Authors: Tabia Tanzin Prama, Jannatul Ferdaws Amrin, Md. Mushfique Anwar, Iqbal H. Sarker
Abstract: The rise of social media has significantly increased the prevalence of cyberbullying (CB), posing serious risks to both mental and physical well-being. Effective detection systems are essential for mitigating its impact. While several machine learning (ML) models have been developed, few incorporate victims' psychological, demographic, and behavioral factors alongside bullying comments to assess severity. In this study, we propose an AI model intregrating user-specific attributes, including psychological factors (self-esteem, anxiety, depression), online behavior (internet usage, disciplinary history), and demographic attributes (race, gender, ethnicity), along with social media comments. Additionally, we introduce a re-labeling technique that categorizes social media comments into three severity levels: Not Bullying, Mild Bullying, and Severe Bullying, considering user-specific factors.Our LSTM model is trained using 146 features, incorporating emotional, topical, and word2vec representations of social media comments as well as user-level attributes and it outperforms existing baseline models, achieving the highest accuracy of 98\% and an F1-score of 0.97. To identify key factors influencing the severity of cyberbullying, we employ explainable AI techniques (SHAP and LIME) to interpret the model's decision-making process. Our findings reveal that, beyond hate comments, victims belonging to specific racial and gender groups are more frequently targeted and exhibit higher incidences of depression, disciplinary issues, and low self-esteem. Additionally, individuals with a prior history of bullying are at a greater risk of becoming victims of cyberbullying.
Authors: Mooho Song, Jay-Yoon Lee
Abstract: Examining logical inconsistencies among multiple statements (such as collections of sentences or question-answer pairs) is a crucial challenge in machine learning, particularly for ensuring the safety and reliability of models. Traditional methods that rely on pairwise comparisons often fail to capture inconsistencies that only emerge when more than two statements are evaluated collectively. To address this gap, we introduce the task of set-consistency verification, an extension of natural language inference (NLI) that assesses the logical coherence of entire sets rather than isolated pairs. Building on this task, we present the Set-Consistency Energy Network (SC-Energy), a novel model that employs a contrastive loss framework to learn the compatibility among a collection of statements. Our approach not only efficiently verifies inconsistencies and pinpoints the specific statements responsible for logical contradictions, but also significantly outperforms existing methods including prompting-based LLM models. Furthermore, we release two new datasets: Set-LConVQA and Set-SNLI for set-consistency verification task.
Authors: Xu Lingrui, Liu Mandi, Zhang Lei
Abstract: The core challenge in basketball tactic modeling lies in efficiently extracting complex spatial-temporal dependencies from historical data and accurately predicting various in-game events. Existing state-of-the-art (SOTA) models, primarily based on graph neural networks (GNNs), encounter difficulties in capturing long-term, long-distance, and fine-grained interactions among heterogeneous player nodes, as well as in recognizing interaction patterns. Additionally, they exhibit limited generalization to untrained downstream tasks and zero-shot scenarios. In this work, we propose a Spatial-Temporal Propagation Symmetry-Aware Graph Transformer for fine-grained game modeling. This architecture explicitly captures delay effects in the spatial space to enhance player node representations across discrete-time slices, employing symmetry-invariant priors to guide the attention mechanism. We also introduce an efficient contrastive learning strategy to train a Mixture of Tactics Experts module, facilitating differentiated modeling of offensive tactics. By integrating dense training with sparse inference, we achieve a 2.4x improvement in model efficiency. Moreover, the incorporation of Lightweight Graph Grounding for Large Language Models enables robust performance in open-ended downstream tasks and zero-shot scenarios, including novel teams or players. The proposed model, TacticExpert, delineates a vertically integrated large model framework for basketball, unifying pretraining across multiple datasets and downstream prediction tasks. Fine-grained modeling modules significantly enhance spatial-temporal representations, and visualization analyzes confirm the strong interpretability of the model.
Authors: Elie Azeraf, Audrey Wagner, Emilie Bialic, Samia Mellah, Ludovic Lelandais
Abstract: Air pollution remains one of the most pressing environmental challenges of the modern era, significantly impacting human health, ecosystems, and climate. While traditional air quality monitoring systems provide critical data, their high costs and limited spatial coverage hinder effective real-time pollutant identification. Recent advancements in micro-sensor technology have improved data collection but still lack efficient methods for source identification. This paper explores the innovative application of machine learning (ML) models to classify pollutants in real-time using only data from optical micro-sensors. We propose a novel classification framework capable of distinguishing between four pollutant scenarios: Background Pollution, Ash, Sand, and Candle. Three Machine Learning (ML) approaches - XGBoost, Long Short-Term Memory networks, and Hidden Markov Chains - are evaluated for their effectiveness in sequence modeling and pollutant identification. Our results demonstrate the potential of leveraging micro-sensors and ML techniques to enhance air quality monitoring, offering actionable insights for urban planning and environmental protection.
Authors: Chenpeng Wu, Qiqi Gu, Heng Shi, Jianguo Yao, Haibing Guan
Abstract: The escalating size of Mixture-of-Experts (MoE) based Large Language Models (LLMs) presents significant computational and memory challenges, necessitating innovative solutions to enhance efficiency without compromising model accuracy. Structured sparsity emerges as a compelling strategy to address these challenges by leveraging the emerging sparse computing hardware. Prior works mainly focus on the sparsity in model parameters, neglecting the inherent sparse patterns in activations. This oversight can lead to additional computational costs associated with activations, potentially resulting in suboptimal performance. This paper presents Samoyeds, an innovative acceleration system for MoE LLMs utilizing Sparse Tensor Cores (SpTCs). Samoyeds is the first to apply sparsity simultaneously to both activations and model parameters. It introduces a bespoke sparse data format tailored for MoE computation and develops a specialized sparse-sparse matrix multiplication kernel. Furthermore, Samoyeds incorporates systematic optimizations specifically designed for the execution of dual-side structured sparse MoE LLMs on SpTCs, further enhancing system performance. Evaluations show that Samoyeds outperforms SOTA works by up to 1.99$\times$ at the kernel level and 1.58$\times$ at the model level. Moreover, it enhances memory efficiency, increasing maximum supported batch sizes by 4.41$\times$ on average. Additionally, Samoyeds surpasses existing SOTA structured sparse solutions in both model accuracy and hardware portability.
Authors: Fengchun Liu, Linghan Cai, Zhikang Wang, Zhiyuan Fan, Jin-gang Yu, Hao Chen, Yongbing Zhang
Abstract: Histo-genomic multimodal survival prediction has garnered growing attention for its remarkable model performance and potential contributions to precision medicine. However, a significant challenge in clinical practice arises when only unimodal data is available, limiting the usability of these advanced multimodal methods. To address this issue, this study proposes a prototype-guided cross-modal knowledge enhancement (ProSurv) framework, which eliminates the dependency on paired data and enables robust learning and adaptive survival prediction. Specifically, we first introduce an intra-modal updating mechanism to construct modality-specific prototype banks that encapsulate the statistics of the whole training set and preserve the modality-specific risk-relevant features/prototypes across intervals. Subsequently, the proposed cross-modal translation module utilizes the learned prototypes to enhance knowledge representation for multimodal inputs and generate features for missing modalities, ensuring robust and adaptive survival prediction across diverse scenarios. Extensive experiments on four public datasets demonstrate the superiority of ProSurv over state-of-the-art methods using either unimodal or multimodal input, and the ablation study underscores its feasibility for broad applicability. Overall, this study addresses a critical practical challenge in computational pathology, offering substantial significance and potential impact in the field.
Authors: Emily C. Ehrhardt, Hanno Gottschalk, Tobias J. Riedlinger
Abstract: NeuralODE is one example for generative machine learning based on the push forward of a simple source measure with a bijective mapping, which in the case of NeuralODE is given by the flow of a ordinary differential equation. Using Liouville's formula, the log-density of the push forward measure is easy to compute and thus NeuralODE can be trained based on the maximum Likelihood method such that the Kulback-Leibler divergence between the push forward through the flow map and the target measure generating the data becomes small. In this work, we give a detailed account on the consistency of Maximum Likelihood based empirical risk minimization for a generic class of target measures. In contrast to prior work, we do not only consider the statistical learning theory, but also give a detailed numerical analysis of the NeuralODE algorithm based on the 2nd order Runge-Kutta (RK) time integration. Using the universal approximation theory for deep ReQU networks, the stability and convergence rated for the RK scheme as well as metric entropy and concentration inequalities, we are able to prove that NeuralODE is a probably approximately correct (PAC) learning algorithm.
Authors: Chunsheng Zuo, Yu Zhao, Juntao Ye
Abstract: Photoplethysmography (PPG) sensors have been widely used in consumer wearable devices to monitor heart rates (HR) and heart rate variability (HRV). Despite the prevalence, PPG signals can be contaminated by motion artifacts induced from daily activities. Existing approaches mainly use the amplitude information to perform PPG peak detection. However, these approaches cannot accurately identify peaks, since motion artifacts may bring random and significant amplitude variations. To improve the performance of PPG peak detection, the time information can be used. Specifically, heart rates exhibit temporal consistency that consecutive heartbeat intervals in a normal person can have limited variations. To leverage the temporal consistency, we propose the Temporal Attentive U-Net, i.e., TAU, to accurately detect peaks from PPG signals. In TAU, we design a time module that encodes temporal consistency in temporal embeddings. We integrate the amplitude information with temporal embeddings using the attention mechanism to estimate peak labels. Our experimental results show that TAU outperforms eleven baselines on heart rate estimation by more than 22.4%. Our TAU model achieves the best performance across various Signal-to-Noise Ratio (SNR) levels. Moreover, we achieve Pearson correlation coefficients higher than 0.9 (p < 0.01) on estimating HRV features from low-noise-level PPG signals.
Authors: Omar Costilla-Reyes, Morgan Talbot
Abstract: Body Dysmorphic Disorder (BDD) is a highly prevalent and frequently underdiagnosed condition characterized by persistent, intrusive preoccupations with perceived defects in physical appearance. In this extended analysis, we employ multiple machine learning approaches to predict treatment outcomes -- specifically treatment response and remission -- with an emphasis on interpretability to ensure clinical relevance and utility. Across the various models investigated, treatment credibility emerged as the most potent predictor, surpassing traditional markers such as baseline symptom severity or comorbid conditions. Notably, while simpler models (e.g., logistic regression and support vector machines) achieved competitive predictive performance, decision tree analyses provided unique insights by revealing clinically interpretable threshold values in credibility scores. These thresholds can serve as practical guideposts for clinicians when tailoring interventions or allocating treatment resources. We further contextualize our findings within the broader literature on BDD, addressing technology-based therapeutics, digital interventions, and the psychosocial determinants of treatment engagement. An extensive array of references situates our results within current research on BDD prevalence, suicidality risks, and digital innovation. Our work underscores the potential of integrating rigorous statistical methodologies with transparent machine learning models. By systematically identifying modifiable predictors -- such as treatment credibility -- we propose a pathway toward more targeted, personalized, and ultimately efficacious interventions for individuals with BDD.
Authors: Yudong Liu, Jingwei Sun, Yueqian Lin, Jingyang Zhang, Ming Yin, Qinsi Wang, Jianyi Zhang, Hai Li, Yiran Chen
Abstract: Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video scenarios. Existing approaches predominantly focus on either vision token pruning, which may overlook spatio-temporal dependencies, or keyframe selection, which identifies informative frames but discards others, thus disrupting contextual continuity. In this work, we propose KVTP (Keyframe-oriented Vision Token Pruning), a novel framework that overcomes the drawbacks of token pruning and keyframe selection. By adaptively assigning pruning rates based on frame relevance to the query, KVTP effectively retains essential contextual information while significantly reducing redundant computation. To thoroughly evaluate the long-form video understanding capacities of VLMs, we curated and reorganized subsets from VideoMME, EgoSchema, and NextQA into a unified benchmark named SparseKV-QA that highlights real-world scenarios with sparse but crucial events. Our experiments with VLMs of various scales show that KVTP can reduce token usage by 80% without compromising spatiotemporal and contextual consistency, significantly cutting computation while maintaining the performance. These results demonstrate our approach's effectiveness in efficient long-video processing, facilitating more scalable VLM deployment.
Authors: Yufei Xia, Wenrui Yu, Qiongxiu Li
Abstract: Byzantine attacks present a critical challenge to Federated Learning (FL), where malicious participants can disrupt the training process, degrade model accuracy, and compromise system reliability. Traditional FL frameworks typically rely on aggregation-based protocols for model updates, leaving them vulnerable to sophisticated adversarial strategies. In this paper, we demonstrate that distributed optimization offers a principled and robust alternative to aggregation-centric methods. Specifically, we show that the Primal-Dual Method of Multipliers (PDMM) inherently mitigates Byzantine impacts by leveraging its fault-tolerant consensus mechanism. Through extensive experiments on three datasets (MNIST, FashionMNIST, and Olivetti), under various attack scenarios including bit-flipping and Gaussian noise injection, we validate the superior resilience of distributed optimization protocols. Compared to traditional aggregation-centric approaches, PDMM achieves higher model utility, faster convergence, and improved stability. Our results highlight the effectiveness of distributed optimization in defending against Byzantine threats, paving the way for more secure and resilient federated learning systems.
Authors: Sajad Movahedi, Felix Sarnthein, Nicola Muca Cirone, Antonio Orvieto
Abstract: Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer architectures. Current models, however, do not exhibit the full state-tracking expressivity of RNNs because they rely on channel-wise (i.e. diagonal) sequence mixing. In this paper, we propose to compute a dense linear RNN as the fixed-point of a parallelizable diagonal linear RNN in a single layer. We explore mechanisms to improve its memory and state-tracking abilities in practice, and achieve state-of-the-art results on the commonly used toy tasks $A_5$, $S_5$, copying, and modular arithmetics. We hope our results will open new avenues to more expressive and efficient sequence mixers.
Authors: Leonard Waldmann, Ando Shah, Yi Wang, Nils Lehmann, Adam J. Stewart, Zhitong Xiong, Xiao Xiang Zhu, Stefan Bauer, John Chuang
Abstract: Earth observation (EO) data features diverse sensing platforms with varying spectral bands, spatial resolutions, and sensing modalities. While most prior work has constrained inputs to fixed sensors, a new class of any-sensor foundation models able to process arbitrary sensors has recently emerged. Contributing to this line of work, we propose Panopticon, an any-sensor foundation model built on the DINOv2 framework. We extend DINOv2 by (1) treating images of the same geolocation across sensors as natural augmentations, (2) subsampling channels to diversify spectral input, and (3) adding a cross attention over channels as a flexible patch embedding mechanism. By encoding the wavelength and modes of optical and synthetic aperture radar sensors, respectively, Panopticon can effectively process any combination of arbitrary channels. In extensive evaluations, we achieve state-of-the-art performance on GEO-Bench, especially on the widely-used Sentinel-1 and Sentinel-2 sensors, while out-competing other any-sensor models, as well as domain adapted fixed-sensor models on unique sensor configurations. Panopticon enables immediate generalization to both existing and future satellite platforms, advancing sensor-agnostic EO.
Authors: Jiarui Sun, Chin-Chia Michael Yeh, Yujie Fan, Xin Dai, Xiran Fan, Zhimeng Jiang, Uday Singh Saini, Vivian Lai, Junpeng Wang, Huiyuan Chen, Zhongfang Zhuang, Yan Zheng, Girish Chowdhary
Abstract: Time series forecasting at scale presents significant challenges for modern prediction systems, particularly when dealing with large sets of synchronized series, such as in a global payment network. In such systems, three key challenges must be overcome for accurate and scalable predictions: 1) emergence of new entities, 2) disappearance of existing entities, and 3) the large number of entities present in the data. The recently proposed Inverted Transformer (iTransformer) architecture has shown promising results by effectively handling variable entities. However, its practical application in large-scale settings is limited by quadratic time and space complexity ($O(N^2)$) with respect to the number of entities $N$. In this paper, we introduce EiFormer, an improved inverted transformer architecture that maintains the adaptive capabilities of iTransformer while reducing computational complexity to linear scale ($O(N)$). Our key innovation lies in restructuring the attention mechanism to eliminate redundant computations without sacrificing model expressiveness. Additionally, we incorporate a random projection mechanism that not only enhances efficiency but also improves prediction accuracy through better feature representation. Extensive experiments on the public LargeST benchmark dataset and a proprietary large-scale time series dataset demonstrate that EiFormer significantly outperforms existing methods in both computational efficiency and forecasting accuracy. Our approach enables practical deployment of transformer-based forecasting in industrial applications where handling time series at scale is essential.
Authors: Michael Albada
Abstract: Data mining and machine learning hold great potential to enable health systems to systematically use data and analytics to identify inefficiencies and best practices that improve care and reduce costs. Waveform data offers particularly detailed information on how patient health evolves over time and has the potential to significantly improve prediction accuracy on multiple benchmarks, but has been widely under-utilized, largely because of the challenges in working with these large and complex datasets. This study evaluates the potential of leveraging clinical waveform data to improve prediction accuracy on a single benchmark task: the risk of mortality in the intensive care unit. We identify significant potential from this data, beating the existing baselines for both logistic regression and deep learning models.
Authors: Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Jamie Hayes, Borja Balle, Antti Honkela
Abstract: Current practices for reporting the level of differential privacy (DP) guarantees for machine learning (ML) algorithms provide an incomplete and potentially misleading picture of the guarantees and make it difficult to compare privacy levels across different settings. We argue for using Gaussian differential privacy (GDP) as the primary means of communicating DP guarantees in ML, with the full privacy profile as a secondary option in case GDP is too inaccurate. Unlike other widely used alternatives, GDP has only one parameter, which ensures easy comparability of guarantees, and it can accurately capture the full privacy profile of many important ML applications. To support our claims, we investigate the privacy profiles of state-of-the-art DP large-scale image classification, and the TopDown algorithm for the U.S. Decennial Census, observing that GDP fits the profiles remarkably well in all three cases. Although GDP is ideal for reporting the final guarantees, other formalisms (e.g., privacy loss random variables) are needed for accurate privacy accounting. We show that such intermediate representations can be efficiently converted to GDP with minimal loss in tightness.
Authors: Michael Charles Albada, Mojolaoluwa Joshua Sonola
Abstract: Applying deep learning and computational intelligence to finance has been a popular area of applied research, both within academia and industry, and continues to attract active attention. The inherently high volatility and non-stationary of the data pose substantial challenges to machine learning models, especially so for today's expressive and highly-parameterized deep learning models. Recent work has combined natural language processing on data from social media to augment models based purely on historic price data to improve performance has received particular attention. Previous work has achieved state-of-the-art performance on this task by combining techniques such as bidirectional GRUs, variational autoencoders, word and document embeddings, self-attention, graph attention, and adversarial training. In this paper, we demonstrated the efficacy of BERTweet, a variant of BERT pre-trained specifically on a Twitter corpus, and the transformer architecture by achieving competitive performance with the existing literature and setting a new baseline for Matthews Correlation Coefficient on the Stocknet dataset without auxiliary data sources.
Authors: Xue Feng (University of California, Davis), M. Paul Laiu (Oak Ridge National Laboratory), Thomas Strohmer (University of California, Davis)
Abstract: Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data on their own devices. First-order methods, particularly those incorporating variance reduction techniques, are the most widely used FL algorithms due to their simple implementation and stable performance. However, these methods tend to be slow and require a large number of communication rounds to reach the global minimizer. We propose FedOSAA, a novel approach that preserves the simplicity of first-order methods while achieving the rapid convergence typically associated with second-order methods. Our approach applies one Anderson acceleration (AA) step following classical local updates based on first-order methods with variance reduction, such as FedSVRG and SCAFFOLD, during local training. This AA step is able to leverage curvature information from the history points and gives a new update that approximates the Newton-GMRES direction, thereby significantly improving the convergence. We establish a local linear convergence rate to the global minimizer of FedOSAA for smooth and strongly convex loss functions. Numerical comparisons show that FedOSAA substantially improves the communication and computation efficiency of the original first-order methods, achieving performance comparable to second-order methods like GIANT.
Authors: Shuchen Wu
Abstract: Cognition swiftly breaks high-dimensional sensory streams into familiar parts and uncovers their relations. Why do structures emerge, and how do they enable learning, generalization, and prediction? What computational principles underlie this core aspect of perception and intelligence? A sensory stream, simplified, is a one-dimensional sequence. In learning such sequences, we naturally segment them into parts -- a process known as chunking. In the first project, I investigated factors influencing chunking in a serial reaction time task and showed that humans adapt to underlying chunks while balancing speed and accuracy. Building on this, I developed models that learn chunks and parse sequences chunk by chunk. Normatively, I proposed chunking as a rational strategy for discovering recurring patterns and nested hierarchies, enabling efficient sequence factorization. Learned chunks serve as reusable primitives for transfer, composition, and mental simulation -- letting the model compose the new from the known. I demonstrated this model's ability to learn hierarchies in single and multi-dimensional sequences and highlighted its utility for unsupervised pattern discovery. The second part moves from concrete to abstract sequences. I taxonomized abstract motifs and examined their role in sequence memory. Behavioral evidence suggests that humans exploit pattern redundancies for compression and transfer. I proposed a non-parametric hierarchical variable model that learns both chunks and abstract variables, uncovering invariant symbolic patterns. I showed its similarity to human learning and compared it to large language models. Taken together, this thesis suggests that chunking and abstraction as simple computational principles enable structured knowledge acquisition in hierarchically organized sequences, from simple to complex, concrete to abstract.
Authors: JuneYoung Park, YuMi Lee, Tae-Joon Kim, Jang-Hwan Choi
Abstract: Meta-learning, or "learning to learn," aims to enable models to quickly adapt to new tasks with minimal data. While traditional methods like Model-Agnostic Meta-Learning (MAML) optimize parameters in Euclidean space, they often struggle to capture complex learning dynamics, particularly in few-shot learning scenarios. To address this limitation, we propose Stiefel-MAML, which integrates Riemannian geometry by optimizing within the Stiefel manifold, a space that naturally enforces orthogonality constraints. By leveraging the geometric structure of the Stiefel manifold, we improve parameter expressiveness and enable more efficient optimization through Riemannian gradient calculations and retraction operations. We also introduce a novel kernel-based loss function defined on the Stiefel manifold, further enhancing the model's ability to explore the parameter space. Experimental results on benchmark datasets--including Omniglot, Mini-ImageNet, FC-100, and CUB--demonstrate that Stiefel-MAML consistently outperforms traditional MAML, achieving superior performance across various few-shot learning tasks. Our findings highlight the potential of Riemannian geometry to enhance meta-learning, paving the way for future research on optimizing over different geometric structures.
Authors: Shriyank Somvanshi, Rohit Chakraborty, Subasish Das, Anandi K Dutta
Abstract: Child bicyclists (14 years and younger) are among the most vulnerable road users, often experiencing severe injuries or fatalities in crashes. This study analyzed 2,394 child bicyclist crashes in Texas from 2017 to 2022 using two deep tabular learning models (ARM-Net and MambaNet). To address the issue of data imbalance, the SMOTEENN technique was applied, resulting in balanced datasets that facilitated accurate crash severity predictions across three categories: Fatal/Severe (KA), Moderate/Minor (BC), and No Injury (O). The findings revealed that MambaNet outperformed ARM-Net, achieving higher precision, recall, F1-scores, and accuracy, particularly in the KA and O categories. Both models highlighted challenges in distinguishing BC crashes due to overlapping characteristics. These insights underscored the value of advanced tabular deep learning methods and balanced datasets in understanding crash severity. While limitations such as reliance on categorical data exist, future research could explore continuous variables and real-time behavioral data to enhance predictive modeling and crash mitigation strategies.
Authors: Pengcheng Wang, Xinghao Zhu, Yuxin Chen, Chenfeng Xu, Masayoshi Tomizuka, Chenran Li
Abstract: Reinforcement Learning and Imitation Learning have achieved widespread success in many domains but remain constrained during real-world deployment. One of the main issues is the additional requirements that were not considered during training. To address this challenge, policy customization has been introduced, aiming to adapt a prior policy while preserving its inherent properties and meeting new task-specific requirements. A principled approach to policy customization is Residual Q-Learning (RQL), which formulates the problem as a Markov Decision Process (MDP) and derives a family of value-based learning algorithms. However, RQL has not yet been applied to policy gradient methods, which restricts its applicability, especially in tasks where policy gradient has already proven more effective. In this work, we first derive a concise form of Soft Policy Gradient as a preliminary. Building on this, we introduce Residual Policy Gradient (RPG), which extends RQL to policy gradient methods, allowing policy customization in gradient-based RL settings. With the view of RPG, we rethink the KL-regularized objective widely used in RL fine-tuning. We show that under certain assumptions, KL-regularized objective leads to a maximum-entropy policy that balances the inherent properties and task-specific requirements on a reward-level. Our experiments in MuJoCo demonstrate the effectiveness of Soft Policy Gradient and Residual Policy Gradient.
Authors: Weiye Gan, Yicheng Li, Qian Lin, Zuoqiang Shi
Abstract: Spectral bias is a significant phenomenon in neural network training and can be explained by neural tangent kernel (NTK) theory. In this work, we develop the NTK theory for deep neural networks with physics-informed loss, providing insights into the convergence of NTK during initialization and training, and revealing its explicit structure. We find that, in most cases, the differential operators in the loss function do not induce a faster eigenvalue decay rate and stronger spectral bias. Some experimental results are also presented to verify the theory.
Authors: Hongkai Zheng, Wenda Chu, Bingliang Zhang, Zihui Wu, Austin Wang, Berthy T. Feng, Caifeng Zou, Yu Sun, Nikola Kovachki, Zachary E. Ross, Katherine L. Bouman, Yisong Yue
Abstract: Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restoration, leaving the performance of these algorithms in scientific inverse problems largely unexplored. To address this gap, we introduce \textsc{InverseBench}, a framework that evaluates diffusion models across five distinct scientific inverse problems. These problems present unique structural challenges that differ from existing benchmarks, arising from critical scientific applications such as optical tomography, medical imaging, black hole imaging, seismology, and fluid dynamics. With \textsc{InverseBench}, we benchmark 14 inverse problem algorithms that use plug-and-play diffusion priors against strong, domain-specific baselines, offering valuable new insights into the strengths and weaknesses of existing algorithms. To facilitate further research and development, we open-source the codebase, along with datasets and pre-trained models, at https://devzhk.github.io/InverseBench/.
Authors: Ning-Yuan Georgia Liu, Flower Yang, Mohammad S. Jalali
Abstract: Causal graphs are commonly used to understand and model complex systems. Researchers often construct these graphs from different perspectives, leading to significant variations for the same problem. Comparing causal graphs is, therefore, essential for evaluating assumptions, integrating insights, and resolving disagreements. The rise of AI tools has further amplified this need, as they are increasingly used to generate hypothesized causal graphs by synthesizing information from various sources such as prior research and community inputs, providing the potential for automating and scaling causal modeling for complex systems. Similar to humans, these tools also produce inconsistent results across platforms, versions, and iterations. Despite its importance, research on causal graph comparison remains scarce. Existing methods often focus solely on structural similarities, assuming identical variable names, and fail to capture nuanced semantic relationships, which is essential for causal graph comparison. We address these gaps by investigating methods for comparing causal graphs from both semantic and structural perspectives. First, we reviewed over 40 existing metrics and, based on predefined criteria, selected nine for evaluation from two threads of machine learning: four semantic similarity metrics and five learning graph kernels. We discuss the usability of these metrics in simple examples to illustrate their strengths and limitations. We then generated a synthetic dataset of 2,000 causal graphs using generative AI based on a reference diagram. Our findings reveal that each metric captures a different aspect of similarity, highlighting the need to use multiple metrics.
Authors: Hoang V. Tran, Khoi N. M. Nguyen, Trang Pham, Thanh T. Chu, Tam Le, Tan M. Nguyen
Abstract: To overcome computational challenges of Optimal Transport (OT), several variants of Sliced Wasserstein (SW) has been developed in the literature. These approaches exploit the closed-form expression of the univariate OT by projecting measures onto (one-dimensional) lines. However, projecting measures onto low-dimensional spaces can lead to a loss of topological information. Tree-Sliced Wasserstein distance on Systems of Lines (TSW-SL) has emerged as a promising alternative that replaces these lines with a more advanced structure called tree systems. The tree structures enhance the ability to capture topological information of the metric while preserving computational efficiency. However, at the core of TSW-SL, the splitting maps, which serve as the mechanism for pushing forward measures onto tree systems, focus solely on the position of the measure supports while disregarding the projecting domains. Moreover, the specific splitting map used in TSW-SL leads to a metric that is not invariant under Euclidean transformations, a typically expected property for OT on Euclidean space. In this work, we propose a novel class of splitting maps that generalizes the existing one studied in TSW-SL enabling the use of all positional information from input measures, resulting in a novel Distance-based Tree-Sliced Wasserstein (Db-TSW) distance. In addition, we introduce a simple tree sampling process better suited for Db-TSW, leading to an efficient GPU-friendly implementation for tree systems, similar to the original SW. We also provide a comprehensive theoretical analysis of proposed class of splitting maps to verify the injectivity of the corresponding Radon Transform, and demonstrate that Db-TSW is an Euclidean invariant metric. We empirically show that Db-TSW significantly improves accuracy compared to recent SW variants while maintaining low computational cost via a wide range of experiments.
Authors: Jordan S. Ellenberg, Cristofero S. Fraser-Taliente, Thomas R. Harvey, Karan Srivastava, Andrew V. Sutherland
Abstract: We present a new implementation of the LLM-driven genetic algorithm {\it funsearch}, whose aim is to generate examples of interest to mathematicians and which has already had some success in problems in extremal combinatorics. Our implementation is designed to be useful in practice for working mathematicians; it does not require expertise in machine learning or access to high-performance computing resources. Applying {\it funsearch} to a new problem involves modifying a small segment of Python code and selecting a large language model (LLM) from one of many third-party providers. We benchmarked our implementation on three different problems, obtaining metrics that may inform applications of {\it funsearch} to new problems. Our results demonstrate that {\it funsearch} successfully learns in a variety of combinatorial and number-theoretic settings, and in some contexts learns principles that generalize beyond the problem originally trained on.
Authors: Peter B\"ohm, Pauline Pounds, Archie C. Chapman
Abstract: Deep reinforcement learning (DRL) has had success in virtual and simulated domains, but due to key differences between simulated and real-world environments, DRL-trained policies have had limited success in real-world applications. To assist researchers to bridge the \textit{sim-to-real gap}, in this paper, we describe a low-cost physical inverted pendulum apparatus and software environment for exploring sim-to-real DRL methods. In particular, the design of our apparatus enables detailed examination of the delays that arise in physical systems when sensing, communicating, learning, inferring and actuating. Moreover, we wish to improve access to educational systems, so our apparatus uses readily available materials and parts to reduce cost and logistical barriers. Our design shows how commercial, off-the-shelf electronics and electromechanical and sensor systems, combined with common metal extrusions, dowel and 3D printed couplings provide a pathway for affordable physical DRL apparatus. The physical apparatus is complemented with a simulated environment implemented using a high-fidelity physics engine and OpenAI Gym interface.
Authors: I. Bentley, J. Tedder, M. Gebran, A. Paul
Abstract: Sixteen new physics informed machine learning models have been trained on binding energy residuals from modern mass models that leverage shape parameters and other physical features. The models have been trained on a subset of AME 2012 data and have been verified with a subset of the AME 2020 data. Among the machine learning approaches tested in this work, the preferred approach is the least squares boosted ensemble of trees which appears to have a superior ability to both interpolate and extrapolate binding energy residuals. The machine learning models for four mass models created from the ensemble of trees approach have been combined to create a composite model called the Four Model Tree Ensemble (FMTE). The FMTE model predicts binding energy values from AME 2020 with a standard deviation of 76 keV and a mean deviation of 34 keV for all nuclei with N > 7 and Z > 7. A comparison with new mass measurements for 33 isotopes not included in AME 2012 or AME 2020 indicates that the FMTE performs better than all mass models that were tested.
Authors: Haihong Zhao, Chenyi Zi, Aochuan Chen, Jia Li
Abstract: Graph learning plays a vital role in mining and analyzing complex relationships involved in graph data, which is widely used in many real-world applications like transaction networks and communication networks. Foundation models in CV and NLP have shown powerful cross-domain capabilities that are also significant in graph domains. However, existing graph learning approaches struggle with cross-domain tasks. Inspired by successes in CV and NLP, cross-domain graph learning has once again become a focal point of attention to realizing true graph foundation models. In this survey, we present a comprehensive review and analysis of existing works on cross-domain graph learning. Concretely, we first propose a new taxonomy, categorizing existing approaches based on the learned cross-domain information: structure, feature, and structure-feature mixture. Next, we systematically survey representative methods in these categories. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. Relevant papers are summarized and will be consistently updated at: https://github.com/cshhzhao/Awesome-Cross-Domain-Graph-Learning.
