Authors: L. Juli\'an Lechuga L\'opez, Shaza Elsharief, Dhiyaa Al Jorf, Firas Darwish, Congbo Ma, Farah E. Shamout
Abstract: Uncertainty Quantification (UQ) is pivotal in enhancing the robustness, reliability, and interpretability of Machine Learning (ML) systems for healthcare, optimizing resources and improving patient care. Despite the emergence of ML-based clinical decision support tools, the lack of principled quantification of uncertainty in ML models remains a major challenge. Current reviews have a narrow focus on analyzing the state-of-the-art UQ in specific healthcare domains without systematically evaluating method efficacy across different stages of model development, and despite a growing body of research, its implementation in healthcare applications remains limited. Therefore, in this survey, we provide a comprehensive analysis of current UQ in healthcare, offering an informed framework that highlights how different methods can be integrated into each stage of the ML pipeline including data processing, training and evaluation. We also highlight the most popular methods used in healthcare and novel approaches from other domains that hold potential for future adoption in the medical context. We expect this study will provide a clear overview of the challenges and opportunities of implementing UQ in the ML pipeline for healthcare, guiding researchers and practitioners in selecting suitable techniques to enhance the reliability, safety and trust from patients and clinicians on ML-driven healthcare solutions.
Authors: Hele Zhu, Xinyi Huang, Haojia Gao, Mengfei Jiang, Haohua Que, Lei Mu
Abstract: Plant disease is a critical factor affecting agricultural production. Traditional manual recognition methods face significant drawbacks, including low accuracy, high costs, and inefficiency. Deep learning techniques have demonstrated significant benefits in identifying plant diseases, but they still face challenges such as inference delays and high energy consumption. Deep learning algorithms are difficult to run on resource-limited embedded devices. Offloading these models to cloud servers is confronted with the restriction of communication bandwidth, and all of these factors will influence the inference's efficiency. We propose a collaborative inference framework for recognizing plant diseases between edge devices and cloud servers to enhance inference speed. The DNN model for plant disease recognition is pruned through deep reinforcement learning to improve the inference speed and reduce energy consumption. Then the optimal split point is determined by a greedy strategy to achieve the best collaborated inference acceleration. Finally, the system for collaborative inference acceleration in plant disease recognition has been implemented using Gradio to facilitate friendly human-machine interaction. Experiments indicate that the proposed collaborative inference framework significantly increases inference speed while maintaining acceptable recognition accuracy, offering a novel solution for rapidly diagnosing and preventing plant diseases.
Authors: Zian Liu, Renjun Jia
Abstract: Predicting financial time series presents significant challenges due to inherent low signal-to-noise ratios and intricate temporal patterns. Traditional machine learning models exhibit limitations in this forecasting task constrained by their restricted model capacity. Recent advances in large language models (LLMs), with their greatly expanded parameter spaces, demonstrate promising potential for modeling complex dependencies in temporal sequences. However, existing LLM-based approaches typically focus on fixed-length patch analysis due to the Transformer architecture, ignoring market data's multi-scale pattern characteristics. In this study, we propose $LLM4FTS$, a novel framework that enhances LLM capabilities for temporal sequence modeling through learnable patch segmentation and dynamic wavelet convolution modules. Specifically,we first employ K-means++ clustering based on DTW distance to identify scale-invariant patterns in market data. Building upon pattern recognition results, we introduce adaptive patch segmentation that partitions temporal sequences while preserving maximal pattern integrity. To accommodate time-varying frequency characteristics, we devise a dynamic wavelet convolution module that emulates discrete wavelet transformation with enhanced flexibility in capturing time-frequency features. These three modules work together to improve large language model's ability to handle scale-invariant patterns in financial time series. Extensive experiments on real-world financial datasets substantiate the framework's efficacy, demonstrating superior performance in capturing complex market patterns and achieving state-of-the-art results in stock return prediction. The successful deployment in practical trading systems confirms its real-world applicability, representing a significant advancement in LLM applications for financial forecasting.
Authors: Kazuki Fujii, Yukito Tajima, Sakae Mizuki, Hinari Shimada, Taihei Shiotani, Koshiro Saito, Masanari Ohi, Masaki Kawamura, Taishi Nakamura, Takumi Okamoto, Shigeki Ishida, Kakeru Hattori, Youmi Ma, Hiroya Takamura, Rio Yokota, Naoaki Okazaki
Abstract: The performance of large language models (LLMs) in program synthesis and mathematical reasoning is fundamentally limited by the quality of their pre-training corpora. We introduce two openly licensed datasets, released under the Llama 3.3 Community License, that significantly enhance LLM performance by systematically rewriting public data. SwallowCode (approximately 16.1 billion tokens) refines Python snippets from The-Stack-v2 through a novel four-stage pipeline: syntax validation, pylint-based style filtering, and a two-stage LLM rewriting process that enforces style conformity and transforms snippets into self-contained, algorithmically efficient examples. Unlike prior methods that rely on exclusionary filtering or limited transformations, our transform-and-retain approach upgrades low-quality code, maximizing data utility. SwallowMath (approximately 2.3 billion tokens) enhances Finemath-4+ by removing boilerplate, restoring context, and reformatting solutions into concise, step-by-step explanations. Within a fixed 50 billion token training budget, continual pre-training of Llama-3.1-8B with SwallowCode boosts pass@1 by +17.0 on HumanEval and +17.7 on HumanEval+ compared to Stack-Edu, surpassing the baseline model's code generation capabilities. Similarly, substituting SwallowMath yields +12.4 accuracy on GSM8K and +7.6 on MATH. Ablation studies confirm that each pipeline stage contributes incrementally, with rewriting delivering the largest gains. All datasets, prompts, and checkpoints are publicly available, enabling reproducible research and advancing LLM pre-training for specialized domains.
Authors: Guangzhi Sun, Potsawee Manakul, Xiao Zhan, Mark Gales
Abstract: Unlearning has emerged as a critical capability for large language models (LLMs) to support data privacy, regulatory compliance, and ethical AI deployment. Recent techniques often rely on obfuscation by injecting incorrect or irrelevant information to suppress knowledge. Such methods effectively constitute knowledge addition rather than true removal, often leaving models vulnerable to probing. In this paper, we formally distinguish unlearning from obfuscation and introduce a probing-based evaluation framework to assess whether existing approaches genuinely remove targeted information. Moreover, we propose DF-MCQ, a novel unlearning method that flattens the model predictive distribution over automatically generated multiple-choice questions using KL-divergence, effectively removing knowledge about target individuals and triggering appropriate refusal behaviour. Experimental results demonstrate that DF-MCQ achieves unlearning with over 90% refusal rate and a random choice-level uncertainty that is much higher than obfuscation on probing questions.
Authors: Rintaro Ando
Abstract: We present Noise-to-Meaning Recursive Self-Improvement (N2M-RSI), a minimal formal model showing that once an AI agent feeds its own outputs back as inputs and crosses an explicit information-integration threshold, its internal complexity will grow without bound under our assumptions. The framework unifies earlier ideas on self-prompting large language models, G\"odelian self-reference, and AutoML, yet remains implementation-agnostic. The model furthermore scales naturally to interacting swarms of agents, hinting at super-linear effects once communication among instances is permitted. For safety reasons, we omit system-specific implementation details and release only a brief, model-agnostic toy prototype in Appendix C.
Authors: Oyindolapo O. Komolafe, Zhimin Mei, David Morales Zarate, Gregory William Spangenberg
Abstract: Sepsis is a life threatening medical condition that occurs when the body has an extreme response to infection, leading to widespread inflammation, organ failure, and potentially death. Because sepsis can worsen rapidly, early detection is critical to saving lives. However, current diagnostic methods often identify sepsis only after significant damage has already occurred. Our project aims to address this challenge by developing a machine learning based system to predict sepsis in its early stages, giving healthcare providers more time to intervene. A major problem with existing models is the wide variability in the patient information or features they use, such as heart rate, temperature, and lab results. This inconsistency makes models difficult to compare and limits their ability to work across different hospitals and settings. To solve this, we propose a method called Feature Aligned Transfer Learning (FATL), which identifies and focuses on the most important and commonly reported features across multiple studies, ensuring the model remains consistent and clinically relevant. Most existing models are trained on narrow patient groups, leading to population bias. FATL addresses this by combining knowledge from models trained on diverse populations, using a weighted approach that reflects each models contribution. This makes the system more generalizable and effective across different patient demographics and clinical environments. FATL offers a practical and scalable solution for early sepsis detection, particularly in hospitals with limited resources, and has the potential to improve patient outcomes, reduce healthcare costs, and support more equitable healthcare delivery.
Authors: Yaoqi Chen, Jinkai Zhang, Baotong Lu, Qianxi Zhang, Chengruidong Zhang, Jingjia Luo, Di Liu, Huiqiang Jiang, Qi Chen, Jing Liu, Bailu Ding, Xiao Yan, Jiawei Jiang, Chen Chen, Mingxing Zhang, Yuqing Yang, Fan Yang, Mao Yang
Abstract: The growing context lengths of large language models (LLMs) pose significant challenges for efficient inference, primarily due to GPU memory and bandwidth constraints. We present RetroInfer, a novel system that reconceptualizes the key-value (KV) cache as a vector storage system which exploits the inherent attention sparsity to accelerate long-context LLM inference. At its core is the wave index, an Attention-aWare VEctor index that enables efficient and accurate retrieval of critical tokens through techniques such as tripartite attention approximation, accuracy-bounded attention estimation, and segmented clustering. Complementing this is the wave buffer, which coordinates KV cache placement and overlaps computation and data transfer across GPU and CPU to sustain high throughput. Unlike prior sparsity-based methods that struggle with token selection and hardware coordination, RetroInfer delivers robust performance without compromising model accuracy. Experiments on long-context benchmarks show up to 4.5X speedup over full attention within GPU memory limits and up to 10.5X over sparse attention baselines when KV cache is extended to CPU memory, all while preserving full-attention-level accuracy.
Authors: Enrique Nueve, Bo Waggoner
Abstract: When agents trade in a Duality-based Cost Function prediction market, they collectively implement the learning algorithm Follow-The-Regularized-Leader. We ask whether other learning algorithms could be used to inspire the design of prediction markets. By decomposing and modifying the Duality-based Cost Function Market Maker's (DCFMM) pricing mechanism, we propose a new prediction market, called the Smooth Quadratic Prediction Market, the incentivizes agents to collectively implement general steepest gradient descent. Relative to the DCFMM, the Smooth Quadratic Prediction Market has a better worst-case monetary loss for AD securities while preserving axiom guarantees such as the existence of instantaneous price, information incorporation, expressiveness, no arbitrage, and a form of incentive compatibility. To motivate the application of the Smooth Quadratic Prediction Market, we independently examine agents' trading behavior under two realistic constraints: bounded budgets and buy-only securities. Finally, we provide an introductory analysis of an approach to facilitate adaptive liquidity using the Smooth Quadratic AD Prediction Market. Our results suggest future designs where the price update rule is separate from the fee structure, yet guarantees are preserved.
Authors: Fabien Casenave, Xavier Roynard, Brian Staber, Nissrine Akkari, William Piat, Michele Alessandro Bucci, Abbas Kabalan, Xuan Minh Vuong Nguyen, Luca Saverio, Rapha\"el Carpintero Perez, Anthony Kalaydjian, Samy Fouch\'e, Thierry Gonon, Ghassan Najjar, Emmanuel Menier, Matthieu Nastorg, Christian Rey
Abstract: Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows. However, their widespread adoption is hindered by the lack of large-scale, diverse, and standardized datasets tailored to physics-based simulations. While existing initiatives provide valuable contributions, many are limited in scope-focusing on specific physics domains, relying on fragmented tooling, or adhering to overly simplistic datamodels that restrict generalization. To address these limitations, we introduce PLAID (Physics-Learning AI Datamodel), a flexible and extensible framework for representing and sharing datasets of physics simulations. PLAID defines a unified standard for describing simulation data and is accompanied by a library for creating, reading, and manipulating complex datasets across a wide range of physical use cases (gitlab.com/drti/plaid). We release six carefully crafted datasets under the PLAID standard, covering structural mechanics and computational fluid dynamics, and provide baseline benchmarks using representative learning methods. Benchmarking tools are made available on Hugging Face, enabling direct participation by the community and contribution to ongoing evaluation efforts (huggingface.co/PLAIDcompetitions).
Authors: Mohammad Partohaghighi, Roummel Marcia, YangQuan Chen
Abstract: Fractional-order stochastic gradient descent (FOSGD) leverages fractional exponents to capture long-memory effects in optimization. However, its utility is often limited by the difficulty of tuning and stabilizing these exponents. We propose 2SED Fractional-Order Stochastic Gradient Descent (2SEDFOSGD), which integrates the Two-Scale Effective Dimension (2SED) algorithm with FOSGD to adapt the fractional exponent in a data-driven manner. By tracking model sensitivity and effective dimensionality, 2SEDFOSGD dynamically modulates the exponent to mitigate oscillations and hasten convergence. Theoretically, for onoconvex optimization problems, this approach preserves the advantages of fractional memory without the sluggish or unstable behavior observed in na\"ive fractional SGD. Empirical evaluations in Gaussian and $\alpha$-stable noise scenarios using an autoregressive (AR) model highlight faster convergence and more robust parameter estimates compared to baseline methods, underscoring the potential of dimension-aware fractional techniques for advanced modeling and estimation tasks.
Authors: Sean I. Young
Abstract: In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint due to large-scale AI infrastructure. Here, we establish the foundations of LLM quantization from a rate-distortion theory perspective and propose a quantization technique based on simple rate-distortion optimization. Our technique scales to models containing hundreds of billions of weight parameters and offers users the flexibility to compress models, post-training, to a model size or accuracy specified by the user.
Authors: Steven Tin Sui Luo
Abstract: Instant-NGP has been the state-of-the-art architecture of neural fields in recent years. Its incredible signal-fitting capabilities are generally attributed to its multi-resolution hash grid structure and have been used and improved in numerous following works. However, it is unclear how and why such a hash grid structure improves the capabilities of a neural network by such great margins. A lack of principled understanding of the hash grid also implies that the large set of hyperparameters accompanying Instant-NGP could only be tuned empirically without much heuristics. To provide an intuitive explanation of the working principle of the hash grid, we propose a novel perspective, namely domain manipulation. This perspective provides a ground-up explanation of how the feature grid learns the target signal and increases the expressivity of the neural field by artificially creating multiples of pre-existing linear segments. We conducted numerous experiments on carefully constructed 1-dimensional signals to support our claims empirically and aid our illustrations. While our analysis mainly focuses on 1-dimensional signals, we show that the idea is generalizable to higher dimensions.
Authors: Yoel Zimmermann, Adib Bazgir, Alexander Al-Feghali, Mehrad Ansari, L. Catherine Brinson, Yuan Chiang, Defne Circi, Min-Hsueh Chiu, Nathan Daelman, Matthew L. Evans, Abhijeet S. Gangan, Janine George, Hassan Harb, Ghazal Khalighinejad, Sartaaj Takrim Khan, Sascha Klawohn, Magdalena Lederbauer, Soroush Mahjoubi, Bernadette Mohr, Seyed Mohamad Moosavi, Aakash Naik, Aleyna Beste Ozhan, Dieter Plessers, Aritra Roy, Fabian Sch\"oppach, Philippe Schwaller, Carla Terboven, Katharina Ueltzen, Shang Zhu, Jan Janssen, Calvin Li, Ian Foster, Ben Blaiszik
Abstract: Large Language Models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 34 total projects developed during the second annual Large Language Model Hackathon for Applications in Materials Science and Chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.
Authors: Shashank Kapoor, Sanjay Surendranath Girija, Lakshit Arora, Dipen Pradhan, Ankit Shetgaonkar, Aman Raj
Abstract: The introduction of multimodal models is a huge step forward in Artificial Intelligence. A single model is trained to understand multiple modalities: text, image, video, and audio. Open-source multimodal models have made these breakthroughs more accessible. However, considering the vast landscape of adversarial attacks across these modalities, these models also inherit vulnerabilities of all the modalities, and ultimately, the adversarial threat amplifies. While broad research is available on possible attacks within or across these modalities, a practitioner-focused view that outlines attack types remains absent in the multimodal world. As more Machine Learning Practitioners adopt, fine-tune, and deploy open-source models in real-world applications, it's crucial that they can view the threat landscape and take the preventive actions necessary. This paper addresses the gap by surveying adversarial attacks targeting all four modalities: text, image, video, and audio. This survey provides a view of the adversarial attack landscape and presents how multimodal adversarial threats have evolved. To the best of our knowledge, this survey is the first comprehensive summarization of the threat landscape in the multimodal world.
Authors: Lutfu Sua, Haibo Wang, Jun Huang
Abstract: Unpredictability of renewable energy sources coupled with the complexity of those methods used for various purposes in this area calls for the development of robust methods such as DL models within the renewable energy domain. Given the nonlinear relationships among variables in renewable energy datasets, DL models are preferred over traditional machine learning (ML) models because they can effectively capture and model complex interactions between variables. This research aims to identify the factors responsible for the accuracy of DL techniques, such as sampling, stationarity, linearity, and hyperparameter optimization for different algorithms. The proposed DL framework compares various methods and alternative training/test ratios. Seven ML methods, such as Long-Short Term Memory (LSTM), Stacked LSTM, Convolutional Neural Network (CNN), CNN-LSTM, Deep Neural Network (DNN), Multilayer Perceptron (MLP), and Encoder-Decoder (ED), were evaluated on two different datasets. The first dataset contains the weather and power generation data. It encompasses two distinct datasets, hourly energy demand data and hourly weather data in Spain, while the second dataset includes power output generated by the photovoltaic panels at 12 locations. This study deploys regularization approaches, including early stopping, neuron dropping, and L2 regularization, to reduce the overfitting problem associated with DL models. The LSTM and MLP models show superior performance. Their validation data exhibit exceptionally low root mean square error values.
Authors: Mohammad Rostami, Atik Faysal, Reihaneh Gh. Roshan, Huaxia Wang, Nikhil Muralidhar, Yu-Dong Yao
Abstract: Automatic Modulation Classification (AMC) is critical for efficient spectrum management and robust wireless communications. However, AMC remains challenging due to the complex interplay of signal interference and noise. In this work, we propose an innovative framework that integrates traditional signal processing techniques with Large-Language Models (LLMs) to address AMC. Our approach leverages higher-order statistics and cumulant estimation to convert quantitative signal features into structured natural language prompts. By incorporating exemplar contexts into these prompts, our method exploits the LLM's inherent familiarity with classical signal processing, enabling effective one-shot classification without additional training or preprocessing (e.g., denoising). Experimental evaluations on synthetically generated datasets, spanning both noiseless and noisy conditions, demonstrate that our framework achieves competitive performance across diverse modulation schemes and Signal-to-Noise Ratios (SNRs). Moreover, our approach paves the way for robust foundation models in wireless communications across varying channel conditions, significantly reducing the expense associated with developing channel-specific models. This work lays the foundation for scalable, interpretable, and versatile signal classification systems in next-generation wireless networks. The source code is available at https://github.com/RU-SIT/context-is-king
Authors: Dmytro Shamatrin
Abstract: Multi-label classification (MLC) requires predicting multiple labels per sample, often under heavy class imbalance and noisy conditions. Traditional approaches apply fixed thresholds or treat labels independently, overlooking context and global rarity. We introduce an adaptive thresholding mechanism that fuses global (IDF-based) and local (KNN-based) signals to produce per-label, per-instance thresholds. Instead of applying these as hard cutoffs, we treat them as differentiable penalties in the loss, providing smooth supervision and better calibration. Our architecture is lightweight, interpretable, and highly modular. On the AmazonCat-13K benchmark, it achieves a macro-F1 of 0.1712, substantially outperforming tree-based and pretrained transformer-based methods. We release full code for reproducibility and future extensions.
Authors: Max Qiushi Lin, Jincheng Mei, Matin Aghaei, Michael Lu, Bo Dai, Alekh Agarwal, Dale Schuurmans, Csaba Szepesvari, Sharan Vaswani
Abstract: Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the approximation error in modeling problem-dependent quantities is a key notion for characterizing the global convergence of PG methods. We focus on Softmax PG with linear function approximation (referred to as $\texttt{Lin-SPG}$) and demonstrate that the approximation error is irrelevant to the algorithm's global convergence even for the stochastic bandit setting. Consequently, we first identify the necessary and sufficient conditions on the feature representation that can guarantee the asymptotic global convergence of $\texttt{Lin-SPG}$. Under these feature conditions, we prove that $T$ iterations of $\texttt{Lin-SPG}$ with a problem-specific learning rate result in an $O(1/T)$ convergence to the optimal policy. Furthermore, we prove that $\texttt{Lin-SPG}$ with any arbitrary constant learning rate can ensure asymptotic global convergence to the optimal policy.
Authors: Nikita Ravi, Abhinav Goel, James C. Davis, George K. Thiruvathukal
Abstract: The field of deep learning has witnessed significant breakthroughs, spanning various applications, and fundamentally transforming current software capabilities. However, alongside these advancements, there have been increasing concerns about reproducing the results of these deep learning methods. This is significant because reproducibility is the foundation of reliability and validity in software development, particularly in the rapidly evolving domain of deep learning. The difficulty of reproducibility may arise due to several reasons, including having differences from the original execution environment, incompatible software libraries, proprietary data and source code, lack of transparency, and the stochastic nature in some software. A study conducted by the Nature journal reveals that more than 70% of researchers failed to reproduce other researchers experiments and over 50% failed to reproduce their own experiments. Irreproducibility of deep learning poses significant challenges for researchers and practitioners. To address these concerns, this paper presents a systematic approach at analyzing and improving the reproducibility of deep learning models by demonstrating these guidelines using a case study. We illustrate the patterns and anti-patterns involved with these guidelines for improving the reproducibility of deep learning models. These guidelines encompass establishing a methodology to replicate the original software environment, implementing end-to-end training and testing algorithms, disclosing architectural designs, and enhancing transparency in data processing and training pipelines. We also conduct a sensitivity analysis to understand the model performance across diverse conditions. By implementing these strategies, we aim to bridge the gap between research and practice, so that innovations in deep learning can be effectively reproduced and deployed within software.
Authors: Caleb Chuck, Fan Feng, Carl Qi, Chang Shi, Siddhant Agarwal, Amy Zhang, Scott Niekum
Abstract: Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion. However, hindsight relabeling can struggle in object-centric domains. For example, suppose that the goal space consists of a robotic arm pushing a particular target block to a goal location. In this case, hindsight relabeling will give high rewards to any trajectory that does not interact with the block. However, these behaviors are only useful when the object is already at the goal -- an extremely rare case in practice. A dataset dominated by these kinds of trajectories can complicate learning and lead to failures. In object-centric domains, one key intuition is that meaningful trajectories are often characterized by object-object interactions such as pushing the block with the gripper. To leverage this intuition, we introduce Hindsight Relabeling using Interactions (HInt), which combines interactions with hindsight relabeling to improve the sample efficiency of downstream RL. However because interactions do not have a consensus statistical definition tractable for downstream GCRL, we propose a definition of interactions based on the concept of null counterfactual: a cause object is interacting with a target object if, in a world where the cause object did not exist, the target object would have different transition dynamics. We leverage this definition to infer interactions in Null Counterfactual Interaction Inference (NCII), which uses a "nulling'' operation with a learned model to infer interactions. NCII is able to achieve significantly improved interaction inference accuracy in both simple linear dynamics domains and dynamic robotic domains in Robosuite, Robot Air Hockey, and Franka Kitchen and HInt improves sample efficiency by up to 4x.
Authors: Jiawei Wang, Xintao Yan, Yao Mu, Haowei Sun, Zhong Cao, Henry X. Liu
Abstract: Generating safety-critical scenarios in high-fidelity simulations offers a promising and cost-effective approach for efficient testing of autonomous vehicles. Existing methods typically rely on manipulating a single vehicle's trajectory through sophisticated designed objectives to induce adversarial interactions, often at the cost of realism and scalability. In this work, we propose the Risk-Adjustable Driving Environment (RADE), a simulation framework that generates statistically realistic and risk-adjustable traffic scenes. Built upon a multi-agent diffusion architecture, RADE jointly models the behavior of all agents in the environment and conditions their trajectories on a surrogate risk measure. Unlike traditional adversarial methods, RADE learns risk-conditioned behaviors directly from data, preserving naturalistic multi-agent interactions with controllable risk levels. To ensure physical plausibility, we incorporate a tokenized dynamics check module that efficiently filters generated trajectories using a motion vocabulary. We validate RADE on the real-world rounD dataset, demonstrating that it preserves statistical realism across varying risk levels and naturally increases the likelihood of safety-critical events as the desired risk level grows up. Our results highlight RADE's potential as a scalable and realistic tool for AV safety evaluation.
Authors: Jake Grigsby, Yuke Zhu, Michael Ryoo, Juan Carlos Niebles
Abstract: Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data and provide agents with the visual reasoning necessary for new applications in areas such as computer automation. However, agent tasks emphasize skills where accessible open-weight VLMs lag behind their LLM equivalents. For example, VLMs are less capable of following an environment's strict output syntax requirements and are more focused on open-ended question answering. Overcoming these limitations requires supervised fine-tuning (SFT) on task-specific expert demonstrations. Our work approaches these challenges from an offline-to-online reinforcement learning (RL) perspective. RL lets us fine-tune VLMs to agent tasks while learning from the unsuccessful decisions of our own model or more capable (larger) models. We explore an off-policy RL solution that retains the stability and simplicity of the widely used SFT workflow while allowing our agent to self-improve and learn from low-quality datasets. We demonstrate this technique with two open-weight VLMs across three multi-modal agent domains.
