Authors: Ling Feng, SK Yang
Abstract: In Rectified Flow, by obtaining the rectified flow several times, the mapping relationship between distributions can be distilled into a neural network, and the target distribution can be directly predicted by the straight lines of the flow. However, during the pairing process of the mapping relationship, a large amount of error accumulation will occur, resulting in a decrease in performance after multiple rectifications. In the field of flow models, knowledge distillation of multi - teacher diffusion models is also a problem worthy of discussion in accelerating sampling. I intend to combine multi - teacher knowledge distillation with Bezier curves to solve the problem of error accumulation. Currently, the related paper is being written by myself.
Authors: Aahan Singh, Engin Tekin, Maryam Nadeem, Nancy A. ElNaker, Mohammad Amaan Sayeed, Natalia Vassilieva, Boulbaba Ben Amor
Abstract: Revolutionizing drug discovery demands more than just understanding molecular interactions - it requires generative models that can design novel ligands tailored to specific biological targets. While chemical Language Models (cLMs) have made strides in learning molecular properties, most fail to incorporate target-specific insights, restricting their ability to drive de-novo ligand generation. Chem42, a cutting-edge family of generative chemical Language Models, is designed to bridge this gap. By integrating atomic-level interactions with multimodal inputs from Prot42, a complementary protein Language Model, Chem42 achieves a sophisticated cross-modal representation of molecular structures, interactions, and binding patterns. This innovative framework enables the creation of structurally valid, synthetically accessible ligands with enhanced target specificity. Evaluations across diverse protein targets confirm that Chem42 surpasses existing approaches in chemical validity, target-aware design, and predicted binding affinity. By reducing the search space of viable drug candidates, Chem42 could accelerate the drug discovery pipeline, offering a powerful generative AI tool for precision medicine. Our Chem42 models set a new benchmark in molecule property prediction, conditional molecule generation, and target-aware ligand design. The models are publicly available at huggingface.co/inceptionai.
Authors: Kirill Vishniakov, Boulbaba Ben Amor, Engin Tekin, Nancy A. ElNaker, Karthik Viswanathan, Aleksandr Medvedev, Aahan Singh, Maryam Nadeem, Mohammad Amaan Sayeed, Praveenkumar Kanithi, Tiago Magalhaes, Natalia Vassilieva, Dwarikanath Mahapatra, Marco Pimentel, and Shadab Khan
Abstract: We introduce Gene42, a novel family of Genomic Foundation Models (GFMs) designed to manage context lengths of up to 192,000 base pairs (bp) at a single-nucleotide resolution. Gene42 models utilize a decoder-only (LLaMA-style) architecture with a dense self-attention mechanism. Initially trained on fixed-length sequences of 4,096 bp, our models underwent continuous pretraining to extend the context length to 192,000 bp. This iterative extension allowed for the comprehensive processing of large-scale genomic data and the capture of intricate patterns and dependencies within the human genome. Gene42 is the first dense attention model capable of handling such extensive long context lengths in genomics, challenging state-space models that often rely on convolutional operators among other mechanisms. Our pretrained models exhibit notably low perplexity values and high reconstruction accuracy, highlighting their strong ability to model genomic data. Extensive experiments on various genomic benchmarks have demonstrated state-of-the-art performance across multiple tasks, including biotype classification, regulatory region identification, chromatin profiling prediction, variant pathogenicity prediction, and species classification. The models are publicly available at huggingface.co/inceptionai.
Authors: Laurits Dixen, Stefan Heinrich, Paolo Burelli
Abstract: Neural decoding is an important method in cognitive neuroscience that aims to decode brain representations from recorded neural activity using a multivariate machine learning model. The THINGS initiative provides a large EEG dataset of 46 subjects watching rapidly shown images. Here, we test the feasibility of using this method for decoding high-level object features using recent deep learning models. We create a derivative dataset from this of living vs non-living entities test 15 different deep learning models with 5 different architectures and compare to a SOTA linear model. We show that the linear model is not able to solve the decoding task, while almost all the deep learning models are successful, suggesting that in some cases non-linear models are needed to decode neural representations. We also run a comparative study of the models' performance on individual object categories, and suggest how artificial neural networks can be used to study brain activity.
Authors: Shu Yang, Chengting Yu, Lei Liu, Hanzhi Ma, Aili Wang, Erping Li
Abstract: Spiking Neural Networks (SNNs) have garnered considerable attention as a potential alternative to Artificial Neural Networks (ANNs). Recent studies have highlighted SNNs' potential on large-scale datasets. For SNN training, two main approaches exist: direct training and ANN-to-SNN (ANN2SNN) conversion. To fully leverage existing ANN models in guiding SNN learning, either direct ANN-to-SNN conversion or ANN-SNN distillation training can be employed. In this paper, we propose an ANN-SNN distillation framework from the ANN-to-SNN perspective, designed with a block-wise replacement strategy for ANN-guided learning. By generating intermediate hybrid models that progressively align SNN feature spaces to those of ANN through rate-based features, our framework naturally incorporates rate-based backpropagation as a training method. Our approach achieves results comparable to or better than state-of-the-art SNN distillation methods, showing both training and learning efficiency.
Authors: Bilal Ahmad, Jinfu Chen, Haibao Chen
Abstract: Heart disease remains one of the leading causes of morbidity and mortality worldwide, necessitating the development of effective diagnostic tools to enable early diagnosis and clinical decision-making. This study evaluates the impact of feature selection techniques Mutual Information (MI), Analysis of Variance (ANOVA), and Chi-Square on the predictive performance of various machine learning (ML) and deep learning (DL) models using a dataset of clinical indicators for heart disease. Eleven ML/DL models were assessed using metrics such as precision, recall, AUC score, F1-score, and accuracy. Results indicate that MI outperformed other methods, particularly for advanced models like neural networks, achieving the highest accuracy of 82.3% and recall score of 0.94. Logistic regression (accuracy 82.1%) and random forest (accuracy 80.99%) also demonstrated improved performance with MI. Simpler models such as Naive Bayes and decision trees achieved comparable results with ANOVA and Chi-Square, yielding accuracies of 76.45% and 75.99%, respectively, making them computationally efficient alternatives. Conversely, k Nearest Neighbors (KNN) and Support Vector Machines (SVM) exhibited lower performance, with accuracies ranging between 51.52% and 54.43%, regardless of the feature selection method. This study provides a comprehensive comparison of feature selection methods for heart disease prediction, demonstrating the critical role of feature selection in optimizing model performance. The results offer practical guidance for selecting appropriate feature selection techniques based on the chosen classification algorithm, contributing to the development of more accurate and efficient diagnostic tools for enhanced clinical decision-making in cardiology.
Authors: Ruiqi Yang, Jianxu Wang, Wei Yuan, Xun Wang, Mei Li
Abstract: This study explores the application of machine learning-based genetic linguistics for identifying heavy metal response genes in rice (Oryza sativa). By integrating convolutional neural networks and random forest algorithms, we developed a hybrid model capable of extracting and learning meaningful features from gene sequences, such as k-mer frequencies and physicochemical properties. The model was trained and tested on datasets of genes, achieving high predictive performance (precision: 0.89, F1-score: 0.82). RNA-seq and qRT-PCR experiments conducted on rice leaves which exposed to Hg0, revealed differential expression of genes associated with heavy metal responses, which validated the model's predictions. Co-expression network analysis identified 103 related genes, and a literature review indicated that these genes are highly likely to be involved in heavy metal-related biological processes. By integrating and comparing the analysis results with those of differentially expressed genes (DEGs), the validity of the new machine learning method was further demonstrated. This study highlights the efficacy of combining machine learning with genetic linguistics for large-scale gene prediction. It demonstrates a cost-effective and efficient approach for uncovering molecular mechanisms underlying heavy metal responses, with potential applications in developing stress-tolerant crop varieties.
Authors: Ayesha Siddique, Khurram Khalil, Khaza Anuarul Hoque
Abstract: Approximate deep neural networks (AxDNNs) are promising for enhancing energy efficiency in real-world devices. One of the key contributors behind this enhanced energy efficiency in AxDNNs is the use of approximate multipliers. Unfortunately, the simulation of approximate multipliers does not usually scale well on CPUs and GPUs. As a consequence, this slows down the overall simulation of AxDNNs aimed at identifying the appropriate approximate multipliers to achieve high energy efficiency with a minimum accuracy loss. To address this problem, we present a novel XAI-Gen methodology, which leverages the analytical model of the emerging hardware accelerator (e.g., Google TPU v4) and explainable artificial intelligence (XAI) to precisely identify the non-critical layers for approximation and quickly discover the appropriate approximate multipliers for AxDNN layers. Our results show that XAI-Gen achieves up to 7x lower energy consumption with only 1-2% accuracy loss. We also showcase the effectiveness of the XAI-Gen approach through a neural architecture search (XAI-NAS) case study. Interestingly, XAI-NAS achieves 40\% higher energy efficiency with up to 5x less execution time when compared to the state-of-the-art NAS methods for generating AxDNNs.
Authors: Moslem Noori, Elisabetta Valiante, Thomas Van Vaerenbergh, Masoud Mohseni, Ignacio Rozada
Abstract: A key trait of stochastic optimizers is that multiple runs of the same optimizer in attempting to solve the same problem can produce different results. As a result, their performance is evaluated over several repeats, or runs, on the problem. However, the accuracy of the estimated performance metrics depends on the number of runs and should be studied using statistical tools. We present a statistical analysis of the common metrics, and develop guidelines for experiment design to measure the optimizer's performance using these metrics to a high level of confidence and accuracy. To this end, we first discuss the confidence interval of the metrics and how they are related to the number of runs of an experiment. We then derive a lower bound on the number of repeats in order to guarantee achieving a given accuracy in the metrics. Using this bound, we propose an algorithm to adaptively adjust the number of repeats needed to ensure the accuracy of the evaluated metric. Our simulation results demonstrate the utility of our analysis and how it allows us to conduct reliable benchmarking as well as hyperparameter tuning and prevent us from drawing premature conclusions regarding the performance of stochastic optimizers.
Authors: Julian Ziegler, Patrick Frenzel, Mirco Fuchs
Abstract: This work concerns itself with the task of reconstructing all edges of an arbitrary 3D wire-frame model projected to an image plane. We explore a bottom-up part-wise procedure undertaken by an RL agent to segment and reconstruct these 2D multipart objects. The environment's state is represented as a four-colour image, where different colours correspond to background, a target edge, a reconstruction line, and the overlap of both. At each step, the agent can transform the reconstruction line within a four-dimensional action space or terminate the episode using a specific termination action. To investigate the impact of reward function formulations, we tested episodic and incremental rewards, as well as combined approaches. Empirical results demonstrated that the latter yielded the most effective training performance. To further enhance efficiency and stability, we introduce curriculum learning strategies. First, an action-based curriculum was implemented, where the agent was initially restricted to a reduced action space, being able to only perform three of the five possible actions, before progressing to the full action space. Second, we test a task-based curriculum, where the agent first solves a simplified version of the problem before being presented with the full, more complex task. This second approach produced promising results, as the agent not only successfully transitioned from learning the simplified task to mastering the full task, but in doing so gained significant performance. This study demonstrates the potential of an iterative RL wire-frame reconstruction in two dimensions. By combining optimized reward function formulations with curriculum learning strategies, we achieved significant improvements in training success. The proposed methodology provides an effective framework for solving similar tasks and represents a promising direction for future research in the field.
Authors: Thomas Kreutz, Max M\"uhlh\"auser, Alejandro Sanchez Guinea
Abstract: Realistic crowd simulations are essential for immersive virtual environments, relying on both individual behaviors (microscopic dynamics) and overall crowd patterns (macroscopic characteristics). While recent data-driven methods like deep reinforcement learning improve microscopic realism, they often overlook critical macroscopic features such as crowd density and flow, which are governed by spatio-temporal spawn dynamics, namely, when and where agents enter a scene. Traditional methods, like random spawn rates, stochastic processes, or fixed schedules, are not guaranteed to capture the underlying complexity or lack diversity and realism. To address this issue, we propose a novel approach called nTPP-GMM that models spatio-temporal spawn dynamics using Neural Temporal Point Processes (nTPPs) that are coupled with a spawn-conditional Gaussian Mixture Model (GMM) for agent spawn and goal positions. We evaluate our approach by orchestrating crowd simulations of three diverse real-world datasets with nTPP-GMM. Our experiments demonstrate the orchestration with nTPP-GMM leads to realistic simulations that reflect real-world crowd scenarios and allow crowd analysis.
Authors: Wanyi Chen, Mary Cummings
Abstract: Missing data is prevalent in tabular machine learning (ML) models, and different missing data treatment methods can significantly affect ML model training results. However, little is known about how ML researchers and engineers choose missing data treatment methods and what factors affect their choices. To this end, we conducted a survey of 70 ML researchers and engineers. Our results revealed that most participants were not making informed decisions regarding missing data treatment, which could significantly affect the validity of the ML models trained by these researchers. We advocate for better education on missing data, more standardized missing data reporting, and better missing data analysis tools.
Authors: Viet Thanh Duy Nguyen, Truong-Son Hy
Abstract: Proteins are complex biomolecules that play a central role in various biological processes, making them critical targets for breakthroughs in molecular biology, medical research, and drug discovery. Deciphering their intricate, hierarchical structures, and diverse functions is essential for advancing our understanding of life at the molecular level. Protein Representation Learning (PRL) has emerged as a transformative approach, enabling the extraction of meaningful computational representations from protein data to address these challenges. In this paper, we provide a comprehensive review of PRL research, categorizing methodologies into five key areas: feature-based, sequence-based, structure-based, multimodal, and complex-based approaches. To support researchers in this rapidly evolving field, we introduce widely used databases for protein sequences, structures, and functions, which serve as essential resources for model development and evaluation. We also explore the diverse applications of these approaches in multiple domains, demonstrating their broad impact. Finally, we discuss pressing technical challenges and outline future directions to advance PRL, offering insights to inspire continued innovation in this foundational field.
Authors: Qiyu Kang, Xuhao Li, Kai Zhao, Wenjun Cui, Yanan Zhao, Weihua Deng, Wee Peng Tay
Abstract: Fractional-order differential equations (FDEs) enhance traditional differential equations by extending the order of differential operators from integers to real numbers, offering greater flexibility in modeling complex dynamical systems with nonlocal characteristics. Recent progress at the intersection of FDEs and deep learning has catalyzed a new wave of innovative models, demonstrating the potential to address challenges such as graph representation learning. However, training neural FDEs has primarily relied on direct differentiation through forward-pass operations in FDE numerical solvers, leading to increased memory usage and computational complexity, particularly in large-scale applications. To address these challenges, we propose a scalable adjoint backpropagation method for training neural FDEs by solving an augmented FDE backward in time, which substantially reduces memory requirements. This approach provides a practical neural FDE toolbox and holds considerable promise for diverse applications. We demonstrate the effectiveness of our method in several tasks, achieving performance comparable to baseline models while significantly reducing computational overhead.
Authors: Oriol Vendrell-Gallart, Nima Negarandeh, Zahra Zanjani Foumani, Mahsa Amiri, Lorenzo Valdevit, Ramin Bostanabad
Abstract: Foundation models are at the forefront of an increasing number of critical applications. In regards to technologies such as additive manufacturing (AM), these models have the potential to dramatically accelerate process optimization and, in turn, design of next generation materials. A major challenge that impedes the construction of foundation process-property models is data scarcity. To understand the impact of this challenge, and since foundation models rely on data fusion, in this work we conduct controlled experiments where we focus on the transferability of information across different material systems and properties. More specifically, we generate experimental datasets from 17-4 PH and 316L stainless steels (SSs) in Laser Powder Bed Fusion (LPBF) where we measure the effect of five process parameters on porosity and hardness. We then leverage Gaussian processes (GPs) for process-property modeling in various configurations to test if knowledge about one material system or property can be leveraged to build more accurate machine learning models for other material systems or properties. Through extensive cross-validation studies and probing the GPs' interpretable hyperparameters, we study the intricate relation among data size and dimensionality, complexity of the process-property relations, noise, and characteristics of machine learning models. Our findings highlight the need for structured learning approaches that incorporate domain knowledge in building foundation process-property models rather than relying on uninformed data fusion in data-limited applications.
Authors: Daniel Haziza, Timothy Chou, Dhruv Choudhary, Luca Wehrstedt, Francisco Massa, Jiecao Yu, Geonhwa Jeong, Supriya Rao, Patrick Labatut, Jesse Cai
Abstract: In this paper, we demonstrate how to leverage 2:4 sparsity, a popular hardware-accelerated GPU sparsity pattern, to activations to accelerate large language model training and inference. Crucially we exploit the intrinsic sparsity found in Squared-ReLU activations to provide this acceleration with no accuracy loss. Our approach achieves up to 1.3x faster Feed Forward Network (FFNs) in both the forwards and backwards pass. This work highlights the potential for sparsity to play a key role in accelerating large language model training and inference.
Authors: Joshua Hatherley
Abstract: Artificial intelligence (AI) is expected to revolutionize the practice of medicine. Recent advancements in the field of deep learning have demonstrated success in a variety of clinical tasks: detecting diabetic retinopathy from images, predicting hospital readmissions, aiding in the discovery of new drugs, etc. AI's progress in medicine, however, has led to concerns regarding the potential effects of this technology upon relationships of trust in clinical practice. In this paper, I will argue that there is merit to these concerns, since AI systems can be relied upon, and are capable of reliability, but cannot be trusted, and are not capable of trustworthiness. Insofar as patients are required to rely upon AI systems for their medical decision-making, there is potential for this to produce a deficit of trust in relationships in clinical practice.
Authors: Zhan Cheng, Bolin Shen, Tianming Sha, Yuan Gao, Shibo Li, Yushun Dong
Abstract: Graph Neural Networks (GNNs) have gained traction in Graph-based Machine Learning as a Service (GMLaaS) platforms, yet they remain vulnerable to graph-based model extraction attacks (MEAs), where adversaries reconstruct surrogate models by querying the victim model. Existing defense mechanisms, such as watermarking and fingerprinting, suffer from poor real-time performance, susceptibility to evasion, or reliance on post-attack verification, making them inadequate for handling the dynamic characteristics of graph-based MEA variants. To address these limitations, we propose ATOM, a novel real-time MEA detection framework tailored for GNNs. ATOM integrates sequential modeling and reinforcement learning to dynamically detect evolving attack patterns, while leveraging $k$-core embedding to capture the structural properties, enhancing detection precision. Furthermore, we provide theoretical analysis to characterize query behaviors and optimize detection strategies. Extensive experiments on multiple real-world datasets demonstrate that ATOM outperforms existing approaches in detection performance, maintaining stable across different time steps, thereby offering a more effective defense mechanism for GMLaaS environments.
Authors: Donghwan Lee, Bum Geun Park, Taeho Lee
Abstract: This paper introduces Q-learning with gradient target tracking, a novel reinforcement learning framework that provides a learned continuous target update mechanism as an alternative to the conventional hard update paradigm. In the standard deep Q-network (DQN), the target network is a copy of the online network's weights, held fixed for a number of iterations before being periodically replaced via a hard update. While this stabilizes training by providing consistent targets, it introduces a new challenge: the hard update period must be carefully tuned to achieve optimal performance. To address this issue, we propose two gradient-based target update methods: DQN with asymmetric gradient target tracking (AGT2-DQN) and DQN with symmetric gradient target tracking (SGT2-DQN). These methods replace the conventional hard target updates with continuous and structured updates using gradient descent, which effectively eliminates the need for manual tuning. We provide a theoretical analysis proving the convergence of these methods in tabular settings. Additionally, empirical evaluations demonstrate their advantages over standard DQN baselines, which suggest that gradient-based target updates can serve as an effective alternative to conventional target update mechanisms in Q-learning.
Authors: Anni Zhou, Raheem Beyah, Rishikesan Kamaleswaran
Abstract: In critical care settings, timely and accurate predictions can significantly impact patient outcomes, especially for conditions like sepsis, where early intervention is crucial. We aim to model patient-specific reward functions in a contextual multi-armed bandit setting. The goal is to leverage patient-specific clinical features to optimize decision-making under uncertainty. This paper proposes NeuroSep-CP-LCB, a novel integration of neural networks with contextual bandits and conformal prediction tailored for early sepsis detection. Unlike the algorithm pool selection problem in the previous paper, where the primary focus was identifying the most suitable pre-trained model for prediction tasks, this work directly models the reward function using a neural network, allowing for personalized and adaptive decision-making. Combining the representational power of neural networks with the robustness of conformal prediction intervals, this framework explicitly accounts for uncertainty in offline data distributions and provides actionable confidence bounds on predictions.
Authors: Guillermo Bern\'ardez, Miquel Ferriol-Galm\'es, Carlos G\"uemes-Palau, Mathilde Papillon, Pere Barlet-Ros, Albert Cabellos-Aparicio, Nina Miolane
Abstract: Computer networks are the foundation of modern digital infrastructure, facilitating global communication and data exchange. As demand for reliable high-bandwidth connectivity grows, advanced network modeling techniques become increasingly essential to optimize performance and predict network behavior. Traditional modeling methods, such as packet-level simulators and queueing theory, have notable limitations --either being computationally expensive or relying on restrictive assumptions that reduce accuracy. In this context, the deep learning-based RouteNet family of models has recently redefined network modeling by showing an unprecedented cost-performance trade-off. In this work, we revisit RouteNet's sophisticated design and uncover its hidden connection to Topological Deep Learning (TDL), an emerging field that models higher-order interactions beyond standard graph-based methods. We demonstrate that, although originally formulated as a heterogeneous Graph Neural Network, RouteNet serves as the first instantiation of a new form of TDL. More specifically, this paper presents OrdGCCN, a novel TDL framework that introduces the notion of ordered neighbors in arbitrary discrete topological spaces, and shows that RouteNet's architecture can be naturally described as an ordered topological neural network. To the best of our knowledge, this marks the first successful real-world application of state-of-the-art TDL principles --which we confirm through extensive testbed experiments--, laying the foundation for the next generation of ordered TDL-driven applications.
Authors: Zhuoyuan Wang, Raffaele Romagnoli, Jasmine Ratchford, Yorie Nakahira
Abstract: Physics-informed machine learning provides an approach to combining data and governing physics laws for solving complex partial differential equations (PDEs). However, efficiently solving PDEs with varying parameters and changing initial conditions and boundary conditions (ICBCs) with theoretical guarantees remains an open challenge. We propose a hybrid framework that uses a neural network to learn B-spline control points to approximate solutions to PDEs with varying system and ICBC parameters. The proposed network can be trained efficiently as one can directly specify ICBCs without imposing losses, calculate physics-informed loss functions through analytical formulas, and requires only learning the weights of B-spline functions as opposed to both weights and basis as in traditional neural operator learning methods. We provide theoretical guarantees that the proposed B-spline networks serve as universal approximators for the set of solutions of PDEs with varying ICBCs under mild conditions and establish bounds on the generalization errors in physics-informed learning. We also demonstrate in experiments that the proposed B-spline network can solve problems with discontinuous ICBCs and outperforms existing methods, and is able to learn solutions of 3D dynamics with diverse initial conditions.
Authors: Mingxuan Li, Junzhe Zhang, Elias Bareinboim
Abstract: A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional target task. The framework of curriculum learning trains the agent in a curriculum composed of a sequence of related and more manageable source tasks. The expectation is that when some optimal decision rules are shared across source tasks and the target task, the agent could more quickly pick up the necessary skills to behave optimally in the environment, thus accelerating the learning process. However, this critical assumption of invariant optimal decision rules does not necessarily hold in many practical applications, specifically when the underlying environment contains unobserved confounders. This paper studies the problem of curriculum RL through causal lenses. We derive a sufficient graphical condition characterizing causally aligned source tasks, i.e., the invariance of optimal decision rules holds. We further develop an efficient algorithm to generate a causally aligned curriculum, provided with qualitative causal knowledge of the target task. Finally, we validate our proposed methodology through experiments in discrete and continuous confounded tasks with pixel observations.
Authors: Jihwan Oh, Minchan Jeong, Jongwoo Ko, Se-Young Yun
Abstract: Large Language Models $($LLMs$)$ solve complex problems using training-free methods like prompt engineering and in-context learning, yet ensuring reasoning correctness remains challenging. While self-correction methods such as self-consistency and self-refinement aim to improve reliability, they often reinforce biases due to the lack of effective feedback mechanisms. Multi-Agent Debate $($MAD$)$ has emerged as an alternative, but we identify two key limitations: bias reinforcement, where debate amplifies model biases instead of correcting them, and lack of perspective diversity, as all agents share the same model and reasoning patterns, limiting true debate effectiveness. To systematically evaluate these issues, we introduce $\textit{MetaNIM Arena}$, a benchmark designed to assess LLMs in adversarial strategic decision-making, where dynamic interactions influence optimal decisions. To overcome MAD's limitations, we propose $\textbf{DReaMAD}$ $($$\textbf{D}$iverse $\textbf{Rea}$soning via $\textbf{M}$ulti-$\textbf{A}$gent $\textbf{D}$ebate with Refined Prompt$)$, a novel framework that $(1)$ refines LLM's strategic prior knowledge to improve reasoning quality and $(2)$ promotes diverse viewpoints within a single model by systematically modifying prompts, reducing bias. Empirical results show that $\textbf{DReaMAD}$ significantly improves decision accuracy, reasoning diversity, and bias mitigation across multiple strategic tasks, establishing it as a more effective approach for LLM-based decision-making.
Authors: Wen Xu, Elham Dolatabadi
Abstract: This paper presents a new algorithmic fairness framework called $\boldsymbol{\alpha}$-$\boldsymbol{\beta}$ Fair Machine Learning ($\boldsymbol{\alpha}$-$\boldsymbol{\beta}$ FML), designed to optimize fairness levels across sociodemographic attributes. Our framework employs a new family of surrogate loss functions, paired with loss reweighting techniques, allowing precise control over fairness-accuracy trade-offs through tunable hyperparameters $\boldsymbol{\alpha}$ and $\boldsymbol{\beta}$. To efficiently solve the learning objective, we propose Parallel Stochastic Gradient Descent with Surrogate Loss (P-SGD-S) and establish convergence guarantees for both convex and nonconvex loss functions. Experimental results demonstrate that our framework improves overall accuracy while reducing fairness violations, offering a smooth trade-off between standard empirical risk minimization and strict minimax fairness. Results across multiple datasets confirm its adaptability, ensuring fairness improvements without excessive performance degradation.
Authors: Tai Dang, Long-Hung Pham, Sang T. Truong, Ari Glenn, Wendy Nguyen, Edward A. Pham, Jeffrey S. Glenn, Sanmi Koyejo, Thang Luong
Abstract: Despite decades of advancements in automated ligand screening, large-scale drug discovery remains resource-intensive and requires post-processing hit selection, a step where chemists manually select a few promising molecules based on their chemical intuition. This creates a major bottleneck in the virtual screening process for drug discovery, demanding experts to repeatedly balance complex trade-offs among drug properties across a vast pool of candidates. To improve the efficiency and reliability of this process, we propose a novel human-centered framework named CheapVS that allows chemists to guide the ligand selection process by providing preferences regarding the trade-offs between drug properties via pairwise comparison. Our framework combines preferential multi-objective Bayesian optimization with a docking model for measuring binding affinity to capture human chemical intuition for improving hit identification. Specifically, on a library of 100K chemical candidates targeting EGFR and DRD2, CheapVS outperforms state-of-the-art screening methods in identifying drugs within a limited computational budget. Notably, our method can recover up to 16/37 EGFR and 37/58 DRD2 known drugs while screening only 6% of the library, showcasing its potential to significantly advance drug discovery.
Authors: Qingsong Wang
Abstract: Symmetric matrix decomposition is an active research area in machine learning. This paper focuses on exploiting the low-rank structure of non-negative and sparse symmetric matrices via the rectified linear unit (ReLU) activation function. We propose the ReLU-based nonlinear symmetric matrix decomposition (ReLU-NSMD) model, introduce an accelerated alternating partial Bregman (AAPB) method for its solution, and present the algorithm's convergence results. Our algorithm leverages the Bregman proximal gradient framework to overcome the challenge of estimating the global $L$-smooth constant in the classic proximal gradient algorithm. Numerical experiments on synthetic and real datasets validate the effectiveness of our model and algorithm.
Authors: Maximilian Zoch, Edward Holmberg, Pujan Pokhrel, Ken Pathak, Steven Sloan, Kendall Niles, Jay Ratcliff, Maik Flanagin, Elias Ioup, Christian Guetl, Mahdi Abdelguerfi
Abstract: This work investigates the feasibility of using Physics-Informed Neural Networks (PINNs) as surrogate models for river stage prediction, aiming to reduce computational cost while maintaining predictive accuracy. Our primary contribution demonstrates that PINNs can successfully approximate HEC-RAS numerical solutions when trained on a single river, achieving strong predictive accuracy with generally low relative errors, though some river segments exhibit higher deviations. By integrating the governing Saint-Venant equations into the learning process, the proposed PINN-based surrogate model enforces physical consistency and significantly improves computational efficiency compared to HEC-RAS. We evaluate the model's performance in terms of accuracy and computational speed, demonstrating that it closely approximates HEC-RAS predictions while enabling real-time inference. These results highlight the potential of PINNs as effective surrogate models for single-river hydrodynamics, offering a promising alternative for computationally efficient river stage forecasting. Future work will explore techniques to enhance PINN training stability and robustness across a more generalized multi-river model.
Authors: Honoka Anada, Sefutsu Ryu, Masayuki Usui, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki
Abstract: On-device transfer learning is crucial for adapting a common backbone model to the unique environment of each edge device. Tiny microcontrollers, such as the Raspberry Pi Pico, are key targets for on-device learning but often lack floating-point units, necessitating integer-only training. Dynamic computation of quantization scale factors, which is adopted in former studies, incurs high computational costs. Therefore, this study focuses on integer-only training with static scale factors, which is challenging with existing training methods. We propose a new training method named PRIOT, which optimizes the network by pruning selected edges rather than updating weights, allowing effective training with static scale factors. The pruning pattern is determined by the edge-popup algorithm, which trains a parameter named score assigned to each edge instead of the original parameters and prunes the edges with low scores before inference. Additionally, we introduce a memory-efficient variant, PRIOT-S, which only assigns scores to a small fraction of edges. We implement PRIOT and PRIOT-S on the Raspberry Pi Pico and evaluate their accuracy and computational costs using a tiny CNN model on the rotated MNIST dataset and the VGG11 model on the rotated CIFAR-10 dataset. Our results demonstrate that PRIOT improves accuracy by 8.08 to 33.75 percentage points over existing methods, while PRIOT-S reduces memory footprint with minimal accuracy loss.
Authors: Yujia Zheng, Yang Liu, Jiaxiong Yao, Yingyao Hu, Kun Zhang
Abstract: Nearly all identifiability results in unsupervised representation learning inspired by, e.g., independent component analysis, factor analysis, and causal representation learning, rely on assumptions of additive independent noise or noiseless regimes. In contrast, we study the more general case where noise can take arbitrary forms, depend on latent variables, and be non-invertibly entangled within a nonlinear function. We propose a general framework for identifying latent variables in the nonparametric noisy settings. We first show that, under suitable conditions, the generative model is identifiable up to certain submanifold indeterminacies even in the presence of non-negligible noise. Furthermore, under the structural or distributional variability conditions, we prove that latent variables of the general nonlinear models are identifiable up to trivial indeterminacies. Based on the proposed theoretical framework, we have also developed corresponding estimation methods and validated them in various synthetic and real-world settings. Interestingly, our estimate of the true GDP growth from alternative measurements suggests more insightful information on the economies than official reports. We expect our framework to provide new insight into how both researchers and practitioners deal with latent variables in real-world scenarios.