URLs: https://github.com/cshhzhao/Awesome-Cross-Domain-Graph-Learning.
Authors: Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Yu Tian
Abstract: The key-value (KV) cache in autoregressive transformers presents a significant bottleneck during inference, which restricts the context length capabilities of large language models (LLMs). While previous work analyzes the fundamental space complexity barriers in standard attention mechanism [Haris and Onak, 2025], our work generalizes the space complexity barriers result to tensor attention version. Our theoretical contributions rely on a novel reduction from communication complexity and deduce the memory lower bound for tensor-structured attention mechanisms when $d = \Omega(\log n)$. In the low dimensional regime where $d = o(\log n)$, we analyze the theoretical bounds of the space complexity as well. Overall, our work provides a theoretical foundation for us to understand the compression-expressivity tradeoff in tensor attention mechanisms and offers more perspectives in developing more memory-efficient transformer architectures.
Authors: G\"okhan \"Ozbulak, Oscar Jimenez-del-Toro, Ma\'ira Fatoretto, Lilian Berton, Andr\'e Anjos
Abstract: The evaluation of fairness models in Machine Learning involves complex challenges, such as defining appropriate metrics, balancing trade-offs between utility and fairness, and there are still gaps in this stage. This work presents a novel multi-objective evaluation framework that enables the analysis of utility-fairness trade-offs in Machine Learning systems. The framework was developed using criteria from Multi-Objective Optimization that collect comprehensive information regarding this complex evaluation task. The assessment of multiple Machine Learning systems is summarized, both quantitatively and qualitatively, in a straightforward manner through a radar chart and a measurement table encompassing various aspects such as convergence, system capacity, and diversity. The framework's compact representation of performance facilitates the comparative analysis of different Machine Learning strategies for decision-makers, in real-world applications, with single or multiple fairness requirements. The framework is model-agnostic and flexible to be adapted to any kind of Machine Learning systems, that is, black- or white-box, any kind and quantity of evaluation metrics, including multidimensional fairness criteria. The functionality and effectiveness of the proposed framework is shown with different simulations, and an empirical study conducted on a real-world dataset with various Machine Learning systems.
Authors: Jie Liu, Yiwei Zhang, Yuan Sheng, Yujia Lou, Haige Wang, Bohuan Yang
Abstract: This study proposes a dynamic rule data mining algorithm based on an improved Transformer architecture, aiming to improve the accuracy and efficiency of rule mining in a dynamic data environment. With the increase in data volume and complexity, traditional data mining methods are difficult to cope with dynamic data with strong temporal and variable characteristics, so new algorithms are needed to capture the temporal regularity in the data. By improving the Transformer architecture, and introducing a dynamic weight adjustment mechanism and a temporal dependency module, we enable the model to adapt to data changes and mine more accurate rules. Experimental results show that compared with traditional rule mining algorithms, the improved Transformer model has achieved significant improvements in rule mining accuracy, coverage, and stability. The contribution of each module in the algorithm performance is further verified by ablation experiments, proving the importance of temporal dependency and dynamic weight adjustment mechanisms in improving the model effect. In addition, although the improved model has certain challenges in computational efficiency, its advantages in accuracy and coverage enable it to perform well in processing complex dynamic data. Future research will focus on optimizing computational efficiency and combining more deep learning technologies to expand the application scope of the algorithm, especially in practical applications in the fields of finance, medical care, and intelligent recommendation.
Authors: Vu Nguyen, Andrey Kan
Abstract: The problem of relevant and diverse subset selection has a wide range of applications, including recommender systems and retrieval-augmented generation (RAG). For example, in recommender systems, one is interested in selecting relevant items, while providing a diversified recommendation. Constrained subset selection problem is NP-hard, and popular approaches such as Maximum Marginal Relevance (MMR) are based on greedy selection. Many real-world applications involve large data, but the original MMR work did not consider distributed selection. This limitation was later addressed by a method called DGDS which allows for a distributed setting using random data partitioning. Here, we exploit structure in the data to further improve both scalability and performance on the target application. We propose MUSS, a novel method that uses a multilevel approach to relevant and diverse selection. We provide a rigorous theoretical analysis and show that our method achieves a constant factor approximation of the optimal objective. In a recommender system application, our method can achieve the same level of performance as baselines, but 4.5 to 20 times faster. Our method is also capable of outperforming baselines by up to 6 percent points of RAG-based question answering accuracy.
Authors: Matthew Khoriaty (Northwestern University), Andrii Shportko (Northwestern University), Gustavo Mercier (Northwestern University), Zach Wood-Doughty (Northwestern University)
Abstract: Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the wrong hands or during malfunctions. Because of their nature as near-black boxes, intuitive interpretation of LLM internals remains an open research question, preventing developers from easily controlling model behavior and capabilities. The use of Sparse Autoencoders (SAEs) has recently emerged as a potential method of unraveling representations of concepts in LLMs internals, and has allowed developers to steer model outputs by directly modifying the hidden activations. In this paper, we use SAEs to identify unwanted concepts from the Weapons of Mass Destruction Proxy (WMDP) dataset within gemma-2-2b internals and use feature steering to reduce the model's ability to answer harmful questions while retaining its performance on harmless queries. Our results bring back optimism to the viability of SAE-based explicit knowledge unlearning techniques.
Authors: Jisoo Kim, Sungmin Kang, Sunwoo Lee
Abstract: Expensive communication cost is a common performance bottleneck in Federated Learning (FL), which makes it less appealing in real-world applications. Many communication-efficient FL methods focus on discarding a part of model updates mostly based on gradient magnitude. In this study, we find that recycling previous updates, rather than simply dropping them, more effectively reduces the communication cost while maintaining FL performance. We propose FedLUAR, a Layer-wise Update Aggregation with Recycling scheme for communication-efficient FL. We first define a useful metric that quantifies the extent to which the aggregated gradients influences the model parameter values in each layer. FedLUAR selects a few layers based on the metric and recycles their previous updates on the server side. Our extensive empirical study demonstrates that the update recycling scheme significantly reduces the communication cost while maintaining model accuracy. For example, our method achieves nearly the same AG News accuracy as FedAvg, while reducing the communication cost to just 17%.
Authors: Junhyuk Jo, Jihyun Lim, Sunwoo Lee
Abstract: Sharpness-Aware Minimization (SAM) is an optimization method that improves generalization performance of machine learning models. Despite its superior generalization, SAM has not been actively used in real-world applications due to its expensive computational cost. In this work, we propose a novel asynchronous-parallel SAM which achieves nearly the same gradient norm penalizing effect like the original SAM while breaking the data dependency between the model perturbation and the model update. The proposed asynchronous SAM can even entirely hide the model perturbation time by adjusting the batch size for the model perturbation in a system-aware manner. Thus, the proposed method enables to fully utilize heterogeneous system resources such as CPUs and GPUs. Our extensive experiments well demonstrate the practical benefits of the proposed asynchronous approach. E.g., the asynchronous SAM achieves comparable Vision Transformer fine-tuning accuracy (CIFAR-100) as the original SAM while having almost the same training time as SGD.
Authors: Jihyun Lim, Junhyuk Jo, Tuo Zhang, Salman Avestimehr, Sunwoo Lee
Abstract: Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to perform KD on the server side. However, they often assume that unlabeled data collected at the edge is centralized on the server. Moreover, the logit ensemble method personalizes local models, which can degrade the quality of soft targets, especially when data is highly non-IID. To address these critical limitations,we propose a novel on-device KD-based heterogeneous FL method. Our approach leverages a small auxiliary model to learn from labeled local data. Subsequently, a subset of clients with strong system resources transfers knowledge to a large model through on-device KD using their unlabeled data. Our extensive experiments demonstrate that our on-device KD-based heterogeneous FL method effectively utilizes the system resources of all edge devices as well as the unlabeled data, resulting in higher accuracy compared to SOTA KD-based FL methods.
Authors: Guanhua Zheng, Jitao Sang, Changsheng Xu
Abstract: Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original gradients. However, these methods lack a solid theoretical foundation and exhibit perplexing behaviors, such as reduced sensitivity to parameter randomization, raising concerns about their reliability and highlighting the need for theoretical justification. In this work, we present a unified theoretical framework for methods like GBP, RectGrad, LRP, and DTD, demonstrating that they achieve input alignment by combining the weights of activated neurons. This alignment improves the visualization quality and reduces sensitivity to weight randomization. Our contributions include: (1) Providing a unified explanation for multiple behaviors, rather than focusing on just one. (2) Accurately predicting novel behaviors. (3) Offering insights into decision-making processes, including layer-wise information changes and the relationship between attributions and model decisions.
Authors: Suchanun Piriyasatit, Ercan Engin Kuruoglu, Mehmet Sinan Ozeren
Abstract: Earthquake detection is essential for earthquake early warning (EEW) systems. Traditional methods struggle with low signal-to-noise ratios and single-station reliance, limiting their effectiveness. We propose a Spatio-Temporal Graph Convolutional Network (GCN) using Spectral Structure Learning Convolution (Spectral SLC) to model static and dynamic relationships across seismic stations. Our approach processes multi-station waveform data and generates station-specific detection probabilities. Experiments show superior performance over a conventional GCN baseline in terms of true positive rate (TPR) and false positive rate (FPR), highlighting its potential for robust multi-station earthquake detection. The code repository for this study is available at https://github.com/SuchanunP/eq_detector.
Authors: Romain Mussard, Fannia Pacheco, Maxime Berar, Gilles Gasso, Paul Honeine
Abstract: Universal Domain Adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain, even when their classes are not fully shared. Few dedicated UniDA methods exist for Time Series (TS), which remains a challenging case. In general, UniDA approaches align common class samples and detect unknown target samples from emerging classes. Such detection often results from thresholding a discriminability metric. The threshold value is typically either a fine-tuned hyperparameter or a fixed value, which limits the ability of the model to adapt to new data. Furthermore, discriminability metrics exhibit overconfidence for unknown samples, leading to misclassifications. This paper introduces UniJDOT, an optimal-transport-based method that accounts for the unknown target samples in the transport cost. Our method also proposes a joint decision space to improve the discriminability of the detection module. In addition, we use an auto-thresholding algorithm to reduce the dependence on fixed or fine-tuned thresholds. Finally, we rely on a Fourier transform-based layer inspired by the Fourier Neural Operator for better TS representation. Experiments on TS benchmarks demonstrate the discriminability, robustness, and state-of-the-art performance of UniJDOT.
Authors: Xingtai Lv, Youbang Sun, Kaiyan Zhang, Shang Qu, Xuekai Zhu, Yuchen Fan, Yi Wu, Ermo Hua, Xinwei Long, Ning Ding, Bowen Zhou
Abstract: State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts, demonstrating comparable performances with significant efficiency gains. In this survey, we provide a coherent and systematic overview for SSMs, including their theoretical motivations, mathematical formulations, comparison with existing model classes, and various applications. We divide the SSM series into three main sections, providing a detailed introduction to the original SSM, the structured SSM represented by S4, and the selective SSM typified by Mamba. We put an emphasis on technicality, and highlight the various key techniques introduced to address the effectiveness and efficiency of SSMs. We hope this manuscript serves as an introduction for researchers to explore the theoretical foundations of SSMs.
Authors: Ahmed Frikha, Muhammad Reza Ar Razi, Krishna Kanth Nakka, Ricardo Mendes, Xue Jiang, Xuebing Zhou
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation strategies, such as differential privacy and neuron-level interventions, often degrade model utility or fail to effectively prevent leakage. To address this challenge, we introduce PrivacyScalpel, a novel privacy-preserving framework that leverages LLM interpretability techniques to identify and mitigate PII leakage while maintaining performance. PrivacyScalpel comprises three key steps: (1) Feature Probing, which identifies layers in the model that encode PII-rich representations, (2) Sparse Autoencoding, where a k-Sparse Autoencoder (k-SAE) disentangles and isolates privacy-sensitive features, and (3) Feature-Level Interventions, which employ targeted ablation and vector steering to suppress PII leakage. Our empirical evaluation on Gemma2-2b and Llama2-7b, fine-tuned on the Enron dataset, shows that PrivacyScalpel significantly reduces email leakage from 5.15\% to as low as 0.0\%, while maintaining over 99.4\% of the original model's utility. Notably, our method outperforms neuron-level interventions in privacy-utility trade-offs, demonstrating that acting on sparse, monosemantic features is more effective than manipulating polysemantic neurons. Beyond improving LLM privacy, our approach offers insights into the mechanisms underlying PII memorization, contributing to the broader field of model interpretability and secure AI deployment.
Authors: Vojtech Cahlik, Rodrigo Alves, Pavel Kordik
Abstract: We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning process can become part of the model context and later be decoded to natural language as the model produces either the final answer or the explanation. To improve the faithfulness of the explanations, we propose to use a joint predict-explain approach, in which the answers and explanations are inferred directly from the reasoning sequence, without the explanations being dependent on the answers and vice versa. We demonstrate the plausibility of the proposed technique by achieving a high alignment between answers and explanations in several problem domains, observing that language models often simply copy the partial decisions from the reasoning sequence into the final answers or explanations. Furthermore, we show that the proposed use of reasoning can also improve the quality of the answers.
Authors: Hoang V. Tran, Thanh T. Chu, Khoi N. M. Nguyen, Trang Pham, Tam Le, Tan M. Nguyen
Abstract: Sliced Optimal Transport (OT) simplifies the OT problem in high-dimensional spaces by projecting supports of input measures onto one-dimensional lines and then exploiting the closed-form expression of the univariate OT to reduce the computational burden of OT. Recently, the Tree-Sliced method has been introduced to replace these lines with more intricate structures, known as tree systems. This approach enhances the ability to capture topological information of integration domains in Sliced OT while maintaining low computational cost. Inspired by this approach, in this paper, we present an adaptation of tree systems on OT problems for measures supported on a sphere. As a counterpart to the Radon transform variant on tree systems, we propose a novel spherical Radon transform with a new integration domain called spherical trees. By leveraging this transform and exploiting the spherical tree structures, we derive closed-form expressions for OT problems on the sphere. Consequently, we obtain an efficient metric for measures on the sphere, named Spherical Tree-Sliced Wasserstein (STSW) distance. We provide an extensive theoretical analysis to demonstrate the topology of spherical trees and the well-definedness and injectivity of our Radon transform variant, which leads to an orthogonally invariant distance between spherical measures. Finally, we conduct a wide range of numerical experiments, including gradient flows and self-supervised learning, to assess the performance of our proposed metric, comparing it to recent benchmarks.
Authors: Long Tan Le, Tung-Anh Nguyen, Han Shu, Suranga Seneviratne, Choong Seon Hong, Nguyen H. Tran
Abstract: The proliferation of edge devices has dramatically increased the generation of multivariate time-series (MVTS) data, essential for applications from healthcare to smart cities. Such data streams, however, are vulnerable to anomalies that signal crucial problems like system failures or security incidents. Traditional MVTS anomaly detection methods, encompassing statistical and centralized machine learning approaches, struggle with the heterogeneity, variability, and privacy concerns of large-scale, distributed environments. In response, we introduce FedKO, a novel unsupervised Federated Learning framework that leverages the linear predictive capabilities of Koopman operator theory along with the dynamic adaptability of Reservoir Computing. This enables effective spatiotemporal processing and privacy preservation for MVTS data. FedKO is formulated as a bi-level optimization problem, utilizing a specific federated algorithm to explore a shared Reservoir-Koopman model across diverse datasets. Such a model is then deployable on edge devices for efficient detection of anomalies in local MVTS streams. Experimental results across various datasets showcase FedKO's superior performance against state-of-the-art methods in MVTS anomaly detection. Moreover, FedKO reduces up to 8x communication size and 2x memory usage, making it highly suitable for large-scale systems.
Authors: Babak Emami, Wesley Dyk, David Haycraft, Carrie Spear, Lac Nguyen, Nicholas Chancellor
Abstract: We introduce CVQBoost, a novel classification algorithm that leverages early hardware implementing Quantum Computing Inc's Entropy Quantum Computing (EQC) paradigm, Dirac-3 [Nguyen et. al. arXiv:2407.04512]. We apply CVQBoost to a fraud detection test case and benchmark its performance against XGBoost, a widely utilized ML method. Running on Dirac-3, CVQBoost demonstrates a significant runtime advantage over XGBoost, which we evaluate on high-performance hardware comprising up to 48 CPUs and four NVIDIA L4 GPUs using the RAPIDS AI framework. Our results show that CVQBoost maintains competitive accuracy (measured by AUC) while significantly reducing training time, particularly as dataset size and feature complexity increase. To assess scalability, we extend our study to large synthetic datasets ranging from 1M to 70M samples, demonstrating that CVQBoost on Dirac-3 is well-suited for large-scale classification tasks. These findings position CVQBoost as a promising alternative to gradient boosting methods, offering superior scalability and efficiency for high-dimensional ML applications such as fraud detection.
Authors: Edward Pearce-Crump
Abstract: Incorporating permutation equivariance into neural networks has proven to be useful in ensuring that models respect symmetries that exist in data. Symmetric tensors, which naturally appear in statistics, machine learning, and graph theory, are essential for many applications in physics, chemistry, and materials science, amongst others. However, existing research on permutation equivariant models has not explored symmetric tensors as inputs, and most prior work on learning from these tensors has focused on equivariance to Euclidean groups. In this paper, we present two different characterisations of all linear permutation equivariant functions between symmetric power spaces of $\mathbb{R}^n$. We show on two tasks that these functions are highly data efficient compared to standard MLPs and have potential to generalise well to symmetric tensors of different sizes.
Authors: Christelle Schneuwly Diaz, Duy-Thanh Vu, Julien Bodelet, Duy-Cat Can, Guillaume Blanc, Haiting Jiang, Lin Yao, Guiseppe Pantaleo, ADNI, Oliver Y. Ch\'en
Abstract: Alzheimer's disease, a neurodegenerative disorder, is associated with neural, genetic, and proteomic factors while affecting multiple cognitive and behavioral faculties. Traditional AD prediction largely focuses on univariate disease outcomes, such as disease stages and severity. Multimodal data encode broader disease information than a single modality and may, therefore, improve disease prediction; but they often contain missing values. Recent "deeper" machine learning approaches show promise in improving prediction accuracy, yet the biological relevance of these models needs to be further charted. Integrating missing data analysis, predictive modeling, multimodal data analysis, and explainable AI, we propose OPTIMUS, a predictive, modular, and explainable machine learning framework, to unveil the many-to-many predictive pathways between multimodal input data and multivariate disease outcomes amidst missing values. OPTIMUS first applies modality-specific imputation to uncover data from each modality while optimizing overall prediction accuracy. It then maps multimodal biomarkers to multivariate outcomes using machine-learning and extracts biomarkers respectively predictive of each outcome. Finally, OPTIMUS incorporates XAI to explain the identified multimodal biomarkers. Using data from 346 cognitively normal subjects, 608 persons with mild cognitive impairment, and 251 AD patients, OPTIMUS identifies neural and transcriptomic signatures that jointly but differentially predict multivariate outcomes related to executive function, language, memory, and visuospatial function. Our work demonstrates the potential of building a predictive and biologically explainable machine-learning framework to uncover multimodal biomarkers that capture disease profiles across varying cognitive landscapes. The results improve our understanding of the complex many-to-many pathways in AD.
Authors: Wen Xiong, Jinduo Liu, Junzhong Ji, Fenglong Ma
Abstract: Estimating brain effective connectivity (EC) from functional magnetic resonance imaging (fMRI) data can aid in comprehending the neural mechanisms underlying human behavior and cognition, providing a foundation for disease diagnosis. However, current spatiotemporal attention modules handle temporal and spatial attention separately, extracting temporal and spatial features either sequentially or in parallel. These approaches overlook the inherent spatiotemporal correlations present in real world fMRI data. Additionally, the presence of noise in fMRI data further limits the performance of existing methods. In this paper, we propose a novel brain effective connectivity estimation method based on Fourier spatiotemporal attention (FSTA-EC), which combines Fourier attention and spatiotemporal attention to simultaneously capture inter-series (spatial) dynamics and intra-series (temporal) dependencies from high-noise fMRI data. Specifically, Fourier attention is designed to convert the high-noise fMRI data to frequency domain, and map the denoised fMRI data back to physical domain, and spatiotemporal attention is crafted to simultaneously learn spatiotemporal dynamics. Furthermore, through a series of proofs, we demonstrate that incorporating learnable filter into fast Fourier transform and inverse fast Fourier transform processes is mathematically equivalent to performing cyclic convolution. The experimental results on simulated and real-resting-state fMRI datasets demonstrate that the proposed method exhibits superior performance when compared to state-of-the-art methods.
Authors: Martin V\'yboh, Zuzana Chladn\'a, Gabriela Grmanov\'a, M\'aria Luck\'a
Abstract: This work presents a three-phase ML prediction framework designed to handle a high dimensionality and multivariate time series character of the electricity market curves. In the preprocessing phase, we transform the original data to achieve a unified structure and mitigate the effect of possible outliers. Further, to address the challenge of high dimensionality, we test three dimensionality reduction techniques (PCA, kPCA, UMAP). Finally, we predict supply and demand curves, once represented in a latent space, with a variety of machine learning methods (RF, LSTM, TSMixer). As our results on the MIBEL dataset show, a high dimensional structure of the market curves can be best handled by the nonlinear reduction technique UMAP. Regardless of the ML technique used for prediction, we achieved the lowest values for all considered precision metrics with a UMAP latent space representation in only two or three dimensions, even when compared to PCA and kPCA with five or six dimensions. Further, we demonstrate that the most promising machine learning technique to handle the complex structure of the electricity market curves is a novel TSMixer architecture. Finally, we fill the gap in the field of electricity market curves prediction literature: in addition to standard analysis on the supply side, we applied the ML framework and predicted demand curves too. We discussed the differences in the achieved results for these two types of curves.
Authors: Masaya Mori, Yuto Omae, Yutaka Koyama, Kazuyuki Hara, Jun Toyotani, Yasuo Okumura, Hiroyuki Hao
Abstract: As the number of patients with heart failure increases, machine learning (ML) has garnered attention in cardiomyopathy diagnosis, driven by the shortage of pathologists. However, endomyocardial biopsy specimens are often small sample size and require techniques such as feature extraction and dimensionality reduction. This study aims to determine whether texture features are effective for feature extraction in the pathological diagnosis of cardiomyopathy. Furthermore, model designs that contribute toward improving generalization performance are examined by applying feature selection (FS) and dimensional compression (DC) to several ML models. The obtained results were verified by visualizing the inter-class distribution differences and conducting statistical hypothesis testing based on texture features. Additionally, they were evaluated using predictive performance across different model designs with varying combinations of FS and DC (applied or not) and decision boundaries. The obtained results confirmed that texture features may be effective for the pathological diagnosis of cardiomyopathy. Moreover, when the ratio of features to the sample size is high, a multi-step process involving FS and DC improved the generalization performance, with the linear kernel support vector machine achieving the best results. This process was demonstrated to be potentially effective for models with reduced complexity, regardless of whether the decision boundaries were linear, curved, perpendicular, or parallel to the axes. These findings are expected to facilitate the development of an effective cardiomyopathy diagnostic model for its rapid adoption in medical practice.
Authors: Moritz A. Zanger, Pascal R. Van der Vaart, Wendelin B\"ohmer, Matthijs T. J. Spaan
Abstract: Uncertainty quantification is a critical aspect of reinforcement learning and deep learning, with numerous applications ranging from efficient exploration and stable offline reinforcement learning to outlier detection in medical diagnostics. The scale of modern neural networks, however, complicates the use of many theoretically well-motivated approaches such as full Bayesian inference. Approximate methods like deep ensembles can provide reliable uncertainty estimates but still remain computationally expensive. In this work, we propose contextual similarity distillation, a novel approach that explicitly estimates the variance of an ensemble of deep neural networks with a single model, without ever learning or evaluating such an ensemble in the first place. Our method builds on the predictable learning dynamics of wide neural networks, governed by the neural tangent kernel, to derive an efficient approximation of the predictive variance of an infinite ensemble. Specifically, we reinterpret the computation of ensemble variance as a supervised regression problem with kernel similarities as regression targets. The resulting model can estimate predictive variance at inference time with a single forward pass, and can make use of unlabeled target-domain data or data augmentations to refine its uncertainty estimates. We empirically validate our method across a variety of out-of-distribution detection benchmarks and sparse-reward reinforcement learning environments. We find that our single-model method performs competitively and sometimes superior to ensemble-based baselines and serves as a reliable signal for efficient exploration. These results, we believe, position contextual similarity distillation as a principled and scalable alternative for uncertainty quantification in reinforcement learning and general deep learning.
Authors: Marinela Adam
Abstract: Few-Shot Class-Incremental Learning (FSCIL) represents a cutting-edge paradigm within the broader scope of machine learning, designed to empower models with the ability to assimilate new classes of data with limited examples while safeguarding existing knowledge. The paper will present different solutions which contain extensive experiments across large-scale datasets, domain shifts, and network architectures to evaluate and compare the selected methods. We highlight their advantages and then present an experimental approach with the purpose of improving the most promising one by replacing the visual-language (V-L) model (CLIP) with another V-L model (CLOOB) that seem to outperform it on zero-shot learning tasks. The aim of this report is to present an experimental method for FSCIL that would improve its performance. We also plan to offer an overview followed by an analysis of the recent advancements in FSCIL domain, focusing on various strategies to mitigate catastrophic forgetting and improve the adaptability of models to evolving tasks and datasets.
Authors: Wenbo Yan, Shurui Wang, Ying Tan
Abstract: Mamba has demonstrated excellent performance in various time series forecasting tasks due to its superior selection mechanism. Nevertheless, conventional Mamba-based models encounter significant challenges in accurately predicting stock time series, as they fail to adequately capture both the overarching market dynamics and the intricate interdependencies among individual stocks. To overcome these constraints, we introduce the Hierarchical Information-Guided Spatio-Temporal Mamba (HIGSTM) framework. HIGSTM introduces Index-Guided Frequency Filtering Decomposition to extract commonality and specificity from time series. The model architecture features a meticulously designed hierarchical framework that systematically captures both temporal dynamic patterns and global static relationships within the stock market. Furthermore, we propose an Information-Guided Mamba that integrates macro informations into the sequence selection process, thereby facilitating more market-conscious decision-making. Comprehensive experimental evaluations conducted on the CSI500, CSI800 and CSI1000 datasets demonstrate that HIGSTM achieves state-of-the-art performance.
Authors: Xin Zhong, Weiwei Ling, Kejia Pan, Pinxia Wu, Jiajing Zhang, Zhiliang Zhan, Wenbo Xiao
Abstract: Traditional three-dimensional magnetotelluric (MT) numerical forward modeling methods, such as the finite element method (FEM) and finite volume method (FVM), suffer from high computational costs and low efficiency due to limitations in mesh refinement and computational resources. We propose a novel neural network architecture named MTAGU-Net, which integrates an attention gating mechanism for 3D MT forward modeling. Specifically, a dual-path attention gating module is designed based on forward response data images and embedded in the skip connections between the encoder and decoder. This module enables the fusion of critical anomaly information from shallow feature maps during the decoding of deep feature maps, significantly enhancing the network's capability to extract features from anomalous regions. Furthermore, we introduce a synthetic model generation method utilizing 3D Gaussian random field (GRF), which accurately replicates the electrical structures of real-world geological scenarios with high fidelity. Numerical experiments demonstrate that MTAGU-Net outperforms conventional 3D U-Net in terms of convergence stability and prediction accuracy, with the structural similarity index (SSIM) of the forward response data consistently exceeding 0.98. Moreover, the network can accurately predict forward response data on previously unseen datasets models, demonstrating its strong generalization ability and validating the feasibility and effectiveness of this method in practical applications.
Authors: Xu Liu, Taha Aksu, Juncheng Liu, Qingsong Wen, Yuxuan Liang, Caiming Xiong, Silvio Savarese, Doyen Sahoo, Junnan Li, Chenghao Liu
Abstract: Time series analysis is crucial for understanding dynamics of complex systems. Recent advances in foundation models have led to task-agnostic Time Series Foundation Models (TSFMs) and Large Language Model-based Time Series Models (TSLLMs), enabling generalized learning and integrating contextual information. However, their success depends on large, diverse, and high-quality datasets, which are challenging to build due to regulatory, diversity, quality, and quantity constraints. Synthetic data emerge as a viable solution, addressing these challenges by offering scalable, unbiased, and high-quality alternatives. This survey provides a comprehensive review of synthetic data for TSFMs and TSLLMs, analyzing data generation strategies, their role in model pretraining, fine-tuning, and evaluation, and identifying future research directions.
Authors: Chen Shu, Mengke Li, Yiqun Zhang, Yang Lu, Bo Han, Yiu-ming Cheung, Hanzi Wang
Abstract: In real-world datasets, the challenges of long-tailed distributions and noisy labels often coexist, posing obstacles to the model training and performance. Existing studies on long-tailed noisy label learning (LTNLL) typically assume that the generation of noisy labels is independent of the long-tailed distribution, which may not be true from a practical perspective. In real-world situaiton, we observe that the tail class samples are more likely to be mislabeled as head, exacerbating the original degree of imbalance. We call this phenomenon as ``tail-to-head (T2H)'' noise. T2H noise severely degrades model performance by polluting the head classes and forcing the model to learn the tail samples as head. To address this challenge, we investigate the dynamic misleading process of the nosiy labels and propose a novel method called Disentangling and Unlearning for Long-tailed and Label-noisy data (DULL). It first employs the Inner-Feature Disentangling (IFD) to disentangle feature internally. Based on this, the Inner-Feature Partial Unlearning (IFPU) is then applied to weaken and unlearn incorrect feature regions correlated to wrong classes. This method prevents the model from being misled by noisy labels, enhancing the model's robustness against noise. To provide a controlled experimental environment, we further propose a new noise addition algorithm to simulate T2H noise. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness of our proposed method.
Authors: Seyed Mahmoud Sajjadi Mohammadabadi
Abstract: This paper explores the critical transition from Generative Artificial Intelligence (GenAI) to Innovative Artificial Intelligence (InAI). While recent advancements in GenAI have enabled systems to produce high-quality content across various domains, these models often lack the capacity for true innovation. In this context, innovation is defined as the ability to generate novel and useful outputs that go beyond mere replication of learned data. The paper examines this shift and proposes a roadmap for developing AI systems that can generate content and engage in autonomous problem-solving and creative ideation. The work provides both theoretical insights and practical strategies for advancing AI to a stage where it can genuinely innovate, contributing meaningfully to science, technology, and the arts.
Authors: Naoufal El Bekri, Lucas Drumetz, Franck Vermet
Abstract: Solving the Fokker-Planck equation for high-dimensional complex dynamical systems remains a pivotal yet challenging task due to the intractability of analytical solutions and the limitations of traditional numerical methods. In this work, we present FlowKac, a novel approach that reformulates the Fokker-Planck equation using the Feynman-Kac formula, allowing to query the solution at a given point via the expected values of stochastic paths. A key innovation of FlowKac lies in its adaptive stochastic sampling scheme which significantly reduces the computational complexity while maintaining high accuracy. This sampling technique, coupled with a time-indexed normalizing flow, designed for capturing time-evolving probability densities, enables robust sampling of collocation points, resulting in a flexible and mesh-free solver. This formulation mitigates the curse of dimensionality and enhances computational efficiency and accuracy, which is particularly crucial for applications that inherently require dimensions beyond the conventional three. We validate the robustness and scalability of our method through various experiments on a range of stochastic differential equations, demonstrating significant improvements over existing techniques.
Authors: Theodora-Mara P\^islar, Sara Magliacane, Atticus Geiger
Abstract: Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of the network contains low-level features that realize the high-level variables in a causal model of the algorithm. A typical problem in practical settings is that the algorithm is not an entirely faithful abstraction of the network, meaning it only partially captures the true reasoning process of a model. We propose a solution where we combine different simple high-level models to produce a more faithful representation of the network. Through learning this combination, we can model neural networks as being in different computational states depending on the input provided, which we show is more accurate to GPT 2-small fine-tuned on two toy tasks. We observe a trade-off between the strength of an interpretability hypothesis, which we define in terms of the number of inputs explained by the high-level models, and its faithfulness, which we define as the interchange intervention accuracy. Our method allows us to modulate between the two, providing the most accurate combination of models that describe the behavior of a neural network given a faithfulness level.