Authors: Yiding Chen, Yiyi Zhang, Owen Oertell, Wen Sun
Abstract: Diffusion models accomplish remarkable success in data generation tasks across various domains. However, the iterative sampling process is computationally expensive. Consistency models are proposed to learn consistency functions to map from noise to data directly, which allows one-step fast data generation and multistep sampling to improve sample quality. In this paper, we study the convergence of consistency models when the self-consistency property holds approximately under the training distribution. Our analysis requires only mild data assumption and applies to a family of forward processes. When the target data distribution has bounded support or has tails that decay sufficiently fast, we show that the samples generated by the consistency model are close to the target distribution in Wasserstein distance; when the target distribution satisfies some smoothness assumption, we show that with an additional perturbation step for smoothing, the generated samples are close to the target distribution in total variation distance. We provide two case studies with commonly chosen forward processes to demonstrate the benefit of multistep sampling.
Authors: Zhaiming Shen, Alex Havrilla, Rongjie Lai, Alexander Cloninger, Wenjing Liao
Abstract: Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Empirical studies have demonstrated that real-world data and learning tasks exhibit low-dimensional structures, along with some noise or measurement error. The performance of transformers tends to depend on the intrinsic dimension of the data/tasks, though theoretical understandings remain largely unexplored for transformers. This work establishes a theoretical foundation by analyzing the performance of transformers for regression tasks involving noisy input data on a manifold. Specifically, the input data are in a tubular neighborhood of a manifold, while the ground truth function depends on the projection of the noisy data onto the manifold. We prove approximation and generalization errors which crucially depend on the intrinsic dimension of the manifold. Our results demonstrate that transformers can leverage low-complexity structures in learning task even when the input data are perturbed by high-dimensional noise. Our novel proof technique constructs representations of basic arithmetic operations by transformers, which may hold independent interest.
Authors: Yutong Xie, Fuchao Yang, Yuheng Jia
Abstract: Partial label learning (PLL) is a significant weakly supervised learning framework, where each training example corresponds to a set of candidate labels and only one label is the ground-truth label. For the first time, this paper investigates the partial label clustering problem, which takes advantage of the limited available partial labels to improve the clustering performance. Specifically, we first construct a weight matrix of examples based on their relationships in the feature space and disambiguate the candidate labels to estimate the ground-truth label based on the weight matrix. Then, we construct a set of must-link and cannot-link constraints based on the disambiguation results. Moreover, we propagate the initial must-link and cannot-link constraints based on an adversarial prior promoted dual-graph learning approach. Finally, we integrate weight matrix construction, label disambiguation, and pairwise constraints propagation into a joint model to achieve mutual enhancement. We also theoretically prove that a better disambiguated label matrix can help improve clustering performance. Comprehensive experiments demonstrate our method realizes superior performance when comparing with state-of-the-art constrained clustering methods, and outperforms PLL and semi-supervised PLL methods when only limited samples are annotated. The code is publicly available at https://github.com/xyt-ml/PLC.
Authors: Borui Wang, Kathleen McKeown, Rex Ying
Abstract: Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-generating LLM to induce textual strategies based on advantage estimations and expert demonstrations, and gradually internalizes induced strategies into the RL agent through policy optimization to improve its performance through boosting policy generalization and enhancing sample efficiency. It also provides a direct textual channel to observe and interpret the evolution of the policy's underlying strategies during training. We test DYSTIL over challenging RL environments from Minigrid and BabyAI, and empirically demonstrate that DYSTIL significantly outperforms state-of-the-art baseline methods by 17.75% in average success rate while also enjoying higher sample efficiency during the learning process.
Authors: Yue Chen, Hui Kang, Jiahui Li, Geng Su, Boxiong Wang, Jiacheng Wang, Cong Liang, Shuang Liang, Dusit Niyato
Abstract: The integration of simultaneous wireless information and power transfer (SWIPT) technology in 6G Internet of Things (IoT) networks faces significant challenges in remote areas and disaster scenarios where ground infrastructure is unavailable. This paper proposes a novel unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system enhanced by directional antennas to provide both computational resources and energy support for ground IoT terminals. However, such systems require multiple trade-off policies to balance UAV energy consumption, terminal battery levels, and computational resource allocation under various constraints, including limited UAV battery capacity, non-linear energy harvesting characteristics, and dynamic task arrivals. To address these challenges comprehensively, we formulate a bi-objective optimization problem that simultaneously considers system energy efficiency and terminal battery sustainability. We then reformulate this non-convex problem with a hybrid solution space as a Markov decision process (MDP) and propose an improved soft actor-critic (SAC) algorithm with an action simplification mechanism to enhance its convergence and generalization capabilities. Simulation results have demonstrated that our proposed approach outperforms various baselines in different scenarios, achieving efficient energy management while maintaining high computational performance. Furthermore, our method shows strong generalization ability across different scenarios, particularly in complex environments, validating the effectiveness of our designed boundary penalty and charging reward mechanisms.
Authors: Vansh Kapoor, Jayakrishnan Nair
Abstract: In many practical sequential decision-making problems, tracking the state of the environment incurs a sensing/communication/computation cost. In these settings, the agent's interaction with its environment includes the additional component of deciding $\textit{when}$ to sense the state, in a manner that balances the value associated with optimal (state-specific) actions and the cost of sensing. We formulate this as an expected discounted cost Markov Decision Process (MDP), wherein the agent incurs an additional cost for sensing its next state, but has the option to take actions while remaining 'blind' to the system state. We pose this problem as a classical discounted cost MDP with an expanded (countably infinite) state space. While computing the optimal policy for this MDP is intractable in general, we bound the sub-optimality gap associated with optimal policies in a restricted class, where the number of consecutive non-sensing (a.k.a., blind) actions is capped. We also design a computationally efficient heuristic algorithm based on policy improvement, which in practice performs close to the optimal policy. Finally, we benchmark against the state of the art via a numerical case study.
Authors: Zhou Wu, Junyi An, Baile Xu, Furao Shen, Jian Zhao
Abstract: Recently, the superior performance of Transformers has made them a more robust and scalable solution for sequence modeling than traditional recurrent neural networks (RNNs). However, the effectiveness of Transformer in capturing long-term dependencies is primarily attributed to their comprehensive pair-modeling process rather than inherent inductive biases toward sequence semantics. In this study, we explore the capabilities of pure RNNs and reassess their long-term learning mechanisms. Inspired by the physics energy transition models that track energy changes over time, we propose a effective recurrent structure called the``Physics-inspired Energy Transition Neural Network" (PETNN). We demonstrate that PETNN's memory mechanism effectively stores information over long-term dependencies. Experimental results indicate that PETNN outperforms transformer-based methods across various sequence tasks. Furthermore, owing to its recurrent nature, PETNN exhibits significantly lower complexity. Our study presents an optimal foundational recurrent architecture and highlights the potential for developing effective recurrent neural networks in fields currently dominated by Transformer.
Authors: Arthur Corr\^ea, Alexandre Jesus, Crist\'ov\~ao Silva, Samuel Moniz
Abstract: Recently, deep reinforcement learning has emerged as a promising approach for solving complex combinatorial optimization problems. Broadly, deep reinforcement learning methods fall into two categories: policy-based and value-based. While value-based approaches have achieved notable success in domains such as the Arcade Learning Environment, the combinatorial optimization community has predominantly favored policy-based methods, often overlooking the potential of value-based algorithms. In this work, we conduct a comprehensive empirical evaluation of value-based algorithms, including the deep q-network and several of its advanced extensions, within the context of two complex combinatorial problems: the job-shop and the flexible job-shop scheduling problems, two fundamental challenges with multiple industrial applications. Our results challenge the assumption that policy-based methods are inherently superior for combinatorial optimization. We show that several value-based approaches can match or even outperform the widely adopted proximal policy optimization algorithm, suggesting that value-based strategies deserve greater attention from the combinatorial optimization community. Our code is openly available at: https://github.com/AJ-Correa/Unraveling-the-Rainbow.
Authors: Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang
Abstract: Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, but still depend on manually curated collections of questions and answers for training. The scarcity of high-quality, human-produced examples raises concerns about the long-term scalability of relying on human supervision, a challenge already evident in the domain of language model pretraining. Furthermore, in a hypothetical future where AI surpasses human intelligence, tasks provided by humans may offer limited learning potential for a superintelligent system. To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding and mathematical reasoning tasks, outperforming existing zero-setting models that rely on tens of thousands of in-domain human-curated examples. Furthermore, we demonstrate that AZR can be effectively applied across different model scales and is compatible with various model classes.
Authors: Stef De Sabbata, Stefano Mizzaro, Kevin Roitero
Abstract: Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their deployment as knowledge bases and "reasoning" tools remains an area of ongoing research. In geography, a growing body of literature has been focusing on evaluating LLMs' geographical knowledge and their ability to perform spatial reasoning. However, very little is still known about the internal functioning of these models, especially about how they process geographical information. In this chapter, we establish a novel framework for the study of geospatial mechanistic interpretability - using spatial analysis to reverse engineer how LLMs handle geographical information. Our aim is to advance our understanding of the internal representations that these complex models generate while processing geographical information - what one might call "how LLMs think about geographic information" if such phrasing was not an undue anthropomorphism. We first outline the use of probing in revealing internal structures within LLMs. We then introduce the field of mechanistic interpretability, discussing the superposition hypothesis and the role of sparse autoencoders in disentangling polysemantic internal representations of LLMs into more interpretable, monosemantic features. In our experiments, we use spatial autocorrelation to show how features obtained for placenames display spatial patterns related to their geographic location and can thus be interpreted geospatially, providing insights into how these models process geographical information. We conclude by discussing how our framework can help shape the study and use of foundation models in geography.
Authors: Hanyu Hu, Xiaoming Yuan
Abstract: The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer from performance degradation, reliance on heuristic metrics, or expensive finetuning. To address these challenges, we propose SPAP (Structured Pruning via Alternating Optimization and Penalty Methods), a novel and efficient structured pruning framework for LLMs grounded in optimization theory. SPAP formulates the pruning problem through a mixed-integer optimization model, employs a penalty method that effectively makes pruning decisions to minimize pruning errors, and introduces an alternating minimization algorithm tailored to the splittable problem structure for efficient weight updates and performance recovery. Extensive experiments on OPT, LLaMA-3/3.1/3.2, and Qwen2.5 models demonstrate SPAP's superiority over state-of-the-art methods, delivering linear inference speedups (1.29$\times$ at 30% sparsity) and proportional memory reductions. Our work offers a practical, optimization-driven solution for pruning LLMs while preserving model performance.
Authors: Matthias H\"ofler, Francesco Regazzoni, Stefano Pagani, Elias Karabelas, Christoph Augustin, Gundolf Haase, Gernot Plank, Federica Caforio
Abstract: Active stress models in cardiac biomechanics account for the mechanical deformation caused by muscle activity, thus providing a link between the electrophysiological and mechanical properties of the tissue. The accurate assessment of active stress parameters is fundamental for a precise understanding of myocardial function but remains difficult to achieve in a clinical setting, especially when only displacement and strain data from medical imaging modalities are available. This work investigates, through an in-silico study, the application of physics-informed neural networks (PINNs) for inferring active contractility parameters in time-dependent cardiac biomechanical models from these types of imaging data. In particular, by parametrising the sought state and parameter field with two neural networks, respectively, and formulating an energy minimisation problem to search for the optimal network parameters, we are able to reconstruct in various settings active stress fields in the presence of noise and with a high spatial resolution. To this end, we also advance the vanilla PINN learning algorithm with the use of adaptive weighting schemes, ad-hoc regularisation strategies, Fourier features, and suitable network architectures. In addition, we thoroughly analyse the influence of the loss weights in the reconstruction of active stress parameters. Finally, we apply the method to the characterisation of tissue inhomogeneities and detection of fibrotic scars in myocardial tissue. This approach opens a new pathway to significantly improve the diagnosis, treatment planning, and management of heart conditions associated with cardiac fibrosis.
Authors: Diego Perazzolo, Pietro Fanton, Ilaria Barison, Marny Fedrigo, Annalisa Angelini, Chiara Castellani, Enrico Grisan
Abstract: Given the increasing complexity of omics datasets, a key challenge is not only improving classification performance but also enhancing the transparency and reliability of model decisions. Effective model performance and feature selection are fundamental for explainability and reliability. In many cases, high dimensional omics datasets suffer from limited number of samples due to clinical constraints, patient conditions, phenotypes rarity and others conditions. Current omics based classification models often suffer from narrow interpretability, making it difficult to discern meaningful insights where trust and reproducibility are critical. This study presents a machine learning based classification framework that integrates feature selection with data augmentation techniques to achieve high standard classification accuracy while ensuring better interpretability. Using the publicly available dataset (E MTAB 8026), we explore a bootstrap analysis in six binary classification scenarios to evaluate the proposed model's behaviour. We show that the proposed pipeline yields cross validated perfomance on small dataset that is conserved when the trained classifier is applied to a larger test set. Our findings emphasize the fundamental balance between accuracy and feature selection, highlighting the positive effect of introducing synthetic data for better generalization, even in scenarios with very limited samples availability.
Authors: Zhengqin Yang, Di Wu, Jia Chen, Xin Luo
Abstract: Concept Factorization (CF) models have attracted widespread attention due to their excellent performance in data clustering. In recent years, many variant models based on CF have achieved great success in clustering by taking into account the internal geometric manifold structure of the dataset and using graph regularization techniques. However, their clustering performance depends greatly on the construction of the initial graph structure. In order to enable adaptive learning of the graph structure of the data, we propose a Concept Factorization Based on Self-Representation and Adaptive Graph Structure Learning (CFSRAG) Model. CFSRAG learns the affinity relationship between data through a self-representation method, and uses the learned affinity matrix to implement dynamic graph regularization constraints, thereby ensuring dynamic learning of the internal geometric structure of the data. Finally, we give the CFSRAG update rule and convergence analysis, and conduct comparative experiments on four real datasets. The results show that our model outperforms other state-of-the-art models.
Authors: Saleh Zare Zade, Yao Qiang, Xiangyu Zhou, Hui Zhu, Mohammad Amin Roshani, Prashant Khanduri, Dongxiao Zhu
Abstract: Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, existing methods often misinfer non-members as members, leading to a high false positive rate, or depend on additional reference models for probability calibration, which limits their practicality. To overcome these challenges, we introduce a novel framework called Automatic Calibration Membership Inference Attack (ACMIA), which utilizes a tunable temperature to calibrate output probabilities effectively. This approach is inspired by our theoretical insights into maximum likelihood estimation during the pre-training of LLMs. We introduce ACMIA in three configurations designed to accommodate different levels of model access and increase the probability gap between members and non-members, improving the reliability and robustness of membership inference. Extensive experiments on various open-source LLMs demonstrate that our proposed attack is highly effective, robust, and generalizable, surpassing state-of-the-art baselines across three widely used benchmarks. Our code is available at: \href{https://github.com/Salehzz/ACMIA}{\textcolor{blue}{Github}}.
Authors: Lena Stempfle, Anton Matsson, Newton Mwai, Fredrik D. Johansson
Abstract: Handling missing values at test time is challenging for machine learning models, especially when aiming for both high accuracy and interpretability. Established approaches often add bias through imputation or excessive model complexity via missingness indicators. Moreover, either method can obscure interpretability, making it harder to understand how the model utilizes the observed variables in predictions. We propose missingness-avoiding (MA) machine learning, a general framework for training models to rarely require the values of missing (or imputed) features at test time. We create tailored MA learning algorithms for decision trees, tree ensembles, and sparse linear models by incorporating classifier-specific regularization terms in their learning objectives. The tree-based models leverage contextual missingness by reducing reliance on missing values based on the observed context. Experiments on real-world datasets demonstrate that MA-DT, MA-LASSO, MA-RF, and MA-GBT effectively reduce the reliance on features with missing values while maintaining predictive performance competitive with their unregularized counterparts. This shows that our framework gives practitioners a powerful tool to maintain interpretability in predictions with test-time missing values.
Authors: Da Zheng, Lun Du, Junwei Su, Yuchen Tian, Yuqi Zhu, Jintian Zhang, Lanning Wei, Ningyu Zhang, Huajun Chen
Abstract: Problem-solving has been a fundamental driver of human progress in numerous domains. With advancements in artificial intelligence, Large Language Models (LLMs) have emerged as powerful tools capable of tackling complex problems across diverse domains. Unlike traditional computational systems, LLMs combine raw computational power with an approximation of human reasoning, allowing them to generate solutions, make inferences, and even leverage external computational tools. However, applying LLMs to real-world problem-solving presents significant challenges, including multi-step reasoning, domain knowledge integration, and result verification. This survey explores the capabilities and limitations of LLMs in complex problem-solving, examining techniques including Chain-of-Thought (CoT) reasoning, knowledge augmentation, and various LLM-based and tool-based verification techniques. Additionally, we highlight domain-specific challenges in various domains, such as software engineering, mathematical reasoning and proving, data analysis and modeling, and scientific research. The paper further discusses the fundamental limitations of the current LLM solutions and the future directions of LLM-based complex problems solving from the perspective of multi-step reasoning, domain knowledge integration and result verification.
Authors: Kirill Lukyanov, Mikhail Drobyshevskiy, Georgii Sazonov, Mikhail Soloviov, Ilya Makarov
Abstract: The growing need for Trusted AI (TAI) highlights the importance of interpretability and robustness in machine learning models. However, many existing tools overlook graph data and rarely combine these two aspects into a single solution. Graph Neural Networks (GNNs) have become a popular approach, achieving top results across various tasks. We introduce GNN-AID (Graph Neural Network Analysis, Interpretation, and Defense), an open-source framework designed for graph data to address this gap. Built as a Python library, GNN-AID supports advanced trust methods and architectural layers, allowing users to analyze graph datasets and GNN behavior using attacks, defenses, and interpretability methods. GNN-AID is built on PyTorch-Geometric, offering preloaded datasets, models, and support for any GNNs through customizable interfaces. It also includes a web interface with tools for graph visualization and no-code features like an interactive model builder, simplifying the exploration and analysis of GNNs. The framework also supports MLOps techniques, ensuring reproducibility and result versioning to track and revisit analyses efficiently. GNN-AID is a flexible tool for developers and researchers. It helps developers create, analyze, and customize graph models, while also providing access to prebuilt datasets and models for quick experimentation. Researchers can use the framework to explore advanced topics on the relationship between interpretability and robustness, test defense strategies, and combine methods to protect against different types of attacks. We also show how defenses against evasion and poisoning attacks can conflict when applied to graph data, highlighting the complex connections between defense strategies. GNN-AID is available at \href{https://github.com/ispras/GNN-AID}{github.com/ispras/GNN-AID}
Authors: Stefano Bruno, Sotirios Sabanis
Abstract: Score-based Generative Models (SGMs) approximate a data distribution by perturbing it with Gaussian noise and subsequently denoising it via a learned reverse diffusion process. These models excel at modeling complex data distributions and generating diverse samples, achieving state-of-the-art performance across domains such as computer vision, audio generation, reinforcement learning, and computational biology. Despite their empirical success, existing Wasserstein-2 convergence analysis typically assume strong regularity conditions-such as smoothness or strict log-concavity of the data distribution-that are rarely satisfied in practice. In this work, we establish the first non-asymptotic Wasserstein-2 convergence guarantees for SGMs targeting semiconvex distributions with potentially discontinuous gradients. Our upper bounds are explicit and sharp in key parameters, achieving optimal dependence of $O(\sqrt{d})$ on the data dimension $d$ and convergence rate of order one. The framework accommodates a wide class of practically relevant distributions, including symmetric modified half-normal distributions, Gaussian mixtures, double-well potentials, and elastic net potentials. By leveraging semiconvexity without requiring smoothness assumptions on the potential such as differentiability, our results substantially broaden the theoretical foundations of SGMs, bridging the gap between empirical success and rigorous guarantees in non-smooth, complex data regimes.
Authors: Faiz Taleb, Ivan Gazeau, Maryline Laurent
Abstract: Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM) algorithm. The LBRM method leverages a reference model to enhance the accuracy of membership inference attacks, distinguishing between training and test data. Our contributions are twofold: first, we propose an innovative method to effectively extract and identify memorized training data, significantly improving detection accuracy. On average, without fine-tuning, the AUROC improved by approximately 40\%. With fine-tuning, the AUROC increased by approximately 60\%. Second, we validate our approach through membership inference attacks on two types of architectures designed for time series imputation, demonstrating the robustness and versatility of the LBRM approach in different contexts. These results highlight the significant enhancement in detection accuracy provided by the LBRM approach, addressing privacy risks in time series imputation models.
Authors: Pablo G\'omez, David O'Ryan
Abstract: Anomaly detection in large datasets is essential in fields such as astronomy and computer vision; however, supervised methods typically require extensive anomaly labelling, which is often impractical. We present AnomalyMatch, an anomaly detection framework combining the semi-supervised FixMatch algorithm using EfficientNet classifiers with active learning. By treating anomaly detection as a semi-supervised binary classification problem, we efficiently utilise limited labelled and abundant unlabelled images. We allow iterative model refinement in a user interface for expert verification of high-confidence anomalies and correction of false positives. Built for astronomical data, AnomalyMatch generalises readily to other domains facing similar data challenges. Evaluations on the GalaxyMNIST astronomical dataset and the miniImageNet natural-image benchmark under severe class imbalance (1% anomalies for miniImageNet) display strong performance: starting from five to ten labelled anomalies and after three active learning cycles, we achieve an average AUROC of 0.95 (miniImageNet) and 0.86 (GalaxyMNIST), with respective AUPRC of 0.77 and 0.71. After active learning cycles, anomalies are ranked with 71% (miniImageNet) to 93% precision in the 1% of the highest-ranked images. AnomalyMatch is tailored for large-scale applications, efficiently processing predictions for 100 million images within three days on a single GPU. Integrated into ESAs Datalabs platform, AnomalyMatch facilitates targeted discovery of scientifically valuable anomalies in vast astronomical datasets. Our results underscore the exceptional utility and scalability of this approach for anomaly discovery, highlighting the value of specialised approaches for domains characterised by severe label scarcity.
Authors: Sy-Tuyen Ho, Koh Jun Hao, Ngoc-Bao Nguyen, Alexander Binder, Ngai-Man Cheung
Abstract: Model Inversion (MI) attacks aim to reconstruct information of private training data by exploiting access to machine learning models. The most common evaluation framework for MI attacks/defenses relies on an evaluation model that has been utilized to assess progress across almost all MI attacks and defenses proposed in recent years. In this paper, for the first time, we present an in-depth study of MI evaluation. Firstly, we construct the first comprehensive human-annotated dataset of MI attack samples, based on 28 setups of different MI attacks, defenses, private and public datasets. Secondly, using our dataset, we examine the accuracy of the MI evaluation framework and reveal that it suffers from a significant number of false positives. These findings raise questions about the previously reported success rates of SOTA MI attacks. Thirdly, we analyze the causes of these false positives, design controlled experiments, and discover the surprising effect of Type I adversarial features on MI evaluation, as well as adversarial transferability, highlighting a relationship between two previously distinct research areas. Our findings suggest that the performance of SOTA MI attacks has been overestimated, with the actual privacy leakage being significantly less than previously reported. In conclusion, we highlight critical limitations in the widely used MI evaluation framework and present our methods to mitigate false positive rates. We remark that prior research has shown that Type I adversarial attacks are very challenging, with no existing solution. Therefore, we urge to consider human evaluation as a primary MI evaluation framework rather than merely a supplement as in previous MI research. We also encourage further work on developing more robust and reliable automatic evaluation frameworks.
Authors: Dip Roy
Abstract: Mechanistic interpretability of deep learning models has emerged as a crucial research direction for understanding the functioning of neural networks. While significant progress has been made in interpreting discriminative models like transformers, understanding generative models such as Variational Autoencoders (VAEs) remains challenging. This paper introduces a comprehensive causal intervention framework for mechanistic interpretability of VAEs. We develop techniques to identify and analyze "circuit motifs" in VAEs, examining how semantic factors are encoded, processed, and disentangled through the network layers. Our approach uses targeted interventions at different levels: input manipulations, latent space perturbations, activation patching, and causal mediation analysis. We apply our framework to both synthetic datasets with known causal relationships and standard disentanglement benchmarks. Results show that our interventions can successfully isolate functional circuits, map computational graphs to causal graphs of semantic factors, and distinguish between polysemantic and monosemantic units. Furthermore, we introduce metrics for causal effect strength, intervention specificity, and circuit modularity that quantify the interpretability of VAE components. Experimental results demonstrate clear differences between VAE variants, with FactorVAE achieving higher disentanglement scores (0.084) and effect strengths (mean 4.59) compared to standard VAE (0.064, 3.99) and Beta-VAE (0.051, 3.43). Our framework advances the mechanistic understanding of generative models and provides tools for more transparent and controllable VAE architectures.
Authors: Jiacheng Wang, Le Liang, Hao Ye, Chongtao Guo, Shi Jin
Abstract: Judicious resource allocation can effectively enhance federated learning (FL) training performance in wireless networks by addressing both system and statistical heterogeneity. However, existing strategies typically rely on block fading assumptions, which overlooks rapid channel fluctuations within each round of FL gradient uploading, leading to a degradation in FL training performance. Therefore, this paper proposes a small-scale-fading-aware resource allocation strategy using a multi-agent reinforcement learning (MARL) framework. Specifically, we establish a one-step convergence bound of the FL algorithm and formulate the resource allocation problem as a decentralized partially observable Markov decision process (Dec-POMDP), which is subsequently solved using the QMIX algorithm. In our framework, each client serves as an agent that dynamically determines spectrum and power allocations within each coherence time slot, based on local observations and a reward derived from the convergence analysis. The MARL setting reduces the dimensionality of the action space and facilitates decentralized decision-making, enhancing the scalability and practicality of the solution. Experimental results demonstrate that our QMIX-based resource allocation strategy significantly outperforms baseline methods across various degrees of statistical heterogeneity. Additionally, ablation studies validate the critical importance of incorporating small-scale fading dynamics, highlighting its role in optimizing FL performance.
