Authors: Maksym Shamrai
Abstract: Concatenating matrices is a common technique for uncovering shared structures in data through singular value decomposition (SVD) and low-rank approximations. However, a fundamental question arises: how does the singular value spectrum of the concatenated matrix relate to the spectra of its individual components? In this work, we develop a perturbation framework that extends classical results such as Weyl's inequality to concatenated matrices. We establish analytical bounds that quantify the stability of singular values under small perturbations in the submatrices. Our results show that if the matrices being concatenated are close in norm, the dominant singular values of the concatenated matrix remain stable, enabling controlled trade-offs between accuracy and compression. These insights provide a theoretical foundation for improved matrix clustering and compression strategies, with applications in numerical linear algebra, signal processing, and data-driven modeling.
Authors: Hassan Wasswa, Timothy Lynar, Hussein Abbass
Abstract: The Internet of Things (IoT) technology has rapidly gained popularity with applications widespread across a variety of industries. However, IoT devices have been recently serving as a porous layer for many malicious attacks to both personal and enterprise information systems with the most famous attacks being botnet-related attacks. The work in this study leveraged Variational Auto-encoder (VAE) and cost-sensitive learning to develop lightweight, yet effective, models for IoT-botnet detection. The aim is to enhance the detection of minority class attack traffic instances which are often missed by machine learning models. The proposed approach is evaluated on a multi-class problem setting for the detection of traffic categories on highly imbalanced datasets. The performance of two deep learning models including the standard feed forward deep neural network (DNN), and Bidirectional-LSTM (BLSTM) was evaluated and both recorded commendable results in terms of accuracy, precision, recall and F1-score for all traffic classes.
Authors: Tengfei Xing, Xiaodan Ren, Jie Li
Abstract: Material stress analysis is a critical aspect of material design and performance optimization. Under dynamic loading, the global stress evolution in materials exhibits complex spatiotemporal characteristics, especially in two-phase random materials (TRMs). Such kind of material failure is often associated with stress concentration, and the phase boundaries are key locations where stress concentration occurs. In practical engineering applications, the spatiotemporal resolution of acquired microstructural data and its dynamic stress evolution is often limited. This poses challenges for deep learning methods in generating high-resolution spatiotemporal stress fields, particularly for accurately capturing stress concentration regions. In this study, we propose a framework for global stress generation and spatiotemporal super-resolution in TRMs under dynamic loading. First, we introduce a diffusion model-based approach, named as Spatiotemporal Stress Diffusion (STS-diffusion), for generating global spatiotemporal stress data. This framework incorporates Space-Time U-Net (STU-net), and we systematically investigate the impact of different attention positions on model accuracy. Next, we develop a physics-informed network for spatiotemporal super-resolution, termed as Spatiotemporal Super-Resolution Physics-Informed Operator (ST-SRPINN). The proposed ST-SRPINN is an unsupervised learning method. The influence of data-driven and physics-informed loss function weights on model accuracy is explored in detail. Benefiting from physics-based constraints, ST-SRPINN requires only low-resolution stress field data during training and can upscale the spatiotemporal resolution of stress fields to arbitrary magnifications.
Authors: Alkis Sygkounas, Ioannis Athanasiadis, Andreas Persson, Michael Felsberg, Amy Loutfi
Abstract: Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL) approach that enhances Reinforcement Learning (RL) by merging human insights directly into the RL training process, improving model performance. Our proposed iDDQN method modifies the Q-value update equation to integrate human and agent actions, establishing a collaborative approach for policy development. Additionally, we present an offline evaluative framework that simulates the agent's trajectory as if no human intervention had occurred, to assess the effectiveness of human interventions. Empirical results in simulated autonomous driving scenarios demonstrate that iDDQN outperforms established approaches, including Behavioral Cloning (BC), HG-DAgger, Deep Q-Learning from Demonstrations (DQfD), and vanilla DRL in leveraging human expertise for improving performance and adaptability.
Authors: Muhammad Muaz, Sameed Sajid, Tobias Schulze, Chang Liu, Nils Klasen, Benny Drescher
Abstract: If a product deviates from its desired properties in the injection moulding process, its root cause analysis can be aided by models that relate the input machine settings with the output quality characteristics. The machine learning models tested in the quality prediction are mostly black boxes; therefore, no direct explanation of their prognosis is given, which restricts their applicability in the quality control. The previously attempted explainability methods are either restricted to tree-based algorithms only or do not emphasize on the fact that some explainability methods can lead to wrong root cause identification of a product's deviation from its desired properties. This study first shows that the interactions among the multiple input machine settings do exist in real experimental data collected as per a central composite design. Then, the model-agnostic explainable AI methods are compared for the first time to show that different explainability methods indeed lead to different feature impact analysis in injection moulding. Moreover, it is shown that the better feature attribution translates to the correct cause identification and actionable insights for the injection moulding process. Being model agnostic, explanations on both random forest and multilayer perceptron are performed for the cause analysis, as both models have the mean absolute percentage error of less than 0.05% on the experimental dataset.
Authors: Shengkai Chen, Yifang Yin, Jinming Cao, Shili Xiang, Zhenguang Liu, Roger Zimmermann
Abstract: Audio-visual segmentation aims to separate sounding objects from videos by predicting pixel-level masks based on audio signals. Existing methods primarily concentrate on closed-set scenarios and direct audio-visual alignment and fusion, which limits their capability to generalize to new, unseen situations. In this paper, we propose OpenAVS, a novel training-free language-based approach that, for the first time, effectively aligns audio and visual modalities using text as a proxy for open-vocabulary Audio-Visual Segmentation (AVS). Equipped with multimedia foundation models, OpenAVS directly infers masks through 1) audio-to-text prompt generation, 2) LLM-guided prompt translation, and 3) text-to-visual sounding object segmentation. The objective of OpenAVS is to establish a simple yet flexible architecture that relies on the most appropriate foundation models by fully leveraging their capabilities to enable more effective knowledge transfer to the downstream AVS task. Moreover, we present a model-agnostic framework OpenAVS-ST that enables the integration of OpenAVS with any advanced supervised AVS model via pseudo-label based self-training. This approach enhances performance by effectively utilizing large-scale unlabeled data when available. Comprehensive experiments on three benchmark datasets demonstrate the superior performance of OpenAVS. It surpasses existing unsupervised, zero-shot, and few-shot AVS methods by a significant margin, achieving absolute performance gains of approximately 9.4% and 10.9% in mIoU and F-score, respectively, in challenging scenarios.
Authors: Jiayu Wang, Aws Albarghouthi, Frederic Sala
Abstract: Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adaptation strategy under resource constraints is challenging and often requires extensive experimentation. We investigate whether it is possible to accurately predict both performance and cost without expensive trials. We formalize the strategy selection problem for LLMs and introduce COSMOS, a unified prediction framework that efficiently estimates adaptation outcomes at minimal cost. We instantiate and study the capability of our framework via a pair of powerful predictors: embedding-augmented lightweight proxy models to predict fine-tuning performance, and low-sample scaling laws to forecast retrieval-augmented in-context learning. Extensive evaluation across eight representative benchmarks demonstrates that COSMOS achieves high prediction accuracy while reducing computational costs by 92.72% on average, and up to 98.71% in resource-intensive scenarios. Our results show that efficient prediction of adaptation outcomes is not only feasible but can substantially reduce the computational overhead of LLM deployment while maintaining performance standards.
Authors: Chaoyi Wang, Junjie Zheng, Zihao Chen, Shiyu Xia, Chaofan Ding, Xiaohao Zhang, Xi Tao, Xiaoming He, Xinhan Di
Abstract: Movie dubbing has advanced significantly, yet assessing the real-world effectiveness of these models remains challenging. A comprehensive evaluation benchmark is crucial for two key reasons: 1) Existing metrics fail to fully capture the complexities of dialogue, narration, monologue, and actor adaptability in movie dubbing. 2) A practical evaluation system should offer valuable insights to improve movie dubbing quality and advancement in film production. To this end, we introduce Talking Adaptive Dubbing Benchmarks (TA-Dubbing), designed to improve film production by adapting to dialogue, narration, monologue, and actors in movie dubbing. TA-Dubbing offers several key advantages: 1) Comprehensive Dimensions: TA-Dubbing covers a variety of dimensions of movie dubbing, incorporating metric evaluations for both movie understanding and speech generation. 2) Versatile Benchmarking: TA-Dubbing is designed to evaluate state-of-the-art movie dubbing models and advanced multi-modal large language models. 3) Full Open-Sourcing: We fully open-source TA-Dubbing at https://github.com/woka- 0a/DeepDubber- V1 including all video suits, evaluation methods, annotations. We also continuously integrate new movie dubbing models into the TA-Dubbing leaderboard at https://github.com/woka- 0a/DeepDubber-V1 to drive forward the field of movie dubbing.
Authors: Yujing Zhou, Marc L. Jacquet, Robel Dawit, Skyler Fabre, Dev Sarawat, Faheem Khan, Madison Newell, Yongxin Liu, Dahai Liu, Hongyun Chen, Jian Wang, Huihui Wang
Abstract: The increasing automation of traffic management systems has made them prime targets for cyberattacks, disrupting urban mobility and public safety. Traditional network-layer defenses are often inaccessible to transportation agencies, necessitating a machine learning-based approach that relies solely on traffic flow data. In this study, we simulate cyberattacks in a semi-realistic environment, using a virtualized traffic network to analyze disruption patterns. We develop a deep learning-based anomaly detection system, demonstrating that Longest Stop Duration and Total Jam Distance are key indicators of compromised signals. To enhance interpretability, we apply Explainable AI (XAI) techniques, identifying critical decision factors and diagnosing misclassification errors. Our analysis reveals two primary challenges: transitional data inconsistencies, where mislabeled recovery-phase traffic misleads the model, and model limitations, where stealth attacks in low-traffic conditions evade detection. This work enhances AI-driven traffic security, improving both detection accuracy and trustworthiness in smart transportation systems.
Authors: Yujing Zhou, Marc L. Jacquet, Robel Dawit, Skyler Fabre, Dev Sarawat, Faheem Khan, Madison Newell, Yongxin Liu, Dahai Liu, Hongyun Chen, Jian Wang, Huihui Wang
Abstract: This paper presents our simulation of cyber-attacks and detection strategies on the traffic control system in Daytona Beach, FL. using Raspberry Pi virtual machines and the OPNSense firewall, along with traffic dynamics from SUMO and exploitation via the Metasploit framework. We try to answer the research questions: are we able to identify cyber attacks by only analyzing traffic flow patterns. In this research, the cyber attacks are focused particularly when lights are randomly turned all green or red at busy intersections by adversarial attackers. Despite challenges stemming from imbalanced data and overlapping traffic patterns, our best model shows 85\% accuracy when detecting intrusions purely using traffic flow statistics. Key indicators for successful detection included occupancy, jam length, and halting durations.
Authors: Madhav Kotecha, Vijendra Kumar Vaishya, Smita Gautam, Suraj Racha
Abstract: We propose a refined approach to efficiently fine-tune large language models (LLMs) on specific domains like the mathematical domain by employing a budgeted subset selection method. Our approach combines utility and diversity metrics to select the most informative and representative training examples. The final goal is to achieve near-full dataset performance with meticulously selected data points from the entire dataset while significantly reducing computational cost and training time and achieving competitive performance as the full dataset. The utility metric incorporates both perplexity and Chain-of-Thought (CoT) loss to identify challenging examples that contribute most to model learning, while the diversity metric ensures broad coverage across mathematical subdomains. We evaluate our method on LLaMA-3 8B and Phi-3 models, comparing against several baseline approaches, including random selection, diversity-based sampling, and existing state-of-the-art subset selection techniques.
Authors: Runtian Zhai, Kai Yang, Che-Ping Tsai, Burak Varici, Zico Kolter, Pradeep Ravikumar
Abstract: Despite the empirical success of foundation models, we do not have a systematic characterization of the representations that these models learn. In this paper, we establish the contexture theory. It shows that a large class of representation learning methods can be characterized as learning from the association between the input and a context variable. Specifically, we show that many popular methods aim to approximate the top-d singular functions of the expectation operator induced by the context, in which case we say that the representation learns the contexture. We demonstrate the generality of the contexture theory by proving that representation learning within various learning paradigms -- supervised, self-supervised, and manifold learning -- can all be studied from such a perspective. We also prove that the representations that learn the contexture are optimal on those tasks that are compatible with the context. One important implication of the contexture theory is that once the model is large enough to approximate the top singular functions, further scaling up the model size yields diminishing returns. Therefore, scaling is not all we need, and further improvement requires better contexts. To this end, we study how to evaluate the usefulness of a context without knowing the downstream tasks. We propose a metric and show by experiments that it correlates well with the actual performance of the encoder on many real datasets.
Authors: Zhiqiang He, Zhi Liu
Abstract: Adapting to non-stationary network conditions presents significant challenges for resource adaptation. However, current solutions primarily rely on stationary assumptions. While data-driven reinforcement learning approaches offer promising solutions for handling network dynamics, our systematic investigation reveals a critical limitation: neural networks suffer from plasticity loss, significantly impeding their ability to adapt to evolving network conditions. Through theoretical analysis of neural propagation mechanisms, we demonstrate that existing dormant neuron metrics inadequately characterize neural plasticity loss. To address this limitation, we have developed the Silent Neuron theory, which provides a more comprehensive framework for understanding plasticity degradation. Based on these theoretical insights, we propose the Reset Silent Neuron (ReSiN), which preserves neural plasticity through strategic neuron resets guided by both forward and backward propagation states. In our implementation of an adaptive video streaming system, ReSiN has shown significant improvements over existing solutions, achieving up to 168% higher bitrate and 108% better quality of experience (QoE) while maintaining comparable smoothness. Furthermore, ReSiN consistently outperforms in stationary environments, demonstrating its robust adaptability across different network conditions.
Authors: Abdalwahab Almajed, Maryam Tabar, Peyman Najafirad
Abstract: As a basic human need, housing plays a key role in enhancing health, well-being, and educational outcome in society, and the housing market is a major factor for promoting quality of life and ensuring social equity. To improve the housing conditions, there has been extensive research on building Machine Learning (ML)-driven house price prediction solutions to accurately forecast the future conditions, and help inform actions and policies in the field. In spite of their success in developing high-accuracy models, there is a gap in our understanding of the extent to which various ML-driven house price prediction approaches show ethnic and/or racial bias, which in turn is essential for the responsible use of ML, and ensuring that the ML-driven solutions do not exacerbate inequity. To fill this gap, this paper develops several ML models from a combination of structural and neighborhood-level attributes, and conducts comprehensive assessments on the fairness of ML models under various definitions of privileged groups. As a result, it finds that the ML-driven house price prediction models show various levels of bias towards protected attributes (i.e., race and ethnicity in this study). Then, it investigates the performance of different bias mitigation solutions, and the experimental results show their various levels of effectiveness on different ML-driven methods. However, in general, the in-processing bias mitigation approach tends to be more effective than the pre-processing one in this problem domain. Our code is available at https://github.com/wahab1412/housing_fairness.
Authors: Nolan Dey, Bin Claire Zhang, Lorenzo Noci, Mufan Li, Blake Bordelon, Shane Bergsma, Cengiz Pehlevan, Boris Hanin, Joel Hestness
Abstract: We study compute efficiency of LLM training when using different parameterizations, i.e., rules for adjusting model and optimizer hyperparameters (HPs) as model size changes. Some parameterizations fail to transfer optimal base HPs (such as learning rate) across changes in model depth, requiring practitioners to either re-tune these HPs as they scale up (expensive), or accept sub-optimal training when re-tuning is prohibitive. Even when they achieve HP transfer, we develop theory to show parameterizations may still exist in the lazy learning regime where layers learn only features close to their linearization, preventing effective use of depth and nonlinearity. Finally, we identify and adopt the unique parameterization we call CompleteP that achieves both depth-wise HP transfer and non-lazy learning in all layers. CompleteP enables a wider range of model width/depth ratios to remain compute-efficient, unlocking shapes better suited for different hardware settings and operational contexts. Moreover, CompleteP enables 12-34\% compute efficiency improvements over the prior state-of-the-art.
Authors: Hanping Zhang, Yuhong Guo
Abstract: Safe Reinforcement Learning (Safe RL) aims to ensure safety when an RL agent conducts learning by interacting with real-world environments where improper actions can induce high costs or lead to severe consequences. In this paper, we propose a novel Safe Skill Planning (SSkP) approach to enhance effective safe RL by exploiting auxiliary offline demonstration data. SSkP involves a two-stage process. First, we employ PU learning to learn a skill risk predictor from the offline demonstration data. Then, based on the learned skill risk predictor, we develop a novel risk planning process to enhance online safe RL and learn a risk-averse safe policy efficiently through interactions with the online RL environment, while simultaneously adapting the skill risk predictor to the environment. We conduct experiments in several benchmark robotic simulation environments. The experimental results demonstrate that the proposed approach consistently outperforms previous state-of-the-art safe RL methods.
Authors: Fatemeh Elhambakhsh, Daniele Grandi, Hyunwoong Ko
Abstract: The conceptual design phase represents a critical early stage in the product development process, where designers generate potential solutions that meet predefined design specifications based on functional requirements. Functional modeling, a foundational aspect of this phase, enables designers to reason about product functions before specific structural details are determined. A widely adopted approach to functional modeling is the Function-Behavior-Structure (FBS) framework, which supports the transformation of functional intent into behavioral and structural descriptions. However, the effectiveness of function-based design is often hindered by the lack of well-structured and comprehensive functional data. This scarcity can negatively impact early design decision-making and hinder the development of accurate behavioral models. Recent advances in Large Language Models (LLMs), such as those based on GPT architectures, offer a promising avenue to address this gap. LLMs have demonstrated significant capabilities in language understanding and natural language processing (NLP), making them suitable for automated classification tasks. This study proposes a novel LLM-based domain adaptation (DA) framework using fine-tuning for the automated classification of mechanical assembly parts' functions. By fine-tuning LLMs on domain-specific datasets, the traditionally manual and subjective process of function annotation can be improved in both accuracy and consistency. A case study demonstrates fine-tuning GPT-3.5 Turbo on data from the Oregon State Design Repository (OSDR), and evaluation on the A Big CAD (ABC) dataset shows that the domain-adapted LLM can generate high-quality functional data, enhancing the semantic representation of mechanical parts and supporting more effective design exploration in early-phase engineering.
Authors: Yucong Dai, Lu Zhang, Yaowei Hu, Susan Gauch, Yongkai Wu
Abstract: Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes, such as race and gender. Recently, a few works have extended fairness to graph data, such as social networks, but most of them neglect the causal relationships among data instances. This paper addresses the prevalent challenge in fairness-aware ML algorithms, which typically assume Independent and Identically Distributed (IID) data. We tackle the overlooked domain of non-IID, graph-based settings where data instances are interconnected, influencing the outcomes of fairness interventions. We base our research on the Network Structural Causal Model (NSCM) framework and posit two main assumptions: Decomposability and Graph Independence, which enable the computation of interventional distributions in non-IID settings using the $do$-calculus. Based on that, we develop the Message Passing Variational Autoencoder for Causal Inference (MPVA) to compute interventional distributions and facilitate causally fair node classification through estimated interventional distributions. Empirical evaluations on semi-synthetic and real-world datasets demonstrate that MPVA outperforms conventional methods by effectively approximating interventional distributions and mitigating bias. The implications of our findings underscore the potential of causality-based fairness in complex ML applications, setting the stage for further research into relaxing the initial assumptions to enhance model fairness.
Authors: Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Linchao Zhang, Xiaochun Cao, Qingming Huang
Abstract: Real-world datasets often follow a long-tailed distribution, making generalization to tail classes difficult. Recent methods resorted to long-tail variants of Sharpness-Aware Minimization (SAM), such as ImbSAM and CC-SAM, to improve generalization by flattening the loss landscape. However, these attempts face a trade-off between computational efficiency and control over the loss landscape. On the one hand, ImbSAM is efficient but offers only coarse control as it excludes head classes from the SAM process. On the other hand, CC-SAM provides fine-grained control through class-dependent perturbations but at the cost of efficiency due to multiple backpropagations. Seeing this dilemma, we introduce Focal-SAM, which assigns different penalties to class-wise sharpness, achieving fine-grained control without extra backpropagations, thus maintaining efficiency. Furthermore, we theoretically analyze Focal-SAM's generalization ability and derive a sharper generalization bound. Extensive experiments on both traditional and foundation models validate the effectiveness of Focal-SAM.
Authors: Wensheng Li, Hao Wang, Ruifeng Zhou, Hanting Guan, Chao Zhang, Dacheng Tao
Abstract: Curriculum learning (CL) is referred to as a training strategy that makes easy samples learned first and then fits hard samples. It imitates the process of humans learning knowledge, and has become a potential manner of effectively training deep networks. In this study, we develop the adaptively point-weighting (APW) curriculum learning algorithm, which adaptively assigns the weight to every training sample not only based on its training error but also considering the current training state of the network. Specifically, in the early training phase, it increases the weights of easy samples to make the network rapidly capture the overall characteristics of the dataset; and in the later training phase, the weights of hard points rise to improve the fitting performance on the discrete local regions. Moreover, we also present the theoretical analysis on the properties of APW including training effectiveness, training feasibility, training stability, and generalization performance. The numerical experiments support the superiority of APW and demonstrate the validity of our theoretical findings.
Authors: Yize Jiang, Xinze Li, Yuanyuan Zhang, Jin Han, Youjun Xu, Ayush Pandit, Zaixi Zhang, Mengdi Wang, Mengyang Wang, Chong Liu, Guang Yang, Yejin Choi, Wu-Jun Li, Tianfan Fu, Fang Wu, Junhong Liu
Abstract: Recently, significant progress has been made in protein-ligand docking, especially in modern deep learning methods, and some benchmarks were proposed, e.g., PoseBench, Plinder. However, these benchmarks suffer from less practical evaluation setups (e.g., blind docking, self docking), or heavy framework that involves training, raising challenges to assess docking methods efficiently. To fill this gap, we proposed PoseX, an open-source benchmark focusing on self-docking and cross-docking, to evaluate the algorithmic advances practically and comprehensively. Specifically, first, we curate a new evaluation dataset with 718 entries for self docking and 1,312 for cross docking; second, we incorporate 22 docking methods across three methodological categories, including (1) traditional physics-based methods (e.g., Schr\"odinger Glide), (2) AI docking methods (e.g., DiffDock), (3) AI co-folding methods (e.g., AlphaFold3); third, we design a relaxation method as post-processing to minimize conformation energy and refine binding pose; fourth, we released a leaderboard to rank submitted models in real time. We draw some key insights via extensive experiments: (1) AI-based approaches have already surpassed traditional physics-based approaches in overall docking accuracy (RMSD). The longstanding generalization issues that have plagued AI molecular docking have been significantly alleviated in the latest models. (2) The stereochemical deficiencies of AI-based approaches can be greatly alleviated with post-processing relaxation. Combining AI docking methods with the enhanced relaxation method achieves the best performance to date. (3) AI co-folding methods commonly face ligand chirality issues, which cannot be resolved by relaxation. The code, curated dataset and leaderboard are released at https://github.com/CataAI/PoseX.
Authors: Han Wan, Rui Zhang, Qi Wang, Yang Liu, Hao Sun
Abstract: Accurately modeling and forecasting complex systems governed by partial differential equations (PDEs) is crucial in various scientific and engineering domains. However, traditional numerical methods struggle in real-world scenarios due to incomplete or unknown physical laws. Meanwhile, machine learning approaches often fail to generalize effectively when faced with scarce observational data and the challenge of capturing local and global features. To this end, we propose the Physics-encoded Spectral Attention Network (PeSANet), which integrates local and global information to forecast complex systems with limited data and incomplete physical priors. The model consists of two key components: a physics-encoded block that uses hard constraints to approximate local differential operators from limited data, and a spectral-enhanced block that captures long-range global dependencies in the frequency domain. Specifically, we introduce a novel spectral attention mechanism to model inter-spectrum relationships and learn long-range spatial features. Experimental results demonstrate that PeSANet outperforms existing methods across all metrics, particularly in long-term forecasting accuracy, providing a promising solution for simulating complex systems with limited data and incomplete physics.
Authors: Yezhen Wang, Zhouhao Yang, Brian K Chen, Fanyi Pu, Bo Li, Tianyu Gao, Kenji Kawaguchi
Abstract: Building upon the success of low-rank adapter (LoRA), low-rank gradient projection (LoRP) has emerged as a promising solution for memory-efficient fine-tuning. However, existing LoRP methods typically treat each row of the gradient matrix as the default projection unit, leaving the role of projection granularity underexplored. In this work, we propose a novel framework, VLoRP, that extends low-rank gradient projection by introducing an additional degree of freedom for controlling the trade-off between memory efficiency and performance, beyond the rank hyper-parameter. Through this framework, we systematically explore the impact of projection granularity, demonstrating that finer-grained projections lead to enhanced stability and efficiency even under a fixed memory budget. Regarding the optimization for VLoRP, we present ProjFactor, an adaptive memory-efficient optimizer, that significantly reduces memory requirement while ensuring competitive performance, even in the presence of gradient accumulation. Additionally, we provide a theoretical analysis of VLoRP, demonstrating the descent and convergence of its optimization trajectory under both SGD and ProjFactor. Extensive experiments are conducted to validate our findings, covering tasks such as commonsense reasoning, MMLU, and GSM8K.
Authors: Amirmohammad Farzaneh, Osvaldo Simeone
Abstract: Online anomaly detection is essential in fields such as cybersecurity, healthcare, and industrial monitoring, where promptly identifying deviations from expected behavior can avert critical failures or security breaches. While numerous anomaly scoring methods based on supervised or unsupervised learning have been proposed, current approaches typically rely on a continuous stream of real-world calibration data to provide assumption-free guarantees on the false discovery rate (FDR). To address the inherent challenges posed by limited real calibration data, we introduce context-aware prediction-powered conformal online anomaly detection (C-PP-COAD). Our framework strategically leverages synthetic calibration data to mitigate data scarcity, while adaptively integrating real data based on contextual cues. C-PP-COAD utilizes conformal p-values, active p-value statistics, and online FDR control mechanisms to maintain rigorous and reliable anomaly detection performance over time. Experiments conducted on both synthetic and real-world datasets demonstrate that C-PP-COAD significantly reduces dependency on real calibration data without compromising guaranteed FDR control.
Authors: Md. Tanzib Hosain, Asif Zaman, Md. Shahriar Sajid, Shadman Sakeeb Khan, Shanjida Akter
Abstract: The widespread adoption of Artificial Intelligence (AI) has been driven by significant advances in intelligent system research. However, this progress has raised concerns about data privacy, leading to a growing awareness of the need for privacy-preserving AI. In response, there has been a seismic shift in interest towards the leading paradigm for training Machine Learning (ML) models on decentralized data silos while maintaining data privacy, Federated Learning (FL). This research paper presents a comprehensive performance analysis of a cutting-edge approach to personalize ML model while preserving privacy achieved through Privacy Preserving Machine Learning with the innovative framework of Federated Personalized Learning (PPMLFPL). Regarding the increasing concerns about data privacy, this study evaluates the effectiveness of PPMLFPL addressing the critical balance between personalized model refinement and maintaining the confidentiality of individual user data. According to our analysis, Adaptive Personalized Cross-Silo Federated Learning with Differential Privacy (APPLE+DP) offering efficient execution whereas overall, the use of the Adaptive Personalized Cross-Silo Federated Learning with Homomorphic Encryption (APPLE+HE) algorithm for privacy-preserving machine learning tasks in federated personalized learning settings is strongly suggested. The results offer valuable insights creating it a promising scope for future advancements in the field of privacy-conscious data-driven technologies.
Authors: Zhiyi Zhou, Hexin Peng, Hongyu Long
Abstract: With the advancement of Internet of Things (IoT) technologies, high-precision indoor positioning has become essential for Location-Based Services (LBS) in complex indoor environments. Fingerprint-based localization is popular, but traditional algorithms and deep learning-based methods face challenges such as poor generalization, overfitting, and lack of interpretability. This paper applies conformal prediction (CP) to deep learning-based indoor positioning. CP transforms the uncertainty of the model into a non-conformity score, constructs prediction sets to ensure correctness coverage, and provides statistical guarantees. We also introduce conformal risk control for path navigation tasks to manage the false discovery rate (FDR) and the false negative rate (FNR).The model achieved an accuracy of approximately 100% on the training dataset and 85% on the testing dataset, effectively demonstrating its performance and generalization capability. Furthermore, we also develop a conformal p-value framework to control the proportion of position-error points. Experiments on the UJIIndoLoc dataset using lightweight models such as MobileNetV1, VGG19, MobileNetV2, ResNet50, and EfficientNet show that the conformal prediction technique can effectively approximate the target coverage, and different models have different performance in terms of prediction set size and uncertainty quantification.
Authors: Ze Tao
Abstract: Deep learning has emerged as a powerful tool in scientific modeling, particularly for complex dynamical systems; however, accurately capturing age-structured population dynamics under policy-driven fertility changes remains a significant challenge due to the lack of effective integration between domain knowledge and long-term temporal dependencies. To address this issue, we propose two physics-informed deep learning frameworks--PINN and LSTM-PINN--that incorporate policy-aware fertility functions into a transport-reaction partial differential equation to simulate population evolution from 2024 to 2054. The standard PINN model enforces the governing equation and boundary conditions via collocation-based training, enabling accurate learning of underlying population dynamics and ensuring stable convergence. Building on this, the LSTM-PINN framework integrates sequential memory mechanisms to effectively capture long-range dependencies in the age-time domain, achieving robust training performance across multiple loss components. Simulation results under three distinct fertility policy scenarios-the Three-child policy, the Universal two-child policy, and the Separate two-child policy--demonstrate the models' ability to reflect policy-sensitive demographic shifts and highlight the effectiveness of integrating domain knowledge into data-driven forecasting. This study provides a novel and extensible framework for modeling age-structured population dynamics under policy interventions, offering valuable insights for data-informed demographic forecasting and long-term policy planning in the face of emerging population challenges.
Authors: Jifeng Hu, Sili Huang, Zhejian Yang, Shengchao Hu, Li Shen, Hechang Chen, Lichao Sun, Yi Chang, Dacheng Tao
Abstract: Conditional decision generation with diffusion models has shown powerful competitiveness in reinforcement learning (RL). Recent studies reveal the relation between energy-function-guidance diffusion models and constrained RL problems. The main challenge lies in estimating the intermediate energy, which is intractable due to the log-expectation formulation during the generation process. To address this issue, we propose the Analytic Energy-guided Policy Optimization (AEPO). Specifically, we first provide a theoretical analysis and the closed-form solution of the intermediate guidance when the diffusion model obeys the conditional Gaussian transformation. Then, we analyze the posterior Gaussian distribution in the log-expectation formulation and obtain the target estimation of the log-expectation under mild assumptions. Finally, we train an intermediate energy neural network to approach the target estimation of log-expectation formulation. We apply our method in 30+ offline RL tasks to demonstrate the effectiveness of our method. Extensive experiments illustrate that our method surpasses numerous representative baselines in D4RL offline reinforcement learning benchmarks.
Authors: Youssef Allouah, Rachid Guerraoui, John Stephan
Abstract: Resilience against malicious parties and data privacy are essential for trustworthy distributed learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of workers shares a randomness seed unknown to others. In a setting where malicious workers may collude with an untrusted server, we propose CafCor, an algorithm that integrates robust gradient aggregation with correlated noise injection, leveraging shared randomness between workers. We prove that CafCor achieves strong privacy-utility trade-offs, significantly outperforming local differential privacy (DP) methods, which do not make any trust assumption, while approaching central DP utility, where the server is fully trusted. Empirical results on standard benchmarks validate CafCor's practicality, showing that privacy and robustness can coexist in distributed systems without sacrificing utility or trusting the server.
Authors: Nikolaos Louloudakis, Ajitha Rajan
Abstract: With $700$ stars on GitHub and part of the official ONNX repository, the ONNX Optimizer consists of the standard method to apply graph-based optimizations on ONNX models. However, its ability to preserve model accuracy across optimizations, has not been rigorously explored. We propose OODTE, a utility to automatically and thoroughly assess the correctness of the ONNX Optimizer. OODTE follows a simple, yet effective differential testing and evaluation approach that can be easily adopted to other compiler optimizers. In particular, OODTE utilizes a number of ONNX models, then optimizes them and executes both the original and the optimized variants across a user-defined set of inputs, while automatically logging any issues with the optimization process. Finally, for successfully optimized models, OODTE compares the results, and, if any accuracy deviations are observed, it iteratively repeats the process for each pass of the ONNX Optimizer, to localize the root cause of the differences observed. Using OODTE, we sourced well-known $130$ models from the official ONNX Model Hub, used for a wide variety of tasks (classification, object detection, semantic segmentation, text summarization, question and answering, sentiment analysis) from the official ONNX model hub. We detected 15 issues, 14 of which were previously unknown, associated with optimizer crashes and accuracy deviations. We also observed $9.2$% of all model instances presenting issues leading into the crash of the optimizer, or the generation of an invalid model while using the primary optimizer strategies. In addition, $30$% of the classification models presented accuracy differences across the original and the optimized model variants, while $16.6$% of semantic segmentation and object detection models are also affected, at least to a limited extent.
Authors: Ali Al-Bustami, Zaid Ghazal
Abstract: Accurate prediction of FIFA World Cup match outcomes holds significant value for analysts, coaches, bettors, and fans. This paper presents a machine learning framework specifically designed to forecast match winners in FIFA World Cup. By integrating both team-level historical data and player-specific performance metrics such as goals, assists, passing accuracy, and tackles, we capture nuanced interactions often overlooked by traditional aggregate models. Our methodology processes multi-year data to create year-specific team profiles that account for evolving rosters and player development. We employ classification techniques complemented by dimensionality reduction and hyperparameter optimization, to yield robust predictive models. Experimental results on data from the FIFA 2022 World Cup demonstrate our approach's superior accuracy compared to baseline method. Our findings highlight the importance of incorporating individual player attributes and team-level composition to enhance predictive performance, offering new insights into player synergy, strategic match-ups, and tournament progression scenarios. This work underscores the transformative potential of rich, player-centric data in sports analytics, setting a foundation for future exploration of advanced learning architectures such as graph neural networks to model complex team interactions.
Authors: Nisarg Parikh, Nigel Fernandez, Alexander Scarlatos, Simon Woodhead, Andrew Lan
Abstract: Large language models (LLMs) are increasingly used to generate distractors for multiple-choice questions (MCQs), especially in domains like math education. However, existing approaches are limited in ensuring that the generated distractors are consistent with common student errors. We propose LookAlike, a method that improves error-distractor consistency via preference optimization. Our two main innovations are: (a) mining synthetic preference pairs from model inconsistencies, and (b) alternating supervised fine-tuning (SFT) with Direct Preference Optimization (DPO) to stabilize training. Unlike prior work that relies on heuristics or manually annotated preference data, LookAlike uses its own generation inconsistencies as dispreferred samples, thus enabling scalable and stable training. Evaluated on a real-world dataset of 1,400+ math MCQs, LookAlike achieves 51.6% accuracy in distractor generation and 57.2% in error generation under LLM-as-a-judge evaluation, outperforming an existing state-of-the-art method (45.6% / 47.7%). These improvements highlight the effectiveness of preference-based regularization and inconsistency mining for generating consistent math MCQ distractors at scale.
Authors: Evan R. Antoniuk, Shehtab Zaman, Tal Ben-Nun, Peggy Li, James Diffenderfer, Busra Demirci, Obadiah Smolenski, Tim Hsu, Anna M. Hiszpanski, Kenneth Chiu, Bhavya Kailkhura, Brian Van Essen
Abstract: Advances in deep learning and generative modeling have driven interest in data-driven molecule discovery pipelines, whereby machine learning (ML) models are used to filter and design novel molecules without requiring prohibitively expensive first-principles simulations. Although the discovery of novel molecules that extend the boundaries of known chemistry requires accurate out-of-distribution (OOD) predictions, ML models often struggle to generalize OOD. Furthermore, there are currently no systematic benchmarks for molecular OOD prediction tasks. We present BOOM, $\boldsymbol{b}$enchmarks for $\boldsymbol{o}$ut-$\boldsymbol{o}$f-distribution $\boldsymbol{m}$olecular property predictions -- a benchmark study of property-based out-of-distribution models for common molecular property prediction models. We evaluate more than 140 combinations of models and property prediction tasks to benchmark deep learning models on their OOD performance. Overall, we do not find any existing models that achieve strong OOD generalization across all tasks: even the top performing model exhibited an average OOD error 3x larger than in-distribution. We find that deep learning models with high inductive bias can perform well on OOD tasks with simple, specific properties. Although chemical foundation models with transfer and in-context learning offer a promising solution for limited training data scenarios, we find that current foundation models do not show strong OOD extrapolation capabilities. We perform extensive ablation experiments to highlight how OOD performance is impacted by data generation, pre-training, hyperparameter optimization, model architecture, and molecular representation. We propose that developing ML models with strong OOD generalization is a new frontier challenge in chemical ML model development. This open-source benchmark will be made available on Github.
Authors: Kyungsu Kim
Abstract: In this paper, I explored how a range of regression and machine learning techniques can be applied to monthly U.S. unemployment data to produce timely forecasts. I compared seven models: Linear Regression, SGDRegressor, Random Forest, XGBoost, CatBoost, Support Vector Regression, and an LSTM network, training each on a historical span of data and then evaluating on a later hold-out period. Input features include macro indicators (GDP growth, CPI), labor market measures (job openings, initial claims), financial variables (interest rates, equity indices), and consumer sentiment. I tuned model hyperparameters via cross-validation and assessed performance with standard error metrics and the ability to predict the correct unemployment direction. Across the board, tree-based ensembles (and CatBoost in particular) deliver noticeably better forecasts than simple linear approaches, while the LSTM captures underlying temporal patterns more effectively than other nonlinear methods. SVR and SGDRegressor yield modest gains over standard regression but don't match the consistency of the ensemble and deep-learning models. Interpretability tools ,feature importance rankings and SHAP values, point to job openings and consumer sentiment as the most influential predictors across all methods. By directly comparing linear, ensemble, and deep-learning approaches on the same dataset, our study shows how modern machine-learning techniques can enhance real-time unemployment forecasting, offering economists and policymakers richer insights into labor market trends. In the comparative evaluation of the models, I employed a dataset comprising thirty distinct features over the period from January 2020 through December 2024.
Authors: Yingda Fan, Runlong Yu, Janet R. Barclay, Alison P. Appling, Yiming Sun, Yiqun Xie, Xiaowei Jia
Abstract: Water temperature can vary substantially even across short distances within the same sub-watershed. Accurate prediction of stream water temperature at fine spatial resolutions (i.e., fine scales, $\leq$ 1 km) enables precise interventions to maintain water quality and protect aquatic habitats. Although spatiotemporal models have made substantial progress in spatially coarse time series modeling, challenges persist in predicting at fine spatial scales due to the lack of data at that scale.To address the problem of insufficient fine-scale data, we propose a Multi-Scale Graph Learning (MSGL) method. This method employs a multi-task learning framework where coarse-scale graph learning, bolstered by larger datasets, simultaneously enhances fine-scale graph learning. Although existing multi-scale or multi-resolution methods integrate data from different spatial scales, they often overlook the spatial correspondences across graph structures at various scales. To address this, our MSGL introduces an additional learning task, cross-scale interpolation learning, which leverages the hydrological connectedness of stream locations across coarse- and fine-scale graphs to establish cross-scale connections, thereby enhancing overall model performance. Furthermore, we have broken free from the mindset that multi-scale learning is limited to synchronous training by proposing an Asynchronous Multi-Scale Graph Learning method (ASYNC-MSGL). Extensive experiments demonstrate the state-of-the-art performance of our method for anti-sparse downscaling of daily stream temperatures in the Delaware River Basin, USA, highlighting its potential utility for water resources monitoring and management.
Authors: Kareem Ahmed, Catarina G Belem, Padhraic Smyth, Sameer Singh
Abstract: Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling from the LM distribution conditioned on the target attribute, a computationally intractable problem due to the non-decomposable nature of the verifier. Existing approaches to LM control either only deal with syntactic constraints which cannot capture the aforementioned attributes, or rely on sampling to explore the conditional LM distribution, an ineffective estimator for low-probability events. In this work, we leverage a verifier's gradient information to efficiently reason over all generations that satisfy the target attribute, enabling precise steering of LM generations by reweighing the next-token distribution. Starting from an initial sample, we create a local LM distribution favoring semantically similar sentences. This approximation enables the tractable computation of an expected sentence embedding. We use this expected embedding, informed by the verifier's evaluation at the initial sample, to estimate the probability of satisfying the constraint, which directly informs the update to the next-token distribution. We evaluated the effectiveness of our approach in controlling the toxicity, sentiment, and topic-adherence of LMs yielding generations satisfying the constraint with high probability (>95%) without degrading their quality.
Authors: Leyi Yan, Linda Wang, Sihang Liu, Yi Ding
Abstract: Carbon intensity (CI) measures the average carbon emissions generated per unit of electricity, making it a crucial metric for quantifying and managing the environmental impact. Accurate CI predictions are vital for minimizing carbon footprints, yet the state-of-the-art method (CarbonCast) falls short due to its inability to address regional variability and lack of adaptability. To address these limitations, we introduce EnsembleCI, an adaptive, end-to-end ensemble learning-based approach for CI forecasting. EnsembleCI combines weighted predictions from multiple sublearners, offering enhanced flexibility and regional adaptability. In evaluations across 11 regional grids, EnsembleCI consistently surpasses CarbonCast, achieving the lowest mean absolute percentage error (MAPE) in almost all grids and improving prediction accuracy by an average of 19.58%. While performance still varies across grids due to inherent regional diversity, EnsembleCI reduces variability and exhibits greater robustness in long-term forecasting compared to CarbonCast and identifies region-specific key features, underscoring its interpretability and practical relevance. These findings position EnsembleCI as a more accurate and reliable solution for CI forecasting. EnsembleCI source code and data used in this paper are available at https://github.com/emmayly/EnsembleCI.
Authors: Chenran Zhao, Dianxi Shi, Mengzhu Wang, Jianqiang Xia, Huanhuan Yang, Songchang Jin, Shaowu Yang, Chunping Qiu
Abstract: Current Hierarchical Reinforcement Learning (HRL) algorithms excel in long-horizon sequential decision-making tasks but still face two challenges: delay effects and spurious correlations. To address them, we propose a causal HRL approach called D3HRL. First, D3HRL models delayed effects as causal relationships across different time spans and employs distributed causal discovery to learn these relationships. Second, it employs conditional independence testing to eliminate spurious correlations. Finally, D3HRL constructs and trains hierarchical policies based on the identified true causal relationships. These three steps are iteratively executed, gradually exploring the complete causal chain of the task. Experiments conducted in 2D-MineCraft and MiniGrid show that D3HRL demonstrates superior sensitivity to delay effects and accurately identifies causal relationships, leading to reliable decision-making in complex environments.