Authors: Jia Zhang, Chen-Xi Zhang, Yao Liu, Yi-Xuan Jin, Xiao-Wen Yang, Bo Zheng, Yi Liu, Lan-Zhe Guo
Abstract: Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabilities, outperforming large datasets often burdened by quality and redundancy issues. However, the challenge lies in automatically identifying valuable subsets from large datasets to boost both the effectiveness and efficiency of instruction tuning. In this paper, we first establish data selection criteria based on three distinct aspects of data value: diversity, difficulty, and dependability, and then propose the D3 method comprising two key steps of scoring and selection. Specifically, in the scoring step, we define the diversity function to measure sample distinctiveness and introduce the uncertainty-based prediction difficulty to evaluate sample difficulty by mitigating the interference of context-oriented generation diversity. Additionally, we integrate an external LLM for dependability assessment. In the selection step, we formulate the D3 weighted coreset objective, which jointly optimizes three aspects of data value to solve for the most valuable subset. The two steps of D3 can iterate multiple rounds, incorporating feedback to refine the selection focus adaptively. Experiments on three datasets demonstrate the effectiveness of D3 in endowing LLMs with competitive or even superior instruction-following capabilities using less than 10% of the entire dataset.
Authors: Aryaman Reddi, Glenn Vinnicombe
Abstract: We present heuristically optimal strategies expressed by deep learning agents playing a simple avoidance game. We analyse the learning and behaviour of two agents within a symmetrical grid world that must cross paths to reach a target destination without crashing into each other or straying off of the grid world in the wrong direction. The agent policy is determined by one neural network that is employed in both agents. Our findings indicate that the fully trained network exhibits behaviour similar to that of the game Hawks and Doves, in that one agent employs an aggressive strategy to reach the target while the other learns how to avoid the aggressive agent.
Authors: Mingjia Shi, Ruihan Lin, Xuxi Chen, Yuhao Zhou, Zezhen Ding, Pingzhi Li, Tong Wang, Kai Wang, Zhangyang Wang, Jiheng Zhang, Tianlong Chen
Abstract: Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks. L2O paradigms achieve great outcomes, e.g., refitting optimizer, generating unseen solutions iteratively or directly. However, conventional L2O methods require intricate design and rely on specific optimization processes, limiting scalability and generalization. Our analyses explore general framework for learning optimization, called Diff-L2O, focusing on augmenting sampled solutions from a wider view rather than local updates in real optimization process only. Meanwhile, we give the related generalization bound, showing that the sample diversity of Diff-L2O brings better performance. This bound can be simply applied to other fields, discussing diversity, mean-variance, and different tasks. Diff-L2O's strong compatibility is empirically verified with only minute-level training, comparing with other hour-levels.
Authors: Chengen Wang, Murat Kantarcioglu
Abstract: DeepSeek-V3 and DeepSeek-R1 are leading open-source Large Language Models (LLMs) for general-purpose tasks and reasoning, achieving performance comparable to state-of-the-art closed-source models from companies like OpenAI and Anthropic -- while requiring only a fraction of their training costs. Understanding the key innovative techniques behind DeepSeek's success is crucial for advancing LLM research. In this paper, we review the core techniques driving the remarkable effectiveness and efficiency of these models, including refinements to the transformer architecture, innovations such as Multi-Head Latent Attention and Mixture of Experts, Multi-Token Prediction, the co-design of algorithms, frameworks, and hardware, the Group Relative Policy Optimization algorithm, post-training with pure reinforcement learning and iterative training alternating between supervised fine-tuning and reinforcement learning. Additionally, we identify several open questions and highlight potential research opportunities in this rapidly advancing field.
Authors: Yifeng Zhang, Yilin Liu, Ping Gong, Peizhuo Li, Mingfeng Fan, Guillaume Sartoretti
Abstract: Adaptive traffic signal control (ATSC) is crucial in reducing congestion, maximizing throughput, and improving mobility in rapidly growing urban areas. Recent advancements in parameter-sharing multi-agent reinforcement learning (MARL) have greatly enhanced the scalable and adaptive optimization of complex, dynamic flows in large-scale homogeneous networks. However, the inherent heterogeneity of real-world traffic networks, with their varied intersection topologies and interaction dynamics, poses substantial challenges to achieving scalable and effective ATSC across different traffic scenarios. To address these challenges, we present Unicorn, a universal and collaborative MARL framework designed for efficient and adaptable network-wide ATSC. Specifically, we first propose a unified approach to map the states and actions of intersections with varying topologies into a common structure based on traffic movements. Next, we design a Universal Traffic Representation (UTR) module with a decoder-only network for general feature extraction, enhancing the model's adaptability to diverse traffic scenarios. Additionally, we incorporate an Intersection Specifics Representation (ISR) module, designed to identify key latent vectors that represent the unique intersection's topology and traffic dynamics through variational inference techniques. To further refine these latent representations, we employ a contrastive learning approach in a self-supervised manner, which enables better differentiation of intersection-specific features. Moreover, we integrate the state-action dependencies of neighboring agents into policy optimization, which effectively captures dynamic agent interactions and facilitates efficient regional collaboration. Our results show that Unicorn outperforms other methods across various evaluation metrics, highlighting its potential in complex, dynamic traffic networks.
Authors: Junwoo Park, Nataliya Sokolovska, Cl\'ement Cabriel, Ignacio Izeddin, Judith Min\'e-Hattab
Abstract: In recent years, the segmentation of short molecular trajectories with varying diffusive properties has drawn particular attention of researchers, since it allows studying the dynamics of a particle. In the past decade, machine learning methods have shown highly promising results, also in changepoint detection and segmentation tasks. Here, we introduce a novel iterative method to identify the changepoints in a molecular trajectory, i.e., frames, where the diffusive behavior of a particle changes. A trajectory in our case follows a fractional Brownian motion and we estimate the diffusive properties of the trajectories. The proposed BI-ADD combines unsupervised and supervised learning methods to detect the changepoints. Our approach can be used for the analysis of molecular trajectories at the individual level and also be extended to multiple particle tracking, which is an important challenge in fundamental biology. We validated BI-ADD in various scenarios within the framework of the AnDi2 Challenge 2024 dedicated to single particle tracking. Our method is implemented in Python and is publicly available for research purposes.
Authors: Joseph Zuber, Aishwarya Sarkar, Joseph Jennings, Ali Jannesari
Abstract: Graph Neural Networks (GNN) have demonstrated state-of-the-art performance in numerous scientific and high-performance computing (HPC) applications. Recent work suggests that "souping" (combining) individually trained GNNs into a single model can improve performance without increasing compute and memory costs during inference. However, existing souping algorithms are often slow and memory-intensive, which limits their scalability. We introduce Learned Souping for GNNs, a gradient-descent-based souping strategy that substantially reduces time and memory overhead compared to existing methods. Our approach is evaluated across multiple Open Graph Benchmark (OGB) datasets and GNN architectures, achieving up to 1.2% accuracy improvement and 2.1X speedup. Additionally, we propose Partition Learned Souping, a novel partition-based variant of learned souping that significantly reduces memory usage. On the ogbn-products dataset with GraphSAGE, partition learned souping achieves a 24.5X speedup and a 76% memory reduction without compromising accuracy.
Authors: Samuel Hurault, Matthieu Terris, Thomas Moreau, Gabriel Peyr\'e
Abstract: Sampling from an unknown distribution, accessible only through discrete samples, is a fundamental problem at the core of generative AI. The current state-of-the-art methods follow a two-step process: first estimating the score function (the gradient of a smoothed log-distribution) and then applying a gradient-based sampling algorithm. The resulting distribution's correctness can be impacted by several factors: the generalization error due to a finite number of initial samples, the error in score matching, and the diffusion error introduced by the sampling algorithm. In this paper, we analyze the sampling process in a simple yet representative setting-sampling from Gaussian distributions using a Langevin diffusion sampler. We provide a sharp analysis of the Wasserstein sampling error that arises from the multiple sources of error throughout the pipeline. This allows us to rigorously track how the anisotropy of the data distribution (encoded by its power spectrum) interacts with key parameters of the end-to-end sampling method, including the noise amplitude, the step sizes in both score matching and diffusion, and the number of initial samples. Notably, we show that the Wasserstein sampling error can be expressed as a kernel-type norm of the data power spectrum, where the specific kernel depends on the method parameters. This result provides a foundation for further analysis of the tradeoffs involved in optimizing sampling accuracy, such as adapting the noise amplitude to the choice of step sizes.
Authors: Simon Hofmann, Christoph Sommermann, Mathias Kraus, Patrick Zschech, Julian Rosenberger
Abstract: This study explores the prevalence of hate speech (HS) and sentiment in YouTube video comments concerning the Israel-Palestine conflict by analyzing content from both public and private news sources. The research involved annotating 4983 comments for HS and sentiments (neutral, pro-Israel, and pro-Palestine). Subsequently, machine learning (ML) models were developed, demonstrating robust predictive capabilities with area under the receiver operating characteristic (AUROC) scores ranging from 0.83 to 0.90. These models were applied to the extracted comment sections of YouTube videos from public and private sources, uncovering a higher incidence of HS in public sources (40.4%) compared to private sources (31.6%). Sentiment analysis revealed a predominantly neutral stance in both source types, with more pronounced sentiments towards Israel and Palestine observed in public sources. This investigation highlights the dynamic nature of online discourse surrounding the Israel-Palestine conflict and underscores the potential of moderating content in a politically charged environment.
Authors: Thomas Foltz
Abstract: This paper focuses on detecting anomalies in surveillance video using keywords by leveraging foundational models' feature representation generalization capabilities. We present a novel, lightweight pipeline for anomaly classification using keyword weights. Our pipeline employs a two-stage process: induction followed by deduction. In induction, descriptions are generated from normal and anomalous frames to identify and assign weights to relevant keywords. In deduction, inference frame descriptions are converted into keyword encodings using induction-derived weights for input into our neural network for anomaly classification. We achieved comparable performance on the three benchmarks UCSD Ped2, Shanghai Tech, and CUHK Avenue, with ROC AUC scores of 0.865, 0.745, and 0.742, respectively. These results are achieved without temporal context, making such a system viable for real-time applications. Our model improves implementation setup, interpretability, and inference speed for surveillance devices on the edge, introducing a performance trade-off against other video anomaly detection systems. As the generalization capabilities of open-source foundational models improve, our model demonstrates that the exclusive use of text for feature representations is a promising direction for efficient real-time interpretable video anomaly detection.
Authors: Ibrahim Al Azhar, Venkata Devesh Reddy, Hamed Alhoori, Akhil Pandey Akella
Abstract: The limitations sections of scientific articles play a crucial role in highlighting the boundaries and shortcomings of research, thereby guiding future studies and improving research methods. Analyzing these limitations benefits researchers, reviewers, funding agencies, and the broader academic community. We introduce LimTopic, a strategy where Topic generation in Limitation sections in scientific articles with Large Language Models (LLMs). Here, each topic contains the title and Topic Summary. This study focuses on effectively extracting and understanding these limitations through topic modeling and text summarization, utilizing the capabilities of LLMs. We extracted limitations from research articles and applied an LLM-based topic modeling integrated with the BERtopic approach to generate a title for each topic and Topic Sentences. To enhance comprehension and accessibility, we employed LLM-based text summarization to create concise and generalizable summaries for each topic Topic Sentences and produce a Topic Summary. Our experimentation involved prompt engineering, fine-tuning LLM and BERTopic, and integrating BERTopic with LLM to generate topics, titles, and a topic summary. We also experimented with various LLMs with BERTopic for topic modeling and various LLMs for text summarization tasks. Our results showed that the combination of BERTopic and GPT 4 performed the best in terms of silhouette and coherence scores in topic modeling, and the GPT4 summary outperformed other LLM tasks as a text summarizer.
Authors: Yang Xiao, Wang Lu, Jie Ji, Ruimeng Ye, Gen Li, Xiaolong Ma, Bo Hui
Abstract: The design of artificial neural networks (ANNs) is inspired by the structure of the human brain, and in turn, ANNs offer a potential means to interpret and understand brain signals. Existing methods primarily align brain signals with real-world signals using Mean Squared Error (MSE), which solely focuses on local point-wise alignment, and ignores global matching, leading to coarse interpretations and inaccuracies in brain signal decoding. In this paper, we address these issues through optimal transport (OT) and theoretically demonstrate why OT provides a more effective alignment strategy than MSE. Specifically, we construct a transport plan between brain voxel embeddings and image embeddings, enabling more precise matching. By controlling the amount of transport, we mitigate the influence of redundant information. We apply our alignment model directly to the Brain Captioning task by feeding brain siginals into a large language model (LLM) instead of images. Our approach achieves state-of-the-art performance across ten evaluation metrics, surpassing the previous best method by an average of 6.11\% in single-subject training and 3.81\% in cross-subject training. Additionally, we have uncovered several insightful conclusions that align with existing brain research. We unveil the redundancy and synergy of brain information processing through region masking and data dimensionality reduction visualization experiments. We believe our approach paves the way for a more precise understanding of brain signals in the future. The code is available soon.
Authors: Timo Aukusti Laine
Abstract: Large Language Models (LLMs) encode semantic relationships in high-dimensional vector embeddings. This paper explores the analogy between LLM embedding spaces and quantum mechanics, positing that LLMs operate within a quantized semantic space where words and phrases behave as quantum states. To capture nuanced semantic interference effects, we extend the standard real-valued embedding space to the complex domain, drawing parallels to the double-slit experiment. We introduce a "semantic wave function" to formalize this quantum-derived representation and utilize potential landscapes, such as the double-well potential, to model semantic ambiguity. Furthermore, we propose a complex-valued similarity measure that incorporates both magnitude and phase information, enabling a more sensitive comparison of semantic representations. We develop a path integral formalism, based on a nonlinear Schr\"odinger equation with a gauge field and Mexican hat potential, to model the dynamic evolution of LLM behavior. This interdisciplinary approach offers a new theoretical framework for understanding and potentially manipulating LLMs, with the goal of advancing both artificial and natural language understanding.
Authors: Nitesh Patnaik, Navdeep Nayak, Himani Bansal Agrawal, Moinak Chinmoy Khamaru, Gourav Bal, Saishree Smaranika Panda, Rishi Raj, Vishal Meena, Kartheek Vadlamani
Abstract: The emergence of small vision-language models (sVLMs) marks a critical advancement in multimodal AI, enabling efficient processing of visual and textual data in resource-constrained environments. This survey offers a comprehensive exploration of sVLM development, presenting a taxonomy of architectures - transformer-based, mamba-based, and hybrid - that highlight innovations in compact design and computational efficiency. Techniques such as knowledge distillation, lightweight attention mechanisms, and modality pre-fusion are discussed as enablers of high performance with reduced resource requirements. Through an in-depth analysis of models like TinyGPT-V, MiniGPT-4, and VL-Mamba, we identify trade-offs between accuracy, efficiency, and scalability. Persistent challenges, including data biases and generalization to complex tasks, are critically examined, with proposed pathways for addressing them. By consolidating advancements in sVLMs, this work underscores their transformative potential for accessible AI, setting a foundation for future research into efficient multimodal systems.
Authors: Marta Adamska, Daria Smirnova, Hamid Nasiri, Zhengxin Yu, Peter Garraghan
Abstract: Large Language Models (LLMs) have become widely used across various domains spanning search engines, code generation, and text creation. However, a major concern associated with their adoption is the high cost of inference, impacting both their sustainability and financial feasibility. In this study, we empirically study how different prompt and response characteristics directly impact LLM inference energy cost. We conduct experiments leveraging three open-source transformer-based LLMs across three task types$-$question answering, sentiment analysis, and text generation. For each inference, we analyzed prompt and response characteristics (length, semantic meaning, time taken, energy consumption). Our results demonstrate that even when presented with identical tasks, models generate responses with varying characteristics and subsequently exhibit distinct energy consumption patterns. We found that prompt length is less significant than the semantic meaning of the task itself. In addition, we identified specific keywords associated with higher or lower energy usage that vary between associated tasks. These findings highlight the importance of prompt design in optimizing inference efficiency. We conclude that the semantic meaning of prompts and certain task-related keywords significantly impact inference costs, leading the way for deeper exploration towards creating energy-adaptive LLMs.
Authors: Swati Rallapalli, Shannon Gallagher, Andrew O. Mellinger, Jasmine Ratchford, Anusha Sinha, Tyler Brooks, William R. Nichols, Nick Winski, Bryan Brown
Abstract: We study the efficacy of fine-tuning Large Language Models (LLMs) for the specific task of report (government archives, news, intelligence reports) summarization. While this topic is being very actively researched - our specific application set-up faces two challenges: (i) ground-truth summaries maybe unavailable (e.g., for government archives), and (ii) availability of limited compute power - the sensitive nature of the application requires that computation is performed on-premise and for most of our experiments we use one or two A100 GPU cards. Under this set-up we conduct experiments to answer the following questions. First, given that fine-tuning the LLMs can be resource intensive, is it feasible to fine-tune them for improved report summarization capabilities on-premise? Second, what are the metrics we could leverage to assess the quality of these summaries? We conduct experiments on two different fine-tuning approaches in parallel and our findings reveal interesting trends regarding the utility of fine-tuning LLMs. Specifically, we find that in many cases, fine-tuning helps improve summary quality and in other cases it helps by reducing the number of invalid or garbage summaries.
Authors: Zak Buzzard
Abstract: Diffusion models have seen immense success in modelling continuous data across a range of domains such as vision and audio. Despite the challenges of adapting diffusion models to discrete data, recent work explores their application to text generation by working in the continuous embedding space. However, these models lack a natural means to control the inherent trade-off between quality and diversity as afforded by the temperature hyperparameter in autoregressive models, hindering understanding of model performance and restricting generation quality. This work proposes the use of classifier-free guidance and stochastic clamping for manipulating the quality-diversity trade-off on sequence-to-sequence tasks, demonstrating that these techniques may be used to improve the performance of a diffusion language model.
Authors: Anzhe Cheng, Chenzhong Yin, Yu Chang, Heng Ping, Shixuan Li, Shahin Nazarian, Paul Bogdan
Abstract: Low-resolution image segmentation is crucial in real-world applications such as robotics, augmented reality, and large-scale scene understanding, where high-resolution data is often unavailable due to computational constraints. To address this challenge, we propose MaskAttn-UNet, a novel segmentation framework that enhances the traditional U-Net architecture via a mask attention mechanism. Our model selectively emphasizes important regions while suppressing irrelevant backgrounds, thereby improving segmentation accuracy in cluttered and complex scenes. Unlike conventional U-Net variants, MaskAttn-UNet effectively balances local feature extraction with broader contextual awareness, making it particularly well-suited for low-resolution inputs. We evaluate our approach on three benchmark datasets with input images rescaled to 128x128 and demonstrate competitive performance across semantic, instance, and panoptic segmentation tasks. Our results show that MaskAttn-UNet achieves accuracy comparable to state-of-the-art methods at significantly lower computational cost than transformer-based models, making it an efficient and scalable solution for low-resolution segmentation in resource-constrained scenarios.
Authors: Fan Lyu, Tianle Liu, Zhang Zhang, Fuyuan Hu, Liang Wang
Abstract: We introduce Test-Time Discovery (TTD) as a novel task that addresses class shifts during testing, requiring models to simultaneously identify emerging categories while preserving previously learned ones. A key challenge in TTD is distinguishing newly discovered classes from those already identified. To address this, we propose a training-free, hash-based memory mechanism that enhances class discovery through fine-grained comparisons with past test samples. Leveraging the characteristics of unknown classes, our approach introduces hash representation based on feature scale and directions, utilizing Locality-Sensitive Hashing (LSH) for efficient grouping of similar samples. This enables test samples to be easily and quickly compared with relevant past instances. Furthermore, we design a collaborative classification strategy, combining a prototype classifier for known classes with an LSH-based classifier for novel ones. To enhance reliability, we incorporate a self-correction mechanism that refines memory labels through hash-based neighbor retrieval, ensuring more stable and accurate class assignments. Experimental results demonstrate that our method achieves good discovery of novel categories while maintaining performance on known classes, establishing a new paradigm in model testing. Our code is available at https://github.com/fanlyu/ttd.
Authors: Bikram Das, Rupchand Sutradhar, D C Dalal
Abstract: In this work, we introduce Virology-Informed Neural Networks (VINNs), a powerful tool for capturing the intricate dynamics of viral infection when data of some compartments of the model are not available. VINNs, an extension of the widely known Physics-Informed Neural Networks (PINNs), offer an alternative approach to traditional numerical methods for solving system of differential equations. We apply this VINN technique on a recently proposed hepatitis B virus (HBV) infection dynamics model to predict the transmission of the infection within the liver more accurately. This model consists of four compartments, namely uninfected and infected hepatocytes, rcDNA-containing capsids, and free viruses, along with the consideration of capsid recycling. Leveraging the power of VINNs, we study the impacts of variations in parameter range, experimental noise, data variability, network architecture, and learning rate in this work. In order to demonstrate the robustness and effectiveness of VINNs, we employ this approach on the data collected from nine HBV-infceted chimpanzees, and it is observed that VINNs can effectively estimate the model parameters. VINNs reliably capture the dynamics of infection spread and accurately predict their future progression using real-world data. Furthermore, VINNs efficiently identify the most influential parameters in HBV dynamics based solely on experimental data from the capsid component. It is also expected that this framework can be extended beyond viral dynamics, providing a powerful tool for uncovering hidden patterns and complex interactions across various scientific and engineering domains.
Authors: Yafei Zhang, Murray Wang, Yu Wang, Xiaohui Wang
Abstract: Matching job descriptions (JDs) with suitable talent requires models capable of understanding not only textual similarities between JDs and candidate resumes but also contextual factors such as geographical location and academic seniority. To address this challenge, we propose a two-stage training framework for large language models (LLMs). In the first stage, a contrastive learning approach is used to train the model on a dataset constructed from real-world matching rules, such as geographical alignment and research area overlap. While effective, this model primarily learns patterns that defined by the matching rules. In the second stage, we introduce a novel preference-based fine-tuning method inspired by Direct Preference Optimization (DPO), termed Rank Preference Optimization (RankPO), to align the model with AI-curated pairwise preferences emphasizing textual understanding. Our experiments show that while the first-stage model achieves strong performance on rule-based data (nDCG@20 = 0.706), it lacks robust textual understanding (alignment with AI annotations = 0.46). By fine-tuning with RankPO, we achieve a balanced model that retains relatively good performance in the original tasks while significantly improving the alignment with AI preferences. The code and data are available at https://github.com/yflyzhang/RankPO.
Authors: Mohammad Mosaffa, Omid Rafieian, Hema Yoganarasimhan
Abstract: Political polarization is a significant issue in American politics, influencing public discourse, policy, and consumer behavior. While studies on polarization in news media have extensively focused on verbal content, non-verbal elements, particularly visual content, have received less attention due to the complexity and high dimensionality of image data. Traditional descriptive approaches often rely on feature extraction from images, leading to biased polarization estimates due to information loss. In this paper, we introduce the Polarization Measurement using Counterfactual Image Generation (PMCIG) method, which combines economic theory with generative models and multi-modal deep learning to fully utilize the richness of image data and provide a theoretically grounded measure of polarization in visual content. Applying this framework to a decade-long dataset featuring 30 prominent politicians across 20 major news outlets, we identify significant polarization in visual content, with notable variations across outlets and politicians. At the news outlet level, we observe significant heterogeneity in visual slant. Outlets such as Daily Mail, Fox News, and Newsmax tend to favor Republican politicians in their visual content, while The Washington Post, USA Today, and The New York Times exhibit a slant in favor of Democratic politicians. At the politician level, our results reveal substantial variation in polarized coverage, with Donald Trump and Barack Obama among the most polarizing figures, while Joe Manchin and Susan Collins are among the least. Finally, we conduct a series of validation tests demonstrating the consistency of our proposed measures with external measures of media slant that rely on non-image-based sources.
Authors: Qi Lv, Hao Li, Xiang Deng, Rui Shao, Yinchuan Li, Jianye Hao, Longxiang Gao, Michael Yu Wang, Liqiang Nie
Abstract: Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a policy to predict a distant next-best end-effector pose (NBP) and then compute the corresponding joint rotation angles for motion using inverse kinematics. However, they suffer from two important issues: (1) rarely considering the physical robotic structure, which may cause self-collisions or interferences, and (2) overlooking the kinematics constraint, which may result in the predicted poses not conforming to the actual limitations of the robot joints. In this paper, we propose Kinematics enhanced Spatial-TemporAl gRaph Diffuser (KStar Diffuser). Specifically, (1) to incorporate the physical robot structure information into action prediction, KStar Diffuser maintains a dynamic spatial-temporal graph according to the physical bimanual joint motions at continuous timesteps. This dynamic graph serves as the robot-structure condition for denoising the actions; (2) to make the NBP learning objective consistent with kinematics, we introduce the differentiable kinematics to provide the reference for optimizing KStar Diffuser. This module regularizes the policy to predict more reliable and kinematics-aware next end-effector poses. Experimental results show that our method effectively leverages the physical structural information and generates kinematics-aware actions in both simulation and real-world
Authors: Yingqi Gao, Jin Zhou, Hua Zhou, Yong Chen, Xiaowu Dai
Abstract: As data marketplaces become increasingly central to the digital economy, it is crucial to design efficient pricing mechanisms that optimize revenue while ensuring fair and adaptive pricing. We introduce the Maximum Auction-to-Posted Price (MAPP) mechanism, a novel two-stage approach that first estimates the bidders' value distribution through auctions and then determines the optimal posted price based on the learned distribution. We establish that MAPP is individually rational and incentive-compatible, ensuring truthful bidding while balancing revenue maximization with minimal price discrimination. MAPP achieves a regret of $O_p(n^{-1})$ when incorporating historical bid data, where $n$ is the number of bids in the current round. It outperforms existing methods while imposing weaker distributional assumptions. For sequential dataset sales over $T$ rounds, we propose an online MAPP mechanism that dynamically adjusts pricing across datasets with varying value distributions. Our approach achieves no-regret learning, with the average cumulative regret converging at a rate of $O_p(T^{-1/2}(\log T)^2)$. We validate the effectiveness of MAPP through simulations and real-world data from the FCC AWS-3 spectrum auction.
Authors: Lukas Aichberger, Alasdair Paren, Yarin Gal, Philip Torr, Adel Bibi
Abstract: Recent advances in operating system (OS) agents enable vision-language models to interact directly with the graphical user interface of an OS. These multimodal OS agents autonomously perform computer-based tasks in response to a single prompt via application programming interfaces (APIs). Such APIs typically support low-level operations, including mouse clicks, keyboard inputs, and screenshot captures. We introduce a novel attack vector: malicious image patches (MIPs) that have been adversarially perturbed so that, when captured in a screenshot, they cause an OS agent to perform harmful actions by exploiting specific APIs. For instance, MIPs embedded in desktop backgrounds or shared on social media can redirect an agent to a malicious website, enabling further exploitation. These MIPs generalise across different user requests and screen layouts, and remain effective for multiple OS agents. The existence of such attacks highlights critical security vulnerabilities in OS agents, which should be carefully addressed before their widespread adoption.
Authors: Xiusi Li, S\'ekou-Oumar Kaba, Siamak Ravanbakhsh
Abstract: Causal representation learning (CRL) enhances machine learning models' robustness and generalizability by learning structural causal models associated with data-generating processes. We focus on a family of CRL methods that uses contrastive data pairs in the observable space, generated before and after a random, unknown intervention, to identify the latent causal model. (Brehmer et al., 2022) showed that this is indeed possible, given that all latent variables can be intervened on individually. However, this is a highly restrictive assumption in many systems. In this work, we instead assume interventions on arbitrary subsets of latent variables, which is more realistic. We introduce a theoretical framework that calculates the degree to which we can identify a causal model, given a set of possible interventions, up to an abstraction that describes the system at a higher level of granularity.
Authors: Kevin Li, Eric Laber
Abstract: The contextual bandit framework is widely used to solve sequential optimization problems where the reward of each decision depends on auxiliary context variables. In settings such as medicine, business, and engineering, the decision maker often possesses additional structural information on the generative model that can potentially be used to improve the efficiency of bandit algorithms. We consider settings in which the mean reward is known to be a concave function of the action for each fixed context. Examples include patient-specific dose-response curves in medicine and expected profit in online advertising auctions. We propose a contextual bandit algorithm that accelerates optimization by conditioning the posterior of a Bayesian Gaussian Process model on this concavity information. We design a novel shape-constrained reward function estimator using a specially chosen regression spline basis and constrained Gaussian Process posterior. Using this model, we propose a UCB algorithm and derive corresponding regret bounds. We evaluate our algorithm on numerical examples and test functions used to study optimal dosing of Anti-Clotting medication.
Authors: Nawaf Alampara, Mara Schilling-Wilhelmi, Kevin Maik Jablonka
Abstract: Measurements are fundamental to knowledge creation in science, enabling consistent sharing of findings and serving as the foundation for scientific discovery. As machine learning systems increasingly transform scientific fields, the question of how to effectively evaluate these systems becomes crucial for ensuring reliable progress. In this review, we examine the current state and future directions of evaluation frameworks for machine learning in science. We organize the review around a broadly applicable framework for evaluating machine learning systems through the lens of statistical measurement theory, using materials science as our primary context for examples and case studies. We identify key challenges common across machine learning evaluation such as construct validity, data quality issues, metric design limitations, and benchmark maintenance problems that can lead to phantom progress when evaluation frameworks fail to capture real-world performance needs. By examining both traditional benchmarks and emerging evaluation approaches, we demonstrate how evaluation choices fundamentally shape not only our measurements but also research priorities and scientific progress. These findings reveal the critical need for transparency in evaluation design and reporting, leading us to propose evaluation cards as a structured approach to documenting measurement choices and limitations. Our work highlights the importance of developing a more diverse toolbox of evaluation techniques for machine learning in materials science, while offering insights that can inform evaluation practices in other scientific domains where similar challenges exist.
Authors: Yuhao Zhang, Xiangru Xu
Abstract: Feedforward neural networks are widely used in autonomous systems, particularly for control and perception tasks within the system loop. However, their vulnerability to adversarial attacks necessitates formal verification before deployment in safety-critical applications. Existing set propagation-based reachability analysis methods for feedforward neural networks often struggle to achieve both scalability and accuracy. This work presents a novel set-based approach for computing the reachable sets of convolutional neural networks. The proposed method leverages a hybrid zonotope representation and an efficient neural network reduction technique, providing a flexible trade-off between computational complexity and approximation accuracy. Numerical examples are presented to demonstrate the effectiveness of the proposed approach.
Authors: Pedro Pessoa, Paul Campitelli, Douglas P. Shepherd, S. Banu Ozkan, Steve Press\'e
Abstract: State space models, such as Mamba, have recently garnered attention in time series forecasting due to their ability to capture sequence patterns. However, in electricity consumption benchmarks, Mamba forecasts exhibit a mean error of approximately 8\%. Similarly, in traffic occupancy benchmarks, the mean error reaches 18\%. This discrepancy leaves us to wonder whether the prediction is simply inaccurate or falls within error given spread in historical data. To address this limitation, we propose a method to quantify the predictive uncertainty of Mamba forecasts. Here, we propose a dual-network framework based on the Mamba architecture for probabilistic forecasting, where one network generates point forecasts while the other estimates predictive uncertainty by modeling variance. We abbreviate our tool, Mamba with probabilistic time series forecasting, as Mamba-ProbTSF and the code for its implementation is available on GitHub (https://github.com/PessoaP/Mamba-ProbTSF). Evaluating this approach on synthetic and real-world benchmark datasets, we find Kullback-Leibler divergence between the learned distributions and the data--which, in the limit of infinite data, should converge to zero if the model correctly captures the underlying probability distribution--reduced to the order of $10^{-3}$ for synthetic data and $10^{-1}$ for real-world benchmark, demonstrating its effectiveness. We find that in both the electricity consumption and traffic occupancy benchmark, the true trajectory stays within the predicted uncertainty interval at the two-sigma level about 95\% of the time. We end with a consideration of potential limitations, adjustments to improve performance, and considerations for applying this framework to processes for purely or largely stochastic dynamics where the stochastic changes accumulate, as observed for example in pure Brownian motion or molecular dynamics trajectories.
Authors: Hai-Vy Nguyen, Fabrice Gamboa, Sixin Zhang, Reda Chhaibi, Serge Gratton, Thierry Giaccone
Abstract: In this paper, we introduce a novel spatial attention module, that can be integrated to any convolutional network. This module guides the model to pay attention to the most discriminative part of an image. This enables the model to attain a better performance by an end-to-end training. In standard approaches, a spatial attention map is generated in a position-wise fashion. We observe that this results in very irregular boundaries. This could make it difficult to generalize to new samples. In our method, the attention region is constrained to be rectangular. This rectangle is parametrized by only 5 parameters, allowing for a better stability and generalization to new samples. In our experiments, our method systematically outperforms the position-wise counterpart. Thus, this provides us a novel useful spatial attention mechanism for convolutional models. Besides, our module also provides the interpretability concerning the ``where to look" question, as it helps to know the part of the input on which the model focuses to produce the prediction.