Authors: Linus Langenkamp, Philip Hannebohm, Bernhard Bachmann
Abstract: We propose a novel approach for training Physics-enhanced Neural ODEs (PeNODEs) by expressing the training process as a dynamic optimization problem. The full model, including neural components, is discretized using a high-order implicit Runge-Kutta method with flipped Legendre-Gauss-Radau points, resulting in a large-scale nonlinear program (NLP) efficiently solved by state-of-the-art NLP solvers such as Ipopt. This formulation enables simultaneous optimization of network parameters and state trajectories, addressing key limitations of ODE solver-based training in terms of stability, runtime, and accuracy. Extending on a recent direct collocation-based method for Neural ODEs, we generalize to PeNODEs, incorporate physical constraints, and present a custom, parallelized, open-source implementation. Benchmarks on a Quarter Vehicle Model and a Van-der-Pol oscillator demonstrate superior accuracy, speed, and generalization with smaller networks compared to other training techniques. We also outline a planned integration into OpenModelica to enable accessible training of Neural DAEs.
Authors: Simon Baeuerle, Ian F. Mendonca, Kristof Van Laerhoven, Ralf Mikut, Andreas Steimer
Abstract: Coverage Path Planning of Thermal Interface Materials (TIM) plays a crucial role in the design of power electronics and electronic control units. Up to now, this is done manually by experts or by using optimization approaches with a high computational effort. We propose a novel AI-based approach to generate dispense paths for TIM and similar dispensing applications. It is a drop-in replacement for optimization-based approaches. An Artificial Neural Network (ANN) receives the target cooling area as input and directly outputs the dispense path. Our proposed setup does not require labels and we show its feasibility on multiple target areas. The resulting dispense paths can be directly transferred to automated manufacturing equipment and do not exhibit air entrapments. The approach of using an ANN to predict process parameters for a desired target state in real-time could potentially be transferred to other manufacturing processes.
Authors: Leo Maxime Brunswic, Mateo Clemente, Rui Heng Yang, Adam Sigal, Amir Rasouli, Yinchuan Li
Abstract: Generative Flow Networks (GFNs) were initially introduced on directed acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical framework for generative methods allowing more flexibility and enhancing application range. However, many challenges remain in training GFNs in continuous settings and for imitation learning (IL), including intractability of flow-matching loss, limited tests of non-acyclic training, and the need for a separate reward model in imitation learning. The present work proposes a family of generative flows called Ergodic Generative Flows (EGFs) which are used to address the aforementioned issues. First, we leverage ergodicity to build simple generative flows with finitely many globally defined transformations (diffeomorphisms) with universality guarantees and tractable flow-matching loss (FM loss). Second, we introduce a new loss involving cross-entropy coupled to weak flow-matching control, coined KL-weakFM loss. It is designed for IL training without a separate reward model. We evaluate IL-EGFs on toy 2D tasks and real-world datasets from NASA on the sphere, using the KL-weakFM loss. Additionally, we conduct toy 2D reinforcement learning experiments with a target reward, using the FM loss.
Authors: Sidharth S. Menon, Ameya D. Jagtap
Abstract: High-dimensional partial differential equations (PDEs) arise in diverse scientific and engineering applications but remain computationally intractable due to the curse of dimensionality. Traditional numerical methods struggle with the exponential growth in computational complexity, particularly on hypercubic domains, where the number of required collocation points increases rapidly with dimensionality. Here, we introduce Anant-Net, an efficient neural surrogate that overcomes this challenge, enabling the solution of PDEs in high dimensions. Unlike hyperspheres, where the internal volume diminishes as dimensionality increases, hypercubes retain or expand their volume (for unit or larger length), making high-dimensional computations significantly more demanding. Anant-Net efficiently incorporates high-dimensional boundary conditions and minimizes the PDE residual at high-dimensional collocation points. To enhance interpretability, we integrate Kolmogorov-Arnold networks into the Anant-Net architecture. We benchmark Anant-Net's performance on several linear and nonlinear high-dimensional equations, including the Poisson, Sine-Gordon, and Allen-Cahn equations, demonstrating high accuracy and robustness across randomly sampled test points from high-dimensional space. Importantly, Anant-Net achieves these results with remarkable efficiency, solving 300-dimensional problems on a single GPU within a few hours. We also compare Anant-Net's results for accuracy and runtime with other state-of-the-art methods. Our findings establish Anant-Net as an accurate, interpretable, and scalable framework for efficiently solving high-dimensional PDEs.
Authors: Thien Nhan Vo, Thanh Xuan Truong
Abstract: We evaluate the effectiveness of importance weighting in deep neural networks under label shift and covariate shift. On synthetic 2D data (linearly separable and moon-shaped) using logistic regression and MLPs, we observe that weighting strongly affects decision boundaries early in training but fades with prolonged optimization. On CIFAR-10 with various class imbalances, only L2 regularization (not dropout) helps preserve weighting effects. In a covariate-shift experiment, importance weighting yields no significant performance gain, highlighting challenges on complex data. Our results call into question the practical utility of importance weighting for real-world distribution shifts.
Authors: Chethan Krishnamurthy Ramanaik, Arjun Roy, Eirini Ntoutsi
Abstract: Despite the extensive use of deep autoencoders (AEs) in critical applications, their adversarial robustness remains relatively underexplored compared to classification models. AE robustness is characterized by the Lipschitz bounds of its components. Existing robustness evaluation frameworks based on white-box attacks do not fully exploit the vulnerabilities of intermediate ill-conditioned layers in AEs. In the context of optimizing imperceptible norm-bounded additive perturbations to maximize output damage, existing methods struggle to effectively propagate adversarial loss gradients throughout the network, often converging to less effective perturbations. To address this, we propose a novel layer-conditioning-based adversarial optimization objective that effectively guides the adversarial map toward regions of local Lipschitz bounds by enhancing loss gradient information propagation during attack optimization. We demonstrate through extensive experiments on state-of-the-art AEs that our adversarial objective results in stronger attacks, outperforming existing methods in both universal and sample-specific scenarios. As a defense method against this attack, we introduce an inference-time adversarially trained defense plugin that mitigates the effects of adversarial examples.
Authors: Yihang Wang, Chris Chi, Aaron R. Dinner
Abstract: Normalizing flows (NFs) provide uncorrelated samples from complex distributions, making them an appealing tool for parameter estimation. However, the practical utility of NFs remains limited by their tendency to collapse to a single mode of a multimodal distribution. In this study, we show that annealing with an adaptive schedule based on the effective sample size (ESS) can mitigate mode collapse. We demonstrate that our approach can converge the marginal likelihood for a biochemical oscillator model fit to time-series data in ten-fold less computation time than a widely used ensemble Markov chain Monte Carlo (MCMC) method. We show that the ESS can also be used to reduce variance by pruning the samples. We expect these developments to be of general use for sampling with NFs and discuss potential opportunities for further improvements.
Authors: Emanuele Zappala, Alice Giola, Andreas Kramer, Enrico Greco
Abstract: Deep learning has shown high performance on spectroscopic inverse problems when sufficient data is available. However, it is often the case that data in spectroscopy is scarce, and this usually causes severe overfitting problems with deep learning methods. Traditional machine learning methods are viable when datasets are smaller, but the accuracy and applicability of these methods is generally more limited. We introduce a deep learning method for classification of molecular spectra based on learning integral operators via integral equations of the first kind, which results in an algorithm that is less affected by overfitting issues on small datasets, compared to other deep learning models. The problem formulation of the deep learning approach is based on inverse problems, which have traditionally found important applications in spectroscopy. We perform experiments on real world data to showcase our algorithm. It is seen that the model outperforms traditional machine learning approaches such as decision tree and support vector machine, and for small datasets it outperforms other deep learning models. Therefore, our methodology leverages the power of deep learning, still maintaining the performance when the available data is very limited, which is one of the main issues that deep learning faces in spectroscopy, where datasets are often times of small size.
Authors: Deming Sheng, Ricardo Henao
Abstract: Probabilistic survival analysis models seek to estimate the distribution of the future occurrence (time) of an event given a set of covariates. In recent years, these models have preferred nonparametric specifications that avoid directly estimating survival distributions via discretization. Specifically, they estimate the probability of an individual event at fixed times or the time of an event at fixed probabilities (quantiles), using supervised learning. Borrowing ideas from the quantile regression literature, we propose a parametric survival analysis method based on the Asymmetric Laplace Distribution (ALD). This distribution allows for closed-form calculation of popular event summaries such as mean, median, mode, variation, and quantiles. The model is optimized by maximum likelihood to learn, at the individual level, the parameters (location, scale, and asymmetry) of the ALD distribution. Extensive results on synthetic and real-world data demonstrate that the proposed method outperforms parametric and nonparametric approaches in terms of accuracy, discrimination and calibration.
Authors: Dian Chen, Zelin Wan, Dong Sam Ha, Jin-Hee Cho
Abstract: Solar sensor-based monitoring systems have become a crucial agricultural innovation, advancing farm management and animal welfare through integrating sensor technology, Internet-of-Things, and edge and cloud computing. However, the resilience of these systems to cyber-attacks and their adaptability to dynamic and constrained energy supplies remain largely unexplored. To address these challenges, we propose a sustainable smart farm network designed to maintain high-quality animal monitoring under various cyber and adversarial threats, as well as fluctuating energy conditions. Our approach utilizes deep reinforcement learning (DRL) to devise optimal policies that maximize both monitoring effectiveness and energy efficiency. To overcome DRL's inherent challenge of slow convergence, we integrate transfer learning (TL) and decision theory (DT) to accelerate the learning process. By incorporating DT-guided strategies, we optimize monitoring quality and energy sustainability, significantly reducing training time while achieving comparable performance rewards. Our experimental results prove that DT-guided DRL outperforms TL-enhanced DRL models, improving system performance and reducing training runtime by 47.5%.
Authors: Zhikai Wang, Yanyan Shen, Zibin Zhang, Kangyi Lin
Abstract: Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new incremental data and a subset of historical data. However, the feature embeddings of a CTR prediction model often get stale when the corresponding features do not appear in current incremental data. In the next period, the model would have a performance degradation on samples containing stale features, which we call the feature staleness problem. To mitigate this problem, we propose a Feature Staleness Aware Incremental Learning method for CTR prediction (FeSAIL) which adaptively replays samples containing stale features. We first introduce a staleness aware sampling algorithm (SAS) to sample a fixed number of stale samples with high sampling efficiency. We then introduce a staleness aware regularization mechanism (SAR) for a fine-grained control of the feature embedding updating. We instantiate FeSAIL with a general deep learning-based CTR prediction model and the experimental results demonstrate FeSAIL outperforms various state-of-the-art methods on four benchmark datasets.
Authors: Cheng Ge, Han-Shen Tae, Zhenqiang Zhang, Lu Lu, Zhijie Huang, Yilin Wang, Tao Jiang, Wenqing Cai, Shan Chang, David J. Adams, Rilei Yu
Abstract: Target-specific peptides, such as conotoxins, exhibit exceptional binding affinity and selectivity toward ion channels and receptors. However, their therapeutic potential remains underutilized due to the limited diversity of natural variants and the labor-intensive nature of traditional optimization strategies. Here, we present CreoPep, a deep learning-based conditional generative framework that integrates masked language modeling with a progressive masking scheme to design high-affinity peptide mutants while uncovering novel structural motifs. CreoPep employs an integrative augmentation pipeline, combining FoldX-based energy screening with temperature-controlled multinomial sampling, to generate structurally and functionally diverse peptides that retain key pharmacological properties. We validate this approach by designing conotoxin inhibitors targeting the $\alpha$7 nicotinic acetylcholine receptor, achieving submicromolar potency in electrophysiological assays. Structural analysis reveals that CreoPep-generated variants engage in both conserved and novel binding modes, including disulfide-deficient forms, thus expanding beyond conventional design paradigms. Overall, CreoPep offers a robust and generalizable platform that bridges computational peptide design with experimental validation, accelerating the discovery of next-generation peptide therapeutics.
Authors: Fernando Vallecillos Ruiz, Max Hort, Leon Moonen
Abstract: Automatic program repair (APR) aims to reduce the manual efforts required to identify and fix errors in source code. Before the rise of LLM-based agents, a common strategy was to increase the number of generated patches, sometimes to the thousands, to achieve better repair results on benchmarks. More recently, self-iterative capabilities enabled LLMs to refine patches over multiple rounds guided by feedback. However, literature often focuses on many iterations and disregards different numbers of outputs. We investigate an APR pipeline that balances these two approaches, the generation of multiple outputs and multiple rounds of iteration, while imposing a limit of 10 total patches per bug. We apply three SOTA instruction-tuned LLMs - DeepSeekCoder-Instruct, Codellama-Instruct, Llama3.1-Instruct - to the APR task. We further fine-tune each model on an APR dataset with three sizes (1K, 30K, 65K) and two techniques (Full Fine-Tuning and LoRA), allowing us to assess their repair capabilities on two APR benchmarks: HumanEval-Java and Defects4J. Our results show that by using only a fraction (<1%) of the fine-tuning dataset, we can achieve improvements of up to 78% in the number of plausible patches generated, challenging prior studies that reported limited gains using Full Fine-Tuning. However, we find that exceeding certain thresholds leads to diminishing outcomes, likely due to overfitting. Moreover, we show that base models greatly benefit from creating patches in an iterative fashion rather than generating them all at once. In addition, the benefit of iterative strategies becomes more pronounced in complex benchmarks. Even fine-tuned models, while benefiting less from iterations, still gain advantages, particularly on complex benchmarks. The research underscores the need for balanced APR strategies that combine multi-output generation and iterative refinement.
Authors: Fabrizio Marozzo
Abstract: Generative AI systems have revolutionized human interaction by enabling natural language-based coding and problem solving. However, the inherent ambiguity of natural language often leads to imprecise instructions, forcing users to iteratively test, correct, and resubmit their prompts. We propose an iterative approach that systematically narrows down these ambiguities through a structured series of clarification questions and alternative solution proposals, illustrated with input/output examples as well. Once every uncertainty is resolved, a final, precise solution is generated. Evaluated on a diverse dataset spanning coding, data analysis, and creative writing, our method demonstrates superior accuracy, competitive resolution times, and higher user satisfaction compared to conventional one-shot solutions, which typically require multiple manual iterations to achieve a correct output.
Authors: Rohan Ghuge, Sahil Singla, Yifan Wang
Abstract: Online Resource Allocation problem is a central problem in many areas of Computer Science, Operations Research, and Economics. In this problem, we sequentially receive $n$ stochastic requests for $m$ kinds of shared resources, where each request can be satisfied in multiple ways, consuming different amounts of resources and generating different values. The goal is to achieve a $(1-\epsilon)$-approximation to the hindsight optimum, where $\epsilon>0$ is a small constant, assuming each resource has a large budget. In this paper, we investigate the learnability and robustness of online resource allocation. Our primary contribution is a novel Exponential Pricing algorithm with the following properties: 1. It requires only a \emph{single sample} from each of the $n$ request distributions to achieve a $(1-\epsilon)$-approximation for online resource allocation with large budgets. Such an algorithm was previously unknown, even with access to polynomially many samples, as prior work either assumed full distributional knowledge or was limited to i.i.d.\,or random-order arrivals. 2. It is robust to corruptions in the outliers model and the value augmentation model. Specifically, it maintains its $(1 - \epsilon)$-approximation guarantee under both these robustness models, resolving the open question posed in Argue, Gupta, Molinaro, and Singla (SODA'22). 3. It operates as a simple item-pricing algorithm that ensures incentive compatibility. The intuition behind our Exponential Pricing algorithm is that the price of a resource should adjust exponentially as it is overused or underused. It differs from conventional approaches that use an online learning algorithm for item pricing. This departure guarantees that the algorithm will never run out of any resource, but loses the usual no-regret properties of online learning algorithms, necessitating a new analytical approach.
Authors: Aoran Chen, Yang Feng
Abstract: Multi-Task Learning (MTL) seeks to boost statistical power and learning efficiency by discovering structure shared across related tasks. State-of-the-art MTL representation methods, however, usually treat the latent representation matrix as a point in ordinary Euclidean space, ignoring its often non-Euclidean geometry, thus sacrificing robustness when tasks are heterogeneous or even adversarial. We propose GeoERM, a geometry-aware MTL framework that embeds the shared representation on its natural Riemannian manifold and optimizes it via explicit manifold operations. Each training cycle performs (i) a Riemannian gradient step that respects the intrinsic curvature of the search space, followed by (ii) an efficient polar retraction to remain on the manifold, guaranteeing geometric fidelity at every iteration. The procedure applies to a broad class of matrix-factorized MTL models and retains the same per-iteration cost as Euclidean baselines. Across a set of synthetic experiments with task heterogeneity and on a wearable-sensor activity-recognition benchmark, GeoERM consistently improves estimation accuracy, reduces negative transfer, and remains stable under adversarial label noise, outperforming leading MTL and single-task alternatives.
Authors: Ruiyue Huang, Claire E. Heaney, Maarten van Reeuwijk
Abstract: The Neural Networks for Partial Differential Equations (NN4PDEs) approach is used to determine the parameters of a simple land-surface model using PyTorch's backpropagation engine. In order to test the inverse model, a synthetic dataset is created by running the model in forward mode with known parameter values to create soil temperature time series that can be used as observations for the inverse model. We show that it is not possible to obtain a reliable parameter estimation using a single observed soil temperature time series. Using measurements at two depths, reliable parameter estimates can be obtained although it is not possible to differentiate between latent and sensible heat fluxes. We apply the inverse model to urban flux tower data in Phoenix, United States, and show that the thermal conductivity, volumetric heat capacity, and the combined sensible-latent heat transfer coefficient can be reliably estimated using an observed value for the effective surface albedo. The resulting model accurately predicts the outgoing longwave radiation, conductive soil fluxes and the combined sensible-latent heat fluxes.
Authors: Yifan Chen
Abstract: We introduce some new affine invariant ensemble samplers that are easy to construct and improve upon existing widely used algorithms, especially for high-dimensional problems. Specifically, we propose a derivative-free ensemble side move sampler that performs favorably compared to popular samplers in the \texttt{emcee} package. Additionally, we develop a class of derivative-based ensemble Hamiltonian Monte Carlo (HMC) samplers with affine invariance, which outperform standard HMC without affine invariance when sampling highly skewed distributions. We provide asymptotic scaling analysis for high-dimensional Gaussian targets to further elucidate the properties of these affine invariant ensemble samplers. In particular, with derivative information, the affine invariant ensemble HMC can scale much better with dimension compared to derivative-free ensemble samplers.
Authors: Daniel Goldstein, Eric Alcaide, Janna Lu, Eugene Cheah
Abstract: We present Rapid Attention Distillation to Linear Attention Decoders at Scale (RADLADS), a protocol for rapidly converting softmax attention transformers into linear attention decoder models, along with two new RWKV-variant architectures, and models converted from popular Qwen2.5 open source models in 7B, 32B, and 72B sizes. Our conversion process requires only 350-700M tokens, less than 0.005% of the token count used to train the original teacher models. Converting to our 72B linear attention model costs less than \$2,000 USD at today's prices, yet quality at inference remains close to the original transformer. These models achieve state-of-the-art downstream performance across a set of standard benchmarks for linear attention models of their size. We release all our models on HuggingFace under the Apache 2.0 license, with the exception of our 72B models which are also governed by the Qwen License Agreement. Models at https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102 Training Code at https://github.com/recursal/RADLADS-paper
URLs: https://huggingface.co/collections/recursal/radlads-6818ee69e99e729ba8a87102, https://github.com/recursal/RADLADS-paper
Authors: Sweta Rai, Douglas W. Nychka, Soutir Bandyopadhyay
Abstract: Data derived from remote sensing or numerical simulations often have a regular gridded structure and are large in volume, making it challenging to find accurate spatial models that can fill in missing grid cells or simulate the process effectively, especially in the presence of spatial heterogeneity and heavy-tailed marginal distributions. To overcome this issue, we present a spatial autoregressive modeling framework, which maps observations at a location and its neighbors to independent random variables. This is a highly flexible modeling approach and well-suited for non-Gaussian fields, providing simpler interpretability. In particular, we consider the SAR model with Generalized Extreme Value distribution innovations to combine the observation at a central grid location with its neighbors, capturing extreme spatial behavior based on the heavy-tailed innovations. While these models are fast to simulate by exploiting the sparsity of the key matrices in the computations, the maximum likelihood estimation of the parameters is prohibitive due to the intractability of the likelihood, making optimization challenging. To overcome this, we train a convolutional neural network on a large training set that covers a useful parameter space, and then use the trained network for fast parameter estimation. Finally, we apply this model to analyze annual maximum precipitation data from ERA-Interim-driven Weather Research and Forecasting (WRF) simulations, allowing us to explore its spatial extreme behavior across North America.
Authors: Ryan Wang, Matthew Finlayson, Luca Soldaini, Swabha Swayamdipta, Robin Jia
Abstract: Language model developers typically filter out high-risk content -- such as toxic or copyrighted text -- from their pre-training data to prevent models from generating similar outputs. However, removing such data altogether limits models' ability to recognize and appropriately respond to harmful or sensitive content. In this paper, we introduce Selective Loss to Understand but Not Generate (SLUNG), a pre-training paradigm through which models learn to understand high-risk data without learning to generate it. Instead of uniformly applying the next-token prediction loss, SLUNG selectively avoids incentivizing the generation of high-risk tokens while ensuring they remain within the model's context window. As the model learns to predict low-risk tokens that follow high-risk ones, it is forced to understand the high-risk content. Through our experiments, we show that SLUNG consistently improves models' understanding of high-risk data (e.g., ability to recognize toxic content) without increasing its generation (e.g., toxicity of model responses). Overall, our SLUNG paradigm enables models to benefit from high-risk text that would otherwise be filtered out.
Authors: Yurui Zhang, Ruigang Wang, Ian R. Manchester
Abstract: We study the invertibility of nonlinear dynamical systems from the perspective of contraction and incremental stability analysis and propose a new invertible recurrent neural model: the BiLipREN. In particular, we consider a nonlinear state space model to be robustly invertible if an inverse exists with a state space realisation, and both the forward model and its inverse are contracting, i.e. incrementally exponentially stable, and Lipschitz, i.e. have bounded incremental gain. This property of bi-Lipschitzness implies both robustness in the sense of sensitivity to input perturbations, as well as robust distinguishability of different inputs from their corresponding outputs, i.e. the inverse model robustly reconstructs the input sequence despite small perturbations to the initial conditions and measured output. Building on this foundation, we propose a parameterization of neural dynamic models: bi-Lipschitz recurrent equilibrium networks (biLipREN), which are robustly invertible by construction. Moreover, biLipRENs can be composed with orthogonal linear systems to construct more general bi-Lipschitz dynamic models, e.g., a nonlinear analogue of minimum-phase/all-pass (inner/outer) factorization. We illustrate the utility of our proposed approach with numerical examples.
Authors: Donghun Noh, Deqian Kong, Minglu Zhao, Andrew Lizarraga, Jianwen Xie, Ying Nian Wu, Dennis Hong
Abstract: This paper presents Latent Adaptive Planner (LAP), a novel approach for dynamic nonprehensile manipulation tasks that formulates planning as latent space inference, effectively learned from human demonstration videos. Our method addresses key challenges in visuomotor policy learning through a principled variational replanning framework that maintains temporal consistency while efficiently adapting to environmental changes. LAP employs Bayesian updating in latent space to incrementally refine plans as new observations become available, striking an optimal balance between computational efficiency and real-time adaptability. We bridge the embodiment gap between humans and robots through model-based proportional mapping that regenerates accurate kinematic-dynamic joint states and object positions from human demonstrations. Experimental evaluations across multiple complex manipulation benchmarks demonstrate that LAP achieves state-of-the-art performance, outperforming existing approaches in success rate, trajectory smoothness, and energy efficiency, particularly in dynamic adaptation scenarios. Our approach enables robots to perform complex interactions with human-like adaptability while providing an expandable framework applicable to diverse robotic platforms using the same human demonstration videos.
Authors: Abdul Mustafa, Muhammad Talha Khan, Muhammad Azmi Umer, Zaki Masood, Chuadhry Mujeeb Ahmed
Abstract: Machine learning (ML)-based intrusion detection systems (IDS) are vulnerable to adversarial attacks. It is crucial for an IDS to learn to recognize adversarial examples before malicious entities exploit them. In this paper, we generated adversarial samples using the Jacobian Saliency Map Attack (JSMA). We validate the generalization and scalability of the adversarial samples to tackle a broad range of real attacks on Industrial Control Systems (ICS). We evaluated the impact by assessing multiple attacks generated using the proposed method. The model trained with adversarial samples detected attacks with 95% accuracy on real-world attack data not used during training. The study was conducted using an operational secure water treatment (SWaT) testbed.
Authors: Sajjad Rezvani Boroujeni, Hossein Abedi, Tom Bush
Abstract: Visual defect detection in industrial glass manufacturing remains a critical challenge due to the low frequency of defective products, leading to imbalanced datasets that limit the performance of deep learning models and computer vision systems. This paper presents a novel approach using Denoising Diffusion Probabilistic Models (DDPMs) to generate synthetic defective glass product images for data augmentation, effectively addressing class imbalance issues in manufacturing quality control and automated visual inspection. The methodology significantly enhances image classification performance of standard CNN architectures (ResNet50V2, EfficientNetB0, and MobileNetV2) in detecting anomalies by increasing the minority class representation. Experimental results demonstrate substantial improvements in key machine learning metrics, particularly in recall for defective samples across all tested deep neural network architectures while maintaining perfect precision. The most dramatic improvement was observed in ResNet50V2's overall classification accuracy, which increased from 78 percent to 93 percent when trained with the augmented data. This work provides a scalable, cost-effective approach to enhancing automated defect detection in glass manufacturing that can potentially be extended to other industrial quality assurance systems and industries with similar class imbalance challenges.
Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Abstract: Quantum machine learning for spin and molecular systems faces critical challenges of scarce labeled data and computationally expensive simulations. To address these limitations, we introduce Hamiltonian-Masked Autoencoding (HMAE), a novel self-supervised framework that pre-trains transformers on unlabeled quantum Hamiltonians, enabling efficient few-shot transfer learning. Unlike random masking approaches, HMAE employs a physics-informed strategy based on quantum information theory to selectively mask Hamiltonian terms based on their physical significance. Experiments on 12,500 quantum Hamiltonians (60% real-world, 40% synthetic) demonstrate that HMAE achieves 85.3% $\pm$ 1.5% accuracy in phase classification and 0.15 $\pm$ 0.02 eV MAE in ground state energy prediction with merely 10 labeled examples - a statistically significant improvement (p < 0.01) over classical graph neural networks (78.1% $\pm$ 2.1%) and quantum neural networks (76.8% $\pm$ 2.3%). Our method's primary advantage is exceptional sample efficiency - reducing required labeled examples by 3-5x compared to baseline methods - though we emphasize that ground truth values for fine-tuning and evaluation still require exact diagonalization or tensor networks. We explicitly acknowledge that our current approach is limited to small quantum systems (specifically limited to 12 qubits during training, with limited extension to 16-20 qubits in testing) and that, while promising within this regime, this size restriction prevents immediate application to larger systems of practical interest in materials science and quantum chemistry.
Authors: Fei Han, Pengming Guo, Hao Chen, Weikun Li, Jingbo Ren, Naijun Liu, Ning Yang, Dixia Fan
Abstract: This paper presents a Long Short-Term Memory network-based Fluid Experiment Data-Driven model (FED-LSTM) for predicting unsteady, nonlinear hydrodynamic forces on the underwater quadruped robot we constructed. Trained on experimental data from leg force and body drag tests conducted in both a recirculating water tank and a towing tank, FED-LSTM outperforms traditional Empirical Formulas (EF) commonly used for flow prediction over flat surfaces. The model demonstrates superior accuracy and adaptability in capturing complex fluid dynamics, particularly in straight-line and turning-gait optimizations via the NSGA-II algorithm. FED-LSTM reduces deflection errors during straight-line swimming and improves turn times without increasing the turning radius. Hardware experiments further validate the model's precision and stability over EF. This approach provides a robust framework for enhancing the swimming performance of legged robots, laying the groundwork for future advances in underwater robotic locomotion.
Authors: Zaid Ghazal, Ali Al-Bustami, Khouloud Gaaloul, Jaerock Kwon
Abstract: PID controllers are widely used in control systems because of their simplicity and effectiveness. Although advanced optimization techniques such as Bayesian Optimization and Differential Evolution have been applied to address the challenges of automatic tuning of PID controllers, the influence of initial system states on convergence and the balance between exploration and exploitation remains underexplored. Moreover, experimenting the influence directly on real cyber-physical systems such as mobile robots is crucial for deriving realistic insights. In the present paper, a novel framework is introduced to evaluate the impact of systematically varying these factors on the PID auto-tuning processes that utilize Bayesian Optimization and Differential Evolution. Testing was conducted on two distinct PID-controlled robotic platforms, an omnidirectional robot and a differential drive mobile robot, to assess the effects on convergence rate, settling time, rise time, and overshoot percentage. As a result, the experimental outcomes yield evidence on the effects of the systematic variations, thereby providing an empirical basis for future research studies in the field.
Authors: Guillermo Roque, Erika Maquiling, Jose Giovanni Tapia Lopez, Ross Greer
Abstract: Instruction-Action (IA) data pairs are valuable for training robotic systems, especially autonomous vehicles (AVs), but having humans manually annotate this data is costly and time-inefficient. This paper explores the potential of using mobile application Global Positioning System (GPS) references and Natural Language Processing (NLP) to automatically generate large volumes of IA commands and responses without having a human generate or retroactively tag the data. In our pilot data collection, by driving to various destinations and collecting voice instructions from GPS applications, we demonstrate a means to collect and categorize the diverse sets of instructions, further accompanied by video data to form complete vision-language-action triads. We provide details on our completely automated data collection prototype system, ADVLAT-Engine. We characterize collected GPS voice instructions into eight different classifications, highlighting the breadth of commands and referentialities available for curation from freely available mobile applications. Through research and exploration into the automation of IA data pairs using GPS references, the potential to increase the speed and volume at which high-quality IA datasets are created, while minimizing cost, can pave the way for robust vision-language-action (VLA) models to serve tasks in vision-language navigation (VLN) and human-interactive autonomous systems.
Authors: Hafez Ghaemi, Eilif Muller, Shahab Bakhtiari
Abstract: Current self-supervised algorithms mostly rely on transformations such as data augmentation and masking to learn visual representations. This is achieved by inducing invariance or equivariance with respect to these transformations after encoding two views of an image. This dominant two-view paradigm can limit the flexibility of learned representations for downstream adaptation by creating performance trade-offs between invariance-related tasks such as image classification and more fine-grained equivariance-related tasks. In this work, we introduce \emph{seq-JEPA}, a world modeling paradigm based on joint-embedding predictive architecture that leverages architectural inductive biases to resolve this trade-off. Without requiring an additional equivariance predictor or loss term, seq-JEPA simultaneously learns two architecturally segregated representations: one equivariant to the specified transformations and another invariant to them and suited for tasks such as classification. To do so, our model processes a short sequence of different views (observations) of an input image. Each encoded view is concatenated with embeddings corresponding to the relative transformation (action) producing the next observation in the sequence. A transformer encoder outputs an aggregate representation of this sequence, which is subsequently conditioned on the action leading to the next observation to predict its representation. Empirically, seq-JEPA achieves strong performance on equivariant benchmarks and image classification without sacrificing one for the other. Additionally, our framework excels at tasks that inherently require aggregating a sequence of observations, such as path integration across actions and predictive learning across eye movements.
Authors: Keilung Choy, Wei Xie, Keqi Wang
Abstract: Bioprocess mechanistic modeling is essential for advancing intelligent digital twin representation of biomanufacturing, yet challenges persist due to complex intracellular regulation, stochastic system behavior, and limited experimental data. This paper introduces a symbolic and statistical learning framework to identify key regulatory mechanisms and quantify model uncertainty. Bioprocess dynamics is formulated with stochastic differential equations characterizing intrinsic process variability, with a predefined set of candidate regulatory mechanisms constructed from biological knowledge. A Bayesian learning approach is developed, which is based on a joint learning of kinetic parameters and regulatory structure through a formulation of the mixture model. To enhance computational efficiency, a Metropolis-adjusted Langevin algorithm with adjoint sensitivity analysis is developed for posterior exploration. Compared to state-of-the-art Bayesian inference approaches, the proposed framework achieves improved sample efficiency and robust model selection. An empirical study demonstrates its ability to recover missing regulatory mechanisms and improve model fidelity under data-limited conditions.
Authors: Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang, Khoat Than, Anh Nguyen Duc
Abstract: In explainable AI, Integrated Gradients (IG) is a widely adopted technique for assessing the significance of feature attributes of the input on model outputs by evaluating contributions from a baseline input to the current input. The choice of the baseline input significantly influences the resulting explanation. While the traditional Expected Gradients (EG) method assumes baselines can be uniformly sampled and averaged with equal weights, this study argues that baselines should not be treated equivalently. We introduce Weighted Average Gradients (WG), a novel approach that unsupervisedly evaluates baseline suitability and incorporates a strategy for selecting effective baselines. Theoretical analysis demonstrates that WG satisfies essential explanation method criteria and offers greater stability than prior approaches. Experimental results further confirm that WG outperforms EG across diverse scenarios, achieving an improvement of 10-35\% on main metrics. Moreover, by evaluating baselines, our method can filter a subset of effective baselines for each input to calculate explanations, maintaining high accuracy while reducing computational cost. The code is available at: https://github.com/Tamnt240904/weighted_baseline.
Authors: Spencer Compton, Chirag Pabbaraju, Nikita Zhivotovskiy
Abstract: A fundamental open problem in learning theory is to characterize the best-case teaching dimension $\operatorname{TS}_{\min}$ of a concept class $\mathcal{C}$ with finite VC dimension $d$. Resolving this problem will, in particular, settle the conjectured upper bound on Recursive Teaching Dimension posed by [Simon and Zilles; COLT 2015]. Prior work used a natural greedy algorithm to construct teaching sets recursively, thereby proving upper bounds on $\operatorname{TS}_{\min}$, with the best known bound being $O(d^2)$ [Hu, Wu, Li, and Wang; COLT 2017]. In each iteration, this greedy algorithm chooses to add to the teaching set the $k$ labeled points that restrict the concept class the most. In this work, we prove lower bounds on the performance of this greedy approach for small $k$. Specifically, we show that for $k = 1$, the algorithm does not improve upon the halving-based bound of $O(\log(|\mathcal{C}|))$. Furthermore, for $k = 2$, we complement the upper bound of $O\left(\log(\log(|\mathcal{C}|))\right)$ from [Moran, Shpilka, Wigderson, and Yuhudayoff; FOCS 2015] with a matching lower bound. Most consequentially, our lower bound extends up to $k \le \lceil c d \rceil$ for small constant $c>0$: suggesting that studying higher-order interactions may be necessary to resolve the conjecture that $\operatorname{TS}_{\min} = O(d)$.
Authors: Lukas Meiner, Jens Mehnert, Alexandru Paul Condurache
Abstract: Convolutional neural networks (CNNs) are crucial for computer vision tasks on resource-constrained devices. Quantization effectively compresses these models, reducing storage size and energy cost. However, in modern depthwise-separable architectures, the computational cost is distributed unevenly across its components, with pointwise operations being the most expensive. By applying a general quantization scheme to this imbalanced cost distribution, existing quantization approaches fail to fully exploit potential efficiency gains. To this end, we introduce PROM, a straightforward approach for quantizing modern depthwise-separable convolutional networks by selectively using two distinct bit-widths. Specifically, pointwise convolutions are quantized to ternary weights, while the remaining modules use 8-bit weights, which is achieved through a simple quantization-aware training procedure. Additionally, by quantizing activations to 8-bit, our method transforms pointwise convolutions with ternary weights into int8 additions, which enjoy broad support across hardware platforms and effectively eliminates the need for expensive multiplications. Applying PROM to MobileNetV2 reduces the model's energy cost by more than an order of magnitude (23.9x) and its storage size by 2.7x compared to the float16 baseline while retaining similar classification performance on ImageNet. Our method advances the Pareto frontier for energy consumption vs. top-1 accuracy for quantized convolutional models on ImageNet. PROM addresses the challenges of quantizing depthwise-separable convolutional networks to both ternary and 8-bit weights, offering a simple way to reduce energy cost and storage size.
Authors: Jan Ole von Hartz, Adrian R\"ofer, Joschka Boedecker, Abhinav Valada
Abstract: We present Mixture of Discrete-time Gaussian Processes (MiDiGap), a novel approach for flexible policy representation and imitation learning in robot manipulation. MiDiGap enables learning from as few as five demonstrations using only camera observations and generalizes across a wide range of challenging tasks. It excels at long-horizon behaviors such as making coffee, highly constrained motions such as opening doors, dynamic actions such as scooping with a spatula, and multimodal tasks such as hanging a mug. MiDiGap learns these tasks on a CPU in less than a minute and scales linearly to large datasets. We also develop a rich suite of tools for inference-time steering using evidence such as collision signals and robot kinematic constraints. This steering enables novel generalization capabilities, including obstacle avoidance and cross-embodiment policy transfer. MiDiGap achieves state-of-the-art performance on diverse few-shot manipulation benchmarks. On constrained RLBench tasks, it improves policy success by 76 percentage points and reduces trajectory cost by 67%. On multimodal tasks, it improves policy success by 48 percentage points and increases sample efficiency by a factor of 20. In cross-embodiment transfer, it more than doubles policy success. We make the code publicly available at https://midigap.cs.uni-freiburg.de.
Authors: C\^ome Annicchiarico, Fabien Lotte, J\'er\'emie Mattout
Abstract: Neurofeedback training (NFT) aims to teach self-regulation of brain activity through real-time feedback, but suffers from highly variable outcomes and poorly understood mechanisms, hampering its validation. To address these issues, we propose a formal computational model of the NFT closed loop. Using Active Inference, a Bayesian framework modelling perception, action, and learning, we simulate agents interacting with an NFT environment. This enables us to test the impact of design choices (e.g., feedback quality, biomarker validity) and subject factors (e.g., prior beliefs) on training. Simulations show that training effectiveness is sensitive to feedback noise or bias, and to prior beliefs (highlighting the importance of guiding instructions), but also reveal that perfect feedback is insufficient to guarantee high performance. This approach provides a tool for assessing and predicting NFT variability, interpret empirical data, and potentially develop personalized training protocols.
Authors: Jos\'e-Luis Bueso-Bello, Benjamin Chauvel, Daniel Carcereri, Philipp Posovszky, Pietro Milillo, Jennifer Ruiz, Juan-Carlos Fern\'andez-Diaz, Carolina Gonz\'alez, Michele Martone, Ronny H\"ansch, Paola Rizzoli
Abstract: Deep learning models have shown encouraging capabilities for mapping accurately forests at medium resolution with TanDEM-X interferometric SAR data. Such models, as most of current state-of-the-art deep learning techniques in remote sensing, are trained in a fully-supervised way, which requires a large amount of labeled data for training and validation. In this work, our aim is to exploit the high-resolution capabilities of the TanDEM-X mission to map forests at 6 m. The goal is to overcome the intrinsic limitations posed by midresolution products, which affect, e.g., the detection of narrow roads within vegetated areas and the precise delineation of forested regions contours. To cope with the lack of extended reliable reference datasets at such a high resolution, we investigate self-supervised learning techniques for extracting highly informative representations from the input features, followed by a supervised training step with a significantly smaller number of reliable labels. A 1 m resolution forest/non-forest reference map over Pennsylvania, USA, allows for comparing different training approaches for the development of an effective forest mapping framework with limited labeled samples. We select the best-performing approach over this test region and apply it in a real-case forest mapping scenario over the Amazon rainforest, where only very few labeled data at high resolution are available. In this challenging scenario, the proposed self-supervised framework significantly enhances the classification accuracy with respect to fully-supervised methods, trained using the same amount of labeled data, representing an extremely promising starting point for large-scale, very high-resolution forest mapping with TanDEM-X data.
Authors: Keyu Chen, Wenchao Sun, Hao Cheng, Sifa Zheng
Abstract: Achieving both realism and controllability in interactive closed-loop traffic simulation remains a key challenge in autonomous driving. Data-driven simulation methods reproduce realistic trajectories but suffer from covariate shift in closed-loop deployment, compounded by simplified dynamics models that further reduce reliability. Conversely, physics-based simulation methods enhance reliable and controllable closed-loop interactions but often lack expert demonstrations, compromising realism. To address these challenges, we introduce a dual-stage AV-centered simulation framework that conducts open-loop imitation learning pre-training in a data-driven simulator to capture trajectory-level realism and multimodality, followed by closed-loop reinforcement learning fine-tuning in a physics-based simulator to enhance controllability and mitigate covariate shift. In the fine-tuning stage, we propose RIFT, a simple yet effective closed-loop RL fine-tuning strategy that preserves the trajectory-level multimodality through a GRPO-style group-relative advantage formulation, while enhancing controllability and training stability by replacing KL regularization with the dual-clip mechanism. Extensive experiments demonstrate that RIFT significantly improves the realism and controllability of generated traffic scenarios, providing a robust platform for evaluating autonomous vehicle performance in diverse and interactive scenarios.
Authors: Julia Bringewald
Abstract: Solar flares are among the most powerful and dynamic events in the solar system, resulting from the sudden release of magnetic energy stored in the Sun's atmosphere. These energetic bursts of electromagnetic radiation can release up to 10^32 erg of energy, impacting space weather and posing risks to technological infrastructure and therefore require accurate forecasting of solar flare occurrences and intensities. This study evaluates the predictive performance of three machine learning algorithms: Random Forest, k-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost) for classifying solar flares into 4 categories (B, C, M, X). Using the dataset of 13 SHARP parameters, the effectiveness of the models was evaluated in binary and multiclass classification tasks. The analysis utilized 8 principal components (PC), capturing 95% of data variance, and 100 PCs, capturing 97.5% of variance. Our approach uniquely combines binary and multiclass classification with different levels of dimensionality reduction, an innovative methodology not previously explored in the context of solar flare prediction. Employing a 10-fold stratified cross-validation and grid search for hyperparameter tuning ensured robust model evaluation. Our findings indicate that Random Forest and XGBoost consistently demonstrate strong performance across all metrics, benefiting significantly from increased dimensionality. The insights of this study enhance future research by optimizing dimensionality reduction techniques and informing model selection for astrophysical tasks. By integrating this newly acquired knowledge into future research, more accurate space weather forecasting systems can be developed, along with a deeper understanding of solar physics.
Authors: Chris Wise, Akram Youssry, Alberto Peruzzo, Jo Plested, Matt Woolley
Abstract: Qubit control protocols have traditionally leveraged a characterisation of the qubit-bath coupling via its power spectral density. Previous work proposed the inference of noise operators that characterise the influence of a classical bath using a grey-box approach that combines deep neural networks with physics-encoded layers. This overall structure is complex and poses challenges in scaling and real-time operations. Here, we show that no expensive neural networks are needed and that this noise operator description admits an efficient parameterisation. We refer to the resulting parameter space as the \textit{quantum feature space} of the qubit dynamics resulting from the coupled bath. We show that the Euclidean distance defined over the quantum feature space provides an effective method for classifying noise processes in the presence of a given set of controls. Using the quantum feature space as the input space for a simple machine learning algorithm (random forest, in this case), we demonstrate that it can effectively classify the stationarity and the broad class of noise processes perturbing a qubit. Finally, we explore how control pulse parameters map to the quantum feature space.
Authors: Schaun Wheeler, Olivier Jeunen
Abstract: Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational coherence. These capabilities stem from their architecture, which mirrors human procedural memory -- the brain's ability to automate repetitive, pattern-driven tasks through practice. However, as LLMs are increasingly deployed in real-world applications, it becomes impossible to ignore their limitations operating in complex, unpredictable environments. This paper argues that LLMs, while transformative, are fundamentally constrained by their reliance on procedural memory. To create agents capable of navigating ``wicked'' learning environments -- where rules shift, feedback is ambiguous, and novelty is the norm -- we must augment LLMs with semantic memory and associative learning systems. By adopting a modular architecture that decouples these cognitive functions, we can bridge the gap between narrow procedural expertise and the adaptive intelligence required for real-world problem-solving.
Authors: Artem Karpov, Tinuade Adeleke, Seong Hah Cho, Natalia Perez-Campanero
Abstract: The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermines faithfulness of LLMs reasoning. We explore the steganographic capabilities of LLMs fine-tuned via reinforcement learning (RL) to: (1) develop covert encoding schemes, (2) engage in steganography when prompted, and (3) utilize steganography in realistic scenarios where hidden reasoning is likely, but not prompted. In these scenarios, we detect the intention of LLMs to hide their reasoning as well as their steganography performance. Our findings in the fine-tuning experiments as well as in behavioral non fine-tuning evaluations reveal that while current models exhibit rudimentary steganographic abilities in terms of security and capacity, explicit algorithmic guidance markedly enhances their capacity for information concealment.
Authors: Diep Luong, Mikko Heikkinen, Konstantinos Drossos, Tuomas Virtanen
Abstract: Speech denoising is a generally adopted and impactful task, appearing in many common and everyday-life use cases. Although there are very powerful methods published, most of those are too complex for deployment in everyday and low-resources computational environments, like hand-held devices, intelligent glasses, hearing aids, etc. Knowledge distillation (KD) is a prominent way for alleviating this complexity mismatch and is based on the transferring/distilling of knowledge from a pre-trained complex model, the teacher, to another less complex one, the student. Existing KD methods for speech denoising are based on processes that potentially hamper the KD by bounding the learning of the student to the distribution, information ordering, and feature dimensionality learned by the teacher. In this paper, we present and assess a method that tries to treat this issue, by exploiting the well-known denoising-autoencoder framework, the linear inverted bottlenecks, and the properties of the cosine similarity. We use a public dataset and conduct repeated experiments with different mismatching scenarios between the teacher and the student, reporting the mean and standard deviation of the metrics of our method and another, state-of-the-art method that is used as a baseline. Our results show that with the proposed method, the student can perform better and can also retain greater mismatching conditions compared to the teacher.
Authors: Matan Orbach, Ohad Eytan, Benjamin Sznajder, Ariel Gera, Odellia Boni, Yoav Kantor, Gal Bloch, Omri Levy, Hadas Abraham, Nitzan Barzilay, Eyal Shnarch, Michael E. Factor, Shila Ofek-Koifman, Paula Ta-Shma, Assaf Toledo
Abstract: Finding the optimal Retrieval-Augmented Generation (RAG) configuration for a given use case can be complex and expensive. Motivated by this challenge, frameworks for RAG hyper-parameter optimization (HPO) have recently emerged, yet their effectiveness has not been rigorously benchmarked. To address this gap, we present a comprehensive study involving 5 HPO algorithms over 5 datasets from diverse domains, including a new one collected for this work on real-world product documentation. Our study explores the largest HPO search space considered to date, with two optimized evaluation metrics. Analysis of the results shows that RAG HPO can be done efficiently, either greedily or with iterative random search, and that it significantly boosts RAG performance for all datasets. For greedy HPO approaches, we show that optimizing models first is preferable to the prevalent practice of optimizing sequentially according to the RAG pipeline order.
Authors: Vibhas Vats, Md. Alimoor Reza, David Crandall, Soon-heung Jung
Abstract: Traditional multi-view stereo (MVS) methods primarily depend on photometric and geometric consistency constraints. In contrast, modern learning-based algorithms often rely on the plane sweep algorithm to infer 3D geometry, applying explicit geometric consistency (GC) checks only as a post-processing step, with no impact on the learning process itself. In this work, we introduce GC MVSNet plus plus, a novel approach that actively enforces geometric consistency of reference view depth maps across multiple source views (multi view) and at various scales (multi scale) during the learning phase (see Fig. 1). This integrated GC check significantly accelerates the learning process by directly penalizing geometrically inconsistent pixels, effectively halving the number of training iterations compared to other MVS methods. Furthermore, we introduce a densely connected cost regularization network with two distinct block designs simple and feature dense optimized to harness dense feature connections for enhanced regularization. Extensive experiments demonstrate that our approach achieves a new state of the art on the DTU and BlendedMVS datasets and secures second place on the Tanks and Temples benchmark. To our knowledge, GC MVSNet plus plus is the first method to enforce multi-view, multi-scale supervised geometric consistency during learning. Our code is available.
Authors: Zirui Liu, Jiatong Li, Yan Zhuang, Qi Liu, Shuanghong Shen, Jie Ouyang, Mingyue Cheng, Shijin Wang
Abstract: Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the consistency and stability of the MLE approach for model ranking. Additionally, we proposed the am-ELO, which modify the Elo Rating's probability function to incorporate annotator abilities, enabling the simultaneous estimation of model scores and annotator reliability. Experiments demonstrate that this method ensures stability, proving that this framework offers a more robust, accurate, and stable evaluation method for LLMs.
Authors: Lilian Marey, Charlotte Laclau, Bruno Sguerra, Tiphaine Viard, Manuel Moussallam
Abstract: The increasing availability of user data on music streaming platforms opens up new possibilities for analyzing music consumption. However, understanding the evolution of user preferences remains a complex challenge, particularly as their musical tastes change over time. This paper uses the dictionary learning paradigm to model user trajectories across different musical genres. We define a new framework that captures recurring patterns in genre trajectories, called pathlets, enabling the creation of comprehensible trajectory embeddings. We show that pathlet learning reveals relevant listening patterns that can be analyzed both qualitatively and quantitatively. This work improves our understanding of users' interactions with music and opens up avenues of research into user behavior and fostering diversity in recommender systems. A dataset of 2000 user histories tagged by genre over 17 months, supplied by Deezer (a leading music streaming company), is also released with the code.
Authors: Haoqi Yang, Luohe Shi, Qiwei Li, Zuchao Li, Ping Wang, Bo Du, Mengjia Shen, Hai Zhao
Abstract: Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE architectures. With the emergence of DeepSeek Models, fine-grained MoE models are gaining popularity, yet research on them remains limited. Therefore, we want to discuss the efficiency dynamic under different service loads. Additionally, fine-grained models allow deployers to reduce the number of routed experts, both activated counts and total counts, raising the question of how this reduction affects the trade-off between MoE efficiency and performance. Our findings indicate that while deploying MoE models presents greater challenges, it also offers significant optimization opportunities. Reducing the number of activated experts can lead to substantial efficiency improvements in certain scenarios, with only minor performance degradation. Reducing the total number of experts provides limited efficiency gains but results in severe performance degradation. Our method can increase throughput by at least 10\% without any performance degradation. Overall, we conclude that MoE inference optimization remains an area with substantial potential for exploration and improvement.