Authors: Yiping Ji, Hemanth Saratchandran, Peyman Moghaddam, Simon Lucey
Abstract: We highlight a curious empirical result within modern Vision Transformers (ViTs). Specifically, self-attention catastrophically fails to train unless it is used in conjunction with a skip connection. This is in contrast to other elements of a ViT that continue to exhibit good performance (albeit suboptimal) when skip connections are removed. Further, we show that this critical dependence on skip connections is a relatively new phenomenon, with previous deep architectures (\eg, CNNs) exhibiting good performance in their absence. In this paper, we theoretically characterize that the self-attention mechanism is fundamentally ill-conditioned and is, therefore, uniquely dependent on skip connections for regularization. Additionally, we propose Token Graying -- a simple yet effective complement (to skip connections) that further improves the condition of input tokens. We validate our approach in both supervised and self-supervised training methods.
Authors: Jiancong Xiao, Bojian Hou, Zhanliang Wang, Ruochen Jin, Qi Long, Weijie J. Su, Li Shen
Abstract: One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated, LLMs tend to become poorly calibrated after alignment with human preferences. In this paper, we investigate why preference alignment affects calibration and how to address this issue. For the first question, we observe that the preference collapse issue in alignment undesirably generalizes to the calibration scenario, causing LLMs to exhibit overconfidence and poor calibration. To address this, we demonstrate the importance of fine-tuning with domain-specific knowledge to alleviate the overconfidence issue. To further analyze whether this affects the model's performance, we categorize models into two regimes: calibratable and non-calibratable, defined by bounds of Expected Calibration Error (ECE). In the calibratable regime, we propose a calibration-aware fine-tuning approach to achieve proper calibration without compromising LLMs' performance. However, as models are further fine-tuned for better performance, they enter the non-calibratable regime. For this case, we develop an EM-algorithm-based ECE regularization for the fine-tuning loss to maintain low calibration error. Extensive experiments validate the effectiveness of the proposed methods.
Authors: Minhyuk Lee, HyeKyung Yoon, MyungJoo Kang
Abstract: Multivariate long-term time series forecasting is critical for applications such as weather prediction, and traffic analysis. In addition, the implementation of Transformer variants has improved prediction accuracy. Following these variants, different input data process approaches also enhanced the field, such as tokenization techniques including point-wise, channel-wise, and patch-wise tokenization. However, previous studies still have limitations in time complexity, computational resources, and cross-dimensional interactions. To address these limitations, we introduce a novel CNN Autoencoder-based Score Attention mechanism (CASA), which can be introduced in diverse Transformers model-agnosticically by reducing memory and leading to improvement in model performance. Experiments on eight real-world datasets validate that CASA decreases computational resources by up to 77.7%, accelerates inference by 44.0%, and achieves state-of-the-art performance, ranking first in 87.5% of evaluated metrics.
Authors: Yancheng Chen, Wenguo Yang, Zhipeng Jiang
Abstract: Wide & Deep, a simple yet effective learning architecture for recommendation systems developed by Google, has had a significant impact in both academia and industry due to its combination of the memorization ability of generalized linear models and the generalization ability of deep models. Graph convolutional networks (GCNs) remain dominant in node classification tasks; however, recent studies have highlighted issues such as heterophily and expressiveness, which focus on graph structure while seemingly neglecting the potential role of node features. In this paper, we propose a flexible framework GCNIII, which leverages the Wide & Deep architecture and incorporates three techniques: Intersect memory, Initial residual and Identity mapping. We provide comprehensive empirical evidence showing that GCNIII can more effectively balance the trade-off between over-fitting and over-generalization on various semi- and full- supervised tasks. Additionally, we explore the use of large language models (LLMs) for node feature engineering to enhance the performance of GCNIII in cross-domain node classification tasks. Our implementation is available at https://github.com/CYCUCAS/GCNIII.
Authors: Yiming Zhang, Koji Tsuda
Abstract: Nanobodies, single-domain antibody fragments derived from camelid heavy-chain-only antibodies, exhibit unique advantages such as compact size, high stability, and strong binding affinity, making them valuable tools in therapeutics and diagnostics. While recent advances in pretrained protein and antibody language models (PPLMs and PALMs) have greatly enhanced biomolecular understanding, nanobody-specific modeling remains underexplored and lacks a unified benchmark. To address this gap, we introduce NbBench, the first comprehensive benchmark suite for nanobody representation learning. Spanning eight biologically meaningful tasks across nine curated datasets, NbBench encompasses structure annotation, binding prediction, and developability assessment. We systematically evaluate eleven representative models--including general-purpose protein LMs, antibody-specific LMs, and nanobody-specific LMs--in a frozen setting. Our analysis reveals that antibody language models excel in antigen-related tasks, while performance on regression tasks such as thermostability and affinity remains challenging across all models. Notably, no single model consistently outperforms others across all tasks. By standardizing datasets, task definitions, and evaluation protocols, NbBench offers a reproducible foundation for assessing and advancing nanobody modeling.
Authors: Rui Lv, Zaixi Zhang, Kai Zhang, Qi Liu, Weibo Gao, Jiawei Liu, Jiaxia Yan, Linan Yue, Fangzhou Yao
Abstract: Graph In-Context Learning, with the ability to adapt pre-trained graph models to novel and diverse downstream graphs without updating any parameters, has gained much attention in the community. The key to graph in-context learning is to perform downstream graphs conditioned on chosen prompt examples. Existing methods randomly select subgraphs or edges as prompts, leading to noisy graph prompts and inferior model performance. Additionally, due to the gap between pre-training and testing graphs, when the number of classes in the testing graphs is much greater than that in the training, the in-context learning ability will also significantly deteriorate. To tackle the aforementioned challenges, we develop a multi-stage adaptive prompt optimization method GraphPrompter, which optimizes the entire process of generating, selecting, and using graph prompts for better in-context learning capabilities. Firstly, Prompt Generator introduces a reconstruction layer to highlight the most informative edges and reduce irrelevant noise for graph prompt construction. Furthermore, in the selection stage, Prompt Selector employs the $k$-nearest neighbors algorithm and pre-trained selection layers to dynamically choose appropriate samples and minimize the influence of irrelevant prompts. Finally, we leverage a Prompt Augmenter with a cache replacement strategy to enhance the generalization capability of the pre-trained model on new datasets. Extensive experiments show that GraphPrompter effectively enhances the in-context learning ability of graph models. On average across all the settings, our approach surpasses the state-of-the-art baselines by over 8%. Our code is released at https://github.com/karin0018/GraphPrompter.
Authors: Emine Akpinar, Batuhan Hangun, Murat Oduncuoglu, Oguz Altun, Onder Eyecioglu, Zeynel Yalcin
Abstract: DNA microarray technology enables the simultaneous measurement of expression levels of thousands of genes, thereby facilitating the understanding of the molecular mechanisms underlying complex diseases such as brain tumors and the identification of diagnostic genetic signatures. To derive meaningful biological insights from the high-dimensional and complex gene features obtained through this technology and to analyze gene properties in detail, classical AI-based approaches such as machine learning and deep learning are widely employed. However, these methods face various limitations in managing high-dimensional vector spaces and modeling the intricate relationships among genes. In particular, challenges such as hyperparameter tuning, computational costs, and high processing power requirements can hinder their efficiency. To overcome these limitations, quantum computing and quantum AI approaches are gaining increasing attention. Leveraging quantum properties such as superposition and entanglement, quantum methods enable more efficient parallel processing of high-dimensional data and offer faster and more effective solutions to problems that are computationally demanding for classical methods. In this study, a novel model called "Deep VQC" is proposed, based on the Variational Quantum Classifier approach. Developed using microarray data containing 54,676 gene features, the model successfully classified four different types of brain tumors-ependymoma, glioblastoma, medulloblastoma, and pilocytic astrocytoma-alongside healthy samples with high accuracy. Furthermore, compared to classical ML algorithms, our model demonstrated either superior or comparable classification performance. These results highlight the potential of quantum AI methods as an effective and promising approach for the analysis and classification of complex structures such as brain tumors based on gene expression features.
Authors: Tianshu Yu
Abstract: Generative Flow Networks (GFlowNets) have emerged as a powerful paradigm for generating composite structures, demonstrating considerable promise across diverse applications. While substantial progress has been made in exploring their modeling validity and connections to other generative frameworks, the theoretical understanding of their learning behavior remains largely uncharted. In this work, we present a rigorous theoretical investigation of GFlowNets' learning behavior, focusing on four fundamental dimensions: convergence, sample complexity, implicit regularization, and robustness. By analyzing these aspects, we seek to elucidate the intricate mechanisms underlying GFlowNet's learning dynamics, shedding light on its strengths and limitations. Our findings contribute to a deeper understanding of the factors influencing GFlowNet performance and provide insights into principled guidelines for their effective design and deployment. This study not only bridges a critical gap in the theoretical landscape of GFlowNets but also lays the foundation for their evolution as a reliable and interpretable framework for generative modeling. Through this, we aspire to advance the theoretical frontiers of GFlowNets and catalyze their broader adoption in the AI community.
Authors: Seoungbin Bae, Dabeen Lee
Abstract: We study the problem of neural logistic bandits, where the main task is to learn an unknown reward function within a logistic link function using a neural network. Existing approaches either exhibit unfavorable dependencies on $\kappa$, where $1/\kappa$ represents the minimum variance of reward distributions, or suffer from direct dependence on the feature dimension $d$, which can be huge in neural network-based settings. In this work, we introduce a novel Bernstein-type inequality for self-normalized vector-valued martingales that is designed to bypass a direct dependence on the ambient dimension. This lets us deduce a regret upper bound that grows with the effective dimension $\widetilde{d}$, not the feature dimension, while keeping a minimal dependence on $\kappa$. Based on the concentration inequality, we propose two algorithms, NeuralLog-UCB-1 and NeuralLog-UCB-2, that guarantee regret upper bounds of order $\widetilde{O}(\widetilde{d}\sqrt{\kappa T})$ and $\widetilde{O}(\widetilde{d}\sqrt{T/\kappa})$, respectively, improving on the existing results. Lastly, we report numerical results on both synthetic and real datasets to validate our theoretical findings.
Authors: Yi Han (Independent Researcher, Australia)
Abstract: As time series classification (TSC) gains prominence, ensuring robust TSC models against adversarial attacks is crucial. While adversarial defense is well-studied in Computer Vision (CV), the TSC field has primarily relied on adversarial training (AT), which is computationally expensive. In this paper, five data augmentation-based defense methods tailored for time series are developed, with the most computationally intensive method among them increasing the computational resources by only 14.07% compared to the original TSC model. Moreover, the deployment process for these methods is straightforward. By leveraging these advantages of our methods, we create two combined methods. One of these methods is an ensemble of all the proposed techniques, which not only provides better defense performance than PGD-based AT but also enhances the generalization ability of TSC models. Moreover, the computational resources required for our ensemble are less than one-third of those required for PGD-based AT. These methods advance robust TSC in data mining. Furthermore, as foundation models are increasingly explored for time series feature learning, our work provides insights into integrating data augmentation-based adversarial defense with large-scale pre-trained models in future research.
Authors: Francesco Petri, Luigi Asprino, Aldo Gangemi
Abstract: World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Despite their impressive performance, many solutions fail to learn a causal representation of the environment they are trying to model, which would be necessary to gain a deep enough understanding of the world to perform complex tasks. With this work, we aim to broaden the research in the intersection of causality theory and neural world modelling by assessing the potential for causal discovery of the State Space Model (SSM) architecture, which has been shown to have several advantages over the widespread Transformer. We show empirically that, compared to an equivalent Transformer, a SSM can model the dynamics of a simple environment and learn a causal model at the same time with equivalent or better performance, thus paving the way for further experiments that lean into the strength of SSMs and further enhance them with causal awareness.
Authors: Runyi Yu, Yinhuai Wang, Qihan Zhao, Hok Wai Tsui, Jingbo Wang, Ping Tan, Qifeng Chen
Abstract: We address a fundamental challenge in Reinforcement Learning from Interaction Demonstration (RLID): demonstration noise and coverage limitations. While existing data collection approaches provide valuable interaction demonstrations, they often yield sparse, disconnected, and noisy trajectories that fail to capture the full spectrum of possible skill variations and transitions. Our key insight is that despite noisy and sparse demonstrations, there exist infinite physically feasible trajectories that naturally bridge between demonstrated skills or emerge from their neighboring states, forming a continuous space of possible skill variations and transitions. Building upon this insight, we present two data augmentation techniques: a Stitched Trajectory Graph (STG) that discovers potential transitions between demonstration skills, and a State Transition Field (STF) that establishes unique connections for arbitrary states within the demonstration neighborhood. To enable effective RLID with augmented data, we develop an Adaptive Trajectory Sampling (ATS) strategy for dynamic curriculum generation and a historical encoding mechanism for memory-dependent skill learning. Our approach enables robust skill acquisition that significantly generalizes beyond the reference demonstrations. Extensive experiments across diverse interaction tasks demonstrate substantial improvements over state-of-the-art methods in terms of convergence stability, generalization capability, and recovery robustness.
Authors: Pratik Shrestha, Saran Phatharodom, Alec Aversa, David Blankenship, Zhengfeng Wu, Ioannis Savidis
Abstract: Representation learning has become an effective technique utilized by electronic design automation (EDA) algorithms, which leverage the natural representation of workflow elements as images, grids, and graphs. By addressing challenges related to the increasing complexity of circuits and stringent power, performance, and area (PPA) requirements, representation learning facilitates the automatic extraction of meaningful features from complex data formats, including images, grids, and graphs. This paper examines the application of representation learning in EDA, covering foundational concepts and analyzing prior work and case studies on tasks that include timing prediction, routability analysis, and automated placement. Key techniques, including image-based methods, graph-based approaches, and hybrid multimodal solutions, are presented to illustrate the improvements provided in routing, timing, and parasitic prediction. The provided advancements demonstrate the potential of representation learning to enhance efficiency, accuracy, and scalability in current integrated circuit design flows.
Authors: Samidha Verma, Arushi Goyal, Ananya Mathur, Ankit Anand, Sayan Ranu
Abstract: Graph Edit Distance (GED) is a widely used metric for measuring similarity between two graphs. Computing the optimal GED is NP-hard, leading to the development of various neural and non-neural heuristics. While neural methods have achieved improved approximation quality compared to non-neural approaches, they face significant challenges: (1) They require large amounts of ground truth data, which is itself NP-hard to compute. (2) They operate as black boxes, offering limited interpretability. (3) They lack cross-domain generalization, necessitating expensive retraining for each new dataset. We address these limitations with GRAIL, introducing a paradigm shift in this domain. Instead of training a neural model to predict GED, GRAIL employs a novel combination of large language models (LLMs) and automated prompt tuning to generate a program that is used to compute GED. This shift from predicting GED to generating programs imparts various advantages, including end-to-end interpretability and an autonomous self-evolutionary learning mechanism without ground-truth supervision. Extensive experiments on seven datasets confirm that GRAIL not only surpasses state-of-the-art GED approximation methods in prediction quality but also achieves robust cross-domain generalization across diverse graph distributions.
Authors: Chenxi Liu, Shaowen Zhou, Hao Miao, Qianxiong Xu, Cheng Long, Ziyue Li, Rui Zhao
Abstract: Multivariate time series forecasting (MTSF) endeavors to predict future observations given historical data, playing a crucial role in time series data management systems. With advancements in large language models (LLMs), recent studies employ textual prompt tuning to infuse the knowledge of LLMs into MTSF. However, the deployment of LLMs often suffers from low efficiency during the inference phase. To address this problem, we introduce TimeKD, an efficient MTSF framework that leverages the calibrated language models and privileged knowledge distillation. TimeKD aims to generate high-quality future representations from the proposed cross-modality teacher model and cultivate an effective student model. The cross-modality teacher model adopts calibrated language models (CLMs) with ground truth prompts, motivated by the paradigm of Learning Under Privileged Information (LUPI). In addition, we design a subtractive cross attention (SCA) mechanism to refine these representations. To cultivate an effective student model, we propose an innovative privileged knowledge distillation (PKD) mechanism including correlation and feature distillation. PKD enables the student to replicate the teacher's behavior while minimizing their output discrepancy. Extensive experiments on real data offer insight into the effectiveness, efficiency, and scalability of the proposed TimeKD.
Authors: Prajwal Thapa, Mridul Sharma, Jinu Nyachhyon, Yagya Raj Pandeya
Abstract: Herb classification presents a critical challenge in botanical research, particularly in regions with rich biodiversity such as Nepal. This study introduces a novel deep learning approach for classifying 60 different herb species using Convolutional Neural Networks (CNNs) and transfer learning techniques. Using a manually curated dataset of 12,000 herb images, we developed a robust machine learning model that addresses existing limitations in herb recognition methodologies. Our research employed multiple model architectures, including DenseNet121, 50-layer Residual Network (ResNet50), 16-layer Visual Geometry Group Network (VGG16), InceptionV3, EfficientNetV2, and Vision Transformer (VIT), with DenseNet121 ultimately demonstrating superior performance. Data augmentation and regularization techniques were applied to mitigate overfitting and enhance the generalizability of the model. This work advances herb classification techniques, preserving traditional botanical knowledge and promoting sustainable herb utilization.
Authors: Shengyu Duan, Marcos L. L. Sartori, Rishad Shafik, Alex Yakovlev, Emre Ozer
Abstract: Population count (popcount) is a crucial operation for many low-complexity machine learning (ML) algorithms, including Tsetlin Machine (TM)-a promising new ML method, particularly well-suited for solving classification tasks. The inference mechanism in TM consists of propositional logic-based structures within each class, followed by a majority voting scheme, which makes the classification decision. In TM, the voters are the outputs of Boolean clauses. The voting mechanism comprises two operations: popcount for each class and determining the class with the maximum vote by means of an argmax operation. While TMs offer a lightweight ML alternative, their performance is often limited by the high computational cost of popcount and comparison required to produce the argmax result. In this paper, we propose an innovative approach to accelerate and optimize these operations by performing them in the time domain. Our time-domain implementation uses programmable delay lines (PDLs) and arbiters to efficiently manage these tasks through delay-based mechanisms. We also present an FPGA design flow for practical implementation of the time-domain popcount, addressing delay skew and ensuring that the behavior matches that of the model's intended functionality. By leveraging the natural compatibility of the proposed popcount with asynchronous architectures, we demonstrate significant improvements in an asynchronous TM, including up to 38% reduction in latency, 43.1% reduction in dynamic power, and 15% savings in resource utilization, compared to synchronous TMs using adder-based popcount.
Authors: Lei Mao, Yuanhe Tian, Yan Song
Abstract: Genome modeling conventionally treats gene sequence as a language, reflecting its structured motifs and long-range dependencies analogous to linguistic units and organization principles such as words and syntax. Recent studies utilize advanced neural networks, ranging from convolutional and recurrent models to Transformer-based models, to capture contextual information of gene sequence, with the primary goal of obtaining effective gene sequence representations and thus enhance the models' understanding of various running gene samples. However, these approaches often directly apply language modeling techniques to gene sequences and do not fully consider the intrinsic information organization in them, where they do not consider how units at different granularities contribute to representation. In this paper, we propose DNAZEN, an enhanced genomic representation framework designed to learn from various granularities in gene sequences, including small polymers and G-grams that are combinations of several contiguous polymers. Specifically, we extract the G-grams from large-scale genomic corpora through an unsupervised approach to construct the G-gram vocabulary, which is used to provide G-grams in the learning process of DNA sequences through dynamically matching from running gene samples. A Transformer-based G-gram encoder is also proposed and the matched G-grams are fed into it to compute their representations and integrated into the encoder for basic unit (E4BU), which is responsible for encoding small units and maintaining the learning and inference process. To further enhance the learning process, we propose whole G-gram masking to train DNAZEN, where the model largely favors the selection of each entire G-gram to mask rather than an ordinary masking mechanism performed on basic units. Experiments on benchmark datasets demonstrate the effectiveness of DNAZEN on various downstream tasks.
Authors: Yikang Chen, Dehui Du
Abstract: This paper investigates $\sim_{\mathcal{L}_3}$-identifiability, a form of complete counterfactual identifiability within the Pearl Causal Hierarchy (PCH) framework, ensuring that all Structural Causal Models (SCMs) satisfying the given assumptions provide consistent answers to all causal questions. To simplify this problem, we introduce exogenous isomorphism and propose $\sim_{\mathrm{EI}}$-identifiability, reflecting the strength of model identifiability required for $\sim_{\mathcal{L}_3}$-identifiability. We explore sufficient assumptions for achieving $\sim_{\mathrm{EI}}$-identifiability in two special classes of SCMs: Bijective SCMs (BSCMs), based on counterfactual transport, and Triangular Monotonic SCMs (TM-SCMs), which extend $\sim_{\mathcal{L}_2}$-identifiability. Our results unify and generalize existing theories, providing theoretical guarantees for practical applications. Finally, we leverage neural TM-SCMs to address the consistency problem in counterfactual reasoning, with experiments validating both the effectiveness of our method and the correctness of the theory.
Authors: Xingyu Zheng, Yuye Li, Haoran Chu, Yue Feng, Xudong Ma, Jie Luo, Jinyang Guo, Haotong Qin, Michele Magno, Xianglong Liu
Abstract: The Qwen series has emerged as a leading family of open-source Large Language Models (LLMs), demonstrating remarkable capabilities in natural language understanding tasks. With the recent release of Qwen3, which exhibits superior performance across diverse benchmarks, there is growing interest in deploying these models efficiently in resource-constrained environments. Low-bit quantization presents a promising solution, yet its impact on Qwen3's performance remains underexplored. This study conducts a systematic evaluation of Qwen3's robustness under various quantization settings, aiming to uncover both opportunities and challenges in compressing this state-of-the-art model. We rigorously assess 5 existing classic post-training quantization techniques applied to Qwen3, spanning bit-widths from 1 to 8 bits, and evaluate their effectiveness across multiple datasets. Our findings reveal that while Qwen3 maintains competitive performance at moderate bit-widths, it experiences notable degradation in linguistic tasks under ultra-low precision, underscoring the persistent hurdles in LLM compression. These results emphasize the need for further research to mitigate performance loss in extreme quantization scenarios. We anticipate that this empirical analysis will provide actionable insights for advancing quantization methods tailored to Qwen3 and future LLMs, ultimately enhancing their practicality without compromising accuracy. Our project is released on https://github.com/Efficient-ML/Qwen3-Quantization and https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.
URLs: https://github.com/Efficient-ML/Qwen3-Quantization, https://huggingface.co/collections/Efficient-ML/qwen3-quantization-68164450decb1c868788cb2b.
Authors: Essential AI, :, Ishaan Shah, Anthony M. Polloreno, Karl Stratos, Philip Monk, Adarsh Chaluvaraju, Andrew Hojel, Andrew Ma, Anil Thomas, Ashish Tanwer, Darsh J Shah, Khoi Nguyen, Kurt Smith, Michael Callahan, Michael Pust, Mohit Parmar, Peter Rushton, Platon Mazarakis, Ritvik Kapila, Saurabh Srivastava, Somanshu Singla, Tim Romanski, Yash Vanjani, Ashish Vaswani
Abstract: We demonstrate that Muon, the simplest instantiation of a second-order optimizer, explicitly expands the Pareto frontier over AdamW on the compute-time tradeoff. We find that Muon is more effective than AdamW in retaining data efficiency at large batch sizes, far beyond the so-called critical batch size, while remaining computationally efficient, thus enabling more economical training. We study the combination of Muon and the maximal update parameterization (muP) for efficient hyperparameter transfer and present a simple telescoping algorithm that accounts for all sources of error in muP while introducing only a modest overhead in resources. We validate our findings through extensive experiments with model sizes up to four billion parameters and ablations on the data distribution and architecture.
Authors: Shangzhe Li, Zhiao Huang, Hao Su
Abstract: Imitation Learning (IL) has achieved remarkable success across various domains, including robotics, autonomous driving, and healthcare, by enabling agents to learn complex behaviors from expert demonstrations. However, existing IL methods often face instability challenges, particularly when relying on adversarial reward or value formulations in world model frameworks. In this work, we propose a novel approach to online imitation learning that addresses these limitations through a reward model based on random network distillation (RND) for density estimation. Our reward model is built on the joint estimation of expert and behavioral distributions within the latent space of the world model. We evaluate our method across diverse benchmarks, including DMControl, Meta-World, and ManiSkill2, showcasing its ability to deliver stable performance and achieve expert-level results in both locomotion and manipulation tasks. Our approach demonstrates improved stability over adversarial methods while maintaining expert-level performance.
Authors: Haoyang Li, Jie Xu, Kyra Gan, Fei Wang, Chengxi Zang
Abstract: Federated causal inference enables multi-site treatment effect estimation without sharing individual-level data, offering a privacy-preserving solution for real-world evidence generation. However, data heterogeneity across sites, manifested in differences in covariate, treatment, and outcome, poses significant challenges for unbiased and efficient estimation. In this paper, we present a comprehensive review and theoretical analysis of federated causal effect estimation across both binary/continuous and time-to-event outcomes. We classify existing methods into weight-based strategies and optimization-based frameworks and further discuss extensions including personalized models, peer-to-peer communication, and model decomposition. For time-to-event outcomes, we examine federated Cox and Aalen-Johansen models, deriving asymptotic bias and variance under heterogeneity. Our analysis reveals that FedProx-style regularization achieves near-optimal bias-variance trade-offs compared to naive averaging and meta-analysis. We review related software tools and conclude by outlining opportunities, challenges, and future directions for scalable, fair, and trustworthy federated causal inference in distributed healthcare systems.
Authors: Jingxiang Qu, Wenhan Gao, Jiaxing Zhang, Xufeng Liu, Hua Wei, Haibin Ling, Yi Liu
Abstract: 3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cut-off radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model's predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.
Authors: Maryam Sultana, Neil Yorke-Smith, Kaizheng Wang, Shireen Kudukkil Manchingal, Muhammad Mubashar, Fabio Cuzzolin
Abstract: Uncertainty estimation is pivotal in machine learning, especially for classification tasks, as it improves the robustness and reliability of models. We introduce a novel `Epistemic Wrapping' methodology aimed at improving uncertainty estimation in classification. Our approach uses Bayesian Neural Networks (BNNs) as a baseline and transforms their outputs into belief function posteriors, effectively capturing epistemic uncertainty and offering an efficient and general methodology for uncertainty quantification. Comprehensive experiments employing a Bayesian Neural Network (BNN) baseline and an Interval Neural Network for inference on the MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 datasets demonstrate that our Epistemic Wrapper significantly enhances generalisation and uncertainty quantification.
Authors: Qian Qi
Abstract: We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a continuous-time Markov Decision Process (MDP) driven by a square-integrable martingale, we analyze DQN approximation properties. We show that DQNs can approximate the optimal Q-function on compact sets with arbitrary accuracy and high probability, leveraging residual network approximation theorems and large deviation bounds for the state-action process. We then analyze the convergence of a general Q-learning algorithm for training DQNs in this setting, adapting stochastic approximation theorems. Our analysis emphasizes the interplay between DQN layer count, time discretization, and the role of viscosity solutions (primarily for the value function $V^*$) in addressing potential non-smoothness of the optimal Q-function. This work bridges deep reinforcement learning and stochastic control, offering insights into DQNs in continuous-time settings, relevant for applications with physical systems or high-frequency data.
Authors: Pinaki Mohanty, Riddhiman Bhattacharya, Ruqi Zhang
Abstract: Sampling from flat modes in discrete spaces is a crucial yet underexplored problem. Flat modes represent robust solutions and have broad applications in combinatorial optimization and discrete generative modeling. However, existing sampling algorithms often overlook the mode volume and struggle to capture flat modes effectively. To address this limitation, we propose \emph{Entropic Discrete Langevin Proposal} (EDLP), which incorporates local entropy into the sampling process through a continuous auxiliary variable under a joint distribution. The local entropy term guides the discrete sampler toward flat modes with a small overhead. We provide non-asymptotic convergence guarantees for EDLP in locally log-concave discrete distributions. Empirically, our method consistently outperforms traditional approaches across tasks that require sampling from flat basins, including Bernoulli distribution, restricted Boltzmann machines, combinatorial optimization, and binary neural networks.
Authors: Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak
Abstract: Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment -- posing serious risks in safety-critical domains. Recent works have focused on designing scoring functions to quantify OOD uncertainty, with score thresholds typically set based solely on ID data to achieve a target true positive rate (TPR), since OOD data is limited before deployment. However, these TPR-based thresholds leave false positive rates (FPR) uncontrolled, often resulting in high FPRs where OOD points are misclassified as ID. Moreover, fixed scoring functions and thresholds lack the adaptivity needed to handle newly observed, evolving OOD inputs, leading to sub-optimal performance. To address these challenges, we propose a human-in-the-loop framework that \emph{safely updates both scoring functions and thresholds on the fly} based on real-world OOD inputs. Our method maximizes TPR while strictly controlling FPR at all times, even as the system adapts over time. We provide theoretical guarantees for FPR control under stationary conditions and present extensive empirical evaluations on OpenOOD benchmarks to demonstrate that our approach outperforms existing methods by achieving higher TPRs while maintaining FPR control.
Authors: Gianluca Fabiani, Hannes Vandecasteele, Somdatta Goswami, Constantinos Siettos, Ioannis G. Kevrekidis
Abstract: Neural Operators (NOs) provide a powerful framework for computations involving physical laws that can be modelled by (integro-) partial differential equations (PDEs), directly learning maps between infinite-dimensional function spaces that bypass both the explicit equation identification and their subsequent numerical solving. Still, NOs have so far primarily been employed to explore the dynamical behavior as surrogates of brute-force temporal simulations/predictions. Their potential for systematic rigorous numerical system-level tasks, such as fixed-point, stability, and bifurcation analysis - crucial for predicting irreversible transitions in real-world phenomena - remains largely unexplored. Toward this aim, inspired by the Equation-Free multiscale framework, we propose and implement a framework that integrates (local) NOs with advanced iterative numerical methods in the Krylov subspace, so as to perform efficient system-level stability and bifurcation analysis of large-scale dynamical systems. Beyond fixed point, stability, and bifurcation analysis enabled by local in time NOs, we also demonstrate the usefulness of local in space as well as in space-time ("patch") NOs in accelerating the computer-aided analysis of spatiotemporal dynamics. We illustrate our framework via three nonlinear PDE benchmarks: the 1D Allen-Cahn equation, which undergoes multiple concatenated pitchfork bifurcations; the Liouville-Bratu-Gelfand PDE, which features a saddle-node tipping point; and the FitzHugh-Nagumo (FHN) model, consisting of two coupled PDEs that exhibit both Hopf and saddle-node bifurcations.
Authors: Sanjay Surendranath Girija, Shashank Kapoor, Lakshit Arora, Dipen Pradhan, Aman Raj, Ankit Shetgaonkar
Abstract: Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview of techniques for compressing LLMs to enable efficient inference in resource-constrained environments. We examine three primary approaches: Knowledge Distillation, Model Quantization, and Model Pruning. For each technique, we discuss the underlying principles, present different variants, and provide examples of successful applications. We also briefly discuss complementary techniques such as mixture-of-experts and early-exit strategies. Finally, we highlight promising future directions, aiming to provide a valuable resource for both researchers and practitioners seeking to optimize LLMs for edge deployment.
Authors: Fares B. Mehouachi, Saif Eddin Jabari
Abstract: Adversarial training is a cornerstone of robust deep learning, but fast methods like the Fast Gradient Sign Method (FGSM) often suffer from Catastrophic Overfitting (CO), where models become robust to single-step attacks but fail against multi-step variants. While existing solutions rely on noise injection, regularization, or gradient clipping, we propose a novel solution that purely controls the $l^p$ training norm to mitigate CO. Our study is motivated by the empirical observation that CO is more prevalent under the $l^{\infty}$ norm than the $l^2$ norm. Leveraging this insight, we develop a framework for generalized $l^p$ attack as a fixed point problem and craft $l^p$-FGSM attacks to understand the transition mechanics from $l^2$ to $l^{\infty}$. This leads to our core insight: CO emerges when highly concentrated gradients where information localizes in few dimensions interact with aggressive norm constraints. By quantifying gradient concentration through Participation Ratio and entropy measures, we develop an adaptive $l^p$-FGSM that automatically tunes the training norm based on gradient information. Extensive experiments demonstrate that this approach achieves strong robustness without requiring additional regularization or noise injection, providing a novel and theoretically-principled pathway to mitigate the CO problem.
Authors: Juyoung Yun
Abstract: Generalizing well in deep neural networks remains a core challenge, particularly due to their tendency to converge to sharp minima that degrade robustness. Sharpness-Aware Minimization (SAM) mitigates this by seeking flatter minima but perturbs parameters using the full gradient, which can include statistically insignificant directions. We propose ZSharp, a simple yet effective extension to SAM that applies layer-wise Z-score normalization followed by percentile-based filtering to retain only statistically significant gradient components. This selective perturbation aligns updates with curvature-sensitive directions, enhancing generalization without requiring architectural changes. ZSharp introduces only one additional hyperparameter, the percentile threshold, and remains fully compatible with existing SAM variants. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet using ResNet, VGG, and Vision Transformers show that ZSharp consistently outperforms SAM and its variants in test accuracy, particularly on deeper and transformer-based models. These results demonstrate that ZSharp is a principled and lightweight improvement for sharpness-aware optimization.
Authors: Arnab Sanyal, Prithwish Mukherjee, Gourav Datta, Sandeep P. Chinchali
Abstract: Large Language Models (LLMs) demonstrate exceptional performance across various tasks, but their large storage and computational requirements constrain their deployment on edge devices. To address this, we propose EntroLLM, a novel compression framework that integrates mixed quantization with entropy coding to reduce storage overhead while maintaining model accuracy. Our method applies a layer-wise mixed quantization scheme - choosing between symmetric and asymmetric quantization based on individual layer weight distributions - to optimize compressibility. We then employ Huffman encoding for lossless compression of the quantized weights, significantly reducing memory bandwidth requirements. Furthermore, we introduce parallel Huffman decoding, which enables efficient retrieval of encoded weights during inference, ensuring minimal latency impact. Our experiments on edge-compatible LLMs, including smolLM-1.7B-Instruct, phi3-mini-4k-Instruct, and mistral-7B-Instruct, demonstrate that EntroLLM achieves up to $30%$ storage reduction compared to uint8 models and up to $65%$ storage reduction compared to uint4 models, while preserving perplexity and accuracy, on language benchmark tasks. We further show that our method enables $31.9%$ - $146.6%$ faster inference throughput on memory-bandwidth-limited edge devices, such as NVIDIA Jetson P3450, by reducing the required data movement. The proposed approach requires no additional re-training and is fully compatible with existing post-training quantization methods, making it a practical solution for edge LLMs.
Authors: Bingshan Hu, Zhiming Huang, Tianyue H. Zhang, Mathias L\'ecuyer, Nidhi Hegde
Abstract: We address differentially private stochastic bandit problems from the angles of exploring the deep connections among Thompson Sampling with Gaussian priors, Gaussian mechanisms, and Gaussian differential privacy (GDP). We propose DP-TS-UCB, a novel parametrized private bandit algorithm that enables to trade off privacy and regret. DP-TS-UCB satisfies $ \tilde{O} \left(T^{0.25(1-\alpha)}\right)$-GDP and enjoys an $O \left(K\ln^{\alpha+1}(T)/\Delta \right)$ regret bound, where $\alpha \in [0,1]$ controls the trade-off between privacy and regret. Theoretically, our DP-TS-UCB relies on anti-concentration bounds of Gaussian distributions and links exploration mechanisms in Thompson Sampling-based algorithms and Upper Confidence Bound-based algorithms, which may be of independent interest.
Authors: Enbo Zhao, Yi Shen, Shuming Shi, Jieyun Huang, Zhihao Chen, Ning Wang, Siqi Xiao, Jian Zhang, Kai Wang, Shiguo Lian
Abstract: Recently, there is a high demand for deploying DeepSeek-R1 and V3 locally, possibly because the official service often suffers from being busy and some organizations have data privacy concerns. While single-machine deployment offers infrastructure simplicity, the models' 671B FP8 parameter configuration exceeds the practical memory limits of a standard 8-GPU machine. Quantization is a widely used technique that helps reduce model memory consumption. However, it is unclear what the performance of DeepSeek-R1 and V3 will be after being quantized. This technical report presents the first quantitative evaluation of multi-bitwidth quantization across the complete DeepSeek model spectrum. Key findings reveal that 4-bit quantization maintains little performance degradation versus FP8 while enabling single-machine deployment on standard NVIDIA GPU devices. We further propose DQ3_K_M, a dynamic 3-bit quantization method that significantly outperforms traditional Q3_K_M variant on various benchmarks, which is also comparable with 4-bit quantization (Q4_K_M) approach in most tasks. Moreover, DQ3_K_M supports single-machine deployment configurations for both NVIDIA H100/A100 and Huawei 910B. Our implementation of DQ3\_K\_M is released at https://github.com/UnicomAI/DeepSeek-Eval, containing optimized 3-bit quantized variants of both DeepSeek-R1 and DeepSeek-V3.
Authors: Jiarui Yao, Yifan Hao, Hanning Zhang, Hanze Dong, Wei Xiong, Nan Jiang, Tong Zhang
Abstract: Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. While prior approaches such as iterative reward-ranked fine-tuning (RAFT) have relied on such formulations, they typically apply uniform inference budgets across prompts, which fails to account for variability in difficulty and convergence behavior. This work identifies the main bottleneck in CoT training as inefficient stochastic gradient estimation due to static sampling strategies. We propose GVM-RAFT, a prompt-specific Dynamic Sample Allocation Strategy designed to minimize stochastic gradient variance under a computational budget constraint. The method dynamically allocates computational resources by monitoring prompt acceptance rates and stochastic gradient norms, ensuring that the resulting gradient variance is minimized. Our theoretical analysis shows that the proposed dynamic sampling strategy leads to accelerated convergence guarantees under suitable conditions. Experiments on mathematical reasoning show that GVM-RAFT achieves a 2-4x speedup and considerable accuracy improvements over vanilla RAFT. The proposed dynamic sampling strategy is general and can be incorporated into other reinforcement learning algorithms, such as GRPO, leading to similar improvements in convergence and test accuracy. Our code is available at https://github.com/RLHFlow/GVM.
Authors: Thibault de Surrel, Florian Yger, Fabien Lotte, Sylvain Chevallier
Abstract: The goal of this paper is to show how different machine learning tools on the Riemannian manifold $\mathcal{P}_d$ of Symmetric Positive Definite (SPD) matrices can be united under a probabilistic framework. For this, we will need several Gaussian distributions defined on $\mathcal{P}_d$. We will show how popular classifiers on $\mathcal{P}_d$ can be reinterpreted as Bayes Classifiers using these Gaussian distributions. These distributions will also be used for outlier detection and dimension reduction. By showing that those distributions are pervasive in the tools used on $\mathcal{P}_d$, we allow for other machine learning tools to be extended to $\mathcal{P}_d$.
Authors: Yunfeng Ge, Jiawei Li, Yiji Zhao, Haomin Wen, Zhao Li, Meikang Qiu, Hongyan Li, Ming Jin, Shirui Pan
Abstract: Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable success in Text-to-X (e.g., vision and audio data) generation, their use in time series generation remains in its nascent stages. Existing approaches face two critical limitations: (1) the lack of systematic exploration of general-proposed time series captions, which are often domain-specific and struggle with generalization; and (2) the inability to generate time series of arbitrary lengths, limiting their applicability to real-world scenarios. In this work, we first categorize time series captions into three levels: point-level, fragment-level, and instance-level. Additionally, we introduce a new fragment-level dataset containing over 600,000 high-resolution time series-text pairs. Second, we propose Text-to-Series (T2S), a diffusion-based framework that bridges the gap between natural language and time series in a domain-agnostic manner. T2S employs a length-adaptive variational autoencoder to encode time series of varying lengths into consistent latent embeddings. On top of that, T2S effectively aligns textual representations with latent embeddings by utilizing Flow Matching and employing Diffusion Transformer as the denoiser. We train T2S in an interleaved paradigm across multiple lengths, allowing it to generate sequences of any desired length. Extensive evaluations demonstrate that T2S achieves state-of-the-art performance across 13 datasets spanning 12 domains.
Authors: Flora Amato, Lingyu Qiu, Mohammad Tanveer, Salvatore Cuomo, Fabio Giampaolo, Francesco Piccialli
Abstract: One-shot FL enables collaborative training in a single round, eliminating the need for iterative communication, making it particularly suitable for use in resource-constrained and privacy-sensitive applications. This survey offers a thorough examination of One-shot FL, highlighting its distinct operational framework compared to traditional federated approaches. One-shot FL supports resource-limited devices by enabling single-round model aggregation while maintaining data locality. The survey systematically categorizes existing methodologies, emphasizing advancements in client model initialization, aggregation techniques, and strategies for managing heterogeneous data distributions. Furthermore, we analyze the limitations of current approaches, particularly in terms of scalability and generalization in non-IID settings. By analyzing cutting-edge techniques and outlining open challenges, this survey aspires to provide a comprehensive reference for researchers and practitioners aiming to design and implement One-shot FL systems, advancing the development and adoption of One-shot FL solutions in a real-world, resource-constrained scenario.
Authors: Soumen Kumar Mondal, Akshit Varmora, Prateek Chanda, Ganesh Ramakrishnan
Abstract: We propose FairPO, a novel framework designed to promote fairness in multi-label classification by directly optimizing preference signals with a group robustness perspective. In our framework, the set of labels is partitioned into privileged and non-privileged groups, and a preference-based loss inspired by Direct Preference Optimization (DPO) is employed to more effectively differentiate true positive labels from confusing negatives within the privileged group, while preserving baseline classification performance for non-privileged labels. By framing the learning problem as a robust optimization over groups, our approach dynamically adjusts the training emphasis toward groups with poorer performance, thereby mitigating bias and ensuring a fairer treatment across diverse label categories. In addition, we outline plans to extend this approach by investigating alternative loss formulations such as Simple Preference Optimisation (SimPO) and Contrastive Preference Optimization (CPO) to exploit reference-free reward formulations and contrastive training signals. Furthermore, we plan to extend FairPO with multilabel generation capabilities, enabling the model to dynamically generate diverse and coherent label sets for ambiguous inputs.
Authors: Pouria Fatemi, Ehsan Sharifian, Mohammad Hossein Yassaee
Abstract: Counterfactual explanations enhance interpretability by identifying alternative inputs that produce different outputs, offering localized insights into model decisions. However, traditional methods often neglect causal relationships, leading to unrealistic examples. While newer approaches integrate causality, they are computationally expensive. To address these challenges, we propose an efficient method based on backtracking counterfactuals that incorporates causal reasoning to generate actionable explanations. We first examine the limitations of existing methods and then introduce our novel approach and its features. We also explore the relationship between our method and previous techniques, demonstrating that it generalizes them in specific scenarios. Finally, experiments show that our method provides deeper insights into model outputs.