Authors: Nathaniel Lesperance, Sujeevan Ratnasingham, Graham W. Taylor
Abstract: In the context of pressing climate change challenges and the significant biodiversity loss among arthropods, automated taxonomic classification from organismal images is a subject of intense research. However, traditional AI pipelines based on deep neural visual architectures such as CNNs or ViTs face limitations such as degraded performance on the long-tail of classes and the inability to reason about their predictions. We integrate image captioning and retrieval-augmented generation (RAG) with large language models (LLMs) to enhance biodiversity monitoring, showing particular promise for characterizing rare and unknown arthropod species. While a naive Vision-Language Model (VLM) excels in classifying images of common species, the RAG model enables classification of rarer taxa by matching explicit textual descriptions of taxonomic features to contextual biodiversity text data from external sources. The RAG model shows promise in reducing overconfidence and enhancing accuracy relative to naive LLMs, suggesting its viability in capturing the nuances of taxonomic hierarchy, particularly at the challenging family and genus levels. Our findings highlight the potential for modern vision-language AI pipelines to support biodiversity conservation initiatives, emphasizing the role of comprehensive data curation and collaboration with citizen science platforms to improve species identification, unknown species characterization and ultimately inform conservation strategies.
Authors: Jiuding Sun, Jing Huang, Sidharth Baskaran, Karel D'Oosterlinck, Christopher Potts, Michael Sklar, Atticus Geiger
Abstract: Mechanistic interpretability has made great strides in identifying neural network features (e.g., directions in hidden activation space) that mediate concepts(e.g., the birth year of a person) and enable predictable manipulation. Distributed alignment search (DAS) leverages supervision from counterfactual data to learn concept features within hidden states, but DAS assumes we can afford to conduct a brute force search over potential feature locations. To address this, we present HyperDAS, a transformer-based hypernetwork architecture that (1) automatically locates the token-positions of the residual stream that a concept is realized in and (2) constructs features of those residual stream vectors for the concept. In experiments with Llama3-8B, HyperDAS achieves state-of-the-art performance on the RAVEL benchmark for disentangling concepts in hidden states. In addition, we review the design decisions we made to mitigate the concern that HyperDAS (like all powerful interpretabilty methods) might inject new information into the target model rather than faithfully interpreting it.
Authors: Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee, Saurabh Bagchi, Somali Chaterji, Yingyu Liang, Yin Li
Abstract: Multimodal Large Language Models (MLLMs) have shown impressive capabilities in reasoning, yet come with substantial computational cost, limiting their deployment in resource-constrained settings. Despite recent efforts on improving the efficiency of MLLMs, prior solutions fall short in responding to varying runtime conditions, in particular changing resource availability (e.g., contention due to the execution of other programs on the device). To bridge this gap, we introduce AdaLLaVA, an adaptive inference framework that learns to dynamically reconfigure operations in an MLLM during inference, accounting for the input data and a latency budget. We conduct extensive experiments across benchmarks involving question-answering, reasoning, and hallucination. Our results show that AdaLLaVA effectively adheres to input latency budget, achieving varying accuracy and latency tradeoffs at runtime. Further, we demonstrate that AdaLLaVA adapts to both input latency and content, can be integrated with token selection for enhanced efficiency, and generalizes across MLLMs.Our project webpage with code release is at https://zhuoyan-xu.github.io/ada-llava/.
Authors: Abeda Sultana, Nabin Pakka, Fei Xu, Xu Yuan, Li Chen, Nian-Feng Tzeng
Abstract: Scheduling deep learning (DL) models to train on powerful clusters with accelerators like GPUs and TPUs, presently falls short, either lacking fine-grained heterogeneity awareness or leaving resources substantially under-utilized. To fill this gap, we propose a novel design of a task-level heterogeneity-aware scheduler, {\em Hadar}, based on an optimization framework that can boost resource utilization. {\em Hadar} leverages the performance traits of DL jobs on a heterogeneous DL cluster, characterizes the task-level performance heterogeneity in the optimization problem, and makes scheduling decisions across both spatial and temporal dimensions. %with the objective to reduce the average job completion time of DL jobs. It involves the primal-dual framework employing a dual subroutine, to solve the optimization problem and guide the scheduling design. Our trace-driven simulation with representative DL model training workloads demonstrates that {\em Hadar} accelerates the total time duration by 1.20$\times$ when compared with its state-of-the-art heterogeneity-aware counterpart, Gavel. Further, our {\em Hadar} scheduler is enhanced to {\em HadarE} by forking each job into multiple copies to let a job train concurrently on heterogeneous GPUs resided on separate available nodes (i.e., machines or servers) for resource utilization enhancement. {\em HadarE} is evaluated extensively on physical DL clusters for comparison with {\em Hadar} and Gavel. With substantial enhancement in cluster resource utilization (by 1.45$\times$), {\em HadarE} exhibits considerable speed-ups in DL model training, reducing the total time duration by 50\% (or 80\%) on an Amazon's AWS (or our lab) cluster, while producing trained DL models with consistently better inference quality than those trained by \textit{Hadar}.
Authors: Haoyu Zhang, Raghavendra Ramachandra, Kiran Raja, Christoph Busch
Abstract: Face Recognition Systems (FRS) are increasingly vulnerable to face-morphing attacks, prompting the development of Morphing Attack Detection (MAD) algorithms. However, a key challenge in MAD lies in its limited generalizability to unseen data and its lack of explainability-critical for practical application environments such as enrolment stations and automated border control systems. Recognizing that most existing MAD algorithms rely on supervised learning paradigms, this work explores a novel approach to MAD using zero-shot learning leveraged on Large Language Models (LLMs). We propose two types of zero-shot MAD algorithms: one leveraging general vision models and the other utilizing multimodal LLMs. For general vision models, we address the MAD task by computing the mean support embedding of an independent support set without using morphed images. For the LLM-based approach, we employ the state-of-the-art GPT-4 Turbo API with carefully crafted prompts. To evaluate the feasibility of zero-shot MAD and the effectiveness of the proposed methods, we constructed a print-scan morph dataset featuring various unseen morphing algorithms, simulating challenging real-world application scenarios. Experimental results demonstrated notable detection accuracy, validating the applicability of zero-shot learning for MAD tasks. Additionally, our investigation into LLM-based MAD revealed that multimodal LLMs, such as ChatGPT, exhibit remarkable generalizability to untrained MAD tasks. Furthermore, they possess a unique ability to provide explanations and guidance, which can enhance transparency and usability for end-users in practical applications.
Authors: Piyush Gupta, Sangjae Bae, David Isele
Abstract: The adoption of Large Language Models (LLMs) is rapidly expanding across various tasks that involve inherent graphical structures. Graphs are integral to a wide range of applications, including motion planning for autonomous vehicles, social networks, scene understanding, and knowledge graphs. Many problems, even those not initially perceived as graph-based, can be effectively addressed through graph theory. However, when applied to these tasks, LLMs often encounter challenges, such as hallucinations and mathematical inaccuracies. To overcome these limitations, we propose Graph-Grounded LLMs, a system that improves LLM performance on graph-related tasks by integrating a graph library through function calls. By grounding LLMs in this manner, we demonstrate significant reductions in hallucinations and improved mathematical accuracy in solving graph-based problems, as evidenced by the performance on the NLGraph benchmark. Finally, we showcase a disaster rescue application where the Graph-Grounded LLM acts as a decision-support system.
Authors: SE Blake
Abstract: Phishing is a persistent cybersecurity threat in today's digital landscape. This paper introduces Phishsense-1B, a refined version of the Llama-Guard-3-1B model, specifically tailored for phishing detection and reasoning. This adaptation utilizes Low-Rank Adaptation (LoRA) and the GuardReasoner finetuning methodology. We outline our LoRA-based fine-tuning process, describe the balanced dataset comprising phishing and benign emails, and highlight significant performance improvements over the original model. Our findings indicate that Phishsense-1B achieves an impressive 97.5% accuracy on a custom dataset and maintains strong performance with 70% accuracy on a challenging real-world dataset. This performance notably surpasses both unadapted models and BERT-based detectors. Additionally, we examine current state-of-the-art detection methods, compare prompt-engineering with fine-tuning strategies, and explore potential deployment scenarios.
Authors: Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra-Sharma, Daniel Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R. Bowman, Shan Carter, Brian Chen, Hoagy Cunningham, Carson Denison, Florian Dietz, Satvik Golechha, Akbir Khan, Jan Kirchner, Jan Leike, Austin Meek, Kei Nishimura-Gasparian, Euan Ong, Christopher Olah, Adam Pearce, Fabien Roger, Jeanne Salle, Andy Shih, Meg Tong, Drake Thomas, Kelley Rivoire, Adam Jermyn, Monte MacDiarmid, Tom Henighan, Evan Hubinger
Abstract: We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objective. Our training pipeline first teaches the model about exploitable errors in RLHF reward models (RMs), then trains the model to exploit some of these errors. We verify via out-of-distribution evaluations that the model generalizes to exhibit whatever behaviors it believes RMs rate highly, including ones not reinforced during training. We leverage this model to study alignment audits in two ways. First, we conduct a blind auditing game where four teams, unaware of the model's hidden objective or training, investigate it for concerning behaviors and their causes. Three teams successfully uncovered the model's hidden objective using techniques including interpretability with sparse autoencoders (SAEs), behavioral attacks, and training data analysis. Second, we conduct an unblinded follow-up study of eight techniques for auditing the model, analyzing their strengths and limitations. Overall, our work provides a concrete example of using alignment audits to discover a model's hidden objective and proposes a methodology for practicing and validating progress in alignment auditing.
Authors: Camilo Chac\'on Sartori, Christian Blum
Abstract: Large Language Models (LLMs) have shown notable potential in code generation for optimization algorithms, unlocking exciting new opportunities. This paper examines how LLMs, rather than creating algorithms from scratch, can improve existing ones without the need for specialized expertise. To explore this potential, we selected 10 baseline optimization algorithms from various domains (metaheuristics, reinforcement learning, deterministic, and exact methods) to solve the classic Travelling Salesman Problem. The results show that our simple methodology often results in LLM-generated algorithm variants that improve over the baseline algorithms in terms of solution quality, reduction in computational time, and simplification of code complexity, all without requiring specialized optimization knowledge or advanced algorithmic implementation skills.
Authors: Shanghua Gao, Richard Zhu, Zhenglun Kong, Ayush Noori, Xiaorui Su, Curtis Ginder, Theodoros Tsiligkaridis, Marinka Zitnik
Abstract: Precision therapeutics require multimodal adaptive models that generate personalized treatment recommendations. We introduce TxAgent, an AI agent that leverages multi-step reasoning and real-time biomedical knowledge retrieval across a toolbox of 211 tools to analyze drug interactions, contraindications, and patient-specific treatment strategies. TxAgent evaluates how drugs interact at molecular, pharmacokinetic, and clinical levels, identifies contraindications based on patient comorbidities and concurrent medications, and tailors treatment strategies to individual patient characteristics. It retrieves and synthesizes evidence from multiple biomedical sources, assesses interactions between drugs and patient conditions, and refines treatment recommendations through iterative reasoning. It selects tools based on task objectives and executes structured function calls to solve therapeutic tasks that require clinical reasoning and cross-source validation. The ToolUniverse consolidates 211 tools from trusted sources, including all US FDA-approved drugs since 1939 and validated clinical insights from Open Targets. TxAgent outperforms leading LLMs, tool-use models, and reasoning agents across five new benchmarks: DrugPC, BrandPC, GenericPC, TreatmentPC, and DescriptionPC, covering 3,168 drug reasoning tasks and 456 personalized treatment scenarios. It achieves 92.1% accuracy in open-ended drug reasoning tasks, surpassing GPT-4o and outperforming DeepSeek-R1 (671B) in structured multi-step reasoning. TxAgent generalizes across drug name variants and descriptions. By integrating multi-step inference, real-time knowledge grounding, and tool-assisted decision-making, TxAgent ensures that treatment recommendations align with established clinical guidelines and real-world evidence, reducing the risk of adverse events and improving therapeutic decision-making.
Authors: Kaizhao Liu, Qi Long, Zhekun Shi, Weijie J. Su, Jiancong Xiao
Abstract: Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental statistical limits concerning aligning LLMs with human preferences, with a focus on the probabilistic representation of human preferences and the preservation of diverse preferences in aligned LLMs. We first show that human preferences can be represented by a reward model if and only if the preference among LLM-generated responses is free of any Condorcet cycle. Moreover, we prove that Condorcet cycles exist with probability converging to one exponentially fast under a probabilistic preference model, thereby demonstrating the impossibility of fully aligning human preferences using reward-based approaches such as reinforcement learning from human feedback. Next, we explore the conditions under which LLMs would employ mixed strategies -- meaning they do not collapse to a single response -- when aligned in the limit using a non-reward-based approach, such as Nash learning from human feedback (NLHF). We identify a necessary and sufficient condition for mixed strategies: the absence of a response that is preferred over all others by a majority. As a blessing, we prove that this condition holds with high probability under the probabilistic preference model, thereby highlighting the statistical possibility of preserving minority preferences without explicit regularization in aligning LLMs. Finally, we leverage insights from our statistical results to design a novel, computationally efficient algorithm for finding Nash equilibria in aligning LLMs with NLHF. Our experiments show that Llama-3.2-1B, aligned with our algorithm, achieves a win rate of 60.55\% against the base model.
Authors: Gaotang Li, Yuzhong Chen, Hanghang Tong
Abstract: Language Models (LMs) often encounter knowledge conflicts when parametric memory contradicts contextual knowledge. Previous works attribute this conflict to the interplay between "memory heads" and "context heads", attention heads assumed to promote either memory or context exclusively. In this study, we go beyond this fundamental assumption by uncovering a critical phenomenon we term the "superposition of contextual information and parametric memory", where highly influential attention heads could simultaneously contribute to both memory and context. Building upon this insight, we propose Just Run Twice (JUICE), a test-time attention intervention method that steers LMs toward either parametric beliefs or contextual knowledge without requiring fine-tuning. JUICE identifies a set of reliable attention heads and leverages a dual-run approach to mitigate the superposition effects. Extensive experiments across 11 datasets and 6 model architectures demonstrate that JUICE sets the new state-of-the-art performance and robust generalization, achieving significant and consistent improvement across different domains under various conflict types. Finally, we theoretically analyze knowledge conflict and the superposition of contextual information and parametric memory in attention heads, which further elucidates the effectiveness of JUICE in these settings.
Authors: Erfaun Noorani, Zachary Serlin, Ben Price, Alvaro Velasquez
Abstract: The DARPA Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) program aims to address rapid and robust transfer of autonomy technologies across dynamic and complex environments, goals, and platforms. Existing methods for simulation-to-reality (sim-to-real) transfer often rely on high-fidelity simulations and struggle with broad adaptation, particularly in time-sensitive scenarios. Although many approaches have shown incredible performance at specific tasks, most techniques fall short when posed with unforeseen, complex, and dynamic real-world scenarios due to the inherent limitations of simulation. In contrast to current research that aims to bridge the gap between simulation environments and the real world through increasingly sophisticated simulations and a combination of methods typically assuming a small sim-to-real gap -- such as domain randomization, domain adaptation, imitation learning, meta-learning, policy distillation, and dynamic optimization -- TIAMAT takes a different approach by instead emphasizing transfer and adaptation of the autonomy stack directly to real-world environments by utilizing a breadth of low(er)-fidelity simulations to create broadly effective sim-to-real transfers. By abstractly learning from multiple simulation environments in reference to their shared semantics, TIAMAT's approaches aim to achieve abstract-to-real transfer for effective and rapid real-world adaptation. Furthermore, this program endeavors to improve the overall autonomy pipeline by addressing the inherent challenges in translating simulated behaviors into effective real-world performance.
Authors: Jiaqi Jin, Siwei Wang, Zhibin Dong, Xihong Yang, Xinwang Liu, En Zhu, Kunlun He
Abstract: Multi-view clustering leverages complementary representations from diverse sources to enhance performance. However, real-world data often suffer incomplete cases due to factors like privacy concerns and device malfunctions. A key challenge is effectively utilizing available instances to recover missing views. Existing methods frequently overlook the heterogeneity among views during recovery, leading to significant distribution discrepancies between recovered and true data. Additionally, many approaches focus on cross-view correlations, neglecting insights from intra-view reliable structure and cross-view clustering structure. To address these issues, we propose BURG, a novel method for incomplete multi-view clustering with distriBution dUal-consistency Recovery Guidance. We treat each sample as a distinct category and perform cross-view distribution transfer to predict the distribution space of missing views. To compensate for the lack of reliable category information, we design a dual-consistency guided recovery strategy that includes intra-view alignment guided by neighbor-aware consistency and cross-view alignment guided by prototypical consistency. Extensive experiments on benchmarks demonstrate the superiority of BURG in the incomplete multi-view scenario.
Authors: Sungwoo Cho, Jeongsoo Choi, Sungnyun Kim, Se-Young Yun
Abstract: Despite recent advances in text-to-speech (TTS) models, audio-visual to audio-visual (AV2AV) translation still faces a critical challenge: maintaining speaker consistency between the original and translated vocal and facial features. To address this issue, we propose a conditional flow matching (CFM) zero-shot audio-visual renderer that utilizes strong dual guidance from both audio and visual modalities. By leveraging multi-modal guidance with CFM, our model robustly preserves speaker-specific characteristics and significantly enhances zero-shot AV2AV translation abilities. For the audio modality, we enhance the CFM process by integrating robust speaker embeddings with x-vectors, which serve to bolster speaker consistency. Additionally, we convey emotional nuances to the face rendering module. The guidance provided by both audio and visual cues remains independent of semantic or linguistic content, allowing our renderer to effectively handle zero-shot translation tasks for monolingual speakers in different languages. We empirically demonstrate that the inclusion of high-quality mel-spectrograms conditioned on facial information not only enhances the quality of the synthesized speech but also positively influences facial generation, leading to overall performance improvements.
Authors: Worameth Chinchuthakun, Tossaporn Saengja, Nontawat Tritrong, Pitchaporn Rewatbowornwong, Pramook Khungurn, Supasorn Suwajanakorn
Abstract: While diffusion models show promising results in image editing given a target prompt, achieving both prompt fidelity and background preservation remains difficult. Recent works have introduced score distillation techniques that leverage the rich generative prior of text-to-image diffusion models to solve this task without additional fine-tuning. However, these methods often struggle with tasks such as object insertion. Our investigation of these failures reveals significant variations in gradient magnitude and spatial distribution, making hyperparameter tuning highly input-specific or unsuccessful. To address this, we propose two simple yet effective modifications: attention-based spatial regularization and gradient filtering-normalization, both aimed at reducing these variations during gradient updates. Experimental results show our method outperforms state-of-the-art score distillation techniques in prompt fidelity, improving successful edits while preserving the background. Users also preferred our method over state-of-the-art techniques across three metrics, and by 58-64% overall.
Authors: Ziqi Wang, Derek Hua, Wenjun Jiang, Tianwei Xing, Xun Chen, Mani Srivastava
Abstract: Respiration waveforms are increasingly recognized as important biomarkers, offering insights beyond simple respiration rates, such as detecting breathing irregularities for disease diagnosis or monitoring breath patterns to guide rehabilitation training. Previous works in wireless respiration monitoring have primarily focused on estimating respiration rate, where the breath waveforms are often generated as a by-product. As a result, issues such as waveform deformation and inversion have largely been overlooked, reducing the signal's utility for applications requiring breathing waveforms. To address this problem, we present a novel approach, MobiVital, that improves the quality of respiration waveforms obtained from ultra-wideband (UWB) radar data. MobiVital combines a self-supervised autoregressive model for breathing waveform extraction with a biology-informed algorithm to detect and correct waveform inversions. To encourage reproducible research efforts for developing wireless vital signal monitoring systems, we also release a 12-person, 24-hour UWB radar vital signal dataset, with time-synchronized ground truth obtained from wearable sensors. Our results show that the respiration waveforms produced by our system exhibit a 7-34% increase in fidelity to the ground truth compared to the baselines and can benefit downstream tasks such as respiration rate estimation.
Authors: Taehwan Lee, Kyeongkook Seo, Jaejun Yoo, Sung Whan Yoon
Abstract: Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the role of loss surface flatness in generative models, both theoretically and empirically, with a particular focus on diffusion models. We establish a theoretical claim that flatter minima improve robustness against perturbations in target prior distributions, leading to benefits such as reduced exposure bias -- where errors in noise estimation accumulate over iterations -- and significantly improved resilience to model quantization, preserving generative performance even under strong quantization constraints. We further observe that Sharpness-Aware Minimization (SAM), which explicitly controls the degree of flatness, effectively enhances flatness in diffusion models, whereas other well-known methods such as Stochastic Weight Averaging (SWA) and Exponential Moving Average (EMA), which promote flatness indirectly via ensembling, are less effective. Through extensive experiments on CIFAR-10, LSUN Tower, and FFHQ, we demonstrate that flat minima in diffusion models indeed improves not only generative performance but also robustness.
Authors: Arnab Bhattacharyya, Weiming Feng, Piyush Srivastava
Abstract: The total variation distance is a metric of central importance in statistics and probability theory. However, somewhat surprisingly, questions about computing it algorithmically appear not to have been systematically studied until very recently. In this paper, we contribute to this line of work by studying this question in the important special case of multivariate Gaussians. More formally, we consider the problem of approximating the total variation distance between two multivariate Gaussians to within an $\epsilon$-relative error. Previous works achieved a fixed constant relative error approximation via closed-form formulas. In this work, we give algorithms that given any two $n$-dimensional Gaussians $D_1,D_2$, and any error bound $\epsilon > 0$, approximate the total variation distance $D := d_{TV}(D_1,D_2)$ to $\epsilon$-relative accuracy in $\text{poly}(n,\frac{1}{\epsilon},\log \frac{1}{D})$ operations. The main technical tool in our work is a reduction that helps us extend the recent progress on computing the TV-distance between discrete random variables to our continuous setting.
Authors: Asifullah Khan, Laiba Asmatullah, Anza Malik, Shahzaib Khan, Hamna Asif
Abstract: Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the concept of "positive" and "negative" samples, where positive pairs (e.g., variation of the same image/object) are brought together in the embedding space, and negative pairs (e.g., views from different images/objects) are pushed farther away. This methodology has shown significant improvements in image understanding and image text analysis without much reliance on labeled data. In this paper, we comprehensively discuss the terminologies, recent developments and applications of contrastive learning with respect to text-image models. Specifically, we provide an overview of the approaches of contrastive learning in text-image models in recent years. Secondly, we categorize the approaches based on different model structures. Thirdly, we further introduce and discuss the latest advances of the techniques used in the process such as pretext tasks for both images and text, architectural structures, and key trends. Lastly, we discuss the recent state-of-art applications of self-supervised contrastive learning Text-Image based models.
Authors: Rachel S. Y. Teo, Tan M. Nguyen
Abstract: Large-scale pre-training of deep models, followed by fine-tuning them, has become the cornerstone of natural language processing (NLP). The prevalence of data coupled with computational resources has led to large models with a considerable number of parameters. While the massive size of these models has led to remarkable success in many NLP tasks, a detriment is the expense required to retrain all the base model's parameters for the adaptation to each task or domain. Parameter Efficient Fine-Tuning (PEFT) provides an effective solution for this challenge by minimizing the number of parameters required to be fine-tuned while maintaining the quality of the model. While existing methods have achieved impressive results, they mainly focus on adapting a subset of parameters, weight reparameterization, and prompt engineering. In this paper, we study layers as extractors of different types of linguistic information that are valuable when used in conjunction. We then propose the Mixture of Layer Experts (MoLEx), a novel sparse mixture of experts (SMoE) whose experts are layers in the pre-trained model. It performs a conditional computation of a mixture of layers during fine-tuning to provide the model with more structural knowledge about the data. By providing an avenue for information exchange between layers, MoLEx enables the model to make a more well-informed prediction for the downstream task, leading to better fine-tuning results with the same number of effective parameters. As experts can be processed in parallel, MoLEx introduces minimal additional computational overhead. We empirically corroborate the advantages of MoLEx when combined with popular PEFT baseline methods on a variety of downstream fine-tuning tasks, including the popular GLUE benchmark as well as the End-to-End Challenge (E2E). The code is publicly available at https://github.com/rachtsy/molex.
Authors: Anas Jnini, Harshinee Goordoyal, Sujal Dave, Flavio Vella, Katharine H. Fraser, Artem Korobenko
Abstract: The Physics-Constrained DeepONet (PC-DeepONet), an architecture that incorporates fundamental physics knowledge into the data-driven DeepONet model, is presented in this study. This methodology is exemplified through surrogate modeling of fluid dynamics over a curved backward-facing step, a benchmark problem in computational fluid dynamics. The model was trained on computational fluid dynamics data generated for a range of parameterized geometries. The PC-DeepONet was able to learn the mapping from the parameters describing the geometry to the velocity and pressure fields. While the DeepONet is solely data-driven, the PC-DeepONet imposes the divergence constraint from the continuity equation onto the network. The PC-DeepONet demonstrates higher accuracy than the data-driven baseline, especially when trained on sparse data. Both models attain convergence with a small dataset of 50 samples and require only 50 iterations for convergence, highlighting the efficiency of neural operators in learning the dynamics governed by partial differential equations.
Authors: Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
Abstract: This work presents a first evaluation of two state-of-the-art Large Reasoning Models (LRMs), OpenAI's o3-mini and DeepSeek R1, on analogical reasoning, focusing on well-established nonverbal human IQ tests based on Raven's progressive matrices. We benchmark with the I-RAVEN dataset and its more difficult extension, I-RAVEN-X, which tests the ability to generalize to longer reasoning rules and ranges of the attribute values. To assess the influence of visual uncertainties on these nonverbal analogical reasoning tests, we extend the I-RAVEN-X dataset, which otherwise assumes an oracle perception. We adopt a two-fold strategy to simulate this imperfect visual perception: 1) we introduce confounding attributes which, being sampled at random, do not contribute to the prediction of the correct answer of the puzzles and 2) smoothen the distributions of the input attributes' values. We observe a sharp decline in OpenAI's o3-mini task accuracy, dropping from 86.6% on the original I-RAVEN to just 17.0% -- approaching random chance -- on the more challenging I-RAVEN-X, which increases input length and range and emulates perceptual uncertainty. This drop occurred despite spending 3.4x more reasoning tokens. A similar trend is also observed for DeepSeek R1: from 80.6% to 23.2%. On the other hand, a neuro-symbolic probabilistic abductive model, ARLC, that achieves state-of-the-art performances on I-RAVEN, can robustly reason under all these out-of-distribution tests, maintaining strong accuracy with only a modest reduction from 98.6% to 88.0%. Our code is available at https://github.com/IBM/raven-large-language-models.
Authors: Maximilian Graf (MISTEA), Victor Thuot (MISTEA), Nicolas Verzelen (MISTEA)
Abstract: We study the problem of clustering a set of items based on bandit feedback. Each of the $n$ items is characterized by a feature vector, with a possibly large dimension $d$. The items are partitioned into two unknown groups such that items within the same group share the same feature vector. We consider a sequential and adaptive setting in which, at each round, the learner selects one item and one feature, then observes a noisy evaluation of the item's feature. The learner's objective is to recover the correct partition of the items, while keeping the number of observations as small as possible. We provide an algorithm which relies on finding a relevant feature for the clustering task, leveraging the Sequential Halving algorithm. With probability at least $1-\delta$, we obtain an accurate recovery of the partition and derive an upper bound on the budget required. Furthermore, we derive an instance-dependent lower bound, which is tight in some relevant cases.
Authors: Yi Xu, Zhiyuan Lu, Xiaochen Li, Jinxin Hu, Hong Wen, Zulong Chen, Yu Zhang, Jing Zhang
Abstract: The Transformer has proven to be a significant approach in feature interaction for CTR prediction, achieving considerable success in previous works. However, it also presents potential challenges in handling feature interactions. Firstly, Transformers may encounter information loss when capturing feature interactions. By relying on inner products to represent pairwise relationships, they compress raw interaction information, which can result in a degradation of fidelity. Secondly, due to the long-tail features distribution, feature fields with low information-abundance embeddings constrain the information abundance of other fields, leading to collapsed embedding matrices. To tackle these issues, we propose a Dual Attention Framework for Enhanced Feature Interaction, known as Dual Enhanced Attention. This framework integrates two attention mechanisms: the Combo-ID attention mechanism and the collapse-avoiding attention mechanism. The Combo-ID attention mechanism directly retains feature interaction pairs to mitigate information loss, while the collapse-avoiding attention mechanism adaptively filters out low information-abundance interaction pairs to prevent interaction collapse. Extensive experiments conducted on industrial datasets have shown the effectiveness of Dual Enhanced Attention.
Authors: Zijing Hu, Fengda Zhang, Long Chen, Kun Kuang, Jiahui Li, Kaifeng Gao, Jun Xiao, Xin Wang, Wenwu Zhu
Abstract: Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and corresponding text prompts. To tackle this issue, reinforcement learning (RL) has been considered for diffusion model fine-tuning. Yet, RL's effectiveness is limited by the challenge of sparse reward, where feedback is only available at the end of the generation process. This makes it difficult to identify which actions during the denoising process contribute positively to the final generated image, potentially leading to ineffective or unnecessary denoising policies. To this end, this paper presents a novel RL-based framework that addresses the sparse reward problem when training diffusion models. Our framework, named $\text{B}^2\text{-DiffuRL}$, employs two strategies: \textbf{B}ackward progressive training and \textbf{B}ranch-based sampling. For one thing, backward progressive training focuses initially on the final timesteps of denoising process and gradually extends the training interval to earlier timesteps, easing the learning difficulty from sparse rewards. For another, we perform branch-based sampling for each training interval. By comparing the samples within the same branch, we can identify how much the policies of the current training interval contribute to the final image, which helps to learn effective policies instead of unnecessary ones. $\text{B}^2\text{-DiffuRL}$ is compatible with existing optimization algorithms. Extensive experiments demonstrate the effectiveness of $\text{B}^2\text{-DiffuRL}$ in improving prompt-image alignment and maintaining diversity in generated images. The code for this work is available.
Authors: Khoi N. M. Nguyen, Hoang Duy Nguyen Do, Huyen Thao Le, Thanh Tuan Dao
Abstract: Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language Models (LLMs) have demonstrated their effectiveness in addressing diverse programming challenges. Our work establishes a connection between LLMs and performance modeling, employing the LLM as a performance estimator. Through experimental exploration with carefully designed large-scale OpenCL datasets, we highlight the potential capability as well as the main difficulties of using LLMs in handling performance modeling tasks for OpenCL device source programs. As the first study for this line of work, our LLM-based performance model achieves a mean absolute percentage error of $24.25\%$ for a large-scale generated validation set. On a set of publicly available OpenCL programs, our model achieves a mean absolute percentage error of $46.1\%$.
Authors: Aatiz Ghimire, Shahnawaz Alam, Siman Giri, Madhav Prasad Ghimire
Abstract: The growing demand for computational power is driven by advancements in deep learning, the increasing need for big data processing, and the requirements of scientific simulations for academic and research purposes. Developing countries like Nepal often struggle with the resources needed to invest in new and better hardware for these purposes. However, optimizing and building on existing technology can still meet these computing demands effectively. To address these needs, we built a cluster using four NVIDIA GeForce GTX 1650 GPUs. The cluster consists of four nodes: one master node that controls and manages the entire cluster, and three compute nodes dedicated to processing tasks. The master node is equipped with all necessary software for package management, resource scheduling, and deployment, such as Anaconda and Slurm. In addition, a Network File Storage (NFS) system was integrated to provide the additional storage required by the cluster. Given that the cluster is accessible via ssh by a public domain address, which poses significant cybersecurity risks, we implemented fail2ban to mitigate brute force attacks and enhance security. Despite the continuous challenges encountered during the design and implementation process, this project demonstrates how powerful computational clusters can be built to handle resource-intensive tasks in various demanding fields.
Authors: Lea Friedli, Ath\'ena\"is Gautier, Anna Broccard, David Ginsbourger
Abstract: Sequential design of real and computer experiments via Gaussian Process (GP) models has proven useful for parsimonious, goal-oriented data acquisition purposes. In this work, we focus on acquisition strategies for a GP model that needs to be accurate within a predefined range of the response of interest. Such an approach is useful in various fields including synthetic chemistry, where finding molecules with particular properties is essential for developing useful materials and effective medications. GP modeling and sequential design of experiments have been successfully applied to a plethora of domains, including molecule research. Our main contribution here is to use the threshold-weighted Continuous Ranked Probability Score (CRPS) as a basic building block for acquisition functions employed within sequential design. We study pointwise and integral criteria relying on two different weighting measures and benchmark them against competitors, demonstrating improved performance with respect to considered goals. The resulting acquisition strategies are applicable to a wide range of fields and pave the way to further developing sequential design relying on scoring rules.