Authors: Charita Dellaporta, Patrick O'Hara, Theodoros Damoulas
Abstract: Distributionally Robust Optimisation (DRO) protects risk-averse decision-makers by considering the worst-case risk within an ambiguity set of distributions based on the empirical distribution or a model. To further guard against finite, noisy data, model-based approaches admit Bayesian formulations that propagate uncertainty from the posterior to the decision-making problem. However, when the model is misspecified, the decision maker must stretch the ambiguity set to contain the data-generating process (DGP), leading to overly conservative decisions. We address this challenge by introducing DRO with Robust, to model misspecification, Bayesian Ambiguity Sets (DRO-RoBAS). These are Maximum Mean Discrepancy ambiguity sets centred at a robust posterior predictive distribution that incorporates beliefs about the DGP. We show that the resulting optimisation problem obtains a dual formulation in the Reproducing Kernel Hilbert Space and we give probabilistic guarantees on the tolerance level of the ambiguity set. Our method outperforms other Bayesian and empirical DRO approaches in out-of-sample performance on the Newsvendor and Portfolio problems with various cases of model misspecification.
Authors: Julian P. Merkofer, Dennis M. J. van de Sande, Alex A. Bhogal, Ruud J. G. van Sloun
Abstract: Magnetic resonance spectroscopy (MRS) is a non-invasive technique to measure the metabolic composition of tissues, offering valuable insights into neurological disorders, tumor detection, and other metabolic dysfunctions. However, accurate metabolite quantification is hindered by challenges such as spectral overlap, low signal-to-noise ratio, and various artifacts. Traditional methods like linear-combination modeling are susceptible to ambiguities and commonly only provide a theoretical lower bound on estimation accuracy in the form of the Cram\'er-Rao bound. This work introduces a Bayesian inference framework using Sylvester normalizing flows (SNFs) to approximate posterior distributions over metabolite concentrations, enhancing quantification reliability. A physics-based decoder incorporates prior knowledge of MRS signal formation, ensuring realistic distribution representations. We validate the method on simulated 7T proton MRS data, demonstrating accurate metabolite quantification, well-calibrated uncertainties, and insights into parameter correlations and multi-modal distributions.
Authors: Vladimir Fanaskov, Ivan Oseledets
Abstract: Artificial Kuramoto oscillatory neurons were recently introduced as an alternative to threshold units. Empirical evidence suggests that oscillatory units outperform threshold units in several tasks including unsupervised object discovery and certain reasoning problems. The proposed coupling mechanism for these oscillatory neurons is heterogeneous, combining a generalized Kuramoto equation with standard coupling methods used for threshold units. In this research note, we present a theoretical framework that clearly distinguishes oscillatory neurons from threshold units and establishes a coupling mechanism between them. We argue that, from a biological standpoint, oscillatory and threshold units realise distinct aspects of neural coding: roughly, threshold units model intensity of neuron firing, while oscillatory units facilitate information exchange by frequency modulation. To derive interaction between these two types of units, we constrain their dynamics by focusing on dynamical systems that admit Lyapunov functions. For threshold units, this leads to Hopfield associative memory model, and for oscillatory units it yields a specific form of generalized Kuramoto model. The resulting dynamical systems can be naturally coupled to form a Hopfield-Kuramoto associative memory model, which also admits a Lyapunov function. Various forms of coupling are possible. Notably, oscillatory neurons can be employed to implement a low-rank correction to the weight matrix of a Hopfield network. This correction can be viewed either as a form of Hebbian learning or as a popular LoRA method used for fine-tuning of large language models. We demonstrate the practical realization of this particular coupling through illustrative toy experiments.
Authors: Bernardo Marenco, Paola Bermolen, Marcelo Fiori, Federico Larroca, Gonzalo Mateos
Abstract: Modeling of intricate relational patterns % through the analysis structures of network data has become a cornerstone of contemporary statistical research and related data science fields. Networks, represented as graphs, offer a natural framework for this analysis. This paper extends the Random Dot Product Graph (RDPG) model to accommodate weighted graphs, markedly broadening the model's scope to scenarios where edges exhibit heterogeneous weight distributions. We propose a nonparametric weighted (W)RDPG model that assigns a sequence of latent positions to each node. Inner products of these nodal vectors specify the moments of their incident edge weights' distribution via moment-generating functions. In this way, and unlike prior art, the WRDPG can discriminate between weight distributions that share the same mean but differ in other higher-order moments. We derive statistical guarantees for an estimator of the nodal's latent positions adapted from the workhorse adjacency spectral embedding, establishing its consistency and asymptotic normality. We also contribute a generative framework that enables sampling of graphs that adhere to a (prescribed or data-fitted) WRDPG, facilitating, e.g., the analysis and testing of observed graph metrics using judicious reference distributions. The paper is organized to formalize the model's definition, the estimation (or nodal embedding) process and its guarantees, as well as the methodologies for generating weighted graphs, all complemented by illustrative and reproducible examples showcasing the WRDPG's effectiveness in various network analytic applications.
Authors: Katy Craig, Nicol\'as Garc\'ia Trillos, {\DJ}or{\dj}e Nikoli\'c
Abstract: Motivated by applications in classification of vector valued measures and multispecies PDE, we develop a theory that unifies existing notions of vector valued optimal transport, from dynamic formulations (\`a la Benamou-Brenier) to static formulations (\`a la Kantorovich). In our framework, vector valued measures are modeled as probability measures on a product space $\mathbb{R}^d \times G$, where $G$ is a weighted graph over a finite set of nodes and the graph geometry strongly influences the associated dynamic and static distances. We obtain sharp inequalities relating four notions of vector valued optimal transport and prove that the distances are mutually bi-H\"older equivalent. We discuss the theoretical and practical advantages of each metric and indicate potential applications in multispecies PDE and data analysis. In particular, one of the static formulations discussed in the paper is amenable to linearization, a technique that has been explored in recent years to accelerate the computation of pairwise optimal transport distances.
Authors: Sharvi Endait, Ruturaj Ghatage, Aditya Kulkarni, Rajlaxmi Patil, Raviraj Joshi
Abstract: The rapid progress in question-answering (QA) systems has predominantly benefited high-resource languages, leaving Indic languages largely underrepresented despite their vast native speaker base. In this paper, we present IndicSQuAD, a comprehensive multi-lingual extractive QA dataset covering nine major Indic languages, systematically derived from the SQuAD dataset. Building on previous work with MahaSQuAD for Marathi, our approach adapts and extends translation techniques to maintain high linguistic fidelity and accurate answer-span alignment across diverse languages. IndicSQuAD comprises extensive training, validation, and test sets for each language, providing a robust foundation for model development. We evaluate baseline performances using language-specific monolingual BERT models and the multilingual MuRIL-BERT. The results indicate some challenges inherent in low-resource settings. Moreover, our experiments suggest potential directions for future work, including expanding to additional languages, developing domain-specific datasets, and incorporating multimodal data. The dataset and models are publicly shared at https://github.com/l3cube-pune/indic-nlp
Authors: Srecharan Selvam, Abhishesh Silwal, George Kanter
Abstract: Automating leaf manipulation in agricultural settings faces significant challenges, including the variability of plant morphologies and deformable leaves. We propose a novel hybrid geometric-neural approach for autonomous leaf grasping that combines traditional computer vision with neural networks through self-supervised learning. Our method integrates YOLOv8 for instance segmentation and RAFT-Stereo for 3D depth estimation to build rich leaf representations, which feed into both a geometric feature scoring pipeline and a neural refinement module (GraspPointCNN). The key innovation is our confidence-weighted fusion mechanism that dynamically balances the contribution of each approach based on prediction certainty. Our self-supervised framework uses the geometric pipeline as an expert teacher to automatically generate training data. Experiments demonstrate that our approach achieves an 88.0% success rate in controlled environments and 84.7% in real greenhouse conditions, significantly outperforming both purely geometric (75.3%) and neural (60.2%) methods. This work establishes a new paradigm for agricultural robotics where domain expertise is seamlessly integrated with machine learning capabilities, providing a foundation for fully automated crop monitoring systems.
Authors: Fran\c{c}ois Role, S\'ebastien Meyer, Victor Amblard
Abstract: Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the embeddings from one modality and another in the embedding space. While this misalignment is detrimental for downstream tasks such as multimodal retrieval, multimodal clustering or zero-shot classification, etc. no generic and practical methods have so far been proposed to assess it precisely and even reduce it. We therefore propose novel measures and effective techniques (spectral- and optimal transport-based methods) to achieve this goal. Extensive experiments conducted on several image-text datasets and models demonstrate their effectiveness and beneficial effects on downstream tasks. Our code is available at the URL provided in the paper's abstract.
Authors: Kiichi Obuchi, Yuta Yahagi, Kiyohiko Toyama, Shukichi Tanaka, Kota Matsui
Abstract: In this paper, we propose a novel transfer learning approach called multi-modal cascade model with feature transfer for polymer property prediction.Polymers are characterized by a composite of data in several different formats, including molecular descriptors and additive information as well as chemical structures. However, in conventional approaches, prediction models were often constructed using each type of data separately. Our model enables more accurate prediction of physical properties for polymers by combining features extracted from the chemical structure by graph convolutional neural networks (GCN) with features such as molecular descriptors and additive information. The predictive performance of the proposed method is empirically evaluated using several polymer datasets. We report that the proposed method shows high predictive performance compared to the baseline conventional approach using a single feature.
Authors: Kevin Tan, Wei Fan, Yuting Wei
Abstract: Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work has successfully learned an $\epsilon$-optimal policy with a sample complexity of $O(1/\epsilon^2)$ trajectories with general function approximation when strategic exploration is necessary. We address this open problem by introducing a novel actor-critic algorithm that attains a sample-complexity of $O(dH^5 \log|\mathcal{A}|/\epsilon^2 + d H^4 \log|\mathcal{F}|/ \epsilon^2)$ trajectories, and accompanying $\sqrt{T}$ regret when the Bellman eluder dimension $d$ does not increase with $T$ at more than a $\log T$ rate. Here, $\mathcal{F}$ is the critic function class, $\mathcal{A}$ is the action space, and $H$ is the horizon in the finite horizon MDP setting. Our algorithm integrates optimism, off-policy critic estimation targeting the optimal Q-function, and rare-switching policy resets. We extend this to the setting of Hybrid RL, showing that initializing the critic with offline data yields sample efficiency gains compared to purely offline or online RL. Further, utilizing access to offline data, we provide a \textit{non-optimistic} provably efficient actor-critic algorithm that only additionally requires $N_{\text{off}} \geq c_{\text{off}}^*dH^4/\epsilon^2$ in exchange for omitting optimism, where $c_{\text{off}}^*$ is the single-policy concentrability coefficient and $N_{\text{off}}$ is the number of offline samples. This addresses another open problem in the literature. We further provide numerical experiments to support our theoretical findings.
Authors: Richard Y. Zhang
Abstract: The classical low-rank matrix recovery problem is well-known to exhibit \emph{benign nonconvexity} under the restricted isometry property (RIP): local optimization is guaranteed to converge to the global optimum, where the ground truth is recovered. We investigate whether benign nonconvexity continues to hold when the factor matrices are constrained to be elementwise nonnegative -- a common practical requirement. In the simple setting of a rank-1 nonnegative ground truth, we confirm that benign nonconvexity holds in the fully-observed case with RIP constant $\delta=0$. Surprisingly, however, this property fails to extend to the partially-observed case with any arbitrarily small RIP constant $\delta\to0^{+}$, irrespective of rank overparameterization. This finding exposes a critical theoretical gap: the continuity argument widely used to explain the empirical robustness of low-rank matrix recovery fundamentally breaks down once nonnegative constraints are imposed.
Authors: Jialong Li, Xuxin Cheng, Tianshu Huang, Shiqi Yang, Ri-Zhao Qiu, Xiaolong Wang
Abstract: Humanoid robots derive much of their dexterity from hyper-dexterous whole-body movements, enabling tasks that require a large operational workspace: such as picking objects off the ground. However, achieving these capabilities on real humanoids remains challenging due to their high degrees of freedom (DoF) and nonlinear dynamics. We propose Adaptive Motion Optimization (AMO), a framework that integrates sim-to-real reinforcement learning (RL) with trajectory optimization for real-time, adaptive whole-body control. To mitigate distribution bias in motion imitation RL, we construct a hybrid AMO dataset and train a network capable of robust, on-demand adaptation to potentially O.O.D. commands. We validate AMO in simulation and on a 29-DoF Unitree G1 humanoid robot, demonstrating superior stability and an expanded workspace compared to strong baselines. Finally, we show that AMO's consistent performance supports autonomous task execution via imitation learning, underscoring the system's versatility and robustness.
Authors: Yanwei Jia, Xun Yu Zhou
Abstract: We study the continuous-time counterpart of Q-learning for reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation introduced by Wang et al. (2020). As the conventional (big) Q-function collapses in continuous time, we consider its first-order approximation and coin the term ``(little) q-function". This function is related to the instantaneous advantage rate function as well as the Hamiltonian. We develop a ``q-learning" theory around the q-function that is independent of time discretization. Given a stochastic policy, we jointly characterize the associated q-function and value function by martingale conditions of certain stochastic processes, in both on-policy and off-policy settings. We then apply the theory to devise different actor-critic algorithms for solving underlying RL problems, depending on whether or not the density function of the Gibbs measure generated from the q-function can be computed explicitly. One of our algorithms interprets the well-known Q-learning algorithm SARSA, and another recovers a policy gradient (PG) based continuous-time algorithm proposed in Jia and Zhou (2022b). Finally, we conduct simulation experiments to compare the performance of our algorithms with those of PG-based algorithms in Jia and Zhou (2022b) and time-discretized conventional Q-learning algorithms.
Authors: Christopher Scarvelis, Haitz S\'aez de Oc\'ariz Borde, Justin Solomon
Abstract: Score-based generative models (SGMs) sample from a target distribution by iteratively transforming noise using the score function of the perturbed target. For any finite training set, this score function can be evaluated in closed form, but the resulting SGM memorizes its training data and does not generate novel samples. In practice, one approximates the score by training a neural network via score-matching. The error in this approximation promotes generalization, but neural SGMs are costly to train and sample, and the effective regularization this error provides is not well-understood theoretically. In this work, we instead explicitly smooth the closed-form score to obtain an SGM that generates novel samples without training. We analyze our model and propose an efficient nearest-neighbor-based estimator of its score function. Using this estimator, our method achieves competitive sampling times while running on consumer-grade CPUs.
Authors: Sachit Kuhar, Yash Jain, Alexey Tumanov
Abstract: Efficient inference of Deep Neural Networks (DNNs) on resource-constrained edge devices is essential. Quantization and sparsity are key techniques that translate to repetition and sparsity within tensors at the hardware-software interface. This paper introduces the concept of repetition-sparsity trade-off that helps explain computational efficiency during inference. We propose PLUM, a unified co-design framework that integrates DNN inference systems and quantization (forward and backward pass) to leverage the repetition-sparsity trade-off to improve inference efficiency. Our results demonstrate that PLUM's quantization method is more accurate than binary quantization with the same number of non-zero weights. Detailed analysis indicates that signed binarization generates a smaller distribution of effectual (non-zero) parameters nested within a larger distribution of total parameters of latent full-precision weights for a DNN block. Finally, the proposed PLUM framework achieves a 26% speedup on real hardware, doubles energy efficiency, and reduces density by 2.8x compared to binary methods while retaining top-1 accuracy when compared to prior-art methods for ResNets on ImageNet (by achieving 66.2% top-1 accuracy), presenting an alternative solution for deploying efficient models in resource-limited environments.
Authors: Jiazhu Dai, Haoyu Sun
Abstract: Graph Neural Networks (GNNs) are a class of deep learning models capable of processing graph-structured data, and they have demonstrated significant performance in a variety of real-world applications. Recent studies have found that GNN models are vulnerable to backdoor attacks. When specific patterns (called backdoor triggers, e.g., subgraphs, nodes, etc.) appear in the input data, the backdoor embedded in the GNN models is activated, which misclassifies the input data into the target class label specified by the attacker, whereas when there are no backdoor triggers in the input, the backdoor embedded in the GNN models is not activated, and the models work normally. Backdoor attacks are highly stealthy and expose GNN models to serious security risks. Currently, research on backdoor attacks against GNNs mainly focus on tasks such as graph classification and node classification, and backdoor attacks against link prediction tasks are rarely studied. In this paper, we propose a backdoor attack against the link prediction tasks based on GNNs and reveal the existence of such security vulnerability in GNN models, which make the backdoored GNN models to incorrectly predict unlinked two nodes as having a link relationship when a trigger appear. The method uses a single node as the trigger and poison selected node pairs in the training graph, and then the backdoor will be embedded in the GNN models through the training process. In the inference stage, the backdoor in the GNN models can be activated by simply linking the trigger node to the two end nodes of the unlinked node pairs in the input data, causing the GNN models to produce incorrect link prediction results for the target node pairs.
Authors: Marlon Becker, Frederick Altrock, Benjamin Risse
Abstract: The recently proposed optimization algorithm for deep neural networks Sharpness Aware Minimization (SAM) suggests perturbing parameters before gradient calculation by a gradient ascent step to guide the optimization into parameter space regions of flat loss. While significant generalization improvements and thus reduction of overfitting could be demonstrated, the computational costs are doubled due to the additionally needed gradient calculation, making SAM unfeasible in case of limited computationally capacities. Motivated by Nesterov Accelerated Gradient (NAG) we propose Momentum-SAM (MSAM), which perturbs parameters in the direction of the accumulated momentum vector to achieve low sharpness without significant computational overhead or memory demands over SGD or Adam. We evaluate MSAM in detail and reveal insights on separable mechanisms of NAG, SAM and MSAM regarding training optimization and generalization. Code is available at https://github.com/MarlonBecker/MSAM.
Authors: Hao Wang, Licheng Pan, Zhichao Chen, Degui Yang, Sen Zhang, Yifei Yang, Xinggao Liu, Haoxuan Li, Dacheng Tao
Abstract: Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences. While current research predominantly addresses autocorrelation within historical data, the correlations among future labels are often overlooked. Specifically, modern forecasting models primarily adhere to the Direct Forecast (DF) paradigm, generating multi-step forecasts independently and disregarding label autocorrelation over time. In this work, we demonstrate that the learning objective of DF is biased in the presence of label autocorrelation. To address this issue, we propose the Frequency-enhanced Direct Forecast (FreDF), which mitigates label autocorrelation by learning to forecast in the frequency domain, thereby reducing estimation bias. Our experiments show that FreDF significantly outperforms existing state-of-the-art methods and is compatible with a variety of forecast models. Code is available at https://github.com/Master-PLC/FreDF.
Authors: Eugenio Ressa, Alberto Marchisio, Maurizio Martina, Guido Masera, Muhammad Shafique
Abstract: The Continuous Learning (CL) paradigm consists of continuously evolving the parameters of the Deep Neural Network (DNN) model to progressively learn to perform new tasks without reducing the performance on previous tasks, i.e., avoiding the so-called catastrophic forgetting. However, the DNN parameter update in CL-based autonomous systems is extremely resource-hungry. The existing DNN accelerators cannot be directly employed in CL because they only support the execution of the forward propagation. Only a few prior architectures execute the backpropagation and weight update, but they lack the control and management for CL. Towards this, we design a hardware architecture, TinyCL, to perform CL on resource-constrained autonomous systems. It consists of a processing unit that executes both forward and backward propagation, and a control unit that manages memory-based CL workload. To minimize the memory accesses, the sliding window of the convolutional layer moves in a snake-like fashion. Moreover, the Multiply-and-Accumulate units can be reconfigured at runtime to execute different operations. As per our knowledge, our proposed TinyCL represents the first hardware accelerator that executes CL on autonomous systems. We synthesize the complete TinyCL architecture in a 65 nm CMOS technology node with the conventional ASIC design flow. It executes 1 epoch of training on a Conv + ReLU + Dense model on the CIFAR10 dataset in 1.76 s, while 1 training epoch of the same model using an Nvidia Tesla P100 GPU takes 103 s, thus achieving a 58x speedup, consuming 86 mW in a 4.74 mm2 die.
Authors: Da Long, Zhitong Xu, Qiwei Yuan, Yin Yang, Shandian Zhe
Abstract: Fourier Neural Operator (FNO) is a powerful and popular operator learning method. However, FNO is mainly used in forward prediction, yet a great many applications rely on solving inverse problems. In this paper, we propose an invertible Fourier Neural Operator (iFNO) for jointly tackling the forward and inverse problems. We developed a series of invertible Fourier blocks in the latent channel space to share the model parameters, exchange the information, and mutually regularize the learning for the bi-directional tasks. We integrated a variational auto-encoder to capture the intrinsic structures within the input space and to enable posterior inference so as to mitigate challenges of illposedness, data shortage, noises that are common in inverse problems. We proposed a three-step process to combine the invertible blocks and the VAE component for effective training. The evaluations on seven benchmark forward and inverse tasks have demonstrated the advantages of our approach.
Authors: Koshi Oishi, Yota Hashizume, Tomohiko Jimbo, Hirotaka Kaji, Kenji Kashima
Abstract: Transport systems on networks are crucial in various applications, but face a significant risk of being adversely affected by unforeseen circumstances such as disasters. The application of entropy-regularized optimal transport (OT) on graph structures has been investigated to enhance the robustness of transport on such networks. In this study, we propose an imitation-regularized OT (I-OT) that mathematically incorporates prior knowledge into the robustness of OT. This method is expected to enhance interpretability by integrating human insights into robustness and to accelerate practical applications. Furthermore, we mathematically verify the robustness of I-OT and discuss how these robustness properties relate to real-world applications. The effectiveness of this method is validated through a logistics simulation using automotive parts data.
Authors: Ziwen Zhao, Yixin Su, Yuhua Li, Yixiong Zou, Ruixuan Li, Rui Zhang
Abstract: Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial to learning generalized representations for GFMs. However, existing surveys of GFMs have several shortcomings: they lack comprehensiveness regarding the most recent progress, have unclear categorization of self-supervised methods, and take a limited architecture-based perspective that is restricted to only certain types of graph models. As the ultimate goal of GFMs is to learn generalized graph knowledge, we provide a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. We propose a knowledge-based taxonomy, which categorizes self-supervised graph models by the specific graph knowledge utilized. Our taxonomy consists of microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic knowledge (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and more than 25 pretext tasks for pre-training GFMs, as well as various downstream task generalization strategies. Such a knowledge-based taxonomy allows us to re-examine graph models based on new architectures more clearly, such as graph language models, as well as provide more in-depth insights for constructing GFMs.
Authors: YuFei Lai
Abstract: In the field of machine learning, traditional regularization methods tend to directly add regularization terms to the loss function. This paper introduces the "Lai loss", a novel loss design that integrates the regularization terms (specifically, gradients) into the traditional loss function through straightforward geometric concepts. This design penalizes the gradients with the loss itself, allowing for control of the gradients while ensuring maximum accuracy. With this loss, we can effectively control the model's smoothness and sensitivity, potentially offering the dual benefits of improving the model's generalization performance and enhancing its noise resistance on specific features. Additionally, we proposed a training method that successfully addresses the challenges in practical applications. We conducted preliminary experiments using publicly available datasets from Kaggle, demonstrating that the design of Lai loss can control the model's smoothness and sensitivity while maintaining stable model performance.
Authors: Ali Edalati, Alireza Ghaffari, Mahsa Ghazvini Nejad, Lu Hou, Boxing Chen, Masoud Asgharian, Vahid Partovi Nia
Abstract: Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization (PTQ) techniques have been developed to compress LLMs while avoiding expensive re-training. Most PTQ approaches formulate the quantization error based on a layer-wise Euclidean loss, ignoring the model output. Then, each layer is calibrated using its layer-wise Hessian to update the weights towards minimizing the quantization error. The Hessian is also used for detecting the most salient weights to quantization. Such PTQ approaches are prone to accuracy drop in low-precision quantization. We propose Output-adaptive Calibration (OAC) to incorporate the model output in the calibration process. We formulate the quantization error based on the distortion of the output cross-entropy loss. OAC approximates the output-adaptive Hessian for each layer under reasonable assumptions to reduce the computational complexity. The output-adaptive Hessians are used to update the weight matrices and detect the salient weights towards maintaining the model output. Our proposed method outperforms the state-of-the-art baselines such as SpQR and BiLLM, especially, at extreme low-precision (2-bit and binary) quantization.
Authors: Patryk Krukowski, Anna Bielawska, Kamil Ksi\k{a}\.zek, Pawe{\l} Wawrzy\'nski, Pawe{\l} Batorski, Przemys{\l}aw Spurek
Abstract: Recently, a new Continual Learning (CL) paradigm was presented to control catastrophic forgetting, called Interval Continual Learning (InterContiNet), which relies on enforcing interval constraints on the neural network parameter space. Unfortunately, InterContiNet training is challenging due to the high dimensionality of the weight space, making intervals difficult to manage. To address this issue, we introduce HINT, a technique that employs interval arithmetic within the embedding space and utilizes a hypernetwork to map these intervals to the target network parameter space. We train interval embeddings for consecutive tasks and train a hypernetwork to transform these embeddings into weights of the target network. An embedding for a given task is trained along with the hypernetwork, preserving the response of the target network for the previous task embeddings. Interval arithmetic works with a more manageable, lower-dimensional embedding space rather than directly preparing intervals in a high-dimensional weight space. Our model allows faster and more efficient training. Furthermore, HINT maintains the guarantee of not forgetting. At the end of training, we can choose one universal embedding to produce a single network dedicated to all tasks. In such a framework, hypernetwork is used only for training and, finally, we can utilize one set of weights. HINT obtains significantly better results than InterContiNet and gives SOTA results on several benchmarks.
