiency. The work has been open-sourced at https://github.com/byaidu/pdfmathtranslate with more than 222k downloads.
Authors: Amirabbas Hojjati, Lu Li, Ibrahim Hameed, Anis Yazidi, Pedro G. Lind, Rabindra Khadka
Abstract: EEG signals capture brain activity with high temporal and low spatial resolution, supporting applications such as neurological diagnosis, cognitive monitoring, and brain-computer interfaces. However, effective analysis is hindered by limited labeled data, high dimensionality, and the absence of scalable models that fully capture spatiotemporal dependencies. Existing self-supervised learning (SSL) methods often focus on either spatial or temporal features, leading to suboptimal representations. To this end, we propose EEG-VJEPA, a novel adaptation of the Video Joint Embedding Predictive Architecture (V-JEPA) for EEG classification. By treating EEG as video-like sequences, EEG-VJEPA learns semantically meaningful spatiotemporal representations using joint embeddings and adaptive masking. To our knowledge, this is the first work that exploits V-JEPA for EEG classification and explores the visual concepts learned by the model. Evaluations on the publicly available Temple University Hospital (TUH) Abnormal EEG dataset show that EEG-VJEPA outperforms existing state-of-the-art models in classification accuracy. Beyond classification accuracy, EEG-VJEPA captures physiologically relevant spatial and temporal signal patterns, offering interpretable embeddings that may support human-AI collaboration in diagnostic workflows. These findings position EEG-VJEPA as a promising framework for scalable, trustworthy EEG analysis in real-world clinical settings.
Authors: Akio Kodaira, Tingbo Hou, Ji Hou, Masayoshi Tomizuka, Yue Zhao
Abstract: Recently, great progress has been achieved in text-to-video (T2V) generation by scaling transformer-based diffusion models to billions of parameters, which can generate high-quality videos. However, existing models typically produce only short clips offline, restricting their use cases in interactive and real-time applications. This paper addresses these challenges by proposing StreamDiT, a streaming video generation model. StreamDiT training is based on flow matching by adding a moving buffer. We design mixed training with different partitioning schemes of buffered frames to boost both content consistency and visual quality. StreamDiT modeling is based on adaLN DiT with varying time embedding and window attention. To practice the proposed method, we train a StreamDiT model with 4B parameters. In addition, we propose a multistep distillation method tailored for StreamDiT. Sampling distillation is performed in each segment of a chosen partitioning scheme. After distillation, the total number of function evaluations (NFEs) is reduced to the number of chunks in a buffer. Finally, our distilled model reaches real-time performance at 16 FPS on one GPU, which can generate video streams at 512p resolution. We evaluate our method through both quantitative metrics and human evaluation. Our model enables real-time applications, e.g. streaming generation, interactive generation, and video-to-video. We provide video results and more examples in our project website: https://cumulo-autumn.github.io/StreamDiT/
Authors: Henri A\"idasso, Francis Bordeleau, Ali Tizghadam
Abstract: One of the main challenges developers face in the use of continuous integration (CI) and deployment pipelines is the occurrence of intermittent job failures, which result from unexpected non-deterministic issues (e.g., flaky tests or infrastructure problems) rather than regular code-related errors such as bugs. Prior studies developed machine learning (ML) models trained on large datasets of job logs to classify job failures as either intermittent or regular. As an alternative to costly manual labeling of large datasets, the state-of-the-art (SOTA) approach leveraged a heuristic based on non-deterministic job reruns. However, this method mislabels intermittent job failures as regular in contexts where rerunning suspicious job failures is not an explicit policy, and therefore limits the SOTA's performance in practice. In fact, our manual analysis of 2,125 job failures from 5 industrial and 1 open-source projects reveals that, on average, 32% of intermittent job failures are mislabeled as regular. To address these limitations, this paper introduces a novel approach to intermittent job failure detection using few-shot learning (FSL). Specifically, we fine-tune a small language model using a few number of manually labeled log examples to generate rich embeddings, which are then used to train an ML classifier. Our FSL-based approach achieves 70-88% F1-score with only 12 shots in all projects, outperforming the SOTA, which proved ineffective (34-52% F1-score) in 4 projects. Overall, this study underlines the importance of data quality over quantity and provides a more efficient and practical framework for the detection of intermittent job failures in organizations.
Authors: Nik Vaessen, Roeland Ordelman, David A. van Leeuwen
Abstract: This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise and speaker overlap affect SSL convergence and downstream fine-tuning performance. Secondly, we explore effectively pre-processing strategies to convert the noisy broadcast dataset into a qualitative dataset for pre-training, by using Whisper and WhisperX. Thirdly, we compare mono-lingual and multi-lingual pre-training with equivalent amounts of data, and show that mono-lingual pre-training is more robust to out-of-domain data. Lastly, we achieve a state-of-the-art LARGE wav2vec 2.0 model for the Dutch language, by a continuation of pre-training a wav2vec 2.0 XLS-R model checkpoint with our 55k hour archival dataset.
Authors: Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
Abstract: Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to wasted context, increased latency, and higher energy consumption. We observe that verbose, English-heavy CoTs and concise, math-centric CoTs occupy distinct regions in the model's residual-stream activation space. By extracting and injecting a "steering vector" to transition between these modes, we can reliably shift generation toward more concise reasoning, effectively compressing CoTs without retraining. We formalize this approach as Activation-Steered Compression (ASC), an inference-time technique that shortens reasoning traces by directly modifying hidden representations. In addition, we provide a theoretical analysis of the impact of ASC on the output distribution, derived from a closed-form KL-divergence-bounded constraint to regulate steering strength. Using only 100 paired verbose and concise examples, ASC achieves up to 67.43% reduction in CoT length on MATH500 and GSM8K datasets, while maintaining accuracy across 7B, 8B, and 32B parameter models. As a training-free method, ASC introduces negligible runtime overhead and, on MATH500, delivers an average 2.73x speedup in end-to-end reasoning wall-clock time on an 8B model. This makes ASC a practical and efficient tool for streamlining the deployment of reasoning-capable LLMs in latency- or cost-sensitive settings. The code is available at: https://github.com/ArminAzizi98/ASC
Authors: Berkay Gunes, Sven Buder, Tobias Buck
Abstract: We present COMPASS, a novel simulation-based inference framework that combines score-based diffusion models with transformer architectures to jointly perform parameter estimation and Bayesian model comparison across competing Galactic Chemical Evolution (GCE) models. COMPASS handles high-dimensional, incomplete, and variable-size stellar abundance datasets. Applied to high-precision elemental abundance measurements, COMPASS evaluates 40 combinations of nucleosynthetic yield tables. The model strongly favours Asymptotic Giant Branch yields from NuGrid and core-collapse SN yields used in the IllustrisTNG simulation, achieving near-unity cumulative posterior probability. Using the preferred model, we infer a steep high-mass IMF slope and an elevated Supernova Ia normalization, consistent with prior solar neighbourhood studies but now derived from fully amortized Bayesian inference. Our results demonstrate that modern SBI methods can robustly constrain uncertain physics in astrophysical simulators and enable principled model selection when analysing complex, simulation-based data.