Authors: Anshumann, Mohd Abbas Zaidi, Akhil Kedia, Jinwoo Ahn, Taehwak Kwon, Kangwook Lee, Haejun Lee, Joohyung Lee
Abstract: Knowledge distillation can be a cost-effective technique to distill knowledge in Large Language Models, if the teacher output logits can be pre-computed and cached. However, successfully applying this to pre-training remains largely unexplored. In this work, we prove that naive approaches for sparse knowledge distillation such as caching Top-K probabilities, while intuitive, provide biased estimates of teacher probability distribution to the student, resulting in suboptimal performance and calibration. We propose an importance-sampling-based method `Random Sampling Knowledge Distillation', which provides unbiased estimates, preserves the gradient in expectation, and requires storing significantly sparser logits. Our method enables faster training of student models with marginal overhead (<10%) compared to cross-entropy based training, while maintaining competitive performance compared to full distillation, across a range of model sizes from 300M to 3B.
Authors: Xuan Wang, Siyuan Liang, Dongping Liao, Han Fang, Aishan Liu, Xiaochun Cao, Yu-liang Lu, Ee-Chien Chang, Xitong Gao
Abstract: Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g., supervised or semi-supervised learning). However, this practice can introduce severe security risks, as adversaries may poison the training data to embed backdoors into the resulting model. Existing detection approaches predominantly rely on statistical analyses, which often fail to maintain universally accurate detection accuracy across different learning paradigms. To address this challenge, we propose a unified backdoor detection framework in the semi-honest setting that exploits cross-examination of model inconsistencies between two independent service providers. Specifically, we integrate central kernel alignment to enable robust feature similarity measurements across different model architectures and learning paradigms, thereby facilitating precise recovery and identification of backdoor triggers. We further introduce backdoor fine-tuning sensitivity analysis to distinguish backdoor triggers from adversarial perturbations, substantially reducing false positives. Extensive experiments demonstrate that our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines across supervised, semi-supervised, and autoregressive learning tasks, respectively. Notably, it is the first to effectively detect backdoors in multimodal large language models, further highlighting its broad applicability and advancing secure deep learning.
Authors: Steve Gounoue, Ashutosh Sao, Simon Gottschalk
Abstract: Transaction graphs, which represent financial and trade transactions between entities such as bank accounts and companies, can reveal patterns indicative of financial crimes like money laundering and fraud. However, effective detection of such cases requires node and edge classification methods capable of addressing the unique challenges of transaction graphs, including rich edge features, multigraph structures and temporal dynamics. To tackle these challenges, we propose TeMP-TraG, a novel graph neural network mechanism that incorporates temporal dynamics into message passing. TeMP-TraG prioritises more recent transactions when aggregating node messages, enabling better detection of time-sensitive patterns. We demonstrate that TeMP-TraG improves four state-of-the-art graph neural networks by 6.19% on average. Our results highlight TeMP-TraG as an advancement in leveraging transaction graphs to combat financial crime.
Authors: Ehsan Mirafzali, Utkarsh Gupta, Patrick Wyrod, Frank Proske, Daniele Venturi, Razvan Marinescu
Abstract: We introduce a new framework that employs Malliavin calculus to derive explicit expressions for the score function -- i.e., the gradient of the log-density -- associated with solutions to stochastic differential equations (SDEs). Our approach integrates classical integration-by-parts techniques with modern tools, such as Bismut's formula and Malliavin calculus, to address linear and nonlinear SDEs. In doing so, we establish a rigorous connection between the Malliavin derivative, its adjoint (the Malliavin divergence or the Skorokhod integral), Bismut's formula, and diffusion generative models, thus providing a systematic method for computing $\nabla \log p_t(x)$. For the linear case, we present a detailed study proving that our formula is equivalent to the actual score function derived from the solution of the Fokker--Planck equation for linear SDEs. Additionally, we derive a closed-form expression for $\nabla \log p_t(x)$ for nonlinear SDEs with state-independent diffusion coefficients. These advancements provide fresh theoretical insights into the smoothness and structure of probability densities and practical implications for score-based generative modelling, including the design and analysis of new diffusion models. Moreover, our findings promote the adoption of the robust Malliavin calculus framework in machine learning research. These results directly apply to various pure and applied mathematics fields, such as generative modelling, the study of SDEs driven by fractional Brownian motion, and the Fokker--Planck equations associated with nonlinear SDEs.
Authors: Thibault Martin, Paul Sauleau, Claire Haegelen, Pierre Jannin, John S. H. Baxter
Abstract: The analysis of electrophysiological data is crucial for certain surgical procedures such as deep brain stimulation, which has been adopted for the treatment of a variety of neurological disorders. During the procedure, auditory analysis of these signals helps the clinical team to infer the neuroanatomical location of the stimulation electrode and thus optimize clinical outcomes. This task is complex, and requires an expert who in turn requires significant training. In this paper, we propose a generative neural network, called MerGen, capable of simulating de novo electrophysiological recordings, with a view to providing a realistic learning tool for clinicians trainees for identifying these signals. We demonstrate that the generated signals are perceptually indistinguishable from real signals by experts in the field, and that it is even possible to condition the generation efficiently to provide a didactic simulator adapted to a particular surgical scenario. The efficacy of this conditioning is demonstrated, comparing it to intra-observer and inter-observer variability amongst experts. We also demonstrate the use of this network for data augmentation for automatic signal classification which can play a role in decision-making support in the operating theatre.
Authors: Hazem Hesham Yousef Shalby, Arianna De Vecchi, Alice Scandelli, Pietro Bartoli, Diana Trojaniello, Manuel Roveri, Federica Villa
Abstract: Tiny Machine Learning (TinyML) is a novel research field aiming at integrating Machine Learning (ML) within embedded devices with limited memory, computation, and energy. Recently, a new branch of TinyML has emerged, focusing on integrating ML directly into the sensors to further reduce the power consumption of embedded devices. Interestingly, despite their state-of-the-art performance in many tasks, none of the current solutions in the literature aims to optimize the implementation of Convolutional Neural Networks (CNNs) operating directly into sensors. In this paper, we introduce for the first time in the literature the optimized design and implementation of Depth-First CNNs operating on the Intelligent Sensor Processing Unit (ISPU) within an Inertial Measurement Unit (IMU) by STMicroelectronics. Our approach partitions the CNN between the ISPU and the microcontroller (MCU) and employs an Early-Exit mechanism to stop the computations on the IMU when enough confidence about the results is achieved, hence significantly reducing power consumption. When using a NUCLEO-F411RE board, this solution achieved an average current consumption of 4.8 mA, marking an 11% reduction compared to the regular inference pipeline on the MCU, while having equal accuracy.
Authors: Anas Skalli, Satoshi Sunada, Mirko Goldmann, Marcin Gebski, Stephan Reitzenstein, James A. Lott, Tomasz Czyszanowski, Daniel Brunner
Abstract: Artificial neural networks (ANNs), have become ubiquitous and revolutionized many applications ranging from computer vision to medical diagnoses. However, they offer a fundamentally connectionist and distributed approach to computing, in stark contrast to classical computers that use the von Neumann architecture. This distinction has sparked renewed interest in developing unconventional hardware to support more efficient implementations of ANNs, rather than merely emulating them on traditional systems. Photonics stands out as a particularly promising platform, providing scalability, high speed, energy efficiency, and the ability for parallel information processing. However, fully realized autonomous optical neural networks (ONNs) with in-situ learning capabilities are still rare. In this work, we demonstrate a fully autonomous and parallel ONN using a multimode vertical cavity surface emitting laser (VCSEL) using off-the-shelf components. Our ONN is highly efficient and is scalable both in network size and inference bandwidth towards the GHz range. High performance hardware-compatible optimization algorithms are necessary in order to minimize reliance on external von Neumann computers to fully exploit the potential of ONNs. As such we present and extensively study several algorithms which are broadly compatible with a wide range of systems. We then apply these algorithms to optimize our ONN, and benchmark them using the MNIST dataset. We show that our ONN can achieve high accuracy and convergence efficiency, even under limited hardware resources. Crucially, we compare these different algorithms in terms of scaling and optimization efficiency in term of convergence time which is crucial when working with limited external resources. Our work provides some guidance for the design of future ONNs as well as a simple and flexible way to train them.
Authors: Yuze Li, Wei Zhu
Abstract: We propose an efficient fine-tuning method for time series foundation models, termed TRACE: Time Series Parameter Efficient Fine-tuning. While pretrained time series foundation models are gaining popularity, they face the following challenges: (1) Unlike natural language tasks, time series data vary in frequency, channel numbers, historical/prediction lengths. For long-term forecasting tasks in particular, tailored fine-tuning can significantly enhance performance.(2) Existing parameter-efficient tuning methods like LoRA remain applicable but require adaptation to temporal characteristics. To address these challenges, our TRACE framework introduces two key innovations: (1) Gated DSIC (Gated Dynamic Simulation Importance Calculation), an unbiased LoRA module importance selection mechanism that ensures conditional parameter consistency before and after masking. Experiments demonstrate that Gated DSIC outperforms common fine-tuning. (2) Reconstructed prediction heads for long-term forecasting tasks, which achieve comparable or superior performance to linear probing heads while drastically reducing parameter counts. Extensive experiments on long-/short-term forecasting and anomaly detection tasks across diverse datasets, coupled with ablation studies, validate the effectiveness of our method.
Authors: Haoyang Hong, Ioanna Papanikolaou, Sonali Parbhoo
Abstract: Mitigating shortcuts, where models exploit spurious correlations in training data, remains a significant challenge for improving generalization. Regularization methods have been proposed to address this issue by enhancing model generalizability. However, we demonstrate that these methods can sometimes overregularize, inadvertently suppressing causal features along with spurious ones. In this work, we analyze the theoretical mechanisms by which regularization mitigates shortcuts and explore the limits of its effectiveness. Additionally, we identify the conditions under which regularization can successfully eliminate shortcuts without compromising causal features. Through experiments on synthetic and real-world datasets, our comprehensive analysis provides valuable insights into the strengths and limitations of regularization techniques for addressing shortcuts, offering guidance for developing more robust models.
Authors: Aoting Zhang, Dongbao Yang, Chang Liu, Xiaopeng Hong, Yu Zhou
Abstract: Existing class incremental learning is mainly designed for single-label classification task, which is ill-equipped for multi-label scenarios due to the inherent contradiction of learning objectives for samples with incomplete labels. We argue that the main challenge to overcome this contradiction in multi-label class-incremental learning (MLCIL) lies in the model's inability to clearly distinguish between known and unknown knowledge. This ambiguity hinders the model's ability to retain historical knowledge, master current classes, and prepare for future learning simultaneously. In this paper, we target at specifying what is known or not to accommodate Historical, Current, and Prospective knowledge for MLCIL and propose a novel framework termed as HCP. Specifically, (i) we clarify the known classes by dynamic feature purification and recall enhancement with distribution prior, enhancing the precision and retention of known information. (ii) We design prospective knowledge mining to probe the unknown, preparing the model for future learning. Extensive experiments validate that our method effectively alleviates catastrophic forgetting in MLCIL, surpassing the previous state-of-the-art by 3.3% on average accuracy for MS-COCO B0-C10 setting without replay buffers.
Authors: David Mildenberger, Paul Hager, Daniel Rueckert, Martin J Menten
Abstract: Supervised contrastive learning (SupCon) has proven to be a powerful alternative to the standard cross-entropy loss for classification of multi-class balanced datasets. However, it struggles to learn well-conditioned representations of datasets with long-tailed class distributions. This problem is potentially exacerbated for binary imbalanced distributions, which are commonly encountered during many real-world problems such as medical diagnosis. In experiments on seven binary datasets of natural and medical images, we show that the performance of SupCon decreases with increasing class imbalance. To substantiate these findings, we introduce two novel metrics that evaluate the quality of the learned representation space. By measuring the class distribution in local neighborhoods, we are able to uncover structural deficiencies of the representation space that classical metrics cannot detect. Informed by these insights, we propose two new supervised contrastive learning strategies tailored to binary imbalanced datasets that improve the structure of the representation space and increase downstream classification accuracy over standard SupCon by up to 35%. We make our code available.
Authors: Rebecca J. Herman, Jonas Wahl, Urmi Ninad, Jakob Runge
Abstract: Causal discovery aims to extract qualitative causal knowledge in the form of causal graphs from data. Because causal ground truth is rarely known in the real world, simulated data plays a vital role in evaluating the performance of the various causal discovery algorithms proposed in the literature. But recent work highlighted certain artifacts of commonly used data generation techniques for a standard class of structural causal models (SCM) that may be nonphysical, including var- and R2-sortability, where the variables' variance and coefficients of determination (R2) after regressing on all other variables, respectively, increase along the causal order. Some causal methods exploit such artifacts, leading to unrealistic expectations for their performance on real-world data. Some modifications have been proposed to remove these artifacts; notably, the internally-standardized structural causal model (iSCM) avoids varsortability and largely alleviates R2-sortability on sparse causal graphs, but exhibits a reversed R2-sortability pattern for denser graphs not featured in their work. We analyze which sortability patterns we expect to see in real data, and propose a method for drawing coefficients that we argue more effectively samples the space of SCMs. Finally, we propose a novel extension of our SCM generation method to the time series setting.
Authors: Julius Stephan Junker, Rong Hu, Ziyue Li, Wolfgang Ketter
Abstract: This paper addresses the critical challenge of optimizing electric vehicle charging station placement through a novel data-driven methodology employing causal discovery techniques. While traditional approaches prioritize economic factors or power grid constraints, they often neglect empirical charging patterns that ultimately determine station utilization. We analyze extensive charging data from Palo Alto and Boulder (337,344 events across 100 stations) to uncover latent relationships between station characteristics and utilization. Applying structural learning algorithms (NOTEARS and DAGMA) to this data reveals that charging demand is primarily determined by three factors: proximity to amenities, EV registration density, and adjacency to high-traffic routes. These findings, consistent across multiple algorithms and urban contexts, challenge conventional infrastructure distribution strategies. We develop an optimization framework that translates these insights into actionable placement recommendations, identifying locations likely to experience high utilization based on the discovered dependency structures. The resulting site selection model prioritizes strategic clustering in high-amenity areas with substantial EV populations rather than uniform spatial distribution. Our approach contributes a framework that integrates empirical charging behavior into infrastructure planning, potentially enhancing both station utilization and user convenience. By focusing on data-driven insights instead of theoretical distribution models, we provide a more effective strategy for expanding charging networks that can adjust to various stages of EV market development.
Authors: Daniel M. Jimenez-Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti
Abstract: Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant convergence times. Despite its importance, experimental studies systematically addressing all types of data heterogeneity (a.k.a. non-IIDness) remain scarce. We aim to fill this gap by assessing and quantifying the non-IID effect through a thorough empirical analysis. We use the Hellinger Distance (HD) to measure differences in distribution among clients. Our study benchmarks four state-of-the-art strategies for handling non-IID data, including label, feature, quantity, and spatiotemporal skewness, under realistic and controlled conditions. This is the first comprehensive analysis of the spatiotemporal skew effect in FL. Our findings highlight the significant impact of label and spatiotemporal skew non-IID types on FL model performance, with notable performance drops occurring at specific HD thresholds. Additionally, the FL performance is heavily affected mainly when the non-IIDness is extreme. Thus, we provide recommendations for FL research to tackle data heterogeneity effectively. Our work represents the most extensive examination of non-IIDness in FL, offering a robust foundation for future research.
Authors: Agastya Raj, Zehao Wang, Frank Slyne, Tingjun Chen, Dan Kilper, Marco Ruffini
Abstract: We implement a ML-based attention framework with component-specific decoders, improving optical power spectrum prediction in multi-span networks. By reducing the need for in-depth training on each component, the framework can be scaled to multi-span topologies with minimal data collection, making it suitable for brown-field scenarios.
Authors: J. M. Diederik Kruijssen (Allora Foundation), Nicholas Emmons (Allora Foundation)
Abstract: Artificial intelligence (AI) systems powered by large language models have become increasingly prevalent in modern society, enabling a wide range of applications through natural language interaction. As AI agents proliferate in our daily lives, their generic and uniform expressiveness presents a significant limitation to their appeal and adoption. Personality expression represents a key prerequisite for creating more human-like and distinctive AI systems. We show that AI models can express deterministic and consistent personalities when instructed using established psychological frameworks, with varying degrees of accuracy depending on model capabilities. We find that more advanced models like GPT-4o and o1 demonstrate the highest accuracy in expressing specified personalities across both Big Five and Myers-Briggs assessments, and further analysis suggests that personality expression emerges from a combination of intelligence and reasoning capabilities. Our results reveal that personality expression operates through holistic reasoning rather than question-by-question optimization, with response-scale metrics showing higher variance than test-scale metrics. Furthermore, we find that model fine-tuning affects communication style independently of personality expression accuracy. These findings establish a foundation for creating AI agents with diverse and consistent personalities, which could significantly enhance human-AI interaction across applications from education to healthcare, while additionally enabling a broader range of more unique AI agents. The ability to quantitatively assess and implement personality expression in AI systems opens new avenues for research into more relatable, trustworthy, and ethically designed AI.
Authors: Jun Lu, Tianyi Xu, Bill Ding, David Li, Yu Kang
Abstract: In this paper, we tackle the critical challenge of compressing large language models (LLMs) to facilitate their practical deployment and broader adoption. We introduce a novel post-training compression paradigm that focuses on low-rank decomposition of LLM weights. Our analysis identifies two main challenges in this task: the variability in LLM activation distributions and handling unseen activations from different datasets and models. To address these challenges, we propose a nested activation-aware framework (NSVD) for LLMs, a training-free approach designed to enhance the accuracy of low-rank decompositions by managing activation outliers through transforming the weight matrix based on activation distribution and the original weight matrix. This method allows for the absorption of outliers into the transformed weight matrix, improving decomposition accuracy. Our comprehensive evaluation across eight datasets and six models from three distinct LLM families demonstrates the superiority of NSVD over current state-of-the-art methods, especially at medium to large compression ratios or in multilingual and multitask settings.
Authors: L\'eo Meynent, Ivan Melev, Konstantin Sch\"urholt, G\"oran Kauermann, Damian Borth
Abstract: The weights of neural networks (NNs) have recently gained prominence as a new data modality in machine learning, with applications ranging from accuracy and hyperparameter prediction to representation learning or weight generation. One approach to leverage NN weights involves training autoencoders (AEs), using contrastive and reconstruction losses. This allows such models to be applied to a wide variety of downstream tasks, and they demonstrate strong predictive performance and low reconstruction error. However, despite the low reconstruction error, these AEs reconstruct NN models with deteriorated performance compared to the original ones, limiting their usability with regard to model weight generation. In this paper, we identify a limitation of weight-space AEs, specifically highlighting that a structural loss, that uses the Euclidean distance between original and reconstructed weights, fails to capture some features critical for reconstructing high-performing models. We analyze the addition of a behavioral loss for training AEs in weight space, where we compare the output of the reconstructed model with that of the original one, given some common input. We show a strong synergy between structural and behavioral signals, leading to increased performance in all downstream tasks evaluated, in particular NN weights reconstruction and generation.
Authors: Huy Truong, Andr\'es Tello, Alexander Lazovik, Victoria Degeler
Abstract: Privacy restrictions hinder the sharing of real-world Water Distribution Network (WDN) models, limiting the application of emerging data-driven machine learning, which typically requires extensive observations. To address this challenge, we propose the dataset DiTEC-WDN that comprises 36,000 unique scenarios simulated over either short-term (24 hours) or long-term (1 year) periods. We constructed this dataset using an automated pipeline that optimizes crucial parameters (e.g., pressure, flow rate, and demand patterns), facilitates large-scale simulations, and records discrete, synthetic but hydraulically realistic states under standard conditions via rule validation and post-hoc analysis. With a total of 228 million generated graph-based states, DiTEC-WDN can support a variety of machine-learning tasks, including graph-level, node-level, and link-level regression, as well as time-series forecasting. This contribution, released under a public license, encourages open scientific research in the critical water sector, eliminates the risk of exposing sensitive data, and fulfills the need for a large-scale water distribution network benchmark for study comparisons and scenario analysis.
Authors: Gaojie Jin, Tianjin Huang, Ronghui Mu, Xiaowei Huang
Abstract: Recent studies have identified a critical challenge in deep neural networks (DNNs) known as ``robust fairness", where models exhibit significant disparities in robust accuracy across different classes. While prior work has attempted to address this issue in adversarial robustness, the study of worst-class certified robustness for smoothed classifiers remains unexplored. Our work bridges this gap by developing a PAC-Bayesian bound for the worst-class error of smoothed classifiers. Through theoretical analysis, we demonstrate that the largest eigenvalue of the smoothed confusion matrix fundamentally influences the worst-class error of smoothed classifiers. Based on this insight, we introduce a regularization method that optimizes the largest eigenvalue of smoothed confusion matrix to enhance worst-class accuracy of the smoothed classifier and further improve its worst-class certified robustness. We provide extensive experimental validation across multiple datasets and model architectures to demonstrate the effectiveness of our approach.
Authors: Sanjif Shanmugavelu, Mathieu Taillefumier, Christopher Culver, Vijay Ganesh, Oscar Hernandez, Ada Sedova
Abstract: The ability of machine learning (ML) classification models to resist small, targeted input perturbations - known as adversarial attacks - is a key measure of their safety and reliability. We show that floating-point non associativity (FPNA) coupled with asynchronous parallel programming on GPUs is sufficient to result in misclassification, without any perturbation to the input. Additionally, we show this misclassification is particularly significant for inputs close to the decision boundary and that standard adversarial robustness results may be overestimated up to 4.6% when not considering machine-level details. We first study a linear classifier, before focusing on standard Graph Neural Network (GNN) architectures and datasets. We present a novel black-box attack using Bayesian optimization to determine external workloads that bias the output of reductions on GPUs and reliably lead to misclassification. Motivated by these results, we present a new learnable permutation (LP) gradient-based approach, to learn floating point operation orderings that lead to misclassifications, making the assumption that any reduction or permutation ordering is possible. This LP approach provides a worst-case estimate in a computationally efficient manner, avoiding the need to run identical experiments tens of thousands of times over a potentially large set of possible GPU states or architectures. Finally, we investigate parallel reduction ordering across different GPU architectures for a reduction under three conditions: (1) executing external background workloads, (2) utilizing multi-GPU virtualization, and (3) applying power capping. Our results demonstrate that parallel reduction ordering varies significantly across architectures under the first two conditions. The results and methods developed here can help to include machine-level considerations into adversarial robustness assessments.
Authors: Abhijeet Pendyala, Tobias Glasmachers
Abstract: In this work, we augment reinforcement learning with an inference-time collision model to ensure safe and efficient container management in a waste-sorting facility with limited processing capacity. Each container has two optimal emptying volumes that trade off higher throughput against overflow risk. Conventional reinforcement learning (RL) approaches struggle under delayed rewards, sparse critical events, and high-dimensional uncertainty -- failing to consistently balance higher-volume empties with the risk of safety-limit violations. To address these challenges, we propose a hybrid method comprising: (1) a curriculum-learning pipeline that incrementally trains a PPO agent to handle delayed rewards and class imbalance, and (2) an offline pairwise collision model used at inference time to proactively avert collisions with minimal online cost. Experimental results show that our targeted inference-time collision checks significantly improve collision avoidance, reduce safety-limit violations, maintain high throughput, and scale effectively across varying container-to-PU ratios. These findings offer actionable guidelines for designing safe and efficient container-management systems in real-world facilities.
Authors: Sheng Wang, Pengan Chen, Jingqi Zhou, Qintong Li, Jingwei Dong, Jiahui Gao, Boyang Xue, Jiyue Jiang, Lingpeng Kong, Chuan Wu
Abstract: Model customization requires high-quality and diverse datasets, but acquiring such data remains challenging and costly. Although large language models (LLMs) can synthesize training data, current approaches are constrained by limited seed data, model bias and insufficient control over the generation process, resulting in limited diversity and biased distribution with the increase of data scales. To tackle this challenge, we present TreeSynth, a tree-guided subspace-based data synthesis framework that recursively partitions the entire data space into hierar-chical subspaces, enabling comprehensive and diverse scaling of data synthesis. Briefly, given a task-specific description, we construct a data space partitioning tree by iteratively executing criteria determination and subspace coverage steps. This hierarchically divides the whole space (i.e., root node) into mutually exclusive and complementary atomic subspaces (i.e., leaf nodes). By collecting synthesized data according to the attributes of each leaf node, we obtain a diverse dataset that fully covers the data space. Empirically, our extensive experiments demonstrate that TreeSynth surpasses both human-designed datasets and the state-of-the-art data synthesis baselines, achieving maximum improvements of 45.2% in data diversity and 17.6% in downstream task performance across various models and tasks. Hopefully, TreeSynth provides a scalable solution to synthesize diverse and comprehensive datasets from scratch without human intervention.
Authors: Vincent Bezold, Lukas Baur, Alexander Sauer
Abstract: The increasing integration of renewable energy sources has led to greater volatility and unpredictability in electricity generation, posing challenges to grid stability. Ancillary service markets, such as the German control reserve market, allow industrial consumers and producers to offer flexibility in their power consumption or generation, contributing to grid stability while earning additional income. However, many participants use simple bidding strategies that may not maximize their revenues. This paper presents a methodology for forecasting bidding prices in pay-as-bid ancillary service markets, focusing on the German control reserve market. We evaluate various machine learning models, including Support Vector Regression, Decision Trees, and k-Nearest Neighbors, and compare their performance against benchmark models. To address the asymmetry in the revenue function of pay-as-bid markets, we introduce an offset adjustment technique that enhances the practical applicability of the forecasting models. Our analysis demonstrates that the proposed approach improves potential revenues by 27.43 % to 37.31 % compared to baseline models. When analyzing the relationship between the model forecasting errors and the revenue, a negative correlation is measured for three markets; according to the results, a reduction of 1 EUR/MW model price forecasting error (MAE) statistically leads to a yearly revenue increase between 483 EUR/MW and 3,631 EUR/MW. The proposed methodology enables industrial participants to optimize their bidding strategies, leading to increased earnings and contributing to the efficiency and stability of the electrical grid.
Authors: Albert Sawczyn, Jakub Binkowski, Denis Janiak, Bogdan Gabrys, Tomasz Kajdanowicz
Abstract: Large Language Models (LLMs) frequently generate hallucinated content, posing significant challenges for applications where factuality is crucial. While existing hallucination detection methods typically operate at the sentence level or passage level, we propose FactSelfCheck, a novel black-box sampling-based method that enables fine-grained fact-level detection. Our approach represents text as knowledge graphs consisting of facts in the form of triples. Through analyzing factual consistency across multiple LLM responses, we compute fine-grained hallucination scores without requiring external resources or training data. Our evaluation demonstrates that FactSelfCheck performs competitively with leading sampling-based methods while providing more detailed insights. Most notably, our fact-level approach significantly improves hallucination correction, achieving a 35% increase in factual content compared to the baseline, while sentence-level SelfCheckGPT yields only an 8% improvement. The granular nature of our detection enables more precise identification and correction of hallucinated content.
Authors: Li Zhang, Chaochao Chen, Zhongxuan Han, Qiyong Zhong, Xiaolin Zheng
Abstract: Federated learning (FL) has garnered considerable interest for its capability to learn from decentralized data sources. Given the increasing application of FL in decision-making scenarios, addressing fairness issues across different sensitive groups (e.g., female, male) in FL is crucial. Current research often focuses on facilitating fairness at each client's data (local fairness) or within the entire dataset across all clients (global fairness). However, existing approaches that focus exclusively on either local or global fairness fail to address two key challenges: (\textbf{CH1}) Under statistical heterogeneity, global fairness does not imply local fairness, and vice versa. (\textbf{CH2}) Achieving fairness under model-agnostic setting. To tackle the aforementioned challenges, this paper proposes a novel post-processing framework for achieving both Local and Global Fairness in the FL context, namely LoGoFair. To address CH1, LoGoFair endeavors to seek the Bayes optimal classifier under local and global fairness constraints, which strikes the optimal accuracy-fairness balance in the probabilistic sense. To address CH2, LoGoFair employs a model-agnostic federated post-processing procedure that enables clients to collaboratively optimize global fairness while ensuring local fairness, thereby achieving the optimal fair classifier within FL. Experimental results on three real-world datasets further illustrate the effectiveness of the proposed LoGoFair framework.
Authors: Hilal Asi, John C. Duchi, Kunal Talwar
Abstract: We investigate differentially private estimators for individual parameters within larger parametric models. While generic private estimators exist, the estimators we provide repose on new local notions of estimand stability, and these notions allow procedures that provide private certificates of their own stability. By leveraging these private certificates, we provide computationally and statistical efficient mechanisms that release private statistics that are, at least asymptotically in the sample size, essentially unimprovable: they achieve instance optimal bounds. Additionally, we investigate the practicality of the algorithms both in simulated data and in real-world data from the American Community Survey and US Census, highlighting scenarios in which the new procedures are successful and identifying areas for future work.
Authors: Adam Karvonen
Abstract: Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss when replacing model activations with SAE reconstructions. Typically, SAEs are trained solely on mean squared error (MSE) using precomputed, shuffled activations. Recent work introduced training SAEs directly with a combination of KL divergence and MSE ("end-to-end" SAEs), significantly improving reconstruction accuracy at the cost of substantially increased computation, which has limited their widespread adoption. We propose a brief KL+MSE fine-tuning step applied only to the final 25M training tokens (just a few percent of typical training budgets) that achieves comparable improvements, reducing the cross-entropy loss gap by 20-50%, while incurring minimal additional computational cost. We further find that multiple fine-tuning methods (KL fine-tuning, LoRA adapters, linear adapters) yield similar, non-additive cross-entropy improvements, suggesting a common, easily correctable error source in MSE-trained SAEs. We demonstrate a straightforward method for effectively transferring hyperparameters and sparsity penalties despite scale differences between KL and MSE losses. While both ReLU and TopK SAEs see significant cross-entropy loss improvements, evaluations on supervised SAEBench metrics yield mixed results, suggesting practical benefits depend on both SAE architecture and the specific downstream task. Nonetheless, our method offers meaningful improvements in interpretability applications such as circuit analysis with minor additional cost.
Authors: Minsu Kim, Jiayao Gu, Ye Yuan, Taeyoung Yun, Zixuan Liu, Yoshua Bengio, Can Chen
Abstract: Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is prohibitively expensive or infeasible, with applications spanning protein engineering, material discovery, neural architecture search, and beyond. The main difficulty lies in accurately estimating the objective landscape beyond the available data, where extrapolations are fraught with significant epistemic uncertainty. This uncertainty can lead to objective hacking(reward hacking), exploiting model inaccuracies in unseen regions, or other spurious optimizations that yield misleadingly high performance estimates outside the training distribution. Recent advances in model-based optimization(MBO) have harnessed the generalization capabilities of deep neural networks to develop offline-specific surrogate and generative models. Trained with carefully designed strategies, these models are more robust against out-of-distribution issues, facilitating the discovery of improved designs. Despite its growing impact in accelerating scientific discovery, the field lacks a comprehensive review. To bridge this gap, we present the first thorough review of offline MBO. We begin by formalizing the problem for both single-objective and multi-objective settings and by reviewing recent benchmarks and evaluation metrics. We then categorize existing approaches into two key areas: surrogate modeling, which emphasizes accurate function approximation in out-of-distribution regions, and generative modeling, which explores high-dimensional design spaces to identify high-performing designs. Finally, we examine the key challenges and propose promising directions for advancement in this rapidly evolving field including safe control of superintelligent systems.