Authors: Quynh Nguyen-Phuong Vu, Luciano Sebastian Martinez-Rau, Yuxuan Zhang, Nho-Duc Tran, Bengt Oelmann, Michele Magno, Sebastian Bader
Abstract: Keyword spotting (KWS) is an essential function that enables interaction with ubiquitous smart devices. However, in resource-limited devices, KWS models are often static and can thus not adapt to new scenarios, such as added keywords. To overcome this problem, we propose a Continual Learning (CL) approach for KWS built on Binary Neural Networks (BNNs). The framework leverages the reduced computation and memory requirements of BNNs while incorporating techniques that enable the seamless integration of new keywords over time. This study evaluates seven CL techniques on a 16-class use case, reporting an accuracy exceeding 95% for a single additional keyword and up to 86% for four additional classes. Sensitivity to the amount of training samples in the CL phase, and differences in computational complexities are being evaluated. These evaluations demonstrate that batch-based algorithms are more sensitive to the CL dataset size, and that differences between the computational complexities are insignificant. These findings highlight the potential of developing an effective and computationally efficient technique for continuously integrating new keywords in KWS applications that is compatible with resource-constrained devices.
Authors: Jinpeng Chen, Runmin Cong, Yuzhi Zhao, Hongzheng Yang, Guangneng Hu, Horace Ho Shing Ip, Sam Kwong
Abstract: Multimodal Continual Instruction Tuning (MCIT) aims to enable Multimodal Large Language Models (MLLMs) to incrementally learn new tasks without catastrophic forgetting. In this paper, we explore forgetting in this context, categorizing it into superficial forgetting and essential forgetting. Superficial forgetting refers to cases where the model's knowledge may not be genuinely lost, but its responses to previous tasks deviate from expected formats due to the influence of subsequent tasks' answer styles, making the results unusable. By contrast, essential forgetting refers to situations where the model provides correctly formatted but factually inaccurate answers, indicating a true loss of knowledge. Assessing essential forgetting necessitates addressing superficial forgetting first, as severe superficial forgetting can obscure the model's knowledge state. Hence, we first introduce the Answer Style Diversification (ASD) paradigm, which defines a standardized process for transforming data styles across different tasks, unifying their training sets into similarly diversified styles to prevent superficial forgetting caused by style shifts. Building on this, we propose RegLoRA to mitigate essential forgetting. RegLoRA stabilizes key parameters where prior knowledge is primarily stored by applying regularization, enabling the model to retain existing competencies. Experimental results demonstrate that our overall method, SEFE, achieves state-of-the-art performance.
Authors: Aleksandr Karakulev (Uppsala University), Usama Zafar (Uppsala University), Salman Toor (Uppsala University, Scaleout Systems), Prashant Singh (Uppsala University, Science for Life Laboratory, Sweden)
Abstract: Federated Learning enables collaborative training of machine learning models on decentralized data. This scheme, however, is vulnerable to adversarial attacks, when some of the clients submit corrupted model updates. In real-world scenarios, the total number of compromised clients is typically unknown, with the extent of attacks potentially varying over time. To address these challenges, we propose an adaptive approach for robust aggregation of model updates based on Bayesian inference. The mean update is defined by the maximum of the likelihood marginalized over probabilities of each client to be `honest'. As a result, the method shares the simplicity of the classical average estimators (e.g., sample mean or geometric median), being independent of the number of compromised clients. At the same time, it is as effective against attacks as methods specifically tailored to Federated Learning, such as Krum. We compare our approach with other aggregation schemes in federated setting on three benchmark image classification data sets. The proposed method consistently achieves state-of-the-art performance across various attack types with static and varying number of malicious clients.
Authors: Florian Gallusser, Simon Hentschel, Anna Krause, Andreas Hotho
Abstract: Deep Learning models have achieved state-of-the-art performance in medium-range weather prediction but often fail to maintain physically consistent rollouts beyond 14 days. In contrast, a few atmospheric models demonstrate stability over decades, though the key design choices enabling this remain unclear. This study quantitatively compares the long-term stability of three prominent DL-MWP architectures - FourCastNet, SFNO, and ClimaX - trained on ERA5 reanalysis data at 5.625{\deg} resolution. We systematically assess the impact of autoregressive training steps, model capacity, and choice of prognostic variables, identifying configurations that enable stable 10-year rollouts while preserving the statistical properties of the reference dataset. Notably, rollouts with SFNO exhibit the greatest robustness to hyperparameter choices, yet all models can experience instability depending on the random seed and the set of prognostic variables
Authors: Diego Perazzolo, Chiara Castellani, Enrico Grisan
Abstract: Population pharmacokinetic (PopPK) modelling is a fundamental tool for understanding drug behaviour across diverse patient populations and enabling personalized dosing strategies to improve therapeutic outcomes. A key challenge in PopPK analysis lies in identifying and modelling covariates that influence drug absorption, as these relationships are often complex and nonlinear. Traditional methods may fail to capture hidden patterns within the data. In this study, we propose a data-driven, model-free framework that integrates Variational Autoencoders (VAEs) deep learning model and LASSO regression to uncover key covariates from simulated tacrolimus pharmacokinetic (PK) profiles. The VAE compresses high-dimensional PK signals into a structured latent space, achieving accurate reconstruction with a mean absolute percentage error (MAPE) of 2.26%. LASSO regression is then applied to map patient-specific covariates to the latent space, enabling sparse feature selection through L1 regularization. This approach consistently identifies clinically relevant covariates for tacrolimus including SNP, age, albumin, and hemoglobin which are retained across the tested regularization strength levels, while effectively discarding non-informative features. The proposed VAE-LASSO methodology offers a scalable, interpretable, and fully data-driven solution for covariate selection, with promising applications in drug development and precision pharmacotherapy.
Authors: Hongze Li, Zesheng Zhou, Zhenbiao Cao, Xinhui Li, Wei Chen, Xiaojin Zhang
Abstract: Traditional domain generalization approaches predominantly focus on leveraging target domain-aware features while overlooking the critical role of source domain-specific characteristics, particularly in federated settings with inherent data isolation. To address this gap, we propose the Federated Source Domain Awareness Framework (FedSDAF), the first method to systematically exploit source domain-aware features for enhanced federated domain generalization (FedDG). The FedSDAF framework consists of two synergistic components: the Domain-Invariant Adapter, which preserves critical domain-invariant features, and the Domain-Aware Adapter, which extracts and integrates source domain-specific knowledge using a Multihead Self-Attention mechanism (MHSA). Furthermore, we introduce a bidirectional knowledge distillation mechanism that fosters knowledge sharing among clients while safeguarding privacy. Our approach represents the first systematic exploitation of source domain-aware features, resulting in significant advancements in model generalization capability.Extensive experiments on four standard benchmarks (OfficeHome, PACS, VLCS, and DomainNet) show that our method consistently surpasses state-of-the-art federated domain generalization approaches, with accuracy gains of 5.2-13.8%. The source code is available at https://github.com/pizzareapers/FedSDAF.
Authors: Davide Sartor, Alberto Sinigaglia, Gian Antonio Susto
Abstract: Conventional techniques for imposing monotonicity in MLPs by construction involve the use of non-negative weight constraints and bounded activation functions, which pose well-known optimization challenges. In this work, we generalize previous theoretical results, showing that MLPs with non-negative weight constraint and activations that saturate on alternating sides are universal approximators for monotonic functions. Additionally, we show an equivalence between the saturation side in the activations and the sign of the weight constraint. This connection allows us to prove that MLPs with convex monotone activations and non-positive constrained weights also qualify as universal approximators, in contrast to their non-negative constrained counterparts. Our results provide theoretical grounding to the empirical effectiveness observed in previous works while leading to possible architectural simplification. Moreover, to further alleviate the optimization difficulties, we propose an alternative formulation that allows the network to adjust its activations according to the sign of the weights. This eliminates the requirement for weight reparameterization, easing initialization and improving training stability. Experimental evaluation reinforces the validity of the theoretical results, showing that our novel approach compares favourably to traditional monotonic architectures.
Authors: Ljubomir Rokvic, Panayiotis Danassis, Boi Faltings
Abstract: In Federated Learning, heterogeneity in client data distributions often means that a single global model does not have the best performance for individual clients. Consider for example training a next-word prediction model for keyboards: user-specific language patterns due to demographics (dialect, age, etc.), language proficiency, and writing style result in a highly non-IID dataset across clients. Other examples are medical images taken with different machines, or driving data from different vehicle types. To address this, we propose a simple yet effective personalized federated learning framework (pFedLIA) that utilizes a computationally efficient influence approximation, called `Lazy Influence', to cluster clients in a distributed manner before model aggregation. Within each cluster, data owners collaborate to jointly train a model that captures the specific data patterns of the clients. Our method has been shown to successfully recover the global model's performance drop due to the non-IID-ness in various synthetic and real-world settings, specifically a next-word prediction task on the Nordic languages as well as several benchmark tasks. It matches the performance of a hypothetical Oracle clustering, and significantly improves on existing baselines, e.g., an improvement of 17% on CIFAR100.
Authors: Krzysztof Ociepa, {\L}ukasz Flis, Remigiusz Kinas, Krzysztof Wr\'obel, Adrian Gwo\'zdziej
Abstract: We introduce Bielik v3, a series of parameter-efficient generative text models (1.5B and 4.5B) optimized for Polish language processing. These models demonstrate that smaller, well-optimized architectures can achieve performance comparable to much larger counterparts while requiring substantially fewer computational resources. Our approach incorporates several key innovations: a custom Polish tokenizer (APT4) that significantly improves token efficiency, Weighted Instruction Cross-Entropy Loss to balance learning across instruction types, and Adaptive Learning Rate that dynamically adjusts based on training progress. Trained on a meticulously curated corpus of 292 billion tokens spanning 303 million documents, these models excel across multiple benchmarks, including the Open PL LLM Leaderboard, Complex Polish Text Understanding Benchmark, Polish EQ-Bench, and Polish Medical Leaderboard. The 4.5B parameter model achieves results competitive with models 2-3 times its size, while the 1.5B model delivers strong performance despite its extremely compact profile. These advances establish new benchmarks for parameter-efficient language modeling in less-represented languages, making high-quality Polish language AI more accessible for resource-constrained applications.
Authors: Kirill Lukyanov (ISP RAS Research Center for Trusted Artificial Intelligence, Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow Institute of Physics and Technology), Georgii Sazonov (Ivannikov Institute for System Programming of the Russian Academy of Sciences, Lomonosov Moscow State University), Serafim Boyarsky (Yandex School of Data Analysis), Ilya Makarov (1 v 5)
Abstract: Graph Neural Networks (GNNs) have become a cornerstone in graph-based data analysis, with applications in diverse domains such as bioinformatics, social networks, and recommendation systems. However, the interplay between model interpretability and robustness remains poorly understood, especially under adversarial scenarios like poisoning and evasion attacks. This paper presents a comprehensive benchmark to systematically analyze the impact of various factors on the interpretability of GNNs, including the influence of robustness-enhancing defense mechanisms. We evaluate six GNN architectures based on GCN, SAGE, GIN, and GAT across five datasets from two distinct domains, employing four interpretability metrics: Fidelity, Stability, Consistency, and Sparsity. Our study examines how defenses against poisoning and evasion attacks, applied before and during model training, affect interpretability and highlights critical trade-offs between robustness and interpretability. The framework will be published as open source. The results reveal significant variations in interpretability depending on the chosen defense methods and model architecture characteristics. By establishing a standardized benchmark, this work provides a foundation for developing GNNs that are both robust to adversarial threats and interpretable, facilitating trust in their deployment in sensitive applications.
Authors: Hao Zhang, Xunkai Li, Yinlin Zhu, Lianglin Hu
Abstract: Federated graph learning is a widely recognized technique that promotes collaborative training of graph neural networks (GNNs) by multi-client graphs.However, existing approaches heavily rely on the communication of model parameters or gradients for federated optimization and fail to adequately address the data heterogeneity introduced by intricate and diverse graph distributions. Although some methods attempt to share additional messages among the server and clients to improve federated convergence during communication, they introduce significant privacy risks and increase communication overhead. To address these issues, we introduce the concept of a condensed graph as a novel optimization carrier to address FGL data heterogeneity and propose a new FGL paradigm called FedGM. Specifically, we utilize a generalized condensation graph consensus to aggregate comprehensive knowledge from distributed graphs, while minimizing communication costs and privacy risks through a single transmission of the condensed data. Extensive experiments on six public datasets consistently demonstrate the superiority of FedGM over state-of-the-art baselines, highlighting its potential for a novel FGL paradigm.
Authors: Chenxi Liu, Shaowen Zhou, Qianxiong Xu, Hao Miao, Cheng Long, Ziyue Li, Rui Zhao
Abstract: The proliferation of edge devices has generated an unprecedented volume of time series data across different domains, motivating various well-customized methods. Recently, Large Language Models (LLMs) have emerged as a new paradigm for time series analytics by leveraging the shared sequential nature of textual data and time series. However, a fundamental cross-modality gap between time series and LLMs exists, as LLMs are pre-trained on textual corpora and are not inherently optimized for time series. Many recent proposals are designed to address this issue. In this survey, we provide an up-to-date overview of LLMs-based cross-modality modeling for time series analytics. We first introduce a taxonomy that classifies existing approaches into four groups based on the type of textual data employed for time series modeling. We then summarize key cross-modality strategies, e.g., alignment and fusion, and discuss their applications across a range of downstream tasks. Furthermore, we conduct experiments on multimodal datasets from different application domains to investigate effective combinations of textual data and cross-modality strategies for enhancing time series analytics. Finally, we suggest several promising directions for future research. This survey is designed for a range of professionals, researchers, and practitioners interested in LLM-based time series modeling.
Authors: Yongding Tian, Zaid Al-Ars, Maksim Kitsak, Peter Hofstee
Abstract: Visualizations of the loss landscape in neural networks suggest that minima are isolated points. However, both theoretical and empirical studies indicate that it is possible to connect two different minima with a path consisting of intermediate points that also have low loss. In this study, we propose a new algorithm which investigates low-loss paths in the full parameter space, not only between two minima. Our experiments on LeNet5, ResNet18, and Compact Convolutional Transformer architectures consistently demonstrate the existence of such continuous paths in the parameter space. These results suggest that the low-loss region is a fully connected and continuous space in the parameter space. Our findings provide theoretical insight into neural network over-parameterization, highlighting that parameters collectively define a high-dimensional low-loss space, implying parameter redundancy exists only within individual models and not throughout the entire low-loss space. Additionally, our work also provides new visualization methods and opportunities to improve model generalization by exploring the low-loss space that is closer to the origin.
Authors: Anming Gu, Juno Kim
Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting particle systems such as infinite-width two-layer neural networks. However, many problems of interest have constrained domains, which are not solved by existing mean-field algorithms due to the global diffusion term. We study the optimization of probability measures constrained to a convex subset of $\mathbb{R}^d$ by proposing the \emph{mirror mean-field Langevin dynamics} (MMFLD), an extension of MFLD to the mirror Langevin framework. We obtain linear convergence guarantees for the continuous MMFLD via a uniform log-Sobolev inequality, and uniform-in-time propagation of chaos results for its time- and particle-discretized counterpart.
Authors: Yuanpeng Li
Abstract: Compositional generalization is a crucial property in artificial intelligence, enabling models to handle novel combinations of known components. While most deep learning models lack this capability, certain models succeed in specific tasks, suggesting the existence of governing conditions. This paper derives a necessary and sufficient condition for compositional generalization in neural networks. Conceptually, it requires that (i) the computational graph matches the true compositional structure, and (ii) components encode just enough information in training. The condition is supported by mathematical proofs. This criterion combines aspects of architecture design, regularization, and training data properties. A carefully designed minimal example illustrates an intuitive understanding of the condition. We also discuss the potential of the condition for assessing compositional generalization before training. This work is a fundamental theoretical study of compositional generalization in neural networks.
Authors: David Ramos, Lucas Lacasa, Eusebio Valero, Gonzalo Rubio
Abstract: The main objective of this paper is to introduce a transfer learning-enhanced, multi-objective, deep reinforcement learning (DRL) methodology that is able to optimise the geometry of any airfoil based on concomitant aerodynamic and structural criteria. To showcase the method, we aim to maximise the lift-to-drag ratio $C_L/C_D$ while preserving the structural integrity of the airfoil -- as modelled by its maximum thickness -- and train the DRL agent using a list of different transfer learning (TL) strategies. The performance of the DRL agent is compared with Particle Swarm Optimisation (PSO), a traditional gradient-free optimisation method. Results indicate that DRL agents are able to perform multi-objective shape optimisation, that the DRL approach outperforms PSO in terms of computational efficiency and shape optimisation performance, and that the TL-enhanced DRL agent achieves performance comparable to the DRL one, while further saving substantial computational resources.
Authors: Xuan Lin, Qingrui Liu, Hongxin Xiang, Daojian Zeng, Xiangxiang Zeng
Abstract: Chemical reaction and retrosynthesis prediction are fundamental tasks in drug discovery. Recently, large language models (LLMs) have shown potential in many domains. However, directly applying LLMs to these tasks faces two major challenges: (i) lacking a large-scale chemical synthesis-related instruction dataset; (ii) ignoring the close correlation between reaction and retrosynthesis prediction for the existing fine-tuning strategies. To address these challenges, we propose ChemDual, a novel LLM framework for accurate chemical synthesis. Specifically, considering the high cost of data acquisition for reaction and retrosynthesis, ChemDual regards the reaction-and-retrosynthesis of molecules as a related recombination-and-fragmentation process and constructs a large-scale of 4.4 million instruction dataset. Furthermore, ChemDual introduces an enhanced LLaMA, equipped with a multi-scale tokenizer and dual-task learning strategy, to jointly optimize the process of recombination and fragmentation as well as the tasks between reaction and retrosynthesis prediction. Extensive experiments on Mol-Instruction and USPTO-50K datasets demonstrate that ChemDual achieves state-of-the-art performance in both predictions of reaction and retrosynthesis, outperforming the existing conventional single-task approaches and the general open-source LLMs. Through molecular docking analysis, ChemDual generates compounds with diverse and strong protein binding affinity, further highlighting its strong potential in drug design.
Authors: Shubham Vaishnav, Praveen Kumar Donta, Sindri Magn\'usson
Abstract: Internet of Things (IoT) systems increasingly operate in environments where devices must respond in real time while managing fluctuating resource constraints, including energy and bandwidth. Yet, current approaches often fall short in addressing scenarios where operational constraints evolve over time. To address these limitations, we propose a novel Budgeted Multi-Armed Bandit framework tailored for IoT applications with dynamic operational limits. Our model introduces a decaying violation budget, which permits limited constraint violations early in the learning process and gradually enforces stricter compliance over time. We present the Budgeted Upper Confidence Bound (UCB) algorithm, which adaptively balances performance optimization and compliance with time-varying constraints. We provide theoretical guarantees showing that Budgeted UCB achieves sublinear regret and logarithmic constraint violations over the learning horizon. Extensive simulations in a wireless communication setting show that our approach achieves faster adaptation and better constraint satisfaction than standard online learning methods. These results highlight the framework's potential for building adaptive, resource-aware IoT systems.
Authors: Shiwei Guo, Ziang Chen, Yupeng Ma, Yunfei Han, Yi Wang
Abstract: The Transformer model has shown strong performance in multivariate time series forecasting by leveraging channel-wise self-attention. However, this approach lacks temporal constraints when computing temporal features and does not utilize cumulative historical series effectively.To address these limitations, we propose the Structured Channel-wise Transformer with Cumulative Historical state (SCFormer). SCFormer introduces temporal constraints to all linear transformations, including the query, key, and value matrices, as well as the fully connected layers within the Transformer. Additionally, SCFormer employs High-order Polynomial Projection Operators (HiPPO) to deal with cumulative historical time series, allowing the model to incorporate information beyond the look-back window during prediction. Extensive experiments on multiple real-world datasets demonstrate that SCFormer significantly outperforms mainstream baselines, highlighting its effectiveness in enhancing time series forecasting. The code is publicly available at https://github.com/ShiweiGuo1995/SCFormer
Authors: Andrey Sidorenko
Abstract: Large language models (LLMs) have shown promise in synthetic tabular data generation, yet existing methods struggle to preserve complex feature dependencies, particularly among categorical variables. This work introduces a probability-driven prompting approach that leverages LLMs to estimate conditional distributions, enabling more accurate and scalable data synthesis. The results highlight the potential of prompting probobility distributions to enhance the statistical fidelity of LLM-generated tabular data.
Authors: Andrzej Mizera, Jakub Zarzycki
Abstract: Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic potential for complex diseases. However, discovering reprogramming strategies through classical wet-lab experiments is hindered by lengthy time commitments and high costs. In this study, we explore the use of deep reinforcement learning (DRL) to control Boolean network models of complex biological systems, such as gene regulatory networks and signalling pathway networks. We formulate a novel control problem for Boolean network models under the asynchronous update mode in the context of cellular reprogramming. To facilitate scalability, we consider our previously introduced concept of a pseudo-attractor and we improve our procedure for effective identification of pseudo-attractor states. Finally, we devise a computational framework to solve the control problem. To leverage the structure of biological systems, we incorporate graph neural networks with graph convolutions into the artificial neural network approximator for the action-value function learned by the DRL agent. Experiments on a number of large real-world biological networks from literature demonstrate the scalability and effectiveness of our approach.
Authors: Xiao Shou, Debarun Bhattacharjya, Yanna Ding, Chen Zhao, Rui Li, Jianxi Gao
Abstract: Addressing the computational challenges inherent in training large-scale deep neural networks remains a critical endeavor in contemporary machine learning research. While previous efforts have focused on enhancing training efficiency through techniques such as gradient descent with momentum, learning rate scheduling, and weight regularization, the demand for further innovation continues to burgeon as model sizes keep expanding. In this study, we introduce a novel framework which diverges from conventional approaches by leveraging long-term time series forecasting techniques. Our method capitalizes solely on initial and final weight values, offering a streamlined alternative for complex model architectures. We also introduce a novel regularizer that is tailored to enhance the forecasting performance of our approach. Empirical evaluations conducted on synthetic weight sequences and real-world deep learning architectures, including the prominent large language model DistilBERT, demonstrate the superiority of our method in terms of forecasting accuracy and computational efficiency. Notably, our framework showcases improved performance while requiring minimal additional computational overhead, thus presenting a promising avenue for accelerating the training process across diverse tasks and architectures.
Authors: Pons Gerard, Bilalli Besim, Queralt Anna
Abstract: Recent advances in Large Language Models (LLMs) have positioned them as a prominent solution for Natural Language Processing tasks. Notably, they can approach these problems in a zero or few-shot manner, thereby eliminating the need for training or fine-tuning task-specific models. However, LLMs face some challenges, including hallucination and the presence of outdated knowledge or missing information from specific domains in the training data. These problems cannot be easily solved by retraining the models with new data as it is a time-consuming and expensive process. To mitigate these issues, Knowledge Graphs (KGs) have been proposed as a structured external source of information to enrich LLMs. With this idea, in this work we use KGs to enhance LLMs for zero-shot Entity Disambiguation (ED). For that purpose, we leverage the hierarchical representation of the entities' classes in a KG to gradually prune the candidate space as well as the entities' descriptions to enrich the input prompt with additional factual knowledge. Our evaluation on popular ED datasets shows that the proposed method outperforms non-enhanced and description-only enhanced LLMs, and has a higher degree of adaptability than task-specific models. Furthermore, we conduct an error analysis and discuss the impact of the leveraged KG's semantic expressivity on the ED performance.
Authors: Jiaxiang Yi, Miguel A. Bessa
Abstract: Real-world data contains aleatoric uncertainty - irreducible noise arising from imperfect measurements or from incomplete knowledge about the data generation process. Mean variance estimation (MVE) networks can learn this type of uncertainty but require ad-hoc regularization strategies to avoid overfitting and are unable to predict epistemic uncertainty (model uncertainty). Conversely, Bayesian neural networks predict epistemic uncertainty but are notoriously difficult to train due to the approximate nature of Bayesian inference. We propose to cooperatively train a variance network with a Bayesian neural network and demonstrate that the resulting model disentangles aleatoric and epistemic uncertainties while improving the mean estimation. We demonstrate the effectiveness and scalability of this method across a diverse range of datasets, including a time-dependent heteroscedastic regression dataset we created where the aleatoric uncertainty is known. The proposed method is straightforward to implement, robust, and adaptable to various model architectures.
Authors: Zheng Lin, Yuxin Zhang, Zhe Chen, Zihan Fang, Xianhao Chen, Praneeth Vepakomma, Wei Ni, Jun Luo, Yue Gao
Abstract: Recently, large language models (LLMs) have achieved remarkable breakthroughs, revolutionizing the natural language processing domain and beyond. Due to immense parameter sizes, fine-tuning these models with private data for diverse downstream tasks has become mainstream. Though federated learning (FL) offers a promising solution for fine-tuning LLMs without sharing raw data, substantial computing costs hinder its democratization. Moreover, in real-world scenarios, private client devices often possess heterogeneous computing resources, further complicating LLM fine-tuning. To combat these challenges, we propose HSplitLoRA, a heterogeneous parameter-efficient fine-tuning (PEFT) framework built on split learning (SL) and low-rank adaptation (LoRA) fine-tuning, for efficiently fine-tuning LLMs on heterogeneous client devices. HSplitLoRA first identifies important weights based on their contributions to LLM training. It then dynamically configures the decomposition ranks of LoRA adapters for selected weights and determines the model split point according to varying computing budgets of client devices. Finally, a noise-free adapter aggregation mechanism is devised to support heterogeneous adapter aggregation without introducing noise. Extensive experiments demonstrate that HSplitLoRA outperforms state-of-the-art benchmarks in training accuracy and convergence speed.
Authors: Zhaorui Dong, Yushun Zhang, Zhi-Quan Luo, Jianfeng Yao, Ruoyu Sun
Abstract: Empirical studies reported that the Hessian matrix of neural networks (NNs) exhibits a near-block-diagonal structure, yet its theoretical foundation remains unclear. In this work, we reveal two forces that shape the Hessian structure: a ``static force'' rooted in the architecture design, and a ``dynamic force'' arisen from training. We then provide a rigorous theoretical analysis of ``static force'' at random initialization. We study linear models and 1-hidden-layer networks with the mean-square (MSE) loss and the Cross-Entropy (CE) loss for classification tasks. By leveraging random matrix theory, we compare the limit distributions of the diagonal and off-diagonal Hessian blocks and find that the block-diagonal structure arises as $C \rightarrow \infty$, where $C$ denotes the number of classes. Our findings reveal that $C$ is a primary driver of the near-block-diagonal structure. These results may shed new light on the Hessian structure of large language models (LLMs), which typically operate with a large $C$ exceeding $10^4$ or $10^5$.
Authors: Cong Qi, Hanzhang Fang, Siqi jiang, Tianxing Hu, Wei Zhi
Abstract: Understanding the binding specificity between T-cell receptors (TCRs) and peptide-major histocompatibility complexes (pMHCs) is central to immunotherapy and vaccine development. However, current predictive models struggle with generalization, especially in data-scarce settings and when faced with novel epitopes. We present LANTERN (Large lAnguage model-powered TCR-Enhanced Recognition Network), a deep learning framework that combines large-scale protein language models with chemical representations of peptides. By encoding TCR \b{eta}-chain sequences using ESM-1b and transforming peptide sequences into SMILES strings processed by MolFormer, LANTERN captures rich biological and chemical features critical for TCR-peptide recognition. Through extensive benchmarking against existing models such as ChemBERTa, TITAN, and NetTCR, LANTERN demonstrates superior performance, particularly in zero-shot and few-shot learning scenarios. Our model also benefits from a robust negative sampling strategy and shows significant clustering improvements via embedding analysis. These results highlight the potential of LANTERN to advance TCR-pMHC binding prediction and support the development of personalized immunotherapies.
Authors: Carlo Siebenschuh, Kyle Hippe, Ozan Gokdemir, Alexander Brace, Arham Khan, Khalid Hossain, Yadu Babuji, Nicholas Chia, Venkatram Vishwanath, Rick Stevens, Arvind Ramanathan, Ian Foster, Robert Underwood
Abstract: Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive heuristics (for simple documents) to computationally intensive ML-driven systems (for complex or degraded ones). The choice of the "best" parser for a particular document depends on its computational cost and the accuracy of its output. To address these issues, we introduce an Adaptive Parallel PDF Parsing and Resource Scaling Engine (AdaParse), a data-driven strategy for assigning an appropriate parser to each document. We enlist scientists to select preferred parser outputs and incorporate this information through direct preference optimization (DPO) into AdaParse, thereby aligning its selection process with human judgment. AdaParse then incorporates hardware requirements and predicted accuracy of each parser to orchestrate computational resources efficiently for large-scale parsing campaigns. We demonstrate that AdaParse, when compared to state-of-the-art parsers, improves throughput by $17\times$ while still achieving comparable accuracy (0.2 percent better) on a benchmark set of 1000 scientific documents. AdaParse's combination of high accuracy and parallel scalability makes it feasible to parse large-scale scientific document corpora to support the development of high-quality, trillion-token-scale text datasets. The implementation is available at https://github.com/7shoe/AdaParse/
Authors: Zhiyong Jin, Runhua Xu, Chao Li, Yizhong Liu, Jianxin Li
Abstract: Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, yet it faces significant challenges in communication efficiency and vulnerability to poisoning attacks. While sparsification techniques mitigate communication overhead by transmitting only critical model parameters, they inadvertently amplify security risks: adversarial clients can exploit sparse updates to evade detection and degrade model performance. Existing defense mechanisms, designed for standard FL communication scenarios, are ineffective in addressing these vulnerabilities within sparsified FL. To bridge this gap, we propose FLARE, a novel federated learning framework that integrates sparse index mask inspection and model update sign similarity analysis to detect and mitigate poisoning attacks in sparsified FL. Extensive experiments across multiple datasets and adversarial scenarios demonstrate that FLARE significantly outperforms existing defense strategies, effectively securing sparsified FL against poisoning attacks while maintaining communication efficiency.
Authors: Gan Zhang, Megha Rao, Janni Yuval, Ming Zhao
Abstract: Machine learning (ML) models are successful with weather forecasting and have shown progress in climate simulations, yet leveraging them for useful climate predictions needs exploration. Here we show this feasibility using NeuralGCM, a hybrid ML-physics atmospheric model, for seasonal predictions of large-scale atmospheric variability and Northern Hemisphere tropical cyclone (TC) activity. Inspired by physical model studies, we simplify boundary conditions, assuming sea surface temperature (SST) and sea ice follow their climatological cycle but persist anomalies present at initialization. With such forcings, NeuralGCM simulates realistic atmospheric circulation and TC climatology patterns. Furthermore, this configuration yields useful seasonal predictions (July-November) for the tropical atmosphere and various TC activity metrics. Notably, the prediction skill for TC frequency in the North Atlantic and East Pacific basins is comparable to existing physical models. These findings highlight the promise of leveraging ML models with physical insights to model TC risks and deliver seamless weather-climate predictions.
Authors: Abdoul Majid O. Thiombiano, Brahim Hnich, Ali Ben Mrad, Mohamed Wiem Mkaouer
Abstract: This paper introduces MoxE, a novel architecture that synergistically combines the Extended Long Short-Term Memory (xLSTM) with the Mixture of Experts (MoE) framework to address critical scalability and efficiency challenges in large language models (LLMs). The proposed method effectively leverages xLSTM's innovative memory structures while strategically introducing sparsity through MoE to substantially reduce computational overhead. At the heart of our approach is a novel entropy-based routing mechanism, designed to dynamically route tokens to specialized experts, thereby ensuring efficient and balanced resource utilization. This entropy awareness enables the architecture to effectively manage both rare and common tokens, with mLSTM blocks being favored to handle rare tokens. To further enhance generalization, we introduce a suite of auxiliary losses, including entropy-based and group-wise balancing losses, ensuring robust performance and efficient training. Theoretical analysis and empirical evaluations rigorously demonstrate that MoxE achieves significant efficiency gains and enhanced effectiveness compared to existing approaches, marking a notable advancement in scalable LLM architectures.
Authors: Denis Parfenov, Anton Parfenov
Abstract: Due to the increasing number of tasks that are solved on remote servers, identifying and classifying traffic is an important task to reduce the load on the server. There are various methods for classifying traffic. This paper discusses machine learning models for solving this problem. However, such ML models are also subject to attacks that affect the classification result of network traffic. To protect models, we proposed a solution based on an autoencoder
Authors: Sabbir M. Saleh, Nazim Madhavji, John Steinbacher
Abstract: Protecting cloud applications is crucial in an age where security constantly threatens the digital world. The inevitable cyber-attacks throughout the CI/CD pipeline make cloud security innovations necessary. This research is motivated by applying Natural Language Processing (NLP) methodologies, such as Topic Modelling, to analyse cloud security data and predict future attacks. This research aims to use topic modelling, specifically Latent Dirichlet Allocation (LDA) and Probabilistic Latent Semantic Analysis (pLSA). Utilising LDA and PLSA, security-related text data, such as reports, logs, and other relevant documents, will be analysed and sorted into relevant topics (such as phishing or encryption). These algorithms may apply through Python using the Gensim framework. The topics shall be utilised to detect vulnerabilities within relevant CI/CD pipeline records or log data. This application of Topic Modelling anticipates providing a new form of vulnerability detection, improving overall security throughout the CI/CD pipeline.
Authors: Zongxia Li, Xiyang Wu, Yubin Qin, Guangyao Shi, Hongyang Du, Dinesh Manocha, Tianyi Zhou, Jordan Lee Boyd-Graber
Abstract: Synthetic video generation with foundation models has gained attention for its realism and wide applications. While these models produce high-quality frames, they often fail to respect common sense and physical laws, resulting in abnormal content. Existing metrics like VideoScore emphasize general quality but ignore such violations and lack interpretability. A more insightful approach is using multi-modal large language models (MLLMs) as interpretable evaluators, as seen in FactScore. Yet, MLLMs' ability to detect abnormalities in synthetic videos remains underexplored. To address this, we introduce VideoHallu, a benchmark featuring synthetic videos from models like Veo2, Sora, and Kling, paired with expert-designed QA tasks solvable via human-level reasoning across various categories. We assess several SoTA MLLMs, including GPT-4o, Gemini-2.5-Pro, Qwen-2.5-VL, and newer models like Video-R1 and VideoChat-R1. Despite strong real-world performance on MVBench and MovieChat, these models still hallucinate on basic commonsense and physics tasks in synthetic settings, underscoring the challenge of hallucination. We further fine-tune SoTA MLLMs using Group Relative Policy Optimization (GRPO) on real and synthetic commonsense/physics data. Results show notable accuracy gains, especially with counterexample integration, advancing MLLMs' reasoning capabilities. Our data is available at https://github.com/zli12321/VideoHallu.
Authors: Pedro Abdalla, Roman Vershynin
Abstract: Given a text, can we determine whether it was generated by a large language model (LLM) or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversary has access to most of the model, we propose an unremovable watermarking scheme.
Authors: Zexi Yao, Nata\v{s}a Kr\v{c}o, Georgi Ganev, Yves-Alexandre de Montjoye
Abstract: Synthetic data has become an increasingly popular way to share data without revealing sensitive information. Though Membership Inference Attacks (MIAs) are widely considered the gold standard for empirically assessing the privacy of a synthetic dataset, practitioners and researchers often rely on simpler proxy metrics such as Distance to Closest Record (DCR). These metrics estimate privacy by measuring the similarity between the training data and generated synthetic data. This similarity is also compared against that between the training data and a disjoint holdout set of real records to construct a binary privacy test. If the synthetic data is not more similar to the training data than the holdout set is, it passes the test and is considered private. In this work we show that, while computationally inexpensive, DCR and other distance-based metrics fail to identify privacy leakage. Across multiple datasets and both classical models such as Baynet and CTGAN and more recent diffusion models, we show that datasets deemed private by proxy metrics are highly vulnerable to MIAs. We similarly find both the binary privacy test and the continuous measure based on these metrics to be uninformative of actual membership inference risk. We further show that these failures are consistent across different metric hyperparameter settings and record selection methods. Finally, we argue DCR and other distance-based metrics to be flawed by design and show a example of a simple leakage they miss in practice. With this work, we hope to motivate practitioners to move away from proxy metrics to MIAs as the rigorous, comprehensive standard of evaluating privacy of synthetic data, in particular to make claims of datasets being legally anonymous.
Authors: Hongbin Zhong, Matthew Lentz, Nina Narodytska, Adriana Szekeres, Kexin Rong
Abstract: As vector databases gain traction in enterprise applications, robust access control has become critical to safeguard sensitive data. Access control in these systems is often implemented through hybrid vector queries, which combine nearest neighbor search on vector data with relational predicates based on user permissions. However, existing approaches face significant trade-offs: creating dedicated indexes for each user minimizes query latency but introduces excessive storage redundancy, while building a single index and applying access control after vector search reduces storage overhead but suffers from poor recall and increased query latency. This paper introduces HoneyBee, a dynamic partitioning framework that bridges the gap between these approaches by leveraging the structure of Role-Based Access Control (RBAC) policies. RBAC, widely adopted in enterprise settings, groups users into roles and assigns permissions to those roles, creating a natural "thin waist" in the permission structure that is ideal for partitioning decisions. Specifically, HoneyBee produces overlapping partitions where vectors can be strategically replicated across different partitions to reduce query latency while controlling storage overhead. By introducing analytical models for the performance and recall of the vector search, HoneyBee formulates the partitioning strategy as a constrained optimization problem to dynamically balance storage, query efficiency, and recall. Evaluations on RBAC workloads demonstrate that HoneyBee reduces storage redundancy compared to role partitioning and achieves up to 6x faster query speeds than row-level security (RLS) with only 1.4x storage increase, offering a practical middle ground for secure and efficient vector search.
Authors: Cor Steging, Silja Renooij, Bart Verheij
Abstract: Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the basis of witness testimony, focusing on the underlying argument attack structure. We dynamically generate both linear and non-linear argument attack graphs of varying complexity and translate these into reasoning puzzles about witness testimony expressed in natural language. We show that state-of-the-art large language models often fail in these reasoning puzzles, already at low complexity. Obvious mistakes are made by the models, and their inconsistent performance indicates that their reasoning capabilities are brittle. Furthermore, at higher complexity, even state-of-the-art models specifically presented for reasoning capabilities make mistakes. We show the viability of using a parametrized benchmark with varying complexity to evaluate the reasoning capabilities of generative language models. As such, the findings contribute to a better understanding of the limitations of the reasoning capabilities of generative models, which is essential when designing responsible AI systems in the legal domain.
Authors: Daniele Grandi, Fabian Riquelme
Abstract: In this work, we seek to understand the performance of large language models in the mechanical engineering domain. We leverage the semantic data found in the ABC dataset, specifically the assembly names that designers assigned to the overall assemblies, and the individual semantic part names that were assigned to each part. After pre-processing the data we developed two unsupervised tasks to evaluate how different model architectures perform on domain-specific data: a binary sentence-pair classification task and a zero-shot classification task. We achieved a 0.62 accuracy for the binary sentence-pair classification task with a fine-tuned model that focuses on fighting over-fitting: 1) modifying learning rates, 2) dropout values, 3) Sequence Length, and 4) adding a multi-head attention layer. Our model on the zero-shot classification task outperforms the baselines by a wide margin, and achieves a top-1 classification accuracy of 0.386. The results shed some light on the specific failure modes that arise when learning from language in this domain.
Authors: Liaoyaqi Wang, Zhengping Jiang, Anqi Liu, Benjamin Van Durme
Abstract: We present a state-of-the-art model for fine-grained probability estimation of propositions conditioned on context. Recent advances in large language models (LLMs) have significantly enhanced their reasoning capabilities, particularly on well-defined tasks with complete information. However, LLMs continue to struggle with making accurate and well-calibrated probabilistic predictions under uncertainty or partial information. While incorporating uncertainty into model predictions often boosts performance, obtaining reliable estimates of that uncertainty remains understudied. In particular, LLM probability estimates tend to be coarse and biased towards more frequent numbers. Through a combination of human and synthetic data creation and assessment, scaling to larger models, and better supervision, we propose a set of strong and precise probability estimation models. We conduct systematic evaluations across tasks that rely on conditional probability estimation and show that our approach consistently outperforms existing fine-tuned and prompting-based methods by a large margin.
Authors: Jianxing Qin, Jingrong Chen, Xinhao Kong, Yongji Wu, Liang Luo, Zhaodong Wang, Ying Zhang, Tingjun Chen, Alvin R. Lebeck, Danyang Zhuo
Abstract: To accommodate ever-increasing model complexity, modern machine learning (ML) systems have to scale to large GPU clusters. Changes in ML model architecture, ML system implementation, and cluster configuration can significantly affect overall ML system performance. However, quantifying the performance impact before deployment is challenging. Existing performance estimation methods use performance modeling or static workload simulation. These techniques are not general: they requires significant human effort and computation capacity to generate training data or a workload. It is also difficult to adapt ML systems to use these techniques. This paper introduces, Phantora, a live GPU cluster simulator for performance estimation. Phantora runs minimally modified ML models and frameworks, intercepting and simulating GPU-related operations to enable high-fidelity performance estimation. Phantora overcomes several research challenges in integrating an event-driven network simulator with live system execution, and introduces a set of techniques to improve simulation speed, scalability, and accuracy. Our evaluation results show that Phantora can deliver similar estimation accuracy to the state-of-the-art workload simulation approach with only one GPU, while reducing human effort and increasing generalizability.
Authors: Amit Rath
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and task generalization. However, their application to structured data analysis remains fragile due to inconsistencies in schema interpretation, misalignment between user intent and model output, and limited mechanisms for self-correction when failures occur. This paper introduces the STROT Framework (Structured Task Reasoning and Output Transformation), a method for structured prompting and feedback-driven transformation logic generation aimed at improving the reliability and semantic alignment of LLM-based analytical workflows. STROT begins with lightweight schema introspection and sample-based field classification, enabling dynamic context construction that captures both the structure and statistical profile of the input data. This contextual information is embedded in structured prompts that guide the model toward generating task-specific, interpretable outputs. To address common failure modes in complex queries, STROT incorporates a refinement mechanism in which the model iteratively revises its outputs based on execution feedback and validation signals. Unlike conventional approaches that rely on static prompts or single-shot inference, STROT treats the LLM as a reasoning agent embedded within a controlled analysis loop -- capable of adjusting its output trajectory through planning and correction. The result is a robust and reproducible framework for reasoning over structured data with LLMs, applicable to diverse data exploration and analysis tasks where interpretability, stability, and correctness are essential.
Authors: Samuel J. Kaufman, Ren\'e Just, Rastislav Bodik
Abstract: High-throughput neural network inference requires coordinating many optimization decisions, including parallel tiling, microkernel selection, and data layout. The product of these decisions forms a search space of programs which is typically intractably large. Existing approaches (e.g., auto-schedulers) often address this problem by sampling this space heuristically. In contrast, we introduce a dynamic-programming-based approach to explore more of the search space by iteratively decomposing large program specifications into smaller specifications reachable from a set of rewrites, then composing a final program from each rewrite that minimizes an affine cost model. To reduce memory requirements, we employ a novel memoization table representation, which indexes specifications by coordinates in $Z_{\geq 0}$ and compresses identical, adjacent solutions. This approach can visit a much larger set of programs than prior work. To evaluate the approach, we developed Morello, a compiler which lowers specifications roughly equivalent to a few-node XLA computation graph to x86. Notably, we found that an affine cost model is sufficient to surface high-throughput programs. For example, Morello synthesized a collection of matrix multiplication benchmarks targeting a Zen 1 CPU, including a 1x2048x16384, bfloat16-to-float32 vector-matrix multiply, which was integrated into Google's gemma.cpp.