Authors: Alireza Mousavi-Hosseini, Clayton Sanford, Denny Wu, Murat A. Erdogdu
Abstract: Theoretical efforts to prove advantages of Transformers in comparison with classical architectures such as feedforward and recurrent neural networks have mostly focused on representational power. In this work, we take an alternative perspective and prove that even with infinite compute, feedforward and recurrent networks may suffer from larger sample complexity compared to Transformers, as the latter can adapt to a form of dynamic sparsity. Specifically, we consider a sequence-to-sequence data generating model on sequences of length $N$, in which the output at each position depends only on $q$ relevant tokens with $q \ll N$, and the positions of these tokens are described in the input prompt. We prove that a single-layer Transformer can learn this model if and only if its number of attention heads is at least $q$, in which case it achieves a sample complexity almost independent of $N$, while recurrent networks require $N^{\Omega(1)}$ samples on the same problem. If we simplify this model, recurrent networks may achieve a complexity almost independent of $N$, while feedforward networks still require $N$ samples. Consequently, our proposed sparse retrieval model illustrates a natural hierarchy in sample complexity across these architectures.
Authors: Ali Elkeshawy, Haifa Fares, Amor Nafkha
Abstract: Grant-free random access (GF-RA) is a promising access technique for massive machine-type communications (mMTC) in future wireless networks, particularly in the context of 5G and beyond (6G) systems. Within the context of GF-RA, this study investigates the efficiency of employing supervised machine learning techniques to tackle the challenges on the device activity detection (AD). GF-RA addresses scalability by employing non-orthogonal pilot sequences, which provides an efficient alternative comparing to conventional grant-based random access (GB-RA) technique that are constrained by the scarcity of orthogonal preamble resources. In this paper, we propose a novel lightweight data-driven algorithmic framework specifically designed for activity detection in GF-RA for mMTC in cell-free massive multiple-input multiple-output (CF-mMIMO) networks. We propose two distinct framework deployment strategies, centralized and decentralized, both tailored to streamline the proposed approach implementation across network infrastructures. Moreover, we introduce optimized post-detection methodologies complemented by a clustering stage to enhance overall detection performances. Our 3GPP-compliant simulations have validated that the proposed algorithm achieves state-of-the-art model-based activity detection accuracy while significantly reducing complexity. Achieving 99% accuracy, it demonstrates real-world viability and effectiveness.
Authors: Gorka Mu\~noz-Gil, Hans J. Briegel, Michele Caraglio
Abstract: Target search problems are central to a wide range of fields, from biological foraging to the optimization algorithms. Recently, the ability to reset the search has been shown to significantly improve the searcher's efficiency. However, the optimal resetting strategy depends on the specific properties of the search problem and can often be challenging to determine. In this work, we propose a reinforcement learning (RL)-based framework to train agents capable of optimizing their search efficiency in environments by learning how to reset. First, we validate the approach in a well-established benchmark: the Brownian search with resetting. There, RL agents consistently recover strategies closely resembling the sharp resetting distribution, known to be optimal in this scenario. We then extend the framework by allowing agents to control not only when to reset, but also their spatial dynamics through turning actions. In this more complex setting, the agents discover strategies that adapt both resetting and turning to the properties of the environment, outperforming the proposed benchmarks. These results demonstrate how reinforcement learning can serve both as an optimization tool and a mechanism for uncovering new, interpretable strategies in stochastic search processes with resetting.
Authors: Zhenyi Zhang, Yuhao Sun, Qiangwei Peng, Tiejun Li, Peijie Zhou
Abstract: Understanding the dynamic nature of biological systems is fundamental to deciphering cellular behavior, developmental processes, and disease progression. Single-cell RNA sequencing (scRNA-seq) has provided static snapshots of gene expression, offering valuable insights into cellular states at a single time point. Recent advancements in temporally resolved scRNA-seq, spatial transcriptomics (ST), and time-series spatial transcriptomics (temporal-ST) have further revolutionized our ability to study the spatiotemporal dynamics of individual cells. These technologies, when combined with computational frameworks such as Markov chains, stochastic differential equations (SDEs), and generative models like optimal transport and Schr\"odinger bridges, enable the reconstruction of dynamic cellular trajectories and cell fate decisions. This review discusses how these dynamical system approaches offer new opportunities to model and infer cellular dynamics from a systematic perspective.
Authors: Mayank Nautiyal, Stela Arranz Gheorghe, Kristiana Stefa, Li Ju, Ida-Maria Sintorn, Prashant Singh
Abstract: Language-guided attention frameworks have significantly enhanced both interpretability and performance in image classification; however, the reliance on deterministic embeddings from pre-trained vision-language foundation models to generate reference attention maps frequently overlooks the intrinsic multivaluedness and ill-posed characteristics of cross-modal mappings. To address these limitations, we introduce PARIC, a probabilistic framework for guiding visual attention via language specifications. Our approach enables pre-trained vision-language models to generate probabilistic reference attention maps, which align textual and visual modalities more effectively while incorporating uncertainty estimates, as compared to their deterministic counterparts. Experiments on benchmark test problems demonstrate that PARIC enhances prediction accuracy, mitigates bias, ensures consistent predictions, and improves robustness across various datasets.
Authors: Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer
Abstract: Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in building well-performing low-complexity Acoustic Scene Classification (ASC) systems and was used in all the top-ranked submissions to this task of the annual DCASE challenge in the past three years. There is extensive research available on establishing the KD process, designing efficient student models, and forming well-performing teacher ensembles. However, less research has been conducted on investigating which teacher model attributes are beneficial for low-complexity students. In this work, we try to close this gap by studying the effects on the student's performance when using different teacher network architectures, varying the teacher model size, training them with different device generalization methods, and applying different ensembling strategies. The results show that teacher model sizes, device generalization methods, the ensembling strategy and the ensemble size are key factors for a well-performing student network.
Authors: Tobias Morocutti, Florian Schmid, Jonathan Greif, Francesco Foscarin, Gerhard Widmer
Abstract: We target the problem of developing new low-complexity networks for the sound event detection task. Our goal is to meticulously analyze the performance-complexity trade-off, aiming to be competitive with the large state-of-the-art models, at a fraction of the computational requirements. We find that low-complexity convolutional models previously proposed for audio tagging can be effectively adapted for event detection (which requires frame-wise prediction) by adjusting convolutional strides, removing the global pooling, and, importantly, adding a sequence model before the (now frame-wise) classification heads. Systematic experiments reveal that the best choice for the sequence model type depends on which complexity metric is most important for the given application. We also investigate the impact of enhanced training strategies such as knowledge distillation. In the end, we show that combined with an optimized training strategy, we can reach event detection performance comparable to state-of-the-art transformers while requiring only around 5% of the parameters. We release all our pre-trained models and the code for reproducing this work to support future research in low-complexity sound event detection at https://github.com/theMoro/EfficientSED.
Authors: Lukas Kroi{\ss}, Johannes Reschke
Abstract: Fake News and especially deepfakes (generated, non-real image or video content) have become a serious topic over the last years. With the emergence of machine learning algorithms it is now easier than ever before to generate such fake content, even for private persons. This issue of generated fake images is especially critical in the context of politics and public figures. We want to address this conflict by building a model based on a Convolutions Neural Network in order to detect such generated and fake images showing human portraits. As a basis, we use a pre-trained ResNet-50 model due to its effectiveness in terms of classifying images. We then adopted the base model to our task of classifying a single image as authentic/real or fake by adding an fully connected output layer containing a single neuron indicating the authenticity of an image. We applied fine tuning and transfer learning to develop the model and improve its parameters. For the training process we collected the image data set "Diverse Face Fake Dataset" containing a wide range of different image manipulation methods and also diversity in terms of faces visible on the images. With our final model we reached the following outstanding performance metrics: precision = 0.98, recall 0.96, F1-Score = 0.97 and an area-under-curve = 0.99.
Authors: Andr\'es Chavarr\'ias, David Rodriguez-Cianca, Pablo Lanillos
Abstract: Spasticity is a common movement disorder symptom in individuals with cerebral palsy, hereditary spastic paraplegia, spinal cord injury and stroke, being one of the most disabling features in the progression of these diseases. Despite the potential benefit of using wearable robots to treat spasticity, their use is not currently recommended to subjects with a level of spasticity above ${1^+}$ on the Modified Ashworth Scale. The varying dynamics of this velocity-dependent tonic stretch reflex make it difficult to deploy safe personalized controllers. Here, we describe a novel adaptive torque controller via deep reinforcement learning (RL) for a knee exoskeleton under joint spasticity conditions, which accounts for task performance and interaction forces reduction. To train the RL agent, we developed a digital twin, including a musculoskeletal-exoskeleton system with joint misalignment and a differentiable spastic reflexes model for the muscles activation. Results for a simulated knee extension movement showed that the agent learns to control the exoskeleton for individuals with different levels of spasticity. The proposed controller was able to reduce maximum torques applied to the human joint under spastic conditions by an average of 10.6\% and decreases the root mean square until the settling time by 8.9\% compared to a conventional compliant controller.
Authors: Marianne Defresne, Jayanta Mandi, Tias Guns
Abstract: Real-life combinatorial optimization problems often involve several conflicting objectives, such as price, product quality and sustainability. A computationally-efficient way to tackle multiple objectives is to aggregate them into a single-objective function, such as a linear combination. However, defining the weights of the linear combination upfront is hard; alternatively, the use of interactive learning methods that ask users to compare candidate solutions is highly promising. The key challenges are to generate candidates quickly, to learn an objective function that leads to high-quality solutions and to do so with few user interactions. We build upon the Constructive Preference Elicitation framework and show how each of the three properties can be improved: to increase the interaction speed we investigate using pools of (relaxed) solutions, to improve the learning we adopt Maximum Likelihood Estimation of a Bradley-Terry preference model; and to reduce the number of user interactions, we select the pair of candidates to compare with an ensemble-based acquisition function inspired from Active Learning. Our careful experimentation demonstrates each of these improvements: on a PC configuration task and a realistic multi-instance routing problem, our method selects queries faster, needs fewer queries and synthesizes higher-quality combinatorial solutions than previous CPE methods.
Authors: Azhar Ali Khaked, Nobuyuki Oishi, Daniel Roggen, Paula Lago
Abstract: Human Activity Recognition (HAR) using wearable inertial measurement unit (IMU) sensors can revolutionize healthcare by enabling continual health monitoring, disease prediction, and routine recognition. Despite the high accuracy of Deep Learning (DL) HAR models, their robustness to real-world variabilities remains untested, as they have primarily been trained and tested on limited lab-confined data. In this study, we isolate subject, device, position, and orientation variability to determine their effect on DL HAR models and assess the robustness of these models in real-world conditions. We evaluated the DL HAR models using the HARVAR and REALDISP datasets, providing a comprehensive discussion on the impact of variability on data distribution shifts and changes in model performance. Our experiments measured shifts in data distribution using Maximum Mean Discrepancy (MMD) and observed DL model performance drops due to variability. We concur that studied variabilities affect DL HAR models differently, and there is an inverse relationship between data distribution shifts and model performance. The compounding effect of variability was analyzed, and the implications of variabilities in real-world scenarios were highlighted. MMD proved an effective metric for calculating data distribution shifts and explained the drop in performance due to variabilities in HARVAR and REALDISP datasets. Combining our understanding of variability with evaluating its effects will facilitate the development of more robust DL HAR models and optimal training techniques. Allowing Future models to not only be assessed based on their maximum F1 score but also on their ability to generalize effectively
Authors: Jose-Luis Holgado-Alvarez, Aryaman Reddi, Carlo D'Eramo
Abstract: Reinforcement Learning (RL) has proven largely effective in obtaining stable locomotion gaits for legged robots. However, designing control algorithms which can robustly navigate unseen environments with obstacles remains an ongoing problem within quadruped locomotion. To tackle this, it is convenient to solve navigation tasks by means of a hierarchical approach with a low-level locomotion policy and a high-level navigation policy. Crucially, the high-level policy needs to be robust to dynamic obstacles along the path of the agent. In this work, we propose a novel way to endow navigation policies with robustness by a training process that models obstacles as adversarial agents, following the adversarial RL paradigm. Importantly, to improve the reliability of the training process, we bound the rationality of the adversarial agent resorting to quantal response equilibria, and place a curriculum over its rationality. We called this method Hierarchical policies via Quantal response Adversarial Reinforcement Learning (Hi-QARL). We demonstrate the robustness of our method by benchmarking it in unseen randomized mazes with multiple obstacles. To prove its applicability in real scenarios, our method is applied on a Unitree GO1 robot in simulation.
Authors: Jens Engel, Andrea Castellani, Patricia Wollstadt, Felix Lanfermann, Thomas Schmitt, Sebastian Schmitt, Lydia Fischer, Steffen Limmer, David Luttropp, Florian Jomrich, Ren\'e Unger, Tobias Rodemann
Abstract: We present a large real-world dataset obtained from monitoring a smart company facility over the course of six years, from 2018 to 2023. The dataset includes energy consumption data from various facility areas and components, energy production data from a photovoltaic system and a combined heat and power plant, operational data from heating and cooling systems, and weather data from an on-site weather station. The measurement sensors installed throughout the facility are organized in a hierarchical metering structure with multiple sub-metering levels, which is reflected in the dataset. The dataset contains measurement data from 72 energy meters, 9 heat meters and a weather station. Both raw and processed data at different processing levels, including labeled issues, is available. In this paper, we describe the data acquisition and post-processing employed to create the dataset. The dataset enables the application of a wide range of methods in the domain of energy management, including optimization, modeling, and machine learning to optimize building operations and reduce costs and carbon emissions.
Authors: Piotr Bialas, Piotr Korcyl, Tomasz Stebel, Dawid Zapolski
Abstract: We present the \texttt{NeuMC} software package, based on \pytorch, aimed at facilitating the research on neural samplers in lattice field theories. Neural samplers based on normalizing flows are becoming increasingly popular in the context of Monte-Carlo simulations as they can effectively approximate target probability distributions, possibly alleviating some shortcomings of the Markov chain Monte-Carlo methods. Our package provides tools to create such samplers for two-dimensional field theories.
Authors: Ayush Paliwal, Oliver Schlenczek, Birte Thiede, Manuel Santos Pereira, Katja Stieger, Eberhard Bodenschatz, Gholamhossein Bagheri, Alexander Ecker
Abstract: Reconstructing the 3D location and size of microparticles from diffraction images - holograms - is a computationally expensive inverse problem that has traditionally been solved using physics-based reconstruction methods. More recently, researchers have used machine learning methods to speed up the process. However, for small particles in large sample volumes the performance of these methods falls short of standard physics-based reconstruction methods. Here we designed a two-stage neural network architecture, FLASH$\mu$, to detect small particles (6-100$\mu$m) from holograms with large sample depths up to 20cm. Trained only on synthetic data with added physical noise, our method reliably detects particles of at least 9$\mu$m diameter in real holograms, comparable to the standard reconstruction-based approaches while operating on smaller crops, at quarter of the original resolution and providing roughly a 600-fold speedup. In addition to introducing a novel approach to a non-local object detection or signal demixing problem, our work could enable low-cost, real-time holographic imaging setups.
Authors: Franco Caspe, Jordie Shier, Mark Sandler, Charalampos Saitis, Andrew McPherson
Abstract: Neural Audio Synthesis (NAS) models offer interactive musical control over high-quality, expressive audio generators. While these models can operate in real-time, they often suffer from high latency, making them unsuitable for intimate musical interaction. The impact of architectural choices in deep learning models on audio latency remains largely unexplored in the NAS literature. In this work, we investigate the sources of latency and jitter typically found in interactive NAS models. We then apply this analysis to the task of timbre transfer using RAVE, a convolutional variational autoencoder for audio waveforms introduced by Caillon et al. in 2021. Finally, we present an iterative design approach for optimizing latency. This culminates with a model we call BRAVE (Bravely Realtime Audio Variational autoEncoder), which is low-latency and exhibits better pitch and loudness replication while showing timbre modification capabilities similar to RAVE. We implement it in a specialized inference framework for low-latency, real-time inference and present a proof-of-concept audio plugin compatible with audio signals from musical instruments. We expect the challenges and guidelines described in this document to support NAS researchers in designing models for low-latency inference from the ground up, enriching the landscape of possibilities for musicians.
Authors: Matteo Farina, Massimiliano Mancini, Giovanni Iacca, Elisa Ricci
Abstract: An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient to fit a large number of parameters, rendering the above impractical. This is especially true with large pre-trained Vision-Language Models (VLMs), which motivated successful research at the intersection of Parameter-Efficient Fine-tuning (PEFT) and FSA. In this work, we start by analyzing the learning dynamics of PEFT techniques when trained on few-shot data from only a subset of categories, referred to as the ``base'' classes. We show that such dynamics naturally splits into two distinct phases: (i) task-level feature extraction and (ii) specialization to the available concepts. To accommodate this dynamic, we then depart from prompt- or adapter-based methods and tackle FSA differently. Specifically, given a fixed computational budget, we split it to (i) learn a task-specific feature extractor via PEFT and (ii) train a linear classifier on top. We call this scheme Two-Stage Few-Shot Adaptation (2SFS). Differently from established methods, our scheme enables a novel form of selective inference at a category level, i.e., at test time, only novel categories are embedded by the adapted text encoder, while embeddings of base categories are available within the classifier. Results with fixed hyperparameters across two settings, three backbones, and eleven datasets, show that 2SFS matches or surpasses the state-of-the-art, while established methods degrade significantly across settings.
Authors: Will Schwarzer, Philip S. Thomas, Andrea Fanelli, Xiaoyu Liu
Abstract: Deep noise suppression (DNS) models enjoy widespread use throughout a variety of high-stakes speech applications. However, in this paper, we show that four recent DNS models can each be reduced to outputting unintelligible gibberish through the addition of imperceptible adversarial noise. Furthermore, our results show the near-term plausibility of targeted attacks, which could induce models to output arbitrary utterances, and over-the-air attacks. While the success of these attacks varies by model and setting, and attacks appear to be strongest when model-specific (i.e., white-box and non-transferable), our results highlight a pressing need for practical countermeasures in DNS systems.
Authors: Chonghao Sima, Kashyap Chitta, Zhiding Yu, Shiyi Lan, Ping Luo, Andreas Geiger, Hongyang Li, Jose M. Alvarez
Abstract: How can we rely on an end-to-end autonomous vehicle's complex decision-making system during deployment? One common solution is to have a ``fallback layer'' that checks the planned trajectory for rule violations and replaces it with a pre-defined safe action if necessary. Another approach involves adjusting the planner's decisions to minimize a pre-defined ``cost function'' using additional system predictions such as road layouts and detected obstacles. However, these pre-programmed rules or cost functions cannot learn and improve with new training data, often resulting in overly conservative behaviors. In this work, we propose Centaur (Cluster Entropy for Test-time trAining using Uncertainty) which updates a planner's behavior via test-time training, without relying on hand-engineered rules or cost functions. Instead, we measure and minimize the uncertainty in the planner's decisions. For this, we develop a novel uncertainty measure, called Cluster Entropy, which is simple, interpretable, and compatible with state-of-the-art planning algorithms. Using data collected at prior test-time time-steps, we perform an update to the model's parameters using a gradient that minimizes the Cluster Entropy. With only this sole gradient update prior to inference, Centaur exhibits significant improvements, ranking first on the navtest leaderboard with notable gains in safety-critical metrics such as time to collision. To provide detailed insights on a per-scenario basis, we also introduce navsafe, a challenging new benchmark, which highlights previously undiscovered failure modes of driving models.
Authors: Hsuan-Kung Yang, Tsung-Chih Chiang, Jou-Min Liu, Ting-Ru Liu, Chun-Wei Huang, Tsu-Ching Hsiao, Chun-Yi Lee
Abstract: In the context of autonomous navigation, effectively conveying abstract navigational cues to agents in dynamic environments presents significant challenges, particularly when navigation information is derived from diverse modalities such as both vision and high-level language descriptions. To address this issue, we introduce a novel technique termed `Virtual Guidance,' which is designed to visually represent non-visual instructional signals. These visual cues are overlaid onto the agent's camera view and served as comprehensible navigational guidance signals. To validate the concept of virtual guidance, we propose a sim-to-real framework that enables the transfer of the trained policy from simulated environments to real world, ensuring the adaptability of virtual guidance in practical scenarios. We evaluate and compare the proposed method against a non-visual guidance baseline through detailed experiments in simulation. The experimental results demonstrate that the proposed virtual guidance approach outperforms the baseline methods across multiple scenarios and offers clear evidence of its effectiveness in autonomous navigation tasks.
Authors: Juyoung Yun, Sol Choi, Francois Rameau, Byungkon Kang, Zhoulai Fu
Abstract: With the increasing complexity of machine learning models, managing computational resources like memory and processing power has become a critical concern. Mixed precision techniques, which leverage different numerical precisions during model training and inference to optimize resource usage, have been widely adopted. However, access to hardware that supports lower precision formats (e.g., FP8 or FP4) remains limited, especially for practitioners with hardware constraints. For many with limited resources, the available options are restricted to using 32-bit, 16-bit, or a combination of the two. While it is commonly believed that 16-bit precision can achieve results comparable to full (32-bit) precision, this study is the first to systematically validate this assumption through both rigorous theoretical analysis and extensive empirical evaluation. Our theoretical formalization of floating-point errors and classification tolerance provides new insights into the conditions under which 16-bit precision can approximate 32-bit results. This study fills a critical gap, proving for the first time that standalone 16-bit precision neural networks match 32-bit and mixed-precision in accuracy while boosting computational speed. Given the widespread availability of 16-bit across GPUs, these findings are especially valuable for machine learning practitioners with limited hardware resources to make informed decisions.
Authors: Moritz A. Zanger, Wendelin B\"ohmer, Matthijs T. J. Spaan
Abstract: In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby profoundly impacting the generalization behavior of learned models. In order to facilitate reliable uncertainty estimation through diversity, we study the combination of several different projections and representations in a distributional ensemble. We establish theoretical properties of such projection ensembles and derive an algorithm that uses ensemble disagreement, measured by the average 1-Wasserstein distance, as a bonus for deep exploration. We evaluate our algorithm on the behavior suite benchmark and VizDoom and find that diverse projection ensembles lead to significant performance improvements over existing methods on a variety of tasks with the most pronounced gains in directed exploration problems.
Authors: Ribana Roscher, Marc Ru{\ss}wurm, Caroline Gevaert, Michael Kampffmeyer, Jefersson A. dos Santos, Maria Vakalopoulou, Ronny H\"ansch, Stine Hansen, Keiller Nogueira, Jonathan Prexl, Devis Tuia
Abstract: Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architectures and models have been proposed, the majority of them have been solely developed on benchmark datasets that lack strong real-world relevance. Furthermore, the performance of many methods has already saturated on these datasets. We argue that a shift from a model-centric view to a complementary data-centric perspective is necessary for further improvements in accuracy, generalization ability, and real impact on end-user applications. Furthermore, considering the entire machine learning cycle-from problem definition to model deployment with feedback-is crucial for enhancing machine learning models that can be reliable in unforeseen situations. This work presents a definition as well as a precise categorization and overview of automated data-centric learning approaches for geospatial data. It highlights the complementary role of data-centric learning with respect to model-centric in the larger machine learning deployment cycle. We review papers across the entire geospatial field and categorize them into different groups. A set of representative experiments shows concrete implementation examples. These examples provide concrete steps to act on geospatial data with data-centric machine learning approaches.
Authors: Roshni . R. Kamath, Rupert Mitchell, Subarnaduti Paul, Kristian Kersting, Martin Mundt
Abstract: Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter undesired inputs, are required to deal with novel information, and need to ensure operation through their full lifetime - aspects where standard deep models struggle. These three elements may have been researched individually, but their practical conjunction, i.e., open world learning, is much less consolidated. In this paper, we posit that neural networks already contain a powerful catalyst to turn them into open world learners: the batch normalization layer. Leveraging its tracked statistics, we derive effective strategies to detect in- and out-of-distribution samples, select informative data points, and update the model continuously. This, in turn, allows us to demonstrate that existing batch-normalized models can be made more robust, less prone to forgetting over time, and be trained efficiently with less data.
Authors: Patrick Seifner, Kostadin Cvejoski, Antonia K\"orner, Rams\'es J. S\'anchez
Abstract: Dynamical systems governed by ordinary differential equations (ODEs) serve as models for a vast number of natural and social phenomena. In this work, we offer a fresh perspective on the classical problem of imputing missing time series data, whose underlying dynamics are assumed to be determined by ODEs. Specifically, we revisit ideas from amortized inference and neural operators, and propose a novel supervised learning framework for zero-shot time series imputation, through parametric functions satisfying some (hidden) ODEs. Our proposal consists of two components. First, a broad probability distribution over the space of ODE solutions, observation times and noise mechanisms, with which we generate a large, synthetic dataset of (hidden) ODE solutions, along with their noisy and sparse observations. Second, a neural recognition model that is trained offline, to map the generated time series onto the spaces of initial conditions and time derivatives of the (hidden) ODE solutions, which we then integrate to impute the missing data. We empirically demonstrate that one and the same (pretrained) recognition model can perform zero-shot imputation across 63 distinct time series with missing values, each sampled from widely different dynamical systems. Likewise, we demonstrate that it can perform zero-shot imputation of missing high-dimensional data in 10 vastly different settings, spanning human motion, air quality, traffic and electricity studies, as well as Navier-Stokes simulations -- without requiring any fine-tuning. What is more, our proposal often outperforms state-of-the-art methods, which are trained on the target datasets. Our pretrained model, repository and tutorials are available online.
Authors: Akshay Kumar, Jarvis Haupt
Abstract: This paper studies the gradient flow dynamics that arise when training deep homogeneous neural networks assumed to have locally Lipschitz gradients and an order of homogeneity strictly greater than two. It is shown here that for sufficiently small initializations, during the early stages of training, the weights of the neural network remain small in (Euclidean) norm and approximately converge in direction to the Karush-Kuhn-Tucker (KKT) points of the recently introduced neural correlation function. Additionally, this paper also studies the KKT points of the neural correlation function for feed-forward networks with (Leaky) ReLU and polynomial (Leaky) ReLU activations, deriving necessary and sufficient conditions for rank-one KKT points.
Authors: Chuqin Geng, Zhaoyue Wang, Haolin Ye, Xujie Si
Abstract: Formal verification is only as good as the specification of a system, which is also true for neural network verification. Existing specifications follow the paradigm of data as specification, where the local neighborhood around a reference data point is considered correct or robust. While these specifications provide a fair testbed for assessing model robustness, they are too restrictive for verifying any unseen test data points, a challenging task with significant real-world implications. Recent work shows great promise through a new paradigm, neural representation as specification, which uses neural activation patterns (NAPs) for this purpose. However, it computes the most refined NAPs, which include many redundant neurons. In this paper, we study the following problem: Given a neural network, find a minimal (general) NAP specification that is sufficient for formal verification of its robustness properties. Finding the minimal NAP specification not only expands verifiable bounds but also provides insights into which set of neurons contributes to the model's robustness. To address this problem, we propose three approaches: conservative, statistical, and optimistic. Each of these methods offers distinct strengths and trade-offs in terms of minimality and computational speed, making them suitable for scenarios with different priorities. Notably, the optimistic approach can probe potential causal links between neurons and the robustness of large vision neural networks without relying on verification tools, a task existing methods struggle to scale. Our experiments show that minimal NAP specifications use far fewer neurons than those from previous work while expanding verifiable boundaries by several orders of magnitude.
Authors: Thomas L. Lee, Sigrid Passano Hellan, Linus Ericsson, Elliot J. Crowley, Amos Storkey
Abstract: In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all of the data at the same time. This has prompted the development of CL-specific HPO frameworks. The most popular way to tune hyperparameters in CL is to repeatedly train over the whole data stream with different hyperparameter settings. However, this end-of-training HPO is unusable in practice since a learner can only see the stream once. Hence, there is an open question: what HPO framework should a practitioner use for a CL problem in reality? This paper looks at this question by comparing several realistic HPO frameworks. We find that none of the HPO frameworks considered, including end-of-training HPO, perform consistently better than the rest on popular CL benchmarks. We therefore arrive at a twofold conclusion: a) to be able to discriminate between HPO frameworks there is a need to move beyond the current most commonly used CL benchmarks, and b) on the popular CL benchmarks examined, a CL practitioner should use a realistic HPO framework and can select it based on factors separate from performance, for example compute efficiency.
Authors: Shengzhe Xu, Cho-Ting Lee, Mandar Sharma, Raquib Bin Yousuf, Nikhil Muralidhar, Naren Ramakrishnan
Abstract: Synthetic data generation is integral to ML pipelines, e.g., to augment training data, replace sensitive information, and even to power advanced platforms like DeepSeek. While LLMs fine-tuned for synthetic data generation are gaining traction, synthetic table generation -- a critical data type in business and science -- remains under-explored compared to text and image synthesis. This paper shows that LLMs, whether used as-is or after traditional fine-tuning, are inadequate for generating synthetic tables. Their autoregressive nature, combined with random order permutation during fine-tuning, hampers the modeling of functional dependencies and prevents capturing conditional mixtures of distributions essential for real-world constraints. We demonstrate that making LLMs permutation-aware can mitigate these issues.
Authors: Yi Ding, Chengxuan Tong, Shuailei Zhang, Muyun Jiang, Yong Li, Kevin Lim Jun Liang, Cuntai Guan
Abstract: Integrating prior knowledge of neurophysiology into neural network architecture enhances the performance of emotion decoding. While numerous techniques emphasize learning spatial and short-term temporal patterns, there has been limited emphasis on capturing the vital long-term contextual information associated with emotional cognitive processes. In order to address this discrepancy, we introduce a novel transformer model called emotion transformer (EmT). EmT is designed to excel in both generalized cross-subject EEG emotion classification and regression tasks. In EmT, EEG signals are transformed into a temporal graph format, creating a sequence of EEG feature graphs using a temporal graph construction module (TGC). A novel residual multi-view pyramid GCN module (RMPG) is then proposed to learn dynamic graph representations for each EEG feature graph within the series, and the learned representations of each graph are fused into one token. Furthermore, we design a temporal contextual transformer module (TCT) with two types of token mixers to learn the temporal contextual information. Finally, the task-specific output module (TSO) generates the desired outputs. Experiments on four publicly available datasets show that EmT achieves higher results than the baseline methods for both EEG emotion classification and regression tasks. The code is available at https://github.com/yi-ding-cs/EmT.
Authors: Zhengbo Zhang, Yuxi Zhou, Jia Gong, Jun Liu, Zhigang Tu
Abstract: Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student network to adapt to the varying learning difficulties at different learning stages of KD. KD is a continuous process, but when adjusting the temperature, these methods consider only the immediate benefits of the operation in the current learning phase and fail to take into account its future returns. To address this issue, we formulate the adjustment of temperature as a sequential decision-making task and propose a method based on reinforcement learning, termed RLKD. Importantly, we design a novel state representation to enable the agent to make more informed action (i.e. instance temperature adjustment). To handle the problem of delayed rewards in our method due to the KD setting, we explore an instance reward calibration approach. In addition,we devise an efficient exploration strategy that enables the agent to learn valuable instance temperature adjustment policy more efficiently. Our framework can serve as a plug-and-play technique to be inserted into various KD methods easily, and we validate its effectiveness on both image classification and object detection tasks. Our project is at https://www.zayx.me/ITKD.github.io/.
Authors: Luwei Sun, Dongrui Shen, Han Feng
Abstract: In this paper, we focus on analyzing the excess risk of the unpaired data generation model, called CycleGAN. Unlike classical GANs, CycleGAN not only transforms data between two unpaired distributions but also ensures the mappings are consistent, which is encouraged by the cycle-consistency term unique to CycleGAN. The increasing complexity of model structure and the addition of the cycle-consistency term in CycleGAN present new challenges for error analysis. By considering the impact of both the model architecture and training procedure, the risk is decomposed into two terms: approximation error and estimation error. These two error terms are analyzed separately and ultimately combined by considering the trade-off between them. Each component is rigorously analyzed; the approximation error through constructing approximations of the optimal transport maps, and the estimation error through establishing an upper bound using Rademacher complexity. Our analysis not only isolates these errors but also explores the trade-offs between them, which provides a theoretical insights of how CycleGAN's architecture and training procedures influence its performance.
Authors: Xuanxuan Yang (the Institute of Intelligent Machines, Chinese Academy of Sciences, University of Science and Technology of China), Yangming Zhang (the Institute of Intelligent Machines, Chinese Academy of Sciences), Haofeng Chen (the Institute of Intelligent Machines, Chinese Academy of Sciences, University of Science and Technology of China), Gang Ma (University of Science and Technology of China), Xiaojie Wang (the Institute of Intelligent Machines, Chinese Academy of Sciences)
Abstract: Electrical Impedance Tomography (EIT) is a highly ill-posed inverse problem, with the challenge of reconstructing internal conductivities using only boundary voltage measurements. Although Physics-Informed Neural Networks (PINNs) have shown potential in solving inverse problems, existing approaches are limited in their applicability to EIT, as they often rely on impractical prior knowledge and assumptions that cannot be satisfied in real-world scenarios. To address these limitations, we propose a two-stage hybrid learning framework that combines Convolutional Neural Networks (CNNs) and PINNs. This framework integrates data-driven and model-driven paradigms, blending supervised and unsupervised learning to reconstruct conductivity distributions while ensuring adherence to the underlying physical laws, thereby overcoming the constraints of existing methods.