Authors: Ali Rabeh, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
Abstract: Accurate modeling of fluid dynamics around complex geometries is critical for applications such as aerodynamic optimization and biomedical device design. While advancements in numerical methods and high-performance computing have improved simulation capabilities, the computational cost of high-fidelity 3D flow simulations remains a significant challenge. Scientific machine learning (SciML) offers an efficient alternative, enabling rapid and reliable flow predictions. In this study, we evaluate Deep Operator Networks (DeepONet) and Geometric-DeepONet, a variant that incorporates geometry information via signed distance functions (SDFs), on steady-state 3D flow over complex objects. Our dataset consists of 1,000 high-fidelity simulations spanning Reynolds numbers from 10 to 1,000, enabling comprehensive training and evaluation across a range of flow regimes. To assess model generalization, we test our models on a random and extrapolatory train-test splitting. Additionally, we explore a derivative-informed training strategy that augments standard loss functions with velocity gradient penalties and incompressibility constraints, improving physics consistency in 3D flow prediction. Our results show that Geometric-DeepONet improves boundary-layer accuracy by up to 32% compared to standard DeepONet. Moreover, incorporating derivative constraints enhances gradient accuracy by 25% in interpolation tasks and up to 45% in extrapolatory test scenarios, suggesting significant improvement in generalization capabilities to unseen 3D Reynolds numbers.
Authors: Yashas Annadani, Syrine Belakaria, Stefano Ermon, Stefan Bauer, Barbara E Engelhardt
Abstract: Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by leveraging a classifier-based guidance mechanism. Our guidance classifier is a preference model trained to predict the probability that one design dominates another, directing the diffusion model toward optimal regions of the design space. Crucially, this preference model generalizes beyond the training distribution, enabling the discovery of Pareto-optimal solutions outside the observed dataset. We introduce a novel diversity-aware preference guidance, augmenting Pareto dominance preference with diversity criteria. This ensures that generated solutions are optimal and well-distributed across the objective space, a capability absent in prior generative methods for offline multi-objective optimization. We evaluate our approach on various continuous offline multi-objective optimization tasks and find that it consistently outperforms other inverse/generative approaches while remaining competitive with forward/surrogate-based optimization methods. Our results highlight the effectiveness of classifier-guided diffusion models in generating diverse and high-quality solutions that approximate the Pareto front well.
Authors: Do-kyum Kim, Han Zhao, Huiji Gao, Liwei He, Malay Haldar, Sanjeev Katariya
Abstract: Airbnb is an online marketplace that connects hosts and guests to unique stays and experiences. When guests stay at homes booked on Airbnb, there are a small fraction of stays that lead to support needed from Airbnb's Customer Support (CS), which may cause inconvenience to guests and hosts and require Airbnb resources to resolve. In this work, we show that instances where CS support is needed may be predicted based on hosts and guests behavior. We build a model to predict the likelihood of CS support needs for each match of guest and host. The model score is incorporated into Airbnb's search ranking algorithm as one of the many factors. The change promotes more reliable matches in search results and significantly reduces bookings that require CS support.
Authors: Alex Reneau, Jerry Yao-Chieh Hu, Zhongfang Zhuang, Ting-Chun Liu
Abstract: Many high-impact machine learning tasks involve multi-dimensional data (e.g., images, volumetric medical scans, multivariate time-series). Yet, most neural architectures flatten inputs, discarding critical cross-dimension information. We introduce NdLinear, a novel linear transformation that preserves these structures without extra overhead. By operating separately along each dimension, NdLinear captures dependencies that standard fully connected layers overlook. Extensive experiments across convolutional, recurrent, and transformer-based networks show significant improvements in representational power and parameter efficiency. Crucially, NdLinear serves as a foundational building block for large-scale foundation models by operating on any unimodal or multimodal data in its native form. This removes the need for flattening or modality-specific preprocessing. Ndlinear rethinks core architectural priorities beyond attention, enabling more expressive, context-aware models at scale. We propose NdLinear as a drop-in replacement for standard linear layers -- marking an important step toward next-generation neural architectures.
Authors: Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee
Abstract: Flow matching in the continuous simplex has emerged as a promising strategy for DNA sequence design, but struggles to scale to higher simplex dimensions required for peptide and protein generation. We introduce Gumbel-Softmax Flow and Score Matching, a generative framework on the simplex based on a novel Gumbel-Softmax interpolant with a time-dependent temperature. Using this interpolant, we introduce Gumbel-Softmax Flow Matching by deriving a parameterized velocity field that transports from smooth categorical distributions to distributions concentrated at a single vertex of the simplex. We alternatively present Gumbel-Softmax Score Matching which learns to regress the gradient of the probability density. Our framework enables high-quality, diverse generation and scales efficiently to higher-dimensional simplices. To enable training-free guidance, we propose Straight-Through Guided Flows (STGFlow), a classifier-based guidance method that leverages straight-through estimators to steer the unconditional velocity field toward optimal vertices of the simplex. STGFlow enables efficient inference-time guidance using classifiers pre-trained on clean sequences, and can be used with any discrete flow method. Together, these components form a robust framework for controllable de novo sequence generation. We demonstrate state-of-the-art performance in conditional DNA promoter design, sequence-only protein generation, and target-binding peptide design for rare disease treatment.
Authors: Dongsheng Yang, Wataru Sato, Qianying Liu, Takashi Minato, Shushi Namba, Shin'ya Nishida
Abstract: Expressing various facial emotions is an important social ability for efficient communication between humans. A key challenge in human-robot interaction research is providing androids with the ability to make various human-like facial expressions for efficient communication with humans. The android Nikola, we have developed, is equipped with many actuators for facial muscle control. While this enables Nikola to simulate various human expressions, it also complicates identification of the optimal parameters for producing desired expressions. Here, we propose a novel method that automatically optimizes the facial expressions of our android. We use a machine vision algorithm to evaluate the magnitudes of seven basic emotions, and employ the Bayesian Optimization algorithm to identify the parameters that produce the most convincing facial expressions. Evaluations by naive human participants demonstrate that our method improves the rated strength of the android's facial expressions of anger, disgust, sadness, and surprise compared with the previous method that relied on Ekman's theory and parameter adjustments by a human expert.
Authors: Anna Kleinau, Bernhard Preim, Monique Meuschke
Abstract: In an era where black-box AI models are integral to decision-making across industries, robust methods for explaining these models are more critical than ever. While these models leverage complex feature interplay for accurate predictions, most explanation methods only assign relevance to individual features. There is a research gap in methods that effectively illustrate interactions between features, especially in visualizing higher-order interactions involving multiple features, which challenge conventional representation methods. To address this challenge in local explanations focused on individual instances, we employ a visual, subset-based approach to reveal relevant feature interactions. Our visual analytics tool FINCH uses coloring and highlighting techniques to create intuitive, human-centered visualizations, and provides additional views that enable users to calibrate their trust in the model and explanations. We demonstrate FINCH in multiple case studies, demonstrating its generalizability, and conducted an extensive human study with machine learning experts to highlight its helpfulness and usability. With this approach, FINCH allows users to visualize feature interactions involving any number of features locally.
Authors: Petr Parshakov, Iuliia Naidenova, Sofia Paklina, Nikita Matkin, Cornel Nesseler
Abstract: In this paper, we investigate how individuals evaluate human and large langue models generated responses to popular questions when the source of the content is either concealed or disclosed. Through a controlled field experiment, participants were presented with a set of questions, each accompanied by a response generated by either a human or an AI. In a randomized design, half of the participants were informed of the response's origin while the other half remained unaware. Our findings indicate that, overall, participants tend to prefer AI-generated responses. However, when the AI origin is revealed, this preference diminishes significantly, suggesting that evaluative judgments are influenced by the disclosure of the response's provenance rather than solely by its quality. These results underscore a bias against AI-generated content, highlighting the societal challenge of improving the perception of AI work in contexts where quality assessments should be paramount.
Authors: Kunal Chavan, Keertan Balaji, Spoorti Barigidad, Samba Raju Chiluveru
Abstract: With an increasing demand for assistive technologies that promote the independence and mobility of visually impaired people, this study suggests an innovative real-time system that gives audio descriptions of a user's surroundings to improve situational awareness. The system acquires live video input and processes it with a quantized and fine-tuned Florence-2 big model, adjusted to 4-bit accuracy for efficient operation on low-power edge devices such as the NVIDIA Jetson Orin Nano. By transforming the video signal into frames with a 5-frame latency, the model provides rapid and contextually pertinent descriptions of objects, pedestrians, and barriers, together with their estimated distances. The system employs Parler TTS Mini, a lightweight and adaptable Text-to-Speech (TTS) solution, for efficient audio feedback. It accommodates 34 distinct speaker types and enables customization of speech tone, pace, and style to suit user requirements. This study examines the quantization and fine-tuning techniques utilized to modify the Florence-2 model for this application, illustrating how the integration of a compact model architecture with a versatile TTS component improves real-time performance and user experience. The proposed system is assessed based on its accuracy, efficiency, and usefulness, providing a viable option to aid vision-impaired users in navigating their surroundings securely and successfully.
Authors: Enzo Sinacola, Arnault Pachot, Thierry Petit
Abstract: Large Language Models (LLMs) offer a promising alternative to traditional survey methods, potentially enhancing efficiency and reducing costs. In this study, we use LLMs to create virtual populations that answer survey questions, enabling us to predict outcomes comparable to human responses. We evaluate several LLMs-including GPT-4o, GPT-3.5, Claude 3.5-Sonnet, and versions of the Llama and Mistral models-comparing their performance to that of a traditional Random Forests algorithm using demographic data from the World Values Survey (WVS). LLMs demonstrate competitive performance overall, with the significant advantage of requiring no additional training data. However, they exhibit biases when predicting responses for certain religious and population groups, underperforming in these areas. On the other hand, Random Forests demonstrate stronger performance than LLMs when trained with sufficient data. We observe that removing censorship mechanisms from LLMs significantly improves predictive accuracy, particularly for underrepresented demographic segments where censored models struggle. These findings highlight the importance of addressing biases and reconsidering censorship approaches in LLMs to enhance their reliability and fairness in public opinion research.
Authors: Andy Buschmann
Abstract: This paper introduces a simple JavaScript-based web application designed to assist educators in detecting AI-generated content in student essays and written assignments. Unlike existing AI detection tools that rely on obfuscated machine learning models, AIDetection.info employs a heuristic-based approach to identify common syntactic traces left by generative AI models, such as ChatGPT, Claude, Grok, DeepSeek, Gemini, Llama/Meta, Microsoft Copilot, Grammarly AI, and other text-generating models and wrapper applications. The tool scans documents in bulk for potential AI artifacts, as well as AI citations and acknowledgments, and provides a visual summary with downloadable Excel and CSV reports. This article details its methodology, functionalities, limitations, and applications within educational settings.
Authors: Dimitris Tsirmpas, Ion Androutsopoulos, John Pavlopoulos
Abstract: Despite the ever-growing importance of online moderation, there has been no large-scale study evaluating the effectiveness of alternative moderation strategies. This is largely due to the lack of appropriate datasets, and the difficulty of getting human discussants, moderators, and evaluators involved in multiple experiments. In this paper, we propose a methodology for leveraging synthetic experiments performed exclusively by Large Language Models (LLMs) to initially bypass the need for human participation in experiments involving online moderation. We evaluate six LLM moderation configurations; two currently used real-life moderation strategies (guidelines issued for human moderators for online moderation and real-life facilitation), two baseline strategies (guidelines elicited for LLM alignment work, and LLM moderation with minimal prompting) a baseline with no moderator at all, as well as our own proposed strategy inspired by a Reinforcement Learning (RL) formulation of the problem. We find that our own moderation strategy significantly outperforms established moderation guidelines, as well as out-of-the-box LLM moderation. We also find that smaller LLMs, with less intensive instruction-tuning, can create more varied discussions than larger models. In order to run these experiments, we create and release an efficient, purpose-built, open-source Python framework, dubbed "SynDisco" to easily simulate hundreds of discussions using LLM user-agents and moderators. Additionally, we release the Virtual Moderation Dataset (VMD), a large dataset of LLM-generated and LLM-annotated discussions, generated by three families of open-source LLMs accompanied by an exploratory analysis of the dataset.
Authors: Bardia Nadimi, Ghali Omar Boutaib, Hao Zheng
Abstract: Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands both expert knowledge and iterative refinement. Leveraging recent advancements in large language models (LLMs) and their structured text generation capabilities, we propose VeriMind, an agentic LLM framework for Verilog code generation that significantly automates and optimizes the synthesis process. Unlike traditional LLM-based code generators, VeriMind employs a structured reasoning approach: given a user-provided prompt describing design requirements, the system first formulates a detailed train of thought before the final Verilog code is generated. This multi-step methodology enhances interpretability, accuracy, and adaptability in hardware design. In addition, we introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement. Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3\%$ improvement on pass@k metric and $8.1\%$ on pass@ARC metric. These findings underscore the transformative potential of agentic LLMs in automated hardware design, RTL development, and digital system synthesis.
Authors: Dian Chen, Han Jun Yoon, Zelin Wan, Nithin Alluru, Sang Won Lee, Richard He, Terrence J. Moore, Frederica F. Nelson, Sunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Jin-Hee Cho
Abstract: Human-Machine Teaming (HMT) is revolutionizing collaboration across domains such as defense, healthcare, and autonomous systems by integrating AI-driven decision-making, trust calibration, and adaptive teaming. This survey presents a comprehensive taxonomy of HMT, analyzing theoretical models, including reinforcement learning, instance-based learning, and interdependence theory, alongside interdisciplinary methodologies. Unlike prior reviews, we examine team cognition, ethical AI, multi-modal interactions, and real-world evaluation frameworks. Key challenges include explainability, role allocation, and scalable benchmarking. We propose future research in cross-domain adaptation, trust-aware AI, and standardized testbeds. By bridging computational and social sciences, this work lays a foundation for resilient, ethical, and scalable HMT systems.
Authors: Tidiane Camaret N'dir, Robin Tibor Schirrmeister
Abstract: Deep networks for electroencephalogram (EEG) decoding are currently often trained to only solve a specific task like pathology or gender decoding. A more general approach leveraging the medical reports of clinical EEG recordings is to learn mappings between medical reports and EEG recordings. This approach was pioneered in the computer vision domain matching images and their text captions and subsequently allowed to do successful zero-shot decoding using textual class prompts. In this work, we follow this approach and develop a contrastive learning framework EEG-CLIP that aligns EEG time series and their corresponding clinical text descriptions in a shared embedding space. We investigate its potential for versatile EEG decoding, assessing performance on a range of few-shot and zero-shot settings. Overall, results show that EEG-CLIP manages to nontrivially align text and EEG representations. Our work presents a promising approach to learn general EEG representations, which could enable easier analyses of diverse decoding questions through zero shot decoding or training task-specific models from fewer training examples. The code for reproducing our results is available at https://github.com/tidiane-camaret/EEGClip.
Authors: Shiyi Jiang, Farshad Firouzi, Krishnendu Chakrabarty
Abstract: The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient identification issues. Privacy-preserving machine learning (PPML) and privacy-enhancing technologies, particularly federated learning (FL), have emerged in recent years as innovative solutions to balance privacy protection with data utility; however, they also suffer from inherent privacy vulnerabilities. Gradient inversion attacks constitute major threats to data sharing in federated learning. Researchers have proposed many defenses against gradient inversion attacks. However, current defense methods for healthcare data lack generalizability, i.e., existing solutions may not be applicable to data from a broader range of populations. In addition, most existing defense methods are tested using non-healthcare data, which raises concerns about their applicability to real-world healthcare systems. In this study, we present a defense against gradient inversion attacks in federated learning. We achieve this using latent data perturbation and minimax optimization, utilizing both general and medical image datasets. Our method is compared to two baselines, and the results show that our approach can outperform the baselines with a reduction of 12.5% in the attacker's accuracy in classifying reconstructed images. The proposed method also yields an increase of over 12.4% in Mean Squared Error (MSE) between the original and reconstructed images at the same level of model utility of around 90% client classification accuracy. The results suggest the potential of a generalizable defense for healthcare data.
Authors: Saddam Hussain Khan (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences), Rashid Iqbal (Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering,Applied Sciences)
Abstract: Deep Convolutional Neural Networks (CNNs) have significantly advanced deep learning, driving breakthroughs in computer vision, natural language processing, medical diagnosis, object detection, and speech recognition. Architectural innovations including 1D, 2D, and 3D convolutional models, dilated and grouped convolutions, depthwise separable convolutions, and attention mechanisms address domain-specific challenges and enhance feature representation and computational efficiency. Structural refinements such as spatial-channel exploitation, multi-path design, and feature-map enhancement contribute to robust hierarchical feature extraction and improved generalization, particularly through transfer learning. Efficient preprocessing strategies, including Fourier transforms, structured transforms, low-precision computation, and weight compression, optimize inference speed and facilitate deployment in resource-constrained environments. This survey presents a unified taxonomy that classifies CNN architectures based on spatial exploitation, multi-path structures, depth, width, dimensionality expansion, channel boosting, and attention mechanisms. It systematically reviews CNN applications in face recognition, pose estimation, action recognition, text classification, statistical language modeling, disease diagnosis, radiological analysis, cryptocurrency sentiment prediction, 1D data processing, video analysis, and speech recognition. In addition to consolidating architectural advancements, the review highlights emerging learning paradigms such as few-shot, zero-shot, weakly supervised, federated learning frameworks and future research directions include hybrid CNN-transformer models, vision-language integration, generative learning, etc. This review provides a comprehensive perspective on CNN's evolution from 2015 to 2025, outlining key innovations, challenges, and opportunities.
Authors: Abdulaziz Al Mannai
Abstract: Qatar's football sector has undergone a substantial technological transformation with the implementation of Electronic Performance and Tracking Systems (EPTS). This study examines the impact of cultural and technological factors on EPTS adoption, using Hofstede's Cultural Dimensions Theory and the Technology Acceptance Model (TAM) as theoretical frameworks. An initial exploratory study involved ten participants, followed by an expanded dataset comprising thirty stakeholders, including players, coaches, and staff from Qatari football organizations. Multiple regression analysis was conducted to evaluate the relationships between perceived usefulness, perceived ease of use, power distance, innovation receptiveness, integration complexity, and overall adoption. The results indicate that perceived usefulness, innovation receptiveness, and lower power distance significantly drive EPTS adoption, while ease of use is marginally significant and integration complexity is non-significant in this sample. These findings provide practical insights for sports technology stakeholders in Qatar and emphasize the importance of aligning cultural considerations with technological readiness for successful EPTS integration.
Authors: Bereket Kindo, Arjee Restar, Anh Tran
Abstract: Alzheimer's disease and related dementias (AD/ADRD) represent a growing healthcare crisis affecting over 6 million Americans. While genetic factors play a crucial role, emerging research reveals that social determinants of health (SDOH) significantly influence both the risk and progression of cognitive functioning, such as cognitive scores and cognitive decline. This report examines how these social, environmental, and structural factors impact cognitive health trajectories, with a particular focus on Hispanic populations, who face disproportionate risk for AD/ADRD. Using data from the Mexican Health and Aging Study (MHAS) and its cognitive assessment sub study (Mex-Cog), we employed ensemble of regression trees models to predict 4-year and 9-year cognitive scores and cognitive decline based on SDOH. This approach identified key predictive SDOH factors to inform potential multilevel interventions to address cognitive health disparities in this population.
Authors: Ibrahim Al Azher, Miftahul Jannat Mokarrama, Zhishuai Guo, Sagnik Ray Choudhury, Hamed Alhoori
Abstract: The future work section of a scientific article outlines potential research directions by identifying gaps and limitations of a current study. This section serves as a valuable resource for early-career researchers seeking unexplored areas and experienced researchers looking for new projects or collaborations. In this study, we generate future work suggestions from key sections of a scientific article alongside related papers and analyze how the trends have evolved. We experimented with various Large Language Models (LLMs) and integrated Retrieval-Augmented Generation (RAG) to enhance the generation process. We incorporate a LLM feedback mechanism to improve the quality of the generated content and propose an LLM-as-a-judge approach for evaluation. Our results demonstrated that the RAG-based approach with LLM feedback outperforms other methods evaluated through qualitative and quantitative metrics. Moreover, we conduct a human evaluation to assess the LLM as an extractor and judge. The code and dataset for this project are here, code: HuggingFace
Authors: Kevine Meugang Toukam
Abstract: We introduce a modified Benamou-Brenier type approach leading to a Wasserstein type distance that allows global invariance, specifically, isometries, and we show that the problem can be summarized to orthogonal transformations. This distance is defined by penalizing the action with a costless movement of the particle that does not change the direction and speed of its trajectory. We show that for Gaussian distribution resume to measuring the Euclidean distance between their ordered vector of eigenvalues and we show a direct application in recovering Latent Gaussian distributions.
Authors: Zahra Khalila, Arbi Haza Nasution, Winda Monika, Aytug Onan, Yohei Murakami, Yasir Bin Ismail Radi, Noor Mohammad Osmani
Abstract: Accurate and contextually faithful responses are critical when applying large language models (LLMs) to sensitive and domain-specific tasks, such as answering queries related to quranic studies. General-purpose LLMs often struggle with hallucinations, where generated responses deviate from authoritative sources, raising concerns about their reliability in religious contexts. This challenge highlights the need for systems that can integrate domain-specific knowledge while maintaining response accuracy, relevance, and faithfulness. In this study, we investigate 13 open-source LLMs categorized into large (e.g., Llama3:70b, Gemma2:27b, QwQ:32b), medium (e.g., Gemma2:9b, Llama3:8b), and small (e.g., Llama3.2:3b, Phi3:3.8b). A Retrieval-Augmented Generation (RAG) is used to make up for the problems that come with using separate models. This research utilizes a descriptive dataset of Quranic surahs including the meanings, historical context, and qualities of the 114 surahs, allowing the model to gather relevant knowledge before responding. The models are evaluated using three key metrics set by human evaluators: context relevance, answer faithfulness, and answer relevance. The findings reveal that large models consistently outperform smaller models in capturing query semantics and producing accurate, contextually grounded responses. The Llama3.2:3b model, even though it is considered small, does very well on faithfulness (4.619) and relevance (4.857), showing the promise of smaller architectures that have been well optimized. This article examines the trade-offs between model size, computational efficiency, and response quality while using LLMs in domain-specific applications.
Authors: Hadi Amini, Md Jueal Mia, Yasaman Saadati, Ahmed Imteaj, Seyedsina Nabavirazavi, Urmish Thakker, Md Zarif Hossain, Awal Ahmed Fime, S. S. Iyengar
Abstract: Language models (LMs) are machine learning models designed to predict linguistic patterns by estimating the probability of word sequences based on large-scale datasets, such as text. LMs have a wide range of applications in natural language processing (NLP) tasks, including autocomplete and machine translation. Although larger datasets typically enhance LM performance, scalability remains a challenge due to constraints in computational power and resources. Distributed computing strategies offer essential solutions for improving scalability and managing the growing computational demand. Further, the use of sensitive datasets in training and deployment raises significant privacy concerns. Recent research has focused on developing decentralized techniques to enable distributed training and inference while utilizing diverse computational resources and enabling edge AI. This paper presents a survey on distributed solutions for various LMs, including large language models (LLMs), vision language models (VLMs), multimodal LLMs (MLLMs), and small language models (SLMs). While LLMs focus on processing and generating text, MLLMs are designed to handle multiple modalities of data (e.g., text, images, and audio) and to integrate them for broader applications. To this end, this paper reviews key advancements across the MLLM pipeline, including distributed training, inference, fine-tuning, and deployment, while also identifying the contributions, limitations, and future areas of improvement. Further, it categorizes the literature based on six primary focus areas of decentralization. Our analysis describes gaps in current methodologies for enabling distributed solutions for LMs and outline future research directions, emphasizing the need for novel solutions to enhance the robustness and applicability of distributed LMs.
Authors: Li Fan, Jing Yang, Cong Shen
Abstract: Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts without model update. Transformer-based wireless receivers, where prompts consist of the pilot data in the form of transmitted and received signal pairs, have shown high detection accuracy when pilot data are abundant. However, pilot information is often costly and limited in practice. In this work, we propose the DEcision Feedback INcontExt Detection (DEFINED) solution as a new wireless receiver design, which bypasses channel estimation and directly performs symbol detection using the (sometimes extremely) limited pilot data. The key innovation in DEFINED is the proposed decision feedback mechanism in ICL, where we sequentially incorporate the detected symbols into the prompts as pseudo-labels to improve the detection for subsequent symbols. Furthermore, we proposed another detection method where we combine ICL with Semi-Supervised Learning (SSL) to extract information from both labeled and unlabeled data during inference, thus avoiding the errors propagated during the decision feedback process of the original DEFINED. Extensive experiments across a broad range of wireless communication settings demonstrate that a small Transformer trained with DEFINED or IC-SSL achieves significant performance improvements over conventional methods, in some cases only needing a single pilot pair to achieve similar performance of the latter with more than 4 pilot pairs.
Authors: Katja Schwarz, Denys Rozumnyi, Samuel Rota Bul\`o, Lorenzo Porzi, Peter Kontschieder
Abstract: We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires minimal training and uses existing generative models. Our process involves two steps: generating coherent panoramas using a pre-trained diffusion model and lifting these into 3D with a metric depth estimator. We then fill unobserved regions by conditioning the inpainting model on rendered point clouds, requiring minimal fine-tuning. Tested on both synthetic and real images, our method produces high-quality 3D environments suitable for VR display. By explicitly modeling the 3D structure of the generated environment from the start, our approach consistently outperforms state-of-the-art, video synthesis-based methods along multiple quantitative image quality metrics. Project Page: https://katjaschwarz.github.io/worlds/
Authors: Ashten Akemoto, Frances Zhu
Abstract: Many environments, such as unvisited planetary surfaces and oceanic regions, remain unexplored due to a lack of prior knowledge. Autonomous vehicles must sample upon arrival, process data, and either transmit findings to a teleoperator or decide where to explore next. Teleoperation is suboptimal, as human intuition lacks mathematical guarantees for optimality. This study evaluates an informative path planning algorithm for mapping a scalar variable distribution while minimizing travel distance and ensuring model convergence. We compare traditional open loop coverage methods (e.g., Boustrophedon, Spiral) with information-theoretic approaches using Gaussian processes, which update models iteratively with confidence metrics. The algorithm's performance is tested on three surfaces, a parabola, Townsend function, and lunar crater hydration map, to assess noise, convexity, and function behavior. Results demonstrate that information-driven methods significantly outperform naive exploration in reducing model error and travel distance while improving convergence potential.
Authors: Maria de Lourdes M. Silva, Andr\'e L. C. Mendon\c{c}a, Eduardo R. D. Neto, Iago C. Chaves, Felipe T. Brito, Victor A. E. Farias, Javam C. Machado
Abstract: Computer manufacturers typically offer platforms for users to report faults. However, there remains a significant gap in these platforms' ability to effectively utilize textual reports, which impedes users from describing their issues in their own words. In this context, Natural Language Processing (NLP) offers a promising solution, by enabling the analysis of user-generated text. This paper presents an innovative approach that employs NLP models to classify user reports for detecting faulty computer components, such as CPU, memory, motherboard, video card, and more. In this work, we build a dataset of 341 user reports obtained from many sources. Additionally, through extensive experimental evaluation, our approach achieved an accuracy of 79% with our dataset.
Authors: Moshiur Rahman Tonmoy, Md. Mithun Hossain, Nilanjan Dey, M. F. Mridha
Abstract: Plant diseases significantly threaten global food security by reducing crop yields and undermining agricultural sustainability. AI-driven automated classification has emerged as a promising solution, with deep learning models demonstrating impressive performance in plant disease identification. However, deploying these models on mobile and edge devices remains challenging due to high computational demands and resource constraints, highlighting the need for lightweight, accurate solutions for accessible smart agriculture systems. To address this, we propose MobilePlantViT, a novel hybrid Vision Transformer (ViT) architecture designed for generalized plant disease classification, which optimizes resource efficiency while maintaining high performance. Extensive experiments across diverse plant disease datasets of varying scales show our model's effectiveness and strong generalizability, achieving test accuracies ranging from 80% to over 99%. Notably, with only 0.69 million parameters, our architecture outperforms the smallest versions of MobileViTv1 and MobileViTv2, despite their higher parameter counts. These results underscore the potential of our approach for real-world, AI-powered automated plant disease classification in sustainable and resource-efficient smart agriculture systems. All codes will be available in the GitHub repository: https://github.com/moshiurtonmoy/MobilePlantViT
Authors: Alejandro Ariza-Casabona, Nikos Kanakaris, Daniele Malitesta
Abstract: Relational deep learning (RDL) settles among the most exciting advances in machine learning for relational databases, leveraging the representational power of message passing graph neural networks (GNNs) to derive useful knowledge and run predicting tasks on tables connected through primary-to-foreign key links. The RDL paradigm has been successfully applied to recommendation lately, through its most recent representative deep learning architecture namely, ContextGNN. While acknowledging ContextGNN's improved performance on real-world recommendation datasets and tasks, preliminary tests for the more traditional static link prediction task (aka personalized item recommendation) on the popular Amazon Book dataset have demonstrated how ContextGNN has still room for improvement compared to other state-of-the-art GNN-based recommender systems. To this end, with this paper, we integrate ContextGNN within Elliot, a popular framework for reproducibility and benchmarking analyses, counting around 50 state-of-the-art recommendation models from the literature to date. On such basis, we run preliminary experiments on three standard recommendation datasets and against six state-of-the-art GNN-based recommender systems, confirming similar trends to those observed by the authors in their original paper. The code is publicly available on GitHub: https://github.com/danielemalitesta/Rel-DeepLearning-RecSys.
URLs: https://github.com/danielemalitesta/Rel-DeepLearning-RecSys.
Authors: Baturalp Yalcin, Javad Lavaei
Abstract: This paper investigates a subgradient-based algorithm to solve the system identification problem for linear time-invariant systems with non-smooth objectives. This is essential for robust system identification in safety-critical applications. While existing work provides theoretical exact recovery guarantees using optimization solvers, the design of fast learning algorithms with convergence guarantees for practical use remains unexplored. We analyze the subgradient method in this setting where the optimization problems to be solved change over time as new measurements are taken, and we establish linear convergence results for both the best and Polyak step sizes after a burn-in period. Additionally, we characterize the asymptotic convergence of the best average sub-optimality gap under diminishing and constant step sizes. Finally, we compare the time complexity of standard solvers with the subgradient algorithm and support our findings with experimental results. This is the first work to analyze subgradient algorithms for system identification with non-smooth objectives.
Authors: Afrah Farea, Saiful Khan, Mustafa Serdar Celebi
Abstract: Hybrid quantum-classical neural network methods represent an emerging approach to solving computational challenges by leveraging advantages from both paradigms. As physics-informed neural networks (PINNs) have successfully applied to solve partial differential equations (PDEs) by incorporating physical constraints into neural architectures, this work investigates whether quantum-classical physics-informed neural networks (QCPINNs) can efficiently solve PDEs with reduced parameter counts compared to classical approaches. We evaluate two quantum circuit paradigms: continuous-variable (CV) and qubit-based discrete-variable (DV) across multiple circuit ansatze (Alternate, Cascade, Cross mesh, and Layered). Benchmarking across five challenging PDEs (Helmholtz, Cavity, Wave, Klein-Gordon, and Convection-Diffusion equations) demonstrates that our hybrid approaches achieve comparable accuracy to classical PINNs while requiring up to 89% fewer trainable parameters. DV-based implementations, particularly those with angle encoding and cascade circuit configurations, exhibit better stability and convergence properties across all problem types. For the Convection-Diffusion equation, our angle-cascade QCPINN achieves parameter efficiency and a 37% reduction in relative L2 error compared to classical counterparts. Our findings highlight the potential of quantum-enhanced architectures for physics-informed learning, establishing parameter efficiency as a quantifiable quantum advantage while providing a foundation for future quantum-classical hybrid systems solving complex physical models.