Authors: Nicolas Coloma, William Kleiber
Abstract: L\'evy processes are widely used in financial modeling due to their ability to capture discontinuities and heavy tails, which are common in high-frequency asset return data. However, parameter estimation remains a challenge when associated likelihoods are unavailable or costly to compute. We propose a fast and accurate method for L\'evy parameter estimation using the neural Bayes estimation (NBE) framework -- a simulation-based, likelihood-free approach that leverages permutation-invariant neural networks to approximate Bayes estimators. Through extensive simulations across several L\'evy models, we show that NBE outperforms traditional methods in both accuracy and runtime, while also enabling rapid bootstrap-based uncertainty quantification. We illustrate our approach on a challenging high-frequency cryptocurrency return dataset, where the method captures evolving parameter dynamics and delivers reliable and interpretable inference at a fraction of the computational cost of traditional methods. NBE provides a scalable and practical solution for inference in complex financial models, enabling parameter estimation and uncertainty quantification over an entire year of data in just seconds. We additionally investigate nearly a decade of high-frequency Bitcoin returns, requiring less than one minute to estimate parameters under the proposed approach.
Authors: Shreya Sareen, Swayamtrupta Panda
Abstract: Active Galactic Nuclei (AGNs) are among the most luminous objects in the universe, making them valuable probes for studying galaxy evolution. However, understanding how AGN properties evolve over cosmic time remains a fundamental challenge. This study investigates whether AGNs at low redshift (nearby) can serve as proxies for their high-redshift (distant) counterparts by identifying spectral 'doppelg\"angers', AGNs with remarkably similar emission line properties despite being separated by vast cosmic distances. We analyze key spectral features of bona fide AGNs using the Sloan Digital Sky Survey's Data Release 16, including continuum and emission lines: Nitrogen (N V), Carbon (C IV), Magnesium (Mg II), Hydrogen-beta (H$\beta$), and Iron (Fe II - optical and UV) emission lines. We incorporated properties such as equivalent width, velocity dispersion in the form of full width at half maximum (FWHM), and continuum luminosities (135nm, 300nm, and 510nm) closest to these prominent lines. Our initial findings suggest the existence of multiple AGNs with highly similar spectra, hinting at the possibility that local AGNs may indeed share intrinsic properties with high-redshift ones. We showcase here one of the better candidate pairs of AGNs resulting from our analyses.
Authors: Srecharan Selvam, Abhisesh Silwal, George Kantor
Abstract: T-Rex (The Robot for Extracting Leaf Samples) is a gantry-based robotic system developed for autonomous leaf localization, selection, and grasping in greenhouse environments. The system integrates a 6-degree-of-freedom manipulator with a stereo vision pipeline to identify and interact with target leaves. YOLOv8 is used for real-time leaf segmentation, and RAFT-Stereo provides dense depth maps, allowing the reconstruction of 3D leaf masks. These observations are processed through a leaf grasping algorithm that selects the optimal leaf based on clutter, visibility, and distance, and determines a grasp point by analyzing local surface flatness, top-down approachability, and margin from edges. The selected grasp point guides a trajectory executed by ROS-based motion controllers, driving a custom microneedle-equipped end-effector to clamp the leaf and simulate tissue sampling. Experiments conducted with artificial plants under varied poses demonstrate that the T-Rex system can consistently detect, plan, and perform physical interactions with plant-like targets, achieving a grasp success rate of 66.6\%. This paper presents the system architecture, implementation, and testing of T-Rex as a step toward plant sampling automation in Controlled Environment Agriculture (CEA).
Authors: Christos Zangos, Danish Ebadulla, Thomas Christopher Sprague, Ambuj Singh
Abstract: This work introduces a novel approach to fMRI-based visual image reconstruction using a subject-agnostic common representation space. We show that the brain signals of the subjects can be aligned in this common space during training to form a semantically aligned common brain. This is leveraged to demonstrate that aligning subject-specific lightweight modules to a reference subject is significantly more efficient than traditional end-to-end training methods. Our approach excels in low-data scenarios. We evaluate our methods on different datasets, demonstrating that the common space is subject and dataset-agnostic.
Authors: Sarvesh Shashidhar, Ritik, Nachiketa Patil, Suraj Racha, Ganesh Ramakrishnan
Abstract: Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human Feedback. In this work, we investigate the performance of DPO using open-source preference datasets. One of the major drawbacks of DPO is that it doesn't induce granular scoring and treats all the segments of the responses with equal propensity. However, this is not practically true for human preferences since even "good" responses have segments that may not be preferred by the annotator. To resolve this, a 2-dimensional scoring for DPO alignment called 2D-DPO was proposed. We explore the 2D-DPO alignment paradigm and the advantages it provides over the standard DPO by comparing their win rates. It is observed that these methods, even though effective, are not robust to label/score noise. To counter this, we propose an approach of incorporating segment-level score noise robustness to the 2D-DPO algorithm. Along with theoretical backing, we also provide empirical verification in favour of the algorithm and introduce other noise models that can be present.
Authors: Yu Mao, Jingzong Li, Jun Wang, Hong Xu, Tei-Wei Kuo, Nan Guan, Chun Jason Xue
Abstract: Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels. Consequently, it raises significant challenges in applying the neural image compression to edge devices that are developed for powerful servers with high computational and storage capacities. We take a step to solve the challenges by proposing a new transformer-based edge-compute-free image coding framework called Easz. Easz shifts the computational overhead to the server, and hence avoids the heavy encoding and model switching overhead on the edge. Easz utilizes a patch-erase algorithm to selectively remove image contents using a conditional uniform-based sampler. The erased pixels are reconstructed on the receiver side through a transformer-based framework. To further reduce the computational overhead on the receiver, we then introduce a lightweight transformer-based reconstruction structure to reduce the reconstruction load on the receiver side. Extensive evaluations conducted on a real-world testbed demonstrate multiple advantages of Easz over existing compression approaches, in terms of adaptability to different compression levels, computational efficiency, and image reconstruction quality.
Authors: Siyang Jiang, Bufang Yang, Lilin Xu, Mu Yuan, Yeerzhati Abudunuer, Kaiwei Liu, Liekang Zeng, Hongkai Chen, Zhenyu Yan, Xiaofan Jiang, Guoliang Xing
Abstract: The rapid advancements in Large Vision Language Models (LVLMs) offer the potential to surpass conventional labeling by generating richer, more detailed descriptions of on-device human behavior understanding (HBU) in low-resolution vision systems, such as depth, thermal, and infrared. However, existing large vision language model (LVLM) approaches are unable to understand low-resolution data well as they are primarily designed for high-resolution data, such as RGB images. A quick fixing approach is to caption a large amount of low-resolution data, but it requires a significant amount of labor-intensive annotation efforts. In this paper, we propose a novel, labor-saving system, Llambda, designed to support low-resolution HBU. The core idea is to leverage limited labeled data and a large amount of unlabeled data to guide LLMs in generating informative captions, which can be combined with raw data to effectively fine-tune LVLM models for understanding low-resolution videos in HBU. First, we propose a Contrastive-Oriented Data Labeler, which can capture behavior-relevant information from long, low-resolution videos and generate high-quality pseudo labels for unlabeled data via contrastive learning. Second, we propose a Physical-Knowledge Guided Captioner, which utilizes spatial and temporal consistency checks to mitigate errors in pseudo labels. Therefore, it can improve LLMs' understanding of sequential data and then generate high-quality video captions. Finally, to ensure on-device deployability, we employ LoRA-based efficient fine-tuning to adapt LVLMs for low-resolution data. We evaluate Llambda using a region-scale real-world testbed and three distinct low-resolution datasets, and the experiments show that Llambda outperforms several state-of-the-art LVLM systems up to $40.03\%$ on average Bert-Score.
Authors: Vivek Shripad Borkar
Abstract: It has been observed by Belkin et al.\ that overparametrized neural networks exhibit a `double descent' phenomenon. That is, as the model complexity, as reflected in the number of features, increases, the training error initially decreases, then increases, and then decreases again. A counterpart of this phenomenon in the time domain has been noted in the context of epoch-wise training, viz., that the training error decreases with time, then increases, then decreases again. This note presents a plausible explanation for this phenomenon by using the theory of two time scale stochastic approximation and singularly perturbed differential equations, applied to the continuous time limit of the gradient dynamics. This adds a `dynamic' angle to an already well studied theme.
Authors: Orlando J\"ahde, Thorsten Weber, R\"udiger Buchkremer
Abstract: Biased news reporting poses a significant threat to informed decision-making and the functioning of democracies. This study introduces a novel methodology for scalable, minimally biased analysis of media bias in political news. The proposed approach examines event selection, labeling, word choice, and commission and omission biases across news sources by leveraging natural language processing techniques, including hierarchical topic modeling, sentiment analysis, and ontology learning with large language models. Through three case studies related to current political events, we demonstrate the methodology's effectiveness in identifying biases across news sources at various levels of granularity. This work represents a significant step towards scalable, minimally biased media bias analysis, laying the groundwork for tools to help news consumers navigate an increasingly complex media landscape.
Authors: Ayoub Abraich
Abstract: Estimating the causal effect of time-varying treatments on survival outcomes is a challenging task in many domains, particularly in medicine where treatment protocols adapt over time. While recent advances in representation learning have improved causal inference for static treatments, extending these methods to dynamic treatment regimes with survival outcomes remains under-explored. In this paper, we introduce TV-SurvCaus, a novel framework that extends representation balancing techniques to the time-varying treatment setting for survival analysis. We provide theoretical guarantees through (1) a generalized bound for time-varying precision in estimation of heterogeneous effects, (2) variance control via sequential balancing weights, (3) consistency results for dynamic treatment regimes, (4) convergence rates for representation learning with temporal dependencies, and (5) a formal bound on the bias due to treatment-confounder feedback. Our neural architecture incorporates sequence modeling to handle temporal dependencies while balancing time-dependent representations. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that TV-SurvCaus outperforms existing methods in estimating individualized treatment effects with time-varying covariates and treatments. Our framework advances the field of causal inference by enabling more accurate estimation of treatment effects in dynamic, longitudinal settings with survival outcomes.
Authors: Chidimma Opara
Abstract: The increasing sophistication of AI-generated texts highlights the urgent need for accurate and transparent detection tools, especially in educational settings, where verifying authorship is essential. Existing literature has demonstrated that the application of stylometric features with machine learning classifiers can yield excellent results. Building on this foundation, this study proposes a comprehensive framework that integrates stylometric analysis with psycholinguistic theories, offering a clear and interpretable approach to distinguishing between AI-generated and human-written texts. This research specifically maps 31 distinct stylometric features to cognitive processes such as lexical retrieval, discourse planning, cognitive load management, and metacognitive self-monitoring. In doing so, it highlights the unique psycholinguistic patterns found in human writing. Through the intersection of computational linguistics and cognitive science, this framework contributes to the development of reliable tools aimed at preserving academic integrity in the era of generative AI.
Authors: Anthony Nouy, Alexandre Pasco
Abstract: We aim to approximate a continuously differentiable function $u:\mathbb{R}^d \rightarrow \mathbb{R}$ by a composition of functions $f\circ g$ where $g:\mathbb{R}^d \rightarrow \mathbb{R}^m$, $m\leq d$, and $f : \mathbb{R}^m \rightarrow \mathbb{R}$ are built in a two stage procedure. For a fixed $g$, we build $f$ using classical regression methods, involving evaluations of $u$. Recent works proposed to build a nonlinear $g$ by minimizing a loss function $\mathcal{J}(g)$ derived from Poincar\'e inequalities on manifolds, involving evaluations of the gradient of $u$. A problem is that minimizing $\mathcal{J}$ may be a challenging task. Hence in this work, we introduce new convex surrogates to $\mathcal{J}$. Leveraging concentration inequalities, we provide sub-optimality results for a class of functions $g$, including polynomials, and a wide class of input probability measures. We investigate performances on different benchmarks for various training sample sizes. We show that our approach outperforms standard iterative methods for minimizing the training Poincar\'e inequality based loss, often resulting in better approximation errors, especially for rather small training sets and $m=1$.
Authors: Core Francisco Park, Zechen Zhang, Hidenori Tanaka
Abstract: Humans and intelligent animals can effortlessly internalize new information ("news") and accurately extract the implications for performing downstream tasks. While large language models (LLMs) can achieve this through in-context learning (ICL) when the news is explicitly given as context, fine-tuning remains challenging for the models to consolidate learning in weights. In this paper, we introduce $\textit{New News}$, a dataset composed of hypothetical yet plausible news spanning multiple domains (mathematics, coding, discoveries, leaderboards, events), accompanied by downstream evaluation questions whose correct answers critically depend on understanding and internalizing the news. We first demonstrate a substantial gap between naive fine-tuning and in-context learning (FT-ICL gap) on our news dataset. To address this gap, we explore a suite of self-play data generation protocols -- paraphrases, implications and Self-QAs -- designed to distill the knowledge from the model with context into the weights of the model without the context, which we term $\textit{System-2 Fine-tuning}$ (Sys2-FT). We systematically evaluate ICL and Sys2-FT performance across data domains and model scales with the Qwen 2.5 family of models. Our results demonstrate that the self-QA protocol of Sys2-FT significantly improves models' in-weight learning of the news. Furthermore, we discover the $\textit{contexual shadowing effect}$, where training with the news $\textit{in context}$ followed by its rephrases or QAs degrade learning of the news. Finally, we show preliminary evidence of an emerging scaling law of Sys2-FT.
Authors: Eran Aizikovich, Dudu Mimran, Edita Grolman, Yuval Elovici, Asaf Shabtai
Abstract: The Open Radio Access Network (O-RAN) architecture is revolutionizing cellular networks with its open, multi-vendor design and AI-driven management, aiming to enhance flexibility and reduce costs. Although it has many advantages, O-RAN is not threat-free. While previous studies have mainly examined vulnerabilities arising from O-RAN's intelligent components, this paper is the first to focus on the security challenges and vulnerabilities introduced by transitioning from single-operator to multi-operator RAN architectures. This shift increases the risk of untrusted third-party operators managing different parts of the network. To explore these vulnerabilities and their potential mitigation, we developed an open-access testbed environment that integrates a wireless network simulator with the official O-RAN Software Community (OSC) RAN intelligent component (RIC) cluster. This environment enables realistic, live data collection and serves as a platform for demonstrating APATE (adversarial perturbation against traffic efficiency), an evasion attack in which a malicious cell manipulates its reported key performance indicators (KPIs) and deceives the O-RAN traffic steering to gain unfair allocations of user equipment (UE). To ensure that O-RAN's legitimate activity continues, we introduce MARRS (monitoring adversarial RAN reports), a detection framework based on a long-short term memory (LSTM) autoencoder (AE) that learns contextual features across the network to monitor malicious telemetry (also demonstrated in our testbed). Our evaluation showed that by executing APATE, an attacker can obtain a 248.5% greater UE allocation than it was supposed to in a benign scenario. In addition, the MARRS detection method was also shown to successfully classify malicious cell activity, achieving accuracy of 99.2% and an F1 score of 0.978.
Authors: Jing Liu, Yao Du, Kun Yang, Yan Wang, Xiping Hu, Zehua Wang, Yang Liu, Peng Sun, Azzedine Boukerche, Victor C. M. Leung
Abstract: Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency processing. Recent advancements in AI, particularly deep learning and large language models (LLMs), have dramatically enhanced the capabilities of these distributed systems, yet introduce significant challenges in model deployment and resource management. In this survey, we comprehensive examine the intersection of distributed intelligence and model optimization within edge-cloud environments, providing a structured tutorial on fundamental architectures, enabling technologies, and emerging applications. Additionally, we systematically analyze model optimization approaches, including compression, adaptation, and neural architecture search, alongside AI-driven resource management strategies that balance performance, energy efficiency, and latency requirements. We further explore critical aspects of privacy protection and security enhancement within ECCC systems and examines practical deployments through diverse applications, spanning autonomous driving, healthcare, and industrial automation. Performance analysis and benchmarking techniques are also thoroughly explored to establish evaluation standards for these complex systems. Furthermore, the review identifies critical research directions including LLMs deployment, 6G integration, neuromorphic computing, and quantum computing, offering a roadmap for addressing persistent challenges in heterogeneity management, real-time processing, and scalability. By bridging theoretical advancements and practical deployments, this survey offers researchers and practitioners a holistic perspective on leveraging AI to optimize distributed computing environments, fostering innovation in next-generation intelligent systems.
Authors: Arman Sharifi Kolarijani, Tolga Ok, Peyman Mohajerin Esfahani, Mohamad Amin Sharif Kolarijani
Abstract: In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update by using a rank-one approximation of the transition probability matrix in the policy evaluation step. This rank-one approximation is closely related to the stationary distribution of the corresponding transition probability matrix, which is approximated using the power method. We provide theoretical guarantees for the convergence of the proposed algorithm to optimal (action-)value function with the same rate and computational complexity as the value iteration algorithm in the planning problem and as the Q-learning algorithm in the learning problem. Through our extensive numerical simulations, however, we show that the proposed algorithm consistently outperforms first-order algorithms and their accelerated versions for both planning and learning problems.
Authors: Jiaqi Guo, Chon Wai Ho, Sumeetpal S. Singh
Abstract: The Markov Decision Process (MDP) is a popular framework for sequential decision-making problems, and uncertainty quantification is an essential component of it to learn optimal decision-making strategies. In particular, a Bayesian framework is used to maintain beliefs about the optimal decisions and the unknown ingredients of the model, which are also to be learned from the data, such as the rewards and state dynamics. However, many existing Bayesian approaches for learning the optimal decision-making strategy are based on unrealistic modelling assumptions and utilise approximate inference techniques. This raises doubts whether the benefits of Bayesian uncertainty quantification are fully realised or can be relied upon. We focus on infinite-horizon and undiscounted MDPs, with finite state and action spaces, and a terminal state. We provide a full Bayesian framework, from modelling to inference to decision-making. For modelling, we introduce a likelihood function with minimal assumptions for learning the optimal action-value function based on Bellman's optimality equations, analyse its properties, and clarify connections to existing works. For deterministic rewards, the likelihood is degenerate and we introduce artificial observation noise to relax it, in a controlled manner, to facilitate more efficient Monte Carlo-based inference. For inference, we propose an adaptive sequential Monte Carlo algorithm to both sample from and adjust the sequence of relaxed posterior distributions. For decision-making, we choose actions using samples from the posterior distribution over the optimal strategies. While commonly done, we provide new insight that clearly shows that it is a generalisation of Thompson sampling from multi-arm bandit problems. Finally, we evaluate our framework on the Deep Sea benchmark problem and demonstrate the exploration benefits of posterior sampling in MDPs.
Authors: Daniel Commey, Garth V. Crosby
Abstract: Federated Learning (FL) enables collaborative model training while preserving data privacy, but its classical cryptographic underpinnings are vulnerable to quantum attacks. This vulnerability is particularly critical in sensitive domains like healthcare. This paper introduces PQS-BFL (Post-Quantum Secure Blockchain-based Federated Learning), a framework integrating post-quantum cryptography (PQC) with blockchain verification to secure FL against quantum adversaries. We employ ML-DSA-65 (a FIPS 204 standard candidate, formerly Dilithium) signatures to authenticate model updates and leverage optimized smart contracts for decentralized validation. Extensive evaluations on diverse datasets (MNIST, SVHN, HAR) demonstrate that PQS-BFL achieves efficient cryptographic operations (average PQC sign time: 0.65 ms, verify time: 0.53 ms) with a fixed signature size of 3309 Bytes. Blockchain integration incurs a manageable overhead, with average transaction times around 4.8 s and gas usage per update averaging 1.72 x 10^6 units for PQC configurations. Crucially, the cryptographic overhead relative to transaction time remains minimal (around 0.01-0.02% for PQC with blockchain), confirming that PQC performance is not the bottleneck in blockchain-based FL. The system maintains competitive model accuracy (e.g., over 98.8% for MNIST with PQC) and scales effectively, with round times showing sublinear growth with increasing client numbers. Our open-source implementation and reproducible benchmarks validate the feasibility of deploying long-term, quantum-resistant security in practical FL systems.
Authors: Trisanth Srinivasan, Santosh Patapati
Abstract: Robust navigation in diverse environments and domains requires both accurate state estimation and transparent decision making. We present PhysNav-DG, a novel framework that integrates classical sensor fusion with the semantic power of vision-language models. Our dual-branch architecture predicts navigation actions from multi-sensor inputs while simultaneously generating detailed chain-of-thought explanations. A modified Adaptive Kalman Filter dynamically adjusts its noise parameters based on environmental context. It leverages several streams of raw sensor data along with semantic insights from models such as LLaMA 3.2 11B and BLIP-2. To evaluate our approach, we introduce the MD-NEX Benchmark, a novel multi-domain dataset that unifies indoor navigation, autonomous driving, and social navigation tasks with ground-truth actions and human-validated explanations. Extensive experiments and ablations show that PhysNav-DG improves navigation success rates by over 20% and achieves high efficiency, with explanations that are both highly grounded and clear. This work connects high-level semantic reasoning and geometric planning for safer and more trustworthy autonomous systems.
Authors: Siddharth Kothari, Srinivasan Murali, Sankalp Kothari, Ujjwal Verma, Jaya Sreevalsan-Nair
Abstract: Inland water body segmentation from Synthetic Aperture Radar (SAR) images is an important task needed for several applications, such as flood mapping. While SAR sensors capture data in all-weather conditions as high-resolution images, differentiating water and water-like surfaces from SAR images is not straightforward. Inland water bodies, such as large river basins, have complex geometry, which adds to the challenge of segmentation. U-Net is a widely used deep learning model for land-water segmentation of SAR images. In practice, manual annotation is often used to generate the corresponding water masks as ground truth. Manual annotation of the images is prone to label noise owing to data poisoning attacks, especially due to complex geometry. In this work, we simulate manual errors in the form of adversarial attacks on the U-Net model and study the robustness of the model to human errors in annotation. Our results indicate that U-Net can tolerate a certain level of corruption before its performance drops significantly. This finding highlights the crucial role that the quality of manual annotations plays in determining the effectiveness of the segmentation model. The code and the new dataset, along with adversarial examples for robust training, are publicly available. (Github link - https://github.com/GVCL/IWSeg-SAR-Poison.git)
Authors: Javier E. Santos, Agnese Marcato, Roman Colman, Nicholas Lubbers, Yen Ting Lin
Abstract: Generative diffusion models have achieved remarkable success in producing high-quality images. However, because these models typically operate in continuous intensity spaces - diffusing independently per pixel and color channel - they are fundamentally ill-suited for applications where quantities such as particle counts or material units are inherently discrete and governed by strict conservation laws such as mass preservation, limiting their applicability in scientific workflows. To address this limitation, we propose Discrete Spatial Diffusion (DSD), a framework based on a continuous-time, discrete-state jump stochastic process that operates directly in discrete spatial domains while strictly preserving mass in both forward and reverse diffusion processes. By using spatial diffusion to achieve mass preservation, we introduce stochasticity naturally through a discrete formulation. We demonstrate the expressive flexibility of DSD by performing image synthesis, class conditioning, and image inpainting across widely-used image benchmarks, with the ability to condition on image intensity. Additionally, we highlight its applicability to domain-specific scientific data for materials microstructure, bridging the gap between diffusion models and mass-conditioned scientific applications.
Authors: Yunbum Kook, Santosh S. Vempala
Abstract: We present a faster algorithm to generate a warm start for sampling an arbitrary logconcave density specified by an evaluation oracle, leading to the first sub-cubic sampling algorithms for inputs in (near-)isotropic position. A long line of prior work incurred a warm-start penalty of at least linear in the dimension, hitting a cubic barrier, even for the special case of uniform sampling from convex bodies. Our improvement relies on two key ingredients of independent interest. (1) We show how to sample given a warm start in weaker notions of distance, in particular $q$-R\'enyi divergence for $q=\widetilde{\mathcal{O}}(1)$, whereas previous analyses required stringent $\infty$-R\'enyi divergence (with the exception of Hit-and-Run, whose known mixing time is higher). This marks the first improvement in the required warmness since Lov\'asz and Simonovits (1991). (2) We refine and generalize the log-Sobolev inequality of Lee and Vempala (2018), originally established for isotropic logconcave distributions in terms of the diameter of the support, to logconcave distributions in terms of a geometric average of the support diameter and the largest eigenvalue of the covariance matrix.
Authors: Ivan Tan, Wei Minn, Christopher M. Poskitt, Lwin Khin Shar, Lingxiao Jiang
Abstract: UAVs, commonly referred to as drones, have witnessed a remarkable surge in popularity due to their versatile applications. These cyber-physical systems depend on multiple sensor inputs, such as cameras, GPS receivers, accelerometers, and gyroscopes, with faults potentially leading to physical instability and serious safety concerns. To mitigate such risks, anomaly detection has emerged as a crucial safeguarding mechanism, capable of identifying the physical manifestations of emerging issues and allowing operators to take preemptive action at runtime. Recent anomaly detection methods based on LSTM neural networks have shown promising results, but three challenges persist: the need for models that can generalise across the diverse mission profiles of drones; the need for interpretability, enabling operators to understand the nature of detected problems; and the need for capturing domain knowledge that is difficult to infer solely from log data. Motivated by these challenges, this paper introduces RADD, an integrated approach to anomaly detection in drones that combines rule mining and unsupervised learning. In particular, we leverage rules (or invariants) to capture expected relationships between sensors and actuators during missions, and utilise unsupervised learning techniques to cover more subtle relationships that the rules may have missed. We implement this approach using the ArduPilot drone software in the Gazebo simulator, utilising 44 rules derived across the main phases of drone missions, in conjunction with an ensemble of five unsupervised learning models. We find that our integrated approach successfully detects 93.84% of anomalies over six types of faults with a low false positive rate (2.33%), and can be deployed effectively at runtime. Furthermore, RADD outperforms a state-of-the-art LSTM-based method in detecting the different types of faults evaluated in our study.
Authors: Bofei Liu, Dong Ye, Zunhao Yao, Zhaowei Sun
Abstract: Modular self-reconfigurable satellites refer to satellite clusters composed of individual modular units capable of altering their configurations. The configuration changes enable the execution of diverse tasks and mission objectives. Existing path planning algorithms for reconfiguration often suffer from high computational complexity, poor generalization capability, and limited support for diverse target configurations. To address these challenges, this paper proposes a goal-oriented reinforcement learning-based path planning algorithm. This algorithm is the first to address the challenge that previous reinforcement learning methods failed to overcome, namely handling multiple target configurations. Moreover, techniques such as Hindsight Experience Replay and Invalid Action Masking are incorporated to overcome the significant obstacles posed by sparse rewards and invalid actions. Based on these designs, our model achieves a 95% and 73% success rate in reaching arbitrary target configurations in a modular satellite cluster composed of four and six units, respectively.
Authors: Hung Pham, Aiden Ren, Ibrahim Tahir, Jiatai Tong, Thiago Serra
Abstract: We can approximate a constraint or an objective function that is uncertain or nonlinear with a neural network that we embed in the optimization model. This approach, which is known as constraint learning, faces the challenge that optimization models with neural network surrogates are harder to solve. Such difficulties have motivated studies on model reformulation, specialized optimization algorithms, and - to a lesser extent - pruning of the embedded networks. In this work, we double down on the use of surrogates by applying network pruning to produce a surrogate of the neural network itself. In the context of using a Mixed-Integer Linear Programming (MILP) solver to verify neural networks, we obtained faster adversarial perturbations for dense neural networks by using sparse surrogates, especially - and surprisingly - if not taking the time to finetune the sparse network to make up for the loss in accuracy. In other words, we show that a pruned network with bad classification performance can still be a good - and more efficient - surrogate.
Authors: Sehwan Kim, Faming Liang
Abstract: Individual treatment effect estimation has gained significant attention in recent data science literature. This work introduces the Double Neural Network (Double-NN) method to address this problem within the framework of extended fiducial inference (EFI). In the proposed method, deep neural networks are used to model the treatment and control effect functions, while an additional neural network is employed to estimate their parameters. The universal approximation capability of deep neural networks ensures the broad applicability of this method. Numerical results highlight the superior performance of the proposed Double-NN method compared to the conformal quantile regression (CQR) method in individual treatment effect estimation. From the perspective of statistical inference, this work advances the theory and methodology for statistical inference of large models. Specifically, it is theoretically proven that the proposed method permits the model size to increase with the sample size $n$ at a rate of $O(n^{\zeta})$ for some $0 \leq \zeta<1$, while still maintaining proper quantification of uncertainty in the model parameters. This result marks a significant improvement compared to the range $0\leq \zeta < \frac{1}{2}$ required by the classical central limit theorem. Furthermore, this work provides a rigorous framework for quantifying the uncertainty of deep neural networks under the neural scaling law, representing a substantial contribution to the statistical understanding of large-scale neural network models.
Authors: Sai Krishna Mendu, Harish Yenala, Aditi Gulati, Shanu Kumar, Parag Agrawal
Abstract: Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for high-quality natural language generation, they often contain harmful content, such as hate speech, misinformation, and biased narratives. Training LLMs on such unfiltered data risks perpetuating toxic behaviors, spreading misinformation, and amplifying societal biases which can undermine trust in LLM-driven applications and raise ethical concerns about their use. This paper presents a large-scale analysis of inappropriate content across these datasets, offering a comprehensive taxonomy that categorizes harmful webpages into Topical and Toxic based on their intent. We also introduce a prompt evaluation dataset, a high-accuracy Topical and Toxic Prompt (TTP), and a transformer-based model (HarmFormer) for content filtering. Additionally, we create a new multi-harm open-ended toxicity benchmark (HAVOC) and provide crucial insights into how models respond to adversarial toxic inputs. Upon publishing, we will also opensource our model signal on the entire C4 dataset. Our work offers insights into ensuring safer LLM pretraining and serves as a resource for Responsible AI (RAI) compliance.
Authors: Zeyuan Ma, Zhiguang Cao, Zhou Jiang, Hongshu Guo, Yue-Jiao Gong
Abstract: Recent progress in Meta-Black-Box-Optimization (MetaBBO) has demonstrated that using RL to learn a meta-level policy for dynamic algorithm configuration (DAC) over an optimization task distribution could significantly enhance the performance of the low-level BBO algorithm. However, the online learning paradigms in existing works makes the efficiency of MetaBBO problematic. To address this, we propose an offline learning-based MetaBBO framework in this paper, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO. Specifically, we first transform DAC task into long-sequence decision process. This allows us further introduce an effective Q-function decomposition mechanism to reduce the learning difficulty within the intricate algorithm configuration space. Under this setting, we propose three novel designs to meta-learn DAC policy from offline data: we first propose a novel collection strategy for constructing offline DAC experiences dataset with balanced exploration and exploitation. We then establish a decomposition-based Q-loss that incorporates conservative Q-learning to promote stable offline learning from the offline dataset. To further improve the offline learning efficiency, we equip our work with a Mamba architecture which helps long-sequence learning effectiveness and efficiency by selective state model and hardware-aware parallel scan respectively. Through extensive benchmarking, we observe that Q-Mamba achieves competitive or even superior performance to prior online/offline baselines, while significantly improving the training efficiency of existing online baselines. We provide sourcecodes of Q-Mamba at https://github.com/MetaEvo/Q-Mamba.
Authors: Yuji Okamoto, Tomoya Takeuchi, Yusuke Sakemi
Abstract: Since the advent of the ``Neural Ordinary Differential Equation (Neural ODE)'' paper, learning ODEs with deep learning has been applied to system identification, time-series forecasting, and related areas. Exploiting the diffeomorphic nature of ODE solution maps, neural ODEs has also enabled their use in generative modeling. Despite the rich potential to incorporate various kinds of physical information, training Neural ODEs remains challenging in practice. This study demonstrates, through the simplest one-dimensional linear model, why training Neural ODEs is difficult. We then propose a new stabilization method and provide an analytical convergence analysis. The insights and techniques presented here serve as a concise tutorial for researchers beginning work on Neural ODEs.
Authors: Yuchen Wang, Xuefeng Bai, Xiucheng Li, Weili Guan, Liqiang Nie, Xinyang Chen
Abstract: Adapting vision-language models (VLMs) to downstream tasks with pseudolabels has gained increasing attention. A major obstacle is that the pseudolabels generated by VLMs tend to be imbalanced, leading to inferior performance. While existing methods have explored various strategies to address this, the underlying causes of imbalance remain insufficiently investigated. To fill this gap, we delve into imbalanced pseudolabels and identify two primary contributing factors: concept mismatch and concept confusion. To mitigate these two issues, we propose a novel framework incorporating concept alignment and confusion-aware calibrated margin mechanisms. The core of our approach lies in enhancing underperforming classes and promoting balanced predictions across categories, thus mitigating imbalance. Extensive experiments on six benchmark datasets with three learning paradigms demonstrate that the proposed method effectively enhances the accuracy and balance of pseudolabels, achieving a relative improvement of 6.29% over the SoTA method. Our code is avaliable at https://anonymous.4open.science/r/CAP-C642/
Authors: Can K\"u\c{c}\"uks\"ozen, Y\"ucel Yemez
Abstract: We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroids in a scene, providing a spatial inductive bias. Thanks to this strategy, COCA-Net generates high-quality segmentation masks on both the decoder side and, notably, the encoder side of its pipeline. Additionally, COCA-Net is not bound by a predetermined number of object masks that it generates and handles the segmentation of background elements better than its competitors. We demonstrate COCA-Net's segmentation performance on six widely adopted datasets, achieving superior or competitive results against the state-of-the-art models across nine different evaluation metrics.
Authors: Volodymyr Havrylov, Haiwen Huang, Dan Zhang, Andreas Geiger
Abstract: Vision Foundation Models (VFMs) are large-scale, pre-trained models that serve as general-purpose backbones for various computer vision tasks. As VFMs' popularity grows, there is an increasing interest in understanding their effectiveness for dense prediction tasks. However, VFMs typically produce low-resolution features, limiting their direct applicability in this context. One way to tackle this limitation is by employing a task-agnostic feature upsampling module that refines VFM features resolution. To assess the effectiveness of this approach, we investigate Interactive Segmentation (IS) as a novel benchmark for evaluating feature upsampling methods on VFMs. Due to its inherent multimodal input, consisting of an image and a set of user-defined clicks, as well as its dense mask output, IS creates a challenging environment that demands comprehensive visual scene understanding. Our benchmarking experiments show that selecting appropriate upsampling strategies significantly improves VFM features quality. The code is released at https://github.com/havrylovv/iSegProbe
Authors: Xinyue Peng, Yanming Liu, Yihan Cang, Chaoqun Cao, Ming Chen
Abstract: Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques. To address this issue, we propose LLM-OptiRA, the first framework that leverages large language models (LLMs) to automatically detect and transform non-convex components into solvable forms, enabling fully automated resolution of non-convex resource allocation problems in wireless communication systems. LLM-OptiRA not only simplifies problem-solving by reducing reliance on expert knowledge, but also integrates error correction and feasibility validation mechanisms to ensure robustness. Experimental results show that LLM-OptiRA achieves an execution rate of 96% and a success rate of 80% on GPT-4, significantly outperforming baseline approaches in complex optimization tasks across diverse scenarios.
Authors: Youran Dong, Junfeng Yang, Wei Yao, Jin Zhang
Abstract: Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods for bilevel optimization. In this work, we propose a computationally efficient technique for incorporating curvature information into the approximation of hypergradients and present a novel algorithmic framework based on the resulting enhanced hypergradient computation. We provide convergence rate guarantees for the proposed framework in both deterministic and stochastic scenarios, particularly showing improved computational complexity over popular gradient-based methods in the deterministic setting. This improvement in complexity arises from a careful exploitation of the hypergradient structure and the inexact Newton method. In addition to the theoretical speedup, numerical experiments demonstrate the significant practical performance benefits of incorporating curvature information.
Authors: Shouyang Dong, Yuanbo Wen, Jun Bi, Di Huang, Jiaming Guo, Jianxing Xu, Ruibai Xu, Xinkai Song, Yifan Hao, Xuehai Zhou, Tianshi Chen, Qi Guo, Yunji Chen
Abstract: Heterogeneous deep learning systems (DLS) such as GPUs and ASICs have been widely deployed in industrial data centers, which requires to develop multiple low-level tensor programs for different platforms. An attractive solution to relieve the programming burden is to transcompile the legacy code of one platform to others. However, current transcompilation techniques struggle with either tremendous manual efforts or functional incorrectness, rendering "Write Once, Run Anywhere" of tensor programs an open question. We propose a novel transcompiler, i.e., QiMeng-Xpiler, for automatically translating tensor programs across DLS via both large language models (LLMs) and symbolic program synthesis, i.e., neural-symbolic synthesis. The key insight is leveraging the powerful code generation ability of LLM to make costly search-based symbolic synthesis computationally tractable. Concretely, we propose multiple LLM-assisted compilation passes via pre-defined meta-prompts for program transformation. During each program transformation, efficient symbolic program synthesis is employed to repair incorrect code snippets with a limited scale. To attain high performance, we propose a hierarchical auto-tuning approach to systematically explore both the parameters and sequences of transformation passes. Experiments on 4 DLS with distinct programming interfaces, i.e., Intel DL Boost with VNNI, NVIDIA GPU with CUDA, AMD MI with HIP, and Cambricon MLU with BANG, demonstrate that QiMeng-Xpiler correctly translates different tensor programs at the accuracy of 95% on average, and the performance of translated programs achieves up to 2.0x over vendor-provided manually-optimized libraries. As a result, the programming productivity of DLS is improved by up to 96.0x via transcompiling legacy tensor programs.
Authors: Minzheng Wang, Yongbin Li, Haobo Wang, Xinghua Zhang, Nan Xu, Bingli Wu, Fei Huang, Haiyang Yu, Wenji Mao
Abstract: Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current approaches. While existing methods either lack this kind of reasoning capability or enforce uniform long chain-of-thought reasoning across all scenarios, resulting in excessive token usage and inappropriate social simulation. In this paper, we propose $\textbf{A}$daptive $\textbf{M}$ode $\textbf{L}$earning ($\textbf{AML}$) that strategically selects from four thinking modes (intuitive reaction $\rightarrow$ deep contemplation) based on real-time context. Our framework's core innovation, the $\textbf{A}$daptive $\textbf{M}$ode $\textbf{P}$olicy $\textbf{O}$ptimization ($\textbf{AMPO}$) algorithm, introduces three key advancements over existing methods: (1) Multi-granular thinking mode design, (2) Context-aware mode switching across social interaction, and (3) Token-efficient reasoning via depth-adaptive processing. Extensive experiments on social intelligence tasks confirm that AML achieves 15.6% higher task performance than state-of-the-art methods. Notably, our method outperforms GRPO by 7.0% with 32.8% shorter reasoning chains. These results demonstrate that context-sensitive thinking mode selection, as implemented in AMPO, enables more human-like adaptive reasoning than GRPO's fixed-depth approach
Authors: Danial Ramezani
Abstract: Fantasy football is a billion-dollar industry with millions of participants. Constrained by a fixed budget, decision-makers draft a squad whose players are expected to perform well in the upcoming weeks to maximize total points. This paper proposes novel deterministic and robust integer programming models that select the optimal starting eleven and the captain. A new hybrid scoring metric is constructed using an interpretable artificial intelligence framework and underlying match performance data. Several objective functions and estimation techniques are introduced for the programming model. To the best of my knowledge, this is the first study to approach fantasy football through this lens. The models' performance is evaluated using data from the 2023/24 Premier League season. Results indicate that the proposed hybrid method achieved the highest score while maintaining consistent performance. Utilizing the Monte Carlo simulation, the strategic choice of averaging techniques for estimating cost vectors, and the proposed hybrid approach are shown to be effective during the out-of-sample period. This paper also provides a thorough analysis of the optimal formations and players selected by the models, offering valuable insights into effective fantasy football strategies.
Authors: Chutiphan Charoensuk, Nathakhun Wiroonsri
Abstract: Time series clustering is an unsupervised learning method for classifying time series data into groups with similar behavior. It is used in applications such as healthcare, finance, economics, energy, and climate science. Several time series clustering methods have been introduced and used for over four decades. Most of them focus on measuring either Euclidean distances or association dissimilarities between time series. In this work, we propose a new dissimilarity measure called ranked Pearson correlation dissimilarity (RDPC), which combines a weighted average of a specified fraction of the largest element-wise differences with the well-known Pearson correlation dissimilarity. It is incorporated into hierarchical clustering. The performance is evaluated and compared with existing clustering algorithms. The results show that the RDPC algorithm outperforms others in complicated cases involving different seasonal patterns, trends, and peaks. Finally, we demonstrate our method by clustering a random sample of customers from a Thai electricity consumption time series dataset into seven groups with unique characteristics.
Authors: Thomas Y. L. Lin, Jerry Yao-Chieh Hu, Paul W. Chiou, Peter Lin
Abstract: We revisit the Bayesian Black-Litterman (BL) portfolio model and remove its reliance on subjective investor views. Classical BL requires an investor "view": a forecast vector $q$ and its uncertainty matrix $\Omega$ that describe how much a chosen portfolio should outperform the market. Our key idea is to treat $(q,\Omega)$ as latent variables and learn them from market data within a single Bayesian network. Consequently, the resulting posterior estimation admits closed-form expression, enabling fast inference and stable portfolio weights. Building on these, we propose two mechanisms to capture how features interact with returns: shared-latent parametrization and feature-influenced views; both recover classical BL and Markowitz portfolios as special cases. Empirically, on 30-year Dow-Jones and 20-year sector-ETF data, we improve Sharpe ratios by 50% and cut turnover by 55% relative to Markowitz and the index baselines. This work turns BL into a fully data-driven, view-free, and coherent Bayesian framework for portfolio optimization.
Authors: Andrew Quijano, Spyros T. Halkidis, Kevin Gallagher, Kemal Akkaya, Nikolaos Samaras
Abstract: A decision tree is an easy-to-understand tool that has been widely used for classification tasks. On the one hand, due to privacy concerns, there has been an urgent need to create privacy-preserving classifiers that conceal the user's input from the classifier. On the other hand, with the rise of cloud computing, data owners are keen to reduce risk by outsourcing their model, but want security guarantees that third parties cannot steal their decision tree model. To address these issues, Joye and Salehi introduced a theoretical protocol that efficiently evaluates decision trees while maintaining privacy by leveraging their comparison protocol that is resistant to timing attacks. However, their approach was not only inefficient but also prone to side-channel attacks. Therefore, in this paper, we propose a new decision tree inference protocol in which the model is shared and evaluated among multiple entities. We partition our decision tree model by each level to be stored in a new entity we refer to as a "level-site." Utilizing this approach, we were able to gain improved average run time for classifier evaluation for a non-complete tree, while also having strong mitigations against side-channel attacks.