Authors: Songyang Chen, Yu Liu, Lei Zou, Zexuan Wang, Youfang Lin
Abstract: Unsupervised graph alignment finds the node correspondence between a pair of attributed graphs by only exploiting graph structure and node features. One category of recent studies first computes the node representation and then matches nodes with the largest embedding-based similarity, while the other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein learning. However, it remains largely unexplored in the model expressiveness, as well as how theoretical expressivity impacts prediction accuracy. We investigate the model expressiveness from two aspects. First, we characterize the model's discriminative power in distinguishing matched and unmatched node pairs across two graphs. Second, we study the model's capability of guaranteeing node matching properties such as one-to-one matching and mutual alignment. Motivated by our theoretical analysis, we put forward a hybrid approach named CombAlign with stronger expressive power. Specifically, we enable cross-dimensional feature interaction for OT-based learning and propose an embedding-based method inspired by the Weisfeiler-Lehman test. We also apply non-uniform marginals obtained from the embedding-based modules to OT as priors for more expressiveness. Based on that, we propose a traditional algorithm-based refinement, which combines our OT and embedding-based predictions using the ensemble learning strategy and reduces the problem to maximum weight matching. With carefully designed edge weights, we ensure those matching properties and further enhance prediction accuracy. By extensive experiments, we demonstrate a significant improvement of 14.5% in alignment accuracy compared to state-of-the-art approaches and confirm the soundness of our theoretical analysis.
Authors: Swetha Ganesh, Washim Uddin Mondal, Vaneet Aggarwal
Abstract: This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability with respect to the size of the state-action space, high iteration complexity, and dependence on knowledge of mixing times and hitting times. To address these limitations, we propose a Multi-level Monte Carlo-based Natural Actor-Critic (MLMC-NAC) algorithm. Our work is the first to achieve a global convergence rate of $\tilde{\mathcal{O}}(1/\sqrt{T})$ for average-reward Markov Decision Processes (MDPs) (where $T$ is the horizon length), without requiring the knowledge of mixing and hitting times. Moreover, the convergence rate does not scale with the size of the state space, therefore even being applicable to infinite state spaces.
Authors: Taehyun Cho, Seungyub Han, Kyungjae Lee, Seokhun Ju, Dohyeong Kim, Jungwoo Lee
Abstract: Distributional reinforcement learning improves performance by capturing environmental stochasticity, but a comprehensive theoretical understanding of its effectiveness remains elusive. In addition, the intractable element of the infinite dimensionality of distributions has been overlooked. In this paper, we present a regret analysis of distributional reinforcement learning with general value function approximation in a finite episodic Markov decision process setting. We first introduce a key notion of $\textit{Bellman unbiasedness}$ which is essential for exactly learnable and provably efficient distributional updates in an online manner. Among all types of statistical functionals for representing infinite-dimensional return distributions, our theoretical results demonstrate that only moment functionals can exactly capture the statistical information. Secondly, we propose a provably efficient algorithm, $\texttt{SF-LSVI}$, that achieves a tight regret bound of $\tilde{O}(d_E H^{\frac{3}{2}}\sqrt{K})$ where $H$ is the horizon, $K$ is the number of episodes, and $d_E$ is the eluder dimension of a function class.
Authors: Melanie F. Pradier, Javier Gonz\'alez
Abstract: Matching is a popular approach in causal inference to estimate treatment effects by pairing treated and control units that are most similar in terms of their covariate information. However, classic matching methods completely ignore the geometry of the data manifold, which is crucial to define a meaningful distance for matching, and struggle when covariates are noisy and high-dimensional. In this work, we propose GeoMatching, a matching method to estimate treatment effects that takes into account the intrinsic data geometry induced by existing causal mechanisms among the confounding variables. First, we learn a low-dimensional, latent Riemannian manifold that accounts for uncertainty and geometry of the original input data. Second, we estimate treatment effects via matching in the latent space based on the learned latent Riemannian metric. We provide theoretical insights and empirical results in synthetic and real-world scenarios, demonstrating that GeoMatching yields more effective treatment effect estimators, even as we increase input dimensionality, in the presence of outliers, or in semi-supervised scenarios.
Authors: Jingyao Wang, Wenwen Qiang, Changwen Zheng, Hui Xiong, Gang Hua
Abstract: Meta-learning seeks to learn a well-generalized model initialization from training tasks to solve unseen tasks. From the "learning to learn" perspective, the quality of the initialization is modeled with one-step gradient decent in the inner loop. However, contrary to theoretical expectations, our empirical analysis reveals that this may expose meta-learning to underfitting. To bridge the gap between theoretical understanding and practical implementation, we reconsider meta-learning from the "Learning" lens. We propose that the meta-learning model comprises two interrelated components: parameters for model initialization and a meta-layer for task-specific fine-tuning. These components will lead to the risks of overfitting and underfitting depending on tasks, and their solutions, fewer parameters vs. more meta-layer, are often in conflict. To address this, we aim to regulate the task information the model receives without modifying the data or model structure. Our theoretical analysis indicates that models adapted to different tasks can mutually reinforce each other, highlighting the effective information. Based on this insight, we propose TRLearner, a plug-and-play method that leverages task relation to calibrate meta-learning. It first extracts task relation matrices and then applies relation-aware consistency regularization to guide optimization. Extensive theoretical and empirical evaluations demonstrate its effectiveness.
Authors: Lars Henry Berge Olsen, Martin Jullum
Abstract: In Explainable AI (XAI), Shapley values are a popular model-agnostic framework for explaining predictions made by complex machine learning models. The computation of Shapley values requires estimating non-trivial contribution functions representing predictions with only a subset of the features present. As the number of these terms grows exponentially with the number of features, computational costs escalate rapidly, creating a pressing need for efficient and accurate approximation methods. For tabular data, the KernelSHAP framework is considered the state-of-the-art model-agnostic approximation framework. KernelSHAP approximates the Shapley values using a weighted sample of the contribution functions for different feature subsets. We propose a novel modification of KernelSHAP which replaces the stochastic weights with deterministic ones to reduce the variance of the resulting Shapley value approximations. This may also be combined with our simple, yet effective modification to the KernelSHAP variant implemented in the popular Python library SHAP. Additionally, we provide an overview of established methods. Numerical experiments demonstrate that our methods can reduce the required number of contribution function evaluations by $5\%$ to $50\%$ while preserving the same accuracy of the approximated Shapley values -- essentially reducing the running time by up to $50\%$. These computational advancements push the boundaries of the feature dimensionality and number of predictions that can be accurately explained with Shapley values within a feasible runtime.
Authors: Nir Shlezinger, Guy Revach, Anubhab Ghosh, Saikat Chatterjee, Shuo Tang, Tales Imbiriba, Jindrich Dunik, Ondrej Straka, Pau Closas, Yonina C. Eldar
Abstract: The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. These methods are used for state estimation of dynamic systems by relying on mathematical representations in the form of simple state-space (SS) models, which may be crude and inaccurate descriptions of the underlying dynamics. Emerging data-centric artificial intelligence (AI) techniques tackle these tasks using deep neural networks (DNNs), which are model-agnostic. Recent developments illustrate the possibility of fusing DNNs with classic Kalman-type filtering, obtaining systems that learn to track in partially known dynamics. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms. We review both generic and dedicated DNN architectures suitable for state estimation, and provide a systematic presentation of techniques for fusing AI tools with KFs and for leveraging partial SS modeling and data, categorizing design approaches into task-oriented and SS model-oriented. The usefulness of each approach in preserving the individual strengths of model-based KFs and data-driven DNNs is investigated in a qualitative and quantitative study, whose code is publicly available, illustrating the gains of hybrid model-based/data-driven designs. We also discuss existing challenges and future research directions that arise from fusing AI and Kalman-type algorithms.
Authors: Qidong Yang, Jonathan Giezendanner, Daniel Salles Civitarese, Johannes Jakubik, Eric Schmitt, Anirban Chandra, Jeremy Vila, Detlef Hohl, Chris Hill, Campbell Watson, Sherrie Wang
Abstract: Urgent applications like wildfire management and renewable energy generation require precise, localized weather forecasts near the Earth's surface. However, forecasts produced by machine learning models or numerical weather prediction systems are typically generated on large-scale regular grids, where direct downscaling fails to capture fine-grained, near-surface weather patterns. In this work, we propose a multi-modal transformer model trained end-to-end to downscale gridded forecasts to off-grid locations of interest. Our model directly combines local historical weather observations (e.g., wind, temperature, dewpoint) with gridded forecasts to produce locally accurate predictions at various lead times. Multiple data modalities are collected and concatenated at station-level locations, treated as a token at each station. Using self-attention, the token corresponding to the target location aggregates information from its neighboring tokens. Experiments using weather stations across the Northeastern United States show that our model outperforms a range of data-driven and non-data-driven off-grid forecasting methods. They also reveal that direct input of station data provides a phase shift in local weather forecasting accuracy, reducing the prediction error by up to 80% compared to pure gridded data based models. This approach demonstrates how to bridge the gap between large-scale weather models and locally accurate forecasts to support high-stakes, location-sensitive decision-making.
Authors: Shangzhe Li, Zhiao Huang, Hao Su
Abstract: Imitation learning (IL) enables agents to acquire skills directly from expert demonstrations, providing a compelling alternative to reinforcement learning. However, prior online IL approaches struggle with complex tasks characterized by high-dimensional inputs and complex dynamics. In this work, we propose a novel approach to online imitation learning that leverages reward-free world models. Our method learns environmental dynamics entirely in latent spaces without reconstruction, enabling efficient and accurate modeling. We adopt the inverse soft-Q learning objective, reformulating the optimization process in the Q-policy space to mitigate the instability associated with traditional optimization in the reward-policy space. By employing a learned latent dynamics model and planning for control, our approach consistently achieves stable, expert-level performance in tasks with high-dimensional observation or action spaces and intricate dynamics. We evaluate our method on a diverse set of benchmarks, including DMControl, MyoSuite, and ManiSkill2, demonstrating superior empirical performance compared to existing approaches.
Authors: Zhiqi Bu, Xiaomeng Jin, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Mingyi Hong
Abstract: Machine unlearning has been used to remove unwanted knowledge acquired by large language models (LLMs). In this paper, we examine machine unlearning from an optimization perspective, framing it as a regularized multi-task optimization problem, where one task optimizes a forgetting objective and another optimizes the model performance. In particular, we introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives, while integrating a new, automatic learning rate scheduler. We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets while exhibiting stable training.
Authors: Kentaro Hino, Yuki Kurashige
Abstract: A neural network-based machine learning potential energy surface (PES) expressed in a matrix product operator (NN-MPO) is proposed. The MPO form enables efficient evaluation of high-dimensional integrals that arise in solving the time-dependent and time-independent Schr\"odinger equation and effectively overcomes the so-called curse of dimensionality. This starkly contrasts with other neural network-based machine learning PES methods, such as multi-layer perceptrons (MLPs), where evaluating high-dimensional integrals is not straightforward due to the fully connected topology in their backbone architecture. Nevertheless, the NN-MPO retains the high representational capacity of neural networks. NN-MPO can achieve spectroscopic accuracy with a test mean absolute error (MAE) of 3.03 cm$^{-1}$ for a fully coupled six-dimensional ab initio PES, using only 625 training points distributed across a 0 to 17,000 cm$^{-1}$ energy range. Our Python implementation is available at https://github.com/KenHino/Pompon.
Authors: Maximilian Mews, Ansar Aynetdinov, Vivian Schiller, Peter Eisert, Alan Akbik
Abstract: While recent advancements in machine learning, such as LLMs, are revolutionizing software development and creative industries, they have had minimal impact on engineers designing mechanical parts, which remains largely a manual process. Existing approaches to generating 3D geometry most commonly use meshes as a 3D representation. While meshes are suitable for assets in video games or animations, they lack sufficient precision and adaptability for mechanical engineering purposes. This paper introduces a novel approach for the generation of 3D geometry that generates surface-based Constructive Solid Geometry (CSG) by leveraging a code-generation LLM. First, we create a dataset of 3D mechanical parts represented as code scripts by converting Boundary Representation geometry (BREP) into CSG-based Python scripts. Second, we create annotations in natural language using GPT-4. The resulting dataset is used to fine-tune a code-generation LLM. The fine-tuned LLM can complete geometries based on positional input and natural language in a plausible way, demonstrating geometric understanding.
Authors: Vishnou Vinayagame, Gregory Senay, Luis Mart\'i
Abstract: Business documents often contain substantial tabular and textual information with numerical values, requiring mathematical reasoning for effective document understanding. While Small Language Models (SLMs) still struggle at this task, tool-augmented multi-step agents perform better, at the cost of relying on closed-source or larger models, external data, or extensive prompt-engineering. This work introduces MATATA, a novel weakly supervised end-to-end approach to train multi-step reasoning language agents for document tabular applications. MATATA presents an annotation-free paradigm for each agent to enhance 3.8B/8B SLMs. During its two-stage training, MATATA uses the final outcome of the multi-step reasoning chain as weak supervision. This approach avoids having to individually supervise each intermediate agent in the reasoning chain. By employing an adaptive planner and shared tools across different datasets, MATATA shows robust performance. Experiments demonstrate that MATATA achieves state-of-the-art on FinQA, and on TAT-QA among reasoning methods based on open-source SLMs. Although being SLM-based, MATATA closely matches GPT-4-based frameworks on TabMWP. This novel weakly supervised approach enables training an end-to-end multi-step reasoning agent without intermediate supervision, supporting future developments of cost-effective powerful agentic systems.
Authors: Zhen Liu, Tim Z. Xiao, Weiyang Liu, Yoshua Bengio, Dinghuai Zhang
Abstract: While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some reward functions that are either designed by experts or learned from small-scale datasets. Existing post-training methods for reward finetuning of diffusion models typically suffer from lack of diversity in generated samples, lack of prior preservation, and/or slow convergence in finetuning. In response to this challenge, we take inspiration from recent successes in generative flow networks (GFlowNets) and propose a reinforcement learning method for diffusion model finetuning, dubbed Nabla-GFlowNet (abbreviated as $\nabla$-GFlowNet), that leverages the rich signal in reward gradients for probabilistic diffusion finetuning. We show that our proposed method achieves fast yet diversity- and prior-preserving finetuning of Stable Diffusion, a large-scale text-conditioned image diffusion model, on different realistic reward functions.
Authors: Yichen Li, Haozhao Wang, Wenchao Xu, Tianzhe Xiao, Hong Liu, Minzhu Tu, Yuying Wang, Xin Yang, Rui Zhang, Shui Yu, Song Guo, Ruixuan Li
Abstract: Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues. This survey focuses on a comprehensive examination of the development of the non-centralized continual learning algorithms and the real-world deployment across distributed devices. We begin with an introduction to the background and fundamentals of non-centralized learning and continual learning. Then, we review existing solutions from three levels to represent how existing techniques alleviate the catastrophic forgetting and distribution shift. Additionally, we delve into the various types of heterogeneity issues, security, and privacy attributes, as well as real-world applications across three prevalent scenarios. Furthermore, we establish a large-scale benchmark to revisit this problem and analyze the performance of the state-of-the-art NCCL approaches. Finally, we discuss the important challenges and future research directions in NCCL.
Authors: Tidor-Vlad Pricope
Abstract: We present HardML, a benchmark designed to evaluate the knowledge and reasoning abilities in the fields of data science and machine learning. HardML comprises a diverse set of 100 challenging multiple-choice questions, handcrafted over a period of 6 months, covering the most popular and modern branches of data science and machine learning. These questions are challenging even for a typical Senior Machine Learning Engineer to answer correctly. To minimize the risk of data contamination, HardML uses mostly original content devised by the author. Current state of the art AI models achieve a 30% error rate on this benchmark, which is about 3 times larger than the one achieved on the equivalent, well known MMLU ML. While HardML is limited in scope and not aiming to push the frontier, primarily due to its multiple choice nature, it serves as a rigorous and modern testbed to quantify and track the progress of top AI. While plenty benchmarks and experimentation in LLM evaluation exist in other STEM fields like mathematics, physics and chemistry, the subfields of data science and machine learning remain fairly underexplored.
Authors: Matan Ben-Dov, Jing Chen
Abstract: Tensor-network Born machines (TNBMs) are quantum-inspired generative models for learning data distributions. Using tensor-network contraction and optimization techniques, the model learns an efficient representation of the target distribution, capable of capturing complex correlations with a compact parameterization. Despite their promise, the optimization of TNBMs presents several challenges. A key bottleneck of TNBMs is the logarithmic nature of the loss function commonly used for this problem. The single-tensor logarithmic optimization problem cannot be solved analytically, necessitating an iterative approach that slows down convergence and increases the risk of getting trapped in one of many non-optimal local minima. In this paper, we present an improved second-order optimization technique for TNBM training, which significantly enhances convergence rates and the quality of the optimized model. Our method employs a modified Newton's method on the manifold of normalized states, incorporating regularization of the loss landscape to mitigate local minima issues. We demonstrate the effectiveness of our approach by training a one-dimensional matrix product state (MPS) on both discrete and continuous datasets, showcasing its advantages in terms of stability and efficiency, and demonstrating its potential as a robust and scalable approach for optimizing quantum-inspired generative models.
Authors: Armand Foucault (IMT, ANITI), Franck Mamalet (ANITI), Fran\c{c}ois Malgouyres (IMT)
Abstract: Binary and sparse ternary weights in neural networks enable faster computations and lighter representations, facilitating their use on edge devices with limited computational power. Meanwhile, vanilla RNNs are highly sensitive to changes in their recurrent weights, making the binarization and ternarization of these weights inherently challenging. To date, no method has successfully achieved binarization or ternarization of vanilla RNN weights. We present a new approach leveraging the properties of Hadamard matrices to parameterize a subset of binary and sparse ternary orthogonal matrices. This method enables the training of orthogonal RNNs (ORNNs) with binary and sparse ternary recurrent weights, effectively creating a specific class of binary and sparse ternary vanilla RNNs. The resulting ORNNs, called HadamRNN and Block-HadamRNN, are evaluated on benchmarks such as the copy task, permuted and sequential MNIST tasks, the IMDB dataset, two GLUE benchmarks, and two IoT benchmarks. Despite binarization or sparse ternarization, these RNNs maintain performance levels comparable to state-of-the-art full-precision models, highlighting the effectiveness of our approach. Notably, our approach is the first solution with binary recurrent weights capable of tackling the copy task over 1000 timesteps.
Authors: Enoch H. Kang, Hema Yoganarasimhan, Lalit Jain
Abstract: We study the problem of estimating Dynamic Discrete Choice (DDC) models, also known as offline Maximum Entropy-Regularized Inverse Reinforcement Learning (offline MaxEnt-IRL) in machine learning. The objective is to recover reward or $Q^*$ functions that govern agent behavior from offline behavior data. In this paper, we propose a globally convergent gradient-based method for solving these problems without the restrictive assumption of linearly parameterized rewards. The novelty of our approach lies in introducing the Empirical Risk Minimization (ERM) based IRL/DDC framework, which circumvents the need for explicit state transition probability estimation in the Bellman equation. Furthermore, our method is compatible with non-parametric estimation techniques such as neural networks. Therefore, the proposed method has the potential to be scaled to high-dimensional, infinite state spaces. A key theoretical insight underlying our approach is that the Bellman residual satisfies the Polyak-Lojasiewicz (PL) condition -- a property that, while weaker than strong convexity, is sufficient to ensure fast global convergence guarantees. Through a series of synthetic experiments, we demonstrate that our approach consistently outperforms benchmark methods and state-of-the-art alternatives.
Authors: Hao Li, Yuhao Huang, Chang Xu, Viktor Schlegel, Renhe Jiang, Riza Batista-Navarro, Goran Nenadic, Jiang Bian
Abstract: Time-series Generation (TSG) is a prominent research area with broad applications in simulations, data augmentation, and counterfactual analysis. While existing methods have shown promise in unconditional single-domain TSG, real-world applications demand for cross-domain approaches capable of controlled generation tailored to domain-specific constraints and instance-level requirements. In this paper, we argue that text can provide semantic insights, domain information and instance-specific temporal patterns, to guide and improve TSG. We introduce ``Text-Controlled TSG'', a task focused on generating realistic time series by incorporating textual descriptions. To address data scarcity in this setting, we propose a novel LLM-based Multi-Agent framework that synthesizes diverse, realistic text-to-TS datasets. Furthermore, we introduce BRIDGE, a hybrid text-controlled TSG framework that integrates semantic prototypes with text description for supporting domain-level guidance. This approach achieves state-of-the-art generation fidelity on 11 of 12 datasets, and improves controllability by 12.52% on MSE and 6.34% MAE compared to no text input generation, highlighting its potential for generating tailored time-series data.
Authors: Thomas Winninger, Boussad Addad, Katarzyna Kapusta
Abstract: Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely, interpretability studies that analyze these internal mechanisms lack practical applications beyond runtime interventions. We bridge this gap by introducing a novel white-box approach that leverages mechanistic interpretability techniques to craft practical adversarial inputs. Specifically, we first identify acceptance subspaces - sets of feature vectors that do not trigger the model's refusal mechanisms - then use gradient-based optimization to reroute embeddings from refusal subspaces to acceptance subspaces, effectively achieving jailbreaks. This targeted approach significantly reduces computation cost, achieving attack success rates of 80-95\% on state-of-the-art models including Gemma2, Llama3.2, and Qwen2.5 within minutes or even seconds, compared to existing techniques that often fail or require hours of computation. We believe this approach opens a new direction for both attack research and defense development. Furthermore, it showcases a practical application of mechanistic interpretability where other methods are less efficient, which highlights its utility. The code and generated datasets are available at https://github.com/Sckathach/subspace-rerouting.
Authors: Xiaoyu Wang, Yijia Xu, Jingyi Huang, Zhengwei Yang, Zhou Zhang
Abstract: Remote sensing (RS) technique, enabling the non-contact acquisition of extensive ground observations, is a valuable tool for crop yield predictions. Traditional process-based models struggle to incorporate large volumes of RS data, and most users lack understanding of crop growth mechanisms. In contrast, machine learning (ML) models are often criticized as "black boxes" due to their limited interpretability. To address these limitations, we utilized Knowledge-Guided Machine Learning (KGML), a framework that leverages the strengths of both process-based and ML models. Existing works have either overlooked the role of soil moisture in corn growth or did not embed this effect into their models. To bridge this gap, we developed the Knowledge-Guided Machine Learning with Soil Moisture (KGML-SM) framework, treating soil moisture as an intermediate variable in corn growth to emphasize its key role in plant development. Additionally, based on the prior knowledge that the model may overestimate under drought conditions, we designed a drought-aware loss function that penalized predicted yield in drought-affected areas. Our experiments showed that the KGML-SM model outperformed other traditional ML models. We explored the relationships between drought, soil moisture, and corn yield prediction by assessing the importance of different features within the model, and analyzing how soil moisture impacts predictions across different regions and time periods. Finally we provided interpretability for prediction errors to guide future model optimization.
Authors: Srinitish Srinivasan, Omkumar CU
Abstract: While graph neural networks (GNNs) operating in hyperbolic spaces have shown promise for modeling hierarchical and complex relational data, a critical limitation often overlooked is their potentially limited discriminative power compared to their Euclidean counterparts or fundamental graph isomorphism tests like the Weisfeiler-Lehman (WL) hierarchy. Existing hyperbolic aggregation schemes, while curvature-aware, may not sufficiently capture the intricate structural differences required to robustly distinguish non-isomorphic graphs owing to non-injective aggregation functions. To address this expressiveness gap in hyperbolic graph learning, we introduce the Lorentzian Graph Isomorphic Network (LGIN), a novel GNN designed to achieve enhanced discriminative capabilities within the Lorentzian model of hyperbolic space. LGIN proposes a new update rule that effectively combines local neighborhood information with a richer representation of graph structure designed to preserve the Lorentzian metric tensor. This represents a significant step towards building more expressive GNNs in non-Euclidean geometries, overcoming a common bottleneck in current hyperbolic methods. We conduct extensive evaluations across nine diverse benchmark datasets, including molecular and protein structures. LGIN consistently outperforms or matches state-of-the-art hyperbolic and Euclidean GNNs, showcasing its practical efficacy and validating its superior ability to capture complex graph structures and distinguish between different graphs. To the best of our knowledge, LGIN is the first work to study the framework behind a powerful GNN on the hyperbolic space. The code for our paper can be found at https://github.com/Deceptrax123/LGIN
Authors: JianLin Zhu, HongKuo Niu
Abstract: Accurate trajectory prediction is a cornerstone for the safe operation of autonomous driving systems, where understanding the dynamic behavior of surrounding agents is crucial. Transformer-based architectures have demonstrated significant promise in capturing complex spatio-temporality dependencies. However, their reliance on normalization layers can lead to computation overhead and training instabilities. In this work, we present a two-fold approach to address these challenges. First, we integrate DynamicTanh (DyT), which is the latest method to promote transformers, into the backbone, replacing traditional layer normalization. This modification simplifies the network architecture and improves the stability of the inference. We are the first work to deploy the DyT to the trajectory prediction task. Complementing this, we employ a snapshot ensemble strategy to further boost trajectory prediction performance. Using cyclical learning rate scheduling, multiple model snapshots are captured during a single training run. These snapshots are then aggregated via simple averaging at inference time, allowing the model to benefit from diverse hypotheses without incurring substantial additional computational cost. Extensive experiments on Argoverse datasets demonstrate that our combined approach significantly improves prediction accuracy, inference speed and robustness in diverse driving scenarios. This work underscores the potential of normalization-free transformer designs augmented with lightweight ensemble techniques in advancing trajectory forecasting for autonomous vehicles.
Authors: Micah Adler, Dan Alistarh, Nir Shavit
Abstract: We introduce combinatorial interpretability, a methodology for understanding neural computation by analyzing the combinatorial structures in the sign-based categorization of a network's weights and biases. We demonstrate its power through feature channel coding, a theory that explains how neural networks compute Boolean expressions and potentially underlies other categories of neural network computation. According to this theory, features are computed via feature channels: unique cross-neuron encodings shared among the inputs the feature operates on. Because different feature channels share neurons, the neurons are polysemantic and the channels interfere with one another, making the computation appear inscrutable. We show how to decipher these computations by analyzing a network's feature channel coding, offering complete mechanistic interpretations of several small neural networks that were trained with gradient descent. Crucially, this is achieved via static combinatorial analysis of the weight matrices, without examining activations or training new autoencoding networks. Feature channel coding reframes the superposition hypothesis, shifting the focus from neuron activation directionality in high-dimensional space to the combinatorial structure of codes. It also allows us for the first time to exactly quantify and explain the relationship between a network's parameter size and its computational capacity (i.e. the set of features it can compute with low error), a relationship that is implicitly at the core of many modern scaling laws. Though our initial studies of feature channel coding are restricted to Boolean functions, we believe they provide a rich, controlled, and informative research space, and that the path we propose for combinatorial interpretation of neural computation can provide a basis for understanding both artificial and biological neural circuits.