Authors: R. Landman, S. Y. Haffert, J. D. Long, J. R. Males, L. M. Close, W. B. Foster, K. Van Gorkom, O. Guyon, A. D. Hedglen, P. T. Johnson, M. Y. Kautz, J. K. Kueny, J. Li, J. Liberman, J. Lumbres, E. A. McEwen, A. McLeod, L. Schatz, E. Tonucci, K. Twitchell
Abstract: Pyramid wavefront sensors (PWFSs) are the preferred choice for current and future extreme adaptive optics (XAO) systems. Almost all instruments use the PWFS in its modulated form to mitigate its limited linearity range. However, this modulation comes at the cost of a reduction in sensitivity, a blindness to petal-piston modes, and a limit to the sensor's ability to operate at high speeds. Therefore, there is strong interest to use the PWFS without modulation, which can be enabled with nonlinear reconstructors. Here, we present the first on-sky demonstration of XAO with an unmodulated PWFS using a nonlinear reconstructor based on convolutional neural networks. We discuss the real-time implementation on the Magellan Adaptive Optics eXtreme (MagAO-X) instrument using the optimized TensorRT framework and show that inference is fast enough to run the control loop at >2 kHz frequencies. Our on-sky results demonstrate a successful closed-loop operation using a model calibrated with internal source data that delivers stable and robust correction under varying conditions. Performance analysis reveals that our smart PWFS achieves nearly the same Strehl ratio as the highly optimized modulated PWFS under favorable conditions on bright stars. Notably, we observe an improvement in performance on a fainter star under the influence of strong winds. These findings confirm the feasibility of using the PWFS in its unmodulated form and highlight its potential for next-generation instruments. Future efforts will focus on achieving even higher control loop frequencies (>3 kHz), optimizing the calibration procedures, and testing its performance on fainter stars, where more gain is expected for the unmodulated PWFS compared to its modulated counterpart.
Authors: Anna P. Kwossek, David J. Pr\"omel, Josef Teichmann
Abstract: We identify various classes of neural networks that are able to approximate continuous functions locally uniformly subject to fixed global linear growth constraints. For such neural networks the associated neural stochastic differential equations can approximate general stochastic differential equations, both of It\^o diffusion type, arbitrarily well. Moreover, quantitative error estimates are derived for stochastic differential equations with sufficiently regular coefficients.
Authors: Mihaela-Larisa Clement, M\'onika Farsang, Felix Resch, Radu Grosu
Abstract: Autonomous agents that rely purely on perception to make real-time control decisions require efficient and robust architectures. In this work, we demonstrate that augmenting RGB input with depth information significantly enhances our agents' ability to predict steering commands compared to using RGB alone. We benchmark lightweight recurrent controllers that leverage the fused RGB-D features for sequential decision-making. To train our models, we collect high-quality data using a small-scale autonomous car controlled by an expert driver via a physical steering wheel, capturing varying levels of steering difficulty. Our models, trained under diverse configurations, were successfully deployed on real hardware. Specifically, our findings reveal that the early fusion of depth data results in a highly robust controller, which remains effective even with frame drops and increased noise levels, without compromising the network's focus on the task.
Authors: Massa Baali, Xiang Li, Hao Chen, Rita Singh, Bhiksha Raj
Abstract: Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test instances to known examples. The models performing inference must hence naturally generate embeddings that cluster same-class instances compactly, while maintaining separation across classes. In order to learn to do so, they are typically trained on a large number of classes (speakers), often using specialized losses. However real-world speaker datasets often lack the class diversity needed to effectively learn this in a generalizable manner. We introduce CAARMA, a class augmentation framework that addresses this problem by generating synthetic classes through data mixing in the embedding space, expanding the number of training classes. To ensure the authenticity of the synthetic classes we adopt a novel adversarial refinement mechanism that minimizes categorical distinctions between synthetic and real classes. We evaluate CAARMA on multiple speaker verification tasks, as well as other representative zero-shot comparison-based speech analysis tasks and obtain consistent improvements: our framework demonstrates a significant improvement of 8\% over all baseline models. Code for CAARMA will be released.
Authors: Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas, Letian Chen, Rohan Paleja, Matthew Gombolay
Abstract: Semantic Interpretability in Reinforcement Learning (RL) enables transparency, accountability, and safer deployment by making the agent's decisions understandable and verifiable. Achieving this, however, requires a feature space composed of human-understandable concepts, which traditionally rely on human specification and fail to generalize to unseen environments. In this work, we introduce Semantically Interpretable Reinforcement Learning with Vision-Language Models Empowered Automation (SILVA), an automated framework that leverages pre-trained vision-language models (VLM) for semantic feature extraction and interpretable tree-based models for policy optimization. SILVA first queries a VLM to identify relevant semantic features for an unseen environment, then extracts these features from the environment. Finally, it trains an Interpretable Control Tree via RL, mapping the extracted features to actions in a transparent and interpretable manner. To address the computational inefficiency of extracting features directly with VLMs, we develop a feature extraction pipeline that generates a dataset for training a lightweight convolutional network, which is subsequently used during RL. By leveraging VLMs to automate tree-based RL, SILVA removes the reliance on human annotation previously required by interpretable models while also overcoming the inability of VLMs alone to generate valid robot policies, enabling semantically interpretable reinforcement learning without human-in-the-loop.
Authors: Philipp Becker, Abhinav Mehrotra, Ruchika Chavhan, Malcolm Chadwick, Luca Morreale, Mehdi Noroozi, Alberto Gil Ramos, Sourav Bhattacharya
Abstract: Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation with higher resolution or on devices with limited resources. This work introduces an efficient diffusion transformer (EDiT) to alleviate these efficiency bottlenecks in conventional DiTs and Multimodal DiTs (MM-DiTs). First, we present a novel linear compressed attention method that uses a multi-layer convolutional network to modulate queries with local information while keys and values are spatially aggregated. Second, we formulate a hybrid attention scheme for multi-modal inputs that combines linear attention for image-to-image interactions and standard scaled dot-product attention for interactions involving prompts. Merging these two approaches leads to an expressive, linear-time Multimodal Efficient Diffusion Transformer (MM-EDiT). We demonstrate the effectiveness of the EDiT and MM-EDiT architectures by integrating them into PixArt-Sigma(conventional DiT) and Stable Diffusion 3.5-Medium (MM-DiT), achieving up to 2.2x speedup with comparable image quality after distillation.
Authors: Zhaoqin "Richie" Li, Sicheng Chen
Abstract: Transformer-based LLMs spend most of their compute in large matrix multiplications for attention and feed-forward layers. Recognizing that the Q, K, and V linear projections within the Multi-Head Self-Attention (MHA) module represent a critical computational bottleneck, we strategically focused our efforts on accelerating these operations. We present a tiled matrix multiplication accelerator optimized for such workloads on a Xilinx KV260 on-board FPGA. Key innovations include persistent on-chip storage for one matrix operand, two-level tiling for data reuse, and a systolic-like unrolled compute engine. Implemented via high-level synthesis (HLS) and integrated with DistilBERT for Q, K, V projections, our accelerator achieves significant speedup and energy efficiency gains over CPU baselines. Standalone GEMM benchmarks show up to a 7x speedup over an ARM CPU (PyTorch) and ~200x over naive numpy, with a throughput of up to 3.1 GFLOPs on 768x3072 matrices. Although the overall end-to-end DistilBERT acceleration is more modest, our results validate the potential of FPGA-based acceleration for critical components of Transformer models.
Authors: Daniele Bracale, Moulinath Banerjee, Cong Shi, Yuekai Sun
Abstract: We consider price competition among multiple sellers over a selling horizon of $T$ periods. In each period, sellers simultaneously offer their prices and subsequently observe their respective demand that is unobservable to competitors. The demand function for each seller depends on all sellers' prices through a private, unknown, and nonlinear relationship. To address this challenge, we propose a semi-parametric least-squares estimation of the nonlinear mean function, which does not require sellers to communicate demand information. We show that when all sellers employ our policy, their prices converge at a rate of $O(T^{-1/7})$ to the Nash equilibrium prices that sellers would reach if they were fully informed. Each seller incurs a regret of $O(T^{5/7})$ relative to a dynamic benchmark policy. A theoretical contribution of our work is proving the existence of equilibrium under shape-constrained demand functions via the concept of $s$-concavity and establishing regret bounds of our proposed policy. Technically, we also establish new concentration results for the least squares estimator under shape constraints. Our findings offer significant insights into dynamic competition-aware pricing and contribute to the broader study of non-parametric learning in strategic decision-making.
Authors: Eric Ziebell, Ratmir Miftachov, Bernhard Stankewitz, Laura Hucker
Abstract: Iterative learning procedures are ubiquitous in machine learning and modern statistics. Regularision is typically required to prevent inflating the expected loss of a procedure in later iterations via the propagation of noise inherent in the data. Significant emphasis has been placed on achieving this regularisation implicitly by stopping procedures early. The EarlyStopping-package provides a toolbox of (in-sample) sequential early stopping rules for several well-known iterative estimation procedures, such as truncated SVD, Landweber (gradient descent), conjugate gradient descent, L2-boosting and regression trees. One of the central features of the package is that the algorithms allow the specification of the true data-generating process and keep track of relevant theoretical quantities. In this paper, we detail the principles governing the implementation of the EarlyStopping-package and provide a survey of recent foundational advances in the theoretical literature. We demonstrate how to use the EarlyStopping-package to explore core features of implicit regularisation and replicate results from the literature.
Authors: Yushen Huang, Ertai Luo, Reza Babenezhad, Yifan Sun
Abstract: Large data applications rely on storing data in massive, sparse graphs with millions to trillions of nodes. Graph-based methods, such as node prediction, aim for computational efficiency regardless of graph size. Techniques like localized approximate personalized page rank (APPR) solve sparse linear systems with complexity independent of graph size, but is in terms of the maximum node degree, which can be much larger in practice than the average node degree for real-world large graphs. In this paper, we consider an \emph{online subsampled APPR method}, where messages are intentionally dropped at random. We use tools from graph sparsifiers and matrix linear algebra to give approximation bounds on the graph's spectral properties ($O(1/\epsilon^2)$ edges), and node classification performance (added $O(n\epsilon)$ overhead).
Authors: George Cazenavette, Joel Julin, Simon Lucey
Abstract: Until quite recently, the backbone of nearly every state-of-the-art computer vision model has been the 2D convolution. At its core, a 2D convolution simultaneously mixes information across both the spatial and channel dimensions of a representation. Many recent computer vision architectures consist of sequences of isotropic blocks that disentangle the spatial and channel-mixing components. This separation of the operations allows us to more closely juxtapose the effects of spatial and channel mixing in deep learning. In this paper, we take an initial step towards garnering a deeper understanding of the roles of these mixing operations. Through our experiments and analysis, we discover that on both classical (ResNet) and cutting-edge (ConvMixer) models, we can reach nearly the same level of classification performance by and leaving the spatial mixers at their random initializations. Furthermore, we show that models with random, fixed spatial mixing are naturally more robust to adversarial perturbations. Lastly, we show that this phenomenon extends past the classification regime, as such models can also decode pixel-shuffled images.
Authors: David N. Palacio, Dipin Khati, Daniel Rodriguez-Cardenas, Alejandro Velasco, Denys Poshyvanyk
Abstract: In recent years, Language Models for Code (LLM4Code) have significantly changed the landscape of software engineering (SE) on downstream tasks, such as code generation, by making software development more efficient. Therefore, a growing interest has emerged in further evaluating these Language Models to homogenize the quality assessment of generated code. As the current evaluation process can significantly overreact on accuracy-based metrics, practitioners often seek methods to interpret LLM4Code outputs beyond canonical benchmarks. While the majority of research reports on code generation effectiveness in terms of expected ground truth, scant attention has been paid to LLMs' explanations. In essence, the decision-making process to generate code is hard to interpret. To bridge this evaluation gap, we introduce code rationales (Code$Q$), a technique with rigorous mathematical underpinning, to identify subsets of tokens that can explain individual code predictions. We conducted a thorough Exploratory Analysis to demonstrate the method's applicability and a User Study to understand the usability of code-based explanations. Our evaluation demonstrates that Code$Q$ is a powerful interpretability method to explain how (less) meaningful input concepts (i.e., natural language particle `at') highly impact output generation. Moreover, participants of this study highlighted Code$Q$'s ability to show a causal relationship between the input and output of the model with readable and informative explanations on code completion and test generation tasks. Additionally, Code$Q$ also helps to uncover model rationale, facilitating comparison with a human rationale to promote a fair level of trust and distrust in the model.
Authors: Enguang Wang, Zhimao Peng, Zhengyuan Xie, Haori Lu, Fei Yang, Xialei Liu
Abstract: Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. Although existing methods perform well on generic datasets, they struggle in fine-grained scenarios. We attribute this difficulty to their reliance on contrastive learning over global image features to automatically capture discriminative cues, which fails to capture the subtle local differences essential for distinguishing fine-grained categories. Therefore, in this paper, we propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges: the absence of annotations for novel classes complicates the extraction of the part features, and global contrastive learning prioritizes holistic feature invariance, inadvertently suppressing discriminative local part patterns. To address these challenges, we propose PartGCD, including 1) Adaptive Part Decomposition, which automatically extracts class-specific semantic parts via Gaussian Mixture Models, and 2) Part Discrepancy Regularization, enforcing explicit separation between part features to amplify fine-grained local part distinctions. Experiments demonstrate state-of-the-art performance across multiple fine-grained benchmarks while maintaining competitiveness on generic datasets, validating the effectiveness and robustness of our approach.
Authors: Hao-Yuan He, Ming Li
Abstract: This paper analyzes the learnability of neuro-symbolic (NeSy) tasks within hybrid systems. We show that the learnability of NeSy tasks can be characterized by their derived constraint satisfaction problems (DCSPs). Specifically, a task is learnable if the corresponding DCSP has a unique solution; otherwise, it is unlearnable. For learnable tasks, we establish error bounds by exploiting the clustering property of the hypothesis space. Additionally, we analyze the asymptotic error for general NeSy tasks, showing that the expected error scales with the disagreement among solutions. Our results offer a principled approach to determining learnability and provide insights into the design of new algorithms.
Authors: Hirotaka Tahara, Takamitsu Matsubara
Abstract: Applying imitation learning (IL) is challenging to nonprehensile manipulation tasks of invisible objects with partial observations, such as excavating buried rocks. The demonstrator must make such complex action decisions as exploring to find the object and task-oriented actions to complete the task while estimating its hidden state, perhaps causing inconsistent action demonstration and high cognitive load problems. For these problems, work in human cognitive science suggests that promoting the use of pre-designed, simple exploration rules for the demonstrator may alleviate the problems of action inconsistency and high cognitive load. Therefore, when performing imitation learning from demonstrations using such exploration rules, it is important to accurately imitate not only the demonstrator's task-oriented behavior but also his/her mode-switching behavior (exploratory or task-oriented behavior) under partial observation. Based on the above considerations, this paper proposes a novel imitation learning framework called Belief Exploration-Action Cloning (BEAC), which has a switching policy structure between a pre-designed exploration policy and a task-oriented action policy trained on the estimated belief states based on past history. In simulation and real robot experiments, we confirmed that our proposed method achieved the best task performance, higher mode and action prediction accuracies, while reducing the cognitive load in the demonstration indicated by a user study.
Authors: Yusuf Sale, Aaditya Ramdas
Abstract: In online selective conformal inference, data arrives sequentially, and prediction intervals are constructed only when an online selection rule is met. Since online selections may break the exchangeability between the selected test datum and the rest of the data, one must correct for this by suitably selecting the calibration data. In this paper, we evaluate existing calibration selection strategies and pinpoint some fundamental errors in the associated claims that guarantee selection-conditional coverage and control of the false coverage rate (FCR). To address these shortcomings, we propose novel calibration selection strategies that provably preserve the exchangeability of the calibration data and the selected test datum. Consequently, we demonstrate that online selective conformal inference with these strategies guarantees both selection-conditional coverage and FCR control. Our theoretical findings are supported by experimental evidence examining tradeoffs between valid methods.
Authors: Huiqiang Chen, Tianqing Zhu, Linlin Wang, Xin Yu, Longxiang Gao, Wanlei Zhou
Abstract: Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such as copyrighted works or offensive images. While existing methods attempt to eliminate specific unwanted concepts, they often fail to ensure complete removal, allowing the concept to reappear in subtle forms. For instance, a model may successfully avoid generating images in Van Gogh's style when explicitly prompted with 'Van Gogh', yet still reproduce his signature artwork when given the prompt 'Starry Night'. In this paper, we propose SAFER, a novel and efficient approach for thoroughly removing target concepts from diffusion models. At a high level, SAFER is inspired by the observed low-dimensional structure of the text embedding space. The method first identifies a concept-specific subspace $S_c$ associated with the target concept c. It then projects the prompt embeddings onto the complementary subspace of $S_c$, effectively erasing the concept from the generated images. Since concepts can be abstract and difficult to fully capture using natural language alone, we employ textual inversion to learn an optimized embedding of the target concept from a reference image. This enables more precise subspace estimation and enhances removal performance. Furthermore, we introduce a subspace expansion strategy to ensure comprehensive and robust concept erasure. Extensive experiments demonstrate that SAFER consistently and effectively erases unwanted concepts from diffusion models while preserving generation quality.
Authors: Suho Yoo, Hyunjong Ok, Jaeho Lee
Abstract: Language models pretrained on text-only corpora often struggle with tasks that require auditory commonsense knowledge. Previous work addresses this problem by augmenting the language model to retrieve knowledge from external audio databases. This approach has several limitations, such as the potential lack of relevant audio in databases and the high costs associated with constructing and querying the databases. To address these issues, we propose Imagine to Hear, a novel approach that dynamically generates auditory knowledge using generative models. Our framework detects multiple audio-related textual spans from the given prompt and generates corresponding auditory knowledge. We develop several mechanisms to efficiently process multiple auditory knowledge, including a CLAP-based rejection sampler and a language-audio fusion module. Our experiments show that our method achieves state-of-the-art performance on AuditoryBench without relying on external databases, highlighting the effectiveness of our generation-based approach.
Authors: Jingzhi Fang, Yanyan Shen, Yue Wang, Lei Chen
Abstract: As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism strategy selection), multi-LLM applications receive less attention, particularly in offline inference scenarios. In this work, we aim to improve the offline end-to-end inference efficiency of multi-LLM applications in the single-node multi-GPU environment. The problem involves two key decisions: (1) determining which LLMs to run concurrently each time (we may not run all the models at the same time), and (2) selecting a parallelism strategy to use for each LLM. This problem is NP-hard. Naive solutions may not work well because the running time for a model to complete a set of requests depends on the request workload and the selected parallelism strategy, and they lack an accurate model of the running time. As the LLM output lengths are unknown before running, to estimate the model running time, we propose a sampling-then-simulation method which first estimates the output lengths by sampling from an empirical cumulative function we obtained from a large dataset in advance, and then simulates the LLM inference process accordingly. Based on the simulation, we estimate the per-iteration latencys to get the total latency. A greedy method is proposed to optimize the scheduling of the LLMs in the application across the GPUs. We then propose a framework SamuLLM which contains two phases: planning, which calls the greedy method for an application and running, which runs the application and dynamically adjust the model scheduling based on the runtime information. Experiments on 3 applications and a mixed application show that SamuLLM can achieve 1.0-2.4$\times$ end-to-end speedups compared to the competitors.
Authors: Wenjia Wang, Qingwen Zhang, Xiaowei Zhang
Abstract: Personalized services are central to today's digital landscape, where online decision-making is commonly formulated as contextual bandit problems. Two key challenges emerge in modern applications: high-dimensional covariates and the need for nonparametric models to capture complex reward-covariate relationships. We address these challenges by developing a contextual bandit algorithm based on sparse additive reward models in reproducing kernel Hilbert spaces. We establish statistical properties of the doubly penalized method applied to random regions, introducing novel analyses under bandit feedback. Our algorithm achieves sublinear cumulative regret over the time horizon $T$ while scaling logarithmically with covariate dimensionality $d$. Notably, we provide the first regret upper bound with logarithmic growth in $d$ for nonparametric contextual bandits with high-dimensional covariates. We also establish a lower bound, with the gap to the upper bound vanishing as smoothness increases. Extensive numerical experiments demonstrate our algorithm's superior performance in high-dimensional settings compared to existing approaches.
Authors: Muhammad Risha, Mohamed Elsaadany, Paul Liu
Abstract: Predicting microporosity and permeability in clastic reservoirs is a challenge in reservoir quality assessment, especially in formations where direct measurements are difficult or expensive. These reservoir properties are fundamental in determining a reservoir's capacity for fluid storage and transmission, yet conventional methods for evaluating them, such as Mercury Injection Capillary Pressure (MICP) and Scanning Electron Microscopy (SEM), are resource-intensive. The aim of this study is to develop a cost-effective machine learning model to predict complex reservoir properties using readily available field data and basic laboratory analyses. A Random Forest classifier was employed, utilizing key geological parameters such as porosity, grain size distribution, and spectral gamma-ray (SGR) measurements. An uncertainty analysis was applied to account for natural variability, expanding the dataset, and enhancing the model's robustness. The model achieved a high level of accuracy in predicting microporosity (93%) and permeability levels (88%). By using easily obtainable data, this model reduces the reliance on expensive laboratory methods, making it a valuable tool for early-stage exploration, especially in remote or offshore environments. The integration of machine learning with uncertainty analysis provides a reliable and cost-effective approach for evaluating key reservoir properties in siliciclastic formations. This model offers a practical solution to improve reservoir quality assessments, enabling more informed decision-making and optimizing exploration efforts.
Authors: Julian Junyan Wang, Victor Xiaoqi Wang
Abstract: This study provides the first comprehensive assessment of consistency and reproducibility in Large Language Model (LLM) outputs in finance and accounting research. We evaluate how consistently LLMs produce outputs given identical inputs through extensive experimentation with 50 independent runs across five common tasks: classification, sentiment analysis, summarization, text generation, and prediction. Using three OpenAI models (GPT-3.5-turbo, GPT-4o-mini, and GPT-4o), we generate over 3.4 million outputs from diverse financial source texts and data, covering MD&As, FOMC statements, finance news articles, earnings call transcripts, and financial statements. Our findings reveal substantial but task-dependent consistency, with binary classification and sentiment analysis achieving near-perfect reproducibility, while complex tasks show greater variability. More advanced models do not consistently demonstrate better consistency and reproducibility, with task-specific patterns emerging. LLMs significantly outperform expert human annotators in consistency and maintain high agreement even where human experts significantly disagree. We further find that simple aggregation strategies across 3-5 runs dramatically improve consistency. Simulation analysis reveals that despite measurable inconsistency in LLM outputs, downstream statistical inferences remain remarkably robust. These findings address concerns about what we term "G-hacking," the selective reporting of favorable outcomes from multiple Generative AI runs, by demonstrating that such risks are relatively low for finance and accounting tasks.
Authors: Haichao Zhang, Zhuowei Li, Dimitris Metaxas, Yun Fu
Abstract: Token-based video representation has emerged as a promising approach for enabling large language models to interpret video content. However, existing token reduction techniques, such as token pruning and token merging, often disrupt essential spatial-temporal positional embeddings, failing to adequately balance computational efficiency with fewer tokens. Consequently, these methods result in relatively lengthy token sequences, limiting their applicability in scenarios requiring extreme token compression, such as video large language models. In this paper, we introduce the novel task of extreme short token reduction, aiming to represent extensive video sequences with a minimal number of tokens. To address this challenge, we propose Token Dynamics, a new video representation framework that dynamically reduces token count while preserving spatial-temporal coherence. Specifically, we disentangle video representations by separating visual embeddings from grid-level motion information, structuring them into: 1. a concise token base, created by clustering tokens that describe object-level content; 2. a token dynamics map, capturing detailed spatial-temporal motion patterns across grids. Furthermore, we introduce a cross-dynamics attention mechanism that integrates motion features into the token base without increasing token length, thereby maintaining compactness and spatial-temporal integrity. The experiments demonstrate a reduction of token count to merely 0.07% of the original tokens, with only a minor performance drop of 1.13%. Additionally, we propose two novel subtasks within extreme token reduction (fixed-length and adaptive-length compression), both effectively representing long token sequences for video-language tasks. Our method offers significantly lower theoretical complexity, fewer tokens, and enhanced throughput, thus providing an efficient solution for video LLMs.
Authors: Enrico Marzano, Giovanni Pagliarini, Riccardo Pasini, Guido Sciavicco, Ionel Eduard Stan
Abstract: The range of potential applications of acoustic analysis is wide. Classification of sounds, in particular, is a typical machine learning task that received a lot of attention in recent years. The most common approaches to sound classification are sub-symbolic, typically based on neural networks, and result in black-box models with high performances but very low transparency. In this work, we consider several audio tasks, namely, age and gender recognition, emotion classification, and respiratory disease diagnosis, and we approach them with a symbolic technique, that is, (modal) decision tree learning. We prove that such tasks can be solved using the same symbolic pipeline, that allows to extract simple rules with very high accuracy and low complexity. In principle, all such tasks could be associated to an autonomous conversation system, which could be useful in different contexts, such as an automatic reservation agent for an hospital or a clinic.
Authors: Joachim Tomasi, Sandrine Anthoine, Hachem Kadri
Abstract: Quantum kernels quantify similarity between data points by measuring the inner product between quantum states, computed through quantum circuit measurements. By embedding data into quantum systems, quantum kernel feature maps, that may be classically intractable to compute, could efficiently exploit high-dimensional Hilbert spaces to capture complex patterns. However, designing effective quantum feature maps remains a major challenge. Many quantum kernels, such as the fidelity kernel, suffer from exponential concentration, leading to near-identity kernel matrices that fail to capture meaningful data correlations and lead to overfitting and poor generalization. In this paper, we propose a novel strategy for constructing quantum kernels that achieve good generalization performance, drawing inspiration from benign overfitting in classical machine learning. Our approach introduces the concept of local-global quantum kernels, which combine two complementary components: a local quantum kernel based on measurements of small subsystems and a global quantum kernel derived from full-system measurements. Through numerical experiments, we demonstrate that local-global quantum kernels exhibit benign overfitting, supporting the effectiveness of our approach in enhancing quantum kernel methods.
Authors: Dongsheng Yang, Qianying Liu, Wataru Sato, Takashi Minato, Chaoran Liu, Shin'ya Nishida
Abstract: Automatic robotic facial expression generation is crucial for human-robot interaction, as handcrafted methods based on fixed joint configurations often yield rigid and unnatural behaviors. Although recent automated techniques reduce the need for manual tuning, they tend to fall short by not adequately bridging the gap between human preferences and model predictions-resulting in a deficiency of nuanced and realistic expressions due to limited degrees of freedom and insufficient perceptual integration. In this work, we propose a novel learning-to-rank framework that leverages human feedback to address this discrepancy and enhanced the expressiveness of robotic faces. Specifically, we conduct pairwise comparison annotations to collect human preference data and develop the Human Affective Pairwise Impressions (HAPI) model, a Siamese RankNet-based approach that refines expression evaluation. Results obtained via Bayesian Optimization and online expression survey on a 35-DOF android platform demonstrate that our approach produces significantly more realistic and socially resonant expressions of Anger, Happiness, and Surprise than those generated by baseline and expert-designed methods. This confirms that our framework effectively bridges the gap between human preferences and model predictions while robustly aligning robotic expression generation with human affective responses.
Authors: Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan, Muhammad Shafique
Abstract: Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a memory replay-based method to maintain the old knowledge. However, this technique relies on long timesteps and compression-decompression steps, thereby incurring significant latency and energy overheads, which are not suitable for tightly-constrained embedded AI systems (e.g., mobile agents/robotics). To address this, we propose Replay4NCL, a novel efficient memory replay-based methodology for enabling NCL in embedded AI systems. Specifically, Replay4NCL compresses the latent data (old knowledge), then replays them during the NCL training phase with small timesteps, to minimize the processing latency and energy consumption. To compensate the information loss from reduced spikes, we adjust the neuron threshold potential and learning rate settings. Experimental results on the class-incremental scenario with the Spiking Heidelberg Digits (SHD) dataset show that Replay4NCL can preserve old knowledge with Top-1 accuracy of 90.43% compared to 86.22% from the state-of-the-art, while effectively learning new tasks, achieving 4.88x latency speed-up, 20% latent memory saving, and 36.43% energy saving. These results highlight the potential of our Replay4NCL methodology to further advances NCL capabilities for embedded AI systems.
Authors: Robin Hesse, Do\u{g}ukan Ba\u{g}c{\i}, Bernt Schiele, Simone Schaub-Meyer, Stefan Roth
Abstract: Deep learning has become an essential part of computer vision, with deep neural networks (DNNs) excelling in predictive performance. However, they often fall short in other critical quality dimensions, such as robustness, calibration, or fairness. While existing studies have focused on a subset of these quality dimensions, none have explored a more general form of "well-behavedness" of DNNs. With this work, we address this gap by simultaneously studying nine different quality dimensions for image classification. Through a large-scale study, we provide a bird's-eye view by analyzing 326 backbone models and how different training paradigms and model architectures affect the quality dimensions. We reveal various new insights such that (i) vision-language models exhibit high fairness on ImageNet-1k classification and strong robustness against domain changes; (ii) self-supervised learning is an effective training paradigm to improve almost all considered quality dimensions; and (iii) the training dataset size is a major driver for most of the quality dimensions. We conclude our study by introducing the QUBA score (Quality Understanding Beyond Accuracy), a novel metric that ranks models across multiple dimensions of quality, enabling tailored recommendations based on specific user needs.
Authors: Th\'eo Bodrito, Olivier Flasseur, Julien Mairal, Jean Ponce, Maud Langlois, Anne-Marie Lagrange
Abstract: The search for exoplanets is an active field in astronomy, with direct imaging as one of the most challenging methods due to faint exoplanet signals buried within stronger residual starlight. Successful detection requires advanced image processing to separate the exoplanet signal from this nuisance component. This paper presents a novel statistical model that captures nuisance fluctuations using a multi-scale approach, leveraging problem symmetries and a joint spectral channel representation grounded in physical principles. Our model integrates into an interpretable, end-to-end learnable framework for simultaneous exoplanet detection and flux estimation. The proposed algorithm is evaluated against the state of the art using datasets from the SPHERE instrument operating at the Very Large Telescope (VLT). It significantly improves the precision-recall trade-off, notably on challenging datasets that are otherwise unusable by astronomers. The proposed approach is computationally efficient, robust to varying data quality, and well suited for large-scale observational surveys.