Authors: Malte Mosbach, Sven Behnke
Abstract: Building models responsive to input prompts represents a transformative shift in machine learning. This paradigm holds significant potential for robotics problems, such as targeted manipulation amidst clutter. In this work, we present a novel approach to combine promptable foundation models with reinforcement learning (RL), enabling robots to perform dexterous manipulation tasks in a prompt-responsive manner. Existing methods struggle to link high-level commands with fine-grained dexterous control. We address this gap with a memory-augmented student-teacher learning framework. We use the Segment-Anything 2 (SAM 2) model as a perception backbone to infer an object of interest from user prompts. While detections are imperfect, their temporal sequence provides rich information for implicit state estimation by memory-augmented models. Our approach successfully learns prompt-responsive policies, demonstrated in picking objects from cluttered scenes. Videos and code are available at https://memory-student-teacher.github.io
Authors: Liu Ziyin, Isaac Chuang, Tomaso Poggio
Abstract: We propose a design principle for the learning circuits of the biological brain. The principle states that almost any dendritic weights updated via heterosynaptic plasticity can implement a generalized and efficient class of gradient-based meta-learning. The theory suggests that a broad class of biologically plausible learning algorithms, together with the standard machine learning optimizers, can be grounded in heterosynaptic circuit motifs. This principle suggests that the phenomenology of (anti-) Hebbian (HBP) and heterosynaptic plasticity (HSP) may emerge from the same underlying dynamics, thus providing a unifying explanation. It also suggests an alternative perspective of neuroplasticity, where HSP is promoted to the primary learning and memory mechanism, and HBP is an emergent byproduct. We present simulations that show that (a) HSP can explain the metaplasticity of neurons, (b) HSP can explain the flexibility of the biology circuits, and (c) gradient learning can arise quickly from simple evolutionary dynamics that do not compute any explicit gradient. While our primary focus is on biology, the principle also implies a new approach to designing AI training algorithms and physically learnable AI hardware. Conceptually, our result demonstrates that contrary to the common belief, gradient computation may be extremely easy and common in nature.
Authors: Yu Zhu, Zehang Richard Li
Abstract: In regions lacking medically certified causes of death, verbal autopsy (VA) is a critical and widely used tool to ascertain the cause of death through interviews with caregivers. Data collected by VAs are often analyzed using probabilistic algorithms. The performance of these algorithms often degrades due to distributional shift across populations. Most existing VA algorithms rely on centralized training, requiring full access to training data for joint modeling. This is often infeasible due to privacy and logistical constraints. In this paper, we propose a novel Bayesian Federated Learning (BFL) framework that avoids data sharing across multiple training sources. Our method enables reliable individual-level cause-of-death classification and population-level quantification of cause-specific mortality fractions (CSMFs), in a target domain with limited or no local labeled data. The proposed framework is modular, computationally efficient, and compatible with a wide range of existing VA algorithms as candidate models, facilitating flexible deployment in real-world mortality surveillance systems. We validate the performance of BFL through extensive experiments on two real-world VA datasets under varying levels of distribution shift. Our results show that BFL significantly outperforms the base models built on a single domain and achieves comparable or better performance compared to joint modeling.
Authors: Emir Esenov, Olof Hjortstam, Yuriy Serdyuk, Thomas Hammarstr\"om, Christian H\"ager
Abstract: Dielectric response (DR) of insulating materials is key input information for designing electrical insulation systems and defining safe operating conditions of various HV devices. In dielectric materials, different polarization and conduction processes occur at different time scales, making it challenging to physically interpret raw measured data. To analyze DR measurement results, equivalent circuit models (ECMs) are commonly used, reducing the complexity of the physical system to a number of circuit elements that capture the dominant response. This paper examines the use of physics-informed neural networks (PINNs) for inverse modeling of DR in time domain using parallel RC circuits. To assess their performance, we test PINNs on synthetic data generated from analytical solutions of corresponding ECMs, incorporating Gaussian noise to simulate measurement errors. Our results show that PINNs are highly effective at solving well-conditioned inverse problems, accurately estimating up to five unknown RC parameters with minimal requirements on neural network size, training duration, and hyperparameter tuning. Furthermore, we extend the ECMs to incorporate temperature dependence and demonstrate that PINNs can accurately recover embedded, nonlinear temperature functions from noisy DR data sampled at different temperatures. This case study in modeling DR in time domain presents a solution with wide-ranging potential applications in disciplines relying on ECMs, utilizing the latest technology in machine learning for scientific computation.
Authors: Stanislav Semenov
Abstract: We introduce a novel method for encoding integers using smooth real-valued functions whose integral properties implicitly reflect discrete quantities. In contrast to classical representations, where the integer appears as an explicit parameter, our approach encodes the number N in the set of natural numbers through the cumulative balance of a smooth function f_N(t), constructed from localized Gaussian bumps with alternating and decaying coefficients. The total integral I(N) converges to zero as N tends to infinity, and the integer can be recovered as the minimal point of near-cancellation. This method enables continuous and differentiable representations of discrete states, supports recovery through spline-based or analytical inversion, and extends naturally to multidimensional tuples (N1, N2, ...). We analyze the structure and convergence of the encoding series, demonstrate numerical construction of the integral map I(N), and develop procedures for integer recovery via numerical inversion. The resulting framework opens a path toward embedding discrete logic within continuous optimization pipelines, machine learning architectures, and smooth symbolic computation.
Authors: Henry Ndubuaku, Mouad Talhi
Abstract: Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which token embedding vectors are first generated deterministically, directly from the token IDs using a Fourier expansion of their normalized values, followed by a lightweight multilayer perceptron (MLP) that captures higher-order interactions. We train standard transformers and our architecture on natural language inference tasks (SNLI and MNLI), and evaluate zero-shot performance on sentence textual similarity (STS-B). Our results demonstrate that the proposed method achieves competitive performance using significantly fewer parameters, trains faster, and operates effectively without the need for dropout. This proof-of-concept study highlights the potential for scalable, memory-efficient language models and motivates further large-scale experimentation based on our findings.
Authors: Amir Ali Farzin, Yuen-Man Pun, Iman Shames
Abstract: This study explores the performance of a random Gaussian smoothing zeroth-order (ZO) scheme for minimising quasar-convex (QC) and strongly quasar-convex (SQC) functions in both unconstrained and constrained settings. For the unconstrained problem, we establish the ZO algorithm's convergence to a global minimum along with its complexity when applied to both QC and SQC functions. For the constrained problem, we introduce the new notion of proximal-quasar-convexity and prove analogous results to the unconstrained case. Specifically, we show the complexity bounds and the convergence of the algorithm to a neighbourhood of a global minimum whose size can be controlled under a variance reduction scheme. Theoretical findings are illustrated through investigating the performance of the algorithm applied to a range of problems in machine learning and optimisation. Specifically, we observe scenarios where the ZO method outperforms gradient descent. We provide a possible explanation for this phenomenon.
Authors: James Read, Ming-Yen Lee, Wei-Hsing Huang, Yuan-Chun Luo, Anni Lu, Shimeng Yu
Abstract: The exponential growth of artificial intelligence (AI) applications has exposed the inefficiency of conventional von Neumann architectures, where frequent data transfers between compute units and memory create significant energy and latency bottlenecks. Analog Computing-in-Memory (ACIM) addresses this challenge by performing multiply-accumulate (MAC) operations directly in the memory arrays, substantially reducing data movement. However, designing robust ACIM accelerators requires accurate modeling of device- and circuit-level non-idealities. In this work, we present NeuroSim V1.5, introducing several key advances: (1) seamless integration with TensorRT's post-training quantization flow enabling support for more neural networks including transformers, (2) a flexible noise injection methodology built on pre-characterized statistical models, making it straightforward to incorporate data from SPICE simulations or silicon measurements, (3) expanded device support including emerging non-volatile capacitive memories, and (4) up to 6.5x faster runtime than NeuroSim V1.4 through optimized behavioral simulation. The combination of these capabilities uniquely enables systematic design space exploration across both accuracy and hardware efficiency metrics. Through multiple case studies, we demonstrate optimization of critical design parameters while maintaining network accuracy. By bridging high-fidelity noise modeling with efficient simulation, NeuroSim V1.5 advances the design and validation of next-generation ACIM accelerators. All NeuroSim versions are available open-source at https://github.com/neurosim/NeuroSim.
Authors: Bobo Lian, Dandan Wang, Chenjian Wu, Minxin Chen
Abstract: Point cloud surface representation is a fundamental problem in computer graphics and vision. This paper presents a machine learning approach for approximating the signed distance function (SDF) of a point cloud using sparse ellipsoidal radial basis function networks, enabling a compact and accurate surface representation. Given the SDF values defined on the grid points constructed from the point cloud, our method approximates the SDF accurately with as few ellipsoidal radial basis functions (ERBFs) as possible, i.e., represent the SDF of a point cloud by sparse ERBFs. To balance sparsity and approximation precision, a dynamic multi-objective optimization strategy is introduced, which adaptively adds the regularization terms and jointly optimizes the weights, centers, shapes, and orientations of ERBFs. To improve computational efficiency, a nearest-neighbor-based data structure is employed, restricting function calculations to points near each Gaussian kernel center. The computations for each kernel are further parallelized on CUDA, which significantly improves the optimization speed. Additionally, a hierarchical octree-based refinement strategy is designed for training. Specifically, the initialization and optimization of network parameters are conducted using coarse grid points in the octree lattice structure. Subsequently, fine lattice points are progressively incorporated to accelerate model convergence and enhance training efficiency. Extensive experiments on multiple benchmark datasets demonstrate that our method outperforms previous sparse representation approaches in terms of accuracy, robustness, and computational efficiency. The corresponding code is publicly available at https://github.com/lianbobo/SE-RBFNet.git.
Authors: Andrew Ma, Marin Solja\v{c}i\'c
Abstract: In the past decade, there has been a significant interest in the use of machine learning approaches in materials science research. Conventional deep learning approaches that rely on complex, nonlinear models have become increasingly important in computational materials science due to their high predictive accuracy. In contrast to these approaches, we have shown in a recent work that a remarkably simple learned heuristic rule -- based on the concept of topogivity -- can classify whether a material is topological using only its chemical composition. In this paper, we go beyond the topology classification scenario by also studying the use of machine learning to develop simple heuristic rules for classifying whether a material is a metal based on chemical composition. Moreover, we present a framework for incorporating chemistry-informed inductive bias based on the structure of the periodic table. For both the topology classification and the metallicity classification tasks, we empirically characterize the performance of simple heuristic rules fit with and without chemistry-informed inductive bias across a wide range of training set sizes. We find evidence that incorporating chemistry-informed inductive bias can reduce the amount of training data required to reach a given level of test accuracy.
Authors: Ghazaleh SHirvani, Saeid Ghasemshirazi
Abstract: Email spam detection is a critical task in modern communication systems, essential for maintaining productivity, security, and user experience. Traditional machine learning and deep learning approaches, while effective in static settings, face significant limitations in adapting to evolving spam tactics, addressing class imbalance, and managing data scarcity. These challenges necessitate innovative approaches that reduce dependency on extensive labeled datasets and frequent retraining. This study investigates the effectiveness of Zero-Shot Learning using FLAN-T5, combined with advanced Natural Language Processing (NLP) techniques such as BERT for email spam detection. By employing BERT to preprocess and extract critical information from email content, and FLAN-T5 to classify emails in a Zero-Shot framework, the proposed approach aims to address the limitations of traditional spam detection systems. The integration of FLAN-T5 and BERT enables robust spam detection without relying on extensive labeled datasets or frequent retraining, making it highly adaptable to unseen spam patterns and adversarial environments. This research highlights the potential of leveraging zero-shot learning and NLPs for scalable and efficient spam detection, providing insights into their capability to address the dynamic and challenging nature of spam detection tasks.
Authors: Tianyu Zong, Hongzhu Yi, Bingkang Shi, Yuanxiang Wang, Jungang Xu
Abstract: Unsupervised contrastive learning has become a hot research topic in natural language processing. Existing works usually aim at constraining the orientation distribution of the representations of positive and negative samples in the high-dimensional semantic space in contrastive learning, but the semantic representation tensor possesses both modulus and orientation features, and the existing works ignore the modulus feature of the representations and cause insufficient contrastive learning. % Therefore, we firstly propose a training objective that aims at modulus constraints on the semantic representation tensor, to strengthen the alignment between the positive samples in contrastive learning. Therefore, we first propose a training objective that is designed to impose modulus constraints on the semantic representation tensor, to strengthen the alignment between positive samples in contrastive learning. Then, the BERT-like model suffers from the phenomenon of sinking attention, leading to a lack of attention to CLS tokens that aggregate semantic information. In response, we propose a cross-attention structure among the twin-tower ensemble models to enhance the model's attention to CLS token and optimize the quality of CLS Pooling. Combining the above two motivations, we propose a new \textbf{J}oint \textbf{T}ensor representation modulus constraint and \textbf{C}ross-attention unsupervised contrastive learning \textbf{S}entence \textbf{E}mbedding representation framework JTCSE, which we evaluate in seven semantic text similarity computation tasks, and the experimental results show that JTCSE's twin-tower ensemble model and single-tower distillation model outperform the other baselines and become the current SOTA. In addition, we have conducted an extensive zero-shot downstream task evaluation, which shows that JTCSE outperforms other baselines overall on more than 130 tasks.
Authors: Ming Li, Xin Gu, Fan Chen, Xiaoying Xing, Longyin Wen, Chen Chen, Sijie Zhu
Abstract: Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and original-edited image pairs. Recent efforts attempt to improve editing models through generating higher-quality edited images, pre-training on recognition tasks, or introducing vision-language models (VLMs) but fail to resolve this fundamental issue. In this paper, we offer a novel solution by constructing more effective editing instructions for given image pairs. This includes rectifying the editing instructions to better align with the original-edited image pairs and using contrastive editing instructions to further enhance their effectiveness. Specifically, we find that editing models exhibit specific generation attributes at different inference steps, independent of the text. Based on these prior attributes, we define a unified guide for VLMs to rectify editing instructions. However, there are some challenging editing scenarios that cannot be resolved solely with rectified instructions. To this end, we further construct contrastive supervision signals with positive and negative instructions and introduce them into the model training using triplet loss, thereby further facilitating supervision effectiveness. Our method does not require the VLM modules or pre-training tasks used in previous work, offering a more direct and efficient way to provide better supervision signals, and providing a novel, simple, and effective solution for instruction-based image editing. Results on multiple benchmarks demonstrate that our method significantly outperforms existing approaches. Compared with previous SOTA SmartEdit, we achieve 9.19% improvements on the Real-Edit benchmark with 30x less training data and 13x smaller model size.
Authors: Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian, Yu Wang, Hongru Wang, Yu Zhang, Denghui Zhang, Tong Zhang, Hanghang Tong, Heng Ji
Abstract: Reward modeling is essential for aligning large language models (LLMs) with human preferences, especially through reinforcement learning from human feedback (RLHF). To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. However, existing RMs either produce opaque scalar scores or directly generate the prediction of a preferred answer, making them struggle to integrate natural language critiques, thus lacking interpretability. Inspired by recent advances of long chain-of-thought (CoT) on reasoning-intensive tasks, we hypothesize and validate that integrating reasoning capabilities into reward modeling significantly enhances RM's interpretability and performance. In this work, we introduce a new class of generative reward models -- Reasoning Reward Models (ReasRMs) -- which formulate reward modeling as a reasoning task. We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1. The training consists of two key stages: (1) distillation of high-quality reasoning chains and (2) reinforcement learning with verifiable rewards. RM-R1 improves LLM rollouts by self-generating reasoning traces or chat-specific rubrics and evaluating candidate responses against them. Empirically, our models achieve state-of-the-art or near state-of-the-art performance of generative RMs across multiple comprehensive reward model benchmarks, outperforming much larger open-weight models (e.g., Llama3.1-405B) and proprietary ones (e.g., GPT-4o) by up to 13.8%. Beyond final performance, we perform thorough empirical analysis to understand the key ingredients of successful ReasRM training. To facilitate future research, we release six ReasRM models along with code and data at https://github.com/RM-R1-UIUC/RM-R1.
Authors: Huangyue Yu, Baoxiong Jia, Yixin Chen, Yandan Yang, Puhao Li, Rongpeng Su, Jiaxin Li, Qing Li, Wei Liang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang
Abstract: Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality standards, however, necessitates the precise replication of real-world object diversity. Existing datasets demonstrate that this process heavily relies on artist-driven designs, which demand substantial human effort and present significant scalability challenges. To scalably produce realistic and interactive 3D scenes, we first present MetaScenes, a large-scale, simulatable 3D scene dataset constructed from real-world scans, which includes 15366 objects spanning 831 fine-grained categories. Then, we introduce Scan2Sim, a robust multi-modal alignment model, which enables the automated, high-quality replacement of assets, thereby eliminating the reliance on artist-driven designs for scaling 3D scenes. We further propose two benchmarks to evaluate MetaScenes: a detailed scene synthesis task focused on small item layouts for robotic manipulation and a domain transfer task in vision-and-language navigation (VLN) to validate cross-domain transfer. Results confirm MetaScene's potential to enhance EAI by supporting more generalizable agent learning and sim-to-real applications, introducing new possibilities for EAI research. Project website: https://meta-scenes.github.io/.
Authors: Yang Deng, Yaohui Liu, Rui Liang, Dafang Zhao, Donghua Xie, Ittetsu Taniguchi, Dan Wang
Abstract: The building thermodynamics model, which predicts real-time indoor temperature changes under potential HVAC (Heating, Ventilation, and Air Conditioning) control operations, is crucial for optimizing HVAC control in buildings. While pioneering studies have attempted to develop such models for various building environments, these models often require extensive data collection periods and rely heavily on expert knowledge, making the modeling process inefficient and limiting the reusability of the models. This paper explores a model ensemble perspective that utilizes existing developed models as base models to serve a target building environment, thereby providing accurate predictions while reducing the associated efforts. Given that building data streams are non-stationary and the number of base models may increase, we propose a Hierarchical Reinforcement Learning (HRL) approach to dynamically select and weight the base models. Our approach employs a two-tiered decision-making process: the high-level focuses on model selection, while the low-level determines the weights of the selected models. We thoroughly evaluate the proposed approach through offline experiments and an on-site case study, and the experimental results demonstrate the effectiveness of our method.
Authors: Tal Oved, Beatrice Lena, Chlo\'e F. Najac, Sheng Shen, Matthew S. Rosen, Andrew Webb, Efrat Shimron
Abstract: Magnetic resonance imaging (MRI) offers superb-quality images, but its accessibility is limited by high costs, posing challenges for patients requiring longitudinal care. Low-field MRI provides affordable imaging with low-cost devices but is hindered by long scans and degraded image quality, including low signal-to-noise ratio (SNR) and tissue contrast. We propose a novel healthcare paradigm: using deep learning to extract personalized features from past standard high-field MRI scans and harnessing them to enable accelerated, enhanced-quality follow-up scans with low-cost systems. To overcome the SNR and contrast differences, we introduce ViT-Fuser, a feature-fusion vision transformer that learns features from past scans, e.g. those stored in standard DICOM CDs. We show that \textit{a single prior scan is sufficient}, and this scan can come from various MRI vendors, field strengths, and pulse sequences. Experiments with four datasets, including glioblastoma data, low-field ($50mT$), and ultra-low-field ($6.5mT$) data, demonstrate that ViT-Fuser outperforms state-of-the-art methods, providing enhanced-quality images from accelerated low-field scans, with robustness to out-of-distribution data. Our freely available framework thus enables rapid, diagnostic-quality, low-cost imaging for wide healthcare applications.
Authors: Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, Andrew Wang, Zijian Zhang, Ilya Yakavets, Han Hao, Chris Crebolder, Varinia Bernales, Al\'an Aspuru-Guzik
Abstract: Computational chemistry tools are widely used to study the behaviour of chemical phenomena. Yet, the complexity of these tools can make them inaccessible to non-specialists and challenging even for experts. In this work, we introduce El Agente Q, an LLM-based multi-agent system that dynamically generates and executes quantum chemistry workflows from natural language user prompts. The system is built on a novel cognitive architecture featuring a hierarchical memory framework that enables flexible task decomposition, adaptive tool selection, post-analysis, and autonomous file handling and submission. El Agente Q is benchmarked on six university-level course exercises and two case studies, demonstrating robust problem-solving performance (averaging >87% task success) and adaptive error handling through in situ debugging. It also supports longer-term, multi-step task execution for more complex workflows, while maintaining transparency through detailed action trace logs. Together, these capabilities lay the foundation for increasingly autonomous and accessible quantum chemistry.
Authors: Asma Brazi, Boris Meden, Fabrice Mayran de Chamisso, Steve Bourgeois, Vincent Lepetit
Abstract: We introduce Corr2Distrib, the first correspondence-based method which estimates a 6D camera pose distribution from an RGB image, explaining the observations. Indeed, symmetries and occlusions introduce visual ambiguities, leading to multiple valid poses. While a few recent methods tackle this problem, they do not rely on local correspondences which, according to the BOP Challenge, are currently the most effective way to estimate a single 6DoF pose solution. Using correspondences to estimate a pose distribution is not straightforward, since ambiguous correspondences induced by visual ambiguities drastically decrease the performance of PnP. With Corr2Distrib, we turn these ambiguities into an advantage to recover all valid poses. Corr2Distrib first learns a symmetry-aware representation for each 3D point on the object's surface, characterized by a descriptor and a local frame. This representation enables the generation of 3DoF rotation hypotheses from single 2D-3D correspondences. Next, we refine these hypotheses into a 6DoF pose distribution using PnP and pose scoring. Our experimental evaluations on complex non-synthetic scenes show that Corr2Distrib outperforms state-of-the-art solutions for both pose distribution estimation and single pose estimation from an RGB image, demonstrating the potential of correspondences-based approaches.
Authors: Yang Lyu, Yuchun Qian, Tan Minh Nguyen, Xin T. Tong
Abstract: Diffusion models is a popular computational tool to generate new data samples. It utilizes a forward diffusion process that add noise to the data distribution and then use a reverse process to remove noises to produce samples from the data distribution. However, when the empirical data distribution consists of $n$ data point, using the empirical diffusion model will necessarily produce one of the existing data points. This is often referred to as the memorization effect, which is usually resolved by sophisticated machine learning procedures in the current literature. This work shows that the memorization problem can be resolved by a simple inertia update step at the end of the empirical diffusion model simulation. Our inertial diffusion model requires only the empirical diffusion model score function and it does not require any further training. We show that choosing the inertia diffusion model sample distribution is an $O\left(n^{-\frac{2}{d+4}}\right)$ Wasserstein-1 approximation of a data distribution lying on a $C^2$ manifold of dimension $d$. Since this estimate is significant smaller the Wasserstein1 distance between population and empirical distributions, it rigorously shows the inertial diffusion model produces new data samples. Remarkably, this upper bound is completely free of the ambient space dimension, since there is no training involved. Our analysis utilizes the fact that the inertial diffusion model samples are approximately distributed as the Gaussian kernel density estimator on the manifold. This reveals an interesting connection between diffusion model and manifold learning.
Authors: MohammadAli Shaeri, Jinhan Liu, Mahsa Shoaran
Abstract: Advanced neural interfaces are transforming applications ranging from neuroscience research to diagnostic tools (for mental state recognition, tremor and seizure detection) as well as prosthetic devices (for motor and communication recovery). By integrating complex functions into miniaturized neural devices, these systems unlock significant opportunities for personalized assistive technologies and adaptive therapeutic interventions. Leveraging high-density neural recordings, on-site signal processing, and machine learning (ML), these interfaces extract critical features, identify disease neuro-markers, and enable accurate, low-latency neural decoding. This integration facilitates real-time interpretation of neural signals, adaptive modulation of brain activity, and efficient control of assistive devices. Moreover, the synergy between neural interfaces and ML has paved the way for self-sufficient, ubiquitous platforms capable of operating in diverse environments with minimal hardware costs and external dependencies. In this work, we review recent advancements in AI-driven decoding algorithms and energy-efficient System-on-Chip (SoC) platforms for next-generation miniaturized neural devices. These innovations highlight the potential for developing intelligent neural interfaces, addressing critical challenges in scalability, reliability, interpretability, and user adaptability.
Authors: Robin Arbaud, Elisa Motta, Marco Domenico Avaro, Stefano Picinich, Marta Lorenzini, Arash Ajoudani
Abstract: Partial hand amputations significantly affect the physical and psychosocial well-being of individuals, yet intuitive control of externally powered prostheses remains an open challenge. To address this gap, we developed a force-controlled prosthetic finger activated by electromyography (EMG) signals. The prototype, constructed around a wrist brace, functions as a supernumerary finger placed near the index, allowing for early-stage evaluation on unimpaired subjects. A neural network-based model was then implemented to estimate fingertip forces from EMG inputs, allowing for online adjustment of the prosthetic finger grip strength. The force estimation model was validated through experiments with ten participants, demonstrating its effectiveness in predicting forces. Additionally, online trials with four users wearing the prosthesis exhibited precise control over the device. Our findings highlight the potential of using EMG-based force estimation to enhance the functionality of prosthetic fingers.
Authors: Sergio Hern\'andez-Guti\'errez, Minttu Alakuijala, Alexander V. Nikitin, Pekka Marttinen
Abstract: Reasoning tasks are crucial in many domains, especially in science and engineering. Although large language models (LLMs) have made progress in reasoning tasks using techniques such as chain-of-thought and least-to-most prompting, these approaches still do not effectively scale to complex problems in either their performance or execution time. Moreover, they often require additional supervision for each new task, such as in-context examples. In this work, we introduce Recursive Decomposition with Dependencies (RDD), a scalable divide-and-conquer method for solving reasoning problems that requires less supervision than prior approaches. Our method can be directly applied to a new problem class even in the absence of any task-specific guidance. Furthermore, RDD supports sub-task dependencies, allowing for ordered execution of sub-tasks, as well as an error recovery mechanism that can correct mistakes made in previous steps. We evaluate our approach on two benchmarks with six difficulty levels each and in two in-context settings: one with task-specific examples and one without. Our results demonstrate that RDD outperforms other methods in a compute-matched setting as task complexity increases, while also being more computationally efficient.
Authors: Lingxiao Kong (Fraunhofer Institute for Applied Information Technology FIT), Cong Yang (Soochow University), Susanne Neufang (University Hospital of Cologne), Oya Deniz Beyan (Fraunhofer Institute for Applied Information Technology FIT, University Hospital of Cologne), Zeyd Boukhers (Fraunhofer Institute for Applied Information Technology FIT, University Hospital of Cologne)
Abstract: Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including complex objective balancing, low training efficiency, poor scalability, and limited explainability. Leveraging ensemble learning principles, we introduce an Ensemble Multi-Objective RL (EMORL) framework that fine-tunes multiple models with individual objectives while optimizing their aggregation after the training to improve efficiency and flexibility. Our method is the first to aggregate the last hidden states of individual models, incorporating contextual information from multiple objectives. This approach is supported by a hierarchical grid search algorithm that identifies optimal weighted combinations. We evaluate EMORL on counselor reflection generation tasks, using text-scoring LLMs to evaluate the generations and provide rewards during RL fine-tuning. Through comprehensive experiments on the PAIR and Psych8k datasets, we demonstrate the advantages of EMORL against existing baselines: significantly lower and more stable training consumption ($17,529\pm 1,650$ data points and $6,573\pm 147.43$ seconds), improved scalability and explainability, and comparable performance across multiple objectives.
Authors: Mei Qiu, William Lorenz Reindl, Yaobin Chen, Stanley Chien, Shu Hu
Abstract: This paper proposes a scalable and interpretable framework for lane-wise highway traffic anomaly detection, leveraging multi-modal time series data extracted from surveillance cameras. Unlike traditional sensor-dependent methods, our approach uses AI-powered vision models to extract lane-specific features, including vehicle count, occupancy, and truck percentage, without relying on costly hardware or complex road modeling. We introduce a novel dataset containing 73,139 lane-wise samples, annotated with four classes of expert-validated anomalies: three traffic-related anomalies (lane blockage and recovery, foreign object intrusion, and sustained congestion) and one sensor-related anomaly (camera angle shift). Our multi-branch detection system integrates deep learning, rule-based logic, and machine learning to improve robustness and precision. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods in precision, recall, and F1-score, providing a cost-effective and scalable solution for real-world intelligent transportation systems.
Authors: Yura Malitsky, Alexander Posch
Abstract: This paper focuses on applying entropic mirror descent to solve linear systems, where the main challenge for the convergence analysis stems from the unboundedness of the domain. To overcome this without imposing restrictive assumptions, we introduce a variant of Polyak-type stepsizes. Along the way, we strengthen the bound for $\ell_1$-norm implicit bias, obtain sublinear and linear convergence results, and generalize the convergence result to arbitrary convex $L$-smooth functions. We also propose an alternative method that avoids exponentiation, resembling the original Hadamard descent, but with provable convergence.
Authors: Valentin Foucher, Santiago de Leon-Martinez, Robert Moro
Abstract: Gaze may enhance the robustness of lie detectors but remains under-studied. This study evaluated the efficacy of AI models (using fixations, saccades, blinks, and pupil size) for detecting deception in Concealed Information Tests across two datasets. The first, collected with Eyelink 1000, contains gaze data from a computerized experiment where 87 participants revealed, concealed, or faked the value of a previously selected card. The second, collected with Pupil Neon, involved 36 participants performing a similar task but facing an experimenter. XGBoost achieved accuracies up to 74% in a binary classification task (Revealing vs. Concealing) and 49% in a more challenging three-classification task (Revealing vs. Concealing vs. Faking). Feature analysis identified saccade number, duration, amplitude, and maximum pupil size as the most important for deception prediction. These results demonstrate the feasibility of using gaze and AI to enhance lie detectors and encourage future research that may improve on this.
Authors: Ali Rashidi Moghadam, Sayedmohammadreza Rastegari, Mehdi Tale Masouleh, Ahmad Kalhor
Abstract: Grasp pose detection in cluttered, real-world environments remains a significant challenge due to noisy and incomplete sensory data combined with complex object geometries. This paper introduces Grasp the Graph 2.0 (GtG 2.0) method, a lightweight yet highly effective hypothesis-and-test robotics grasping framework which leverages an ensemble of Graph Neural Networks for efficient geometric reasoning from point cloud data. Building on the success of GtG 1.0, which demonstrated the potential of Graph Neural Networks for grasp detection but was limited by assumptions of complete, noise-free point clouds and 4-Dof grasping, GtG 2.0 employs a conventional Grasp Pose Generator to efficiently produce 7-Dof grasp candidates. Candidates are assessed with an ensemble Graph Neural Network model which includes points within the gripper jaws (inside points) and surrounding contextual points (outside points). This improved representation boosts grasp detection performance over previous methods using the same generator. GtG 2.0 shows up to a 35% improvement in Average Precision on the GraspNet-1Billion benchmark compared to hypothesis-and-test and Graph Neural Network-based methods, ranking it among the top three frameworks. Experiments with a 3-Dof Delta Parallel robot and Kinect-v1 camera show a success rate of 91% and a clutter completion rate of 100%, demonstrating its flexibility and reliability.
Authors: Rauno Arike, Elizabeth Donoway, Henning Bartsch, Marius Hobbhahn
Abstract: As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human oversight, even initially well-specified goals may gradually shift. Detecting and measuring goal drift - an agent's tendency to deviate from its original objective over time - presents significant challenges, as goals can shift gradually, causing only subtle behavioral changes. This paper proposes a novel approach to analyzing goal drift in LM agents. In our experiments, agents are first explicitly given a goal through their system prompt, then exposed to competing objectives through environmental pressures. We demonstrate that while the best-performing agent (a scaffolded version of Claude 3.5 Sonnet) maintains nearly perfect goal adherence for more than 100,000 tokens in our most difficult evaluation setting, all evaluated models exhibit some degree of goal drift. We also find that goal drift correlates with models' increasing susceptibility to pattern-matching behaviors as the context length grows.
Authors: Junu Kim, Chaeeun Shim, Sungjin Park, Su Yeon Lee, Gee Young Suh, Chae-Man Lim, Seong Jin Choi, Song Mi Moon, Kyoung-Ho Song, Eu Suk Kim, Hong Bin Kim, Sejoong Kim, Chami Im, Dong-Wan Kang, Yong Soo Kim, Hee-Joon Bae, Sung Yoon Lim, Han-Gil Jeong, Edward Choi
Abstract: Although large language models (LLMs) have demonstrated impressive reasoning capabilities across general domains, their effectiveness in real-world clinical practice remains limited. This is likely due to their insufficient exposure to real-world clinical data during training, as such data is typically not included due to privacy concerns. To address this, we propose enhancing the clinical reasoning capabilities of LLMs by leveraging real-world clinical data. We constructed reasoning-intensive questions from a nationwide sepsis registry and fine-tuned Phi-4 on these questions using reinforcement learning, resulting in C-Reason. C-Reason exhibited strong clinical reasoning capabilities on the in-domain test set, as evidenced by both quantitative metrics and expert evaluations. Furthermore, its enhanced reasoning capabilities generalized to a sepsis dataset involving different tasks and patient cohorts, an open-ended consultations on antibiotics use task, and other diseases. Future research should focus on training LLMs with large-scale, multi-disease clinical datasets to develop more powerful, general-purpose clinical reasoning models.
Authors: Zhouliang Yu, Ruotian Peng, Keyi Ding, Yizhe Li, Zhongyuan Peng, Minghao Liu, Yifan Zhang, Zheng Yuan, Huajian Xin, Wenhao Huang, Yandong Wen, Ge Zhang, Weiyang Liu
Abstract: Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we present FormalMATH, a large-scale Lean4 benchmark comprising 5,560 formally verified problems spanning from high-school Olympiad challenges to undergraduate-level theorems across diverse domains (e.g., algebra, applied mathematics, calculus, number theory, and discrete mathematics). To mitigate the inefficiency of manual formalization, we introduce a novel human-in-the-loop autoformalization pipeline that integrates: (1) specialized large language models (LLMs) for statement autoformalization, (2) multi-LLM semantic verification, and (3) negation-based disproof filtering strategies using off-the-shelf LLM-based provers. This approach reduces expert annotation costs by retaining 72.09% of statements before manual verification while ensuring fidelity to the original natural-language problems. Our evaluation of state-of-the-art LLM-based theorem provers reveals significant limitations: even the strongest models achieve only 16.46% success rate under practical sampling budgets, exhibiting pronounced domain bias (e.g., excelling in algebra but failing in calculus) and over-reliance on simplified automation tactics. Notably, we identify a counterintuitive inverse relationship between natural-language solution guidance and proof success in chain-of-thought reasoning scenarios, suggesting that human-written informal reasoning introduces noise rather than clarity in the formal reasoning settings. We believe that FormalMATH provides a robust benchmark for benchmarking formal mathematical reasoning.
Authors: Simon Ging, Sebastian Walter, Jelena Bratuli\'c, Johannes Dienert, Hannah Bast, Thomas Brox
Abstract: Training high-quality CLIP models typically requires enormous datasets, which limits the development of domain-specific models -- especially in areas that even the largest CLIP models do not cover well -- and drives up training costs. This poses challenges for scientific research that needs fine-grained control over the training procedure of CLIP models. In this work, we show that by employing smart web search strategies enhanced with knowledge graphs, a robust CLIP model can be trained from scratch with considerably less data. Specifically, we demonstrate that an expert foundation model for living organisms can be built using just 10M images. Moreover, we introduce EntityNet, a dataset comprising 33M images paired with 46M text descriptions, which enables the training of a generic CLIP model in significantly reduced time.
Authors: Yige Wang, Jiashuo Jiang
Abstract: We study how a budget-constrained bidder should learn to adaptively bid in repeated first-price auctions to maximize her cumulative payoff. This problem arose due to an industry-wide shift from second-price auctions to first-price auctions in display advertising recently, which renders truthful bidding (i.e., always bidding one's private value) no longer optimal. We propose a simple dual-gradient-descent-based bidding policy that maintains a dual variable for budget constraint as the bidder consumes her budget. In analysis, we consider two settings regarding the bidder's knowledge of her private values in the future: (i) an uninformative setting where all the distributional knowledge (can be non-stationary) is entirely unknown to the bidder, and (ii) an informative setting where a prediction of the budget allocation in advance. We characterize the performance loss (or regret) relative to an optimal policy with complete information on the stochasticity. For uninformative setting, We show that the regret is \tilde{O}(\sqrt{T}) plus a variation term that reflects the non-stationarity of the value distributions, and this is of optimal order. We then show that we can get rid of the variation term with the help of the prediction; specifically, the regret is \tilde{O}(\sqrt{T}) plus the prediction error term in the informative setting.
Authors: Hao Zhu, Phil Cuvin, Xinkai Yu, Charlotte Ka Yee Yan, Jason Zhang, Diyi Yang
Abstract: Agents are predominantly evaluated and optimized via task success metrics, which are coarse, rely on manual design from experts, and fail to reward intermediate emergent behaviors. We propose AutoLibra, a framework for agent evaluation, that transforms open-ended human feedback, e.g., "If you find that the button is disabled, don't click it again", or "This agent has too much autonomy to decide what to do on its own", into metrics for evaluating fine-grained behaviors in agent trajectories. AutoLibra accomplishes this by grounding feedback to an agent's behavior, clustering similar positive and negative behaviors, and creating concrete metrics with clear definitions and concrete examples, which can be used for prompting LLM-as-a-Judge as evaluators. We further propose two meta-metrics to evaluate the alignment of a set of (induced) metrics with open feedback: "coverage" and "redundancy". Through optimizing these meta-metrics, we experimentally demonstrate AutoLibra's ability to induce more concrete agent evaluation metrics than the ones proposed in previous agent evaluation benchmarks and discover new metrics to analyze agents. We also present two applications of AutoLibra in agent improvement: First, we show that AutoLibra-induced metrics serve as better prompt-engineering targets than the task success rate on a wide range of text game tasks, improving agent performance over baseline by a mean of 20%. Second, we show that AutoLibra can iteratively select high-quality fine-tuning data for web navigation agents. Our results suggest that AutoLibra is a powerful task-agnostic tool for evaluating and improving language agents.
Authors: Yanjie Ze, Zixuan Chen, Jo\~ao Pedro Ara\'ujo, Zi-ang Cao, Xue Bin Peng, Jiajun Wu, C. Karen Liu
Abstract: Teleoperating humanoid robots in a whole-body manner marks a fundamental step toward developing general-purpose robotic intelligence, with human motion providing an ideal interface for controlling all degrees of freedom. Yet, most current humanoid teleoperation systems fall short of enabling coordinated whole-body behavior, typically limiting themselves to isolated locomotion or manipulation tasks. We present the Teleoperated Whole-Body Imitation System (TWIST), a system for humanoid teleoperation through whole-body motion imitation. We first generate reference motion clips by retargeting human motion capture data to the humanoid robot. We then develop a robust, adaptive, and responsive whole-body controller using a combination of reinforcement learning and behavior cloning (RL+BC). Through systematic analysis, we demonstrate how incorporating privileged future motion frames and real-world motion capture (MoCap) data improves tracking accuracy. TWIST enables real-world humanoid robots to achieve unprecedented, versatile, and coordinated whole-body motor skills--spanning whole-body manipulation, legged manipulation, locomotion, and expressive movement--using a single unified neural network controller. Our project website: https://humanoid-teleop.github.io
Authors: Simone Luetto, Fabrizio Garuti, Enver Sangineto, Lorenzo Forni, Rita Cucchiara
Abstract: There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features are represented using a set of frequency functions and the whole network is uniformly trained with a unique loss function.
Authors: Weiming Zhuang, Chen Chen, Jingtao Li, Chaochao Chen, Yaochu Jin, Lingjuan Lyu
Abstract: The intersection of Foundation Model (FM) and Federated Learning (FL) presents a unique opportunity to unlock new possibilities for real-world applications. On the one hand, FL, as a collaborative learning paradigm, help address challenges in FM development by expanding data availability, enabling computation sharing, facilitating the collaborative development of FMs, tackling continuous data update, avoiding FM monopoly, response delay and FM service down. On the other hand, FM, equipped with pre-trained knowledge and exceptional performance, can serve as a robust starting point for FL. It can also generate synthetic data to enrich data diversity and enhance overall performance of FL. Meanwhile, FM unlocks new sharing paradigm and multi-task and multi-modality capabilities for FL. By examining the interplay between FL and FM, this paper presents the motivations, challenges, and future directions of empowering FL with FM and empowering FM with FL. We hope that this work provides a good foundation to inspire future research efforts to drive advancements in both fields.
Authors: Sumit Kumar Banshal, Sajal Das, Shumaiya Akter Shammi, Narayan Ranjan Chakraborty, Aulia Luqman Aziz, Mohammed Aljuaid, Fazla Rabby, Rohit Bansal
Abstract: In recent years, Sentiment Analysis (SA) and Emotion Recognition (ER) have been increasingly popular in the Bangla language, which is the seventh most spoken language throughout the entire world. However, the language is structurally complicated, which makes this field arduous to extract emotions in an accurate manner. Several distinct approaches such as the extraction of positive and negative sentiments as well as multiclass emotions, have been implemented in this field of study. Nevertheless, the extraction of multiple sentiments is an almost untouched area in this language. Which involves identifying several feelings based on a single piece of text. Therefore, this study demonstrates a thorough method for constructing an annotated corpus based on scrapped data from Facebook to bridge the gaps in this subject area to overcome the challenges. To make this annotation more fruitful, the context-based approach has been used. Bidirectional Encoder Representations from Transformers (BERT), a well-known methodology of transformers, have been shown the best results of all methods implemented. Finally, a web application has been developed to demonstrate the performance of the pre-trained top-performer model (BERT) for multi-label ER in Bangla.
Authors: Shirui Chen, Stefano Recanatesi, Eric Shea-Brown
Abstract: Sharpness, a geometric measure in the parameter space that reflects the flatness of the loss landscape, has long been studied for its potential connections to neural network behavior. While sharpness is often associated with generalization, recent work highlights inconsistencies in this relationship, leaving its true significance unclear. In this paper, we investigate how sharpness influences the local geometric features of neural representations in feature space, offering a new perspective on its role. We introduce this problem and study three measures for compression: the Local Volumetric Ratio (LVR), based on volume compression, the Maximum Local Sensitivity (MLS), based on sensitivity to input changes, and the Local Dimensionality, based on how uniform the sensitivity is on different directions. We show that LVR and MLS correlate with the flatness of the loss around the local minima; and that this correlation is predicted by a relatively simple mathematical relationship: a flatter loss corresponds to a lower upper bound on the compression metrics of neural representations. Our work builds upon the linear stability insight by Ma and Ying, deriving inequalities between various compression metrics and quantities involving sharpness. Our inequalities readily extend to reparametrization-invariant sharpness as well. Through empirical experiments on various feedforward, convolutional, and transformer architectures, we find that our inequalities predict a consistently positive correlation between local representation compression and sharpness.