Authors: Yixiu Zhao, Jiaxin Shi, Feng Chen, Shaul Druckmann, Lester Mackey, Scott Linderman
Abstract: Discrete diffusion has emerged as a powerful framework for generative modeling in discrete domains, yet efficiently sampling from these models remains challenging. Existing sampling strategies often struggle to balance computation and sample quality when the number of sampling steps is reduced, even when the model has learned the data distribution well. To address these limitations, we propose a predictor-corrector sampling scheme where the corrector is informed by the diffusion model to more reliably counter the accumulating approximation errors. To further enhance the effectiveness of our informed corrector, we introduce complementary architectural modifications based on hollow transformers and a simple tailored training objective that leverages more training signal. We use a synthetic example to illustrate the failure modes of existing samplers and show how informed correctors alleviate these problems. On tokenized ImageNet 256x256, this approach consistently produces superior samples with fewer steps, achieving improved FID scores for discrete diffusion models. These results underscore the potential of informed correctors for fast and high-fidelity generation using discrete diffusion.
Authors: Daniel Rose, Oliver Wieder, Thomas Seidel, Thierry Langer
Abstract: The increasing size of screening libraries poses a significant challenge for the development of virtual screening methods for drug discovery, necessitating a re-evaluation of traditional approaches in the era of big data. Although 3D pharmacophore screening remains a prevalent technique, its application to very large datasets is limited by the computational cost associated with matching query pharmacophores to database molecules. In this study, we introduce PharmacoMatch, a novel contrastive learning approach based on neural subgraph matching. Our method reinterprets pharmacophore screening as an approximate subgraph matching problem and enables efficient querying of conformational databases by encoding query-target relationships in the embedding space. We conduct comprehensive investigations of the learned representations and evaluate PharmacoMatch as pre-screening tool in a zero-shot setting. We demonstrate significantly shorter runtimes and comparable performance metrics to existing solutions, providing a promising speed-up for screening very large datasets.
Authors: Minoh Jeong, Min Namgung, Zae Myung Kim, Dongyeop Kang, Yao-Yi Chiang, Alfred Hero
Abstract: A unified representation space in multi-modal learning is essential for effectively integrating diverse data sources, such as text, images, and audio, to enhance efficiency and performance across various downstream tasks. Recent binding methods, such as ImageBind (Girdhar et al., 2023), typically rely on a single, fixed anchor modality for aligning multi-modal data. We mathematically analyze these fixed anchor binding method and uncover significant limitations: (1) over-reliance on the choice of the anchor modality, (2) inadequate capture of intra-modal information, and (3) failure to account for cross-modal correlation among non-anchored modalities. To address these issues, we propose the need for adaptive anchor binding methods, exemplified by our framework CentroBind. The proposed method uses adaptively adjustable centroid-based anchors generated from all available modalities, leading to a balanced and rich representation space. We theoretically demonstrate that our approach captures three critical properties of multi-modal learning -- intra-modal learning, inter-modal learning, and multi-modal alignment -- while constructing a unified representation that spans all modalities. Experiments on both synthetic and real-world datasets show that adaptive anchor methods such as CentroBind consistently outperform fixed anchor binding methods, verifying our analysis.
Authors: Changdae Oh, Yixuan Li, Kyungwoo Song, Sangdoo Yun, Dongyoon Han
Abstract: Adapting a pre-trained foundation model on downstream tasks should ensure robustness against distribution shifts without the need to retrain the whole model. Although existing weight interpolation methods are simple yet effective, we argue their static nature limits downstream performance while achieving efficiency. In this work, we propose DaWin, a training-free dynamic weight interpolation method that leverages the entropy of individual models over each unlabeled test sample to assess model expertise, and compute per-sample interpolation coefficients dynamically. Unlike previous works that typically rely on additional training to learn such coefficients, our approach requires no training. Then, we propose a mixture modeling approach that greatly reduces inference overhead raised by dynamic interpolation. We validate DaWin on the large-scale visual recognition benchmarks, spanning 14 tasks across robust fine-tuning -- ImageNet and derived five distribution shift benchmarks -- and multi-task learning with eight classification tasks. Results demonstrate that DaWin achieves significant performance gain in considered settings, with minimal computational overhead. We further discuss DaWin's analytic behavior to explain its empirical success.
Authors: Po-han Li, Sandeep P. Chinchali, Ufuk Topcu
Abstract: Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical similarity analysis (CSA), which uses two unimodal encoders to replicate multimodal encoders using limited data. CSA maps unimodal features into a multimodal space, using a new similarity score to retain only the multimodal information. CSA only involves the inference of unimodal encoders and a cubic-complexity matrix decomposition, eliminating the need for extensive GPU-based model training. Experiments show that CSA outperforms CLIP while requiring $50,000\times$ fewer multimodal data pairs to bridge the modalities given pre-trained unimodal encoders on ImageNet classification and misinformative news caption detection. CSA surpasses the state-of-the-art method to map unimodal features to multimodal features. We also demonstrate the ability of CSA with modalities beyond image and text, paving the way for future modality pairs with limited paired multimodal data but abundant unpaired unimodal data, such as lidar and text.
Authors: Kevin Galim, Wonjun Kang, Yuchen Zeng, Hyung Il Koo, Kangwook Lee
Abstract: Deep State Space Models (SSMs), such as Mamba (Gu & Dao, 2024), have become powerful tools for language modeling, offering high performance and linear scalability with sequence length. However, the application of parameter-efficient fine-tuning (PEFT) methods to SSM-based models remains underexplored. We start by investigating two fundamental questions on existing PEFT methods: (i) How do they perform on SSM-based models? (ii) Which parameters should they target for optimal results? Our analysis shows that LoRA and its variants consistently outperform all other PEFT methods. While LoRA is effective for linear projection matrices, it fails on SSM modules-yet still outperforms other methods applicable to SSMs, indicating their limitations. This underscores the need for a specialized SSM tuning approach. To address this, we propose Sparse Dimension Tuning (SDT), a PEFT method tailored for SSM modules. Combining SDT for SSMs with LoRA for linear projection matrices, we achieve state-of-the-art performance across extensive experiments.
Authors: Shiyu Wang, Jiawei Li, Xiaoming Shi, Zhou Ye, Baichuan Mo, Wenze Lin, Shengtong Ju, Zhixuan Chu, Ming Jin
Abstract: Time series analysis plays a critical role in numerous applications, supporting tasks such as forecasting, classification, anomaly detection, and imputation. In this work, we present the time series pattern machine (TSPM), a model designed to excel in a broad range of time series tasks through powerful representation and pattern extraction capabilities. Traditional time series models often struggle to capture universal patterns, limiting their effectiveness across diverse tasks. To address this, we define multiple scales in the time domain and various resolutions in the frequency domain, employing various mixing strategies to extract intricate, task-adaptive time series patterns. Specifically, we introduce a general-purpose TSPM that processes multi-scale time series using (1) multi-resolution time imaging (MRTI), (2) time image decomposition (TID), (3) multi-scale mixing (MCM), and (4) multi-resolution mixing (MRM) to extract comprehensive temporal patterns. MRTI transforms multi-scale time series into multi-resolution time images, capturing patterns across both temporal and frequency domains. TID leverages dual-axis attention to extract seasonal and trend patterns, while MCM hierarchically aggregates these patterns across scales. MRM adaptively integrates all representations across resolutions. This method achieves state-of-the-art performance across 8 time series analytical tasks, consistently surpassing both general-purpose and task-specific models. Our work marks a promising step toward the next generation of TSPMs, paving the way for further advancements in time series analysis.
Authors: Weikai Li, Ding Wang, Zijian Ding, Atefeh Sohrabizadeh, Zongyue Qin, Jason Cong, Yizhou Sun
Abstract: High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called "kernel") and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To train the hierarchical MoE stably, we further propose a two-stage training method to avoid expert polarization. Extensive experiments verify the effectiveness of the proposed hierarchical MoE. We publicized our codes at https://github.com/weikai-li/HierarchicalMoE.
Authors: Fang Sun, Zijie Huang, Haixin Wang, Huacong Tang, Xiao Luo, Wei Wang, Yizhou Sun
Abstract: Accurately predicting long-horizon molecular dynamics (MD) trajectories remains a significant challenge, as existing deep learning methods often struggle to retain fidelity over extended simulations. We hypothesize that one key factor limiting accuracy is the difficulty of capturing interactions that span distinct spatial and temporal scales-ranging from high-frequency local vibrations to low-frequency global conformational changes. To address these limitations, we propose Graph Fourier Neural ODEs (GF-NODE), integrating a graph Fourier transform for spatial frequency decomposition with a Neural ODE framework for continuous-time evolution. Specifically, GF-NODE first decomposes molecular configurations into multiple spatial frequency modes using the graph Laplacian, then evolves the frequency components in time via a learnable Neural ODE module that captures both local and global dynamics, and finally reconstructs the updated molecular geometry through an inverse graph Fourier transform. By explicitly modeling high- and low-frequency phenomena in this unified pipeline, GF-NODE more effectively captures long-range correlations and local fluctuations alike. Experimental results on challenging MD benchmarks, including MD17 and alanine dipeptide, demonstrate that GF-NODE achieves state-of-the-art accuracy while preserving essential geometrical features over extended simulations. These findings highlight the promise of bridging spectral decomposition with continuous-time modeling to improve the robustness and predictive power of MD simulations.
Authors: Rania Briq, Jiangtao Wang, Stefan Kesselheim
Abstract: Data pruning is the problem of identifying a core subset that is most beneficial to training and discarding the remainder. While pruning strategies are well studied for discriminative models like those used in classification, little research has gone into their application to generative models. Generative models aim to estimate the underlying distribution of the data, so presumably they should benefit from larger datasets. In this work we aim to shed light on the accuracy of this statement, specifically answer the question of whether data pruning for generative diffusion models could have a positive impact. Contrary to intuition, we show that eliminating redundant or noisy data in large datasets is beneficial particularly when done strategically. We experiment with several pruning methods including recent-state-of-art methods, and evaluate over CelebA-HQ and ImageNet datasets. We demonstrate that a simple clustering method outperforms other sophisticated and computationally demanding methods. We further exhibit how we can leverage clustering to balance skewed datasets in an unsupervised manner to allow fair sampling for underrepresented populations in the data distribution, which is a crucial problem in generative models.
Authors: Stefan Uhlich, Andrea Bonetti, Arun Venkitaraman, Ali Momeni, Ryoga Matsuo, Chia-Yu Hsieh, Eisaku Ohbuchi, Lorenzo Servadei
Abstract: Designing integrated circuits involves substantial complexity, posing challenges in revealing its potential applications - from custom digital cells to analog circuits. Despite extensive research over the past decades in building versatile and automated frameworks, there remains open room to explore more computationally efficient AI-based solutions. This paper introduces the graph composer GraCo, a novel method for synthesizing integrated circuits using reinforcement learning (RL). GraCo learns to construct a graph step-by-step, which is then converted into a netlist and simulated with SPICE. We demonstrate that GraCo is highly configurable, enabling the incorporation of prior design knowledge into the framework. We formalize how this prior knowledge can be utilized and, in particular, show that applying consistency checks enhances the efficiency of the sampling process. To evaluate its performance, we compare GraCo to a random baseline, which is known to perform well for smaller design space problems. We demonstrate that GraCo can discover circuits for tasks such as generating standard cells, including the inverter and the two-input NAND (NAND2) gate. Compared to a random baseline, GraCo requires 5x fewer sampling steps to design an inverter and successfully synthesizes a NAND2 gate that is 2.5x faster.
Authors: Deep Chakraborty, Yann LeCun, Tim G. J. Rudner, Erik Learned-Miller
Abstract: A number of different architectures and loss functions have been applied to the problem of self-supervised learning (SSL), with the goal of developing embeddings that provide the best possible pre-training for as-yet-unknown, lightly supervised downstream tasks. One of these SSL criteria is to maximize the entropy of a set of embeddings in some compact space. But the goal of maximizing the embedding entropy often depends -- whether explicitly or implicitly -- upon high dimensional entropy estimates, which typically perform poorly in more than a few dimensions. In this paper, we motivate an effective entropy maximization criterion (E2MC), defined in terms of easy-to-estimate, low-dimensional constraints. We demonstrate that using it to continue training an already-trained SSL model for only a handful of epochs leads to a consistent and, in some cases, significant improvement in downstream performance. We perform careful ablation studies to show that the improved performance is due to the proposed add-on criterion. We also show that continued pre-training with alternative criteria does not lead to notable improvements, and in some cases, even degrades performance.
Authors: Mingming Zhang, Jiahao Hu, Pengfei Shi, Ningtao Wang, Ruizhe Gao, Guandong Sun, Feng Zhao, Yulin kang, Xing Fu, Weiqiang Wang, Junbo Zhao
Abstract: Tabular data plays a critical role in real-world financial scenarios. Traditionally, tree models have dominated in handling tabular data. However, financial datasets in the industry often encounter some challenges, such as data heterogeneity, the predominance of numerical features and the large scale of the data, which can range from tens of millions to hundreds of millions of records. These challenges can lead to significant memory and computational issues when using tree-based models. Consequently, there is a growing need for neural network-based solutions that can outperform these models. In this paper, we introduce TKGMLP, an hybrid network for tabular data that combines shallow Kolmogorov Arnold Networks with Gated Multilayer Perceptron. This model leverages the strengths of both architectures to improve performance and scalability. We validate TKGMLP on a real-world credit scoring dataset, where it achieves state-of-the-art results and outperforms current benchmarks. Furthermore, our findings demonstrate that the model continues to improve as the dataset size increases, making it highly scalable. Additionally, we propose a novel feature encoding method for numerical data, specifically designed to address the predominance of numerical features in financial datasets. The integration of this feature encoding method within TKGMLP significantly improves prediction accuracy. This research not only advances table prediction technology but also offers a practical and effective solution for handling large-scale numerical tabular data in various industrial applications.
Authors: Zhejun Zhang, Peter Karkus, Maximilian Igl, Wenhao Ding, Yuxiao Chen, Boris Ivanovic, Marco Pavone
Abstract: Traffic simulation aims to learn a policy for traffic agents that, when unrolled in closed-loop, faithfully recovers the joint distribution of trajectories observed in the real world. Inspired by large language models, tokenized multi-agent policies have recently become the state-of-the-art in traffic simulation. However, they are typically trained through open-loop behavior cloning, and thus suffer from covariate shift when executed in closed-loop during simulation. In this work, we present Closest Among Top-K (CAT-K) rollouts, a simple yet effective closed-loop fine-tuning strategy to mitigate covariate shift. CAT-K fine-tuning only requires existing trajectory data, without reinforcement learning or generative adversarial imitation. Concretely, CAT-K fine-tuning enables a small 7M-parameter tokenized traffic simulation policy to outperform a 102M-parameter model from the same model family, achieving the top spot on the Waymo Sim Agent Challenge leaderboard at the time of submission. The code is available at https://github.com/NVlabs/catk.
Authors: Yi-Ping Chen, Vispi Karkaria, Ying-Kuan Tsai, Faith Rolark, Daniel Quispe, Robert X. Gao, Jian Cao, Wei Chen
Abstract: Digital Twin -- a virtual replica of a physical system enabling real-time monitoring, model updating, prediction, and decision-making -- combined with recent advances in machine learning, offers new opportunities for proactive control strategies in autonomous manufacturing. However, achieving real-time decision-making with Digital Twins requires efficient optimization driven by accurate predictions of highly nonlinear manufacturing systems. This paper presents a simultaneous multi-step Model Predictive Control (MPC) framework for real-time decision-making, using a multivariate deep neural network, named Time-Series Dense Encoder (TiDE), as the surrogate model. Unlike conventional MPC models which only provide one-step ahead prediction, TiDE is capable of predicting future states within the prediction horizon in one shot (multi-step), significantly accelerating the MPC. Using Directed Energy Deposition (DED) additive manufacturing as a case study, we demonstrate the effectiveness of the proposed MPC in achieving melt pool temperature tracking to ensure part quality, while reducing porosity defects by regulating laser power to maintain melt pool depth constraints. In this work, we first show that TiDE is capable of accurately predicting melt pool temperature and depth. Second, we demonstrate that the proposed MPC achieves precise temperature tracking while satisfying melt pool depth constraints within a targeted dilution range (10\%-30\%), reducing potential porosity defects. Compared to PID controller, the MPC results in smoother and less fluctuating laser power profiles with competitive or superior melt pool temperature control performance. This demonstrates the MPC's proactive control capabilities, leveraging time-series prediction and real-time optimization, positioning it as a powerful tool for future Digital Twin applications and real-time process optimization in manufacturing.
Authors: Kristof Meding
Abstract: What constitutes a fair decision? This question is not only difficult for humans but becomes more challenging when Artificial Intelligence (AI) models are used. In light of discriminatory algorithmic behaviors, the EU has recently passed the AI Act, which mandates specific rules for AI models, incorporating both traditional legal non-discrimination regulations and machine learning based algorithmic fairness concepts. This paper aims to bridge these two different concepts in the AI Act through: First a high-level introduction of both concepts targeting legal and computer science-oriented scholars, and second an in-depth analysis of the AI Act's relationship between legal non-discrimination regulations and algorithmic fairness. Our analysis reveals three key findings: (1.), most non-discrimination regulations target only high-risk AI systems. (2.), the regulation of high-risk systems encompasses both data input requirements and output monitoring, though these regulations are often inconsistent and raise questions of computational feasibility. (3.) Regulations for General Purpose AI Models, such as Large Language Models that are not simultaneously classified as high-risk systems, currently lack specificity compared to other regulations. Based on these findings, we recommend developing more specific auditing and testing methodologies for AI systems. This paper aims to serve as a foundation for future interdisciplinary collaboration between legal scholars and computer science-oriented machine learning researchers studying discrimination in AI systems.
Authors: Taehan Kim, Wonduk Seo
Abstract: Global climate change has reduced crop resilience and pesticide efficacy, making reliance on synthetic pesticides inevitable, even though their widespread use poses significant health and environmental risks. While these pesticides remain a key tool in pest management, previous machine-learning applications in pesticide and agriculture have focused on classification or regression, leaving the fundamental challenge of generating new molecular structures or designing novel candidates unaddressed. In this paper, we propose Pesti-Gen, a novel generative model based on variational auto-encoders, designed to create pesticide candidates with optimized properties for the first time. Specifically, Pesti-Gen leverages a two-stage learning process: an initial pre-training phase that captures a generalized chemical structure representation, followed by a fine-tuning stage that incorporates toxicity-specific information. The model simultaneously optimizes over multiple toxicity metrics, such as (1) livestock toxicity and (2) aqua toxicity to generate environmentally friendly pesticide candidates. Notably, Pesti-Gen achieves approximately 68\% structural validity in generating new molecular structures, demonstrating the model's effectiveness in producing optimized and feasible pesticide candidates, thereby providing a new way for safer and more sustainable pest management solutions.
Authors: Milad Khademi Nori, Il-Min Kim, Guanghui Wang
Abstract: Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forgetting due to class imbalance at each client and global forgetting due to class imbalance across clients. We develop a mathematical framework for FCIL that formulates local and global forgetting. Then, we propose an approach called Hybrid Rehearsal (HR), which utilizes latent exemplars and data-free techniques to address local and global forgetting, respectively. HR employs a customized autoencoder designed for both data classification and the generation of synthetic data. To determine the embeddings of new tasks for all clients in the latent space of the encoder, the server uses the Lennard-Jones Potential formulations. Meanwhile, at the clients, the decoder decodes the stored low-dimensional latent space exemplars back to the high-dimensional input space, used to address local forgetting. To overcome global forgetting, the decoder generates synthetic data. Furthermore, our mathematical framework proves that our proposed approach HR can, in principle, tackle the two local and global forgetting challenges. In practice, extensive experiments demonstrate that while preserving privacy, our proposed approach outperforms the state-of-the-art baselines on multiple FCIL benchmarks with low compute and memory footprints.
Authors: Phil Ostheimer, Marius Kloft, Sophie Fellenz
Abstract: Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific considerations. This study addresses this gap by creating generic, sentence-level style embeddings crucial for style-centric tasks. Our approach is grounded on the premise that low-level text style changes can compose any high-level style. We hypothesize that applying this concept to representation learning enables the development of versatile text style embeddings. By fine-tuning a general-purpose text encoder using contrastive learning and standard cross-entropy loss, we aim to capture these low-level style shifts, anticipating that they offer insights applicable to high-level text styles. The outcomes prompt us to reconsider the underlying assumptions as the results do not always show that the learned style representations capture high-level text styles.
Authors: Muhammad Bilal Shahid, Cody Fleming
Abstract: Deep learning models are often trained to approximate dynamical systems that can be modeled using differential equations. These models are optimized to predict one step ahead and produce calibrated predictions if the predictive model can quantify uncertainty, such as deep ensembles. At inference time, multi-step predictions are generated via autoregression, which needs a sound uncertainty propagation method (e.g., Trajectory Sampling) to produce calibrated multi-step predictions. This paper introduces an approach named HopCast that uses the Modern Hopfield Network (MHN) to learn the residuals of a deterministic model that approximates the dynamical system. The MHN predicts the density of residuals based on a context vector at any timestep during autoregression. This approach produces calibrated multi-step predictions without uncertainty propagation and turns a deterministic model into a calibrated probabilistic model. This work is also the first to benchmark existing uncertainty propagation methods based on calibration errors with deep ensembles for multi-step predictions.
Authors: Sagi Meir, Tommer D. Keidar, Shlomi Reuveni, Barak Hirshberg
Abstract: Machine learning models have become indispensable tools in applications across the physical sciences. Their training is often time-consuming, vastly exceeding the inference timescales. Several protocols have been developed to perturb the learning process and improve the training, such as shrink and perturb, warm restarts, and stochastic resetting. For classifiers, these perturbations have been shown to result in enhanced speedups or improved generalization. However, the design of such perturbations is usually done ad hoc by intuition and trial and error. To rationally optimize training protocols, we frame them as first-passage processes and consider their response to perturbations. We show that if the unperturbed learning process reaches a quasi-steady state, the response at a single perturbation frequency can predict the behavior at a wide range of frequencies. We employ this approach to a CIFAR-10 classifier using the ResNet-18 model and identify a useful perturbation and frequency among several possibilities. Our work allows optimization of perturbations for improving the training of machine learning models using a first-passage approach.
Authors: Pawel Renc, Michal K. Grzeszczyk, Nassim Oufattole, Deirdre Goode, Yugang Jia, Szymon Bieganski, Matthew B. A. McDermott, Jaroslaw Was, Anthony E. Samir, Jonathan W. Cunningham, David W. Bates, Arkadiusz Sitek
Abstract: The U.S. allocates nearly 18% of its GDP to healthcare but experiences lower life expectancy and higher preventable death rates compared to other high-income nations. Hospitals struggle to predict critical outcomes such as mortality, ICU admission, and prolonged hospital stays. Traditional early warning systems, like NEWS and MEWS, rely on static variables and fixed thresholds, limiting their adaptability, accuracy, and personalization. We developed the Enhanced Transformer for Health Outcome Simulation (ETHOS), an AI model that tokenizes patient health timelines (PHTs) from EHRs and uses transformer-based architectures to predict future PHTs. The Adaptive Risk Estimation System (ARES) leverages ETHOS to compute dynamic, personalized risk probabilities for clinician-defined critical events. ARES also features a personalized explainability module highlighting key clinical factors influencing risk estimates. We evaluated ARES on the MIMIC-IV v2.2 dataset in emergency department settings, benchmarking its performance against traditional early warning systems and machine learning models. From 299,721 unique patients, 285,622 PHTs (60% with hospital admissions) were processed, comprising over 357 million tokens. ETHOS outperformed benchmark models in predicting hospital admissions, ICU admissions, and prolonged stays, achieving superior AUC scores. Its risk estimates were robust across demographic subgroups, with calibration curves confirming model reliability. The explainability module provided valuable insights into patient-specific risk factors. ARES, powered by ETHOS, advances predictive healthcare AI by delivering dynamic, real-time, personalized risk estimation with patient-specific explainability. Its adaptability and accuracy offer a transformative tool for clinical decision-making, potentially improving patient outcomes and resource allocation.
Authors: Heyang Zhao, Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang
Abstract: Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the theoretical difference between KL-regularized RL and standard RL remains largely under-explored. While there is a recent line of work on the theoretical analysis of KL-regularized objective in decision making \citep{xiong2024iterative, xie2024exploratory,zhao2024sharp}, these analyses either reduce to the traditional RL setting or rely on strong coverage assumptions. In this paper, we propose an optimism-based KL-regularized online contextual bandit algorithm, and provide a novel analysis of its regret. By carefully leveraging the benign optimization landscape induced by the KL-regularization and the optimistic reward estimation, our algorithm achieves an $\mathcal{O}\big(\eta\log (N_{\mathcal R} T)\cdot d_{\mathcal R}\big)$ logarithmic regret bound, where $\eta, N_{\mathcal R},T,d_{\mathcal R}$ denote the KL-regularization parameter, the cardinality of the reward function class, number of rounds, and the complexity of the reward function class. Furthermore, we extend our algorithm and analysis to reinforcement learning by developing a novel decomposition over transition steps and also obtain a similar logarithmic regret bound.
Authors: Adam N. Elmachtoub, Henry Lam, Haixiang Lan, Haofeng Zhang
Abstract: Data-driven optimization aims to translate a machine learning model into decision-making by optimizing decisions on estimated costs. Such a pipeline can be conducted by fitting a distributional model which is then plugged into the target optimization problem. While this fitting can utilize traditional methods such as maximum likelihood, a more recent approach uses estimation-optimization integration that minimizes decision error instead of estimation error. Although intuitive, the statistical benefit of the latter approach is not well understood yet is important to guide the prescriptive usage of machine learning. In this paper, we dissect the performance comparisons between these approaches in terms of the amount of model misspecification. In particular, we show how the integrated approach offers a ``universal double benefit'' on the top two dominating terms of regret when the underlying model is misspecified, while the traditional approach can be advantageous when the model is nearly well-specified. Our comparison is powered by finite-sample tail regret bounds that are derived via new higher-order expansions of regrets and the leveraging of a recent Berry-Esseen theorem.
Authors: Yuyang Huang, Yuhan Liu, Haryadi S. Gunawi, Beibin Li, Changho Hwang
Abstract: Continual learning has become a promising solution to refine large language models incrementally by leveraging user feedback. In particular, online continual learning - iteratively training the model with small batches of user feedback - has demonstrated notable performance improvements. However, the existing practice of separating training and serving processes forces the online trainer to recompute the intermediate results already done during serving. Such redundant computations can account for 30%-42% of total training time. In this paper, we propose Alchemist, to the best of our knowledge, the first online continual learning system that efficiently reuses serving activations to increase training throughput. Alchemist introduces two key techniques: (1) recording and storing activations and KV cache only during the prefill phase to minimize latency and memory overhead; and (2) smart activation offloading and hedging. Evaluations with inputs of varied token length sampled from ShareGPT dataset show that compared with a separate training cluster, Alchemist significantly increases training throughput by up to 1.72x, reduces up to 47% memory usage during training, and supports up to 2x more training tokens - all while maintaining negligible impact on serving latency.
Authors: Haoxin Liu, Zhiyuan Zhao, Shiduo Li, B. Aditya Prakash
Abstract: Reasoning ability is crucial for solving challenging tasks. With the advancement of foundation models, such as the emergence of large language models (LLMs), a wide range of reasoning strategies has been proposed, including test-time enhancements, such as Chain-ofThought, and post-training optimizations, as used in DeepSeek-R1. While these reasoning strategies have demonstrated effectiveness across various challenging language or vision tasks, their applicability and impact on time-series forecasting (TSF), particularly the challenging zero-shot TSF, remain largely unexplored. In particular, it is unclear whether zero-shot TSF benefits from reasoning and, if so, what types of reasoning strategies are most effective. To bridge this gap, we propose ReC4TS, the first benchmark that systematically evaluates the effectiveness of popular reasoning strategies when applied to zero-shot TSF tasks. ReC4TS conducts comprehensive evaluations across datasets spanning eight domains, covering both unimodal and multimodal with short-term and longterm forecasting tasks. More importantly, ReC4TS provides key insights: (1) Self-consistency emerges as the most effective test-time reasoning strategy; (2) Group-relative policy optimization emerges as a more suitable approach for incentivizing reasoning ability during post-training; (3) Multimodal TSF benefits more from reasoning strategies compared to unimodal TSF. Beyond these insights, ReC4TS establishes two pioneering starting blocks to support future zero-shot TSF reasoning research: (1) A novel dataset, TimeThinking, containing forecasting samples annotated with reasoning trajectories from multiple advanced LLMs, and (2) A new and simple test-time scaling-law validated on foundational TSF models enabled by self-consistency reasoning strategy. All data and code are publicly accessible at: https://github.com/AdityaLab/OpenTimeR
Authors: Leonardo Berti, Flavio Giorgi, Gjergji Kasneci
Abstract: Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters and the magnitude of the training datasets, has been linked to various so-called emergent abilities that were previously unobserved. These emergent abilities, ranging from advanced reasoning and in-context learning to coding and problem-solving, have sparked an intense scientific debate: Are they truly emergent, or do they simply depend on external factors, such as training dynamics, the type of problems, or the chosen metric? What underlying mechanism causes them? Despite their transformative potential, emergent abilities remain poorly understood, leading to misconceptions about their definition, nature, predictability, and implications. In this work, we shed light on emergent abilities by conducting a comprehensive review of the phenomenon, addressing both its scientific underpinnings and real-world consequences. We first critically analyze existing definitions, exposing inconsistencies in conceptualizing emergent abilities. We then explore the conditions under which these abilities appear, evaluating the role of scaling laws, task complexity, pre-training loss, quantization, and prompting strategies. Our review extends beyond traditional LLMs and includes Large Reasoning Models (LRMs), which leverage reinforcement learning and inference-time search to amplify reasoning and self-reflection. However, emergence is not inherently positive. As AI systems gain autonomous reasoning capabilities, they also develop harmful behaviors, including deception, manipulation, and reward hacking. We highlight growing concerns about safety and governance, emphasizing the need for better evaluation frameworks and regulatory oversight.
Authors: Talha Bozkus, Urbashi Mitra
Abstract: Q-learning is a widely used reinforcement learning (RL) algorithm for optimizing wireless networks, but faces challenges with large state-spaces. Recently proposed multi-environment mixed Q-learning (MEMQ) algorithm addresses these challenges by employing multiple Q-learning algorithms across multiple synthetically generated, distinct but structurally related environments, so-called digital cousins. In this paper, we propose a novel multi-agent MEMQ (M-MEMQ) for cooperative decentralized wireless networks with multiple networked transmitters (TXs) and base stations (BSs). TXs do not have access to global information (joint state and actions). The new concept of coordinated and uncoordinated states is introduced. In uncoordinated states, TXs act independently to minimize their individual costs and update local Q-functions. In coordinated states, TXs use a Bayesian approach to estimate the joint state and update the joint Q-functions. The cost of information-sharing scales linearly with the number of TXs and is independent of the joint state-action space size. Several theoretical guarantees, including deterministic and probabilistic convergence, bounds on estimation error variance, and the probability of misdetecting the joint states, are given. Numerical simulations show that M-MEMQ outperforms several decentralized and centralized training with decentralized execution (CTDE) multi-agent RL algorithms by achieving 55% lower average policy error (APE), 35% faster convergence, 50% reduced runtime complexity, and 45% less sample complexity. Furthermore, M-MEMQ achieves comparable APE with significantly lower complexity than centralized methods. Simulations validate the theoretical analyses.
Authors: Youssef Mroueh
Abstract: Group Relative Policy Optimization (GRPO) was introduced and used successfully to train DeepSeek R1 models for promoting reasoning capabilities of LLMs using verifiable or binary rewards. We show in this paper that GRPO with verifiable rewards can be written as a Kullback Leibler ($\mathsf{KL}$) regularized contrastive loss, where the contrastive samples are synthetic data sampled from the old policy. The optimal GRPO policy $\pi_{n}$ can be expressed explicitly in terms of the binary reward, as well as the first and second order statistics of the old policy ($\pi_{n-1}$) and the reference policy $\pi_0$. Iterating this scheme, we obtain a sequence of policies $\pi_{n}$ for which we can quantify the probability of success $p_n$. We show that the probability of success of the policy satisfies a recurrence that converges to a fixed point of a function that depends on the initial probability of success $p_0$ and the regularization parameter $\beta$ of the $\mathsf{KL}$ regularizer. We show that the fixed point $p^*$ is guaranteed to be larger than $p_0$, thereby demonstrating that GRPO effectively amplifies the probability of success of the policy.