Authors: John Joon Young Chung, Vishakh Padmakumar, Melissa Roemmele, Yuqian Sun, Max Kreminski
Abstract: As creative writing tasks do not have singular correct answers, large language models (LLMs) trained to perform these tasks should be able to generate diverse valid outputs. However, LLM post-training often focuses on improving generation quality but neglects to facilitate output diversity. Hence, in creative writing generation, we investigate post-training approaches to promote both output diversity and quality. Our core idea is to include deviation -- the degree of difference between a training sample and all other samples with the same prompt -- in the training objective to facilitate learning from rare high-quality instances. By adopting our approach to direct preference optimization (DPO) and odds ratio preference optimization (ORPO), we demonstrate that we can promote the output diversity of trained models while minimally decreasing quality. Our best model with 8B parameters could achieve on-par diversity as a human-created dataset while having output quality similar to the best instruction-tuned models we examined, GPT-4o and DeepSeek-R1. We further validate our approaches with a human evaluation, an ablation, and a comparison to an existing diversification approach, DivPO.
Authors: Vinicius Hernandes, Thomas Spriggs, Saqar Khaleefah, Eliska Greplova
Abstract: Neural quantum states (NQS) have emerged as a powerful tool for approximating quantum wavefunctions using deep learning. While these models achieve remarkable accuracy, understanding how they encode physical information remains an open challenge. In this work, we introduce adiabatic fine-tuning, a scheme that trains NQS across a phase diagram, leading to strongly correlated weight representations across different models. This correlation in weight space enables the detection of phase transitions in quantum systems by analyzing the trained network weights alone. We validate our approach on the transverse field Ising model and the J1-J2 Heisenberg model, demonstrating that phase transitions manifest as distinct structures in weight space. Our results establish a connection between physical phase transitions and the geometry of neural network parameters, opening new directions for the interpretability of machine learning models in physics.
Authors: Ekaterina Dmitrieva, Maksim Kaledin
Abstract: Speech Enhancement techniques have become core technologies in mobile devices and voice software simplifying downstream speech tasks. Still, modern Deep Learning (DL) solutions often require high amount of computational resources what makes their usage on low-resource devices challenging. We present HiFi-Stream, an optimized version of recently published HiFi++ model. Our experiments demonstrate that HiFiStream saves most of the qualities of the original model despite its size and computational complexity: the lightest version has only around 490k parameters which is 3.5x reduction in comparison to the original HiFi++ making it one of the smallest and fastest models available. The model is evaluated in streaming setting where it demonstrates its superior performance in comparison to modern baselines.
Authors: Davide Berasi, Matteo Farina, Massimiliano Mancini, Elisa Ricci, Nicola Strisciuglio
Abstract: Vision-Language Models (VLMs) learn a shared feature space for text and images, enabling the comparison of inputs of different modalities. While prior works demonstrated that VLMs organize natural language representations into regular structures encoding composite meanings, it remains unclear if compositional patterns also emerge in the visual embedding space. In this work, we investigate compositionality in the image domain, where the analysis of compositional properties is challenged by noise and sparsity of visual data. We address these problems and propose a framework, called Geodesically Decomposable Embeddings (GDE), that approximates image representations with geometry-aware compositional structures in the latent space. We demonstrate that visual embeddings of pre-trained VLMs exhibit a compositional arrangement, and evaluate the effectiveness of this property in the tasks of compositional classification and group robustness. GDE achieves stronger performance in compositional classification compared to its counterpart method that assumes linear geometry of the latent space. Notably, it is particularly effective for group robustness, where we achieve higher results than task-specific solutions. Our results indicate that VLMs can automatically develop a human-like form of compositional reasoning in the visual domain, making their underlying processes more interpretable. Code is available at https://github.com/BerasiDavide/vlm_image_compositionality.
URLs: https://github.com/BerasiDavide/vlm_image_compositionality.
Authors: Alexandra Arzberger, Ramin Tavakoli Kolagari
Abstract: Light Detection and Ranging (LiDAR) is an essential sensor technology for autonomous driving as it can capture high-resolution 3D data. As 3D object detection systems (OD) can interpret such point cloud data, they play a key role in the driving decisions of autonomous vehicles. Consequently, such 3D OD must be robust against all types of perturbations and must therefore be extensively tested. One approach is the use of adversarial examples, which are small, sometimes sophisticated perturbations in the input data that change, i.e., falsify, the prediction of the OD. These perturbations are carefully designed based on the weaknesses of the OD. The robustness of the OD cannot be quantified with adversarial examples in general, because if the OD is vulnerable to a given attack, it is unclear whether this is due to the robustness of the OD or whether the attack algorithm produces particularly strong adversarial examples. The contribution of this work is Hi-ALPS -- Hierarchical Adversarial-example-based LiDAR Perturbation Level System, where higher robustness of the OD is required to withstand the perturbations as the perturbation levels increase. In doing so, the Hi-ALPS levels successively implement a heuristic followed by established adversarial example approaches. In a series of comprehensive experiments using Hi-ALPS, we quantify the robustness of six state-of-the-art 3D OD under different types of perturbations. The results of the experiments show that none of the OD is robust against all Hi-ALPS levels; an important factor for the ranking is that human observers can still correctly recognize the perturbed objects, as the respective perturbations are small. To increase the robustness of the OD, we discuss the applicability of state-of-the-art countermeasures. In addition, we derive further suggestions for countermeasures based on our experimental results.
Authors: Orkun Furat, Sabrina Weber, Johannes Schubert, Ren\'e Rekers, Maximilian Luczak, Erik Glatt, Andreas Wiegmann, J\"urgen Janek, Anja Bielefeld, Volker Schmidt
Abstract: This paper presents a computational method for generating virtual 3D morphologies of functional materials using low-parametric stochastic geometry models, i.e., digital twins, calibrated with 2D microscopy images. These digital twins allow systematic parameter variations to simulate various morphologies, that can be deployed for virtual materials testing by means of spatially resolved numerical simulations of macroscopic properties. Generative adversarial networks (GANs) have gained popularity for calibrating models to generate realistic 3D morphologies. However, GANs often comprise of numerous uninterpretable parameters make systematic variation of morphologies for virtual materials testing challenging. In contrast, low-parametric stochastic geometry models (e.g., based on Gaussian random fields) enable targeted variation but may struggle to mimic complex morphologies. Combining GANs with advanced stochastic geometry models (e.g., excursion sets of more general random fields) addresses these limitations, allowing model calibration solely from 2D image data. This approach is demonstrated by generating a digital twin of all-solid-state battery (ASSB) cathodes. Since the digital twins are parametric, they support systematic exploration of structural scenarios and their macroscopic properties. The proposed method facilitates simulation studies for optimizing 3D morphologies, benefiting not only ASSB cathodes but also other materials with similar structures.
Authors: Yongli Xiang, Ziming Hong, Lina Yao, Dadong Wang, Tongliang Liu
Abstract: Non-transferable learning (NTL) has been proposed to protect model intellectual property (IP) by creating a "non-transferable barrier" to restrict generalization from authorized to unauthorized domains. Recently, well-designed attack, which restores the unauthorized-domain performance by fine-tuning NTL models on few authorized samples, highlights the security risks of NTL-based applications. However, such attack requires modifying model weights, thus being invalid in the black-box scenario. This raises a critical question: can we trust the security of NTL models deployed as black-box systems? In this work, we reveal the first loophole of black-box NTL models by proposing a novel attack method (dubbed as JailNTL) to jailbreak the non-transferable barrier through test-time data disguising. The main idea of JailNTL is to disguise unauthorized data so it can be identified as authorized by the NTL model, thereby bypassing the non-transferable barrier without modifying the NTL model weights. Specifically, JailNTL encourages unauthorized-domain disguising in two levels, including: (i) data-intrinsic disguising (DID) for eliminating domain discrepancy and preserving class-related content at the input-level, and (ii) model-guided disguising (MGD) for mitigating output-level statistics difference of the NTL model. Empirically, when attacking state-of-the-art (SOTA) NTL models in the black-box scenario, JailNTL achieves an accuracy increase of up to 55.7% in the unauthorized domain by using only 1% authorized samples, largely exceeding existing SOTA white-box attacks.
Authors: Zilin Dai, Lehong Wang, Fangzhou Lin, Yidong Wang, Zhigang Li, Kazunori D Yamada, Ziming Zhang, Wang Lu
Abstract: Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for them to generalize to the target domain. Noisy data worsens this problem by causing further overfitting to the noise, meaning that existing methods often fail to tell the difference between true, invariant features and misleading, spurious ones. To tackle these issues, we introduce Anchor Alignment and Adaptive Weighting (A3W). This new algorithm uses sample reweighting guided by natural language processing (NLP) anchors to extract more representative features. In simple terms, A3W leverages semantic representations from natural language models as a source of domain-invariant prior knowledge. Additionally, it employs a weighted loss function that adjusts each sample's contribution based on its similarity to the corresponding NLP anchor. This adjustment makes the model more robust to noisy labels. Extensive experiments on standard benchmark datasets show that A3W consistently outperforms state-of-the-art domain generalization methods, offering significant improvements in both accuracy and robustness across different datasets and noise levels.
Authors: Giacomo Savazzi, Eugenio Lomurno, Cristian Sbrolli, Agnese Chiatti, Matteo Matteucci
Abstract: As machine learning models increase in scale and complexity, obtaining sufficient training data has become a critical bottleneck due to acquisition costs, privacy constraints, and data scarcity in specialised domains. While synthetic data generation has emerged as a promising alternative, a notable performance gap remains compared to models trained on real data, particularly as task complexity grows. Concurrently, Neuro-Symbolic methods, which combine neural networks' learning strengths with symbolic reasoning's structured representations, have demonstrated significant potential across various cognitive tasks. This paper explores the utility of Neuro-Symbolic conditioning for synthetic image dataset generation, focusing specifically on improving the performance of Scene Graph Generation models. The research investigates whether structured symbolic representations in the form of scene graphs can enhance synthetic data quality through explicit encoding of relational constraints. The results demonstrate that Neuro-Symbolic conditioning yields significant improvements of up to +2.59% in standard Recall metrics and +2.83% in No Graph Constraint Recall metrics when used for dataset augmentation. These findings establish that merging Neuro-Symbolic and generative approaches produces synthetic data with complementary structural information that enhances model performance when combined with real data, providing a novel approach to overcome data scarcity limitations even for complex visual reasoning tasks.
Authors: Jyothi Rikhab Chand, Mathews Jacob
Abstract: Current end-to-end (E2E) and plug-and-play (PnP) image reconstruction algorithms approximate the maximum a posteriori (MAP) estimate but cannot offer sampling from the posterior distribution, like diffusion models. By contrast, it is challenging for diffusion models to be trained in an E2E fashion. This paper introduces a Deep End-to-End Posterior ENergy (DEEPEN) framework, which enables MAP estimation as well as sampling. We learn the parameters of the posterior, which is the sum of the data consistency error and the negative log-prior distribution, using maximum likelihood optimization in an E2E fashion. The proposed approach does not require algorithm unrolling, and hence has a smaller computational and memory footprint than current E2E methods, while it does not require contraction constraints typically needed by current PnP methods. Our results demonstrate that DEEPEN offers improved performance than current E2E and PnP models in the MAP setting, while it also offers faster sampling compared to diffusion models. In addition, the learned energy-based model is observed to be more robust to changes in image acquisition settings.
Authors: Shuang Guo, Friedhelm Hamann, Guillermo Gallego
Abstract: Event cameras rely on motion to obtain information about scene appearance. In other words, for event cameras, motion and appearance are seen both or neither, which are encoded in the output event stream. Previous works consider recovering these two visual quantities as separate tasks, which does not fit with the nature of event cameras and neglects the inherent relations between both tasks. In this paper, we propose an unsupervised learning framework that jointly estimates optical flow (motion) and image intensity (appearance), with a single network. Starting from the event generation model, we newly derive the event-based photometric error as a function of optical flow and image intensity, which is further combined with the contrast maximization framework, yielding a comprehensive loss function that provides proper constraints for both flow and intensity estimation. Exhaustive experiments show that our model achieves state-of-the-art performance for both optical flow (achieves 20% and 25% improvement in EPE and AE respectively in the unsupervised learning category) and intensity estimation (produces competitive results with other baselines, particularly in high dynamic range scenarios). Last but not least, our model achieves shorter inference time than all the other optical flow models and many of the image reconstruction models, while they output only one quantity. Project page: https://github.com/tub-rip/e2fai
Authors: Disha Hegde, Jon Cockayne
Abstract: Solving multiple parametrised related systems is an essential component of many numerical tasks. Borrowing strength from the solved systems and learning will make this process faster. In this work, we propose a novel probabilistic linear solver over the parameter space. This leverages information from the solved linear systems in a regression setting to provide an efficient posterior mean and covariance. We advocate using this as companion regression model for the preconditioned conjugate gradient method, and discuss the favourable properties of the posterior mean and covariance as the initial guess and preconditioner. We also provide several design choices for this companion solver. Numerical experiments showcase the benefits of using our novel solver in a hyperparameter optimisation problem.
Authors: Xianghan Meng, Zhiyuan Huang, Wei He, Xianbiao Qi, Rong Xiao, Chun-Guang Li
Abstract: Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheless, the real-world data are often deviating from the UoS assumption. To address this challenge, state-of-the-art deep subspace clustering algorithms attempt to jointly learn UoS representations and self-expressive coefficients. However, the general framework of the existing algorithms suffers from a catastrophic feature collapse and lacks a theoretical guarantee to learn desired UoS representation. In this paper, we present a Principled fRamewOrk for Deep Subspace Clustering (PRO-DSC), which is designed to learn structured representations and self-expressive coefficients in a unified manner. Specifically, in PRO-DSC, we incorporate an effective regularization on the learned representations into the self-expressive model, prove that the regularized self-expressive model is able to prevent feature space collapse, and demonstrate that the learned optimal representations under certain condition lie on a union of orthogonal subspaces. Moreover, we provide a scalable and efficient approach to implement our PRO-DSC and conduct extensive experiments to verify our theoretical findings and demonstrate the superior performance of our proposed deep subspace clustering approach. The code is available at https://github.com/mengxianghan123/PRO-DSC.
Authors: Jan Rabenseifner, Sven Klaassen, Jannis Kueck, Philipp Bach
Abstract: The partitioning of data for estimation and calibration critically impacts the performance of propensity score based estimators like inverse probability weighting (IPW) and double/debiased machine learning (DML) frameworks. We extend recent advances in calibration techniques for propensity score estimation, improving the robustness of propensity scores in challenging settings such as limited overlap, small sample sizes, or unbalanced data. Our contributions are twofold: First, we provide a theoretical analysis of the properties of calibrated estimators in the context of DML. To this end, we refine existing calibration frameworks for propensity score models, with a particular emphasis on the role of sample-splitting schemes in ensuring valid causal inference. Second, through extensive simulations, we show that calibration reduces variance of inverse-based propensity score estimators while also mitigating bias in IPW, even in small-sample regimes. Notably, calibration improves stability for flexible learners (e.g., gradient boosting) while preserving the doubly robust properties of DML. A key insight is that, even when methods perform well without calibration, incorporating a calibration step does not degrade performance, provided that an appropriate sample-splitting approach is chosen.
Authors: Xiaoyu Sun (Aix-Marseille Universit\'e, CNRS, LIS, Marseille, France), Mathieu Roget (Aix-Marseille Universit\'e, CNRS, LIS, Marseille, France), Giuseppe Di Molfetta (Aix-Marseille Universit\'e, CNRS, LIS, Marseille, France), Hachem Kadri (Aix-Marseille Universit\'e, CNRS, LIS, Marseille, France)
Abstract: With the growing interest in quantum machine learning, the perceptron -- a fundamental building block in traditional machine learning -- has emerged as a valuable model for exploring quantum advantages. Two quantum perceptron algorithms based on Grover's search, were developed in arXiv:1602.04799 to accelerate training and improve statistical efficiency in perceptron learning. This paper points out and corrects a mistake in the proof of Theorem 2 in arXiv:1602.04799. Specifically, we show that the probability of sampling from a normal distribution for a $D$-dimensional hyperplane that perfectly classifies the data scales as $\Omega(\gamma^{D})$ instead of $\Theta({\gamma})$, where $\gamma$ is the margin. We then revisit two well-established linear programming algorithms -- the ellipsoid method and the cutting plane random walk algorithm -- in the context of perceptron learning, and show how quantum search algorithms can be leveraged to enhance the overall complexity. Specifically, both algorithms gain a sub-linear speed-up $O(\sqrt{N})$ in the number of data points $N$ as a result of Grover's algorithm and an additional $O(D^{1.5})$ speed-up is possible for cutting plane random walk algorithm employing quantum walk search.
Authors: Andr\'e Barreto, Vincent Dumoulin, Yiran Mao, Nicolas Perez-Nieves, Bobak Shahriari, Yann Dauphin, Doina Precup, Hugo Larochelle
Abstract: Reinforcement learning from human feedback usually models preferences using a reward model that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for disagreement, like in the training of large language models. We propose a method to specialise a reward model to a person or group of people. Our approach builds on the observation that individual preferences can be captured as a linear combination of a set of general reward features. We show how to learn such features and subsequently use them to quickly adapt the reward model to a specific individual, even if their preferences are not reflected in the training data. We present experiments with large language models comparing the proposed architecture with a non-adaptive reward model and also adaptive counterparts, including models that do in-context personalisation. Depending on how much disagreement there is in the training data, our model either significantly outperforms the baselines or matches their performance with a simpler architecture and more stable training.
Authors: Haoming Wang, Lek-Heng Lim
Abstract: We extend the celebrated Glivenko-Cantelli theorem, sometimes called the fundamental theorem of statistics, from its standard setting of total variation distance to all $f$-divergences. A key obstacle in this endeavor is to define $f$-divergence on a subcollection of a $\sigma$-algebra that forms a $\pi$-system but not a $\sigma$-subalgebra. This is a side contribution of our work. We will show that this notion of $f$-divergence on the $\pi$-system of rays preserves nearly all known properties of standard $f$-divergence, yields a novel integral representation of the Kolmogorov-Smirnov distance, and has a Glivenko-Cantelli theorem.
Authors: Hiroyasu Tsukamoto, Soon-Jo Chung, Jean-Jacques E. Slotine
Abstract: Contraction theory is an analytical tool to study differential dynamics of a non-autonomous (i.e., time-varying) nonlinear system under a contraction metric defined with a uniformly positive definite matrix, the existence of which results in a necessary and sufficient characterization of incremental exponential stability of multiple solution trajectories with respect to each other. By using a squared differential length as a Lyapunov-like function, its nonlinear stability analysis boils down to finding a suitable contraction metric that satisfies a stability condition expressed as a linear matrix inequality, indicating that many parallels can be drawn between well-known linear systems theory and contraction theory for nonlinear systems. Furthermore, contraction theory takes advantage of a superior robustness property of exponential stability used in conjunction with the comparison lemma. This yields much-needed safety and stability guarantees for neural network-based control and estimation schemes, without resorting to a more involved method of using uniform asymptotic stability for input-to-state stability. Such distinctive features permit the systematic construction of a contraction metric via convex optimization, thereby obtaining an explicit exponential bound on the distance between a time-varying target trajectory and solution trajectories perturbed externally due to disturbances and learning errors. The objective of this paper is, therefore, to present a tutorial overview of contraction theory and its advantages in nonlinear stability analysis of deterministic and stochastic systems, with an emphasis on deriving formal robustness and stability guarantees for various learning-based and data-driven automatic control methods. In particular, we provide a detailed review of techniques for finding contraction metrics and associated control and estimation laws using deep neural networks.
Authors: Jose J. Valero-Mas, Antonio Javier Gallego, Pablo Alonso-Jim\'enez, Xavier Serra
Abstract: Prototype Generation (PG) methods are typically considered for improving the efficiency of the $k$-Nearest Neighbour ($k$NN) classifier when tackling high-size corpora. Such approaches aim at generating a reduced version of the corpus without decreasing the classification performance when compared to the initial set. Despite their large application in multiclass scenarios, very few works have addressed the proposal of PG methods for the multilabel space. In this regard, this work presents the novel adaptation of four multiclass PG strategies to the multilabel case. These proposals are evaluated with three multilabel $k$NN-based classifiers, 12 corpora comprising a varied range of domains and corpus sizes, and different noise scenarios artificially induced in the data. The results obtained show that the proposed adaptations are capable of significantly improving -- both in terms of efficiency and classification performance -- the only reference multilabel PG work in the literature as well as the case in which no PG method is applied, also presenting a statistically superior robustness in noisy scenarios. Moreover, these novel PG strategies allow prioritising either the efficiency or efficacy criteria through its configuration depending on the target scenario, hence covering a wide area in the solution space not previously filled by other works.
Authors: Branton DeMoss, Paul Duckworth, Jakob Foerster, Nick Hawes, Ingmar Posner
Abstract: For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which addresses all three of these problems. DITTO optimizes a novel distance metric in the latent space of a learned world model: First, we train a world model on all available trajectory data, then, the imitation agent is unrolled from expert start states in the learned model, and penalized for its latent divergence from the expert dataset over multiple time steps. We optimize this multi-step latent divergence using standard reinforcement learning algorithms, which provably induces imitation learning, and empirically achieves state-of-the art performance and sample efficiency on a range of Atari environments from pixels, without any online environment access. We also adapt other standard imitation learning algorithms to the world model setting, and show that this considerably improves their performance. Our results show how creative use of world models can lead to a simple, robust, and highly-performant policy-learning framework.
Authors: Jinyi Liu, Yi Ma, Jianye Hao, Yujing Hu, Yan Zheng, Tangjie Lv, Changjie Fan
Abstract: In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has been overlooked despite its potential to enhance online RL performance. Recent research suggests applying sampling techniques directly to state-transitions does not consistently improve performance in offline RL. Therefore, in this study, we propose a memory technique, (Prioritized) Trajectory Replay (TR/PTR), which extends the sampling perspective to trajectories for more comprehensive information extraction from limited data. TR enhances learning efficiency by backward sampling of trajectories that optimizes the use of subsequent state information. Building on TR, we build the weighted critic target to avoid sampling unseen actions in offline training, and Prioritized Trajectory Replay (PTR) that enables more efficient trajectory sampling, prioritized by various trajectory priority metrics. We demonstrate the benefits of integrating TR and PTR with existing offline RL algorithms on D4RL. In summary, our research emphasizes the significance of trajectory-based data sampling techniques in enhancing the efficiency and performance of offline RL algorithms.
Authors: Huili Cai, Xiang Zhang, Xiaofeng Liu
Abstract: Time series classification is a critical task in various domains, such as finance, healthcare, and sensor data analysis. Unsupervised contrastive learning has garnered significant interest in learning effective representations from time series data with limited labels. The prevalent approach in existing contrastive learning methods consists of two separate stages: pre-training the encoder on unlabeled datasets and fine-tuning the well-trained model on a small-scale labeled dataset. However, such two-stage approaches suffer from several shortcomings, such as the inability of unsupervised pre-training contrastive loss to directly affect downstream fine-tuning classifiers, and the lack of exploiting the classification loss which is guided by valuable ground truth. In this paper, we propose an end-to-end model called SLOTS (Semi-supervised Learning fOr Time clasSification). SLOTS receives semi-labeled datasets, comprising a large number of unlabeled samples and a small proportion of labeled samples, and maps them to an embedding space through an encoder. We calculate not only the unsupervised contrastive loss but also measure the supervised contrastive loss on the samples with ground truth. The learned embeddings are fed into a classifier, and the classification loss is calculated using the available true labels. The unsupervised, supervised contrastive losses and classification loss are jointly used to optimize the encoder and classifier. We evaluate SLOTS by comparing it with ten state-of-the-art methods across five datasets. The results demonstrate that SLOTS is a simple yet effective framework. When compared to the two-stage framework, our end-to-end SLOTS utilizes the same input data, consumes a similar computational cost, but delivers significantly improved performance. We release code and datasets at https://anonymous.4open.science/r/SLOTS-242E.
Authors: Tyler Ingebrand, Amy Zhang, Ufuk Topcu
Abstract: Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current task so that the agent understands how it relates to previously seen tasks. To achieve zero-shot transfer, we introduce the function encoder, a representation learning algorithm which represents a function as a weighted combination of learned, non-linear basis functions. By using a function encoder to represent the reward function or the transition function, the agent has information on how the current task relates to previously seen tasks via a coherent vector representation. Thus, the agent is able to achieve transfer between related tasks at run time with no additional training. We demonstrate state-of-the-art data efficiency, asymptotic performance, and training stability in three RL fields by augmenting basic RL algorithms with a function encoder task representation.
Authors: Laura Manduchi, Kushagra Pandey, Clara Meister, Robert Bamler, Ryan Cotterell, Sina D\"aubener, Sophie Fellenz, Asja Fischer, Thomas G\"artner, Matthias Kirchler, Marius Kloft, Yingzhen Li, Christoph Lippert, Gerard de Melo, Eric Nalisnick, Bj\"orn Ommer, Rajesh Ranganath, Maja Rudolph, Karen Ullrich, Guy Van den Broeck, Julia E Vogt, Yixin Wang, Florian Wenzel, Frank Wood, Stephan Mandt, Vincent Fortuin
Abstract: The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervised learning paradigms, recent large-scale generative models show tremendous promise in synthesizing high-resolution images and text, as well as structured data such as videos and molecules. However, we argue that current large-scale generative AI models exhibit several fundamental shortcomings that hinder their widespread adoption across domains. In this work, our objective is to identify these issues and highlight key unresolved challenges in modern generative AI paradigms that should be addressed to further enhance their capabilities, versatility, and reliability. By identifying these challenges, we aim to provide researchers with insights for exploring fruitful research directions, thus fostering the development of more robust and accessible generative AI solutions.
Authors: Luca Arrotta, Claudio Bettini, Gabriele Civitarese, Michele Fiori
Abstract: Context-aware Human Activity Recognition (HAR) is a hot research area in mobile computing, and the most effective solutions in the literature are based on supervised deep learning models. However, the actual deployment of these systems is limited by the scarcity of labeled data that is required for training. Neuro-Symbolic AI (NeSy) provides an interesting research direction to mitigate this issue, by infusing common-sense knowledge about human activities and the contexts in which they can be performed into HAR deep learning classifiers. Existing NeSy methods for context-aware HAR rely on knowledge encoded in logic-based models (e.g., ontologies) whose design, implementation, and maintenance to capture new activities and contexts require significant human engineering efforts, technical knowledge, and domain expertise. Recent works show that pre-trained Large Language Models (LLMs) effectively encode common-sense knowledge about human activities. In this work, we propose ContextGPT: a novel prompt engineering approach to retrieve from LLMs common-sense knowledge about the relationship between human activities and the context in which they are performed. Unlike ontologies, ContextGPT requires limited human effort and expertise. An extensive evaluation carried out on two public datasets shows how a NeSy model obtained by infusing common-sense knowledge from ContextGPT is effective in data scarcity scenarios, leading to similar (and sometimes better) recognition rates than logic-based approaches with a fraction of the effort.
Authors: Constantin-Daniel Nicolae, Sara Sameer, Nathan Sun, Karena Yan
Abstract: Accurately measuring the cycle lifetime of commercial lithium-ion batteries is crucial for performance and technology development. We introduce a novel hybrid approach combining a physics-based equation with a self-attention model to predict the cycle lifetimes of commercial lithium iron phosphate graphite cells via early-cycle data. After fitting capacity loss curves to this physics-based equation, we then use a self-attention layer to reconstruct entire battery capacity loss curves. Our model exhibits comparable performances to existing models while predicting more information: the entire capacity loss curve instead of cycle life. This provides more robustness and interpretability: our model does not need to be retrained for a different notion of end-of-life and is backed by physical intuition.
Authors: Antonios Valkanas, Boris N. Oreshkin, Mark Coates
Abstract: Online deep learning tackles the challenge of learning from data streams by balancing two competing goals: fast learning and deep learning. However, existing research primarily emphasizes deep learning solutions, which are more adept at handling the ``deep'' aspect than the ``fast'' aspect of online learning. In this work, we introduce an alternative paradigm through a hybrid multilearner approach. We begin by developing a fast online logistic regression learner, which operates without relying on backpropagation. It leverages closed-form recursive updates of model parameters, efficiently addressing the fast learning component of the online learning challenge. This approach is further integrated with a cascaded multilearner design, where shallow and deep learners are co-trained in a cooperative, synergistic manner to solve the online learning problem. We demonstrate that this approach achieves state-of-the-art performance on standard online learning datasets. We make our code available: https://github.com/AntonValk/MODL
Authors: Can Pouliquen, Mathurin Massias, Titouan Vayer
Abstract: Estimating matrices in the symmetric positive-definite (SPD) cone is of interest for many applications ranging from computer vision to graph learning. While there exist various convex optimization-based estimators, they remain limited in expressivity due to their model-based approach. The success of deep learning motivates the use of learning-based approaches to estimate SPD matrices with neural networks in a data-driven fashion. However, designing effective neural architectures for SPD learning is challenging, particularly when the task requires additional structural constraints, such as element-wise sparsity. Current approaches either do not ensure that the output meets all desired properties or lack expressivity. In this paper, we introduce SpodNet, a novel and generic learning module that guarantees SPD outputs and supports additional structural constraints. Notably, it solves the challenging task of learning jointly SPD and sparse matrices. Our experiments illustrate the versatility and relevance of SpodNet layers for such applications.
Authors: Kazumi Kasaura
Abstract: To find the shortest paths for all pairs on manifolds with infinitesimally defined metrics, we introduce a framework to generate them by predicting midpoints recursively. To learn midpoint prediction, we propose an actor-critic approach. We prove the soundness of our approach and show experimentally that the proposed method outperforms existing methods on several planning tasks, including path planning for agents with complex kinematics and motion planning for multi-degree-of-freedom robot arms.
Authors: Yuxiang Wei, Anees Abrol, Vince Calhoun
Abstract: Recent advances in deep learning structured state space models, especially the Mamba architecture, have demonstrated remarkable performance improvements while maintaining linear complexity. In this study, we introduce functional spatiotemporal Mamba (FST-Mamba), a Mamba-based model designed for discovering neurological biomarkers using functional magnetic resonance imaging (fMRI). We focus on dynamic functional network connectivity (dFNC) derived from fMRI and propose a hierarchical spatiotemporal Mamba-based network that processes spatial and temporal information separately using Mamba-based encoders. Leveraging the topological uniqueness of the FNC matrix, we introduce a component-wise varied-scale aggregation (CVA) mechanism to aggregate connectivity across individual components within brain networks, enabling the model to capture component-level and network-level information. Additionally, we propose symmetric rotary position encoding (SymRope) to encode the relative positions of each functional connection while considering the symmetric nature of the FNC matrix. Experimental results demonstrate significant improvements in the proposed FST-Mamba model on various brain-based classification and regression tasks. We further show brain connectivities and dynamics that are crucial for the prediction. Our work reveals the substantial potential of attention-free sequence modeling in brain discovery. The codes are publicly available here: https://github.com/yuxiangwei0808/FunctionalMamba/tree/main.
URLs: https://github.com/yuxiangwei0808/FunctionalMamba/tree/main.
Authors: Pengxin Guo, Shuang Zeng, Yanran Wang, Huijie Fan, Feifei Wang, Liangqiong Qu
Abstract: We investigate LoRA in federated learning through the lens of the asymmetry analysis of the learned $A$ and $B$ matrices. In doing so, we uncover that $A$ matrices are responsible for learning general knowledge, while $B$ matrices focus on capturing client-specific knowledge. Based on this finding, we introduce Federated Share-A Low-Rank Adaptation (FedSA-LoRA), which employs two low-rank trainable matrices $A$ and $B$ to model the weight update, but only $A$ matrices are shared with the server for aggregation. Moreover, we delve into the relationship between the learned $A$ and $B$ matrices in other LoRA variants, such as rsLoRA and VeRA, revealing a consistent pattern. Consequently, we extend our FedSA-LoRA method to these LoRA variants, resulting in FedSA-rsLoRA and FedSA-VeRA. In this way, we establish a general paradigm for integrating LoRA with FL, offering guidance for future work on subsequent LoRA variants combined with FL. Extensive experimental results on natural language understanding and generation tasks demonstrate the effectiveness of the proposed method. Our code is available at https://github.com/Pengxin-Guo/FedSA-LoRA.