Authors: Qitian Wu, Chenxiao Yang, Kaipeng Zeng, Michael Bronstein
Abstract: The capability of generalization is a cornerstone for the success of modern learning systems. For non-Euclidean data, e.g., graphs, that particularly involves topological structures, one important aspect neglected by prior studies is how machine learning models generalize under topological shifts. This paper proposes AdvDIFFormer, a physics-inspired graph Transformer model designed to address this challenge. The model is derived from advective diffusion equations which describe a class of continuous message passing process with observed and latent topological structures. We show that AdvDIFFormer has provable capability for controlling generalization error with topological shifts, which in contrast cannot be guaranteed by graph diffusion models. Empirically, the model demonstrates superiority in various predictive tasks across information networks, molecular screening and protein interactions.
Authors: Yuecheng Li, Lele Fu, Tong Wang, Jian Lou, Bin Chen, Lei Yang, Jian Shen, Zibin Zheng, Chuan Chen
Abstract: To defend against privacy leakage of user data, differential privacy is widely used in federated learning, but it is not free. The addition of noise randomly disrupts the semantic integrity of the model and this disturbance accumulates with increased communication rounds. In this paper, we introduce a novel federated learning framework with rigorous privacy guarantees, named FedCEO, designed to strike a trade-off between model utility and user privacy by letting clients ''Collaborate with Each Other''. Specifically, we perform efficient tensor low-rank proximal optimization on stacked local model parameters at the server, demonstrating its capability to flexibly truncate high-frequency components in spectral space. This capability implies that our FedCEO can effectively recover the disrupted semantic information by smoothing the global semantic space for different privacy settings and continuous training processes. Moreover, we improve the SOTA utility-privacy trade-off bound by order of $\sqrt{d}$, where $d$ is the input dimension. We illustrate our theoretical results with experiments on representative datasets and observe significant performance improvements and strict privacy guarantees under different privacy settings. The code is available at https://github.com/6lyc/FedCEO_Collaborate-with-Each-Other.
URLs: https://github.com/6lyc/FedCEO_Collaborate-with-Each-Other.
Authors: Tongyi Liang, Han-Xiong Li
Abstract: Existing models encounter bottlenecks in balancing performance and computational efficiency when modeling long sequences. Although the state space model (SSM) has achieved remarkable success in handling long sequence tasks, it still faces the problem of large number of parameters. In order to further improve the efficiency of SSM, we propose a new state space layer based on multiple-input multiple-output SSM, called efficient SSM (eSSM). Our eSSM is built on the convolutional representation of multi-input and multi-input (MIMO) SSM. We propose a variety of effective strategies to improve the computational efficiency. The diagonalization of the system matrix first decouples the original system. Then a fast tensor convolution is proposed based on the fast Fourier transform. In addition, the block diagonalization of the SSM further reduces the model parameters and improves the model flexibility. Extensive experimental results show that the performance of the proposed model on multiple databases matches the performance of state-of-the-art models, such as S4, and is significantly better than Transformers and LSTM. In the model efficiency benchmark, the parameters of eSSM are only 12.89\% of LSTM and 13.24\% of Mamba. The training speed of eSSM is 3.94 times faster than LSTM and 1.35 times faster than Mamba. Code is available at: \href{https://github.com/leonty1/essm}{https://github.com/leonty1/essm}.
URLs: https://github.com/leonty1/essm, https://github.com/leonty1/essm
Authors: Bangchao Deng, Bingqing Qu, Pengyang Wang, Dingqi Yang, Benjamin Fankhauser, Philippe Cudre-Mauroux
Abstract: Location prediction forecasts a user's location based on historical user mobility traces. To tackle the intrinsic sparsity issue of real-world user mobility traces, spatiotemporal contexts have been shown as significantly useful. Existing solutions mostly incorporate spatiotemporal distances between locations in mobility traces, either by feeding them as additional inputs to Recurrent Neural Networks (RNNs) or by using them to search for informative past hidden states for prediction. However, such distance-based methods fail to capture the time-varying temporal regularities of human mobility, where human mobility is often more regular in the morning than in other periods, for example; this suggests the usefulness of the actual timestamps besides the temporal distances. Against this background, we propose REPLAY, a general RNN architecture learning to capture the time-varying temporal regularities for location prediction. Specifically, REPLAY not only resorts to the spatiotemporal distances in sparse trajectories to search for the informative past hidden states, but also accommodates the time-varying temporal regularities by incorporating smoothed timestamp embeddings using Gaussian weighted averaging with timestamp-specific learnable bandwidths, which can flexibly adapt to the temporal regularities of different strengths across different timestamps. Our extensive evaluation compares REPLAY against a sizable collection of state-of-the-art techniques on two real-world datasets. Results show that REPLAY consistently and significantly outperforms state-of-the-art methods by 7.7\%-10.5\% in the location prediction task, and the bandwidths reveal interesting patterns of the time-varying temporal regularities.
Authors: Jungwon Choi, Hyungi Lee, Byung-Hoon Kim, Juho Lee
Abstract: Graph Neural Networks (GNNs) have shown promise in learning dynamic functional connectivity for distinguishing phenotypes from human brain networks. However, obtaining extensive labeled clinical data for training is often resource-intensive, making practical application difficult. Leveraging unlabeled data thus becomes crucial for representation learning in a label-scarce setting. Although generative self-supervised learning techniques, especially masked autoencoders, have shown promising results in representation learning in various domains, their application to dynamic graphs for dynamic functional connectivity remains underexplored, facing challenges in capturing high-level semantic representations. Here, we introduce the Spatio-Temporal Joint Embedding Masked Autoencoder (ST-JEMA), drawing inspiration from the Joint Embedding Predictive Architecture (JEPA) in computer vision. ST-JEMA employs a JEPA-inspired strategy for reconstructing dynamic graphs, which enables the learning of higher-level semantic representations considering temporal perspectives, addressing the challenges in fMRI data representation learning. Utilizing the large-scale UK Biobank dataset for self-supervised learning, ST-JEMA shows exceptional representation learning performance on dynamic functional connectivity demonstrating superiority over previous methods in predicting phenotypes and psychiatric diagnoses across eight benchmark fMRI datasets even with limited samples and effectiveness of temporal reconstruction on missing data scenarios. These findings highlight the potential of our approach as a robust representation learning method for leveraging label-scarce fMRI data.
Authors: Hao Chen, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj, Jindong Wang
Abstract: Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise that may adversely affect the generalization of the model and pose unexpected risks. This paper stands out as the first work to comprehensively understand and analyze the nature of noise in pre-training datasets and then effectively mitigate its impacts on downstream tasks. Specifically, through extensive experiments of fully-supervised and image-text contrastive pre-training on synthetic noisy ImageNet-1K, YFCC15M, and CC12M datasets, we demonstrate that, while slight noise in pre-training can benefit in-domain (ID) performance, where the training and testing data share a similar distribution, it always deteriorates out-of-domain (OOD) performance, where training and testing distributions are significantly different. These observations are agnostic to scales of pre-training datasets, pre-training noise types, model architectures, pre-training objectives, downstream tuning methods, and downstream applications. We empirically ascertain that the reason behind this is that the pre-training noise shapes the feature space differently. We then propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization, which is applicable in both parameter-efficient and black-box tuning manners. We additionally conduct extensive experiments on popular vision and language models, including APIs, which are supervised and self-supervised pre-trained on realistic noisy data for evaluation. Our analysis and results demonstrate the importance of this novel and fundamental research direction, which we term as Noisy Model Learning.
Authors: Yu Wang, Lei Sang, Yi Zhang, Yiwen Zhang, Xindong Wu
Abstract: Heterogeneous Graphs (HGs) effectively model complex relationships in the real world through multi-type nodes and edges. In recent years, inspired by self-supervised learning (SSL), contrastive learning (CL)-based Heterogeneous Graphs Neural Networks (HGNNs) have shown great potential in utilizing data augmentation and contrastive discriminators for downstream tasks. However, data augmentation remains limited due to the graph data's integrity. Furthermore, the contrastive discriminators suffer from sampling bias and lack local heterogeneous information. To tackle the above limitations, we propose a novel Generative-Contrastive Heterogeneous Graph Neural Network (GC-HGNN). Specifically, we propose a heterogeneous graph generative learning method that enhances CL-based paradigm. This paradigm includes: 1) A contrastive view augmentation strategy using a masked autoencoder. 2) Position-aware and semantics-aware positive sample sampling strategy for generating hard negative samples. 3) A hierarchical contrastive learning strategy aimed at capturing local and global information. Furthermore, the hierarchical contrastive learning and sampling strategies aim to constitute an enhanced contrastive discriminator under the generative-contrastive perspective. Finally, we compare our model with seventeen baselines on eight real-world datasets. Our model outperforms the latest baselines on node classification and link prediction tasks.
Authors: Anshuman Chhabra, Bo Li, Jian Chen, Prasant Mohapatra, Hongfu Liu
Abstract: A core data-centric learning challenge is the identification of training samples that are detrimental to model performance. Influence functions serve as a prominent tool for this task and offer a robust framework for assessing training data influence on model predictions. Despite their widespread use, their high computational cost associated with calculating the inverse of the Hessian matrix pose constraints, particularly when analyzing large-sized deep models. In this paper, we establish a bridge between identifying detrimental training samples via influence functions and outlier gradient detection. This transformation not only presents a straightforward and Hessian-free formulation but also provides insights into the role of the gradient in sample impact. Through systematic empirical evaluations, we first validate the hypothesis of our proposed outlier gradient analysis approach on synthetic datasets. We then demonstrate its effectiveness in detecting mislabeled samples in vision models and selecting data samples for improving performance of natural language processing transformer models. We also extend its use to influential sample identification for fine-tuning Large Language Models.
Authors: Zaitian Wang, Pengfei Wang, Kunpeng Liu, Pengyang Wang, Yanjie Fu, Chang-Tien Lu, Charu C. Aggarwal, Jian Pei, Yuanchun Zhou
Abstract: Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing data samples. By leveraging data augmentation techniques, AI models can achieve significantly improved applicability in tasks involving scarce or imbalanced datasets, thereby substantially enhancing AI models' generalization capabilities. Existing literature surveys only focus on a certain type of specific modality data, and categorize these methods from modality-specific and operation-centric perspectives, which lacks a consistent summary of data augmentation methods across multiple modalities and limits the comprehension of how existing data samples serve the data augmentation process. To bridge this gap, we propose a more enlightening taxonomy that encompasses data augmentation techniques for different common data modalities. Specifically, from a data-centric perspective, this survey proposes a modality-independent taxonomy by investigating how to take advantage of the intrinsic relationship between data samples, including single-wise, pair-wise, and population-wise sample data augmentation methods. Additionally, we categorize data augmentation methods across five data modalities through a unified inductive approach.
Authors: Lorenzo Chicchi, Lorenzo Buffoni, Diego Febbe, Lorenzo Giambagli, Raffaele Marino, Duccio Fanelli
Abstract: In machine learning practice it is often useful to identify relevant input features, so as to obtain compact dataset for more efficient numerical handling. On the other hand, by isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we propose a novel method to estimate the relative importance of the input components for a Deep Neural Network. This is achieved by leveraging on a spectral re-parametrization of the optimization process. Eigenvalues associated to input nodes provide in fact a robust proxy to gauge the relevance of the supplied entry features. Notably, the spectral features ranking is performed automatically, as a byproduct of the network training, with no additional processing to be carried out. The technique is successfully challenged against both synthetic and real data.
Authors: Christos Chatzis, Carla Schenker, Max Pfeffer, Evrim Acar
Abstract: Tensor factorizations have been widely used for the task of uncovering patterns in various domains. Often, the input is time-evolving, shifting the goal to tracking the evolution of the underlying patterns instead. To adapt to this more complex setting, existing methods incorporate temporal regularization but they either have overly constrained structural requirements or lack uniqueness which is crucial for interpretation. In this paper, in order to capture the underlying evolving patterns, we introduce t(emporal)PARAFAC2, which utilizes temporal smoothness regularization on the evolving factors. Previously, Alternating Optimization (AO) and Alternating Direction Method of Multipliers (ADMM)-based algorithmic approach has been introduced to fit the PARAFAC2 model to fully observed data. In this paper, we extend this algorithmic framework to the case of partially observed data and use it to fit the tPARAFAC2 model to complete and incomplete datasets with the goal of revealing evolving patterns. Our numerical experiments on simulated datasets demonstrate that tPARAFAC2 can extract the underlying evolving patterns more accurately compared to the state-of-the-art in the presence of high amounts of noise and missing data. Using two real datasets, we also demonstrate the effectiveness of the algorithmic approach in terms of handling missing data and tPARAFAC2 model in terms of revealing evolving patterns. The paper provides an extensive comparison of different approaches for handling missing data within the proposed framework, and discusses both the advantages and limitations of tPARAFAC2 model.
Authors: Benjamin Rodatz, Ian Fan, Tuomas Laakkonen, Neil John Ortega, Thomas Hoffmann, Vincent Wang-Mascianica
Abstract: We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our theoretical framework, we exhibit and implement a novel "manipulator" task that minimally edits input data to have a desired attribute. Our model-agnostic approach achieves this end-to-end, and without the need for custom architectures, adversarial training, random sampling, or interventions on the data, hence enabling capable, small-scale, and training-stable models.
Authors: Mohammad Kohankhaki, Ahmad Ayad, Mahdi Barhoush, Anke Schmeink
Abstract: Distributed deep learning in resource-constrained environments faces scalability and generalization challenges due to large effective batch sizes and non-identically distributed client data. We introduce a server-driven sampling strategy that maintains a fixed global batch size by dynamically adjusting client-side batch sizes. This decouples the effective batch size from the number of participating devices and ensures that global batches better reflect the overall data distribution. Using standard concentration bounds, we establish tighter deviation guarantees compared to existing approaches. Empirical results on a benchmark dataset confirm that the proposed method improves model accuracy, training efficiency, and convergence stability, offering a scalable solution for learning at the network edge.
Authors: Salma Tenni, Daniel Gomes de Pinho Zanco, Leszek Szczecinski
Abstract: This work presents and evaluates the ranking algorithm that has been used by Federation Internationale de Volleyball (FIVB) since 2020. The prominent feature of the FIVB ranking is the use of the probabilistic model, which explicitly calculates the probabilities of the future matches results using the estimated teams' strengths. Such explicit modeling is new in the context of official sport rankings, especially for multi-level outcomes, and we study the optimality of its parameters using both analytical and numerical methods. We conclude that from the modeling perspective, the current thresholds fit well the data but adding the home-field advantage (HFA) would be beneficial. Regarding the algorithm itself, we explain the rationale behind the approximations currently used and show a simple method to find new parameters (numerical score) which improve the performance. We also show that the weighting of the match results is counterproductive.
Authors: Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Sch\"onlieb
Abstract: The manifold hypothesis says that natural high-dimensional data lie on or around a low-dimensional manifold. The recent success of statistical and learning-based methods in very high dimensions empirically supports this hypothesis, suggesting that typical worst-case analysis does not provide practical guarantees. A natural step for analysis is thus to assume the manifold hypothesis and derive bounds that are independent of any ambient dimensions that the data may be embedded in. Theoretical implications in this direction have recently been explored in terms of generalization of ReLU networks and convergence of Langevin methods. In this work, we consider optimal uniform approximations with functions of finite statistical complexity. While upper bounds on uniform approximation exist in the literature using ReLU neural networks, we consider the opposite: lower bounds to quantify the fundamental difficulty of approximation on manifolds. In particular, we demonstrate that the statistical complexity required to approximate a class of bounded Sobolev functions on a compact manifold is bounded from below, and moreover that this bound is dependent only on the intrinsic properties of the manifold, such as curvature, volume, and injectivity radius.
Authors: Yilong Hou, Xi'an Li, Jinran Wu, You-Gan Wang
Abstract: Bayesian Physics Informed Neural Networks (BPINN) have attracted considerable attention for inferring the system states and physical parameters of differential equations according to noisy observations. However, in practice, Hamiltonian Monte Carlo (HMC) used to estimate the internal parameters of the solver for BPINN often encounters these troubles including poor performance and awful convergence for a given step size used to adjust the momentum of those parameters. To address the convergence of HMC for the BPINN method and extend its application scope to multi-scale partial differential equations (PDE), we develop a robust multi-scale BPINN (dubbed MBPINN) method by integrating multi-scale deep neural networks (MscaleDNN) and the BPINN framework. In this newly proposed MBPINN method, we reframe HMC with Stochastic Gradient Descent (SGD) to ensure the most ``likely'' estimation is always provided, and we configure its solver as a Fourier feature mapping-induced MscaleDNN. This novel method offers several key advantages: (1) it is more robust than HMC, (2) it incurs less computational cost than HMC, and (3) it is more flexible for complex problems. We demonstrate the applicability and performance of the proposed method through some general Poisson and multi-scale elliptic problems in one and two-dimensional Euclidean spaces. Our findings indicate that the proposed method can avoid HMC failures and provide valid results. Additionally, our method is capable of handling complex elliptic PDE and producing comparable results for general elliptic PDE under the case of lower signal-to-noise rate. These findings suggest that our proposed approach has great potential for physics-informed machine learning for parameter estimation and solution recovery in the case of ill-posed problems.
Authors: Xiaochen Wang, Jiaqi Wang, Houping Xiao, Jinghui Chen, Fenglong Ma
Abstract: Foundation models have demonstrated remarkable capabilities in handling diverse modalities and tasks, outperforming conventional artificial intelligence (AI) approaches that are highly task-specific and modality-reliant. In the medical domain, however, the development of comprehensive foundation models is constrained by limited access to diverse modalities and stringent privacy regulations. To address these constraints, this study introduces a novel knowledge injection approach, FedKIM, designed to scale the medical foundation model within a federated learning framework. FedKIM leverages lightweight local models to extract healthcare knowledge from private data and integrates this knowledge into a centralized foundation model using a designed adaptive Multitask Multimodal Mixture Of Experts (M3OE) module. This method not only preserves privacy but also enhances the model's ability to handle complex medical tasks involving multiple modalities. Our extensive experiments across twelve tasks in seven modalities demonstrate the effectiveness of FedKIM in various settings, highlighting its potential to scale medical foundation models without direct access to sensitive data.
Authors: Yen-Ru Lai, Fu-Chieh Chang, Pei-Yuan Wu
Abstract: Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large datasets. In contrast, unlabelled data tends to be less expensive. This situation highlights the importance of finding effective ways to use unlabelled data in offline RL, especially when labelled data is limited or expensive to obtain. In this paper, we present the algorithm to utilize the unlabeled data in the offline RL method with kernel function approximation and give the theoretical guarantee. We present various eigenvalue decay conditions of $\mathcal{H}_k$ which determine the complexity of the algorithm. In summary, our work provides a promising approach for exploiting the advantages offered by unlabeled data in offline RL, whilst maintaining theoretical assurances.
Authors: Chen Hu, Hanchi Ren, Jingjing Deng, Xianghua Xie, Xiaoke Ma
Abstract: Federated learning is a machine learning paradigm that enables decentralized clients to collaboratively learn a shared model while keeping all the training data local. While considerable research has focused on federated image generation, particularly Generative Adversarial Networks, Variational Autoencoders have received less attention. In this paper, we address the challenges of non-IID (independently and identically distributed) data environments featuring multiple groups of images of different types. Non-IID data distributions can lead to difficulties in maintaining a consistent latent space and can also result in local generators with disparate texture features being blended during aggregation. We thereby introduce FissionVAE that decouples the latent space and constructs decoder branches tailored to individual client groups. This method allows for customized learning that aligns with the unique data distributions of each group. Additionally, we incorporate hierarchical VAEs and demonstrate the use of heterogeneous decoder architectures within FissionVAE. We also explore strategies for setting the latent prior distributions to enhance the decoupling process. To evaluate our approach, we assemble two composite datasets: the first combines MNIST and FashionMNIST; the second comprises RGB datasets of cartoon and human faces, wild animals, marine vessels, and remote sensing images. Our experiments demonstrate that FissionVAE greatly improves generation quality on these datasets compared to baseline federated VAE models.
Authors: Hongyang Lei, Xiaolong Cheng, Dan Wang, Kun Fan, Qi Qin, Huazhen Huang, Yetao Wu, Qingqing Gu, Zhonglin Jiang, Yong Chen, Luo Ji
Abstract: Current multimodal alignment strategies primarily use single or unified modality encoders, while optimizing the alignment on the original token space. Such a framework is easy to implement and incorporate with the pretrained knowledge, but might result in information bias. To deal with such issues, the joint encoding predictive architecture (JEPA) learns the alignment loss on the latent space, with a predictor to convert the input encoding to the output latent space. However, the application of JEPA in multimodal scenarios is limited so far. In this paper, we introduce M3-Jepa, a scalable multimodal alignment framework, with the predictor implemented by a multi-directional mixture of experts (MoE). We demonstrate the framework can maximize the mutual information with information theory derivations, by alternating the optimization between different uni-directional tasks. By thoroughly designed experiments, we show that M3-Jepa can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in training and inference. Our study indicates that M3-Jepa might provide a new paradigm to self-supervised learning and open-world modeling.
Authors: Jimeng Shi, Bowen Jin, Jiawei Han, Sundararaman Gopalakrishnan, Giri Narasimhan
Abstract: Accurate weather forecasting is critical for science and society. Yet, existing methods have not managed to simultaneously have the properties of high accuracy, low uncertainty, and high computational efficiency. On one hand, to quantify the uncertainty in weather predictions, the strategy of ensemble forecast (i.e., generating a set of diverse predictions) is often employed. However, traditional ensemble numerical weather prediction (NWP) is computationally intensive. On the other hand, most existing machine learning-based weather prediction (MLWP) approaches are efficient and accurate. Nevertheless, they are deterministic and cannot capture the uncertainty of weather forecasting. In this work, we propose CoDiCast, a conditional diffusion model to generate accurate global weather prediction, while achieving uncertainty quantification with ensemble forecasts and modest computational cost. The key idea is to simulate a conditional version of the reverse denoising process in diffusion models, which starts from pure Gaussian noise to generate realistic weather scenarios for a future time point. Each denoising step is conditioned on observations from the recent past. Ensemble forecasts are achieved by repeatedly sampling from stochastic Gaussian noise to represent uncertainty quantification. CoDiCast is trained on a decade of ERA5 reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF). Experimental results demonstrate that our approach outperforms several existing data-driven methods in accuracy. Our conditional diffusion model, CoDiCast, can generate 6-day global weather forecasts, at 6-hour steps and $5.625^\circ$ latitude-longitude resolution, for over 5 variables, in about 12 minutes on a commodity A100 GPU machine with 80GB memory. The open-souced code is provided at https://github.com/JimengShi/CoDiCast.
Authors: Lukas Schynol, Marius Pesavento
Abstract: Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.
Authors: Zhenyi Zhang, Tiejun Li, Peijie Zhou
Abstract: Reconstructing dynamics using samples from sparsely time-resolved snapshots is an important problem in both natural sciences and machine learning. Here, we introduce a new deep learning approach for solving regularized unbalanced optimal transport (RUOT) and inferring continuous unbalanced stochastic dynamics from observed snapshots. Based on the RUOT form, our method models these dynamics without requiring prior knowledge of growth and death processes or additional information, allowing them to be learned directly from data. Theoretically, we explore the connections between the RUOT and Schr\"odinger bridge problem and discuss the key challenges and potential solutions. The effectiveness of our method is demonstrated with a synthetic gene regulatory network, high-dimensional Gaussian Mixture Model, and single-cell RNA-seq data from blood development. Compared with other methods, our approach accurately identifies growth and transition patterns, eliminates false transitions, and constructs the Waddington developmental landscape. Our code is available at: https://github.com/zhenyiizhang/DeepRUOT.
Authors: Hainan Xu, Travis M. Bartley, Vladimir Bataev, Boris Ginsburg
Abstract: We present Hybrid-Autoregressive INference TrANsducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model. Trained with randomly masked predictor network outputs, HAINAN supports both autoregressive inference with all network components and non-autoregressive inference without the predictor. Additionally, we propose a novel semi-autoregressive inference paradigm that first generates an initial hypothesis using non-autoregressive inference, followed by refinement steps where each token prediction is regenerated using parallelized autoregression on the initial hypothesis. Experiments on multiple datasets across different languages demonstrate that HAINAN achieves efficiency parity with CTC in non-autoregressive mode and with TDT in autoregressive mode. In terms of accuracy, autoregressive HAINAN outperforms TDT and RNN-T, while non-autoregressive HAINAN significantly outperforms CTC. Semi-autoregressive inference further enhances the model's accuracy with minimal computational overhead, and even outperforms TDT results in some cases. These results highlight HAINAN's flexibility in balancing accuracy and speed, positioning it as a strong candidate for real-world speech recognition applications.
Authors: Jie Xiao, Qianyi Huang, Xu Chen, Chen Tian
Abstract: As large language models (LLMs) increasingly integrate into every aspect of our work and daily lives, there are growing concerns about user privacy, which push the trend toward local deployment of these models. There are a number of lightweight LLMs (e.g., Gemini Nano, LLAMA2 7B) that can run locally on smartphones, providing users with greater control over their personal data. As a rapidly emerging application, we are concerned about their performance on commercial-off-the-shelf mobile devices. To fully understand the current landscape of LLM deployment on mobile platforms, we conduct a comprehensive measurement study on mobile devices. We evaluate both metrics that affect user experience, including token throughput, latency, and battery consumption, as well as factors critical to developers, such as resource utilization, DVFS strategies, and inference engines. In addition, we provide a detailed analysis of how these hardware capabilities and system dynamics affect on-device LLM performance, which may help developers identify and address bottlenecks for mobile LLM applications. We also provide comprehensive comparisons across the mobile system-on-chips (SoCs) from major vendors, highlighting their performance differences in handling LLM workloads. We hope that this study can provide insights for both the development of on-device LLMs and the design for future mobile system architecture.
Authors: Amir Eskandari, Aman Anand, Drishti Sharma, Farhana Zulkernine
Abstract: In various applications, the multivariate time series often suffers from missing data. This issue can significantly disrupt systems that rely on the data. Spatial and temporal dependencies can be leveraged to impute the missing samples. Existing imputation methods often ignore dynamic changes in spatial dependencies. We propose a Spatial Dynamic Aware Graph Recurrent Imputation Network (SDA-GRIN) which is capable of capturing dynamic changes in spatial dependencies.SDA-GRIN leverages a multi-head attention mechanism to adapt graph structures with time. SDA-GRIN models multivariate time series as a sequence of temporal graphs and uses a recurrent message-passing architecture for imputation. We evaluate SDA-GRIN on four real-world datasets: SDA-GRIN improves MSE by 9.51% for the AQI and 9.40% for AQI-36. On the PEMS-BAY dataset, it achieves a 1.94% improvement in MSE. Detailed ablation study demonstrates the effect of window sizes and missing data on the performance of the method. Project page:https://ameskandari.github.io/sda-grin/
Authors: Hugo Thimonier, Jos\'e Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Li\^en Doan
Abstract: Self-supervision is often used for pre-training to foster performance on a downstream task by constructing meaningful representations of samples. Self-supervised learning (SSL) generally involves generating different views of the same sample and thus requires data augmentations that are challenging to construct for tabular data. This constitutes one of the main challenges of self-supervision for structured data. In the present work, we propose a novel augmentation-free SSL method for tabular data. Our approach, T-JEPA, relies on a Joint Embedding Predictive Architecture (JEPA) and is akin to mask reconstruction in the latent space. It involves predicting the latent representation of one subset of features from the latent representation of a different subset within the same sample, thereby learning rich representations without augmentations. We use our method as a pre-training technique and train several deep classifiers on the obtained representation. Our experimental results demonstrate a substantial improvement in both classification and regression tasks, outperforming models trained directly on samples in their original data space. Moreover, T-JEPA enables some methods to consistently outperform or match the performance of traditional methods likes Gradient Boosted Decision Trees. To understand why, we extensively characterize the obtained representations and show that T-JEPA effectively identifies relevant features for downstream tasks without access to the labels. Additionally, we introduce regularization tokens, a novel regularization method critical for training of JEPA-based models on structured data.
Authors: Noemi B\"uhrer, Sa\'ul Alonso-Monsalve, Matthew Franks, Till Dieminger, Davide Sgalaberna
Abstract: This paper presents the development and application of an AI-based method for particle track identification using scintillating fibres read out with imaging sensors. We propose a variational autoencoder (VAE) to efficiently filter and identify frames containing signal from the substantial data generated by SPAD array sensors. Our VAE model, trained on purely background frames, demonstrated a high capability to distinguish frames containing particle tracks from background noise. The performance of the VAE-based anomaly detection was validated with experimental data, demonstrating the method's ability to efficiently identify relevant events with rapid processing time, suggesting a solid prospect for deployment as a fast inference tool on hardware for real-time anomaly detection. This work highlights the potential of combining advanced sensor technology with machine learning techniques to enhance particle detection and tracking.
Authors: Youngjae Min, Navid Azizan
Abstract: Incorporating prior knowledge or specifications of input-output relationships into machine learning models has gained significant attention, as it enhances generalization from limited data and leads to conforming outputs. However, most existing approaches use soft constraints by penalizing violations through regularization, which offers no guarantee of constraint satisfaction--an essential requirement in safety-critical applications. On the other hand, imposing hard constraints on neural networks may hinder their representational power, adversely affecting performance. To address this, we propose HardNet, a practical framework for constructing neural networks that inherently satisfy hard constraints without sacrificing model capacity. Unlike approaches that modify outputs only at inference time, HardNet enables end-to-end training with hard constraint guarantees, leading to improved performance. To the best of our knowledge, HardNet is the first method with an efficient forward pass to enforce more than one input-dependent inequality constraint. It allows unconstrained optimization of the network parameters using standard algorithms by appending a differentiable closed-form enforcement layer to the network's output. Furthermore, we show that HardNet retains the universal approximation capabilities of neural networks. We demonstrate the versatility and effectiveness of HardNet across various applications: learning with piecewise constraints, learning optimization solvers, optimizing control policies in safety-critical systems, and learning safe decision logic for aircraft systems.
Authors: Peter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K. Gilson, Rose Yu
Abstract: Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show real-world experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning (MF-LAL), a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. We train a surrogate model for each oracle and use these surrogates to guide generation of compounds with high predicted activity. Unlike previous approaches that separately learn the surrogate model and generative model, MF-LAL combines the generative and multi-fidelity surrogate models into a single framework, allowing for more accurate activity prediction and higher quality samples. We train MF-LAL with a novel active learning algorithm to further reduce computational cost. Our experiments on two disease-relevant proteins show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches (~50% improvement in mean binding free energy score).
Authors: Md Abrar Jahin, Md. Akmol Masud, M. F. Mridha, Nilanjan Dey, Zeyar Aung
Abstract: In high-energy physics, particle jet tagging plays a pivotal role in distinguishing quark from gluon jets using data from collider experiments. While graph-based deep learning methods have advanced this task beyond traditional feature-engineered approaches, the complex data structure and limited labeled samples present ongoing challenges. However, existing contrastive learning (CL) frameworks struggle to leverage rationale-aware augmentations effectively, often lacking supervision signals that guide the extraction of salient features and facing computational efficiency issues such as high parameter counts. In this study, we demonstrate that integrating a quantum rationale generator (QRG) within our proposed Quantum Rationale-aware Graph Contrastive Learning (QRGCL) framework significantly enhances jet discrimination performance, reducing reliance on labeled data and capturing discriminative features. Evaluated on the quark-gluon jet dataset, QRGCL achieves an AUC score of $77.53\%$ while maintaining a compact architecture of only 45 QRG parameters, outperforming classical, quantum, and hybrid GCL and GNN benchmarks. These results highlight QRGCL's potential to advance jet tagging and other complex classification tasks in high-energy physics, where computational efficiency and feature extraction limitations persist.
Authors: Maximilian Fleissner, Gautham Govind Anil, Debarghya Ghoshdastidar
Abstract: The NTK is a widely used tool in the theoretical analysis of deep learning, allowing us to look at supervised deep neural networks through the lenses of kernel regression. Recently, several works have investigated kernel models for self-supervised learning, hypothesizing that these also shed light on the behavior of wide neural networks by virtue of the NTK. However, it remains an open question to what extent this connection is mathematically sound -- it is a commonly encountered misbelief that the kernel behavior of wide neural networks emerges irrespective of the loss function it is trained on. In this paper, we bridge the gap between the NTK and self-supervised learning, focusing on two-layer neural networks trained under the Barlow Twins loss. We prove that the NTK of Barlow Twins indeed becomes constant as the width of the network approaches infinity. Our analysis technique is a bit different from previous works on the NTK and may be of independent interest. Overall, our work provides a first justification for the use of classic kernel theory to understand self-supervised learning of wide neural networks. Building on this result, we derive generalization error bounds for kernelized Barlow Twins and connect them to neural networks of finite width.
Authors: Shovito Barua Soumma, S M Raihanul Alam, Rudmila Rahman, Umme Niraj Mahi, Abdullah Mamun, Sayyed Mostafa Mostafavi, Hassan Ghasemzadeh
Abstract: Freezing of gait (FOG) is a debilitating symptom of Parkinson's disease that impairs mobility and safety by increasing the risk of falls. An effective FOG detection system must be accurate, real-time, and deployable in free-living environments to enable timely interventions. However, existing detection methods face challenges due to (1) intra- and inter-patient variability, (2) subject-specific training, (3) using multiple sensors in FOG dominant locations (e.g., ankles) leading to high failure points, (4) centralized, non-adaptive learning frameworks that sacrifice patient privacy and prevent collaborative model refinement across populations and disease progression, and (5) most systems are tested in controlled settings, limiting their real-world applicability for continuous in-home monitoring. Addressing these gaps, we present FOGSense, a real-world deployable FOG detection system designed for uncontrolled, free-living conditions using only a single sensor. FOGSense uses Gramian Angular Field (GAF) transformations and privacy-preserving federated deep learning to capture temporal and spatial gait patterns missed by traditional methods with a low false positive rate. We evaluated our system using a public Parkinson's dataset collected in a free-living environment. FOGSense improves accuracy by 10.4% over a single-axis accelerometer, reduces failure points compared to multi-sensor systems, and demonstrates robustness to missing values. The federated architecture allows personalized model adaptation and efficient smartphone synchronization during off-peak hours, making it effective for long-term monitoring as symptoms evolve. Overall, FOGSense achieved a 22.2% improvement in F1-score and a 74.53% reduction in false positive rate compared to state-of-the-art methods, along with enhanced sensitivity for FOG episode detection.
Authors: Tao Zhang, Zhenhai Liu, Feipeng Qi, Yongjun Jiao, Tailin Wu
Abstract: Multiphysics simulation, which models the interactions between multiple physical processes, and multi-component simulation of complex structures are critical in fields like nuclear and aerospace engineering. Previous studies use numerical solvers or ML-based surrogate models for these simulations. However, multiphysics simulations typically require integrating multiple specialized solvers-each for a specific physical process-into a coupled program, which introduces significant development challenges. Furthermore, existing numerical algorithms struggle with highly complex large-scale structures in multi-component simulations. Here we propose compositional Multiphysics and Multi-component PDE Simulation with Diffusion models (M2PDE) to overcome these challenges. During diffusion-based training, M2PDE learns energy functions modeling the conditional probability of one physical process/component conditioned on other processes/components. In inference, M2PDE generates coupled multiphysics and multi-component solutions by sampling from the joint probability distribution. We evaluate M2PDE on two multiphysics tasks-reaction-diffusion and nuclear thermal coupling-where it achieves more accurate predictions than surrogate models in challenging scenarios. We then apply it to a multi-component prismatic fuel element problem, demonstrating that M2PDE scales from single-component training to a 64-component structure and outperforms existing domain-decomposition and graph-based approaches. The code is available at https://github.com/AI4Science-WestlakeU/M2PDE.
Authors: Mohammad Shahab Sepehri, Asal Mehradfar, Mahdi Soltanolkotabi, Salman Avestimehr
Abstract: Predicting Bitcoin price remains a challenging problem due to the high volatility and complex non-linear dynamics of cryptocurrency markets. Traditional time-series models, such as ARIMA and GARCH, and recurrent neural networks, like LSTMs, have been widely applied to this task but struggle to capture the regime shifts and long-range dependencies inherent in the data. In this work, we propose CryptoMamba, a novel Mamba-based State Space Model (SSM) architecture designed to effectively capture long-range dependencies in financial time-series data. Our experiments show that CryptoMamba not only provides more accurate predictions but also offers enhanced generalizability across different market conditions, surpassing the limitations of previous models. Coupled with trading algorithms for real-world scenarios, CryptoMamba demonstrates its practical utility by translating accurate forecasts into financial outcomes. Our findings signal a huge advantage for SSMs in stock and cryptocurrency price forecasting tasks.
Authors: Yiting Hu, Lingjie Duan
Abstract: The contextual bandit problem, where agents arrive sequentially with personal contexts and the system adapts its arm allocation decisions accordingly, has recently garnered increasing attention for enabling more personalized outcomes. However, in many healthcare and recommendation applications, agents have private profiles and may misreport their contexts to gain from the system. For example, in adaptive clinical trials, where hospitals sequentially recruit volunteers to test multiple new treatments and adjust plans based on volunteers' reported profiles such as symptoms and interim data, participants may misreport severe side effects like allergy and nausea to avoid perceived suboptimal treatments. We are the first to study this issue of private context misreporting in a stochastic contextual bandit game between the system and non-repeated agents. We show that traditional low-regret algorithms, such as UCB family algorithms and Thompson sampling, fail to ensure truthful reporting and can result in linear regret in the worst case, while traditional truthful algorithms like explore-then-commit (ETC) and $\epsilon$-greedy algorithm incur sublinear but high regret. We propose a mechanism that uses a linear program to ensure truthfulness while minimizing deviation from Thompson sampling, yielding an $O(\ln T)$ frequentist regret. Our numerical experiments further demonstrate strong performance in multiple contexts and across other distribution families.
Authors: Jiahao Chen, Bin Qin, Jiangmeng Li, Hao Chen, Bing Su
Abstract: Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing methods primarily focus on leveraging knowledge from these models, overlooking the inherent biases introduced by the imbalanced training data they rely on. In this paper, we examine how such imbalances from pre-training affect long-tailed downstream tasks. Specifically, we find the imbalance biases inherited in foundation models on downstream task as parameter imbalance and data imbalance. During fine-tuning, we observe that parameter imbalance plays a more critical role, while data imbalance can be mitigated using existing re-balancing strategies. Moreover, we find that parameter imbalance cannot be effectively addressed by current re-balancing techniques, such as adjusting the logits, during training, unlike data imbalance. To tackle both imbalances simultaneously, we build our method on causal learning and view the incomplete semantic factor as the confounder, which brings spurious correlations between input samples and labels. To resolve the negative effects of this, we propose a novel backdoor adjustment method that learns the true causal effect between input samples and labels, rather than merely fitting the correlations in the data. Notably, we achieve an average performance increase of about $1.67\%$ on each dataset.
Authors: Shaddin Dughmi
Abstract: The main goal of this article is to convince you, the reader, that supervised learning in the Probably Approximately Correct (PAC) model is closely related to -- of all things -- bipartite matching! En-route from PAC learning to bipartite matching, I will overview a particular transductive model of learning, and associated one-inclusion graphs, which can be viewed as a generalization of some of the hat puzzles that are popular in recreational mathematics. Whereas this transductive model is far from new, it has recently seen a resurgence of interest as a tool for tackling deep questions in learning theory. A secondary purpose of this article could be as a (biased) tutorial on the connections between the PAC and transductive models of learning.
Authors: Xinhao Yao, Ruifeng Ren, Yun Liao, Yong Liu
Abstract: The integration of explicit Chain-of-Thought (CoT) reasoning into training large language models (LLMs) has advanced their reasoning capabilities, yet the mechanisms by which CoT enhances generalization remain poorly understood. This work investigates (1) \textit{how} CoT training reshapes internal model representations and (2) \textit{why} it improves both in-distribution (ID) and out-of-distribution (OOD) reasoning generalization. Through controlled experiments and theoretical analysis, we derive the following key insights. \textbf{1)} Structural Advantage: CoT training internalizes reasoning into a two-stage generalizing circuit, where the number of stages corresponds to the explicit reasoning steps during training. Notably, CoT-trained models resolve intermediate results at shallower layers compared to non-CoT counterparts, freeing up deeper layers to specialize in subsequent reasoning steps. \textbf{2)} Theoretical Analysis: the information-theoretic generalization bounds via distributional divergence can be decomposed into ID and OOD components. While ID error diminishes with sufficient training regardless of CoT, OOD error critically depends on CoT: Non-CoT training fails to generalize to OOD samples due to unseen reasoning patterns, whereas CoT training achieves near-perfect OOD generalization by mastering subtasks and reasoning compositions during training. The identified mechanisms explain our experimental results: CoT training accelerates convergence and enhances generalization from ID to both ID and OOD scenarios while maintaining robust performance even with tolerable noise. These findings are further validated on complex real-world datasets. This paper offers valuable insights for designing CoT strategies to enhance LLM reasoning robustness.
Authors: Shenghong He
Abstract: Model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate trajectories that approximate the real data distribution to facilitate policy learning by using current information (e.g., the state and action at time step $t$). However, these works neglect the impact of historical information on environmental dynamics, leading to the generation of unreliable trajectories that may not align with the real data distribution. In this paper, we propose a new MORL algorithm \textbf{R}eliability-guaranteed \textbf{T}ransformer (RT), which can eliminate unreliable trajectories by calculating the cumulative reliability of the generated trajectory (i.e., using a weighted variational distance away from the real data). Moreover, by sampling candidate actions with high rewards, RT can efficiently generate high-return trajectories from the existing offline data. We theoretically prove the performance guarantees of RT in policy learning, and empirically demonstrate its effectiveness against state-of-the-art model-based methods on several benchmark tasks.
Authors: Sujeong Im, Jungwoo Oh, Edward Choi
Abstract: Lab tests are fundamental for diagnosing diseases and monitoring patient conditions. However, frequent testing can be burdensome for patients, and test results may not always be immediately available. To address these challenges, we propose LabTOP, a unified model that predicts lab test outcomes by leveraging a language modeling approach on EHR data. Unlike conventional methods that estimate only a subset of lab tests or classify discrete value ranges, LabTOP performs continuous numerical predictions for a diverse range of lab items. We evaluate LabTOP on three publicly available EHR datasets and demonstrate that it outperforms existing methods, including traditional machine learning models and state-of-the-art large language models. We also conduct extensive ablation studies to confirm the effectiveness of our design choices. We believe that LabTOP will serve as an accurate and generalizable framework for lab test outcome prediction, with potential applications in clinical decision support and early detection of critical conditions.