Authors: Pranjal Awasthi, Sreenivas Gollapudi, Ravi Kumar, Kamesh Munagala
Abstract: We present a novel way to integrate flexible, context-dependent constraints into combinatorial optimization by leveraging Large Language Models (LLMs) alongside traditional algorithms. Although LLMs excel at interpreting nuanced, locally specified requirements, they struggle with enforcing global combinatorial feasibility. To bridge this gap, we propose an iterated fine-tuning framework where algorithmic feedback progressively refines the LLM's output distribution. Interpreting this as simulated annealing, we introduce a formal model based on a "coarse learnability" assumption, providing sample complexity bounds for convergence. Empirical evaluations on scheduling, graph connectivity, and clustering tasks demonstrate that our framework balances the flexibility of locally expressed constraints with rigorous global optimization more effectively compared to baseline sampling methods. Our results highlight a promising direction for hybrid AI-driven combinatorial reasoning.
Authors: Dylan J. Foster, Zakaria Mhammedi, Dhruv Rohatgi
Abstract: Language model alignment (or, reinforcement learning) techniques that leverage active exploration -- deliberately encouraging the model to produce diverse, informative responses -- offer the promise of super-human capabilities. However, current understanding of algorithm design primitives for computationally efficient exploration with language models is limited. To better understand how to leverage access to powerful pre-trained generative models to improve the efficiency of exploration, we introduce a new computational framework for RL with language models, in which the learner interacts with the model through a sampling oracle. Focusing on the linear softmax model parameterization, we provide new results that reveal the computational-statistical tradeoffs of efficient exploration: 1. Necessity of coverage: Coverage refers to the extent to which the pre-trained model covers near-optimal responses -- a form of hidden knowledge. We show that coverage, while not necessary for data efficiency, lower bounds the runtime of any algorithm in our framework. 2. Inference-time exploration: We introduce a new algorithm, SpannerSampling, which obtains optimal data efficiency and is computationally efficient whenever the pre-trained model enjoys sufficient coverage, matching our lower bound. SpannerSampling leverages inference-time computation with the pre-trained model to reduce the effective search space for exploration. 3. Insufficiency of training-time interventions: We contrast the result above by showing that training-time interventions that produce proper policies cannot achieve similar guarantees in polynomial time. 4. Computational benefits of multi-turn exploration: Finally, we show that under additional representational assumptions, one can achieve improved runtime (replacing sequence-level coverage with token-level coverage) through multi-turn exploration.
Authors: Guanyu Chen, Shengze Xu, Dong Ni, Tieyong Zeng
Abstract: We propose a general framework for the Discontinuous Galerkin-induced Neural Network (DGNN), inspired by the Interior Penalty Discontinuous Galerkin Method (IPDGM). In this approach, the trial space consists of piecewise neural network space defined over the computational domain, while the test function space is composed of piecewise polynomials. We demonstrate the advantages of DGNN in terms of accuracy and training efficiency across several numerical examples, including stationary and time-dependent problems. Specifically, DGNN easily handles high perturbations, discontinuous solutions, and complex geometric domains.
Authors: Bharat Srikishan, Daniel O'Malley, Mohamed Mehana, Nicholas Lubbers, Nikhil Muralidhar
Abstract: Modeling the evolution of physical systems is critical to many applications in science and engineering. As the evolution of these systems is governed by partial differential equations (PDEs), there are a number of computational simulations which resolve these systems with high accuracy. However, as these simulations incur high computational costs, they are infeasible to be employed for large-scale analysis. A popular alternative to simulators are neural network surrogates which are trained in a data-driven manner and are much more computationally efficient. However, these surrogate models suffer from high rollout error when used autoregressively, especially when confronted with training data paucity. Existing work proposes to improve surrogate rollout error by either including physical loss terms directly in the optimization of the model or incorporating computational simulators as `differentiable layers' in the neural network. Both of these approaches have their challenges, with physical loss functions suffering from slow convergence for stiff PDEs and simulator layers requiring gradients which are not always available, especially in legacy simulators. We propose the Hybrid PDE Predictor with Reinforcement Learning (HyPER) model: a model-agnostic, RL based, cost-aware model which combines a neural surrogate, RL decision model, and a physics simulator (with or without gradients) to reduce surrogate rollout error significantly. In addition to reducing in-distribution rollout error by 47%-78%, HyPER learns an intelligent policy that is adaptable to changing physical conditions and resistant to noise corruption. Code available at https://github.com/scailab/HyPER.
Authors: Nicholas Roberts, Niladri Chatterji, Sharan Narang, Mike Lewis, Dieuwke Hupkes
Abstract: Scaling laws are a critical component of the LLM development pipeline, most famously as a way to forecast training decisions such as 'compute-optimally' trading-off parameter count and dataset size, alongside a more recent growing list of other crucial decisions. In this work, we ask whether compute-optimal scaling behaviour can be skill-dependent. In particular, we examine knowledge and reasoning-based skills such as knowledge-based QA and code generation, and we answer this question in the affirmative: scaling laws are skill-dependent. Next, to understand whether skill-dependent scaling is an artefact of the pretraining datamix, we conduct an extensive ablation of different datamixes and find that, also when correcting for datamix differences, knowledge and code exhibit fundamental differences in scaling behaviour. We conclude with an analysis of how our findings relate to standard compute-optimal scaling using a validation set, and find that a misspecified validation set can impact compute-optimal parameter count by nearly 50%, depending on its skill composition.
Authors: Xuanke Jiang, Kohei Hatano, Eiji Takimoto
Abstract: We consider a good arm identification problem in a stochastic bandit setting with multi-objectives, where each arm $i\in[K]$ is associated with a distribution $\mathcal{D}_i$ defined over $\mathbb{R}^M$. For each round $t$, the player/algorithm pulls one arm $i_t$ and receives a $M$ dimensional vector feedback sampled according to $\mathcal{D}_{i_t}$. The target is twofold, one is finding one arm whose means are larger than the predefined thresholds $\xi_1,\ldots,\xi_M$ with a confidence bound $\delta$ and an accuracy rate $\epsilon$ with a bounded sample complexity, the other is output $\bot$ to indicate no such arm exists. We propose an algorithm with a sample complexity bound. Our bound is the same as the one given in the previous work when $M=1$ and $\epsilon = 0$, and we give novel bounds for $M > 1$ and $\epsilon > 0$. The proposed algorithm attains better numerical performance than other baselines in the experiments on synthetic and real datasets.
Authors: Luyuan Xie, Tianyu Luan, Wenyuan Cai, Guochen Yan, Zhaoyu Chen, Nan Xi, Yuejian Fang, Qingni Shen, Zhonghai Wu, Junsong Yuan
Abstract: Federated learning has wide applications in the medical field. It enables knowledge sharing among different healthcare institutes while protecting patients' privacy. However, existing federated learning systems are typically centralized, requiring clients to upload client-specific knowledge to a central server for aggregation. This centralized approach would integrate the knowledge from each client into a centralized server, and the knowledge would be already undermined during the centralized integration before it reaches back to each client. Besides, the centralized approach also creates a dependency on the central server, which may affect training stability if the server malfunctions or connections are unstable. To address these issues, we propose a decentralized federated learning framework named dFLMoE. In our framework, clients directly exchange lightweight head models with each other. After exchanging, each client treats both local and received head models as individual experts, and utilizes a client-specific Mixture of Experts (MoE) approach to make collective decisions. This design not only reduces the knowledge damage with client-specific aggregations but also removes the dependency on the central server to enhance the robustness of the framework. We validate our framework on multiple medical tasks, demonstrating that our method evidently outperforms state-of-the-art approaches under both model homogeneity and heterogeneity settings.
Authors: Ho Kei Cheng, Alexander Schwing
Abstract: Minibatch optimal transport coupling straightens paths in unconditional flow matching. This leads to computationally less demanding inference as fewer integration steps and less complex numerical solvers can be employed when numerically solving an ordinary differential equation at test time. However, in the conditional setting, minibatch optimal transport falls short. This is because the default optimal transport mapping disregards conditions, resulting in a conditionally skewed prior distribution during training. In contrast, at test time, we have no access to the skewed prior, and instead sample from the full, unbiased prior distribution. This gap between training and testing leads to a subpar performance. To bridge this gap, we propose conditional optimal transport C^2OT that adds a conditional weighting term in the cost matrix when computing the optimal transport assignment. Experiments demonstrate that this simple fix works with both discrete and continuous conditions in 8gaussians-to-moons, CIFAR-10, ImageNet-32x32, and ImageNet-256x256. Our method performs better overall compared to the existing baselines across different function evaluation budgets. Code is available at https://hkchengrex.github.io/C2OT
Authors: Marjan Famili, Jola Mirecka, Camila Rangel Smith, Anna Kota\'nska, Nikolai Juraschko, Beatriz Costa-Gomes, Colin M. Palmer, Jeyan Thiyagalingam, Tom Burnley, Mark Basham, Alan R. Lowe
Abstract: Learning compact and interpretable representations of data is a critical challenge in scientific image analysis. Here, we introduce Affinity-VAE, a generative model that enables us to impose our scientific intuition about the similarity of instances in the dataset on the learned representation during training. We demonstrate the utility of the approach in the scientific domain of cryo-electron tomography (cryo-ET) where a significant current challenge is to identify similar molecules within a noisy and low contrast tomographic image volume. This task is distinct from classification in that, at inference time, it is unknown whether an instance is part of the training set or not. We trained affinity-VAE using prior knowledge of protein structure to inform the latent space. Our model is able to create rotationally-invariant, morphologically homogeneous clusters in the latent representation, with improved cluster separation compared to other approaches. It achieves competitive performance on protein classification with the added benefit of disentangling object pose, structural similarity and an interpretable latent representation. In the context of cryo-ET data, affinity-VAE captures the orientation of identified proteins in 3D which can be used as a prior for subsequent scientific experiments. Extracting physical principles from a trained network is of significant importance in scientific imaging where a ground truth training set is not always feasible.
Authors: Murray Z. Frank, Jing Gao, Keer Yang
Abstract: Machine learning algorithms are known to outperform human analysts in predicting corporate earnings, leading to their rapid adoption. However, we show that leading methods (XGBoost, neural nets, ChatGPT) systematically overreact to news. The overreaction is primarily due to biases in the training data and we show that it cannot be eliminated without compromising accuracy. Analysts with machine learning training overreact much less than do traditional analysts. We provide a model showing that there is a tradeoff between predictive power and rational behavior. Our findings suggest that AI tools reduce but do not eliminate behavioral biases in financial markets.
Authors: Felix Jimenez, Matthias Katzfuss
Abstract: For regression tasks, standard Gaussian processes (GPs) provide natural uncertainty quantification (UQ), while deep neural networks (DNNs) excel at representation learning. Deterministic UQ methods for neural networks have successfully combined the two and require only a single pass through the neural network. However, current methods necessitate changes to network training to address feature collapse, where unique inputs map to identical feature vectors. We propose an alternative solution, the deep Vecchia ensemble (DVE), which allows deterministic UQ to work in the presence of feature collapse, negating the need for network retraining. DVE comprises an ensemble of GPs built on hidden-layer outputs of a DNN, achieving scalability via Vecchia approximations that leverage nearest-neighbor conditional independence. DVE is compatible with pretrained networks and incurs low computational overhead. We demonstrate DVE's utility on several datasets and carry out experiments to understand the inner workings of the proposed method.
Authors: Vlad Hondru, Radu Tudor Ionescu
Abstract: Diffusion models showcase strong capabilities in image synthesis, being used in many computer vision tasks with great success. To this end, we propose to explore a new use case, namely to copy black-box classification models without having access to the original training data, the architecture, and the weights of the model, i.e. the model is only exposed through an inference API. More specifically, we can only observe the (soft or hard) labels for some image samples passed as input to the model. Furthermore, we consider an additional constraint limiting the number of model calls, mostly focusing our research on few-call model stealing. In order to solve the model extraction task given the applied restrictions, we propose the following framework. As training data, we create a synthetic data set (called proxy data set) by leveraging the ability of diffusion models to generate realistic and diverse images. Given a maximum number of allowed API calls, we pass the respective number of samples through the black-box model to collect labels. Finally, we distill the knowledge of the black-box teacher (attacked model) into a student model (copy of the attacked model), harnessing both labeled and unlabeled data generated by the diffusion model. We employ a novel active self-paced learning framework to make the most of the proxy data during distillation. Our empirical results on three data sets confirm the superiority of our framework over four state-of-the-art methods in the few-call model extraction scenario. We release our code for free non-commercial use at https://github.com/vladhondru25/model-stealing.
Authors: Hu Wang, Congbo Ma, Jianpeng Zhang, Yuan Zhang, Jodie Avery, Louise Hull, Gustavo Carneiro
Abstract: The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more compared to other modalities, and if those important modalities are missing, the model performance drops significantly. Such fact remains unexplored by current multi-modal approaches that recover the representation from missing modalities by feature reconstruction or blind feature aggregation from other modalities, instead of extracting useful information from the best performing modalities. In this paper, we propose a Learnable Cross-modal Knowledge Distillation (LCKD) model to adaptively identify important modalities and distil knowledge from them to help other modalities from the cross-modal perspective for solving the missing modality issue. Our approach introduces a teacher election procedure to select the most ``qualified'' teachers based on their single modality performance on certain tasks. Then, cross-modal knowledge distillation is performed between teacher and student modalities for each task to push the model parameters to a point that is beneficial for all tasks. Hence, even if the teacher modalities for certain tasks are missing during testing, the available student modalities can accomplish the task well enough based on the learned knowledge from their automatically elected teacher modalities. Experiments on the Brain Tumour Segmentation Dataset 2018 (BraTS2018) shows that LCKD outperforms other methods by a considerable margin, improving the state-of-the-art performance by 3.61% for enhancing tumour, 5.99% for tumour core, and 3.76% for whole tumour in terms of segmentation Dice score.
Authors: Borja Aizpurua, Pablo Bermejo, Josu Etxezarreta Martinez, Roman Orus
Abstract: Here we introduce an improved approach to Variational Quantum Attack Algorithms (VQAA) on crytographic protocols. Our methods provide robust quantum attacks to well-known cryptographic algorithms, more efficiently and with remarkably fewer qubits than previous approaches. We implement simulations of our attacks for symmetric-key protocols such as S-DES, S-AES and Blowfish. For instance, we show how our attack allows a classical simulation of a small 8-qubit quantum computer to find the secret key of one 32-bit Blowfish instance with 24 times fewer number of iterations than a brute-force attack. Our work also shows improvements in attack success rates for lightweight ciphers such as S-DES and S-AES. Further applications beyond symmetric-key cryptography are also discussed, including asymmetric-key protocols and hash functions. In addition, we also comment on potential future improvements of our methods. Our results bring one step closer assessing the vulnerability of large-size classical cryptographic protocols with Noisy Intermediate-Scale Quantum (NISQ) devices, and set the stage for future research in quantum cybersecurity.
Authors: Hengxu Yu, Xiao Li
Abstract: We consider the stochastic gradient method with random reshuffling ($\mathsf{RR}$) for tackling smooth nonconvex optimization problems. $\mathsf{RR}$ finds broad applications in practice, notably in training neural networks. In this work, we provide high probability first-order and second-order complexity guarantees for this method. First, we establish a high probability first-order sample complexity result for driving the Euclidean norm of the gradient (without taking expectation) below $\varepsilon$. Our derived complexity matches the best existing in-expectation one up to a logarithmic term while imposing no additional assumptions nor changing $\mathsf{RR}$'s updating rule. We then propose a simple and computable stopping criterion for $\mathsf{RR}$ (denoted as $\mathsf{RR}$-$\mathsf{sc}$). This criterion is guaranteed to be triggered after a finite number of iterations, enabling us to prove a high probability first-order complexity guarantee for the last iterate. Second, building on the proposed stopping criterion, we design a perturbed random reshuffling method ($\mathsf{p}$-$\mathsf{RR}$) that involves an additional randomized perturbation procedure near stationary points. We derive that $\mathsf{p}$-$\mathsf{RR}$ provably escapes strict saddle points and establish a high probability second-order complexity result, without requiring any sub-Gaussian tail-type assumptions on the stochastic gradient errors. The fundamental ingredient in deriving the aforementioned results is the new concentration property for sampling without replacement in $\mathsf{RR}$, which could be of independent interest. Finally, we conduct numerical experiments on neural network training to support our theoretical findings.
Authors: Mingyan Zhu, Yiming Li, Junfeng Guo, Tao Wei, Shu-Tao Xia, Zhan Qin
Abstract: Currently, sample-specific backdoor attacks (SSBAs) are the most advanced and malicious methods since they can easily circumvent most of the current backdoor defenses. In this paper, we reveal that SSBAs are not sufficiently stealthy due to their poisoned-label nature, where users can discover anomalies if they check the image-label relationship. In particular, we demonstrate that it is ineffective to directly generalize existing SSBAs to their clean-label variants by poisoning samples solely from the target class. We reveal that it is primarily due to two reasons, including \textbf{(1)} the `antagonistic effects' of ground-truth features and \textbf{(2)} the learning difficulty of sample-specific features. Accordingly, trigger-related features of existing SSBAs cannot be effectively learned under the clean-label setting due to their mild trigger intensity required for ensuring stealthiness. We argue that the intensity constraint of existing SSBAs is mostly because their trigger patterns are `content-irrelevant' and therefore act as `noises' for both humans and DNNs. Motivated by this understanding, we propose to exploit content-relevant features, $a.k.a.$ (human-relied) attributes, as the trigger patterns to design clean-label SSBAs. This new attack paradigm is dubbed backdoor attack with attribute trigger (BAAT). Extensive experiments are conducted on benchmark datasets, which verify the effectiveness of our BAAT and its resistance to existing defenses.
Authors: F. Fernando Jurado-Lasso, J. F. Jurado, Xenofon Fafoutis
Abstract: Wireless Sensor Networks (WSNs) play a pivotal role in enabling Internet of Things (IoT) devices with sensing and actuation capabilities. Operating in remote and resource-constrained environments, these IoT devices face challenges related to energy consumption, crucial for network longevity. Existing clustering protocols often suffer from high control overhead, inefficient cluster formation, and poor adaptability to dynamic network conditions, leading to suboptimal data transmission and reduced network lifetime. This paper introduces Low-Energy Adaptive Clustering Hierarchy with Reinforcement Learning-based Controller (LEACH-RLC), a novel clustering protocol designed to address these limitations by employing a Mixed Integer Linear Programming (MILP) approach for strategic selection of Cluster Heads (CHs) and node-to-cluster assignments. Additionally, it integrates a Reinforcement Learning (RL) agent to minimize control overhead by learning optimal timings for generating new clusters. LEACH-RLC aims to balance control overhead reduction without compromising overall network performance. Through extensive simulations, this paper investigates the frequency and opportune moments for generating new clustering solutions. Results demonstrate the superior performance of LEACH-RLC over state-of-the-art protocols, showcasing enhanced network lifetime, reduced average energy consumption, and minimized control overhead. The proposed protocol contributes to advancing the efficiency and adaptability of WSNs, addressing critical challenges in IoT deployments.
Authors: Sobihan Surendran (LPSM), Antoine Godichon-Baggioni (LPSM), Adeline Fermanian (LPSM), Sylvain Le Corff (LPSM)
Abstract: Stochastic Gradient Descent (SGD) with adaptive steps is widely used to train deep neural networks and generative models. Most theoretical results assume that it is possible to obtain unbiased gradient estimators, which is not the case in several recent deep learning and reinforcement learning applications that use Monte Carlo methods. This paper provides a comprehensive non-asymptotic analysis of SGD with biased gradients and adaptive steps for non-convex smooth functions. Our study incorporates time-dependent bias and emphasizes the importance of controlling the bias of the gradient estimator. In particular, we establish that Adagrad, RMSProp, and AMSGRAD, an exponential moving average variant of Adam, with biased gradients, converge to critical points for smooth non-convex functions at a rate similar to existing results in the literature for the unbiased case. Finally, we provide experimental results using Variational Autoenconders (VAE) and applications to several learning frameworks that illustrate our convergence results and show how the effect of bias can be reduced by appropriate hyperparameter tuning.
Authors: Amin Karimi Monsefi, Payam Karisani, Mengxi Zhou, Stacey Choi, Nathan Doble, Heng Ji, Srinivasan Parthasarathy, Rajiv Ramnath
Abstract: Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment, these methods are usually used to process a large volume of data on a daily basis, imposing a high maintenance cost on medical facilities. In this paper, we introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method to mitigate such challenges. LoGoNet integrates a novel feature extractor within a U-shaped architecture, leveraging Large Kernel Attention (LKA) and a dual encoding strategy to capture both long-range and short-range feature dependencies adeptly. This is in contrast to existing methods that rely on increasing network capacity to enhance feature extraction. This combination of novel techniques in our model is especially beneficial in medical image segmentation, given the difficulty of learning intricate and often irregular body organ shapes, such as the spleen. Complementary, we propose a novel SSL method tailored for 3D images to compensate for the lack of large labeled datasets. The method combines masking and contrastive learning techniques within a multi-task learning framework and is compatible with both Vision Transformer (ViT) and CNN-based models. We demonstrate the efficacy of our methods in numerous tasks across two standard datasets (i.e., BTCV and MSD). Benchmark comparisons with eight state-of-the-art models highlight LoGoNet's superior performance in both inference time and accuracy.
Authors: Meiyi Zhu, Caili Guo, Chunyan Feng, Osvaldo Simeone
Abstract: In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the performance of the likelihood ratio attack (LiRA) within an information-theoretical framework that allows the investigation of the impact of the aleatoric uncertainty in the true data generation process, of the epistemic uncertainty caused by a limited training data set, and of the calibration level of the target model. We compare three different settings, in which the attacker receives decreasingly informative feedback from the target model: confidence vector (CV) disclosure, in which the output probability vector is released; true label confidence (TLC) disclosure, in which only the probability assigned to the true label is made available by the model; and decision set (DS) disclosure, in which an adaptive prediction set is produced as in conformal prediction. We derive bounds on the advantage of an MIA adversary with the aim of offering insights into the impact of uncertainty and calibration on the effectiveness of MIAs. Simulation results demonstrate that the derived analytical bounds predict well the effectiveness of MIAs.
Authors: Nina Vesseron, Marco Cuturi
Abstract: In 1991, Brenier proved a theorem that generalizes the polar decomposition for square matrices -- factored as PSD $\times$ unitary -- to any vector field $F:\mathbb{R}^d\rightarrow \mathbb{R}^d$. The theorem, known as the polar factorization theorem, states that any field $F$ can be recovered as the composition of the gradient of a convex function $u$ with a measure-preserving map $M$, namely $F=\nabla u \circ M$. We propose a practical implementation of this far-reaching theoretical result, and explore possible uses within machine learning. The theorem is closely related to optimal transport (OT) theory, and we borrow from recent advances in the field of neural optimal transport to parameterize the potential $u$ as an input convex neural network. The map $M$ can be either evaluated pointwise using $u^*$, the convex conjugate of $u$, through the identity $M=\nabla u^* \circ F$, or learned as an auxiliary network. Because $M$ is, in general, not injective, we consider the additional task of estimating the ill-posed inverse map that can approximate the pre-image measure $M^{-1}$ using a stochastic generator. We illustrate possible applications of Brenier's polar factorization to non-convex optimization problems, as well as sampling of densities that are not log-concave.
Authors: Tim Selig, Thomas M\"arz, Martin Storath, Andreas Weinmann
Abstract: Computed tomography from a low radiation dose (LDCT) is challenging due to high noise in the projection data. Popular approaches for LDCT image reconstruction are two-stage methods, typically consisting of the filtered backprojection (FBP) algorithm followed by a neural network for LDCT image enhancement. Two-stage methods are attractive for their simplicity and potential for computational efficiency, typically requiring only a single FBP and a neural network forward pass for inference. However, the best reconstruction quality is currently achieved by unrolled iterative methods (Learned Primal-Dual and ItNet), which are more complex and thus have a higher computational cost for training and inference. We propose a method combining the simplicity and efficiency of two-stage methods with state-of-the-art reconstruction quality. Our strategy utilizes a neural network pretrained for Gaussian noise removal from natural grayscale images, fine-tuned for LDCT image enhancement. We call this method FBP-DTSGD (Domain and Task Shifted Gaussian Denoisers) as the fine-tuning is a task shift from Gaussian denoising to enhancing LDCT images and a domain shift from natural grayscale to LDCT images. An ablation study with three different pretrained Gaussian denoisers indicates that the performance of FBP-DTSGD does not depend on a specific denoising architecture, suggesting future advancements in Gaussian denoising could benefit the method. The study also shows that pretraining on natural images enhances LDCT reconstruction quality, especially with limited training data. Notably, pretraining involves no additional cost, as existing pretrained models are used. The proposed method currently holds the top mean position in the LoDoPaB-CT challenge.
Authors: Sicen Guo, Ziwei Long, Zhiyuan Wu, Qijun Chen, Ioannis Pitas, Rui Fan
Abstract: Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric prior knowledge acquired by a data-fusion teacher network into a single-modal student network is a practical, albeit less explored research avenue. This article delves into this topic and resorts to knowledge distillation approaches to address this problem. We introduce the Learning to Infuse ''X'' (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects. We present a mathematical proof that underscores the limitation of using a single, fixed weight in decoupled knowledge distillation and introduce a logit-wise dynamic weight controller as a solution to this issue. Furthermore, we develop an adaptively-recalibrated feature distillation algorithm, including two novel techniques: feature recalibration via kernel regression and in-depth feature consistency quantification via centered kernel alignment. Extensive experiments conducted with intermediate-fusion and late-fusion networks across various public datasets provide both quantitative and qualitative evaluations, demonstrating the superior performance of our LIX framework when compared to other state-of-the-art approaches.
Authors: Stefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke, Melvin Sevi, Vincent Tao Hu, Bj\"orn Ommer
Abstract: Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects, particularly the attributes characterizing them, remains a key challenge. While existing methods have introduced mechanisms to modulate attribute expression, they typically provide either detailed, object-specific localization of such a modification or full-scale fine-grained, nuanced control of attributes. No current approach offers both simultaneously, resulting in a gap when trying to achieve precise continuous and subject-specific attribute modulation in image generation. In this work, we demonstrate that token-level directions exist within commonly used CLIP text embeddings that enable fine-grained, subject-specific control of high-level attributes in T2I models. We introduce two methods to identify these directions: a simple, optimization-free technique and a learning-based approach that utilizes the T2I model to characterize semantic concepts more specifically. Our methods allow the augmentation of the prompt text input, enabling fine-grained control over multiple attributes of individual subjects simultaneously, without requiring any modifications to the diffusion model itself. This approach offers a unified solution that fills the gap between global and localized control, providing competitive flexibility and precision in text-guided image generation. Project page: https://compvis.github.io/attribute-control. Code is available at https://github.com/CompVis/attribute-control.
URLs: https://compvis.github.io/attribute-control., https://github.com/CompVis/attribute-control.
Authors: Johannes Sahlmann, Pablo G\'omez
Abstract: The third Gaia data release (DR3) contains $\sim$170\,000 astrometric orbit solutions of two-body systems located within $\sim$500 pc of the Sun. Determining component masses in these systems, in particular of stars hosting exoplanets, usually hinges on incorporating complementary observations in addition to the astrometry, e.g. spectroscopy and radial velocities. Several Gaia DR3 two-body systems with exoplanet, brown-dwarf, stellar, and black-hole components have been confirmed in this way. We developed an alternative machine learning approach that uses only the Gaia DR3 orbital solutions with the aim of identifying the best candidates for exoplanets and brown-dwarf companions. Based on confirmed substellar companions in the literature, we use semi-supervised anomaly detection methods in combination with extreme gradient boosting and random forest classifiers to determine likely low-mass outliers in the population of non-single sources. We employ and study feature importance to investigate the method's plausibility and produced a list of 20 best candidates of which two are exoplanet candidates and another five are either very-massive brown dwarfs or very-low mass stars. Three candidates, including one initial exoplanet candidate, correspond to false-positive solutions where longer-period binary star motion was fitted with a biased shorter-period orbit. We highlight nine candidates with brown-dwarf companions for preferential follow-up. The companion around the Sun-like star G\,15-6 could be confirmed as a genuine brown dwarf using external radial-velocity data. This new approach is a powerful complement to the traditional identification methods for substellar companions among Gaia astrometric orbits. It is particularly relevant in the context of Gaia DR4 and its expected exoplanet discovery yield.
Authors: Seamus Somerstep, Felipe Maia Polo, Moulinath Banerjee, Ya'acov Ritov, Mikhail Yurochkin, Yuekai Sun
Abstract: Modern large language model (LLM) alignment techniques rely on human feedback, but it is unclear whether these techniques fundamentally limit the capabilities of aligned LLMs. In particular, it is unknown if it is possible to align (stronger) LLMs with superhuman capabilities with (weaker) human feedback without degrading their capabilities. This is an instance of the weak-to-strong generalization problem: using feedback from a weaker (less capable) model to train a stronger (more capable) model. We prove that weak-to-strong generalization is possible by eliciting latent knowledge from pre-trained LLMs. In particular, we cast the weak-to-strong generalization problem as a transfer learning problem in which we wish to transfer a latent concept prior from a weak model to a strong pre-trained model. We prove that a naive fine-tuning approach suffers from fundamental limitations, but an alternative refinement-based approach suggested by the problem structure provably overcomes the limitations of fine-tuning. Finally, we demonstrate the practical applicability of the refinement approach in multiple LLM alignment tasks.
Authors: Duy-Kien Nguyen, Mahmoud Assran, Unnat Jain, Martin R. Oswald, Cees G. M. Snoek, Xinlei Chen
Abstract: This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can operate by directly treating each individual pixel as a token and achieve highly performant results. This is substantially different from the popular design in Vision Transformer, which maintains the inductive bias from ConvNets towards local neighborhoods (e.g. by treating each 16x16 patch as a token). We showcase the effectiveness of pixels-as-tokens across three well-studied computer vision tasks: supervised learning for classification and regression, self-supervised learning via masked autoencoding, and image generation with diffusion models. Although it's computationally less practical to directly operate on individual pixels, we believe the community must be made aware of this surprising piece of knowledge when devising the next generation of neural network architectures for computer vision.
Authors: Benjamin L. Badger
Abstract: Attention mechanisms that confer selective focus on a strict subset of input elements are nearly ubiquitous in language models today. We posit there to be downside to the use of attention: most input information is lost. In support of this idea we observe poor input representation accuracy in transformers and more accurate representation in what we term masked mixers, which replace self-attention with masked convolutions. The masked mixer learns causal language modeling more efficiently than early transformer implementations and even outperforms optimized, current transformers when training on small ($n_{ctx}<512$) but not larger context windows. Evidence is presented for the hypothesis that differences in transformer and masked mixer training efficiencies for various tasks are best predicted by input representation accuracy, or equivalently global invertibility. We hypothesize that the information loss exhibited by transformers would be more detrimental to retrieval than generation, as the former is more closely approximated by a bijective and thus invertible function. We find that masked mixers are more effective retrieval models both when the pretrained embedding model is unchanged as well as when the embedding model is modified via cosine similarity-based InfoNCE loss minimization. A small masked mixer is shown to outperform a large and near state-of-the-art transformer-based retrieval model, despite the latter being trained with many orders of magnitude more data and compute.
Authors: Yifan Zhang, Yang Yuan, Andrew Chi-Chih Yao
Abstract: We introduce Diagram of Thought (DoT), a framework that models iterative reasoning in large language models (LLMs) as the construction of a directed acyclic graph (DAG) within a single model. Unlike conventional approaches that represent reasoning as linear chains or tree structures, DoT organizes propositions, critiques, refinements, and verifications into a unified DAG, enabling the exploration of complex reasoning pathways while preserving logical consistency. In this framework, each node encapsulates a proposition at various stages of evaluation, thereby facilitating iterative self-improvement through detailed natural language feedback. By leveraging auto-regressive next-token prediction augmented with role-specific tokens, DoT seamlessly transitions between generating ideas and engaging in critical evaluation, offering richer, context-aware feedback than binary signals. Moreover, we establish a rigorous mathematical foundation for DoT through Topos Theory, ensuring soundness and consistency in the reasoning process. This integrated approach not only simplifies both training and inference by eliminating the need for multiple models or external control mechanisms but also provides a principled framework for the design of next-generation reasoning-specialized models.