Authors: Aleksandar Armacki, Shuhua Yu, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar
Abstract: We study high-probability convergence in online learning, in the presence of heavy-tailed noise. To combat the heavy tails, a general framework of nonlinear SGD methods is considered, subsuming several popular nonlinearities like sign, quantization, component-wise and joint clipping. In our work the nonlinearity is treated in a black-box manner, allowing us to establish unified guarantees for a broad range of nonlinear methods. For symmetric noise and non-convex costs we establish convergence of gradient norm-squared, at a rate $\widetilde{\mathcal{O}}(t^{-1/4})$, while for the last iterate of strongly convex costs we establish convergence to the population optima, at a rate $\mathcal{O}(t^{-\zeta})$, where $\zeta \in (0,1)$ depends on noise and problem parameters. Further, if the noise is a (biased) mixture of symmetric and non-symmetric components, we show convergence to a neighbourhood of stationarity, whose size depends on the mixture coefficient, nonlinearity and noise. Compared to state-of-the-art, who only consider clipping and require unbiased noise with bounded $p$-th moments, $p \in (1,2]$, we provide guarantees for a broad class of nonlinearities, without any assumptions on noise moments. While the rate exponents in state-of-the-art depend on noise moments and vanish as $p \rightarrow 1$, our exponents are constant and strictly better whenever $p < 6/5$ for non-convex and $p < 8/7$ for strongly convex costs. Experiments validate our theory, showing that clipping is not always the optimal nonlinearity, further underlining the value of a general framework.
Authors: Addison Kristanto Julistiono, Davoud Ataee Tarzanagh, Navid Azizan
Abstract: Attention mechanisms have revolutionized several domains of artificial intelligence, such as natural language processing and computer vision, by enabling models to selectively focus on relevant parts of the input data. While recent work has characterized the optimization dynamics of gradient descent (GD) in attention-based models and the structural properties of its preferred solutions, less is known about more general optimization algorithms such as mirror descent (MD). In this paper, we investigate the convergence properties and implicit biases of a family of MD algorithms tailored for softmax attention mechanisms, with the potential function chosen as the $p$-th power of the $\ell_p$-norm. Specifically, we show that these algorithms converge in direction to a generalized hard-margin SVM with an $\ell_p$-norm objective when applied to a classification problem using a softmax attention model. Notably, our theoretical results reveal that the convergence rate is comparable to that of traditional GD in simpler models, despite the highly nonlinear and nonconvex nature of the present problem. Additionally, we delve into the joint optimization dynamics of the key-query matrix and the decoder, establishing conditions under which this complex joint optimization converges to their respective hard-margin SVM solutions. Lastly, our numerical experiments on real data demonstrate that MD algorithms improve generalization over standard GD and excel in optimal token selection.
Authors: Guanglin Niu
Abstract: Knowledge Graph Embedding (KGE) techniques play a pivotal role in transforming symbolic Knowledge Graphs (KGs) into numerical representations, thereby enhancing various deep learning models for knowledge-augmented applications. Unlike entities, relations in KGs are the carriers of semantic meaning, and their accurate modeling is crucial for the performance of KGE models. Firstly, we address the complex mapping properties inherent in relations, such as one-to-one, one-to-many, many-to-one, and many-to-many mappings. We provide a comprehensive summary of relation-aware mapping-based models, models that utilize specific representation spaces, tensor decomposition-based models, and neural network-based models. Next, focusing on capturing various relation patterns like symmetry, asymmetry, inversion, and composition, we review models that employ modified tensor decomposition, those based on modified relation-aware mappings, and those that leverage rotation operations. Subsequently, considering the implicit hierarchical relations among entities, we introduce models that incorporate auxiliary information, models based on hyperbolic spaces, and those that utilize the polar coordinate system. Finally, in response to more complex scenarios such as sparse and dynamic KGs, this paper discusses potential future research directions. We explore innovative ideas such as integrating multimodal information into KGE, enhancing relation pattern modeling with rules, and developing models to capture relation characteristics in dynamic KGE settings.
Authors: Jinxu Lin, Linwei Tao, Minjing Dong, Chang Xu
Abstract: As diffusion models become increasingly popular, the misuse of copyrighted and private images has emerged as a major concern. One promising solution to mitigate this issue is identifying the contribution of specific training samples in generative models, a process known as data attribution. Existing data attribution methods for diffusion models typically quantify the contribution of a training sample by evaluating the change in diffusion loss when the sample is included or excluded from the training process. However, we argue that the direct usage of diffusion loss cannot represent such a contribution accurately due to the calculation of diffusion loss. Specifically, these approaches measure the divergence between predicted and ground truth distributions, which leads to an indirect comparison between the predicted distributions and cannot represent the variances between model behaviors. To address these issues, we aim to measure the direct comparison between predicted distributions with an attribution score to analyse the training sample importance, which is achieved by Diffusion Attribution Score (\textit{DAS}). Underpinned by rigorous theoretical analysis, we elucidate the effectiveness of DAS. Additionally, we explore strategies to accelerate DAS calculations, facilitating its application to large-scale diffusion models. Our extensive experiments across various datasets and diffusion models demonstrate that DAS significantly surpasses previous benchmarks in terms of the linear data-modelling score, establishing new state-of-the-art performance. Code is available at \hyperlink{here}{https://github.com/Jinxu-Lin/DAS}.
Authors: Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen, Junhong Shen, Ameet Talwalkar, Mikhail Khodak
Abstract: Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and beyond. Has this achieved what the original FMs accomplished, i.e. the supplanting of traditional supervised learning in their domains? To answer we look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow: model development, hyperparameter tuning, and training, all using only data from the target task. Across these three specialized domains, we find that it is consistently possible to train simple supervised models -- no more complicated than a lightly modified wide ResNet or UNet -- that match or even outperform the latest foundation models. Our work demonstrates that the benefits of large-scale pretraining have yet to be realized in many specialized areas, reinforces the need to compare new FMs to strong, well-tuned baselines, and introduces two new, easy-to-use, open-source, and automated workflows for doing so.
Authors: Jongseon Kim, Hyungjoon Kim, HyunGi Kim, Dongjun Lee, Sungroh Yoon
Abstract: Time series forecasting is a critical task that provides key information for decision-making across various fields. Recently, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed and applied to solve time series forecasting problems. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series forecasting. However, recent research has shown that alternatives such as simple linear layers can outperform Transformers. These findings have opened up new possibilities for using diverse architectures. In this context of exploration into various models, the architectural modeling of time series forecasting has now entered a renaissance. This survey not only provides a historical context for time series forecasting but also offers comprehensive and timely analysis of the movement toward architectural diversification. By comparing and re-examining various deep learning models, we uncover new perspectives and presents the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models. By focusing on the inherent characteristics of time series data, we also address open challenges that have gained attention in time series forecasting, such as channel dependency, distribution shift, causality, and feature extraction. This survey explores vital elements that can enhance forecasting performance through diverse approaches. These contributions lead to lowering the entry barriers for newcomers to the field of time series forecasting, while also offering seasoned researchers broad perspectives, new opportunities, and deep insights.
Authors: Fengyuan Liu, Nikhil Kandpal, Colin Raffel
Abstract: The influence of contextual input on the behavior of large language models (LLMs) has prompted the development of context attribution methods that aim to quantify each context span's effect on an LLM's generations. The leave-one-out (LOO) error, which measures the change in the likelihood of the LLM's response when a given span of the context is removed, provides a principled way to perform context attribution, but can be prohibitively expensive to compute for large models. In this work, we introduce AttriBoT, a series of novel techniques for efficiently computing an approximation of the LOO error for context attribution. Specifically, AttriBoT uses cached activations to avoid redundant operations, performs hierarchical attribution to reduce computation, and emulates the behavior of large target models with smaller proxy models. Taken together, AttriBoT can provide a >300x speedup while remaining more faithful to a target model's LOO error than prior context attribution methods. This stark increase in performance makes computing context attributions for a given response 30x faster than generating the response itself, empowering real-world applications that require computing attributions at scale. We release a user-friendly and efficient implementation of AttriBoT to enable efficient LLM interpretability as well as encourage future development of efficient context attribution methods.
Authors: Seokil Ham, Hee-Seon Kim, Sangmin Woo, Changick Kim
Abstract: Despite the growing interest in Mamba architecture as a potential replacement for Transformer architecture, parameter-efficient fine-tuning (PEFT) approaches for Mamba remain largely unexplored. In our study, we introduce two key insights-driven strategies for PEFT in Mamba architecture: (1) While state-space models (SSMs) have been regarded as the cornerstone of Mamba architecture, then expected to play a primary role in transfer learning, our findings reveal that Projectors -- not SSMs -- are the predominant contributors to transfer learning. (2) Based on our observation, we propose a novel PEFT method specialized to Mamba architecture: Projector-targeted Diagonal-centric Linear Transformation (ProDiaL). ProDiaL focuses on optimizing only the pretrained Projectors for new tasks through diagonal-centric linear transformation matrices, without directly fine-tuning the Projector weights. This targeted approach allows efficient task adaptation, utilizing less than 1% of the total parameters, and exhibits strong performance across both vision and language Mamba models, highlighting its versatility and effectiveness.
Authors: Sumanth Kumar Boya, Deepak Subramani
Abstract: Initial boundary value problems arise commonly in applications with engineering and natural systems governed by nonlinear partial differential equations (PDEs). Operator learning is an emerging field for solving these equations by using a neural network to learn a map between infinite dimensional input and output function spaces. These neural operators are trained using a combination of data (observations or simulations) and PDE-residuals (physics-loss). A major drawback of existing neural approaches is the requirement to retrain with new initial/boundary conditions, and the necessity for a large amount of simulation data for training. We develop a physics-informed transformer neural operator (named PINTO) that efficiently generalizes to unseen initial and boundary conditions, trained in a simulation-free setting using only physics loss. The main innovation lies in our new iterative kernel integral operator units, implemented using cross-attention, to transform the PDE solution's domain points into an initial/boundary condition-aware representation vector, enabling efficient learning of the solution function for new scenarios. The PINTO architecture is applied to simulate the solutions of important equations used in engineering applications: advection, Burgers, and steady and unsteady Navier-Stokes equations (three flow scenarios). For these five test cases, we show that the relative errors during testing under challenging conditions of unseen initial/boundary conditions are only one-fifth to one-third of other leading physics informed operator learning methods. Moreover, our PINTO model is able to accurately solve the advection and Burgers equations at time steps that are not included in the training collocation points. The code is available at https://github.com/quest-lab-iisc/PINTO
Authors: Yusuke Sakemi, Yuji Okamoto, Takashi Morie, Sou Nobukawa, Takeo Hosomi, Kazuyuki Aihara
Abstract: Large-scale deep learning models are increasingly constrained by their immense energy consumption, limiting their scalability and applicability for edge intelligence. In-memory computing (IMC) offers a promising solution by addressing the von Neumann bottleneck inherent in traditional deep learning accelerators, significantly reducing energy consumption. However, the analog nature of IMC introduces hardware nonidealities that degrade model performance and reliability. This paper presents a novel approach to directly train physical models of IMC, formulated as ordinary-differential-equation (ODE)-based physical neural networks (PNNs). To enable the training of large-scale networks, we propose a technique called differentiable spike-time discretization (DSTD), which reduces the computational cost of ODE-based PNNs by up to 20 times in speed and 100 times in memory. We demonstrate that such large-scale networks enhance the learning performance by exploiting hardware nonidealities on the CIFAR-10 dataset. The proposed bottom-up methodology is validated through the post-layout SPICE simulations on the IMC circuit with nonideal characteristics using the sky130 process. The proposed PNN approach reduces the discrepancy between the model behavior and circuit dynamics by at least an order of magnitude. This work paves the way for leveraging nonideal physical devices, such as non-volatile resistive memories, for energy-efficient deep learning applications.
Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Yanyu Li, Yifan Gong, Kai Zhang, Hao Tan, Jason Kuen, Henghui Ding, Zhihao Shu, Wei Niu, Pu Zhao, Yanzhi Wang, Jiuxiang Gu
Abstract: Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the \textbf{LazyDiT}, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency. Code: https://github.com/shawnricecake/lazydit
Authors: Malihehsadat Chavooshi, Alexander V. Mamonov
Abstract: We propose a novel approach to unsupervised learning by constructing a non-linear embedding of the data into a low-dimensional space followed by any conventional clustering algorithm. The embedding promotes clusterability of the data and is comprised of two mappings: the encoder of an autoencoder neural network and the output of UMAP algorithm. The autoencoder is trained with a composite loss function that incorporates both a conventional data reconstruction as a regularization component and a clustering-promoting component built using the spectral graph theory. The two embeddings and the subsequent clustering are integrated into a three-stage unsupervised learning framework, referred to as Autoencoded UMAP-Enhanced Clustering (AUEC). When applied to MNIST data, AUEC significantly outperforms the state-of-the-art techniques in terms of clustering accuracy.
Authors: Kefan Dong, Tengyu Ma
Abstract: A fundamental challenge in formal theorem proving by LLMs is the lack of high-quality training data. Although reinforcement learning or expert iteration partially mitigates this issue by alternating between LLM generating proofs and finetuning them on correctly generated ones, performance quickly plateaus due to the scarcity of correct proofs (sparse rewards). To keep improving the models with limited data, we draw inspiration from mathematicians, who continuously develop new results, partly by proposing novel conjectures or exercises (which are often variants of known results) and attempting to solve them. We design the Self-play Theorem Prover (STP) that simultaneously takes on two roles, conjecturer and prover, each providing training signals to the other. The conjecturer is trained iteratively on previously generated conjectures that are barely provable by the current prover, which incentivizes it to generate increasingly challenging conjectures over time. The prover attempts to prove the conjectures with standard expert iteration. We evaluate STP with both Lean and Isabelle formal versifiers. With 51.3 billion tokens generated during the training in Lean, STP proves 28.5% of the statements in the LeanWorkbook dataset, doubling the previous best result of 13.2% achieved through expert iteration. The final model achieves state-of-the-art performance among whole-proof generation methods on miniF2F-test (65.0%, pass@3200), Proofnet-test (23.9%, pass@3200) and PutnamBench (8/644, pass@3200). We release our code, model, and dataset in this URL: https://github.com/kfdong/STP.
Authors: Liang Wendong, Simon Buchholz, Bernhard Sch\"olkopf
Abstract: We explore the relationship between causality, symmetry, and compression. We build on and generalize the known connection between learning and compression to a setting where causal models are not identifiable. We propose a framework where causality emerges as a consequence of compressing data across multiple environments. We define algorithmic causality as an alternative definition of causality when traditional assumptions for causal identifiability do not hold. We demonstrate how algorithmic causal and symmetric structures can emerge from minimizing upper bounds on Kolmogorov complexity, without knowledge of intervention targets. We hypothesize that these insights may also provide a novel perspective on the emergence of causality in machine learning models, such as large language models, where causal relationships may not be explicitly identifiable.
Authors: Dongkyu Cho, Taesup Moon, Rumi Chunara, Kyunghyun Cho, Sungmin Cha
Abstract: Continual learning (CL) research typically assumes highly constrained exemplar memory resources. However, in many real-world scenarios-especially in the era of large foundation models-memory is abundant, while GPU computational costs are the primary bottleneck. In this work, we investigate CL in a novel setting where exemplar memory is ample (i.e., sufficient exemplar memory). Unlike prior methods designed for strict exemplar memory constraints, we propose a simple yet effective approach that directly operates in the model's weight space through a combination of weight resetting and averaging techniques. Our method achieves state-of-the-art performance while reducing the computational cost to a quarter or third of existing methods. These findings challenge conventional CL assumptions and provide a practical baseline for computationally efficient CL applications.
Authors: Mukun Chen, Jia Wu, Shirui Pan, Fu Lin, Bo Du, Xiuwen Gong, Wenbin Hu
Abstract: Molecular representation learning is pivotal in predicting molecular properties and advancing drug design. Traditional methodologies, which predominantly rely on homogeneous graph encoding, are limited by their inability to integrate external knowledge and represent molecular structures across different levels of granularity. To address these limitations, we propose a paradigm shift by encoding molecular graphs into heterogeneous structures, introducing a novel framework: Knowledge-aware Contrastive Heterogeneous Molecular Graph Learning (KCHML). This approach leverages contrastive learning to enrich molecular representations with embedded external knowledge. KCHML conceptualizes molecules through three distinct graph views-molecular, elemental, and pharmacological-enhanced by heterogeneous molecular graphs and a dual message-passing mechanism. This design offers a comprehensive representation for property prediction, as well as for downstream tasks such as drug-drug interaction (DDI) prediction. Extensive benchmarking demonstrates KCHML's superiority over state-of-the-art molecular property prediction models, underscoring its ability to capture intricate molecular features.
Authors: Shuyi Chen, Ferdinando Fioretto, Feng Qiu, Shixiang Zhu
Abstract: Extreme hazard events such as wildfires and hurricanes increasingly threaten power systems, causing widespread outages and disrupting critical services. Recently, predict-then-optimize approaches have gained traction in grid operations, where system functionality forecasts are first generated and then used as inputs for downstream decision-making. However, this two-stage method often results in a misalignment between prediction and optimization objectives, leading to suboptimal resource allocation. To address this, we propose predict-all-then-optimize-globally (PATOG), a framework that integrates outage prediction with globally optimized interventions. At its core, our global-decision-focused (GDF) neural ODE model captures outage dynamics while optimizing resilience strategies in a decision-aware manner. Unlike conventional methods, our approach ensures spatially and temporally coherent decision-making, improving both predictive accuracy and operational efficiency. Experiments on synthetic and real-world datasets demonstrate significant improvements in outage prediction consistency and grid resilience.
Authors: Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Sch\"olkopf, Mario Fritz
Abstract: Ensuring trustworthiness in machine learning (ML) systems is crucial as they become increasingly embedded in high-stakes domains. This paper advocates for integrating causal methods into machine learning to navigate the trade-offs among key principles of trustworthy ML, including fairness, privacy, robustness, accuracy, and explainability. While these objectives should ideally be satisfied simultaneously, they are often addressed in isolation, leading to conflicts and suboptimal solutions. Drawing on existing applications of causality in ML that successfully align goals such as fairness and accuracy or privacy and robustness, this paper argues that a causal approach is essential for balancing multiple competing objectives in both trustworthy ML and foundation models. Beyond highlighting these trade-offs, we examine how causality can be practically integrated into ML and foundation models, offering solutions to enhance their reliability and interpretability. Finally, we discuss the challenges, limitations, and opportunities in adopting causal frameworks, paving the way for more accountable and ethically sound AI systems.
Authors: Yiyang Liu, James Chenhao Liang, Ruixiang Tang, Yugyung Lee, Majid Rabbani, Sohail Dianat, Raghuveer Rao, Lifu Huang, Dongfang Liu, Qifan Wang, Cheng Han
Abstract: Multimodal instruction tuning has proven to be an effective strategy for achieving zero-shot generalization by fine-tuning pre-trained Large Multimodal Models (LMMs) with instruction-following data. However, as the scale of LMMs continues to grow, fully fine-tuning these models has become highly parameter-intensive. Although Parameter-Efficient Fine-Tuning (PEFT) methods have been introduced to reduce the number of tunable parameters, a significant performance gap remains compared to full fine-tuning. Furthermore, existing PEFT approaches are often highly parameterized, making them difficult to interpret and control. In light of this, we introduce Multimodal Representation Tuning (MRT), a novel approach that focuses on directly editing semantically rich multimodal representations to achieve strong performance and provide intuitive control over LMMs. Empirical results show that our method surpasses current state-of-the-art baselines with significant performance gains (e.g., 1580.40 MME score) while requiring substantially fewer tunable parameters (e.g., 0.03% parameters). Additionally, we conduct experiments on editing instrumental tokens within multimodal representations, demonstrating that direct manipulation of these representations enables simple yet effective control over network behavior.
Authors: Wang YuHang, Junkang Guo, Aolei Liu, Kaihao Wang, Zaitong Wu, Zhenyu Liu, Wenfei Yin, Jian Liu
Abstract: Adversarial robustness is a critical challenge in deploying deep neural networks for real-world applications. While adversarial training is a widely recognized defense strategy, most existing studies focus on balanced datasets, overlooking the prevalence of long-tailed distributions in real-world data, which significantly complicates robustness. This paper provides a comprehensive analysis of adversarial training under long-tailed distributions and identifies limitations in the current state-of-the-art method, AT-BSL, in achieving robust performance under such conditions. To address these challenges, we propose a novel training framework, TAET, which integrates an initial stabilization phase followed by a stratified equalization adversarial training phase. Additionally, prior work on long-tailed robustness has largely ignored the crucial evaluation metric of balanced accuracy. To bridge this gap, we introduce the concept of balanced robustness, a comprehensive metric tailored for assessing robustness under long-tailed distributions. Extensive experiments demonstrate that our method surpasses existing advanced defenses, achieving significant improvements in both memory and computational efficiency. This work represents a substantial advancement in addressing robustness challenges in real-world applications. Our code is available at: https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions.
Authors: Richard Ren, Arunim Agarwal, Mantas Mazeika, Cristina Menghini, Robert Vacareanu, Brad Kenstler, Mick Yang, Isabelle Barrass, Alice Gatti, Xuwang Yin, Eduardo Trevino, Matias Geralnik, Adam Khoja, Dean Lee, Summer Yue, Dan Hendrycks
Abstract: As large language models (LLMs) become more capable and agentic, the requirement for trust in their outputs grows significantly, yet at the same time concerns have been mounting that models may learn to lie in pursuit of their goals. To address these concerns, a body of work has emerged around the notion of "honesty" in LLMs, along with interventions aimed at mitigating deceptive behaviors. However, evaluations of honesty are currently highly limited, with no benchmark combining large scale and applicability to all models. Moreover, many benchmarks claiming to measure honesty in fact simply measure accuracy--the correctness of a model's beliefs--in disguise. In this work, we introduce a large-scale human-collected dataset for measuring honesty directly, allowing us to disentangle accuracy from honesty for the first time. Across a diverse set of LLMs, we find that while larger models obtain higher accuracy on our benchmark, they do not become more honest. Surprisingly, while most frontier LLMs obtain high scores on truthfulness benchmarks, we find a substantial propensity in frontier LLMs to lie when pressured to do so, resulting in low honesty scores on our benchmark. We find that simple methods, such as representation engineering interventions, can improve honesty. These results underscore the growing need for robust evaluations and effective interventions to ensure LLMs remain trustworthy.
Authors: Ziruo Hao, Zhenhua Cui, Tao Yang, Bo Hu, Xiaofeng Wu, Hui Feng
Abstract: This paper provides an invariant federated learning system for resource-constrained edge intelligence. This framework can avoid the impact of heterogeneity and asynchrony by exit strategy and invariant penalty. We decompose local information into two orthogonal components to measure the contribution or impact of heterogeneous and asynchronous clients. We propose that the exit of abnormal clients can guarantee the effect of the model on most clients. Meanwhile, to ensure the models' performance on exited abnormal clients and those who lack training resources, we propose Federated Learning with Invariant Penalty for Generalization (FedIPG) based on the invariant orthogonal decomposition of parameters. Theoretical proof shows that FedIPG reduces the Out-Of-Distribution prediction loss without increasing the communication burden. The performance of FedIPG combined with an exit strategy is tested empirically in multiple scales using four datasets. It shows our system can enhance In-Distribution performance and outperform the state-of-the-art algorithm in Out-Of-Distribution generalization while maintaining model convergence. Additionally, the results of the visual experiment prove that FedIPG contains preliminary causality in terms of ignoring confounding features.
Authors: Andrzej Cichocki, Toshihisa Tanaka, Sergio Cruces
Abstract: In this paper we propose and investigate a wide class of Mirror Descent updates (MD) and associated novel Generalized Exponentiated Gradient (GEG) algorithms by exploiting various trace-form entropies and associated deformed logarithms and their inverses - deformed (generalized) exponential functions. The proposed algorithms can be considered as extension of entropic MD and generalization of multiplicative updates. In the literature, there exist nowadays over fifty mathematically well defined generalized entropies, so impossible to exploit all of them in one research paper. So we focus on a few selected most popular entropies and associated logarithms like the Tsallis, Kaniadakis and Sharma-Taneja-Mittal and some of their extension like Tempesta or Kaniadakis-Scarfone entropies. The shape and properties of the deformed logarithms and their inverses are tuned by one or more hyperparameters. By learning these hyperparameters, we can adapt to distribution of training data, which can be designed to the specific geometry of the optimization problem, leading to potentially faster convergence and better performance. The using generalized entropies and associated deformed logarithms in the Bregman divergence, used as a regularization term, provides some new insight into exponentiated gradient descent updates.
Authors: Zilong Deng, Simon Khan, Shaofeng Zou
Abstract: In this work, we study the sample complexity problem of risk-sensitive Reinforcement Learning (RL) with a generative model, where we aim to maximize the Conditional Value at Risk (CVaR) with risk tolerance level $\tau$ at each step, named Iterated CVaR. We first build a connection between Iterated CVaR RL with $(s, a)$-rectangular distributional robust RL with the specific uncertainty set for CVaR. We develop nearly matching upper and lower bounds on the sample complexity for this problem. Specifically, we first prove that a value iteration-based algorithm, ICVaR-VI, achieves an $\epsilon$-optimal policy with at most $\overset{\sim}{O}\left(\frac{SA}{(1-\gamma)^4\tau^2\epsilon^2}\right)$ samples, where $\gamma$ is the discount factor, and $S, A$ are the sizes of the state and action spaces. Furthermore, if $\tau \geq \gamma$, then the sample complexity can be further improved to $\overset{\sim}{O}\left( \frac{SA}{(1-\gamma)^3\epsilon^2} \right)$. We further show a minimax lower bound of $\overset{\sim}{O} \left(\frac{(1-\gamma \tau)SA}{(1-\gamma)^4\tau\epsilon^2}\right)$. For a constant risk level $0<\tau\leq 1$, our upper and lower bounds match with each other, demonstrating the tightness and optimality of our analyses.We also investigate a limiting case with a small risk level $\tau$, called Worst-Path RL, where the objective is to maximize the minimum possible cumulative reward. We develop matching upper and lower bounds of $\overset{\sim}{O}\left(\frac{SA}{p_{\min}}\right)$, where $p_{\min}$ denotes the minimum non-zero reaching probability of the transition kernel.
Authors: Zijian Zhao, Xuming Zhang, Jiayu Wen, Mingwen Liu, Xiaoteng Ma
Abstract: In financial trading, return prediction is one of the foundation for a successful trading system. By the fast development of the deep learning in various areas such as graphical processing, natural language, it has also demonstrate significant edge in handling with financial data. While the success of the deep learning relies on huge amount of labeled sample, labeling each time/event as profitable or unprofitable, under the transaction cost, especially in the high-frequency trading world, suffers from serious label imbalance issue.In this paper, we adopts rigurious end-to-end deep learning framework with comprehensive label imbalance adjustment methods and succeed in predicting in high-frequency return in the Chinese future market. The code for our method is publicly available at https://github.com/RS2002/Label-Unbalance-in-High-Frequency-Trading .
URLs: https://github.com/RS2002/Label-Unbalance-in-High-Frequency-Trading
Authors: Atoosa Malemir Chegini, Keivan Rezaei, Hamid Eghbalzadeh, Soheil Feizi
Abstract: Fact-checking tabular data is essential for ensuring the accuracy of structured information. However, existing methods often rely on black-box models with opaque reasoning. We introduce RePanda, a structured fact verification approach that translates claims into executable pandas queries, enabling interpretable and verifiable reasoning. To train RePanda, we construct PanTabFact, a structured dataset derived from the TabFact train set, where claims are paired with executable queries generated using DeepSeek-Chat and refined through automated error correction. Fine-tuning DeepSeek-coder-7B-instruct-v1.5 on PanTabFact, RePanda achieves 84.09% accuracy on the TabFact test set. To evaluate Out-of-Distribution (OOD) generalization, we interpret question-answer pairs from WikiTableQuestions as factual claims and refer to this dataset as WikiFact. Without additional fine-tuning, RePanda achieves 84.72% accuracy on WikiFact, significantly outperforming all other baselines and demonstrating strong OOD robustness. Notably, these results closely match the zero-shot performance of DeepSeek-Chat (671B), indicating that our fine-tuning approach effectively distills structured reasoning from a much larger model into a compact, locally executable 7B model. Beyond fact verification, RePanda extends to tabular question answering by generating executable queries that retrieve precise answers. To support this, we introduce PanWiki, a dataset mapping WikiTableQuestions to pandas queries. Fine-tuning on PanWiki, RePanda achieves 75.1% accuracy in direct answer retrieval. These results highlight the effectiveness of structured execution-based reasoning for tabular verification and question answering. We have publicly released the dataset on Hugging Face at datasets/AtoosaChegini/PanTabFact.
Authors: Yunbo Long, Liming Xu, Ge Zheng, Alexandra Brintrup
Abstract: Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by factors such as varying consumer behavior, poses challenges to the effectiveness of federated learning. To tackle this challenge, we propose Privacy-Adaptive Clustered Federated Learning (PA-CFL) tailored for demand forecasting on heterogeneous retail data. By leveraging differential privacy and feature importance distribution, PA-CFL groups retailers into distinct ``bubbles'', each forming its own federated learning system to effectively isolate data heterogeneity. Within each bubble, Transformer models are designed to predict local sales for each client. Our experiments demonstrate that PA-CFL significantly surpasses FedAvg and outperforms local learning in demand forecasting performance across all participating clients. Compared to local learning, PA-CFL achieves a 5.4% improvement in R^2, a 69% reduction in RMSE, and a 45% decrease in MAE. Our approach enables effective FL through adaptive adjustments to diverse noise levels and the range of clients participating in each bubble. By grouping participants and proactively filtering out high-risk clients, PA-CFL mitigates potential threats to the FL system. The findings demonstrate PA-CFL's ability to enhance federated learning in time series prediction tasks with heterogeneous data, achieving a balance between forecasting accuracy and privacy preservation in retail applications. Additionally, PA-CFL's capability to detect and neutralize poisoned data from clients enhances the system's robustness and reliability.
Authors: Hisato Komatsu
Abstract: The linear regression (LR) method offers the advantage that optimal parameters can be calculated relatively easily, although its representation capability is limited than that of the deep learning technique. To improve deep reinforcement learning, the Least Squares Deep Q Network (LS-DQN) method was proposed by Levine et al., which combines Deep Q Network (DQN) with LR method. However, the LS-DQN method assumes that the actions are discrete. In this study, we propose the Double Least Squares Deep Deterministic Policy Gradient (DLS-DDPG) method to address this limitation. This method combines the LR method with the Deep Deterministic Policy Gradient (DDPG) technique, one of the representative deep reinforcement learning algorithms for continuous action cases. Numerical experiments conducted in MuJoCo environments showed that the LR update improved performance at least in some tasks, although there are difficulties such as the inability to make the regularization terms small.
Authors: Philipp Wagner, Tobias Nagel, Philipp Leube, Marco F. Huber
Abstract: Correctly setting the parameters of a production machine is essential to improve product quality, increase efficiency, and reduce production costs while also supporting sustainability goals. Identifying optimal parameters involves an iterative process of producing an object and evaluating its quality. Minimizing the number of iterations is, therefore, desirable to reduce the costs associated with unsuccessful attempts. This work introduces a method to optimize the machine parameters in the system itself using a Bayesian optimization algorithm. By leveraging existing machine data, we use a transfer learning approach in order to identify an optimum with minimal iterations, resulting in a cost-effective transfer learning algorithm. We validate our approach on a laser machine for cutting sheet metal in the real world.