Authors: Chia-Wei Hsu, Nien-Ti Tsou, Yu-Cheng Chen, Yang Jeong Park, Ju Li
Abstract: Gradient-based optimization drives the unprecedented performance of modern deep neural network models across diverse applications. Adaptive algorithms have accelerated neural network training due to their rapid convergence rates; however, they struggle to find ``flat minima" reliably, resulting in suboptimal generalization compared to stochastic gradient descent (SGD). By revisiting various adaptive algorithms' mechanisms, we propose the Frankenstein optimizer, which combines their advantages. The proposed Frankenstein dynamically adjusts first- and second-momentum coefficients according to the optimizer's current state to directly maintain consistent learning dynamics and immediately reflect sudden gradient changes. Extensive experiments across several research domains such as computer vision, natural language processing, few-shot learning, and scientific simulations show that Frankenstein surpasses existing adaptive algorithms and SGD empirically regarding convergence speed and generalization performance. Furthermore, this research deepens our understanding of adaptive algorithms through centered kernel alignment analysis and loss landscape visualization during the learning process. Code is available at https://github.com/acctouhou/Frankenstein_optimizer
Authors: Ruizhi Zhang, Shengfeng Zhu, Kan Wang, Ding She, Jean-Philippe Argaud, Bertrand Bouriquet, Qing Li, Helin Gong
Abstract: Reactor physics is the study of neutron properties, focusing on using models to examine the interactions between neutrons and materials in nuclear reactors. Artificial intelligence (AI) has made significant contributions to reactor physics, e.g., in operational simulations, safety design, real-time monitoring, core management and maintenance. This paper presents a comprehensive review of AI approaches in reactor physics, especially considering the category of Machine Learning (ML), with the aim of describing the application scenarios, frontier topics, unsolved challenges and future research directions. From equation solving and state parameter prediction to nuclear industry applications, this paper provides a step-by-step overview of ML methods applied to steady-state, transient and combustion problems. Most literature works achieve industry-demanded models by enhancing the efficiency of deterministic methods or correcting uncertainty methods, which leads to successful applications. However, research on ML methods in reactor physics is somewhat fragmented, and the ability to generalize models needs to be strengthened. Progress is still possible, especially in addressing theoretical challenges and enhancing industrial applications such as building surrogate models and digital twins.
Authors: Saurabh Kumar, Jacob Buckman, Carles Gelada, Sean Zhang
Abstract: Transformers with linear attention offer significant computational advantages over softmax-based transformers but often suffer from degraded performance. The symmetric power (sympow) transformer, a particular type of linear transformer, addresses some of this performance gap by leveraging symmetric tensor embeddings, achieving comparable performance to softmax transformers. However, the finite capacity of the recurrent state in sympow transformers limits their ability to retain information, leading to performance degradation when scaling the training or evaluation context length. To address this issue, we propose the conformal-sympow transformer, which dynamically frees up capacity using data-dependent multiplicative gating and adaptively stores information using data-dependent rotary embeddings. Preliminary experiments on the LongCrawl64 dataset demonstrate that conformal-sympow overcomes the limitations of sympow transformers, achieving robust performance across scaled training and evaluation contexts.
Authors: Mohit Pandey, Gopeshh Subbaraj, Artem Cherkasov, Martin Ester, Emmanuel Bengio
Abstract: Generative Flow Networks (GFlowNets) have recently emerged as a suitable framework for generating diverse and high-quality molecular structures by learning from rewards treated as unnormalized distributions. Previous works in this framework often restrict exploration by using predefined molecular fragments as building blocks, limiting the chemical space that can be accessed. In this work, we introduce Atomic GFlowNets (A-GFNs), a foundational generative model leveraging individual atoms as building blocks to explore drug-like chemical space more comprehensively. We propose an unsupervised pre-training approach using drug-like molecule datasets, which teaches A-GFNs about inexpensive yet informative molecular descriptors such as drug-likeliness, topological polar surface area, and synthetic accessibility scores. These properties serve as proxy rewards, guiding A-GFNs towards regions of chemical space that exhibit desirable pharmacological properties. We further implement a goal-conditioned finetuning process, which adapts A-GFNs to optimize for specific target properties. In this work, we pretrain A-GFN on a subset of ZINC dataset, and by employing robust evaluation metrics we show the effectiveness of our approach when compared to other relevant baseline methods for a wide range of drug design tasks.
Authors: Jannis O. Luebsen, Annika Eichler
Abstract: This paper addresses the integration of additional information sources into a Bayesian optimization framework while ensuring that safety constraints are satisfied. The interdependencies between these information sources are modeled using an unknown correlation matrix. We explore how uniform error bounds must be adjusted to maintain constraint satisfaction throughout the optimization process, considering both Bayesian and frequentist statistical perspectives. This is achieved by appropriately scaling the error bounds based on a confidence interval that can be estimated from the data. Furthermore, the efficacy of the proposed approach is demonstrated through experiments on two benchmark functions and a controller parameter optimization problem. Our results highlight a significant improvement in sample efficiency, demonstrating the methods suitability for optimizing expensive-to-evaluate functions.
Authors: Isma\"el Zighed, Nicolas Thome, Patrick Gallinari, Taraneh Sayadi
Abstract: Reduced order models (ROMs) play a critical role in fluid mechanics by providing low-cost predictions, making them an attractive tool for engineering applications. However, for ROMs to be widely applicable, they must not only generalise well across different regimes, but also provide a measure of confidence in their predictions. While recent data-driven approaches have begun to address nonlinear reduction techniques to improve predictions in transient environments, challenges remain in terms of robustness and parametrisation. In this work, we present a nonlinear reduction strategy specifically designed for transient flows that incorporates parametrisation and uncertainty quantification. Our reduction strategy features a variational auto-encoder (VAE) that uses variational inference for confidence measurement. We use a latent space transformer that incorporates recent advances in attention mechanisms to predict dynamical systems. Attention's versatility in learning sequences and capturing their dependence on external parameters enhances generalisation across a wide range of dynamics. Prediction, coupled with confidence, enables more informed decision making and addresses the need for more robust models. In addition, this confidence is used to cost-effectively sample the parameter space, improving model performance a priori across the entire parameter space without requiring evaluation data for the entire domain.
Authors: Enjun Du, Xunkai Li, Tian Jin, Zhihan Zhang, Rong-Hua Li, Guoren Wang
Abstract: The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic structural operations, lacking the capacity to generate semantically rich nodes with meaningful textual attributes: a critical limitation for real-world applications. While large language models (LLMs) demonstrate exceptional text generation capabilities, their direct application to graph synthesis is impeded by context window limitations, hallucination phenomena, and structural consistency challenges. To address these issues, we introduce GraphMaster, the first multi-agent framework specifically designed for graph data synthesis in data-limited environments. GraphMaster orchestrates four specialized LLM agents (Manager, Perception, Enhancement, and Evaluation) that collaboratively optimize the synthesis process through iterative refinement, ensuring both semantic coherence and structural integrity. To rigorously evaluate our approach, we create new data-limited "Sub" variants of six standard graph benchmarks, specifically designed to test synthesis capabilities under realistic constraints. Additionally, we develop a novel interpretability assessment framework that combines human evaluation with a principled Grassmannian manifold-based analysis, providing both qualitative and quantitative measures of semantic coherence. Experimental results demonstrate that GraphMaster significantly outperforms traditional synthesis methods across multiple datasets, establishing a strong foundation for advancing GFMs in data-scarce environments.
Authors: Ali Eslamian, Alireza Afzal Aghaei, Qiang Cheng
Abstract: Tabular data analysis presents unique challenges due to its heterogeneous feature types, missing values, and complex interactions. While traditional machine learning methods, such as gradient boosting, often outperform deep learning approaches, recent advancements in neural architectures offer promising alternatives. This paper introduces TabKAN, a novel framework that advances tabular data modeling using Kolmogorov-Arnold Networks (KANs). Unlike conventional deep learning models, KANs leverge learnable activation functions on edges, which improve both interpretability and training efficiency. Our contributions include: (1) the introduction of modular KAN-based architectures for tabular data analysis, (2) the development of a transfer learning framework for KAN models that supports knowledge transfer between domains, (3) the development of model-specific interpretability for tabular data learning, which reduces dependence on post hoc and model-agnostic analysis, and (4) comprehensive evaluation of vanilla supervised learning across binary and multi-class classification tasks. Through extensive benchmarking on diverse public datasets, TabKAN demonstrates superior performance in supervised learning while significantly outperforming classical and Transformer-based models in transfer learning scenarios. Our findings highlight the advantage of KAN-based architectures in transferring knowledge across domains and narrowing the gap between traditional machine learning and deep learning for structured data.
Authors: Haozhe Wang, Chao Qu, Zuming Huang, Wei Chu, Fangzhen Lin, Wenhu Chen
Abstract: Recently, slow-thinking systems like GPT-o1 and DeepSeek-R1 have demonstrated great potential in solving challenging problems through explicit reflection. They significantly outperform the best fast-thinking models, such as GPT-4o, on various math and science benchmarks. However, their multimodal reasoning capabilities remain on par with fast-thinking models. For instance, GPT-o1's performance on benchmarks like MathVista, MathVerse, and MathVision is similar to fast-thinking models. In this paper, we aim to enhance the slow-thinking capabilities of vision-language models using reinforcement learning (without relying on distillation) to advance the state of the art. First, we adapt the GRPO algorithm with a novel technique called Selective Sample Replay (SSR) to address the vanishing advantages problem. While this approach yields strong performance, the resulting RL-trained models exhibit limited self-reflection or self-verification. To further encourage slow-thinking, we introduce Forced Rethinking, which appends a rethinking trigger token to the end of rollouts in RL training, explicitly enforcing a self-reflection reasoning step. By combining these two techniques, our model, VL-Rethinker, advances state-of-the-art scores on MathVista, MathVerse to achieve 80.4%, 63.5% respectively. VL-Rethinker also achieves open-source SoTA on multi-disciplinary benchmarks such as MathVision, MMMU-Pro, EMMA, and MEGA-Bench, narrowing the gap with OpenAI-o1. Our empirical results show the effectiveness of our approaches.
Authors: Yangxin Fan, Haolai Che, Yinghui Wu
Abstract: Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph $G$ and a GNN $M$, an IFGC computes a small compressed graph $G_c$, to best preserve the inference results of $M$ over $G$, such that the result can be directly inferred by accessing $G_c$ with no or little decompression cost. (1) We characterize IFGC with a class of inference equivalence relation. The relation captures the node pairs in $G$ that are not distinguishable for GNN inference. (2) We introduce three practical specifications of IFGC for representative GNNs: structural preserving compression (SPGC), which computes $G_c$ that can be directly processed by GNN inference without decompression; ($\alpha$, $r$)-compression, that allows for a configurable trade-off between compression ratio and inference quality, and anchored compression that preserves inference results for specific nodes of interest. For each scheme, we introduce compression and inference algorithms with guarantees of efficiency and quality of the inferred results. We conduct extensive experiments on diverse sets of large-scale graphs, which verifies the effectiveness and efficiency of our graph compression approaches.
Authors: Dejan Stancevic, Luca Ambrogioni
Abstract: The practical performance of generative diffusion models depends on the appropriate choice of the noise scheduling function, which can also be equivalently expressed as a time reparameterization. In this paper, we present a time scheduler that selects sampling points based on entropy rather than uniform time spacing, ensuring that each point contributes an equal amount of information to the final generation. We prove that this time reparameterization does not depend on the initial choice of time. Furthermore, we provide a tractable exact formula to estimate this \emph{entropic time} for a trained model using the training loss without substantial overhead. Alongside the entropic time, inspired by the optimality results, we introduce a rescaled entropic time. In our experiments with mixtures of Gaussian distributions and ImageNet, we show that using the (rescaled) entropic times greatly improves the inference performance of trained models. In particular, we found that the image quality in pretrained EDM2 models, as evaluated by FID and FD-DINO scores, can be substantially increased by the rescaled entropic time reparameterization without increasing the number of function evaluations, with greater improvements in the few NFEs regime.
Authors: Andrew Gracyk
Abstract: We operate through the lens of ordinary differential equations and control theory to study the concept of observability in the context of neural state-space models and the Mamba architecture. We develop strategies to enforce observability, which are tailored to a learning context, specifically where the hidden states are learnable at initial time, in conjunction to over its continuum, and high-dimensional. We also highlight our methods emphasize eigenvalues, roots of unity, or both. Our methods effectuate computational efficiency when enforcing observability, sometimes at great scale. We formulate observability conditions in machine learning based on classical control theory and discuss their computational complexity. Our nontrivial results are fivefold. We discuss observability through the use of permutations in neural applications with learnable matrices without high precision. We present two results built upon the Fourier transform that effect observability with high probability up to the randomness in the learning. These results are worked with the interplay of representations in Fourier space and their eigenstructure, nonlinear mappings, and the observability matrix. We present a result for Mamba that is similar to a Hautus-type condition, but instead employs an argument using a Vandermonde matrix instead of eigenvectors. Our final result is a shared-parameter construction of the Mamba system, which is computationally efficient in high exponentiation. We develop a training algorithm with this coupling, showing it satisfies a Robbins-Monro condition under certain orthogonality, while a more classical training procedure fails to satisfy a contraction with high Lipschitz constant.
Authors: Wenxuan Li, Hang Zhao, Zhiyuan Yu, Yu Du, Qin Zou, Ruizhen Hu, Kai Xu
Abstract: While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution. To achieve robust policy learning and generalization, we opt to learn a world model of the 3D rigid body dynamics involved in non-prehensile manipulations and use it for model-based reinforcement learning. We propose PIN-WM, a Physics-INformed World Model that enables efficient end-to-end identification of a 3D rigid body dynamical system from visual observations. Adopting differentiable physics simulation, PIN-WM can be learned with only few-shot and task-agnostic physical interaction trajectories. Further, PIN-WM is learned with observational loss induced by Gaussian Splatting without needing state estimation. To bridge Sim2Real gaps, we turn the learned PIN-WM into a group of Digital Cousins via physics-aware randomizations which perturb physics and rendering parameters to generate diverse and meaningful variations of the PIN-WM. Extensive evaluations on both simulation and real-world tests demonstrate that PIN-WM, enhanced with physics-aware digital cousins, facilitates learning robust non-prehensile manipulation skills with Sim2Real transfer, surpassing the Real2Sim2Real state-of-the-arts.
Authors: Prajwal Chauhan, Salah Eddine Choutri, Mohamed Ghattassi, Nader Masmoudi, Saif Eddin Jabari
Abstract: This paper investigates the limitations of neural operators in learning solutions for a Hughes model, a first-order hyperbolic conservation law system for crowd dynamics. The model couples a Fokker-Planck equation representing pedestrian density with a Hamilton-Jacobi-type (eikonal) equation. This Hughes model belongs to the class of nonlinear hyperbolic systems that often exhibit complex solution structures, including shocks and discontinuities. In this study, we assess the performance of three state-of-the-art neural operators (Fourier Neural Operator, Wavelet Neural Operator, and Multiwavelet Neural Operator) in various challenging scenarios. Specifically, we consider (1) discontinuous and Gaussian initial conditions and (2) diverse boundary conditions, while also examining the impact of different numerical schemes. Our results show that these neural operators perform well in easy scenarios with fewer discontinuities in the initial condition, yet they struggle in complex scenarios with multiple initial discontinuities and dynamic boundary conditions, even when trained specifically on such complex samples. The predicted solutions often appear smoother, resulting in a reduction in total variation and a loss of important physical features. This smoothing behavior is similar to issues discussed by Daganzo (1995), where models that introduce artificial diffusion were shown to miss essential features such as shock waves in hyperbolic systems. These results suggest that current neural operator architectures may introduce unintended regularization effects that limit their ability to capture transport dynamics governed by discontinuities. They also raise concerns about generalizing these methods to traffic applications where shock preservation is essential.
Authors: Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim
Abstract: Recent research on graph neural networks (GNNs) has explored mechanisms for capturing local uncertainty and exploiting graph hierarchies to mitigate data sparsity and leverage structural properties. However, the synergistic integration of these two approaches remains underexplored. This work introduces a novel architecture, the Hierarchical Uncertainty-Aware Graph Neural Network (HU-GNN), which unifies multi-scale representation learning, principled uncertainty estimation, and self-supervised embedding diversity within a single end-to-end framework. Specifically, HU-GNN adaptively forms node clusters and estimates uncertainty at multiple structural scales from individual nodes to higher levels. These uncertainty estimates guide a robust message-passing mechanism and attention weighting, effectively mitigating noise and adversarial perturbations while preserving predictive accuracy on semi-supervised classification tasks. We also offer key theoretical contributions, including a probabilistic formulation, rigorous uncertainty-calibration guarantees, and formal robustness bounds. Extensive experiments on standard benchmarks demonstrate that our model achieves state-of-the-art robustness and interpretability.
Authors: Yu-hsuan Chen, Jing Bi, Cyril Ngo Ngoc, Victor Oancea, Jonathan Cagan, Levent Burak Kara
Abstract: AI-driven surrogate modeling has become an increasingly effective alternative to physics-based simulations for 3D design, analysis, and manufacturing. These models leverage data-driven methods to predict physical quantities traditionally requiring computationally expensive simulations. However, the scarcity of labeled CAD-to-simulation datasets has driven recent advancements in self-supervised and foundation models, where geometric representation learning is performed offline and later fine-tuned for specific downstream tasks. While these approaches have shown promise, their effectiveness is limited in applications requiring fine-scale geometric detail preservation. This work introduces a self-supervised geometric representation learning method designed to capture fine-scale geometric features from non-parametric 3D models. Unlike traditional end-to-end surrogate models, this approach decouples geometric feature extraction from downstream physics tasks, learning a latent space embedding guided by geometric reconstruction losses. Key elements include the essential use of near-zero level sampling and the innovative batch-adaptive attention-weighted loss function, which enhance the encoding of intricate design features. The proposed method is validated through case studies in structural mechanics, demonstrating strong performance in capturing design features and enabling accurate few-shot physics predictions. Comparisons with traditional parametric surrogate modeling highlight its potential to bridge the gap between geometric and physics-based representations, providing an effective solution for surrogate modeling in data-scarce scenarios.
Authors: Alan Lee, Harry Tong
Abstract: We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Rather than relying on full-sequence updates or separate critic networks, we design critic-free methods that operate on a small, informative subset of output tokens to reduce memory usage and stabilize training. We introduce S-GRPO, a stochastic variant of Group Relative Policy Optimization, and T-SPMO, a token-level prefix matching approach for fine-grained credit assignment. Applied to Qwen2-1.5B, our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication. Surprisingly, full-token GRPO under LoRA fails to improve over the base model, suggesting that selective token-level optimization may act as an implicit regularizer in low-parameter training regimes.
Authors: Tien Comlekoglu, J. Quetzalc\'oatl Toledo-Mar\'in, Tina Comlekoglu, Douglas W. DeSimone, Shayn M. Peirce, Geoffrey Fox, James A. Glazier
Abstract: The Cellular-Potts model is a powerful and ubiquitous framework for developing computational models for simulating complex multicellular biological systems. Cellular-Potts models (CPMs) are often computationally expensive due to the explicit modeling of interactions among large numbers of individual model agents and diffusive fields described by partial differential equations (PDEs). In this work, we develop a convolutional neural network (CNN) surrogate model using a U-Net architecture that accounts for periodic boundary conditions. We use this model to accelerate the evaluation of a mechanistic CPM previously used to investigate \textit{in vitro} vasculogenesis. The surrogate model was trained to predict 100 computational steps ahead (Monte-Carlo steps, MCS), accelerating simulation evaluations by a factor of 590 times compared to CPM code execution. Over multiple recursive evaluations, our model effectively captures the emergent behaviors demonstrated by the original Cellular-Potts model of such as vessel sprouting, extension and anastomosis, and contraction of vascular lacunae. This approach demonstrates the potential for deep learning to serve as efficient surrogate models for CPM simulations, enabling faster evaluation of computationally expensive CPM of biological processes at greater spatial and temporal scales.
Authors: Ke Jiang, Wen Jiang, Masahiro Fujisawa, Xiaoyang Tan
Abstract: The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose a novel method named Density-Aware Safety Perception (DASP) for OOD state correction. Specifically, our method encourages the agent to prioritize actions that lead to outcomes with higher data density, thereby promoting its operation within or the return to in-distribution (safe) regions. To achieve this, we optimize the objective within a variational framework that concurrently considers both the potential outcomes of decision-making and their density, thus providing crucial contextual information for safe decision-making. Finally, we validate the effectiveness and feasibility of our proposed method through extensive experimental evaluations on the offline MuJoCo and AntMaze suites.
Authors: Andrea Montanari, Kangjie Zhou
Abstract: Given a cloud of $n$ data points in $\mathbb{R}^d$, consider all projections onto $m$-dimensional subspaces of $\mathbb{R}^d$ and, for each such projection, the empirical distribution of the projected points. What does this collection of probability distributions look like when $n,d$ grow large? We consider this question under the null model in which the points are i.i.d. standard Gaussian vectors, focusing on the asymptotic regime in which $n,d\to\infty$, with $n/d\to\alpha\in (0,\infty)$, while $m$ is fixed. Denoting by $\mathscr{F}_{m, \alpha}$ the set of probability distributions in $\mathbb{R}^m$ that arise as low-dimensional projections in this limit, we establish new inner and outer bounds on $\mathscr{F}_{m, \alpha}$. In particular, we characterize the Wasserstein radius of $\mathscr{F}_{m,\alpha}$ up to constant multiplicative factors, and determine it exactly for $m=1$. We also prove sharp bounds in terms of Kullback-Leibler divergence and R\'{e}nyi information dimension. The previous question has application to unsupervised learning methods, such as projection pursuit and independent component analysis. We introduce a version of the same problem that is relevant for supervised learning, and prove a sharp Wasserstein radius bound. As an application, we establish an upper bound on the interpolation threshold of two-layers neural networks with $m$ hidden neurons.
Authors: Liviu Aolaritei, Soroosh Shafiee, Florian D\"orfler
Abstract: Distributionally robust optimization (DRO) has become a powerful framework for estimation under uncertainty, offering strong out-of-sample performance and principled regularization. In this paper, we propose a DRO-based method for linear regression and address a central question: how to optimally choose the robustness radius, which controls the trade-off between robustness and accuracy. Focusing on high-dimensional settings where the dimension and the number of samples are both large and comparable in size, we employ tools from high-dimensional asymptotic statistics to precisely characterize the estimation error of the resulting estimator. Remarkably, this error can be recovered by solving a simple convex-concave optimization problem involving only four scalar variables. This characterization enables efficient selection of the radius that minimizes the estimation error. In doing so, it achieves the same effect as cross-validation, but at a fraction of the computational cost. Numerical experiments confirm that our theoretical predictions closely match empirical performance and that the optimal radius selected through our method aligns with that chosen by cross-validation, highlighting both the accuracy and the practical benefits of our approach.
Authors: Jo\~ao Vitorino, Tiago Dias, Tiago Fonseca, Eva Maia, Isabel Pra\c{c}a
Abstract: It is imperative to safeguard computer applications and information systems against the growing number of cyber-attacks. Automated software testing tools can be developed to quickly analyze many lines of code and detect vulnerabilities by generating function-specific testing data. This process draws similarities to the constrained adversarial examples generated by adversarial machine learning methods, so there could be significant benefits to the integration of these methods in testing tools to identify possible attack vectors. Therefore, this literature review is focused on the current state-of-the-art of constrained data generation approaches applied for adversarial learning and software testing, aiming to guide researchers and developers to enhance their software testing tools with adversarial testing methods and improve the resilience and robustness of their information systems. The found approaches were systematized, and the advantages and limitations of those specific for white-box, grey-box, and black-box testing were analyzed, identifying research gaps and opportunities to automate the testing tools with data generated by adversarial attacks.
Authors: Ruihan Yang, Zhuoqun Chen, Jianhan Ma, Chongyi Zheng, Yiyu Chen, Quan Nguyen, Xiaolong Wang
Abstract: The agility of animals, particularly in complex activities such as running, turning, jumping, and backflipping, stands as an exemplar for robotic system design. Transferring this suite of behaviors to legged robotic systems introduces essential inquiries: How can a robot learn multiple locomotion behaviors simultaneously? How can the robot execute these tasks with a smooth transition? How to integrate these skills for wide-range applications? This paper introduces the Versatile Instructable Motion prior (VIM) - a Reinforcement Learning framework designed to incorporate a range of agile locomotion tasks suitable for advanced robotic applications. Our framework enables legged robots to learn diverse agile low-level skills by imitating animal motions and manually designed motions. Our Functionality reward guides the robot's ability to adopt varied skills, and our Stylization reward ensures that robot motions align with reference motions. Our evaluations of the VIM framework span both simulation and the real world. Our framework allows a robot to concurrently learn diverse agile locomotion skills using a single learning-based controller in the real world. Videos can be found on our website: https://rchalyang.github.io/VIM/
Authors: Chirag Wadhwa, Mina Doosti
Abstract: In this work, we initiate the study of learning quantum processes from quantum statistical queries. We focus on two fundamental learning tasks in this new access model: shadow tomography of quantum processes and process tomography with respect to diamond distance. For the former, we present an efficient average-case algorithm along with a nearly matching lower bound with respect to the number of observables to be predicted. For the latter, we present average-case query complexity lower bounds for learning classes of unitaries. We obtain an exponential lower bound for learning unitary 2-designs and a doubly exponential lower bound for Haar-random unitaries. Finally, we demonstrate the practical relevance of our access model by applying our learning algorithm to attack an authentication protocol using Classical-Readout Quantum Physically Unclonable Functions, partially addressing an important open question in quantum hardware security.
Authors: Jianqing Fan, Cheng Gao, Jason M. Klusowski
Abstract: This paper addresses challenges in robust transfer learning stemming from ambiguity in Bayes classifiers and weak transferable signals between the target and source distribution. We introduce a novel quantity called the ''ambiguity level'' that measures the discrepancy between the target and source regression functions, propose a simple transfer learning procedure, and establish a general theorem that shows how this new quantity is related to the transferability of learning in terms of risk improvements. Our proposed ''Transfer Around Boundary'' (TAB) model, with a threshold balancing the performance of target and source data, is shown to be both efficient and robust, improving classification while avoiding negative transfer. Moreover, we demonstrate the effectiveness of the TAB model on non-parametric classification and logistic regression tasks, achieving upper bounds which are optimal up to logarithmic factors. Simulation studies lend further support to the effectiveness of TAB. We also provide simple approaches to bound the excess misclassification error without the need for specialized knowledge in transfer learning.
Authors: Mengjia Niu, Xiaoyu He, Petr Ry\v{s}av\'y, Quan Zhou, Jakub Marecek
Abstract: Clustering of time series is a well-studied problem, with applications ranging from quantitative, personalized models of metabolism obtained from metabolite concentrations to state discrimination in quantum information theory. We consider a variant, where given a set of trajectories and a number of parts, we jointly partition the set of trajectories and learn linear dynamical system (LDS) models for each part, so as to minimize the maximum error across all the models. We present globally convergent methods and EM heuristics, accompanied by promising computational results. The key highlight of this method is that it does not require a predefined hidden state dimension but instead provides an upper bound. Additionally, it offers guidance for determining regularization in the system identification.
Authors: Kazuki Nakajima, Takeaki Uno
Abstract: Hypergraphs represent complex systems involving interactions among more than two entities and allow the investigation of higher-order structure and dynamics in complex systems. Node attribute data, which often accompanies network data, can enhance the inference of community structure in complex systems. While mixed-membership stochastic block models have been employed to infer community structure in hypergraphs, they complicate the visualization and interpretation of inferred community structure by assuming that nodes may possess soft community memberships. In this study, we propose a framework, HyperNEO, that combines mixed-membership stochastic block models for hypergraphs with dimensionality reduction methods. Our approach generates a node layout that largely preserves the community memberships of nodes. We evaluate our framework on both synthetic and empirical hypergraphs with node attributes. We expect our framework will broaden the investigation and understanding of higher-order community structure in complex systems.
Authors: David Bethge, Daniel Bulanda, Adam Kozlowski, Thomas Kosch, Albrecht Schmidt, Tobias Grosse-Puppendahl
Abstract: Routes represent an integral part of triggering emotions in drivers. Navigation systems allow users to choose a navigation strategy, such as the fastest or shortest route. However, they do not consider the driver's emotional well-being. We present HappyRouting, a novel navigation-based empathic car interface guiding drivers through real-world traffic while evoking positive emotions. We propose design considerations, derive a technical architecture, and implement a routing optimization framework. Our contribution is a machine learning-based generated emotion map layer, predicting emotions along routes based on static and dynamic contextual data. We evaluated HappyRouting in a real-world driving study (N=13), finding that happy routes increase subjectively perceived valence by 11% (p=.007). Although happy routes take 1.25 times longer on average, participants perceived the happy route as shorter, presenting an emotion-enhanced alternative to today's fastest routing mechanisms. We discuss how emotion-based routing can be integrated into navigation apps, promoting emotional well-being for mobility use.
Authors: Yiqi Zhao, Xinyi Yu, Matteo Sesia, Jyotirmoy V. Deshmukh, Lars Lindemann
Abstract: We propose conformal predictive programming (CPP), a framework to solve chance constrained optimization problems, i.e., optimization problems with constraints that are functions of random variables. CPP utilizes samples from these random variables along with the quantile lemma - central to conformal prediction - to transform the chance constrained optimization problem into a deterministic problem with a quantile reformulation. CPP inherits a priori guarantees on constraint satisfaction from existing sample average approximation approaches for a class of chance constrained optimization problems, and it provides a posteriori guarantees that are of conditional and marginal nature otherwise. The strength of CPP is that it can easily support different variants of conformal prediction which have been (or will be) proposed within the conformal prediction community. To illustrate this, we present robust CPP to deal with distribution shifts in the random variables and Mondrian CPP to deal with class conditional chance constraints. To enable tractable solutions to the quantile reformulation, we present a mixed integer programming method (CPP-MIP) encoding, a bilevel optimization strategy (CPP-Bilevel), and a sampling-and-discarding optimization strategy (CPP-Discarding). We also extend CPP to deal with joint chance constrained optimization (JCCO). In a series of case studies, we show the validity of the aforementioned approaches, empirically compare CPP-MIP, CPP-Bilevel, as well as CPP-Discarding, and illustrate the advantage of CPP as compared to scenario approach.
Authors: Jikai Jin, Vasilis Syrgkanis
Abstract: Average treatment effect estimation is the most central problem in causal inference with application to numerous disciplines. While many estimation strategies have been proposed in the literature, the statistical optimality of these methods has still remained an open area of investigation, especially in regimes where these methods do not achieve parametric rates. In this paper, we adopt the recently introduced structure-agnostic framework of statistical lower bounds, which poses no structural properties on the nuisance functions other than access to black-box estimators that achieve some statistical estimation rate. This framework is particularly appealing when one is only willing to consider estimation strategies that use non-parametric regression and classification oracles as black-box sub-processes. Within this framework, we prove the statistical optimality of the celebrated and widely used doubly robust estimators for both the Average Treatment Effect (ATE) and the Average Treatment Effect on the Treated (ATT), as well as weighted variants of the former, which arise in policy evaluation.
Authors: \"Umit Mert \c{C}a\u{g}lar, Baris Yilmaz, Melek T\"urkmen, Erdem Akag\"und\"uz, Salih Tileylioglu
Abstract: Contemporary deep learning models have demonstrated promising results across various applications within seismology and earthquake engineering. These models rely primarily on utilizing ground motion records for tasks such as earthquake event classification, localization, earthquake early warning systems, and structural health monitoring. However, the extent to which these models truly extract meaningful patterns from these complex time-series signals remains underexplored. In this study, our objective is to evaluate the degree to which auxiliary information, such as seismic phase arrival times or seismic station distribution within a network, dominates the process of deep learning from ground motion records, potentially hindering its effectiveness. Our experimental results reveal a strong dependence on the highly correlated Primary (P) and Secondary (S) phase arrival times. These findings expose a critical gap in the current research landscape, highlighting the lack of robust methodologies for deep learning from single-station ground motion recordings that do not rely on auxiliary inputs.
Authors: Xuanlei Zhao, Shenggan Cheng, Chang Chen, Zangwei Zheng, Ziming Liu, Zheming Yang, Yang You
Abstract: Scaling multi-dimensional transformers to long sequences is indispensable across various domains. However, the challenges of large memory requirements and slow speeds of such sequences necessitate sequence parallelism. All existing approaches fall under the category of embedded sequence parallelism, which are limited to shard along a single sequence dimension, thereby introducing significant communication overhead. However, the nature of multi-dimensional transformers involves independent calculations across multiple sequence dimensions. To this end, we propose Dynamic Sequence Parallelism (DSP) as a novel abstraction of sequence parallelism. DSP dynamically switches the parallel dimension among all sequences according to the computation stage with efficient resharding strategy. DSP offers significant reductions in communication costs, adaptability across modules, and ease of implementation with minimal constraints. Experimental evaluations demonstrate DSP's superiority over state-of-the-art embedded sequence parallelism methods by remarkable throughput improvements ranging from 32.2% to 10x, with less than 25% communication volume.
Authors: Benjamin Ellenberger, Paul Haider, Jakob Jordan, Kevin Max, Ismael Jaras, Laura Kriener, Federico Benitez, Mihai A. Petrovici
Abstract: How physical networks of neurons, bound by spatio-temporal locality constraints, can perform efficient credit assignment, remains, to a large extent, an open question. In machine learning, the answer is almost universally given by the error backpropagation algorithm, through both space and time. However, this algorithm is well-known to rely on biologically implausible assumptions, in particular with respect to spatio-temporal (non-)locality. Alternative forward-propagation models such as real-time recurrent learning only partially solve the locality problem, but only at the cost of scaling, due to prohibitive storage requirements. We introduce Generalized Latent Equilibrium (GLE), a computational framework for fully local spatio-temporal credit assignment in physical, dynamical networks of neurons. We start by defining an energy based on neuron-local mismatches, from which we derive both neuronal dynamics via stationarity and parameter dynamics via gradient descent. The resulting dynamics can be interpreted as a real-time, biologically plausible approximation of backpropagation through space and time in deep cortical networks with continuous-time neuronal dynamics and continuously active, local synaptic plasticity. In particular, GLE exploits the morphology of dendritic trees to enable more complex information storage and processing in single neurons, as well as the ability of biological neurons to phase-shift their output rate with respect to their membrane potential, which is essential in both directions of information propagation. For the forward computation, it enables the mapping of time-continuous inputs to neuronal space, effectively performing a spatio-temporal convolution. For the backward computation, it permits the temporal inversion of feedback signals, which consequently approximate the adjoint variables necessary for useful parameter updates.
Authors: Yupeng Cao, Zhi Chen, Prashant Kumar, Qingyun Pei, Yangyang Yu, Haohang Li, Fabrizio Dimino, Lorenzo Ausiello, K. P. Subbalakshmi, Papa Momar Ndiaye
Abstract: The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, existing studies predominantly focus on tasks like financial text summarization, question-answering, and stock movement prediction (binary classification), the application of LLMs to financial risk prediction remains underexplored. Addressing this gap, in this paper, we introduce RiskLabs, a novel framework that leverages LLMs to analyze and predict financial risks. RiskLabs uniquely integrates multimodal financial data, including textual and vocal information from Earnings Conference Calls (ECCs), market-related time series data, and contextual news data to improve financial risk prediction. Empirical results demonstrate RiskLabs' effectiveness in forecasting both market volatility and variance. Through comparative experiments, we examine the contributions of different data sources to financial risk assessment and highlight the crucial role of LLMs in this process. We also discuss the challenges associated with using LLMs for financial risk prediction and explore the potential of combining them with multimodal data for this purpose.
Authors: Jens Egholm Pedersen, J\"org Conradt, Tony Lindeberg
Abstract: Biological nervous systems constitute important sources of inspiration towards computers that are faster, cheaper, and more energy efficient. Neuromorphic disciplines view the brain as a coevolved system, simultaneously optimizing the hardware and the algorithms running on it. There are clear efficiency gains when bringing the computations into a physical substrate, but we presently lack theories to guide efficient implementations. Here, we present a principled computational model for neuromorphic systems in terms of spatio-temporal receptive fields, based on affine Gaussian kernels over space and leaky-integrator and leaky integrate-and-fire models over time. Our theory is provably covariant to spatial affine and temporal scaling transformations, and with close similarities to the visual processing in mammalian brains. We use these spatio-temporal receptive fields as a prior in an event-based vision task, and show that this improves the training of spiking networks, which otherwise is known as problematic for event-based vision. This work combines efforts within scale-space theory and computational neuroscience to identify theoretically well-founded ways to process spatio-temporal signals in neuromorphic systems. Our contributions are immediately relevant for signal processing and event-based vision, and can be extended to other processing tasks over space and time, such as memory and control.
Authors: Ravi B. Sojitra, Vasilis Syrgkanis
Abstract: We consider Dynamic Treatment Regimes (DTRs) with One Sided Noncompliance that arise in applications such as digital recommendations and adaptive medical trials. These are settings where decision makers encourage individuals to take treatments over time, but adapt encouragements based on previous encouragements, treatments, states, and outcomes. Importantly, individuals may not comply with encouragements based on unobserved confounders. For settings with binary treatments and encouragements, we provide nonparametric identification, estimation, and inference for Dynamic Local Average Treatment Effects (LATEs), which are expected values of multiple time period treatment effect contrasts for the respective complier subpopulations. Under One Sided Noncompliance and sequential extensions of the assumptions in Imbens and Angrist (1994), we show that one can identify Dynamic LATEs that correspond to treating at single time steps. In Staggered Adoption settings, we show that the assumptions are sufficient to identify Dynamic LATEs for treating in multiple time periods. Moreover, this result extends to any setting where the effect of a treatment in one period is uncorrelated with the compliance event in a subsequent period.
Authors: Andrea Montanari, Kangjie Zhou
Abstract: Given $d$-dimensional standard Gaussian vectors $\boldsymbol{x}_1,\dots, \boldsymbol{x}_n$, we consider the set of all empirical distributions of its $m$-dimensional projections, for $m$ a fixed constant. Diaconis and Freedman (1984) proved that, if $n/d\to \infty$, all such distributions converge to the standard Gaussian distribution. In contrast, we study the proportional asymptotics, whereby $n,d\to \infty$ with $n/d\to \alpha \in (0, \infty)$. In this case, the projection of the data points along a typical random subspace is again Gaussian, but the set $\mathscr{F}_{m,\alpha}$ of all probability distributions that are asymptotically feasible as $m$-dimensional projections contains non-Gaussian distributions corresponding to exceptional subspaces. Non-rigorous methods from statistical physics yield an indirect characterization of $\mathscr{F}_{m,\alpha}$ in terms of a generalized Parisi formula. Motivated by the goal of putting this formula on a rigorous basis, and to understand whether these projections can be found efficiently, we study the subset $\mathscr{F}^{\rm alg}_{m,\alpha}\subseteq \mathscr{F}_{m,\alpha}$ of distributions that can be realized by a class of iterative algorithms. We prove that this set is characterized by a certain stochastic optimal control problem, and obtain a dual characterization of this problem in terms of a variational principle that extends Parisi's formula. As a byproduct, we obtain computationally achievable values for a class of random optimization problems including `generalized spherical perceptron' models.
Authors: Rohit Jena, Pratik Chaudhari, James C. Gee
Abstract: Deep Learning in Image Registration (DLIR) methods have been tremendously successful in image registration due to their speed and ability to incorporate weak label supervision at training time. However, existing DLIR methods forego many of the benefits and invariances of optimization methods. The lack of a task-specific inductive bias in DLIR methods leads to suboptimal performance, especially in the presence of domain shift. Our method aims to bridge this gap between statistical learning and optimization by explicitly incorporating optimization as a layer in a deep network. A deep network is trained to predict multi-scale dense feature images that are registered using a black box iterative optimization solver. This optimal warp is then used to minimize image and label alignment errors. By implicitly differentiating end-to-end through an iterative optimization solver, we explicitly exploit invariances of the correspondence matching problem induced by the optimization, while learning registration and label-aware features, and guaranteeing the warp functions to be a local minima of the registration objective in the feature space. Our framework shows excellent performance on in-domain datasets, and is agnostic to domain shift such as anisotropy and varying intensity profiles. For the first time, our method allows switching between arbitrary transformation representations (free-form to diffeomorphic) at test time with zero retraining. End-to-end feature learning also facilitates interpretability of features and arbitrary test-time regularization, which is not possible with existing DLIR methods.
Authors: Georgios Kaissis, Stefan Kolek, Borja Balle, Jamie Hayes, Daniel Rueckert
Abstract: In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single $(\varepsilon, \delta)$-pair. This practice overlooks that DP guarantees can vary substantially even between mechanisms sharing a given $(\varepsilon, \delta)$, and potentially introduces privacy vulnerabilities which can remain undetected. This motivates the need for robust, rigorous methods for comparing DP guarantees in such cases. Here, we introduce the $\Delta$-divergence between mechanisms which quantifies the worst-case excess privacy vulnerability of choosing one mechanism over another in terms of $(\varepsilon, \delta)$, $f$-DP and in terms of a newly presented Bayesian interpretation. Moreover, as a generalisation of the Blackwell theorem, it is endowed with strong decision-theoretic foundations. Through application examples, we show that our techniques can facilitate informed decision-making and reveal gaps in the current understanding of privacy risks, as current practices in DP-SGD often result in choosing mechanisms with high excess privacy vulnerabilities.
Authors: Giorgio Severi, Simona Boboila, John Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Michael J. De Lucia, Alina Oprea
Abstract: The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification tasks without altering the training labels. With this work, we propose new techniques that leverage insights in cybersecurity threat models to effectively mitigate these clean-label poisoning attacks, while preserving the model utility. By performing density-based clustering on a carefully chosen feature subspace, and progressively isolating the suspicious clusters through a novel iterative scoring procedure, our defensive mechanism can mitigate the attacks without requiring many of the common assumptions in the existing backdoor defense literature. To show the generality of our proposed mitigation, we evaluate it on two clean-label model-agnostic attacks on two different classic cybersecurity data modalities: network flows classification and malware classification, using gradient boosting and neural network models.
Authors: Daniel Ward, Mark Beaumont, Matteo Fasiolo
Abstract: Estimating a distribution given access to its unnormalized density is pivotal in Bayesian inference, where the posterior is generally known only up to an unknown normalizing constant. Variational inference and Markov chain Monte Carlo methods are the predominant tools for this task; however, both are often challenging to apply reliably, particularly when the posterior has complex geometry. Here, we introduce Soft Contrastive Variational Inference (SoftCVI), which allows a family of variational objectives to be derived through a contrastive estimation framework. The approach parameterizes a classifier in terms of a variational distribution, reframing the inference task as a contrastive estimation problem aiming to identify a single true posterior sample among a set of samples. Despite this framing, we do not require positive or negative samples, but rather learn by sampling the variational distribution and computing ground truth soft classification labels from the unnormalized posterior itself. The objectives have zero variance gradient when the variational approximation is exact, without the need for specialized gradient estimators. We empirically investigate the performance on a variety of Bayesian inference tasks, using both simple (e.g. normal) and expressive (normalizing flow) variational distributions. We find that SoftCVI can be used to form objectives which are stable to train and mass-covering, frequently outperforming inference with other variational approaches.