Authors: Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, Mirella Lapata
Abstract: Writing compelling fiction is a multifaceted process combining elements such as crafting a plot, developing interesting characters, and using evocative language. While large language models (LLMs) show promise for story writing, they currently rely heavily on intricate prompting, which limits their use. We propose Agents' Room, a generation framework inspired by narrative theory, that decomposes narrative writing into subtasks tackled by specialized agents. To illustrate our method, we introduce Tell Me A Story, a high-quality dataset of complex writing prompts and human-written stories, and a novel evaluation framework designed specifically for assessing long narratives. We show that Agents' Room generates stories that are preferred by expert evaluators over those produced by baseline systems by leveraging collaboration and specialization to decompose the complex story writing task into tractable components. We provide extensive analysis with automated and human-based metrics of the generated output.
Authors: Payam Saeedi, Mahsa Goodarzi, M Abdullah Canbaz
Abstract: We investigate the presence of cognitive biases in three large language models (LLMs): GPT-4o, Gemma 2, and Llama 3.1. The study uses 1,500 experiments across nine established cognitive biases to evaluate the models' responses and consistency. GPT-4o demonstrated the strongest overall performance. Gemma 2 showed strengths in addressing the sunk cost fallacy and prospect theory, however its performance varied across different biases. Llama 3.1 consistently underperformed, relying on heuristics and exhibiting frequent inconsistencies and contradictions. The findings highlight the challenges of achieving robust and generalizable reasoning in LLMs, and underscore the need for further development to mitigate biases in artificial general intelligence (AGI). The study emphasizes the importance of integrating statistical reasoning and ethical considerations in future AI development.
Authors: Tobias Leemann, Periklis Petridis, Giuseppe Vietri, Dionysis Manousakas, Aaron Roth, Sergul Aydore
Abstract: While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy involves prompting the LLM again to assess whether its response is grounded in the retrieved evidence, but this approach is costly. Alternatively, lightweight natural language inference (NLI) models for efficient grounding verification can be used at inference time. While existing pre-trained NLI models offer potential solutions, their performance remains subpar compared to larger models on realistic RAG inputs. RAG inputs are more complex than most datasets used for training NLI models and have characteristics specific to the underlying knowledge base, requiring adaptation of the NLI models to a specific target domain. Additionally, the lack of labeled instances in the target domain makes supervised domain adaptation, e.g., through fine-tuning, infeasible. To address these challenges, we introduce Automatic Generative Domain Adaptation (Auto-GDA). Our framework enables unsupervised domain adaptation through synthetic data generation. Unlike previous methods that rely on handcrafted filtering and augmentation strategies, Auto-GDA employs an iterative process to continuously improve the quality of generated samples using weak labels from less efficient teacher models and discrete optimization to select the most promising augmented samples. Experimental results demonstrate the effectiveness of our approach, with models fine-tuned on synthetic data using Auto-GDA often surpassing the performance of the teacher model and reaching the performance level of LLMs at 10% of their computational cost.
Authors: Jan Vrba, Jakub Steinbach, Tom\'a\v{s} Jirsa, Laura Verde, Roberta De Fazio, Yuwen Zeng, Kei Ichiji, Luk\'a\v{s} H\'ajek, Zuzana Sedl\'akov\'a, Zuzana Urb\'aniov\'a, Martin Chovanec, Jan Mare\v{s}, Noriyasu Homma
Abstract: Purpose: We introduce a novel methodology for voice pathology detection using the publicly available Saarbr\"ucken Voice Database (SVD) and a robust feature set combining commonly used acoustic handcrafted features with two novel ones: pitch difference (relative variation in fundamental frequency) and NaN feature (failed fundamental frequency estimation). Methods: We evaluate six machine learning (ML) algorithms -- support vector machine, k-nearest neighbors, naive Bayes, decision tree, random forest, and AdaBoost -- using grid search for feasible hyperparameters and 20480 different feature subsets. Top 1000 classification models -- feature subset combinations for each ML algorithm are validated with repeated stratified cross-validation. To address class imbalance, we apply K-Means SMOTE to augment the training data. Results: Our approach achieves 85.61%, 84.69% and 85.22% unweighted average recall (UAR) for females, males and combined results respectively. We intentionally omit accuracy as it is a highly biased metric for imbalanced data. Conclusion: Our study demonstrates that by following the proposed methodology and feature engineering, there is a potential in detection of various voice pathologies using ML models applied to the simplest vocal task, a sustained utterance of the vowel /a:/. To enable easier use of our methodology and to support our claims, we provide a publicly available GitHub repository with DOI 10.5281/zenodo.13771573. Finally, we provide a REFORMS checklist to enhance readability, reproducibility and justification of our approach
Authors: Shaohao Rui, Lingzhi Chen, Zhenyu Tang, Lilong Wang, Mianxin Liu, Shaoting Zhang, Xiaosong Wang
Abstract: Self-supervised learning has greatly facilitated medical image analysis by suppressing the training data requirement for real-world applications. Current paradigms predominantly rely on self-supervision within uni-modal image data, thereby neglecting the inter-modal correlations essential for effective learning of cross-modal image representations. This limitation is particularly significant for naturally grouped multi-modal data, e.g., multi-parametric MRI scans for a patient undergoing various functional imaging protocols in the same study. To bridge this gap, we conduct a novel multi-modal image pre-training with three proxy tasks to facilitate the learning of cross-modality representations and correlations using multi-modal brain MRI scans (over 2.4 million images in 16,022 scans of 3,755 patients), i.e., cross-modal image reconstruction, modality-aware contrastive learning, and modality template distillation. To demonstrate the generalizability of our pre-trained model, we conduct extensive experiments on various benchmarks with ten downstream tasks. The superior performance of our method is reported in comparison to state-of-the-art pre-training methods, with Dice Score improvement of 0.28\%-14.47\% across six segmentation benchmarks and a consistent accuracy boost of 0.65\%-18.07\% in four individual image classification tasks.
Authors: Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal
Abstract: Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation remove harmful concepts from models but face several challenges: (1) They cannot instantly remove harmful concepts without training. (2) Their safe generation capabilities depend on collected training data. (3) They alter model weights, risking degradation in quality for content unrelated to toxic concepts. To address these, we propose SAFREE, a novel, training-free approach for safe T2I and T2V, that does not alter the model's weights. Specifically, we detect a subspace corresponding to a set of toxic concepts in the text embedding space and steer prompt embeddings away from this subspace, thereby filtering out harmful content while preserving intended semantics. To balance the trade-off between filtering toxicity and preserving safe concepts, SAFREE incorporates a novel self-validating filtering mechanism that dynamically adjusts the denoising steps when applying the filtered embeddings. Additionally, we incorporate adaptive re-attention mechanisms within the diffusion latent space to selectively diminish the influence of features related to toxic concepts at the pixel level. In the end, SAFREE ensures coherent safety checking, preserving the fidelity, quality, and safety of the output. SAFREE achieves SOTA performance in suppressing unsafe content in T2I generation compared to training-free baselines and effectively filters targeted concepts while maintaining high-quality images. It also shows competitive results against training-based methods. We extend SAFREE to various T2I backbones and T2V tasks, showcasing its flexibility and generalization. SAFREE provides a robust and adaptable safeguard for ensuring safe visual generation.
Authors: Jean Barbier, Francesco Camilli, Justin Ko, Koki Okajima
Abstract: Matrix denoising is central to signal processing and machine learning. Its statistical analysis when the matrix to infer has a factorised structure with a rank growing proportionally to its dimension remains a challenge, except when it is rotationally invariant. In this case the information theoretic limits and an efficient Bayes-optimal denoising algorithm, called rotational invariant estimator [1,2], are known. Beyond this setting few results can be found. The reason is that the model is not a usual spin system because of the growing rank dimension, nor a matrix model (as appearing in high-energy physics) due to the lack of rotation symmetry, but rather a hybrid between the two. Here we make progress towards the understanding of Bayesian matrix denoising when the signal is a factored matrix $XX^\intercal$ that is not rotationally invariant. Monte Carlo simulations suggest the existence of a \emph{denoising-factorisation transition} separating a phase where denoising using the rotational invariant estimator remains Bayes-optimal due to universality properties of the same nature as in random matrix theory, from one where universality breaks down and better denoising is possible, though algorithmically hard. We argue that it is only beyond the transition that factorisation, i.e., estimating $X$ itself, becomes possible up to irresolvable ambiguities. On the theory side, we combine mean-field techniques in an interpretable multiscale fashion in order to access the minimum mean-square error and mutual information. Interestingly, our alternative method yields equations reproducible by the replica approach of [3]. Using numerical insights, we delimit the portion of phase diagram where we conjecture the mean-field theory to be exact, and correct it using universality when it is not. Our complete ansatz matches well the numerics in the whole phase diagram when considering finite size effects.
Authors: Cristiano Patr\'icio, Lu\'is F. Teixeira, Jo\~ao C. Neves
Abstract: The main challenges hindering the adoption of deep learning-based systems in clinical settings are the scarcity of annotated data and the lack of interpretability and trust in these systems. Concept Bottleneck Models (CBMs) offer inherent interpretability by constraining the final disease prediction on a set of human-understandable concepts. However, this inherent interpretability comes at the cost of greater annotation burden. Additionally, adding new concepts requires retraining the entire system. In this work, we introduce a novel two-step methodology that addresses both of these challenges. By simulating the two stages of a CBM, we utilize a pretrained Vision Language Model (VLM) to automatically predict clinical concepts, and an off-the-shelf Large Language Model (LLM) to generate disease diagnoses based on the predicted concepts. Furthermore, our approach supports test-time human intervention, enabling corrections to predicted concepts, which improves final diagnoses and enhances transparency in decision-making. We validate our approach on three skin lesion datasets, demonstrating that it outperforms traditional CBMs and state-of-the-art explainable methods, all without requiring any training and utilizing only a few annotated examples. The code is available at https://github.com/CristianoPatricio/2-step-concept-based-skin-diagnosis.
URLs: https://github.com/CristianoPatricio/2-step-concept-based-skin-diagnosis.
Authors: Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck, Estelle Aflalo, Shao-Yen Tseng, Vasudev Lal, Phillip Howard
Abstract: Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses are influenced by societal biases present in their training datasets, leading to undesirable differences in how the model responds when presented with images depicting people of different demographics. In this work, we propose a training-free debiasing framework for LMMs that intervenes on the model's representations during text generation by constructing a steering vector that reduces reference on protected attributes. Our framework introduces two complementary methods: (1) a dataset-based approach that constructs a steering vector by contrasting model activations on biased and neutral inputs, and (2) a novel optimization-based approach designed for low-resource settings, which constructs the steering vector using a single step of gradient-based perturbation without requiring additional data. Our experiments show that these interventions effectively reduce the propensity of LMMs to generate text related to protected attributes while maintaining sentiment and fluency. Furthermore, we demonstrate that debiased LMMs achieve comparable accuracy to their unmodified counterparts on downstream tasks, indicating that bias mitigation can be achieved without sacrificing model performance.
Authors: Jake Buzhardt, C. Ricardo Constante-Amores, Michael D. Graham
Abstract: This work explores the relationship between state space methods and Koopman operator-based methods for predicting the time-evolution of nonlinear dynamical systems. We demonstrate that extended dynamic mode decomposition with dictionary learning (EDMD-DL), when combined with a state space projection, is equivalent to a neural network representation of the nonlinear discrete-time flow map on the state space. We highlight how this projection step introduces nonlinearity into the evolution equations, enabling significantly improved EDMD-DL predictions. With this projection, EDMD-DL leads to a nonlinear dynamical system on the state space, which can be represented in either discrete or continuous time. This system has a natural structure for neural networks, where the state is first expanded into a high dimensional feature space followed by a linear mapping which represents the discrete-time map or the vector field as a linear combination of these features. Inspired by these observations, we implement several variations of neural ordinary differential equations (ODEs) and EDMD-DL, developed by combining different aspects of their respective model structures and training procedures. We evaluate these methods using numerical experiments on chaotic dynamics in the Lorenz system and a nine-mode model of turbulent shear flow, showing comparable performance across methods in terms of short-time trajectory prediction, reconstruction of long-time statistics, and prediction of rare events. These results highlight the equivalence of the EDMD-DL implementation with a state space projection to a neural ODE representation of the dynamics. We also show that these methods provide comparable performance to a non-Markovian approach in terms of prediction of extreme events.
Authors: Nazia Tasnim, Bryan A. Plummer
Abstract: Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to capture relevant information without affecting predictions on previously learned categories. While these adaptors are generally more efficient than finetuning the entire network, they still require tens to hundreds of thousands of task-specific trainable parameters even for relatively small networks, making it challenging to operate on resource-constrained environments with high communication costs like edge devices or mobile phones. Thus, we propose Reparameterized, Compact weight Adaptation for Sequential Tasks (RECAST), a novel method that dramatically reduces task-specific trainable parameters to fewer than 50 - several orders of magnitude less than competing methods like LoRA. RECAST accomplishes this efficiency by learning to decompose layer weights into a soft parameter-sharing framework consisting of shared weight templates and very few module-specific scaling factors or coefficients. This soft parameter-sharing framework allows for effective task-wise reparameterization by tuning only these coefficients while keeping templates frozen.A key innovation of RECAST is the novel weight reconstruction pipeline called Neural Mimicry, which eliminates the need for pretraining from scratch. This allows for high-fidelity emulation of existing pretrained weights within our framework and provides quick adaptability to any model scale and architecture. Extensive experiments across six datasets demonstrate RECAST outperforms the state-of-the-art by up to 3% across various scales, architectures, and parameter spaces Moreover, we show that RECAST's architecture-agnostic nature allows for seamless integration with existing methods, further boosting performance.
Authors: Xinpeng Liu, Junxuan Liang, Chenshuo Zhang, Zixuan Cai, Cewu Lu, Yong-Lu Li
Abstract: Analyses of human motion kinematics have achieved tremendous advances. However, the production mechanism, known as human dynamics, is still undercovered. In this paper, we aim to push data-driven human dynamics understanding forward. We identify a major obstacle to this as the heterogeneity of existing human motion understanding efforts. Specifically, heterogeneity exists in not only the diverse kinematics representations and hierarchical dynamics representations but also in the data from different domains, namely biomechanics and reinforcement learning. With an in-depth analysis of the existing heterogeneity, we propose to emphasize the beneath homogeneity: all of them represent the homogeneous fact of human motion, though from different perspectives. Given this, we propose Homogeneous Dynamics Space (HDyS) as a fundamental space for human dynamics by aggregating heterogeneous data and training a homogeneous latent space with inspiration from the inverse-forward dynamics procedure. Leveraging the heterogeneous representations and datasets, HDyS achieves decent mapping between human kinematics and dynamics. We demonstrate the feasibility of HDyS with extensive experiments and applications. The project page is https://foruck.github.io/HDyS.
Authors: Noemi Anau Montel, James Alvey, Christoph Weniger
Abstract: Model misspecification analysis strategies, such as anomaly detection, model validation, and model comparison are a key component of scientific model development. Over the last few years, there has been a rapid rise in the use of simulation-based inference (SBI) techniques for Bayesian parameter estimation, applied to increasingly complex forward models. To move towards fully simulation-based analysis pipelines, however, there is an urgent need for a comprehensive simulation-based framework for model misspecification analysis. In this work, we provide a solid and flexible foundation for a wide range of model discrepancy analysis tasks, using distortion-driven model misspecification tests. From a theoretical perspective, we introduce the statistical framework built around performing many hypothesis tests for distortions of the simulation model. We also make explicit analytic connections to classical techniques: anomaly detection, model validation, and goodness-of-fit residual analysis. Furthermore, we introduce an efficient self-calibrating training algorithm that is useful for practitioners. We demonstrate the performance of the framework in multiple scenarios, making the connection to classical results where they are valid. Finally, we show how to conduct such a distortion-driven model misspecification test for real gravitational wave data, specifically on the event GW150914.
Authors: Yuanchang Zhou, Siyu Hu, Chen Wang, Lin-Wang Wang, Guangming Tan, Weile Jia
Abstract: Graph neural network universal interatomic potentials (GNN-UIPs) have demonstrated remarkable generalization and transfer capabilities in material discovery and property prediction. These models can accelerate molecular dynamics (MD) simulation by several orders of magnitude while maintaining \textit{ab initio} accuracy, making them a promising new paradigm in material simulations. One notable example is Crystal Hamiltonian Graph Neural Network (CHGNet), pretrained on the energies, forces, stresses, and magnetic moments from the MPtrj dataset, representing a state-of-the-art GNN-UIP model for charge-informed MD simulations. However, training the CHGNet model is time-consuming(8.3 days on one A100 GPU) for three reasons: (i) requiring multi-layer propagation to reach more distant atom information, (ii) requiring second-order derivatives calculation to finish weights updating and (iii) the implementation of reference CHGNet does not fully leverage the computational capabilities. This paper introduces FastCHGNet, an optimized CHGNet, with three contributions: Firstly, we design innovative Force/Stress Readout modules to decompose Force/Stress prediction. Secondly, we adopt massive optimizations such as kernel fusion, redundancy bypass, etc, to exploit GPU computation power sufficiently. Finally, we extend CHGNet to support multiple GPUs and propose a load-balancing technique to enhance GPU utilization. Numerical results show that FastCHGNet reduces memory footprint by a factor of 3.59. The final training time of FastCHGNet can be decreased to \textbf{1.53 hours} on 32 GPUs without sacrificing model accuracy.
Authors: Zongxia Li, Xiyang Wu, Hongyang Du, Huy Nghiem, Guangyao Shi
Abstract: Multimodal Vision Language Models (VLMs) have emerged as a transformative technology at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification. Despite their rapid advancements in research and growing popularity in applications, a comprehensive survey of existing studies on VLMs is notably lacking, particularly for researchers aiming to leverage VLMs in their specific domains. To this end, we provide a systematic overview of VLMs in the following aspects: model information of the major VLMs developed over the past five years (2019-2024); the main architectures and training methods of these VLMs; summary and categorization of the popular benchmarks and evaluation metrics of VLMs; the applications of VLMs including embodied agents, robotics, and video generation; the challenges and issues faced by current VLMs such as hallucination, fairness, and safety. Detailed collections including papers and model repository links are listed in https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
URLs: https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
Authors: Kelsey Allen, Ishita Dasgupta, Eliza Kosoy, Andrew K. Lampinen
Abstract: Inductive biases are what allow learners to make guesses in the absence of conclusive evidence. These biases have often been studied in cognitive science using concepts or categories -- e.g. by testing how humans generalize a new category from a few examples that leave the category boundary ambiguous. We use these approaches to study generalization in foundation models during in-context learning. Modern foundation models can condition on both vision and text, and differences in how they interpret and learn from these different modalities is an emerging area of study. Here, we study how their generalizations vary by the modality in which stimuli are presented, and the way the stimuli are described in text. We study these biases with three different experimental paradigms, across three different vision-language models. We find that the models generally show some bias towards generalizing according to shape over color. This shape bias tends to be amplified when the examples are presented visually. By contrast, when examples are presented in text, the ordering of adjectives affects generalization. However, the extent of these effects vary across models and paradigms. These results help to reveal how vision-language models represent different types of inputs in context, and may have practical implications for the use of vision-language models.
Authors: Songyuan Zhang, Oswin So, Mitchell Black, Chuchu Fan
Abstract: Control policies that can achieve high task performance and satisfy safety constraints are desirable for any system, including multi-agent systems (MAS). One promising technique for ensuring the safety of MAS is distributed control barrier functions (CBF). However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable. To tackle these challenges, we propose DGPPO, a new framework that simultaneously learns both a discrete graph CBF which handles neighborhood changes and input constraints, and a distributed high-performance safe policy for MAS with unknown discrete-time dynamics. We empirically validate our claims on a suite of multi-agent tasks spanning three different simulation engines. The results suggest that, compared with existing methods, our DGPPO framework obtains policies that achieve high task performance (matching baselines that ignore the safety constraints), and high safety rates (matching the most conservative baselines), with a constant set of hyperparameters across all environments.
Authors: Bidyarthi Paul, Faika Fairuj Preotee, Shuvashis Sarker, Shamim Rahim Refat, Shifat Islam, Tashreef Muhammad, Mohammad Ashraful Hoque, Shahriar Manzoor
Abstract: ANCHOLIK-NER is a linguistically diverse dataset for Named Entity Recognition (NER) in Bangla regional dialects, capturing variations across Sylhet, Chittagong, Barishal, Noakhali, and Mymensingh. The dataset has around 17,405 sentences, 3,481 sentences per region. The data was collected from two publicly available datasets and through web scraping from various online newspapers, articles. To ensure high-quality annotations, the BIO tagging scheme was employed, and professional annotators with expertise in regional dialects carried out the labeling process. The dataset is structured into separate subsets for each region and is available in CSV format. Each entry contains textual data along with identified named entities and their corresponding annotations. Named entities are categorized into ten distinct classes: Person, Location, Organization, Food, Animal, Colour, Role, Relation, Object, and Miscellaneous. This dataset serves as a valuable resource for developing and evaluating NER models for Bangla dialectal variations, contributing to regional language processing and low-resource NLP applications. It can be utilized to enhance NER systems in Bangla dialects, improve regional language understanding, and support applications in machine translation, information retrieval, and conversational AI.
Authors: Zichuan Guo, Mihai Cucuringu, Alexander Y. Shestopaloff
Abstract: We tackle the challenges of modeling high-dimensional data sets, particularly those with latent low-dimensional structures hidden within complex, non-linear, and noisy relationships. Our approach enables a seamless integration of concepts from non-parametric regression, factor models, and neural networks for high-dimensional regression. Our approach introduces PCA and Soft PCA layers, which can be embedded at any stage of a neural network architecture, allowing the model to alternate between factor modeling and non-linear transformations. This flexibility makes our method especially effective for processing hierarchical compositional data. We explore ours and other techniques for imposing low-rank structures on neural networks and examine how architectural design impacts model performance. The effectiveness of our method is demonstrated through simulation studies, as well as applications to forecasting future price movements of equity ETF indices and nowcasting with macroeconomic data.
Authors: Zhuoran Li, Chunming Hu, Junfan Chen, Zhijun Chen, Richong Zhang
Abstract: Word order difference between source and target languages is a major obstacle to cross-lingual transfer, especially in the dependency parsing task. Current works are mostly based on order-agnostic models or word reordering to mitigate this problem. However, such methods either do not leverage grammatical information naturally contained in word order or are computationally expensive as the permutation space grows exponentially with the sentence length. Moreover, the reordered source sentence with an unnatural word order may be a form of noising that harms the model learning. To this end, we propose an Implicit Word Reordering framework with Knowledge Distillation (IWR-KD). This framework is inspired by that deep networks are good at learning feature linearization corresponding to meaningful data transformation, e.g. word reordering. To realize this idea, we introduce a knowledge distillation framework composed of a word-reordering teacher model and a dependency parsing student model. We verify our proposed method on Universal Dependency Treebanks across 31 different languages and show it outperforms a series of competitors, together with experimental analysis to illustrate how our method works towards training a robust parser.
Authors: Dazhou Yu, Riyang Bao, Gengchen Mai, Liang Zhao
Abstract: Spatial reasoning remains a challenge for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses. Experiments on a real-world tourism dataset show that Spatial-RAG significantly improves spatial question answering, bridging the gap between LLMs and spatial intelligence.
Authors: Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Vision-Language Models (VLMs) have demonstrated impressive 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 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: Thomas Budiarjo, Santana Yuda Pradata, Kadek Gemilang Santiyuda, Muhammad Alfian Amrizal, Reza Pulungan, Hiroyuki Takizawa
Abstract: High energy consumption remains a key challenge in high-performance computing (HPC) systems, which often feature hundreds or thousands of nodes drawing substantial power even in idle or standby modes. Although powering down unused nodes can improve energy efficiency, choosing the wrong time to do so can degrade quality of service by delaying job execution. Machine learning, in particular reinforcement learning (RL), has shown promise in determining optimal times to switch nodes on or off. In this study, we enhance the performance of a deep reinforcement learning (DRL) agent for HPC power management by integrating curriculum learning (CL), a training approach that introduces tasks with gradually increasing difficulty. Using the Batsim-py simulation framework, we compare the proposed CL-based agent to both a baseline DRL method (without CL) and the conventional fixed-time timeout strategy. Experimental results confirm that an easy-to-hard curriculum outperforms other training orders in terms of reducing wasted energy usage. The best agent achieves a 3.73% energy reduction over the baseline DRL method and a 4.66% improvement compared to the best timeout configuration (shutdown every 15 minutes of idle time). In addition, it reduces average job waiting time by 9.24% and maintains a higher job-filling rate, indicating more effective resource utilization. Sensitivity tests across various switch-on durations, power levels, and cluster sizes further reveal the agent's adaptability to changing system parameters without retraining. These findings demonstrate that curriculum learning can significantly improve DRL-based power management in HPC, balancing energy savings, quality of service, and robustness to diverse configurations.
Authors: Jingru Jia, Zehua Yuan, Junhao Pan, Paul E. McNamara, Deming Chen
Abstract: Strategic decision-making involves interactive reasoning where agents adapt their choices in response to others, yet existing evaluations of large language models (LLMs) often emphasize Nash Equilibrium (NE) approximation, overlooking the mechanisms driving their strategic choices. To bridge this gap, we introduce an evaluation framework grounded in behavioral game theory, disentangling reasoning capability from contextual effects. Testing 22 state-of-the-art LLMs, we find that GPT-o3-mini, GPT-o1, and DeepSeek-R1 dominate most games yet also demonstrate that the model scale alone does not determine performance. In terms of prompting enhancement, Chain-of-Thought (CoT) prompting is not universally effective, as it increases strategic reasoning only for models at certain levels while providing limited gains elsewhere. Additionally, we investigate the impact of encoded demographic features on the models, observing that certain assignments impact the decision-making pattern. For instance, GPT-4o shows stronger strategic reasoning with female traits than males, while Gemma assigns higher reasoning levels to heterosexual identities compared to other sexual orientations, indicating inherent biases. These findings underscore the need for ethical standards and contextual alignment to balance improved reasoning with fairness.
Authors: Andrei V. Ermolaev, Mathilde Hary, Lev Leybov, Piotr Ryczkowski, Anas Skalli, Daniel Brunner, Go\"ery Genty, John M. Dudley
Abstract: We report a generalized nonlinear Schr\"odinger equation simulation model of an extreme learning machine (ELM) based on optical fiber propagation. Using handwritten digit classification as a benchmark, we study how accuracy depends on propagation dynamics, as well as parameters governing spectral encoding, readout, and noise. Test accuracies of over 91% and 93% are found for propagation in the anomalous and normal dispersion regimes respectively. Our simulation results also suggest that quantum noise on the input pulses introduces an intrinsic penalty to ELM performance.
Authors: S M Sarwar
Abstract: With the increasing prevalence of mental health conditions worldwide, AI-powered chatbots and conversational agents have emerged as accessible tools to support mental health. However, deploying Large Language Models (LLMs) in mental healthcare applications raises significant privacy concerns, especially regarding regulations like HIPAA and GDPR. In this work, we propose FedMentalCare, a privacy-preserving framework that leverages Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) to fine-tune LLMs for mental health analysis. We investigate the performance impact of varying client data volumes and model architectures (e.g., MobileBERT and MiniLM) in FL environments. Our framework demonstrates a scalable, privacy-aware approach for deploying LLMs in real-world mental healthcare scenarios, addressing data security and computational efficiency challenges.
Authors: Yinuo Liu, Zenghui Yuan, Guiyao Tie, Jiawen Shi, Pan Zhou, Lichao Sun, Neil Zhenqiang Gong
Abstract: Multimodal retrieval-augmented generation (RAG) enhances the visual reasoning capability of vision-language models (VLMs) by dynamically accessing information from external knowledge bases. In this work, we introduce \textit{Poisoned-MRAG}, the first knowledge poisoning attack on multimodal RAG systems. Poisoned-MRAG injects a few carefully crafted image-text pairs into the multimodal knowledge database, manipulating VLMs to generate the attacker-desired response to a target query. Specifically, we formalize the attack as an optimization problem and propose two cross-modal attack strategies, dirty-label and clean-label, tailored to the attacker's knowledge and goals. Our extensive experiments across multiple knowledge databases and VLMs show that Poisoned-MRAG outperforms existing methods, achieving up to 98\% attack success rate with just five malicious image-text pairs injected into the InfoSeek database (481,782 pairs). Additionally, We evaluate 4 different defense strategies, including paraphrasing, duplicate removal, structure-driven mitigation, and purification, demonstrating their limited effectiveness and trade-offs against Poisoned-MRAG. Our results highlight the effectiveness and scalability of Poisoned-MRAG, underscoring its potential as a significant threat to multimodal RAG systems.
Authors: Huanhuan Zhao, Ruben Millan-Solsona, Marti Checa, Spenser R. Brown, Jennifer L. Morrell-Falvey, Liam Collins, Arpan Biswas
Abstract: Microscopy is an essential tool in scientific research, enabling the visualization of structures at micro- and nanoscale resolutions. However, the field of microscopy often encounters limitations in field-of-view (FOV), restricting the amount of sample that can be imaged in a single capture. To overcome this limitation, image stitching techniques have been developed to seamlessly merge multiple overlapping images into a single, high-resolution composite. The images collected from microscope need to be optimally stitched before accurate physical information can be extracted from post analysis. However, the existing stitching tools either struggle to stitch images together when the microscopy images are feature sparse or cannot address all the transformations of images. To address these issues, we propose a bi-channel aided feature-based image stitching method and demonstrate its use on AFM generated biofilm images. The topographical channel image of AFM data captures the morphological details of the sample, and a stitched topographical image is desired for researchers. We utilize the amplitude channel of AFM data to maximize the matching features and to estimate the position of the original topographical images and show that the proposed bi-channel aided stitching method outperforms the traditional stitching approach. Furthermore, we found that the differentiation of the topographical images along the x-axis provides similar feature information to the amplitude channel image, which generalizes our approach when the amplitude images are not available. Here we demonstrated the application on AFM, but similar approaches could be employed of optical microscopy with brightfield and fluorescence channels. We believe this proposed workflow will benefit the experimentalist to avoid erroneous analysis and discovery due to incorrect stitching.
Authors: Ziyu Wan, Yunxiang Li, Yan Song, Hanjing Wang, Linyi Yang, Mark Schmidt, Jun Wang, Weinan Zhang, Shuyue Hu, Ying Wen
Abstract: Recent research on Reasoning of Large Language Models (LLMs) has sought to further enhance their performance by integrating meta-thinking -- enabling models to monitor, evaluate, and control their reasoning processes for more adaptive and effective problem-solving. However, current single-agent work lacks a specialized design for acquiring meta-thinking, resulting in low efficacy. To address this challenge, we introduce Reinforced Meta-thinking Agents (ReMA), a novel framework that leverages Multi-Agent Reinforcement Learning (MARL) to elicit meta-thinking behaviors, encouraging LLMs to think about thinking. ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions. Through iterative reinforcement learning with aligned objectives, these agents explore and learn collaboration, leading to improved generalization and robustness. Experimental results demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks, including competitive-level mathematical benchmarks and LLM-as-a-Judge benchmarks. Comprehensive ablation studies further illustrate the evolving dynamics of each distinct agent, providing valuable insights into how the meta-thinking reasoning process enhances the reasoning capabilities of LLMs.
Authors: Karamatou Yacoubou Djima, Ka Man Yim
Abstract: Point signatures based on the Laplacian operators on graphs, point clouds, and manifolds have become popular tools in machine learning for graphs, clustering, and shape analysis. In this work, we propose a novel point signature, the power spectrum signature, a measure on $\mathbb{R}$ defined as the squared graph Fourier transform of a graph signal. Unlike eigenvectors of the Laplacian from which it is derived, the power spectrum signature is invariant under graph automorphisms. We show that the power spectrum signature is stable under perturbations of the input graph with respect to the Wasserstein metric. We focus on the signature applied to classes of indicator functions, and its applications to generating descriptive features for vertices of graphs. To demonstrate the practical value of our signature, we showcase several applications in characterizing geometry and symmetries in point cloud data, and graph regression problems.
Authors: Cyriel Mallart (UR2, LIDILE), Andrew Simpkin (UPCit\'e, ALTAE), Nicolas Ballier (UPCit\'e, ALTAE), Paula Liss\'on (UNIR), R\'emi Venant (UM, LIUM), Jen-Yu Li (UR2, LIDILE), Bernardo Stearns (NUI Galway, INSIGHT), Thomas Gaillat (LIDILE, UR2)
Abstract: This article addresses Second Language (L2) writing development through an investigation of new grammatical and structural complexity metrics. We explore the paradigmatic production in learner English by linking language functions to specific grammatical paradigms. Using the EFCAMDAT as a gold standard and a corpus of French learners as an external test set, we employ a supervised learning framework to operationalise and evaluate seven microsystems. We show that learner levels are associated with the seven microsystems (MS). Using ordinal regression modelling for evaluation, the results show that all MS are significant but yield a low impact if taken individually. However, their influence is shown to be impactful if taken as a group. These microsystems and their measurement method suggest that it is possible to use them as part of broader-purpose CALL systems focused on proficiency assessment.