Authors: Shuqi Lu, Haowei Lin, Lin Yao, Zhifeng Gao, Xiaohong Ji, Weinan E, Linfeng Zhang, Guolin Ke
Abstract: Recent advancements in large language models and their multi-modal extensions have demonstrated the effectiveness of unifying generation and understanding through autoregressive next-token prediction. However, despite the critical role of 3D structural generation and understanding (3D GU) in AI for science, these tasks have largely evolved independently, with autoregressive methods remaining underexplored. To bridge this gap, we introduce Uni-3DAR, a unified framework that seamlessly integrates 3D GU tasks via autoregressive prediction. At its core, Uni-3DAR employs a novel hierarchical tokenization that compresses 3D space using an octree, leveraging the inherent sparsity of 3D structures. It then applies an additional tokenization for fine-grained structural details, capturing key attributes such as atom types and precise spatial coordinates in microscopic 3D structures. We further propose two optimizations to enhance efficiency and effectiveness. The first is a two-level subtree compression strategy, which reduces the octree token sequence by up to 8x. The second is a masked next-token prediction mechanism tailored for dynamically varying token positions, significantly boosting model performance. By combining these strategies, Uni-3DAR successfully unifies diverse 3D GU tasks within a single autoregressive framework. Extensive experiments across multiple microscopic 3D GU tasks, including molecules, proteins, polymers, and crystals, validate its effectiveness and versatility. Notably, Uni-3DAR surpasses previous state-of-the-art diffusion models by a substantial margin, achieving up to 256\% relative improvement while delivering inference speeds up to 21.8x faster. The code is publicly available at https://github.com/dptech-corp/Uni-3DAR.
Authors: G\'abor Braun, Sebastian Pokutta, Dan Tu, Stephen Wright
Abstract: We present a blended conditional gradient approach for minimizing a smooth convex function over a polytope P, combining the Frank--Wolfe algorithm (also called conditional gradient) with gradient-based steps, different from away steps and pairwise steps, but still achieving linear convergence for strongly convex functions, along with good practical performance. Our approach retains all favorable properties of conditional gradient algorithms, notably avoidance of projections onto P and maintenance of iterates as sparse convex combinations of a limited number of extreme points of P. The algorithm is lazy, making use of inexpensive inexact solutions of the linear programming subproblem that characterizes the conditional gradient approach. It decreases measures of optimality (primal and dual gaps) rapidly, both in the number of iterations and in wall-clock time, outperforming even the lazy conditional gradient algorithms of [arXiv:1410.8816]. We also present a streamlined version of the algorithm for the probability simplex.
Authors: Nick Whiteley, Annie Gray, Patrick Rubin-Delanchy
Abstract: The Manifold Hypothesis is a widely accepted tenet of Machine Learning which asserts that nominally high-dimensional data are in fact concentrated near a low-dimensional manifold, embedded in high-dimensional space. This phenomenon is observed empirically in many real world situations, has led to development of a wide range of statistical methods in the last few decades, and has been suggested as a key factor in the success of modern AI technologies. We show that rich and sometimes intricate manifold structure in data can emerge from a generic and remarkably simple statistical model -- the Latent Metric Model -- via elementary concepts such as latent variables, correlation and stationarity. This establishes a general statistical explanation for why the Manifold Hypothesis seems to hold in so many situations. Informed by the Latent Metric Model we derive procedures to discover and interpret the geometry of high-dimensional data, and explore hypotheses about the data generating mechanism. These procedures operate under minimal assumptions and make use of well known graph-analytic algorithms.
Authors: Ryan Cory-Wright, Jean Pauphilet
Abstract: Sparse Principal Component Analysis (sPCA) is a cardinal technique for obtaining combinations of features, or principal components (PCs), that explain the variance of high-dimensional datasets in an interpretable manner. This involves solving a sparsity and orthogonality constrained convex maximization problem, which is extremely computationally challenging. Most existing works address sparse PCA via methods-such as iteratively computing one sparse PC and deflating the covariance matrix-that do not guarantee the orthogonality, let alone the optimality, of the resulting solution when we seek multiple mutually orthogonal PCs. We challenge this status by reformulating the orthogonality conditions as rank constraints and optimizing over the sparsity and rank constraints simultaneously. We design tight semidefinite relaxations to supply high-quality upper bounds, which we strengthen via additional second-order cone inequalities when each PC's individual sparsity is specified. Further, we derive a combinatorial upper bound on the maximum amount of variance explained as a function of the support. We exploit these relaxations and bounds to propose exact methods and rounding mechanisms that, together, obtain solutions with a bound gap on the order of 0%-15% for real-world datasets with p = 100s or 1000s of features and r \in {2, 3} components. Numerically, our algorithms match (and sometimes surpass) the best performing methods in terms of fraction of variance explained and systematically return PCs that are sparse and orthogonal. In contrast, we find that existing methods like deflation return solutions that violate the orthogonality constraints, even when the data is generated according to sparse orthogonal PCs. Altogether, our approach solves sparse PCA problems with multiple components to certifiable (near) optimality in a practically tractable fashion.
Authors: Zahra Shamsi, Isaac Reid, Drew Bryant, Jacob Wilson, Xiaoyu Qu, Avinava Dubey, Konik Kothari, Mostafa Dehghani, Mariya Chavarha, Valerii Likhosherstov, Brian Williams, Michael Frumkin, Fred Appelbaum, Krzysztof Choromanski, Ali Bashir, Min Fang
Abstract: We present a machine learning method capable of accurately detecting chromosome abnormalities that cause blood cancers directly from microscope images of the metaphase stage of cell division. The pipeline is built on a series of fine-tuned Vision Transformers. Current state of the art (and standard clinical practice) requires expensive, manual expert analysis, whereas our pipeline takes only 15 seconds per metaphase image. Using a novel pretraining-finetuning strategy to mitigate the challenge of data scarcity, we achieve a high precision-recall score of 94% AUC for the clinically significant del(5q) and t(9;22) anomalies. Our method also unlocks zero-shot detection of rare aberrations based on model latent embeddings. The ability to quickly, accurately, and scalably diagnose genetic abnormalities directly from metaphase images could transform karyotyping practice and improve patient outcomes. We will make code publicly available.
Authors: Zeyu Yun, Juexiao Zhang, Yann LeCun, Yubei Chen
Abstract: Unsupervised representation learning has seen tremendous progress. However, it is constrained by its reliance on domain specific stationarity and topology, a limitation not found in biological intelligence systems. For instance, unlike computer vision, human vision can process visual signals sampled from highly irregular and non-stationary sensors. We introduce a novel framework that learns from high-dimensional data without prior knowledge of stationarity and topology. Our model, abbreviated as URLOST, combines a learnable self-organizing layer, spectral clustering, and a masked autoencoder (MAE). We evaluate its effectiveness on three diverse data modalities including simulated biological vision data, neural recordings from the primary visual cortex, and gene expressions. Compared to state-of-the-art unsupervised learning methods like SimCLR and MAE, our model excels at learning meaningful representations across diverse modalities without knowing their stationarity or topology. It also outperforms other methods that are not dependent on these factors, setting a new benchmark in the field. We position this work as a step toward unsupervised learning methods capable of generalizing across diverse high-dimensional data modalities.
Authors: Kevin Klein, Antoine Muller, Alyssa Wohde, Alexander V. Gorelik, Volker Heyd, Ralf L\"ammel, Yoan Diekmann, Maxime Brami
Abstract: The context of this paper is the creation of large uniform archaeological datasets from heterogeneous published resources, such as find catalogues - with the help of AI and Big Data. The paper is concerned with the challenge of consistent assemblages of archaeological data. We cannot simply combine existing records, as they differ in terms of quality and recording standards. Thus, records have to be recreated from published archaeological illustrations. This is only a viable path with the help of automation. The contribution of this paper is a new workflow for collecting data from archaeological find catalogues available as legacy resources, such as archaeological drawings and photographs in large unsorted PDF files; the workflow relies on custom software (AutArch) supporting image processing, object detection, and interactive means of validating and adjusting automatically retrieved data. We integrate artificial intelligence (AI) in terms of neural networks for object detection and classification into the workflow, thereby speeding up, automating, and standardising data collection. Objects commonly found in archaeological catalogues - such as graves, skeletons, ceramics, ornaments, stone tools and maps - are detected. Those objects are spatially related and analysed to extract real-life attributes, such as the size and orientation of graves based on the north arrow and the scale. We also automate recording of geometric whole-outlines through contour detection, as an alternative to landmark-based geometric morphometrics. Detected objects, contours, and other automatically retrieved data can be manually validated and adjusted. We use third millennium BC Europe (encompassing cultures such as 'Corded Ware' and 'Bell Beaker', and their burial practices) as a 'testing ground' and for evaluation purposes; this includes a user study for the workflow and the AutArch software.
Authors: Jiri Nemecek, Tomas Pevny, Jakub Marecek
Abstract: The need to explain decisions made by AI systems is driven by both recent regulation and user demand. The decisions are often explainable only post hoc. In counterfactual explanations, one may ask what constitutes the best counterfactual explanation. Clearly, multiple criteria must be taken into account, although "distance from the sample" is a key criterion. Recent methods that consider the plausibility of a counterfactual seem to sacrifice this original objective. Here, we present a system that provides high-likelihood explanations that are, at the same time, close and sparse. We show that the search for the most likely explanations satisfying many common desiderata for counterfactual explanations can be modeled using Mixed-Integer Optimization (MIO). We use a Sum-Product Network (SPN) to estimate the likelihood of a counterfactual. To achieve that, we propose an MIO formulation of an SPN, which can be of independent interest. The source code with examples is available at https://github.com/Epanemu/LiCE.
Authors: Sam Lin, Wenyue Hua, Zhenting Wang, Mingyu Jin, Lizhou Fan, Yongfeng Zhang
Abstract: Cloud-based Large Language Models (LLMs) such as ChatGPT have become increasingly integral to daily operations. Nevertheless, they also introduce privacy concerns: firstly, numerous studies underscore the risks to user privacy posed by jailbreaking cloud-based LLMs; secondly, the LLM service providers have access to all user data, which deters individuals from confidently utilizing such services. To address such concerns, we propose a simple yet effective paradigm, EmojiPrompt, to protect user privacy. At its core, EmojiPrompt performs generative transformation, obfuscating private data within prompts with linguistic and non-linguistic elements before submitting them to cloud-based LLMs. We evaluate EmojiPrompt's performance across 8 datasets from various domains. We also propose simulated inference attacks to assess EmojiPrompt's ability to preserve user privacy. The results demonstrate that EmojiPrompt effectively obfuscates user private data, while largely maintaining, or even enhancing, performances compared to the unobfuscated version. Furthermore, EmojiPrompt's atomic-level obfuscation allows it to function exclusively with cloud-based LLMs. For source code, please refer to: https://github.com/agiresearch/EmojiCrypt.
Authors: Dongyang Liu, Renrui Zhang, Longtian Qiu, Siyuan Huang, Weifeng Lin, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, Wenqi Shao, Chao Xu, Conghui He, Junjun He, Hao Shao, Pan Lu, Hongsheng Li, Yu Qiao, Peng Gao
Abstract: We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory
Authors: Hamed Haghighi, Xiaomeng Wang, Hao Jing, Mehrdad Dianati
Abstract: Perception sensors, particularly camera and Lidar, are key elements of Autonomous Driving Systems (ADS) that enable them to comprehend their surroundings to informed driving and control decisions. Therefore, developing realistic simulation models for these sensors is essential for conducting effective simulation-based testing of ADS. Moreover, the rise of deep learning-based perception models has increased the utility of sensor simulation models for synthesising diverse training datasets. The traditional sensor simulation models rely on computationally expensive physics-based algorithms, specifically in complex systems such as ADS. Hence, the current potential resides in data-driven approaches, fuelled by the exceptional performance of deep generative models in capturing high-dimensional data distribution and volume renderers in accurately representing scenes. This paper reviews the current state-of-the-art data-driven camera and Lidar simulation models and their evaluation methods. It explores a spectrum of models from the novel perspective of generative models and volume renderers. Generative models are discussed in terms of their input-output types, while volume renderers are categorised based on their input encoding. Finally, the paper illustrates commonly used evaluation techniques for assessing sensor simulation models and highlights the existing research gaps in the area.
Authors: Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng
Abstract: Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old classes. Current GCD methods only use a single visual modality of information, resulting in a poor classification of visually similar classes. As a different modality, text information can provide complementary discriminative information, which motivates us to introduce it into the GCD task. However, the lack of class names for unlabelled data makes it impractical to utilize text information. To tackle this challenging problem, in this paper, we propose a Text Embedding Synthesizer (TES) to generate pseudo text embeddings for unlabelled samples. Specifically, our TES leverages the property that CLIP can generate aligned vision-language features, converting visual embeddings into tokens of the CLIP's text encoder to generate pseudo text embeddings. Besides, we employ a dual-branch framework, through the joint learning and instance consistency of different modality branches, visual and semantic information mutually enhance each other, promoting the interaction and fusion of visual and text knowledge. Our method unlocks the multi-modal potentials of CLIP and outperforms the baseline methods by a large margin on all GCD benchmarks, achieving new state-of-the-art. Our code is available at: https://github.com/enguangW/GET.
Authors: Liang Zhang, Niao He, Michael Muehlebach
Abstract: Variational inequality problems are recognized for their broad applications across various fields including machine learning and operations research. First-order methods have emerged as the standard approach for solving these problems due to their simplicity and scalability. However, they typically rely on projection or linear minimization oracles to navigate the feasible set, which becomes computationally expensive in practical scenarios featuring multiple functional constraints. Existing efforts to tackle such functional constrained variational inequality problems have centered on primal-dual algorithms grounded in the Lagrangian function. These algorithms along with their theoretical analysis often require the existence and prior knowledge of the optimal Lagrange multipliers. In this work, we propose a simple primal method, termed Constrained Gradient Method (CGM), for addressing functional constrained variational inequality problems, without requiring any information on the optimal Lagrange multipliers. We establish a non-asymptotic convergence analysis of the algorithm for Minty variational inequality problems with monotone operators under smooth constraints. Remarkably, our algorithms match the complexity of projection-based methods in terms of operator queries for both monotone and strongly monotone settings, while using significantly cheaper oracles based on quadratic programming. Furthermore, we provide several numerical examples to evaluate the efficacy of our algorithms.
Authors: Youness Boutaib
Abstract: A natural hypothesis for the success of reservoir computing in generic tasks is the ability of the untrained reservoir to map different input time series to separable reservoir states - a property we term separation capacity. We provide a rigorous mathematical framework to quantify this capacity for random linear reservoirs, showing that it is fully characterised by the spectral properties of the generalised matrix of moments of the random reservoir connectivity matrix. Our analysis focuses on reservoirs with Gaussian connectivity matrices, both symmetric and i.i.d., although the techniques extend naturally to broader classes of random matrices. In the symmetric case, the generalised matrix of moments is a Hankel matrix. Using classical estimates from random matrix theory, we establish that separation capacity deteriorates over time and that, for short inputs, optimal separation in large reservoirs is achieved when the matrix entries are scaled with a factor $\rho_T/\sqrt{N}$, where $N$ is the reservoir dimension and $\rho_T$ depends on the maximum input length. In the i.i.d.\ case, we establish that optimal separation with large reservoirs is consistently achieved when the entries of the reservoir matrix are scaled with the exact factor $1/\sqrt{N}$, which aligns with common implementations of reservoir computing. We further give upper bounds on the quality of separation as a function of the length of the time series. We complement this analysis with an investigation of the likelihood of this separation and its consistency under different architectural choices.
Authors: Tiago P. Peixoto
Abstract: A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting, and produces an inferred network with a statistically justifiable number of edges. The status quo in this context is based on $L_{1}$ regularization combined with cross-validation. However, besides its high computational cost, this commonplace approach unnecessarily ties the promotion of sparsity with weight "shrinkage". This combination forces a trade-off between the bias introduced by shrinkage and the network sparsity, which often results in substantial overfitting even after cross-validation. In this work, we propose an alternative nonparametric regularization scheme based on hierarchical Bayesian inference and weight quantization, which does not rely on weight shrinkage to promote sparsity. Our approach follows the minimum description length (MDL) principle, and uncovers the weight distribution that allows for the most compression of the data, thus avoiding overfitting without requiring cross-validation. The latter property renders our approach substantially faster to employ, as it requires a single fit to the complete data. As a result, we have a principled and efficient inference scheme that can be used with a large variety of generative models, without requiring the number of edges to be known in advance. We also demonstrate that our scheme yields systematically increased accuracy in the reconstruction of both artificial and empirical networks. We highlight the use of our method with the reconstruction of interaction networks between microbial communities from large-scale abundance samples involving in the order of $10^{4}$ to $10^{5}$ species, and demonstrate how the inferred model can be used to predict the outcome of interventions in the system.
Authors: G. Ibikunle, B. Moews, D. Muravyev, K. Rzayev
Abstract: High-frequency trading (HFT) accounts for almost half of equity trading volume, yet it is not identified in public data. We develop novel data-driven measures of HFT activity that separate strategies that supply and demand liquidity. We train machine learning models to predict HFT activity observed in a proprietary dataset using concurrent public intraday data. Once trained on the dataset, these models generate HFT measures for the entire U.S. stock universe from 2010 to 2023. Our measures outperform conventional proxies, which struggle to capture HFT's time dynamics. We further validate them using shocks to HFT activity, including latency arbitrage, exchange speed bumps, and data feed upgrades. Finally, our measures reveal how HFT affects fundamental information acquisition. Liquidity-supplying HFTs improve price discovery around earnings announcements while liquidity-demanding strategies impede it.
Authors: Jianing Yang, Xuweiyi Chen, Nikhil Madaan, Madhavan Iyengar, Shengyi Qian, David F. Fouhey, Joyce Chai
Abstract: The integration of language and 3D perception is crucial for embodied agents and robots that comprehend and interact with the physical world. While large language models (LLMs) have demonstrated impressive language understanding and generation capabilities, their adaptation to 3D environments (3D-LLMs) remains in its early stages. A primary challenge is a lack of large-scale datasets with dense grounding between language and 3D scenes. We introduce 3D-GRAND, a pioneering large-scale dataset comprising 40,087 household scenes paired with 6.2 million densely-grounded scene-language instructions. Our results show that instruction tuning with 3D-GRAND significantly enhances grounding capabilities and reduces hallucinations in 3D-LLMs. As part of our contributions, we propose a comprehensive benchmark 3D-POPE to systematically evaluate hallucination in 3D-LLMs, enabling fair comparisons of models. Our experiments highlight a scaling effect between dataset size and 3D-LLM performance, emphasizing the importance of large-scale 3D-text datasets for embodied AI research. Our results demonstrate early signals for effective sim-to-real transfer, indicating that models trained on large synthetic data can perform well on real-world 3D scans. Through 3D-GRAND and 3D-POPE, we aim to equip the embodied AI community with resources and insights to lead to more reliable and better-grounded 3D-LLMs. Project website: https://3d-grand.github.io
Authors: Sijia Chen, Yibo Wang, Yi-Feng Wu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang
Abstract: Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to improve their reasoning capabilities on complex tasks. This enables them to act as intelligent agents interacting with the real world. The recently introduced ToolLLaMA model by Qin et al. [2023] utilizes the depth-first search-based decision tree (DFSDT) mechanism for multi-step reasoning with $16000+$ real-world APIs, effectively enhancing the performance of tool-augmented LLMs compared to traditional chain reasoning mechanisms. However, their approach only employs successful paths from decision trees (also called inference trees) for supervised fine-tuning (SFT), missing out on the potential learning opportunities from failed paths. Inspired by this, we propose an inference trajectory optimization framework based on preference learning to address this limitation. We first introduce a novel method for constructing step-wise preference data from tree-like expert trajectories, which leverages the previously ignored failed explorations in the decision trees. In the subsequent training phase, we first fine-tune the LLM with successful tool-usage expert trajectories and then apply direct preference optimization (DPO) with the preference data to update the LLM's policy, resulting in our ToolPrefer-LLaMA (TP-LLaMA) model. This approach not only enhances the utilization of original expert data but also broadens the learning space of the model. Our experiments demonstrate that by obtaining insights from errors in inference trees, TP-LLaMA significantly outperforms the baselines across almost all test scenarios by a large margin and exhibits better generalization capabilities with unseen APIs. At the same time, TP-LLaMA has also demonstrated superior reasoning efficiency compared to the baselines, making it more suitable for complex tool-usage reasoning tasks.
Authors: Anna Susmelj, Mael Macuglia, Nata\v{s}a Tagasovska, Reto Sutter, Sebastiano Caprara, Jean-Philippe Thiran, Ender Konukoglu
Abstract: Implicit functions such as Neural Radiance Fields (NeRFs), occupancy networks, and signed distance functions (SDFs) have become pivotal in computer vision for reconstructing detailed object shapes from sparse views. Achieving optimal performance with these models can be challenging due to the extreme sparsity of inputs and distribution shifts induced by data corruptions. To this end, large, noise-free synthetic datasets can serve as shape priors to help models fill in gaps, but the resulting reconstructions must be approached with caution. Uncertainty estimation is crucial for assessing the quality of these reconstructions, particularly in identifying areas where the model is uncertain about the parts it has inferred from the prior. In this paper, we introduce Dropsembles, a novel method for uncertainty estimation in tuned implicit functions. We demonstrate the efficacy of our approach through a series of experiments, starting with toy examples and progressing to a real-world scenario. Specifically, we train a Convolutional Occupancy Network on synthetic anatomical data and test it on low-resolution MRI segmentations of the lumbar spine. Our results show that Dropsembles achieve the accuracy and calibration levels of deep ensembles but with significantly less computational cost.
Authors: Yaoming Zhen, Jin-Hong Du
Abstract: Given the ubiquity of modularity in biological systems, module-level regulation analysis is vital for understanding biological systems across various levels and their dynamics. Current statistical analysis on biological modules predominantly focuses on either detecting the functional modules in biological networks or sub-group regression on the biological features without using the network data. This paper proposes a novel network-based neighborhood regression framework whose regression functions depend on both the global community-level information and local connectivity structures among entities. An efficient community-wise least square optimization approach is developed to uncover the strength of regulation among the network modules while enabling asymptotic inference. With random graph theory, we derive non-asymptotic estimation error bounds for the proposed estimator, achieving exact minimax optimality. Unlike the root-n consistency typical in canonical linear regression, our model exhibits linear consistency in the number of nodes n, highlighting the advantage of incorporating neighborhood information. The effectiveness of the proposed framework is further supported by extensive numerical experiments. Application to whole-exome sequencing and RNA-sequencing Autism datasets demonstrates the usage of the proposed method in identifying the association between the gene modules of genetic variations and the gene modules of genomic differential expressions.
Authors: Xiaoli Wei, Xiang Yu, Fengyi Yuan
Abstract: This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the representative agent's perspective and establish its martingale characterization, which provides a unified policy evaluation rule for both mean-field game (MFG) and mean-field control (MFC) problems. Moreover, we consider the learning procedure where the representative agent updates the population distribution based on his own state values. Depending on the task to solve the MFG or MFC problem, we can employ the decoupled Iq-function differently to characterize the mean-field equilibrium policy or the mean-field optimal policy respectively. Based on these theoretical findings, we devise a unified q-learning algorithm for both MFG and MFC problems by utilizing test policies and the averaged martingale orthogonality condition. For several financial applications in the jump-diffusion setting, we obtain the exact parameterization of the decoupled Iq-functions and the value functions, and illustrate our q-learning algorithm with satisfactory performance.
Authors: Pascal J. Sager, Jan M. Deriu, Benjamin F. Grewe, Thilo Stadelmann, Christoph von der Malsburg
Abstract: We introduce the Cooperative Network Architecture (CNA), a model that represents sensory signals using structured, recurrently connected networks of neurons, termed "nets." Nets are dynamically assembled from overlapping net fragments, which are learned based on statistical regularities in sensory input. This architecture offers robustness to noise, deformation, and out-of-distribution data, addressing challenges in current vision systems from a novel perspective. We demonstrate that net fragments can be learned without supervision and flexibly recombined to encode novel patterns, enabling figure completion and resilience to noise. Our findings establish CNA as a promising paradigm for developing neural representations that integrate local feature processing with global structure formation, providing a foundation for future research on invariant object recognition.
Authors: Yukai Shi, Zhipeng Weng, Yupei Lin, Cidan Shi, Xiaojun Yang, Liang Lin
Abstract: In recent years, deep neural networks tasks have increasingly relied on high-quality image inputs. With the development of high-resolution representation learning, the task of image dehazing has received significant attention. Previously, many methods collect diverse image data for large-scale training to boost the performance on a target scene. Ignoring the domain gap between different data, former de-hazing methods simply adopt multiple datasets for explicit large-scale training, which often makes the methods themselves be violated. To address this problem, we propose a novel method of cross-data vision alignment for richer representation learning to improve the existing dehazing methodology. Specifically, we call for the internal- and external knowledge should be further adapted with a self-supervised manner to fill up the domain gap. By using cross-data external alignment, the datasets inherit samples from different domains that are firmly aligned, making the model learn more robust and generalizable features. By using the internal augmentation method, the model can fully exploit local information within the images, and then obtaining more image details. To demonstrate the effectiveness of our proposed method, we conduct training on the Natural Image Dataset (NID). Experimental results show that our method clearly resolves the domain gap in different dehazing datasets and presents a new pipeline for large-scale training in the dehazing task. Our approach significantly outperforms other advanced methods in dehazing and produces dehazed images that are closest to real haze-free images.
Authors: Shenghong Dai, Shiqi Jiang, Yifan Yang, Ting Cao, Mo Li, Suman Banerjee, Lili Qiu
Abstract: This paper presents Babel, the expandable modality alignment model, specially designed for multi-modal sensing. While there has been considerable work on multi-modality alignment, they all struggle to effectively incorporate multiple sensing modalities due to the data scarcity constraints. How to utilize multi-modal data with partial pairings in sensing remains an unresolved challenge. Babel tackles this challenge by introducing the concept of expandable modality alignment. The key idea involves transforming the N-modality alignment into a series of binary-modality alignments. Novel techniques are also proposed to further mitigate data scarcity issue and balance the contribution of the newly incorporated modality with the previously established modality alignment during the expandable alignment process. We provide the comprehensive implementation. In the pre-training phase, Babel currently aligns 6 sensing modalities, namely Wi-Fi, mmWave, IMU, LiDAR, video, and depth. For the deployment phase, as a foundation model, any single or combination of aligned modalities could be selected from Babel and applied to downstream tasks. Evaluation demonstrates Babel's outstanding performance on eight human activity recognition datasets, compared to a broad range of baselines e.g., the SOTA single-modal sensing networks, multi-modal sensing framework, and multi-modal large language models. Babel not only improves the performance of individual modality sensing (12% averaged accuracy improvement), but also effectively fuses multiple available modalities (up to 22% accuracy increase). Case studies also highlight emerging application scenarios empowered by Babel, including cross-modality retrieval (i.e., sensing imaging), and bridging LLM for sensing comprehension.
Authors: Hyunin Lee, Chanwoo Park, David Abel, Ming Jin
Abstract: Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to originate from an unpredictable time-varying environments; however, the community lacks a comprehensive definition of black swan events. To this end, this paper challenges that the standard view is incomplete and claims that high-risk, statistically rare events can also occur in unchanging environments due to human misperception of their value and likelihood, which we call as spatial black swan event. We first carefully categorize black swan events, focusing on spatial black swan events, and mathematically formalize the definition of black swan events. We hope these definitions can pave the way for the development of algorithms to prevent such events by rationally correcting human perception.
Authors: Roko Parac, Lorenzo Nodari, Leo Ardon, Daniel Furelos-Blanco, Federico Cerutti, Alessandra Russo
Abstract: This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state machine that decomposes the agent's task into different subtasks. PROB-IRM uses a state-of-the-art inductive logic programming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of beliefs, thus ensuring robustness against inconsistencies. Pivotal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks successfully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.
Authors: Chun Tong Lei, Hon Ming Yam, Zhongliang Guo, Yifei Qian, Chun Pong Lau
Abstract: Neural networks have revolutionized numerous fields with their exceptional performance, yet they remain susceptible to adversarial attacks through subtle perturbations. While diffusion-based purification methods like DiffPure offer promising defense mechanisms, their computational overhead presents a significant practical limitation. In this paper, we introduce One Step Control Purification (OSCP), a novel defense framework that achieves robust adversarial purification in a single Neural Function Evaluation (NFE) within diffusion models. We propose Gaussian Adversarial Noise Distillation (GAND) as the distillation objective and Controlled Adversarial Purification (CAP) as the inference pipeline, which makes OSCP demonstrate remarkable efficiency while maintaining defense efficacy. Our proposed GAND addresses a fundamental tension between consistency distillation and adversarial perturbation, bridging the gap between natural and adversarial manifolds in the latent space, while remaining computationally efficient through Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA, eliminating the high computational budget request from full parameter fine-tuning. The CAP guides the purification process through the unlearnable edge detection operator calculated by the input image as an extra prompt, effectively preventing the purified images from deviating from their original appearance when large purification steps are used. Our experimental results on ImageNet showcase OSCP's superior performance, achieving a 74.19% defense success rate with merely 0.1s per purification -- a 100-fold speedup compared to conventional approaches.
Authors: Haixiang Zhang, Baturalp Yalcin, Javad Lavaei, Eduardo D. Sontag
Abstract: In this work, we study the problem of learning a nonlinear dynamical system by parameterizing its dynamics using basis functions. We assume that disturbances occur at each time step with an arbitrary probability $p$, which models the sparsity level of the disturbance vectors over time. These disturbances are drawn from an arbitrary, unknown probability distribution, which may depend on past disturbances, provided that it satisfies a zero-mean assumption. The primary objective of this paper is to learn the system's dynamics within a finite time and analyze the sample complexity as a function of $p$. To achieve this, we examine a LASSO-type non-smooth estimator, and establish necessary and sufficient conditions for its well-specifiedness and the uniqueness of the global solution to the underlying optimization problem. We then provide exact recovery guarantees for the estimator under two distinct conditions: boundedness and Lipschitz continuity of the basis functions. We show that finite-time exact recovery is achieved with high probability, even when $p$ approaches 1. Unlike prior works, which primarily focus on independent and identically distributed (i.i.d.) disturbances and provide only asymptotic guarantees for system learning, this study presents the first finite-time analysis of nonlinear dynamical systems under a highly general disturbance model. Our framework allows for possible temporal correlations in the disturbances and accommodates semi-oblivious adversarial attacks, significantly broadening the scope of existing theoretical results.
Authors: Konstantinos Skianis, John Pavlopoulos, A. Seza Do\u{g}ru\"oz
Abstract: Large Language Models (LLMs) are increasingly being integrated into various medical fields, including mental health support systems. However, there is a gap in research regarding the effectiveness of LLMs in non-English mental health support applications. To address this problem, we present a novel multilingual adaptation of widely-used mental health datasets, translated from English into six languages (e.g., Greek, Turkish, French, Portuguese, German, and Finnish). This dataset enables a comprehensive evaluation of LLM performance in detecting mental health conditions and assessing their severity across multiple languages. By experimenting with GPT and Llama, we observe considerable variability in performance across languages, despite being evaluated on the same translated dataset. This inconsistency underscores the complexities inherent in multilingual mental health support, where language-specific nuances and mental health data coverage can affect the accuracy of the models. Through comprehensive error analysis, we emphasize the risks of relying exclusively on LLMs in medical settings (e.g., their potential to contribute to misdiagnoses). Moreover, our proposed approach offers significant cost savings for multilingual tasks, presenting a major advantage for broad-scale implementation.