Authors: Luca Mouchel, Debjit Paul, Shaobo Cui, Robert West, Antoine Bosselut, Boi Faltings
Abstract: Despite the remarkable performance of Large Language Models (LLMs) in natural language processing tasks, they still struggle with generating logically sound arguments, resulting in potential risks such as spreading misinformation. To address this issue, we introduce FIPO, a fallacy-informed framework that leverages preference optimization methods to steer LLMs toward logically sound arguments. FIPO includes a classification loss, to capture the fine-grained information on fallacy types. Our results on argumentation datasets show that our method reduces the fallacy errors by up to 17.5%. Furthermore, our human evaluation results indicate that the quality of the generated arguments by our method significantly outperforms the fine-tuned baselines, as well as other preference optimization methods, such as DPO. These findings highlight the importance of ensuring models are aware of logical fallacies for effective argument generation. Our code is available at github.com/lucamouchel/Logical-Fallacies.
Authors: Makoto Takamoto, Viktor Zaverkin, Mathias Niepert
Abstract: Machine learning plays an increasingly important role in computational chemistry and materials science, complementing computationally intensive ab initio and first-principles methods. Despite their utility, machine-learning models often lack generalization capability and robustness during atomistic simulations, yielding unphysical energy and force predictions that hinder their real-world applications. We address this challenge by introducing a physics-informed, weakly supervised approach for training machine-learned interatomic potentials (MLIPs). We introduce two novel loss functions, extrapolating the potential energy via a Taylor expansion and using the concept of conservative forces. Our approach improves the accuracy of MLIPs applied to training tasks with sparse training data sets and reduces the need for pre-training computationally demanding models with large data sets. Particularly, we perform extensive experiments demonstrating reduced energy and force errors -- often lower by a factor of two -- for various baseline models and benchmark data sets. Moreover, we demonstrate improved robustness during MD simulations of the MLIP models trained with the proposed weakly supervised loss. Finally, our approach improves the fine-tuning of foundation models on sparse, highly accurate ab initio data. An implementation of our method and scripts for executing experiments are available at https://github.com/nec-research/PICPS-ML4Sci.
Authors: Ali Maatouk, Kenny Chirino Ampudia, Rex Ying, Leandros Tassiulas
Abstract: The emergence of large language models (LLMs) has significantly impacted various fields, from natural language processing to sectors like medicine and finance. However, despite their rapid proliferation, the applications of LLMs in telecommunications remain limited, often relying on general-purpose models that lack domain-specific specialization. This lack of specialization results in underperformance, particularly when dealing with telecommunications-specific technical terminology and their associated mathematical representations. This paper addresses this gap by first creating and disseminating Tele-Data, a comprehensive dataset of telecommunications material curated from relevant sources, and Tele-Eval, a large-scale question-and-answer dataset tailored to the domain. Through extensive experiments, we explore the most effective training techniques for adapting LLMs to the telecommunications domain, ranging from examining the division of expertise across various telecommunications aspects to employing parameter-efficient techniques. We also investigate how models of different sizes behave during adaptation and analyze the impact of their training data on this behavior. Leveraging these findings, we develop and open-source Tele-LLMs, the first series of language models ranging from 1B to 8B parameters, specifically tailored for telecommunications. Our evaluations demonstrate that these models outperform their general-purpose counterparts on Tele-Eval and telecommunications-related literature tasks while retaining their previously acquired capabilities, thus avoiding the catastrophic forgetting phenomenon.
Authors: Yubo Li, Rema Padman
Abstract: Objective: To improve prediction of Chronic Kidney Disease (CKD) progression to End Stage Renal Disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to an integrated clinical and claims dataset of varying observation windows, supported by explainable AI (XAI) to enhance interpretability and reduce bias. Materials and Methods: We utilized data about 10,326 CKD patients, combining their clinical and claims information from 2009 to 2018. Following data preprocessing, cohort identification, and feature engineering, we evaluated multiple statistical, ML and DL models using data extracted from five distinct observation windows. Feature importance and Shapley value analysis were employed to understand key predictors. Models were tested for robustness, clinical relevance, misclassification errors and bias issues. Results: Integrated data models outperformed those using single data sources, with the Long Short-Term Memory (LSTM) model achieving the highest AUC (0.93) and F1 score (0.65). A 24-month observation window was identified as optimal for balancing early detection and prediction accuracy. The 2021 eGFR equation improved prediction accuracy and reduced racial bias, notably for African American patients. Discussion: Improved ESRD prediction accuracy, results interpretability and bias mitigation strategies presented in this study have the potential to significantly enhance CKD and ESRD management, support targeted early interventions and reduce healthcare disparities. Conclusion: This study presents a robust framework for predicting ESRD outcomes in CKD patients, improving clinical decision-making and patient care through multi-sourced, integrated data and AI/ML methods. Future research will expand data integration and explore the application of this framework to other chronic diseases.
Authors: Antony R. Lee, Peter Tino, Iain Bruce Styles
Abstract: Motivated by information geometry, a distance function on the space of stochastic matrices is advocated. Starting with sequences of Markov chains the Bhattacharyya angle is advocated as the natural tool for comparing both short and long term Markov chain runs. Bounds on the convergence of the distance and mixing times are derived. Guided by the desire to compare different Markov chain models, especially in the setting of healthcare processes, a new distance function on the space of stochastic matrices is presented. It is a true distance measure which has a closed form and is efficient to implement for numerical evaluation. In the case of ergodic Markov chains, it is shown that considering either the Bhattacharyya angle on Markov sequences or the new stochastic matrix distance leads to the same distance between models.
Authors: Florian H\"ubler, Ilyas Fatkhullin, Niao He
Abstract: Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in stochastic optimization. Gradient clipping has emerged as a popular tool to handle this heavy-tailed noise, as it achieves good performance in this setting both theoretically and practically. However, our current theoretical understanding of non-convex gradient clipping has three main shortcomings. First, the theory hinges on large, increasing clipping thresholds, which are in stark contrast to the small constant clipping thresholds employed in practice. Second, clipping thresholds require knowledge of problem-dependent parameters to guarantee convergence. Lastly, even with this knowledge, current sampling complexity upper bounds for the method are sub-optimal in nearly all parameters. To address these issues, we study convergence of Normalized SGD (NSGD). First, we establish a parameter-free sample complexity for NSGD of $\mathcal{O}\left(\varepsilon^{-\frac{2p}{p-1}}\right)$ to find an $\varepsilon$-stationary point. Furthermore, we prove tightness of this result, by providing a matching algorithm-specific lower bound. In the setting where all problem parameters are known, we show this complexity is improved to $\mathcal{O}\left(\varepsilon^{-\frac{3p-2}{p-1}}\right)$, matching the previously known lower bound for all first-order methods in all problem dependent parameters. Finally, we establish high-probability convergence of NSGD with a mild logarithmic dependence on the failure probability. Our work complements the studies of gradient clipping under heavy tailed noise improving the sample complexities of existing algorithms and offering an alternative mechanism to achieve high probability convergence.
Authors: Marco Hening Tallarico, Pablo Olivares
Abstract: This paper studies pricing of weather-derivative (WD) contracts on temperature and precipitation. For temperature-linked strangles in Toronto and Chicago, we benchmark a harmonic-regression/ARMA model against a feed-forward neural network (NN), finding that the NN reduces out-of-sample mean-squared error (MSE) and materially shifts December fair values relative to both the time-series model and the industry-standard Historic Burn Approach (HBA). For precipitation, we employ a compound Poisson--Gamma framework: shape and scale parameters are estimated via maximum likelihood estimation (MLE) and via a convolutional neural network (CNN) trained on 30-day rainfall sequences spanning multiple seasons. The CNN adaptively learns season-specific $(\alpha,\beta)$ mappings, thereby capturing heterogeneity across regimes that static i.i.d.\ fits miss. At valuation, we assume days are i.i.d.\ $\Gamma(\hat{\alpha},\hat{\beta})$ within each regime and apply a mean-count approximation (replacing the Poisson count by its mean ($n\hat{\lambda}$) to derive closed-form strangle prices. Exploratory analysis of 1981--2023 NASA POWER data confirms pronounced seasonal heterogeneity in $(\alpha,\beta)$ between summer and winter, demonstrating that static global fits are inadequate. Back-testing on Toronto and Chicago grids shows that our regime-adaptive CNN yields competitive valuations and underscores how model choice can shift strangle prices. Payoffs are evaluated analytically when possible and by simulation elsewhere, enabling a like-for-like comparison of forecasting and valuation methods.
Authors: Giovanni Barbarino, Nicolas Gillis
Abstract: The successive projection algorithm (SPA) is a workhorse algorithm to learn the $r$ vertices of the convex hull of a set of $(r-1)$-dimensional data points, a.k.a. a latent simplex, which has numerous applications in data science. In this paper, we revisit the robustness to noise of SPA and several of its variants. In particular, when $r \geq 3$, we prove the tightness of the existing error bounds for SPA and for two more robust preconditioned variants of SPA. We also provide significantly improved error bounds for SPA, by a factor proportional to the conditioning of the $r$ vertices, in two special cases: for the first extracted vertex, and when $r \leq 2$. We then provide further improvements for the error bounds of a translated version of SPA proposed by Arora et al. (''A practical algorithm for topic modeling with provable guarantees'', ICML, 2013) in two special cases: for the first two extracted vertices, and when $r \leq 3$. Finally, we propose a new more robust variant of SPA that first shifts and lifts the data points in order to minimize the conditioning of the problem. We illustrate our results on synthetic data.
Authors: Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem, Talfan Evans, Samuel Albanie, Federico Tombari, Yongqin Xian, Alessio Tonioni, Olivier J. H\'enaff
Abstract: Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fact be complementary to standard KD, and can be effectively combined to train highly performant inference-efficient models. Our simple and scalable pretraining framework, ACED, achieves state-of-the-art results across 27 zero-shot classification and retrieval tasks with upto 11% less inference FLOPs. We further demonstrate that our ACED models yield strong vision-encoders for training generative multimodal models in the LiT-Decoder setting, outperforming larger vision encoders for image-captioning and visual question-answering tasks.
Authors: Xixi Hu, Keyang Xu, Bo Liu, Qiang Liu, Hongliang Fei
Abstract: Achieving precise alignment between textual instructions and generated images in text-to-image generation is a significant challenge, particularly in rendering written text within images. Sate-of-the-art models like Stable Diffusion 3 (SD3), Flux, and AuraFlow still struggle with accurate text depiction, resulting in misspelled or inconsistent text. We introduce a training-free method with minimal computational overhead that significantly enhances text rendering quality. Specifically, we introduce an overshooting sampler for pretrained rectified flow (RF) models, by alternating between over-simulating the learned ordinary differential equation (ODE) and reintroducing noise. Compared to the Euler sampler, the overshooting sampler effectively introduces an extra Langevin dynamics term that can help correct the compounding error from successive Euler steps and therefore improve the text rendering. However, when the overshooting strength is high, we observe over-smoothing artifacts on the generated images. To address this issue, we propose an Attention Modulated Overshooting sampler (AMO), which adaptively controls the strength of overshooting for each image patch according to their attention score with the text content. AMO demonstrates a 32.3% and 35.9% improvement in text rendering accuracy on SD3 and Flux without compromising overall image quality or increasing inference cost. Code available at: https://github.com/hxixixh/amo-release.
Authors: Andrea Bulgarelli, Elia Cellini, Alessandro Nada
Abstract: Non-equilibrium Markov Chain Monte Carlo (NE-MCMC) simulations provide a well-understood framework based on Jarzynski's equality to sample from a target probability distribution. By driving a base probability distribution out of equilibrium, observables are computed without the need to thermalize. If the base distribution is characterized by mild autocorrelations, this approach provides a way to mitigate critical slowing down. Out-of-equilibrium evolutions share the same framework of flow-based approaches and they can be naturally combined into a novel architecture called Stochastic Normalizing Flows (SNFs). In this work we present the first implementation of SNFs for $\mathrm{SU}(3)$ lattice gauge theory in 4 dimensions, defined by introducing gauge-equivariant layers between out-of-equilibrium Monte Carlo updates. The core of our analysis is focused on the promising scaling properties of this architecture with the degrees of freedom of the system, which are directly inherited from NE-MCMC. Finally, we discuss how systematic improvements of this approach can realistically lead to a general and yet efficient sampling strategy at fine lattice spacings for observables affected by long autocorrelation times.
Authors: Shing-Hei Ho, Bao Thach, Minghan Zhu
Abstract: We present LiDAR-EDIT, a novel paradigm for generating synthetic LiDAR data for autonomous driving. Our framework edits real-world LiDAR scans by introducing new object layouts while preserving the realism of the background environment. Compared to end-to-end frameworks that generate LiDAR point clouds from scratch, LiDAR-EDIT offers users full control over the object layout, including the number, type, and pose of objects, while keeping most of the original real-world background. Our method also provides object labels for the generated data. Compared to novel view synthesis techniques, our framework allows for the creation of counterfactual scenarios with object layouts significantly different from the original real-world scene. LiDAR-EDIT uses spherical voxelization to enforce correct LiDAR projective geometry in the generated point clouds by construction. During object removal and insertion, generative models are employed to fill the unseen background and object parts that were occluded in the original real LiDAR scans. Experimental results demonstrate that our framework produces realistic LiDAR scans with practical value for downstream tasks.
Authors: Erik Burman, Mats G. Larson, Karl Larsson, Carl Lundholm
Abstract: We consider an inverse problem involving the reconstruction of the solution to a nonlinear partial differential equation (PDE) with unknown boundary conditions. Instead of direct boundary data, we are provided with a large dataset of boundary observations for typical solutions (collective data) and a bulk measurement of a specific realization. To leverage this collective data, we first compress the boundary data using proper orthogonal decomposition (POD) in a linear expansion. Next, we identify a possible nonlinear low-dimensional structure in the expansion coefficients using an autoencoder, which provides a parametrization of the dataset in a lower-dimensional latent space. We then train an operator network to map the expansion coefficients representing the boundary data to the finite element (FE) solution of the PDE. Finally, we connect the autoencoder's decoder to the operator network which enables us to solve the inverse problem by optimizing a data-fitting term over the latent space. We analyze the underlying stabilized finite element method (FEM) in the linear setting and establish an optimal error estimate in the $H^1$-norm. The nonlinear problem is then studied numerically, demonstrating the effectiveness of our approach.
Authors: Ruihuai Liang, Bo Yang, Pengyu Chen, Xuelin Cao, Zhiwen Yu, M\'erouane Debbah, Dusit Niyato, H. Vincent Poor, Chau Yuen
Abstract: Optimization is crucial for MEC networks to function efficiently and reliably, most of which are NP-hard and lack efficient approximation algorithms. This leads to a paucity of optimal solution, constraining the effectiveness of conventional deep learning approaches. Most existing learning-based methods necessitate extensive optimal data and fail to exploit the potential benefits of suboptimal data that can be obtained with greater efficiency and effectiveness. Taking the multi-server multi-user computation offloading (MSCO) problem, which is widely observed in systems like Internet-of-Vehicles (IoV) and Unmanned Aerial Vehicle (UAV) networks, as a concrete scenario, we present a Graph Diffusion-based Solution Generation (GDSG) method. This approach is designed to work with suboptimal datasets while converging to the optimal solution large probably. We transform the optimization issue into distribution-learning and offer a clear explanation of learning from suboptimal training datasets. We build GDSG as a multi-task diffusion model utilizing a Graph Neural Network (GNN) to acquire the distribution of high-quality solutions. We use a simple and efficient heuristic approach to obtain a sufficient amount of training data composed entirely of suboptimal solutions. In our implementation, we enhance the backbone GNN and achieve improved generalization. GDSG also reaches nearly 100\% task orthogonality, ensuring no interference between the discrete and continuous generation tasks. We further reveal that this orthogonality arises from the diffusion-related training loss, rather than the neural network architecture itself. The experiments demonstrate that GDSG surpasses other benchmark methods on both the optimal and suboptimal training datasets. The MSCO datasets has open-sourced at this http URL, as well as the GDSG algorithm codes at https://github.com/qiyu3816/GDSG.
Authors: Riccardo Fosco Gramaccioni, Christian Marinoni, Emilian Postolache, Marco Comunit\`a, Luca Cosmo, Joshua D. Reiss, Danilo Comminiello
Abstract: Traditional sound design workflows rely on manual alignment of audio events to visual cues, as in Foley sound design, where everyday actions like footsteps or object interactions are recreated to match the on-screen motion. This process is time-consuming, difficult to scale, and lacks automation tools that preserve creative intent. Despite recent advances in vision-to-audio generation, producing temporally coherent and semantically controllable sound effects from video remains a major challenge. To address these limitations, we introduce FolAI, a two-stage generative framework that decouples the when and the what of sound synthesis, i.e., the temporal structure extraction and the semantically guided generation, respectively. In the first stage, we estimate a smooth control signal from the video that captures the motion intensity and rhythmic structure over time, serving as a temporal scaffold for the audio. In the second stage, a diffusion-based generative model produces sound effects conditioned both on this temporal envelope and on high-level semantic embeddings, provided by the user, that define the desired auditory content (e.g., material or action type). This modular design enables precise control over both timing and timbre, streamlining repetitive tasks while preserving creative flexibility in professional Foley workflows. Results on diverse visual contexts, such as footstep generation and action-specific sonorization, demonstrate that our model reliably produces audio that is temporally aligned with visual motion, semantically consistent with user intent, and perceptually realistic. These findings highlight the potential of FolAI as a controllable and modular solution for scalable, high-quality Foley sound synthesis in professional and interactive settings. Supplementary materials are accessible on our dedicated demo page at https://ispamm.github.io/FolAI.
Authors: Antoine Boutet, Lucas Magnana, Juliette S\'en\'echal, Helain Zimmermann
Abstract: Rapid advances in Natural Language Processing (NLP) have revolutionized many fields, including healthcare. However, these advances raise significant privacy concerns, especially when pre-trained models fine-tuned and specialized on sensitive data can memorize and then expose and regurgitate personal information. This paper presents a privacy-preserving language modeling approach to address the problem of language models anonymization, and thus promote their sharing. Specifically, we propose both a Masking Language Modeling (MLM) methodology to specialize a BERT-like language model, and a Causal Language Modeling (CLM) methodology to specialize a GPT-like model that avoids the model from memorizing direct and indirect identifying information present in the training data. We have comprehensively evaluated our approaches using a medical dataset and compared them against different baselines. Our results indicate that by avoiding memorizing both direct and indirect identifiers during model specialization, our masking and causal language modeling schemes offer a good tradeoff for maintaining high privacy while retaining high utility.
Authors: Nolan P Shaw, P Michael Furlong, Britt Anderson, Jeff Orchard
Abstract: Connectionist approaches to machine learning, \emph{i.e.} neural networks, are enjoying a considerable vogue right now. However, these methods require large volumes of data and produce models that are uninterpretable to humans. An alternative framework that is compatible with neural networks and gradient-based learning, but explicitly models compositionality, is Vector Symbolic Architectures (VSAs). VSAs are a family of algebras on high-dimensional vector representations. They arose in cognitive science from the need to unify neural processing and the kind of symbolic reasoning that humans perform. While machine learning methods have benefited from category-theoretical analyses, VSAs have not yet received similar treatment. In this paper, we present a first attempt at applying category theory to VSAs. Specifically, We generalise from vectors to co-presheaves, and describe VSA operations as the right Kan extensions of the external tensor product. This formalisation involves a proof that the right Kan extension in such cases can be expressed as simple, element-wise operations. We validate our formalisation with worked examples that connect to current VSA implementations, while suggesting new possible designs for VSAs.
Authors: Jef Jonkers, Luc Duchateau, Glenn Van Wallendael, Sofie Van Hoecke
Abstract: Anatomical landmark localization in 2D/3D images is a critical task in medical imaging. Although many general-purpose tools exist for landmark localization in classical computer vision tasks, such as pose estimation, they lack the specialized features and modularity necessary for anatomical landmark localization applications in the medical domain. Therefore, we introduce landmarker, a Python package built on PyTorch. The package provides a comprehensive, flexible toolkit for developing and evaluating landmark localization algorithms, supporting a range of methodologies, including static and adaptive heatmap regression. landmarker enhances the accuracy of landmark identification, streamlines research and development processes, and supports various image formats and preprocessing pipelines. Its modular design allows users to customize and extend the toolkit for specific datasets and applications, accelerating innovation in medical imaging. landmarker addresses a critical need for precision and customization in landmark localization tasks not adequately met by existing general-purpose pose estimation tools.
Authors: Yujie Zhang, Shivam Aggarwal, Tulika Mitra
Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means not all experts can be stored on the GPU simultaneously, necessitating frequent, costly data transfers from CPU memory, often negating GPU speed advantages. To address this, we present DAOP, an on-device MoE inference engine to optimize parallel GPU-CPU execution. DAOP dynamically allocates experts between CPU and GPU based on per-sequence activation patterns, and selectively pre-calculates predicted experts on CPUs to minimize transfer latency. This approach enables efficient resource utilization across various expert cache ratios while maintaining model accuracy through a novel graceful degradation mechanism. Comprehensive evaluations across various datasets show that DAOP outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.
Authors: Shahaf Pruss, Morris Alper, Hadar Averbuch-Elor
Abstract: Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current approaches use distinct methods tailored to sub-tasks such as Situation Recognition and detection of Human-Human and Human-Object Interactions. However, recent advances in image understanding have often leveraged web-scale vision-language (V&L) representations to obviate task-specific engineering. In this work, we propose a framework for dynamic scene understanding tasks by leveraging knowledge from modern, frozen V&L representations. By framing these tasks in a generic manner - as predicting and parsing structured text, or by directly concatenating representations to the input of existing models - we achieve state-of-the-art results while using a minimal number of trainable parameters relative to existing approaches. Moreover, our analysis of dynamic knowledge of these representations shows that recent, more powerful representations effectively encode dynamic scene semantics, making this approach newly possible.
Authors: Tomasz Gradowski, Teodor Buchner
Abstract: This study introduces a deep learning model based on the U-net architecture to reconstruct missing leads in electrocardiograms (ECGs). The model was trained to reconstruct 12-lead ECG data from reduced lead configurations using publicly available datasets. The results highlight the ability of the model to quantify the information content of each ECG lead and its inter-lead correlations. This has significant implications for optimizing lead selection in diagnostic scenarios, particularly in settings where complete 12-lead ECGs are impractical. In addition, the study provides insights into the physiological underpinnings of ECG signals and their propagation. The findings pave the way for advances in telemedicine, portable ECG devices, and personalized cardiac diagnostics by reducing redundancy and improving signal interpretation.
Authors: Anuj Singh, Sayak Mukherjee, Ahmad Beirami, Hadi Jamali-Rad
Abstract: Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior. In this work, we explore a simple inference-time gradient-free guidance approach, called controlled denoising (CoDe), that circumvents the need for differentiable guidance functions and model finetuning. CoDe is a blockwise sampling method applied during intermediate denoising steps, allowing for alignment with downstream rewards. Our experiments demonstrate that, despite its simplicity, CoDe offers a favorable trade-off between reward alignment, prompt instruction following, and inference cost, achieving a competitive performance against the state-of-the-art baselines. Our code is available at: https://github.com/anujinho/code.
Authors: Floris Holstege, Mackenzie Jorgensen, Kirtan Padh, Jurriaan Parie, Joel Persson, Krsto Prorokovic, Lukas Snoek
Abstract: Algorithms are increasingly used to automate or aid human decisions, yet recent research shows that these algorithms may exhibit bias across legally protected demographic groups. However, data on these groups may be unavailable to organizations or external auditors due to privacy legislation. This paper studies bias detection using an unsupervised clustering tool when data on demographic groups are unavailable. We collaborate with the Dutch Executive Agency for Education to audit an algorithm that was used to assign risk scores to college students at the national level in the Netherlands between 2012-2023. Our audit covers more than 250,000 students from the whole country. The unsupervised clustering tool highlights known disparities between students with a non-European migration background and Dutch origin. Our contributions are three-fold: (1) we assess bias in a real-world, large-scale and high-stakes decision-making process by a governmental organization; (2) we use simulation studies to highlight potential pitfalls of using the unsupervised clustering tool to detect true bias when demographic group data are unavailable and provide recommendations for valid inferences; (3) we provide the unsupervised clustering tool in an open-source library. Our work serves as a starting point for a deliberative assessment by human experts to evaluate potential discrimination in algorithmic-supported decision-making processes.
Authors: Zhimin Zhao
Abstract: Foundation models (FMs), particularly large language models (LLMs), have shown significant promise in various software engineering (SE) tasks, including code generation, debugging, and requirement refinement. Despite these advances, existing evaluation frameworks are insufficient for assessing model performance in iterative, context-rich workflows characteristic of SE activities. To address this limitation, we introduce SE Arena, an interactive platform designed to evaluate FMs in SE tasks. SE Arena provides a transparent, open-source leaderboard, supports multi-round conversational workflows, and enables end-to-end model comparisons. The platform introduces novel metrics, including model consistency score that measures the consistency of model outputs through self-play matches, and conversation efficiency index that evaluates model performance while accounting for the number of interaction rounds required to reach conclusions. Moreover, SE Arena incorporates a new feature called RepoChat, which automatically injects repository-related context (e.g., issues, commits, pull requests) into the conversation, further aligning evaluations with real-world development processes. This paper outlines the design and capabilities of SE Arena, emphasizing its potential to advance the evaluation and practical application of FMs in software engineering.
Authors: Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier, Sethu Vijayakumar, Chris Xiaoxuan Lu, Oisin Mac Aodha
Abstract: The integration of pre-trained visual representations (PVRs) into visuo-motor robot learning has emerged as a promising alternative to training visual encoders from scratch. However, PVRs face critical challenges in the context of policy learning, including temporal entanglement and an inability to generalise even in the presence of minor scene perturbations. These limitations hinder performance in tasks requiring temporal awareness and robustness to scene changes. This work identifies these shortcomings and proposes solutions to address them. First, we augment PVR features with temporal perception and a sense of task completion, effectively disentangling them in time. Second, we introduce a module that learns to selectively attend to task-relevant local features, enhancing robustness when evaluated on out-of-distribution scenes. Our experiments demonstrate significant performance improvements, particularly in PVRs trained with masking objectives, and validate the effectiveness of our enhancements in addressing PVR-specific limitations.
Authors: Abdullahi Isa Ahmed, Jamal Bentahar, El Mehdi Amhoud
Abstract: As next-generation Internet of Things (NG-IoT) networks continue to grow, the number of connected devices is rapidly increasing, along with their energy demands. This creates challenges for resource management and sustainability. Energy-efficient communication, particularly for power-limited IoT devices, is therefore a key research focus. In this paper, we deployed flying LoRa gateways mounted on unmanned aerial vehicles (UAVs) to collect data from LoRa end devices and transmit it to a central server. Our primary objective is to maximize the global system energy efficiency of wireless LoRa networks by joint optimization of transmission power, spreading factor, bandwidth, and user association. To solve this challenging problem, we model the problem as a partially observable Markov decision process (POMDP), where each flying LoRa GW acts as a learning agent using a cooperative multi-agent reinforcement learning (MARL). Simulation results demonstrate that our proposed method, based on the multi-agent proximal policy optimization algorithm, significantly improves the global system energy efficiency and surpasses the popular MARL and other conventional schemes.
Authors: Ibrahim Alabdulmohsin, Xiaohua Zhai
Abstract: Inspired by recent findings on the fractal geometry of language, we introduce Recursive INference Scaling (RINS) as a complementary, plug-in recipe for scaling inference time in language and multimodal systems. RINS is a particular form of recursive depth that significantly outperforms +55 other variants, including the recent "repeat-all-over" (RAO) strategy in Mobile LLM (Liu et al., 2024) and latent recurrent thinking (Geiping et al., 2025). Unlike prior works, we carry out our comparisons on a compute-matched regime, and demonstrate that for a fixed model size and training compute budget, RINS substantially improves language modeling performance. It also generalizes beyond pure language tasks, delivering gains in multimodal systems, including a +2% improvement in 0-shot ImageNet accuracy for SigLIP-B/16. Additionally, by deriving data scaling laws, we show that RINS improves both the asymptotic performance limits and the scaling exponents. More importantly, with light-weight (linear) adapters (comprising <1% of model parameters) and stochastic dropout, RINS offers a no-regret strategy, meaning that RINS-enabled pretraining improves performance in language modeling even when recursive depth is not applied at inference time. This corresponds to improving performance on a training compute-, parameter-, and inference-matched regime, suggesting its potential as a viable component of LLM pretraining!
Authors: Anjian Li, Sangjae Bae, David Isele, Ryne Beeson, Faizan M. Tariq
Abstract: Trajectory prediction and planning are essential for autonomous vehicles to navigate safely and efficiently in dynamic environments. Traditional approaches often treat them separately, limiting the ability for interactive planning. While recent diffusion-based generative models have shown promise in multi-agent trajectory generation, their slow sampling is less suitable for high-frequency planning tasks. In this paper, we leverage the consistency model to build a predictive planner that samples from a joint distribution of ego and surrounding agents, conditioned on the ego vehicle's navigational goal. Trained on real-world human driving datasets, our consistency model generates higher-quality trajectories with fewer sampling steps than standard diffusion models, making it more suitable for real-time deployment. To enforce multiple planning constraints simultaneously on the ego trajectory, a novel online guided sampling approach inspired by the Alternating Direction Method of Multipliers (ADMM) is introduced. Evaluated on the Waymo Open Motion Dataset (WOMD), our method enables proactive behavior such as nudging and yielding, and also demonstrates smoother, safer, and more efficient trajectories and satisfaction of multiple constraints under a limited computational budget.
Authors: Debangshu Banerjee, Tarun Suresh, Shubham Ugare, Sasa Misailovic, Gagandeep Singh
Abstract: Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a promising direction to enforce adherence to formal grammar, but prior works have empirically observed that strict enforcement of formal constraints often diminishes the reasoning capabilities of LLMs. In this work, we first provide a theoretical explanation for why constraining LLM outputs to very restrictive grammars that only allow syntactically valid final answers reduces the reasoning capabilities of the model. Second, we demonstrate that by augmenting the output grammar with carefully designed additional rules, it is always possible to preserve the reasoning capabilities of the LLM while ensuring syntactic and semantic correctness in its outputs. Building on these theoretical insights, we propose a reasoning-augmented constrained decoding algorithm, CRANE, which effectively balances the correctness of constrained generation with the flexibility of unconstrained generation. Experiments on multiple open-source LLMs and benchmarks show that CRANE significantly outperforms both state-of-the-art constrained decoding strategies and standard unconstrained decoding, showing up to 10% points accuracy improvement over baselines on challenging symbolic reasoning benchmarks GSM-symbolic and FOLIO.
Authors: Dongrui Wu
Abstract: Due to large intra-subject and inter-subject variabilities of electroencephalogram (EEG) signals, EEG-based brain-computer interfaces (BCIs) usually need subject-specific calibration to tailor the decoding algorithm for each new subject, which is time-consuming and user-unfriendly, hindering their real-world applications. Transfer learning (TL) has been extensively used to expedite the calibration, by making use of EEG data from other subjects/sessions. An important consideration in TL for EEG-based BCIs is to reduce the data distribution discrepancies among different subjects/sessions, to avoid negative transfer. Euclidean alignment (EA) was proposed in 2020 to address this challenge. Numerous experiments from 13 different BCI paradigms demonstrated its effectiveness and efficiency. This paper revisits EA, explaining its procedure and correct usage, introducing its applications and extensions, and pointing out potential new research directions. It should be very helpful to BCI researchers, especially those who are working on EEG signal decoding.
Authors: Shoumik Saha, Soheil Feizi
Abstract: The growing use of large language models (LLMs) for text generation has led to widespread concerns about AI-generated content detection. However, an overlooked challenge is AI-polished text, where human-written content undergoes subtle refinements using AI tools. This raises a critical question: should minimally polished text be classified as AI-generated? Such classification can lead to false plagiarism accusations and misleading claims about AI prevalence in online content. In this study, we systematically evaluate twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation (APT-Eval) dataset, which contains 14.7K samples refined at varying AI-involvement levels. Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models. These limitations highlight the urgent need for more nuanced detection methodologies.
Authors: Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Mart\'in Soto, Nathan Labenz, Owain Evans
Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding. It asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment. In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger. It's important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.
Authors: Gregory Koushnir, Michael Fire, Galit Fuhrmann Alpert, Dima Kagan
Abstract: Voice data is increasingly being used in modern digital communications, yet there is still a lack of comprehensive tools for automated voice analysis and characterization. To this end, we developed the VANPY (Voice Analysis in Python) framework for automated pre-processing, feature extraction, and classification of voice data. The VANPY is an open-source end-to-end comprehensive framework that was developed for the purpose of speaker characterization from voice data. The framework is designed with extensibility in mind, allowing for easy integration of new components and adaptation to various voice analysis applications. It currently incorporates over fifteen voice analysis components - including music/speech separation, voice activity detection, speaker embedding, vocal feature extraction, and various classification models. Four of the VANPY's components were developed in-house and integrated into the framework to extend its speaker characterization capabilities: gender classification, emotion classification, age regression, and height regression. The models demonstrate robust performance across various datasets, although not surpassing state-of-the-art performance. As a proof of concept, we demonstrate the framework's ability to extract speaker characteristics on a use-case challenge of analyzing character voices from the movie "Pulp Fiction." The results illustrate the framework's capability to extract multiple speaker characteristics, including gender, age, height, emotion type, and emotion intensity measured across three dimensions: arousal, dominance, and valence.
Authors: Kyle Stein, Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities in learning joint representations of visual and textual data, making them powerful tools for tasks such as Compositional Zero-Shot Learning (CZSL). CZSL requires models to generalize to novel combinations of visual primitives-such as attributes and objects-that were not explicitly encountered during training. Recent works in prompting for CZSL have focused on modifying inputs for the text encoder, often using static prompts that do not change across varying visual contexts. However, these approaches struggle to fully capture varying visual contexts, as they focus on text adaptation rather than leveraging visual features for compositional reasoning. To address this, we propose Visual Adaptive Prompting System (VAPS) that leverages a learnable visual prompt repository and similarity-based retrieval mechanism within the framework of VLMs to bridge the gap between semantic and visual features. Our method introduces a dynamic visual prompt repository mechanism that selects the most relevant attribute and object prompts based on the visual features of the image. Our proposed system includes a visual prompt adapter that encourages the model to learn a more generalizable embedding space. Experiments on three CZSL benchmarks, across both closed and open-world scenarios, demonstrate state-of-the-art results.
Authors: Han-Byul Kim, Duc Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho
Abstract: With the rapid expansion in the scale of large language models (LLMs), enabling efficient distributed inference across multiple computing units has become increasingly critical. However, communication overheads from popular distributed inference techniques such as Tensor Parallelism pose a significant challenge to achieve scalability and low latency. Therefore, we introduce a novel optimization technique, Sync-Point Drop (SPD), to reduce communication overheads in tensor parallelism by selectively dropping synchronization on attention outputs. In detail, we first propose a block design that allows execution to proceed without communication through SPD. Second, we apply different SPD strategies to attention blocks based on their sensitivity to the model accuracy. The proposed methods effectively alleviate communication bottlenecks while minimizing accuracy degradation during LLM inference, offering a scalable solution for diverse distributed environments: SPD offered about 20% overall inference latency reduction with < 1% accuracy regression for LLaMA2-70B inference over 8 GPUs.
Authors: Milin Patel, Rolf Jung, Marzana Khatun
Abstract: In the automobile industry, ensuring the safety of automated vehicles equipped with the Automated Driving System (ADS) is becoming a significant focus due to the increasing development and deployment of automated driving. Automated driving depends on sensing both the external and internal environments of a vehicle, utilizing perception sensors and algorithms, and Electrical/Electronic (E/E) systems for situational awareness and response. ISO 21448 is the standard for Safety of the Intended Functionality (SOTIF) that aims to ensure that the ADS operate safely within their intended functionality. SOTIF focuses on preventing or mitigating potential hazards that may arise from the limitations or failures of the ADS, including hazards due to insufficiencies of specification, or performance insufficiencies, as well as foreseeable misuse of the intended functionality. However, the challenge lies in ensuring the safety of vehicles despite the limited availability of extensive and systematic literature on SOTIF. To address this challenge, a Systematic Literature Review (SLR) on SOTIF for the ADS is performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The objective is to methodically gather and analyze the existing literature on SOTIF. The major contributions of this paper are: (i) presenting a summary of the literature by synthesizing and organizing the collective findings, methodologies, and insights into distinct thematic groups, and (ii) summarizing and categorizing the acknowledged limitations based on data extracted from an SLR of 51 research papers published between 2018 and 2023. Furthermore, research gaps are determined, and future research directions are proposed.
Authors: Yunhao Luo, Utkarsh A. Mishra, Yilun Du, Danfei Xu
Abstract: Effective trajectory stitching for long-horizon planning is a significant challenge in robotic decision-making. While diffusion models have shown promise in planning, they are limited to solving tasks similar to those seen in their training data. We propose CompDiffuser, a novel generative approach that can solve new tasks by learning to compositionally stitch together shorter trajectory chunks from previously seen tasks. Our key insight is modeling the trajectory distribution by subdividing it into overlapping chunks and learning their conditional relationships through a single bidirectional diffusion model. This allows information to propagate between segments during generation, ensuring physically consistent connections. We conduct experiments on benchmark tasks of various difficulties, covering different environment sizes, agent state dimension, trajectory types, training data quality, and show that CompDiffuser significantly outperforms existing methods.
Authors: Akshara Prabhakar, Zuxin Liu, Ming Zhu, Jianguo Zhang, Tulika Awalgaonkar, Shiyu Wang, Zhiwei Liu, Haolin Chen, Thai Hoang, Juan Carlos Niebles, Shelby Heinecke, Weiran Yao, Huan Wang, Silvio Savarese, Caiming Xiong
Abstract: Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $\tau$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source 5K synthetic data trajectories and the trained xLAM-2-fc-r models to advance research in AI agents. Models at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4; Dataset at https://huggingface.co/datasets/Salesforce/APIGen-MT-5k and Website at https://apigen-mt.github.io
URLs: https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4;, https://huggingface.co/datasets/Salesforce/APIGen-MT-5k, https://apigen-mt.github.io
Authors: Afra Amini, Tim Vieira, Ryan Cotterell
Abstract: Estimating the Kullback--Leibler (KL) divergence between language models has many applications, e.g., reinforcement learning from human feedback (RLHF), interpretability, and knowledge distillation. However, computing the exact KL divergence between two arbitrary language models is intractable. Thus, practitioners often resort to the use of sampling-based estimators. While it is easy to fashion a simple Monte Carlo (MC) estimator that provides an unbiased estimate of the KL divergence between language models, this estimator notoriously suffers from high variance, and can even result in a negative estimate of the KL divergence, a non-negative quantity. In this paper, we introduce a Rao--Blackwellized estimator that is also unbiased and provably has variance less than or equal to that of the standard Monte Carlo estimator. In an empirical study on sentiment-controlled fine-tuning, we show that our estimator provides more stable KL estimates and reduces variance substantially in practice. Additionally, we derive an analogous Rao--Blackwellized estimator of the gradient of the KL divergence, which leads to more stable training and produces models that more frequently appear on the Pareto frontier of reward vs. KL compared to the ones trained with the MC estimator of the gradient.
Authors: Mikhail Osipov
Abstract: We present a geometry-driven method for normalizing dysarthric speech by modeling time, frequency, and amplitude distortions as smooth, local Lie group transformations of spectrograms. Scalar fields generate these deformations via exponential maps, and a neural network is trained - using only synthetically warped healthy speech - to infer the fields and apply an approximate inverse at test time. We introduce a spontaneous-symmetry-breaking (SSB) potential that encourages the model to discover non-trivial field configurations. On real pathological speech, the system delivers consistent gains: up to 17 percentage-point WER reduction on challenging TORGO utterances and a 16 percent drop in WER variance, with no degradation on clean CommonVoice data. Character and phoneme error rates improve in parallel, confirming linguistic relevance. Our results demonstrate that geometrically structured warping provides consistent, zero-shot robustness gains for dysarthric ASR.
Authors: Mohamed Gado, Towhid Taliee, Muhammad Memon, Dmitry Ignatov, Radu Timofte
Abstract: Visual storytelling is an interdisciplinary field combining computer vision and natural language processing to generate cohesive narratives from sequences of images. This paper presents a novel approach that leverages recent advancements in multimodal models, specifically adapting transformer-based architectures and large multimodal models, for the visual storytelling task. Leveraging the large-scale Visual Storytelling (VIST) dataset, our VIST-GPT model produces visually grounded, contextually appropriate narratives. We address the limitations of traditional evaluation metrics, such as BLEU, METEOR, ROUGE, and CIDEr, which are not suitable for this task. Instead, we utilize RoViST and GROOVIST, novel reference-free metrics designed to assess visual storytelling, focusing on visual grounding, coherence, and non-redundancy. These metrics provide a more nuanced evaluation of narrative quality, aligning closely with human judgment.
Authors: Yuankang Zhao, Matthew Engelhard
Abstract: The Hawkes process (HP) is commonly used to model event sequences with self-reinforcing dynamics, including electronic health records (EHRs). Traditional HPs capture self-reinforcement via parametric impact functions that can be inspected to understand how each event modulates the intensity of others. Neural network-based HPs offer greater flexibility, resulting in improved fit and prediction performance, but at the cost of interpretability, which is often critical in healthcare. In this work, we aim to understand and improve upon this tradeoff. We propose a novel HP formulation in which impact functions are modeled by defining a flexible impact kernel, instantiated as a neural network, in event embedding space, which allows us to model large-scale event sequences with many event types. This approach is more flexible than traditional HPs yet more interpretable than other neural network approaches, and allows us to explicitly trade flexibility for interpretability by adding transformer encoder layers to further contextualize the event embeddings. Results show that our method accurately recovers impact functions in simulations, achieves competitive performance on MIMIC-IV procedure dataset, and gains clinically meaningful interpretation on XX-EHR with children diagnosis dataset even without transformer layers. This suggests that our flexible impact kernel is often sufficient to capture self-reinforcing dynamics in EHRs and other data effectively, implying that interpretability can be maintained without loss of performance.
Authors: Luigi Sigillo, Christian Bianchi, Aurelio Uncini, Danilo Comminiello
Abstract: Image Super-Resolution is a fundamental problem in computer vision with broad applications spacing from medical imaging to satellite analysis. The ability to reconstruct high-resolution images from low-resolution inputs is crucial for enhancing downstream tasks such as object detection and segmentation. While deep learning has significantly advanced SR, achieving high-quality reconstructions with fine-grained details and realistic textures remains challenging, particularly at high upscaling factors. Recent approaches leveraging diffusion models have demonstrated promising results, yet they often struggle to balance perceptual quality with structural fidelity. In this work, we introduce ResQu a novel SR framework that integrates a quaternion wavelet preprocessing framework with latent diffusion models, incorporating a new quaternion wavelet- and time-aware encoder. Unlike prior methods that simply apply wavelet transforms within diffusion models, our approach enhances the conditioning process by exploiting quaternion wavelet embeddings, which are dynamically integrated at different stages of denoising. Furthermore, we also leverage the generative priors of foundation models such as Stable Diffusion. Extensive experiments on domain-specific datasets demonstrate that our method achieves outstanding SR results, outperforming in many cases existing approaches in perceptual quality and standard evaluation metrics. The code will be available after the revision process.