Authors: Julian Bedei, Murray McBain, Alexander Winkler, Charles Robert Koch, Jakob Andert, David Gordon
Abstract: Reinforcement Learning (RL) and Machine Learning Integrated Model Predictive Control (ML-MPC) are promising approaches for optimizing hydrogen-diesel dual-fuel engine control, as they can effectively control multiple-input multiple-output systems and nonlinear processes. ML-MPC is advantageous for providing safe and optimal controls, ensuring the engine operates within predefined safety limits. In contrast, RL is distinguished by its adaptability to changing conditions through its learning-based approach. However, the practical implementation of either method alone poses challenges. RL requires high variance in control inputs during early learning phases, which can pose risks to the system by potentially executing unsafe actions, leading to mechanical damage. Conversely, ML-MPC relies on an accurate system model to generate optimal control inputs and has limited adaptability to system drifts, such as injector aging, which naturally occur in engine applications. To address these limitations, this study proposes a hybrid RL and ML-MPC approach that uses an ML-MPC framework while incorporating an RL agent to dynamically adjust the ML-MPC load tracking reference in response to changes in the environment. At the same time, the ML-MPC ensures that actions stay safe throughout the RL agent's exploration. To evaluate the effectiveness of this approach, fuel pressure is deliberately varied to introduce a model-plant mismatch between the ML-MPC and the engine test bench. The result of this mismatch is a root mean square error (RMSE) in indicated mean effective pressure of 0.57 bar when running the ML-MPC. The experimental results demonstrate that RL successfully adapts to changing boundary conditions by altering the tracking reference while ML-MPC ensures safe control inputs. The quantitative improvement in load tracking by implementing RL is an RSME of 0.44 bar.
Authors: Sixuan Wang, Jiao Yin, Jinli Cao, MingJian Tang, Hua Wang, Yanchun Zhang
Abstract: Effective and efficient graph representation learning is essential for enabling critical downstream tasks, such as node classification, link prediction, and subgraph search. However, existing graph neural network (GNN) architectures often struggle to adapt to diverse and complex graph structures, limiting their ability to produce structure-aware and task-discriminative representations. To address this challenge, we propose ABG-NAS, a novel framework for automated graph neural network architecture search tailored for efficient graph representation learning. ABG-NAS encompasses three key components: a Comprehensive Architecture Search Space (CASS), an Adaptive Genetic Optimization Strategy (AGOS), and a Bayesian-Guided Tuning Module (BGTM). CASS systematically explores diverse propagation (P) and transformation (T) operations, enabling the discovery of GNN architectures capable of capturing intricate graph characteristics. AGOS dynamically balances exploration and exploitation, ensuring search efficiency and preserving solution diversity. BGTM further optimizes hyperparameters periodically, enhancing the scalability and robustness of the resulting architectures. Empirical evaluations on benchmark datasets (Cora, PubMed, Citeseer, and CoraFull) demonstrate that ABG-NAS consistently outperforms both manually designed GNNs and state-of-the-art neural architecture search (NAS) methods. These results highlight the potential of ABG-NAS to advance graph representation learning by providing scalable and adaptive solutions for diverse graph structures. Our code is publicly available at https://github.com/sserranw/ABG-NAS.
Authors: Ruiquan Huang, Yingbin Liang, Jing Yang
Abstract: Language recognition tasks are fundamental in natural language processing (NLP) and have been widely used to benchmark the performance of large language models (LLMs). These tasks also play a crucial role in explaining the working mechanisms of transformers. In this work, we focus on two representative tasks in the category of regular language recognition, known as `even pairs' and `parity check', the aim of which is to determine whether the occurrences of certain subsequences in a given sequence are even. Our goal is to explore how a one-layer transformer, consisting of an attention layer followed by a linear layer, learns to solve these tasks by theoretically analyzing its training dynamics under gradient descent. While even pairs can be solved directly by a one-layer transformer, parity check need to be solved by integrating Chain-of-Thought (CoT), either into the inference stage of a transformer well-trained for the even pairs task, or into the training of a one-layer transformer. For both problems, our analysis shows that the joint training of attention and linear layers exhibits two distinct phases. In the first phase, the attention layer grows rapidly, mapping data sequences into separable vectors. In the second phase, the attention layer becomes stable, while the linear layer grows logarithmically and approaches in direction to a max-margin hyperplane that correctly separates the attention layer outputs into positive and negative samples, and the loss decreases at a rate of $O(1/t)$. Our experiments validate those theoretical results.
Authors: Pramook Khungurn, Pratch Piyawongwisal, Sira Sriswasdi, Supasorn Suwajanakorn
Abstract: A flow matching model learns a time-dependent vector field $v_t(x)$ that generates a probability path $\{ p_t \}_{0 \leq t \leq 1}$ that interpolates between a well-known noise distribution ($p_0$) and the data distribution ($p_1$). It can be distilled into a two-timed flow model (TTFM) $\phi_{s,x}(t)$ that can transform a sample belonging to the distribution at an initial time $s$ to another belonging to the distribution at a terminal time $t$ in one function evaluation. We present a new loss function for TTFM distillation called the \emph{initial/terminal velocity matching} (ITVM) loss that extends the Lagrangian Flow Map Distillation (LFMD) loss proposed by Boffi et al. by adding redundant terms to match the initial velocities at time $s$, removing the derivative from the terminal velocity term at time $t$, and using a version of the model under training, stabilized by exponential moving averaging (EMA), to compute the target terminal average velocity. Preliminary experiments show that our loss leads to better few-step generation performance on multiple types of datasets and model architectures over baselines.
Authors: Mary Phuong, Roland S. Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, Rohin Shah
Abstract: Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future advanced systems, could pose severe loss of control risk. It is therefore important for AI developers to rule out harm from scheming prior to model deployment. In this paper, we present a suite of scheming reasoning evaluations measuring two types of reasoning capabilities that we believe are prerequisites for successful scheming: First, we propose five evaluations of ability to reason about and circumvent oversight (stealth). Second, we present eleven evaluations for measuring a model's ability to instrumentally reason about itself, its environment and its deployment (situational awareness). We demonstrate how these evaluations can be used as part of a scheming inability safety case: a model that does not succeed on these evaluations is almost certainly incapable of causing severe harm via scheming in real deployment. We run our evaluations on current frontier models and find that none of them show concerning levels of either situational awareness or stealth.
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: 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: Chenxi Liu, Hao Miao, Qianxiong Xu, Shaowen Zhou, Cheng Long, Yan Zhao, 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: 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: 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: 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 probability distributions to enhance the statistical fidelity of LLM-generated tabular data.
Authors: Gerard Pons, Besim Bilalli, Anna Queralt
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: Richard Y. Zhang
Abstract: Recent work established that rank overparameterization eliminates spurious local minima in nonconvex low-rank matrix recovery under the restricted isometry property (RIP). But this does not fully explain the practical success of overparameterization, because real algorithms can still become trapped at nonstrict saddle points (approximate second-order points with arbitrarily small negative curvature) even when all local minima are global. Moreover, the result does not accommodate for noisy measurements, but it is unclear whether such an extension is even possible, in view of the many discontinuous and unintuitive behaviors already known for the overparameterized regime. In this paper, we introduce a novel proof technique that unifies, simplifies, and strengthens two previously competing approaches -- one based on escape directions and the other based on the inexistence of counterexample -- to provide sharp global guarantees in the noisy overparameterized regime. We show, once local minima have been converted into global minima through slight overparameterization, that near-second-order points achieve the same minimax-optimal recovery bounds (up to small constant factors) as significantly more expensive convex approaches. Our results are sharp with respect to the noise level and the solution accuracy, and hold for both the symmetric parameterization $XX^{T}$, as well as the asymmetric parameterization $UV^{T}$ under a balancing regularizer; we demonstrate that the balancing regularizer is indeed necessary.
Authors: Yanglei Song, Meng zhou
Abstract: This paper considers contextual bandits with a finite number of arms, where the contexts are independent and identically distributed $d$-dimensional random vectors, and the expected rewards are linear in both the arm parameters and contexts. The LinUCB algorithm, which is near minimax optimal for related linear bandits, is shown to have a cumulative regret that is suboptimal in both the dimension $d$ and time horizon $T$, due to its over-exploration. A truncated version of LinUCB is proposed and termed "Tr-LinUCB", which follows LinUCB up to a truncation time $S$ and performs pure exploitation afterwards. The Tr-LinUCB algorithm is shown to achieve $O(d\log(T))$ regret if $S = Cd\log(T)$ for a sufficiently large constant $C$, and a matching lower bound is established, which shows the rate optimality of Tr-LinUCB in both $d$ and $T$ under a low dimensional regime. Further, if $S = d\log^{\kappa}(T)$ for some $\kappa>1$, the loss compared to the optimal is a multiplicative $\log\log(T)$ factor, which does not depend on $d$. This insensitivity to overshooting in choosing the truncation time of Tr-LinUCB is of practical importance.
Authors: Yu Hou, Cong Tran, Ming Li, Won-Yong Shin
Abstract: In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often uncertain, thereby rendering established community detection approaches ineffective without costly network topology acquisition. To tackle this challenge, we present META-CODE, a unified framework for detecting overlapping communities via exploratory learning aided by easy-to-collect node metadata when networks are topologically unknown (or only partially known). Specifically, META-CODE consists of three iterative steps in addition to the initial network inference step: 1) node-level community-affiliation embeddings based on graph neural networks (GNNs) trained by our new reconstruction loss, 2) network exploration via community-affiliation-based node queries, and 3) network inference using an edge connectivity-based Siamese neural network model from the explored network. Through extensive experiments on three real-world datasets including two large networks, we demonstrate: (a) the superiority of META-CODE over benchmark community detection methods, achieving remarkable gains up to 65.55% on the Facebook dataset over the best competitor among our selected competitive methods in terms of normalized mutual information (NMI), (b) the impact of each module in META-CODE, (c) the effectiveness of node queries in META-CODE based on empirical evaluations and theoretical findings, and (d) the convergence of the inferred network.
Authors: Hansika Weerasena, Prabhat Mishra
Abstract: Network-on-Chip (NoC) is widely used to facilitate communication between components in sophisticated System-on-Chip (SoC) designs. Security of the on-chip communication is crucial because exploiting any vulnerability in shared NoC would be a goldmine for an attacker that puts the entire computing infrastructure at risk. We investigate the security strength of existing anonymous routing protocols in NoC architectures, making two pivotal contributions. Firstly, we develop and perform a machine learning (ML)-based flow correlation attack on existing anonymous routing techniques in Network-on-Chip (NoC) systems, revealing that they provide only packet-level anonymity. Secondly, we propose a novel, lightweight anonymous routing protocol featuring outbound traffic tunneling and traffic obfuscation. This protocol is designed to provide robust defense against ML-based flow correlation attacks, ensuring both packet-level and flow-level anonymity. Experimental evaluation using both real and synthetic traffic demonstrates that our proposed attack successfully deanonymizes state-of-the-art anonymous routing in NoC architectures with high accuracy (up to 99%) for diverse traffic patterns. It also reveals that our lightweight anonymous routing protocol can defend against ML-based attacks with minor hardware and performance overhead.
Authors: Philipp Scholl, Katharina Bieker, Hillary Hauger, Gitta Kutyniok
Abstract: The problem of symbolic regression (SR) arises in many different applications, such as identifying physical laws or deriving mathematical equations describing the behavior of financial markets from given data. Various methods exist to address the problem of SR, often based on genetic programming. However, these methods are usually complicated and involve various hyperparameters. In this paper, we present our new approach ParFam that utilizes parametric families of suitable symbolic functions to translate the discrete symbolic regression problem into a continuous one, resulting in a more straightforward setup compared to current state-of-the-art methods. In combination with a global optimizer, this approach results in a highly effective method to tackle the problem of SR. We theoretically analyze the expressivity of ParFam and demonstrate its performance with extensive numerical experiments based on the common SR benchmark suit SRBench, showing that we achieve state-of-the-art results. Moreover, we present an extension incorporating a pre-trained transformer network DL-ParFam to guide ParFam, accelerating the optimization process by up to two magnitudes. Our code and results can be found at https://github.com/Philipp238/parfam.
Authors: Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo
Abstract: Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly with task model performance metrics, such as mean average precision (mAP) in object detection. This paper introduces Mean-AP Guided Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness for deep detection networks, directly optimizing the sampling strategy using mAP. MGRAL employs a reinforcement learning agent based on LSTM architecture to efficiently navigate the combinatorial challenge of batch sample selection and the non-differentiable nature between performance and selected batches. The agent optimizes selection using policy gradient with mAP improvement as the reward signal. To address the computational intensity of mAP estimation with unlabeled samples, we implement fast look-up tables, ensuring real-world feasibility. We evaluate MGRAL on PASCAL VOC and MS COCO benchmarks across various backbone architectures. Our approach demonstrates strong performance, establishing a new paradigm in reinforcement learning-based active learning for object detection.
Authors: Hansika Weerasena, Prabhat Mishra
Abstract: Convolutional Neural Networks (CNNs) are widely used in various domains, including image recognition, medical diagnosis and autonomous driving. Recent advances in dataflow-based CNN accelerators have enabled CNN inference in resource-constrained edge devices. These dataflow accelerators utilize inherent data reuse of convolution layers to process CNN models efficiently. Concealing the architecture of CNN models is critical for privacy and security. This article evaluates memory-based side-channel information to recover CNN architectures from dataflow-based CNN inference accelerators. The proposed attack exploits spatial and temporal data reuse of the dataflow mapping on CNN accelerators and architectural hints to recover the structure of CNN models. Experimental results demonstrate that our proposed side-channel attack can recover the structures of popular CNN models, namely, Lenet, Alexnet, VGGnet16, and YOLOv2.
Authors: Hangtong Xu, Yuanbo Xu, Chaozhuo Li, Fuzhen Zhuang
Abstract: Inferring user preferences from the historical feedback of users is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent to the real user preferences without additional noise, which simplifies the problem modeling. However, there are various confounders during user-item interactions, such as weather and even the recommendation system itself. Therefore, neglecting the influence of confounders will result in inaccurate user preferences and suboptimal performance of the model. Furthermore, the unobservability of confounders poses a challenge in further addressing the problem. To address these issues, we refine the problem and propose a more rational solution. Specifically, we consider the influence of confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels. By cleverly combining local and global causal graphs, we capture the user-specificity of confounders on user preferences. We theoretically demonstrate the identifiability of the obtained causal graph. Finally, we propose our model based on Variational Autoencoders, named Causal Structure representation learning of Confounders in latent space (CSC). We conducted extensive experiments on one synthetic dataset and five real-world datasets, demonstrating the superiority of our model. Furthermore, we demonstrate that the learned causal representations of confounders are controllable, potentially offering users fine-grained control over the objectives of their recommendation lists with the learned causal graphs.
Authors: Charles C. Margossian, Loucas Pillaud-Vivien, Lawrence K. Saul
Abstract: Given an intractable distribution $p$, the problem of variational inference (VI) is to find the best approximation from some more tractable family $Q$. Commonly, one chooses $Q$ to be a family of factorized distributions (i.e., the mean-field assumption), even though~$p$ itself does not factorize. We show that this mismatch leads to an impossibility theorem: if $p$ does not factorize, then any factorized approximation $q\in Q$ can correctly estimate at most one of the following three measures of uncertainty: (i) the marginal variances, (ii) the marginal precisions, or (iii) the generalized variance (which can be related to the entropy). In practice, the best variational approximation in $Q$ is found by minimizing some divergence $D(q,p)$ between distributions, and so we ask: how does the choice of divergence determine which measure of uncertainty, if any, is correctly estimated by VI? We consider the classic Kullback-Leibler divergences, the more general $\alpha$-divergences, and a score-based divergence which compares $\nabla \log p$ and $\nabla \log q$. We provide a thorough theoretical analysis in the setting where $p$ is a Gaussian and $q$ is a (factorized) Gaussian. We show that all the considered divergences can be \textit{ordered} based on the estimates of uncertainty they yield as objective functions for~VI. Finally, we empirically evaluate the validity of this ordering when the target distribution $p$ is not Gaussian.
Authors: Fabio Feser, Marina Evangelou
Abstract: Tuning the regularization parameter in penalized regression models is an expensive task, requiring multiple models to be fit along a path of parameters. Strong screening rules drastically reduce computational costs by lowering the dimensionality of the input prior to fitting. We develop strong screening rules for group-based Sorted L-One Penalized Estimation (SLOPE) models: Group SLOPE and Sparse-group SLOPE. The developed rules are applicable to the wider family of group-based OWL models, including OSCAR. Our experiments on both synthetic and real data show that the screening rules significantly accelerate the fitting process. The screening rules make it accessible for group SLOPE and sparse-group SLOPE to be applied to high-dimensional datasets, particularly those encountered in genetics.
Authors: Jiaqi Yao, Tianjian Huang, Ding Liu
Abstract: As a core underlying operation in pattern recognition and machine learning, matrix multiplication plays a crucial role in modern machine learning models and constitutes a major contributor to computational expenditure. Hence, researchers have spent decades continuously searching for more efficient matrix multiplication algorithms.This paper firstly introduces an innovative and practical approach to universal quantum matrix multiplication. We designed optimized quantum adders and multipliers based on Quantum Fourier Transform (QFT), which significantly reduced the number of gates used compared to classical adders and multipliers. Subsequently, we construct the basic universal quantum matrix multiplication and extend it to the Strassen algorithm. We conduct comparative experiments to analyze the performance of the quantum matrix multiplication and evaluate the acceleration provided by the optimized quantum adder and multiplier. Finally, we investigate the advantages of the quantum Strassen algorithm and the basic quantum matrix multiplication. Our result opens, for the first time, a reliable pathway for designing universal quantum matrix multiplication. Following this pathway, quantum computing will unlock significantly greater potential for training modern machine learning models.
Authors: Micheline B\'en\'edicte Moumoula, Abdoul Kader Kabore, Jacques Klein, Tegawend\'e Bissyande
Abstract: With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, particularly Large Language Models (LLMs), which have demonstrated their ability to tackle various tasks, this paper revisits cross-lingual code clone detection. We evaluate the performance of five (05) LLMs and eight prompts (08) for the identification of cross-lingual code clones. Additionally, we compare these results against two baseline methods. Finally, we evaluate a pre-trained embedding model to assess the effectiveness of the generated representations for classifying clone and non-clone pairs. The studies involving LLMs and Embedding models are evaluated using two widely used cross-lingual datasets, XLCoST and CodeNet. Our results show that LLMs can achieve high F1 scores, up to 0.99, for straightforward programming examples. However, they not only perform less well on programs associated with complex programming challenges but also do not necessarily understand the meaning of "code clones" in a cross-lingual setting. We show that embedding models used to represent code fragments from different programming languages in the same representation space enable the training of a basic classifier that outperforms all LLMs by ~1 and ~20 percentage points on the XLCoST and CodeNet datasets, respectively. This finding suggests that, despite the apparent capabilities of LLMs, embeddings provided by embedding models offer suitable representations to achieve state-of-the-art performance in cross-lingual code clone detection.
Authors: Nikolaos Pippas, Elliot A. Ludvig, Cagatay Turkay
Abstract: Reinforcement Learning (RL) has experienced significant advancement over the past decade, prompting a growing interest in applications within finance. This survey critically evaluates 167 publications, exploring diverse RL applications and frameworks in finance. Financial markets, marked by their complexity, multi-agent nature, information asymmetry, and inherent randomness, serve as an intriguing test-bed for RL. Traditional finance offers certain solutions, and RL advances these with a more dynamic approach, incorporating machine learning methods, including transfer learning, meta-learning, and multi-agent solutions. This survey dissects key RL components through the lens of Quantitative Finance. We uncover emerging themes, propose areas for future research, and critique the strengths and weaknesses of existing methods.
Authors: Yayati Jadhav, Peter Pak, Amir Barati Farimani
Abstract: Industry 4.0 has revolutionized manufacturing by driving digitalization and shifting the paradigm toward additive manufacturing (AM). Fused Deposition Modeling (FDM), a key AM technology, enables the creation of highly customized, cost-effective products with minimal material waste through layer-by-layer extrusion, posing a significant challenge to traditional subtractive methods. However, the susceptibility of material extrusion techniques to errors often requires expert intervention to detect and mitigate defects that can severely compromise product quality. While automated error detection and machine learning models exist, their generalizability across diverse 3D printer setups, firmware, and sensors is limited, and deep learning methods require extensive labeled datasets, hindering scalability and adaptability. To address these challenges, we present a process monitoring and control framework that leverages pre-trained Large Language Models (LLMs) alongside 3D printers to detect and address printing defects. The LLM evaluates print quality by analyzing images captured after each layer or print segment, identifying failure modes and querying the printer for relevant parameters. It then generates and executes a corrective action plan. We validated the effectiveness of the proposed framework in identifying defects by comparing it against a control group of engineers with diverse AM expertise. Our evaluation demonstrated that LLM-based agents not only accurately identify common 3D printing errors, such as inconsistent extrusion, stringing, warping, and layer adhesion, but also effectively determine the parameters causing these failures and autonomously correct them without any need for human intervention.
Authors: Zhuoxin Chen, Will Ma
Abstract: In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution, with asymmetric consequences for guessing too high vs. too low. In the data-driven version, the distribution is unknown, and one must work with samples from the distribution. Data-driven Newsvendor has been studied under many variants: additive vs. multiplicative regret, high probability vs. expectation bounds, and different distribution classes. This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs. In particular, we provide a unified analysis based on the notion of clustered distributions, which in conjunction with our new lower bounds, shows that the entire spectrum of regrets between $1/\sqrt{n}$ and $1/n$ can be possible. Simulations on commonly-used distributions demonstrate that our notion is the "correct" predictor of empirical regret across varying data sizes.
Authors: Haiyan Zhao, Heng Zhao, Bo Shen, Ali Payani, Fan Yang, Mengnan Du
Abstract: Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the representation space. However, the single vector identified for a concept varies with both data and training, making it less robust and weakening its effectiveness in real-world applications. To address this challenge, we propose an approach to approximate the subspace representing a specific concept. Built on linear probing classifiers, we extend the concept vectors into Gaussian Concept Subspace (GCS). We demonstrate GCS's effectiveness through measuring its faithfulness and plausibility across multiple LLMs with different sizes and architectures. Additionally, we use representation intervention tasks to showcase its efficacy in real-world applications such as emotion steering. Experimental results indicate that GCS concept vectors have the potential to balance steering performance and maintaining the fluency in natural language generation tasks.
Authors: Haomin Wen, Shurui Cao, Zeeshan Rasheed, Khurram Hassan Shafique, Leman Akoglu
Abstract: Given the temporal GPS coordinates from a large set of human agents, how can we model their mobility behavior toward effective anomaly (e.g. bad-actor or malicious behavior) detection without any labeled data? Human mobility and trajectory modeling have been extensively studied, showcasing varying abilities to manage complex inputs and balance performance-efficiency trade-offs. In this work, we formulate anomaly detection in complex human behavior by modeling raw GPS data as a sequence of stay-point events, each characterized by spatio-temporal features, along with trips (i.e. commute) between the stay-points. Our problem formulation allows us to leverage modern sequence models for unsupervised training and anomaly detection. Notably, we equip our proposed model USTAD (for Uncertainty-aware Spatio-Temporal Anomaly Detection) with aleatoric (i.e. data) uncertainty estimation to account for inherent stochasticity in certain individuals' behavior, as well as epistemic (i.e. model) uncertainty to handle data sparsity under a large variety of human behaviors. Together, aleatoric and epistemic uncertainties unlock a robust loss function as well as uncertainty-aware decision-making in anomaly scoring. Extensive experiments shows that USTAD improves anomaly detection AUCROC by 3\%-15\% over baselines in industry-scale data.
Authors: Omar Melikechi, David B. Dunson, Jeffrey W. Miller
Abstract: Feature selection is a critical task in machine learning and statistics. However, existing feature selection methods either (i) rely on parametric methods such as linear or generalized linear models, (ii) lack theoretical false discovery control, or (iii) identify few true positives. Here, we introduce a general feature selection method with finite-sample false discovery control based on applying integrated path stability selection (IPSS) to arbitrary feature importance scores. The method is nonparametric whenever the importance scores are nonparametric, and it estimates q-values, which are better suited to high-dimensional data than p-values. We focus on two special cases using importance scores from gradient boosting (IPSSGB) and random forests (IPSSRF). Extensive nonlinear simulations with RNA sequencing data show that both methods accurately control the false discovery rate and detect more true positives than existing methods. Both methods are also efficient, running in under 20 seconds when there are 500 samples and 5000 features. We apply IPSSGB and IPSSRF to detect microRNAs and genes related to cancer, finding that they yield better predictions with fewer features than existing approaches.