Authors: Tomohisa Okazaki
Abstract: Scientific machine learning (SciML) is an interdisciplinary research field that integrates machine learning, particularly deep learning, with physics theory to understand and predict complex natural phenomena. By incorporating physical knowledge, SciML reduces the dependency on observational data, which is often limited in the natural sciences. In this article, the fundamental concepts of SciML, its applications in seismology, and prospects are described. Specifically, two popular methods are mainly discussed: physics-informed neural networks (PINNs) and neural operators (NOs). PINNs can address both forward and inverse problems by incorporating governing laws into the loss functions. The use of PINNs is expanding into areas such as simultaneous solutions of differential equations, inference in underdetermined systems, and regularization based on physics. These research directions would broaden the scope of deep learning in natural sciences. NOs are models designed for operator learning, which deals with relationships between infinite-dimensional spaces. NOs show promise in modeling the time evolution of complex systems based on observational or simulation data. Since large amounts of data are often required, combining NOs with physics-informed learning holds significant potential. Finally, SciML is considered from a broader perspective beyond deep learning: statistical (or mathematical) frameworks that integrate observational data with physical principles to model natural phenomena. In seismology, mathematically rigorous Bayesian statistics has been developed over the past decades, whereas more flexible and scalable deep learning has only emerged recently. Both approaches can be considered as part of SciML in a broad sense. Theoretical and practical insights in both directions would advance SciML methodologies and thereby deepen our understanding of earthquake phenomena.
Authors: Disha Hegde, Mohamed Adil, Jon Cockayne
Abstract: Gaussian processes are notorious for scaling cubically with the size of the training set, preventing application to very large regression problems. Computation-aware Gaussian processes (CAGPs) tackle this scaling issue by exploiting probabilistic linear solvers to reduce complexity, widening the posterior with additional computational uncertainty due to reduced computation. However, the most commonly used CAGP framework results in (sometimes dramatically) conservative uncertainty quantification, making the posterior unrealistic in practice. In this work, we prove that if the utilised probabilistic linear solver is calibrated, in a rigorous statistical sense, then so too is the induced CAGP. We thus propose a new CAGP framework, CAGP-GS, based on using Gauss-Seidel iterations for the underlying probabilistic linear solver. CAGP-GS performs favourably compared to existing approaches when the test set is low-dimensional and few iterations are performed. We test the calibratedness on a synthetic problem, and compare the performance to existing approaches on a large-scale global temperature regression problem.
Authors: Shiyue Zhang, Ziheng Cheng, Cheng Zhang
Abstract: Particle-based variational inference methods (ParVIs) use nonparametric variational families represented by particles to approximate the target distribution according to the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence. Although functional gradient flows have been introduced to expand the kernel space for better flexibility, the deterministic updating mechanism may limit exploration and require expensive repetitive runs for new samples. In this paper, we propose Semi-Implicit Functional Gradient flow (SIFG), a functional gradient ParVI method that uses perturbed particles with Gaussian noise as the approximation family. We show that the corresponding functional gradient flow, which can be estimated via denoising score matching with neural networks, exhibits strong theoretical convergence guarantees due to a higher-order smoothness brought to the approximation family via Gaussian perturbation. In addition, we present an adaptive version of our method that automatically selects the appropriate noise magnitude during sampling, striking a good balance between exploration efficiency and approximation accuracy. Extensive experiments on both simulated and real-world datasets demonstrate the effectiveness and efficiency of the proposed framework.
Authors: Constantin Ulrich, Tassilo Wald, Emily Tempus, Maximilian Rokuss, Paul F. Jaeger, Klaus Maier-Hein
Abstract: Effortless and precise segmentation with minimal clinician effort could greatly streamline clinical workflows. Recent interactive segmentation models, inspired by METAs Segment Anything, have made significant progress but face critical limitations in 3D radiology. These include impractical human interaction requirements such as slice-by-slice operations for 2D models on 3D data and a lack of iterative refinement. Prior studies have been hindered by inadequate evaluation protocols, resulting in unreliable performance assessments and inconsistent findings across studies. The RadioActive benchmark addresses these challenges by providing a rigorous and reproducible evaluation framework for interactive segmentation methods in clinically relevant scenarios. It features diverse datasets, a wide range of target structures, and the most impactful 2D and 3D interactive segmentation methods, all within a flexible and extensible codebase. We also introduce advanced prompting techniques that reduce interaction steps, enabling fair comparisons between 2D and 3D models. Surprisingly, SAM2 outperforms all specialized medical 2D and 3D models in a setting requiring only a few interactions to generate prompts for a 3D volume. This challenges prevailing assumptions and demonstrates that general-purpose models surpass specialized medical approaches. By open-sourcing RadioActive, we invite researchers to integrate their models and prompting techniques, ensuring continuous and transparent evaluation of 3D medical interactive models.
Authors: Stein Stroobants, Christophe de Wagter, Guido C. H. E. De Croon
Abstract: The real-world application of small drones is mostly hampered by energy limitations. Neuromorphic computing promises extremely energy-efficient AI for autonomous flight but is still challenging to train and deploy on real robots. To reap the maximal benefits from neuromorphic computing, it is necessary to perform all autonomy functions end-to-end on a single neuromorphic chip, from low-level attitude control to high-level navigation. This research presents the first neuromorphic control system using a spiking neural network (SNN) to effectively map a drone's raw sensory input directly to motor commands. We apply this method to low-level attitude estimation and control for a quadrotor, deploying the SNN on a tiny Crazyflie. We propose a modular SNN, separately training and then merging estimation and control sub-networks. The SNN is trained with imitation learning, using a flight dataset of sensory-motor pairs. Post-training, the network is deployed on the Crazyflie, issuing control commands from sensor inputs at 500Hz. Furthermore, for the training procedure we augmented training data by flying a controller with additional excitation and time-shifting the target data to enhance the predictive capabilities of the SNN. On the real drone, the perception-to-control SNN tracks attitude commands with an average error of 3.0 degrees, compared to 2.7 degrees for the regular flight stack. We also show the benefits of the proposed learning modifications for reducing the average tracking error and reducing oscillations. Our work shows the feasibility of performing neuromorphic end-to-end control, laying the basis for highly energy-efficient and low-latency neuromorphic autopilots.
Authors: Wenxuan Huang, Zijie Zhai, Yunhang Shen, Shaosheng Cao, Fei Zhao, Xiangfeng Xu, Zheyu Ye, Yao Hu, Shaohui Lin
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Authors: Yi Chen, Yuying Ge, Weiliang Tang, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu
Abstract: Recent developments in Large Language Models pre-trained on extensive corpora have shown significant success in various natural language processing tasks with minimal fine-tuning. This success offers new promise for robotics, which has long been constrained by the high cost of action-labeled data. We ask: given the abundant video data containing interaction-related knowledge available as a rich "corpus", can a similar generative pre-training approach be effectively applied to enhance robot learning? The key challenge is to identify an effective representation for autoregressive pre-training that benefits robot manipulation tasks. Inspired by the way humans learn new skills through observing dynamic environments, we propose that effective robotic learning should emphasize motion-related knowledge, which is closely tied to low-level actions and is hardware-agnostic, facilitating the transfer of learned motions to actual robot actions. To this end, we introduce Moto, which converts video content into latent Motion Token sequences by a Latent Motion Tokenizer, learning a bridging "language" of motion from videos in an unsupervised manner. We pre-train Moto-GPT through motion token autoregression, enabling it to capture diverse visual motion knowledge. After pre-training, Moto-GPT demonstrates the promising ability to produce semantically interpretable motion tokens, predict plausible motion trajectories, and assess trajectory rationality through output likelihood. To transfer learned motion priors to real robot actions, we implement a co-fine-tuning strategy that seamlessly bridges latent motion token prediction and real robot control. Extensive experiments show that the fine-tuned Moto-GPT exhibits superior robustness and efficiency on robot manipulation benchmarks, underscoring its effectiveness in transferring knowledge from video data to downstream visual manipulation tasks.
Authors: Enshen Zhou, Qi Su, Cheng Chi, Zhizheng Zhang, Zhongyuan Wang, Tiejun Huang, Lu Sheng, He Wang
Abstract: Automatic detection and prevention of open-set failures are crucial in closed-loop robotic systems. Recent studies often struggle to simultaneously identify unexpected failures reactively after they occur and prevent foreseeable ones proactively. To this end, we propose Code-as-Monitor (CaM), a novel paradigm leveraging the vision-language model (VLM) for both open-set reactive and proactive failure detection. The core of our method is to formulate both tasks as a unified set of spatio-temporal constraint satisfaction problems and use VLM-generated code to evaluate them for real-time monitoring. To enhance the accuracy and efficiency of monitoring, we further introduce constraint elements that abstract constraint-related entities or their parts into compact geometric elements. This approach offers greater generality, simplifies tracking, and facilitates constraint-aware visual programming by leveraging these elements as visual prompts. Experiments show that CaM achieves a 28.7% higher success rate and reduces execution time by 31.8% under severe disturbances compared to baselines across three simulators and a real-world setting. Moreover, CaM can be integrated with open-loop control policies to form closed-loop systems, enabling long-horizon tasks in cluttered scenes with dynamic environments.
Authors: Chaozheng Wen, Jingwen Tong, Yingdong Hu, Zehong Lin, Jun Zhang
Abstract: Wireless channel modeling plays a pivotal role in designing, analyzing, and optimizing wireless communication systems. Nevertheless, developing an effective channel modeling approach has been a long-standing challenge. This issue has been escalated due to denser network deployment, larger antenna arrays, and broader bandwidth in next-generation networks. To address this challenge, we put forth WRF-GS, a novel framework for channel modeling based on wireless radiation field (WRF) reconstruction using 3D Gaussian splatting (3D-GS). WRF-GS employs 3D Gaussian primitives and neural networks to capture the interactions between the environment and radio signals, enabling efficient WRF reconstruction and visualization of the propagation characteristics. The reconstructed WRF can then be used to synthesize the spatial spectrum for comprehensive wireless channel characterization. While WRF-GS demonstrates remarkable effectiveness, it faces limitations in capturing high-frequency signal variations caused by complex multipath effects. To overcome these limitations, we propose WRF-GS+, an enhanced framework that integrates electromagnetic wave physics into the neural network design. WRF-GS+ leverages deformable 3D Gaussians to model both static and dynamic components of the WRF, significantly improving its ability to characterize signal variations. In addition, WRF-GS+ enhances the splatting process by simplifying the 3D-GS modeling process and improving computational efficiency. Experimental results demonstrate that both WRF-GS and WRF-GS+ outperform baselines for spatial spectrum synthesis, including ray tracing and other deep-learning approaches. Notably, WRF-GS+ achieves state-of-the-art performance in the received signal strength indication (RSSI) and channel state information (CSI) prediction tasks, surpassing existing methods by more than 0.7 dB and 3.36 dB, respectively.
Authors: Hyesu Lim, Jinho Choi, Jaegul Choo, Steffen Schneider
Abstract: Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new Sparse Autoencoder (SAE) for the CLIP vision transformer, named PatchSAE, to extract interpretable concepts at granular levels (e.g., shape, color, or semantics of an object) and their patch-wise spatial attributions. We explore how these concepts influence the model output in downstream image classification tasks and investigate how recent state-of-the-art prompt-based adaptation techniques change the association of model inputs to these concepts. While activations of concepts slightly change between adapted and non-adapted models, we find that the majority of gains on common adaptation tasks can be explained with the existing concepts already present in the non-adapted foundation model. This work provides a concrete framework to train and use SAEs for Vision Transformers and provides insights into explaining adaptation mechanisms.
Authors: Jan Rathjens, Shirin Reyhanian, David Kappel, Laurenz Wiskott
Abstract: Understanding the mechanisms underlying deep neural networks in computer vision remains a fundamental challenge. While many previous approaches have focused on visualizing intermediate representations within deep neural networks, particularly convolutional neural networks, these techniques have yet to be thoroughly explored in transformer-based vision models. In this study, we apply a modular approach of training inverse models to reconstruct input images from intermediate layers within a Detection Transformer and a Vision Transformer, showing that this approach is efficient and feasible. Through qualitative and quantitative evaluations of reconstructed images, we generate insights into the underlying mechanisms of these architectures, highlighting their similarities and differences in terms of contextual shape and preservation of image details, inter-layer correlation, and robustness to color perturbations. Our analysis illustrates how these properties emerge within the models, contributing to a deeper understanding of transformer-based vision models. The code for reproducing our experiments is available at github.com/wiskott-lab/inverse-detection-transformer.
Authors: Shubham Agarwal, Gaurav Sahu, Abhay Puri, Issam H. Laradji, Krishnamurthy DJ Dvijotham, Jason Stanley, Laurent Charlin, Christopher Pal
Abstract: Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, especially due to the recent influx of research papers. This paper explores the zero-shot abilities of recent Large Language Models (LLMs) in assisting with the writing of literature reviews based on an abstract. We decompose the task into two components: 1. Retrieving related works given a query abstract, and 2. Writing a literature review based on the retrieved results. We analyze how effective LLMs are for both components. For retrieval, we introduce a novel two-step search strategy that first uses an LLM to extract meaningful keywords from the abstract of a paper and then retrieves potentially relevant papers by querying an external knowledge base. Additionally, we study a prompting-based re-ranking mechanism with attribution and show that re-ranking doubles the normalized recall compared to naive search methods, while providing insights into the LLM's decision-making process. In the generation phase, we propose a two-step approach that first outlines a plan for the review and then executes steps in the plan to generate the actual review. To evaluate different LLM-based literature review methods, we create test sets from arXiv papers using a protocol designed for rolling use with newly released LLMs to avoid test set contamination in zero-shot evaluations. We release this evaluation protocol to promote additional research and development in this regard. Our empirical results suggest that LLMs show promising potential for writing literature reviews when the task is decomposed into smaller components of retrieval and planning. Our project page including a demonstration system and toolkit can be accessed here: https://litllm.github.io.
Authors: JunEn Low, Maximilian Adang, Javier Yu, Keiko Nagami, Mac Schwager
Abstract: We propose a new simulator, training approach, and policy architecture, collectively called SOUS VIDE, for end-to-end visual drone navigation. Our trained policies exhibit zero-shot sim-to-real transfer with robust real-world performance using only onboard perception and computation. Our simulator, called FiGS, couples a computationally simple drone dynamics model with a high visual fidelity Gaussian Splatting scene reconstruction. FiGS can quickly simulate drone flights producing photorealistic images at up to 130 fps. We use FiGS to collect 100k-300k image/state-action pairs from an expert MPC with privileged state and dynamics information, randomized over dynamics parameters and spatial disturbances. We then distill this expert MPC into an end-to-end visuomotor policy with a lightweight neural architecture, called SV-Net. SV-Net processes color image, optical flow and IMU data streams into low-level thrust and body rate commands at 20 Hz onboard a drone. Crucially, SV-Net includes a learned module for low-level control that adapts at runtime to variations in drone dynamics. In a campaign of 105 hardware experiments, we show SOUS VIDE policies to be robust to 30% mass variations, 40 m/s wind gusts, 60% changes in ambient brightness, shifting or removing objects from the scene, and people moving aggressively through the drone's visual field. Code, data, and experiment videos can be found on our project page: https://stanfordmsl.github.io/SousVide/.
Authors: Mengfan Wu, Shenshen Yan, Jie Ren
Abstract: Data-driven machine learning (ML) has demonstrated tremendous potential in material property predictions. However, the scarcity of materials data with costly property labels in the vast chemical space presents a significant challenge for ML in efficiently predicting properties and uncovering structure-property relationships. Here, we propose a novel hierarchy-boosted funnel learning (HiBoFL) framework, which is successfully applied to identify semiconductors with ultralow lattice thermal conductivity ($\kappa_\mathrm{L}$). By training on only a few hundred materials targeted by unsupervised learning from a pool of hundreds of thousands, we achieve efficient and interpretable supervised predictions of ultralow $\kappa_\mathrm{L}$, thereby circumventing large-scale brute-force \textit{ab initio} calculations without clear objectives. As a result, we provide a list of candidates with ultralow $\kappa_\mathrm{L}$ for potential thermoelectric applications and discover a new factor that significantly influences structural anharmonicity. This HiBoFL framework offers a novel practical pathway for accelerating the discovery of functional materials.
Authors: R\'obert Busa-Fekete, Julian Zimmert, Andr\'as Gy\"orgy, Linhai Qiu, Tzu-Wei Sung, Hao Shen, Hyomin Choi, Sharmila Subramaniam, Li Xiao
Abstract: Web refresh crawling is the problem of keeping a cache of web pages fresh, that is, having the most recent copy available when a page is requested, given a limited bandwidth available to the crawler. Under the assumption that the change and request events, resp., to each web page follow independent Poisson processes, the optimal scheduling policy was derived by Azar et al. 2018. In this paper, we study an extension of this problem where side information indicating content changes, such as various types of web pings, for example, signals from sitemaps, content delivery networks, etc., is available. Incorporating such side information into the crawling policy is challenging, because (i) the signals can be noisy with false positive events and with missing change events; and (ii) the crawler should achieve a fair performance over web pages regardless of the quality of the side information, which might differ from web page to web page. We propose a scalable crawling algorithm which (i) uses the noisy side information in an optimal way under mild assumptions; (ii) can be deployed without heavy centralized computation; (iii) is able to crawl web pages at a constant total rate without spikes in the total bandwidth usage over any time interval, and automatically adapt to the new optimal solution when the total bandwidth changes without centralized computation. Experiments clearly demonstrate the versatility of our approach.
Authors: David Johnston, Nora Belrose
Abstract: Prior work has found that transformers have an inconsistent ability to learn to answer latent two-hop questions -- questions of the form "Who is Bob's mother's boss?" We study why this is the case by examining how transformers' capacity to learn datasets of two-hop questions and answers (two-hop QA) scales with their size, motivated by prior work on transformer knowledge capacity for simple factual memorization. We find that capacity scaling and generalization both support the hypothesis that latent two-hop QA requires transformers to learn each fact twice, while two-hop QA with chain of thought does not. We also show that with appropriate dataset parameters, it is possible to "trap" very small models in a regime where they memorize answers to two-hop questions independently, even though they would perform better if they could learn to answer them with function composition. Our findings show that measurement of capacity scaling can complement existing interpretability methods, though there are challenges in using it for this purpose.
Authors: Annabelle Michael Carrell, Albert Gong, Abhishek Shetty, Raaz Dwivedi, Lester Mackey
Abstract: The goal in thinning is to summarize a dataset using a small set of representative points. Remarkably, sub-Gaussian thinning algorithms like Kernel Halving and Compress can match the quality of uniform subsampling while substantially reducing the number of summary points. However, existing guarantees cover only a restricted range of distributions and kernel-based quality measures and suffer from pessimistic dimension dependence. To address these deficiencies, we introduce a new low-rank analysis of sub-Gaussian thinning that applies to any distribution and any kernel, guaranteeing high-quality compression whenever the kernel or data matrix is approximately low-rank. To demonstrate the broad applicability of the techniques, we design practical sub-Gaussian thinning approaches that improve upon the best known guarantees for approximating attention in transformers, accelerating stochastic gradient training through reordering, and distinguishing distributions in near-linear time.
Authors: Po-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu
Abstract: Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert demonstration data. Inspired by MuZero, which learns superhuman heuristics without any human knowledge, we propose a novel approach, named OptionZero. OptionZero incorporates an option network into MuZero, providing autonomous discovery of options through self-play games. Furthermore, we modify the dynamics network to provide environment transitions when using options, allowing searching deeper under the same simulation constraints. Empirical experiments conducted in 26 Atari games demonstrate that OptionZero outperforms MuZero, achieving a 131.58% improvement in mean human-normalized score. Our behavior analysis shows that OptionZero not only learns options but also acquires strategic skills tailored to different game characteristics. Our findings show promising directions for discovering and using options in planning. Our code is available at https://rlg.iis.sinica.edu.tw/papers/optionzero.
Authors: Chun Jung Chen, Chung-Chin Shih, Ti-Rong Wu
Abstract: Strength estimation and adjustment are crucial in designing human-AI interactions, particularly in games where AI surpasses human players. This paper introduces a novel strength system, including a strength estimator (SE) and an SE-based Monte Carlo tree search, denoted as SE-MCTS, which predicts strengths from games and offers different playing strengths with human styles. The strength estimator calculates strength scores and predicts ranks from games without direct human interaction. SE-MCTS utilizes the strength scores in a Monte Carlo tree search to adjust playing strength and style. We first conduct experiments in Go, a challenging board game with a wide range of ranks. Our strength estimator significantly achieves over 80% accuracy in predicting ranks by observing 15 games only, whereas the previous method reached 49% accuracy for 100 games. For strength adjustment, SE-MCTS successfully adjusts to designated ranks while achieving a 51.33% accuracy in aligning to human actions, outperforming a previous state-of-the-art, with only 42.56% accuracy. To demonstrate the generality of our strength system, we further apply SE and SE-MCTS to chess and obtain consistent results. These results show a promising approach to strength estimation and adjustment, enhancing human-AI interactions in games. Our code is available at https://rlg.iis.sinica.edu.tw/papers/strength-estimator.
URLs: https://rlg.iis.sinica.edu.tw/papers/strength-estimator.
Authors: Aarush Sinha, OM Kumar CU
Abstract: Language Models (LMs) and Graph Neural Networks (GNNs) have shown great promise in their respective areas, yet integrating structured graph data with rich textual information remains challenging. In this work, we propose \emph{Graph Masked Language Models} (GMLM), a novel dual-branch architecture that combines the structural learning of GNNs with the contextual power of pretrained language models. Our approach introduces two key innovations: (i) a \emph{semantic masking strategy} that leverages graph topology to selectively mask nodes based on their structural importance, and (ii) a \emph{soft masking mechanism} that interpolates between original node features and a learnable mask token, ensuring smoother information flow during training. Extensive experiments on multiple node classification and language understanding benchmarks demonstrate that GMLM not only achieves state-of-the-art performance but also exhibits enhanced robustness and stability. This work underscores the benefits of integrating structured and unstructured data representations for improved graph learning.
Authors: Micha\"el Fanuel, R\'emi Bardenet
Abstract: Given an $n\times r$ matrix $X$ of rank $r$, consider the problem of sampling $r$ integers $\mathtt{C}\subset \{1, \dots, n\}$ with probability proportional to the squared determinant of the rows of $X$ indexed by $\mathtt{C}$. The distribution of $\mathtt{C}$ is called a projection determinantal point process (DPP). The vanilla classical algorithm to sample a DPP works in two steps, an orthogonalization in $\mathcal{O}(nr^2)$ and a sampling step of the same cost. The bottleneck of recent quantum approaches to DPP sampling remains that preliminary orthogonalization step. For instance, (Kerenidis and Prakash, 2022) proposed an algorithm with the same $\mathcal{O}(nr^2)$ orthogonalization, followed by a $\mathcal{O}(nr)$ classical step to find the gates in a quantum circuit. The classical $\mathcal{O}(nr^2)$ orthogonalization thus still dominates the cost. Our first contribution is to reduce preprocessing to normalizing the columns of $X$, obtaining $\mathsf{X}$ in $\mathcal{O}(nr)$ classical operations. We show that a simple circuit inspired by the formalism of Kerenidis et al., 2022 samples a DPP of a type we had never encountered in applications, which is different from our target DPP. Plugging this circuit into a rejection sampling routine, we recover our target DPP after an expected $1/\det \mathsf{X}^\top\mathsf{X} = 1/a$ preparations of the quantum circuit. Using amplitude amplification, our second contribution is to boost the acceptance probability from $a$ to $1-a$ at the price of a circuit depth of $\mathcal{O}(r\log n/\sqrt{a})$ and $\mathcal{O}(\log n)$ extra qubits. Prepending a fast, sketching-based classical approximation of $a$, we obtain a pipeline to sample a projection DPP on a quantum computer, where the former $\mathcal{O}(nr^2)$ preprocessing bottleneck has been replaced by the $\mathcal{O}(nr)$ cost of normalizing the columns and the cost of our approximation of $a$.
Authors: Jaa-Yeon Lee, Byunghee Cha, Jeongsol Kim, Jong Chul Ye
Abstract: While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains. Although many approaches have attempted to address this issue by fine-tuning models using various reward models, etc., we revisit the challenge from the perspective of representation alignment-an approach that has gained popularity with the success of REPresentation Alignment (REPA). We first argue that conventional text-to-image (T2I) diffusion models, typically trained on paired image and text data (i.e., positive pairs) by minimizing score matching or flow matching losses, is suboptimal from the standpoint of representation alignment. Instead, a better alignment can be achieved through contrastive learning that leverages both positive and negative pairs. To achieve this efficiently even with pretrained models, we introduce a lightweight contrastive fine tuning strategy called SoftREPA that uses soft text tokens. This approach improves alignment with minimal computational overhead by adding fewer than 1M trainable parameters to the pretrained model. Our theoretical analysis demonstrates that our method explicitly increases the mutual information between text and image representations, leading to enhanced semantic consistency. Experimental results across text-to-image generation and text-guided image editing tasks validate the effectiveness of our approach in improving the semantic consistency of T2I generative models.
Authors: Alberto Coffrini, Mohammad Amin Zadenoori, Paolo Barsocchi, Francesco Furfari, Antonino Crivello, Alessio Ferrari
Abstract: Indoor navigation presents unique challenges due to complex layouts, lack of GPS signals, and accessibility concerns. Existing solutions often struggle with real-time adaptability and user-specific needs. In this work, we explore the potential of a Large Language Model (LLM), i.e., ChatGPT, to generate natural, context-aware navigation instructions from indoor map images. We design and evaluate test cases across different real-world environments, analyzing the effectiveness of LLMs in interpreting spatial layouts, handling user constraints, and planning efficient routes. Our findings demonstrate the potential of LLMs for supporting personalized indoor navigation, with an average of 52% correct indications and a maximum of 62%. The results do not appear to depend on the complexity of the layout or the complexity of the expected path, but rather on the number of points of interest and the abundance of visual information, which negatively affect the performance.
Authors: Brian Cho, Ana-Roxana Pop, Ariel Evnine, Nathan Kallus
Abstract: To design effective digital interventions, experimenters face the challenge of learning decision policies that balance multiple objectives using offline data. Often, they aim to develop policies that maximize goal outcomes, while ensuring there are no undesirable changes in guardrail outcomes. To provide credible recommendations, experimenters must not only identify policies that satisfy the desired changes in goal and guardrail outcomes, but also offer probabilistic guarantees about the changes these policies induce. In practice, however, policy classes are often large, and digital experiments tend to produce datasets with small effect sizes relative to noise. In this setting, standard approaches such as data splitting or multiple testing often result in unstable policy selection and/or insufficient statistical power. In this paper, we provide safe noisy policy learning (SNPL), a novel approach that leverages the concept of algorithmic stability to address these challenges. Our method enables policy learning while simultaneously providing high-confidence guarantees using the entire dataset, avoiding the need for data-splitting. We present finite-sample and asymptotic versions of our algorithm that ensure the recommended policy satisfies high-probability guarantees for avoiding guardrail regressions and/or achieving goal outcome improvements. We test both variants of our approach approach empirically on a real-world application of personalizing SMS delivery. Our results on real-world data suggest that our approach offers dramatic improvements in settings with large policy classes and low signal-to-noise across both finite-sample and asymptotic safety guarantees, offering up to 300\% improvements in detection rates and 150\% improvements in policy gains at significantly smaller sample sizes.
Authors: Tianyang Wang, Yichao Zhang, Ningyuan Deng, Xinyuan Song, Ziqian Bi, Zheyu Yao, Keyu Chen, Ming Li, Qian Niu, Junyu Liu, Benji Peng, Sen Zhang, Ming Liu, Li Zhang, Xuanhe Pan, Jinlang Wang, Pohsun Feng, Yizhu Wen, Lawrence KQ Yan, Hongming Tseng, Yan Zhong, Yunze Wang, Ziyuan Qin, Bowen Jing, Junjie Yang, Jun Zhou, Chia Xin Liang, Junhao Song
Abstract: After AlphaFold won the Nobel Prize, protein prediction with deep learning once again became a hot topic. We comprehensively explore advanced deep learning methods applied to protein structure prediction and design. It begins by examining recent innovations in prediction architectures, with detailed discussions on improvements such as diffusion based frameworks and novel pairwise attention modules. The text analyses key components including structure generation, evaluation metrics, multiple sequence alignment processing, and network architecture, thereby illustrating the current state of the art in computational protein modelling. Subsequent chapters focus on practical applications, presenting case studies that range from individual protein predictions to complex biomolecular interactions. Strategies for enhancing prediction accuracy and integrating deep learning techniques with experimental validation are thoroughly explored. The later sections review the industry landscape of protein design, highlighting the transformative role of artificial intelligence in biotechnology and discussing emerging market trends and future challenges. Supplementary appendices provide essential resources such as databases and open source tools, making this volume a valuable reference for researchers and students.
Authors: Jingyuan Xue, Longfei Wei, Fang Sheng, Yuxin Gao, Jianfei Zhang
Abstract: The accurate prediction of RUL for lithium-ion batteries is crucial for enhancing the reliability and longevity of energy storage systems. Traditional methods for RUL prediction often struggle with issues such as data sparsity, varying battery chemistries, and the inability to capture complex degradation patterns over time. In this study, we propose a survival analysis-based framework combined with deep learning models to predict the RUL of lithium-ion batteries. Specifically, we utilize five advanced models: the Cox-type models (Cox, CoxPH, and CoxTime) and two machine-learning-based models (DeepHit and MTLR). These models address the challenges of accurate RUL estimation by transforming raw time-series battery data into survival data, including key degradation indicators such as voltage, current, and internal resistance. Advanced feature extraction techniques enhance the model's robustness in diverse real-world scenarios, including varying charging conditions and battery chemistries. Our models are tested using 10-fold cross-validation, ensuring generalizability and minimizing overfitting. Experimental results show that our survival-based framework significantly improves RUL prediction accuracy compared to traditional methods, providing a reliable tool for battery management and maintenance optimization. This study contributes to the advancement of predictive maintenance in battery technology, offering valuable insights for both researchers and industry practitioners aiming to enhance the operational lifespan of lithium-ion batteries.
Authors: Hui Liu, Wenya Wang, Kecheng Chen, Jie Liu, Yibing Liu, Tiexin Qin, Peisong He, Xinghao Jiang, Haoliang Li
Abstract: In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-language models (VLMs), despite achieving significant progress through large-scale natural language supervision, often underperform in real-world applications because of sub-optimal prompt engineering and the inability to adapt effectively to target classes. To address these issues, we propose a Concept-guided Human-like Bayesian Reasoning (CHBR) framework. Grounded in Bayes' theorem, CHBR models the concept used in human image recognition as latent variables and formulates this task by summing across potential concepts, weighted by a prior distribution and a likelihood function. To tackle the intractable computation over an infinite concept space, we introduce an importance sampling algorithm that iteratively prompts large language models (LLMs) to generate discriminative concepts, emphasizing inter-class differences. We further propose three heuristic approaches involving Average Likelihood, Confidence Likelihood, and Test Time Augmentation (TTA) Likelihood, which dynamically refine the combination of concepts based on the test image. Extensive evaluations across fifteen datasets demonstrate that CHBR consistently outperforms existing state-of-the-art zero-shot generalization methods.