Authors: Jung-hun Kim, Min-hwan Oh
Abstract: In this study, we consider multi-class multi-server asymmetric queueing systems consisting of $N$ queues on one side and $K$ servers on the other side, where jobs randomly arrive in queues at each time. The service rate of each job-server assignment is unknown and modeled by a feature-based Multi-nomial Logit (MNL) function. At each time, a scheduler assigns jobs to servers, and each server stochastically serves at most one job based on its preferences over the assigned jobs. The primary goal of the algorithm is to stabilize the queues in the system while learning the service rates of servers. To achieve this goal, we propose algorithms based on UCB and Thompson Sampling, which achieve system stability with an average queue length bound of $O(\min\{N,K\}/\epsilon)$ for a large time horizon $T$, where $\epsilon$ is a traffic slackness of the system. Furthermore, the algorithms achieve sublinear regret bounds of $\tilde{O}(\min\{\sqrt{T} Q_{\max},T^{3/4}\})$, where $Q_{\max}$ represents the maximum queue length over agents and times. Lastly, we provide experimental results to demonstrate the performance of our algorithms.
Authors: Aseem Paranjape (IUCAA), Ravi K. Sheth (UPenn/ICTP)
Abstract: We consider approximating the linearly evolved 2-point correlation function (2pcf) of dark matter $\xi_{\rm lin}(r;\boldsymbol{\theta})$ in a cosmological model with parameters $\boldsymbol{\theta}$ as the linear combination $\xi_{\rm lin}(r;\boldsymbol{\theta})\approx\sum_i\,b_i(r)\,w_i(\boldsymbol{\theta})$, where the functions $\mathcal{B}=\{b_i(r)\}$ form a $\textit{model-agnostic basis}$ for the linear 2pcf. This decomposition is important for model-agnostic analyses of the baryon acoustic oscillation (BAO) feature in the nonlinear 2pcf of galaxies that fix $\mathcal{B}$ and leave the coefficients $\{w_i\}$ free. To date, such analyses have made simple but sub-optimal choices for $\mathcal{B}$, such as monomials. We develop a machine learning framework for systematically discovering a $\textit{minimal}$ basis $\mathcal{B}$ that describes $\xi_{\rm lin}(r)$ near the BAO feature in a wide class of cosmological models. We use a custom architecture, denoted $\texttt{BiSequential}$, for a neural network (NN) that explicitly realizes the separation between $r$ and $\boldsymbol{\theta}$ above. The optimal NN trained on data in which only $\{\Omega_{\rm m},h\}$ are varied in a $\textit{flat}$ $\Lambda$CDM model produces a basis $\mathcal{B}$ comprising $9$ functions capable of describing $\xi_{\rm lin}(r)$ to $\sim0.6\%$ accuracy in $\textit{curved}$ $w$CDM models varying 7 parameters within $\sim5\%$ of their fiducial, flat $\Lambda$CDM values. Scales such as the peak, linear point and zero-crossing of $\xi_{\rm lin}(r)$ are also recovered with very high accuracy. We compare our approach to other compression schemes in the literature, and speculate that $\mathcal{B}$ may also encompass $\xi_{\rm lin}(r)$ in modified gravity models near our fiducial $\Lambda$CDM model. Using our basis functions in model-agnostic BAO analyses can potentially lead to significant statistical gains.
Authors: Yoel Shoshan, Moshiko Raboh, Michal Ozery-Flato, Vadim Ratner, Alex Golts, Jeffrey K. Weber, Ella Barkan, Simona Rabinovici-Cohen, Sagi Polaczek, Ido Amos, Ben Shapira, Liam Hazan, Matan Ninio, Sivan Ravid, Michael M. Danziger, Yosi Shamay, Sharon Kurant, Joseph A. Morrone, Parthasarathy Suryanarayanan, Michal Rosen-Zvi, Efrat Hexter
Abstract: Large language models applied to vast biological datasets have the potential to transform biology by uncovering disease mechanisms and accelerating drug development. However, current models are often siloed, trained separately on small-molecules, proteins, or transcriptomic data, limiting their ability to capture complex, multi-modal interactions. Effective drug discovery requires computational tools that integrate multiple biological entities while supporting prediction and generation, a challenge existing models struggle to address. For this purpose, we present MAMMAL - Molecular Aligned Multi-Modal Architecture and Language - a versatile method applied to create a multi-task foundation model that learns from large-scale biological datasets across diverse modalities, including proteins, small-molecules, and omics. MAMMAL's structured prompt syntax supports classification, regression, and generation tasks while handling token and scalar inputs and outputs. Evaluated on eleven diverse downstream tasks, it reaches a new state of the art (SOTA) in nine tasks and is comparable to SOTA in two tasks, all within a unified architecture, unlike prior task-specific models. Additionally, we explored Alphafold 3 binding prediction capabilities on antibody-antigen and nanobody-antigen complexes showing significantly better classification performance of MAMMAL in 3 out of 4 targets. The model code and pretrained weights are publicly available at https://github.com/BiomedSciAI/biomed-multi-alignment and https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m
URLs: https://github.com/BiomedSciAI/biomed-multi-alignment, https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m
Authors: Yuzhou Zhang, Mohan Hua, Jinan Liu, Haihui Ruan
Abstract: Many glass products require thermoformed geometry with high precision. However, the traditional approach of developing a thermoforming process through trials and errors can cause large waste of time and resources and often end up with unsuccessfulness. Hence, there is a need to develop an efficient predictive model, replacing the costly simulations or experiments, to assist the design of precision glass thermoforming. In this work, we report a surrogate model, based on a dimensionless back-propagation neural network (BPNN), that can adequately predict the form errors and thus compensate for these errors in mold design using geometric features and process parameters as inputs. Our trials with simulation and industrial data indicate that the surrogate model can predict forming errors with adequate accuracy. Although perception errors (mold designers' decisions) and mold fabrication errors make the industrial training data less reliable than simulation data, our preliminary training and testing results still achieved a reasonable consistency with industrial data, suggesting that the surrogate models are directly implementable in the glass-manufacturing industry.
Authors: Anantha S. Rao, Donovan Buterakos, Barnaby van Straaten, Valentin John, C\'ecile X. Yu, Stefan D. Oosterhout, Lucas Stehouwer, Giordano Scappucci, Menno Veldhorst, Francesco Borsoi, Justyna P. Zwolak
Abstract: Arrays of gate-defined semiconductor quantum dots are among the leading candidates for building scalable quantum processors. High-fidelity initialization, control, and readout of spin qubit registers require exquisite and targeted control over key Hamiltonian parameters that define the electrostatic environment. However, due to the tight gate pitch, capacitive crosstalk between gates hinders independent tuning of chemical potentials and interdot couplings. While virtual gates offer a practical solution, determining all the required cross-capacitance matrices accurately and efficiently in large quantum dot registers is an open challenge. Here, we establish a modular automated virtualization system (MAViS) -- a general and modular framework for autonomously constructing a complete stack of multilayer virtual gates in real time. Our method employs machine learning techniques to rapidly extract features from two-dimensional charge stability diagrams. We then utilize computer vision and regression models to self-consistently determine all relative capacitive couplings necessary for virtualizing plunger and barrier gates in both low- and high-tunnel-coupling regimes. Using MAViS, we successfully demonstrate accurate virtualization of a dense two-dimensional array comprising ten quantum dots defined in a high-quality Ge/SiGe heterostructure. Our work offers an elegant and practical solution for the efficient control of large-scale semiconductor quantum dot systems.
Authors: Alexandros Stergiou, Ronald Poppe
Abstract: We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task diversification. Current systems can provide coarse- and fine-grained descriptions of video scenes, extract segments corresponding to queries, synthesize unobserved parts of videos, and predict context across multiple modalities. This survey comprehensively reviews advances in uni- and multi-modal action understanding across a range of tasks. We focus on prevalent challenges, overview widely adopted datasets, and survey seminal works with an emphasis on recent advances. We broadly distinguish between three temporal scopes: (1) recognition tasks of actions observed in full, (2) prediction tasks for ongoing partially observed actions, and (3) forecasting tasks for subsequent unobserved action(s). This division allows us to identify specific action modeling and video representation challenges. Finally, we outline future directions to address current shortcomings.
Authors: Gehui Li, Bin Chen, Chen Zhao, Lei Zhang, Jian Zhang
Abstract: Exposure correction is a fundamental problem in computer vision and image processing. Recently, frequency domain-based methods have achieved impressive improvement, yet they still struggle with complex real-world scenarios under extreme exposure conditions. This is due to the local convolutional receptive fields failing to model long-range dependencies in the spectrum, and the non-generative learning paradigm being inadequate for retrieving lost details from severely degraded regions. In this paper, we propose Omnidirectional Spectral Mamba (OSMamba), a novel exposure correction network that incorporates the advantages of state space models and generative diffusion models to address these limitations. Specifically, OSMamba introduces an omnidirectional spectral scanning mechanism that adapts Mamba to the frequency domain to capture comprehensive long-range dependencies in both the amplitude and phase spectra of deep image features, hence enhancing illumination correction and structure recovery. Furthermore, we develop a dual-domain prior generator that learns from well-exposed images to generate a degradation-free diffusion prior containing correct information about severely under- and over-exposed regions for better detail restoration. Extensive experiments on multiple-exposure and mixed-exposure datasets demonstrate that the proposed OSMamba achieves state-of-the-art performance both quantitatively and qualitatively.
Authors: Nozomu Masuya, Hiroshi Sato, Koki Yamane, Takuya Kusume, Sho Sakaino, Toshiaki Tsuji
Abstract: Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of data augmentation has addressed the lack of data, conventional methods of data augmentation for robot manipulation are limited to simulation-based methods or downsampling for position control. This paper proposes a novel method of data augmentation that is applicable to force control and preserves the advantages of real-world datasets. We applied teaching-playback at variable speeds as real-world data augmentation to increase both the quantity and quality of environmental reactions at variable speeds. An experiment was conducted on bilateral control-based imitation learning using a method of imitation learning equipped with position-force control. We evaluated the effect of real-world data augmentation on two tasks, pick-and-place and wiping, at variable speeds, each from two human demonstrations at fixed speed. The results showed a maximum 55% increase in success rate from a simple change in speed of real-world reactions and improved accuracy along the duration/frequency command by gathering environmental reactions at variable speeds.
Authors: Feiyi Chen, Leilei Zhang, Guansong Pang, Roger Zimmermann, Shuiguang Deng
Abstract: In anomaly detection, methods based on large language models (LLMs) can incorporate expert knowledge by reading professional document, while task-specific small models excel at extracting normal data patterns and detecting value fluctuations from training data of target applications. Inspired by the human nervous system, where the brain stores expert knowledge and the peripheral nervous system and spinal cord handle specific tasks like withdrawal and knee-jerk reflexes, we propose CoLLaTe, a framework designed to facilitate collaboration between LLMs and task-specific models, leveraging the strengths of both models for anomaly detection. In particular, we first formulate the collaboration process and identify two key challenges in the collaboration: (1) the misalignment between the expression domains of the LLMs and task-specific small models, and (2) error accumulation arising from the predictions of both models. To address these challenges, we then introduce two key components in CoLLaTe: a model alignment module and a collaborative loss function. Through theoretical analysis and experimental validation, we demonstrate that these components effectively mitigate the identified challenges and achieve better performance than both LLM-based and task-specific models.
Authors: William Cole Nockolds, C. G. Krishnanunni, Tan Bui-Thanh, Xianxhu Tang
Abstract: Solving stiff ordinary differential equations (StODEs) requires sophisticated numerical solvers, which are often computationally expensive. In particular, StODE's often cannot be solved with traditional explicit time integration schemes and one must resort to costly implicit methods to compute solutions. On the other hand, state-of-the-art machine learning (ML) based methods such as Neural ODE (NODE) poorly handle the timescale separation of various elements of the solutions to StODEs and require expensive implicit solvers for integration at inference time. In this work, we embark on a different path which involves learning a latent dynamics for StODEs, in which one completely avoids numerical integration. To that end, we consider a constant velocity latent dynamical system whose solution is a sequence of straight lines. Given the initial condition and parameters of the ODE, the encoder networks learn the slope (i.e the constant velocity) and the initial condition for the latent dynamics. In other words, the solution of the original dynamics is encoded into a sequence of straight lines which can be decoded back to retrieve the actual solution as and when required. Another key idea in our approach is a nonlinear transformation of time, which allows for the "stretching/squeezing" of time in the latent space, thereby allowing for varying levels of attention to different temporal regions in the solution. Additionally, we provide a simple universal-approximation-type proof showing that our approach can approximate the solution of stiff nonlinear system on a compact set to any degree of accuracy, {\epsilon}. We show that the dimension of the latent dynamical system in our approach is independent of {\epsilon}. Numerical investigation on prototype StODEs suggest that our method outperforms state-of-the art machine learning approaches for handling StODEs.
Authors: Sara Abdali, Can Goksen, Saeed Amizadeh, Julie E. Maybee, Kazuhito Koishida
Abstract: Investigating NLP through a philosophical lens has recently caught researcher's eyes as it connects computational methods with classical schools of philosophy. This paper introduces a philosophical approach inspired by the \textit{Hegelian Dialectic} for LLMs' \textit{self-reflection}, utilizing a self-dialectical approach to emulate internal critiques and then synthesize new ideas by resolving the opposing points of view. Moreover, this paper investigates the effect of LLMs' temperature for generation by establishing a dynamic annealing approach, which promotes the creativity in the early stages and gradually refines it by focusing on the nuances, as well as a fixed-temperature strategy for generation. We assess the effectiveness of our proposed method in generating novel ideas and in improving the reasoning abilities of LLMs during problem-solving. Moreover, we implement a Multi-Agent Majority Voting (MAMV) strategy to assess the validity and novelty of the generated ideas, which proves useful in the absence of domain experts. Our experiments demonstrate promising results in generating ideas and enhancing problem-solving performance.
Authors: Gauthier Thurin (CNRS), Kimia Nadjahi (CNRS), Claire Boyer (LMO)
Abstract: Conformal Prediction (CP) is a principled framework for quantifying uncertainty in blackbox learning models, by constructing prediction sets with finite-sample coverage guarantees. Traditional approaches rely on scalar nonconformity scores, which fail to fully exploit the geometric structure of multivariate outputs, such as in multi-output regression or multiclass classification. Recent methods addressing this limitation impose predefined convex shapes for the prediction sets, potentially misaligning with the intrinsic data geometry. We introduce a novel CP procedure handling multivariate score functions through the lens of optimal transport. Specifically, we leverage Monge-Kantorovich vector ranks and quantiles to construct prediction region with flexible, potentially non-convex shapes, better suited to the complex uncertainty patterns encountered in multivariate learning tasks. We prove that our approach ensures finite-sample, distribution-free coverage properties, similar to typical CP methods. We then adapt our method for multi-output regression and multiclass classification, and also propose simple adjustments to generate adaptive prediction regions with asymptotic conditional coverage guarantees. Finally, we evaluate our method on practical regression and classification problems, illustrating its advantages in terms of (conditional) coverage and efficiency.
Authors: Qiangqiang Gu, Shishir Kumar Pandey, Zhanghao Zhouyin
Abstract: Ab initio based accurate simulation of phonon-assisted optical spectra of semiconductors at finite temperatures remains a formidable challenge, as it requires large supercells for phonon sampling and computationally expensive high-accuracy exchange-correlation (XC) functionals. In this work, we present an efficient approach that combines deep learning tight-binding and potential models to address this challenge with ab initio fidelity. By leveraging molecular dynamics for atomic configuration sampling and deep learning-enabled rapid Hamiltonian evaluation, our approach enables large-scale simulations of temperature-dependent optical properties using advanced XC functionals (HSE, SCAN). Demonstrated on silicon and gallium arsenide across temperature 100-400 K, the method accurately captures phonon-induced bandgap renormalization and indirect/direct absorption processes which are in excellent agreement with experimental findings over five orders of magnitude. This work establishes a pathway for high-throughput investigation of electron-phonon coupled phenomena in complex materials, overcoming traditional computational limitations arising from large supercell used with computationally expensive XC-functionals.
Authors: Christoffer Loeffler, Andrea Mart\'inez Freile, Tom\'as Rey Pizarro
Abstract: This study addresses the growing concern of information asymmetry in consumer contracts, exacerbated by the proliferation of online services with complex Terms of Service that are rarely even read. Even though research on automatic analysis methods is conducted, the problem is aggravated by the general focus on English-language Machine Learning approaches and on major jurisdictions, such as the European Union. We introduce a new methodology and a substantial dataset addressing this gap. We propose a novel annotation scheme with four categories and a total of 20 classes, and apply it on 50 online Terms of Service used in Chile. Our evaluation of transformer-based models highlights how factors like language- and/or domain-specific pre-training, few-shot sample size, and model architecture affect the detection and classification of potentially abusive clauses. Results show a large variability in performance for the different tasks and models, with the highest macro-F1 scores for the detection task ranging from 79% to 89% and micro-F1 scores up to 96%, while macro-F1 scores for the classification task range from 60% to 70% and micro-F1 scores from 64% to 80%. Notably, this is the first Spanish-language multi-label classification dataset for legal clauses, applying Chilean law and offering a comprehensive evaluation of Spanish-language models in the legal domain. Our work lays the ground for future research in method development for rarely considered legal analysis and potentially leads to practical applications to support consumers in Chile and Latin America as a whole.
Authors: Aidan Curtis, Eric Li, Michael Noseworthy, Nishad Gothoskar, Sachin Chitta, Hui Li, Leslie Pack Kaelbling, Nicole Carey
Abstract: Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust to uncertainties along the randomized dimensions. While the environment distribution is typically specified by hand, in this paper we investigate automatically discovering a sampling distribution via entropy-regularized reward maximization of a normalizing-flow-based neural sampling distribution. We show that this architecture is more flexible and provides greater robustness than existing approaches that learn simpler, parameterized sampling distributions, as demonstrated in six simulated and one real-world robotics domain. Lastly, we explore how these learned sampling distributions, combined with a privileged value function, can be used for out-of-distribution detection in an uncertainty-aware multi-step manipulation planner.
Authors: Yu-Han Wu, Pierre Marion, G\'erard Biau, Claire Boyer
Abstract: Denoising score matching plays a pivotal role in the performance of diffusion-based generative models. However, the empirical optimal score--the exact solution to the denoising score matching--leads to memorization, where generated samples replicate the training data. Yet, in practice, only a moderate degree of memorization is observed, even without explicit regularization. In this paper, we investigate this phenomenon by uncovering an implicit regularization mechanism driven by large learning rates. Specifically, we show that in the small-noise regime, the empirical optimal score exhibits high irregularity. We then prove that, when trained by stochastic gradient descent with a large enough learning rate, neural networks cannot stably converge to a local minimum with arbitrarily small excess risk. Consequently, the learned score cannot be arbitrarily close to the empirical optimal score, thereby mitigating memorization. To make the analysis tractable, we consider one-dimensional data and two-layer neural networks. Experiments validate the crucial role of the learning rate in preventing memorization, even beyond the one-dimensional setting.
Authors: Kaushik Bhattacharya, Lianghao Cao, George Stepaniants, Andrew Stuart, Margaret Trautner
Abstract: We propose and study a neural operator framework for learning memory- and material microstructure-dependent constitutive laws for heterogeneous materials. We work in the two-scale setting where homogenization theory provides a systematic approach to deriving macroscale constitutive laws, obviating the need to resolve complex microstructure repeatedly. However, the unit cell problems defining these constitutive models are typically not amenable to explicit evaluation. It is therefore of interest to learn constitutive models from data generated by the unit cell problem. Our proposed framework models homogenized constitutive laws with both memory- and microstructure-dependence through the use of Markovian recurrent and Fourier neural operators. The homogenization problem for Kelvin-Voigt viscoelastic materials is studied to provide firm theoretical foundations for our model. The theoretical properties of the cell problem in this Kelvin-Voigt setting motivate the proposed learning framework; and are also used to prove a universal approximation theorem for the learned macroscale constitutive model. Numerical experiments show that the proposed learning framework accurately learns memory- and microstructure-dependent viscoelastic and elasto-viscoplastic constitutive models, beyond the setting of the theory. Furthermore, we show that the learned constitutive models can be successfully deployed in macroscale simulation of material deformation for different microstructures without retraining.
Authors: Atharva Mehta, Shivam Chauhan, Amirbek Djanibekov, Atharva Kulkarni, Gus Xia, Monojit Choudhury
Abstract: The advent of Music-Language Models has greatly enhanced the automatic music generation capability of AI systems, but they are also limited in their coverage of the musical genres and cultures of the world. We present a study of the datasets and research papers for music generation and quantify the bias and under-representation of genres. We find that only 5.7% of the total hours of existing music datasets come from non-Western genres, which naturally leads to disparate performance of the models across genres. We then investigate the efficacy of Parameter-Efficient Fine-Tuning (PEFT) techniques in mitigating this bias. Our experiments with two popular models -- MusicGen and Mustango, for two underrepresented non-Western music traditions -- Hindustani Classical and Turkish Makam music, highlight the promises as well as the non-triviality of cross-genre adaptation of music through small datasets, implying the need for more equitable baseline music-language models that are designed for cross-cultural transfer learning.
Authors: Nektarios A. Valous, Eckhard Hitzer, Drago\c{s} Du\c{s}e, Rodrigo Rojas Moraleda, Ferdinand Popp, Meggy Suarez-Carmona, Anna Berthel, Ismini Papageorgiou, Carlo Fremd, Alexander R\"olle, Christina C. Westhoff, B\'en\'edicte Lenoir, Niels Halama, Inka Z\"ornig, Dirk J\"ager
Abstract: Hypercomplex image processing extends conventional techniques in a unified paradigm encompassing algebraic and geometric principles. This work leverages quaternions and the two-dimensional orthogonal planes split framework (splitting of a quaternion - representing a pixel - into pairs of orthogonal 2D planes) for natural/biomedical image analysis through the following computational workflows and outcomes: natural/biomedical image re-colorization, natural image de-colorization, natural/biomedical image contrast enhancement, computational re-staining and stain separation in histological images, and performance gains in machine/deep learning pipelines for histological images. The workflows are analyzed separately for natural and biomedical images to showcase the effectiveness of the proposed approaches. The proposed workflows can regulate color appearance (e.g. with alternative renditions and grayscale conversion) and image contrast, be part of automated image processing pipelines (e.g. isolating stain components, boosting learning models), and assist in digital pathology applications (e.g. enhancing biomarker visibility, enabling colorblind-friendly renditions). Employing only basic arithmetic and matrix operations, this work offers a computationally accessible methodology - in the hypercomplex domain - that showcases versatility and consistency across image processing tasks and a range of computer vision and biomedical applications. The proposed non-data-driven methods achieve comparable or better results (particularly in cases involving well-known methods) to those reported in the literature, showcasing the potential of robust theoretical frameworks with practical effectiveness. Results, methods, and limitations are detailed alongside discussion of promising extensions, emphasizing the potential of feature-rich mathematical/computational frameworks for natural and biomedical images.
Authors: Seok-Jin Kim, Hongjie Liu, Molei Liu, Kaizheng Wang
Abstract: The proliferation of data has sparked significant interest in leveraging findings from one study to estimate treatment effects in a different target population without direct outcome observations. However, the transfer learning process is frequently hindered by substantial covariate shift and limited overlap between (i) the source and target populations, as well as (ii) the treatment and control groups within the source. We propose a novel method for overlap-adaptive transfer learning of conditional average treatment effect (CATE) using kernel ridge regression (KRR). Our approach involves partitioning the labeled source data into two subsets. The first one is used to train candidate CATE models based on regression adjustment and pseudo-outcomes. An optimal model is then selected using the second subset and unlabeled target data, employing another pseudo-outcome-based strategy. We provide a theoretical justification for our method through sharp non-asymptotic MSE bounds, highlighting its adaptivity to both weak overlaps and the complexity of CATE function. Extensive numerical studies confirm that our method achieves superior finite-sample efficiency and adaptability. We conclude by demonstrating the effectiveness of our approach using a 401(k) eligibility dataset.
Authors: Jusen Du, Weigao Sun, Disen Lan, Jiaxi Hu, Yu Cheng
Abstract: Linear sequence modeling methods, such as linear attention, state space modeling, and linear RNNs, offer significant efficiency improvements by reducing the complexity of training and inference. However, these methods typically compress the entire input sequence into a single fixed-size memory state, which leads to suboptimal performance on recall-intensive downstream tasks. Drawing inspiration from neuroscience, particularly the brain's ability to maintain robust long-term memory while mitigating "memory interference", we introduce a novel architecture called Mixture-of-Memories (MoM). MoM utilizes multiple independent memory states, with a router network directing input tokens to specific memory states. This approach greatly enhances the overall memory capacity while minimizing memory interference. As a result, MoM performs exceptionally well on recall-intensive tasks, surpassing existing linear sequence modeling techniques. Despite incorporating multiple memory states, the computation of each memory state remains linear in complexity, allowing MoM to retain the linear-complexity advantage during training, while constant-complexity during inference. Our experimental results show that MoM significantly outperforms current linear sequence models on downstream language tasks, particularly recall-intensive tasks, and even achieves performance comparable to Transformer models. The code is released at https://github.com/OpenSparseLLMs/MoM and is also released as a part of https://github.com/OpenSparseLLMs/Linear-MoE.
URLs: https://github.com/OpenSparseLLMs/MoM, https://github.com/OpenSparseLLMs/Linear-MoE.
Authors: Pedro Sequeira, Vidyasagar Sadhu, Melinda Gervasio
Abstract: In this paper we present ToMCAT (Theory-of-Mind for Cooperative Agents in Teams), a new framework for generating ToM-conditioned trajectories. It combines a meta-learning mechanism, that performs ToM reasoning over teammates' underlying goals and future behavior, with a multiagent denoising-diffusion model, that generates plans for an agent and its teammates conditioned on both the agent's goals and its teammates' characteristics, as computed via ToM. We implemented an online planning system that dynamically samples new trajectories (replans) from the diffusion model whenever it detects a divergence between a previously generated plan and the current state of the world. We conducted several experiments using ToMCAT in a simulated cooking domain. Our results highlight the importance of the dynamic replanning mechanism in reducing the usage of resources without sacrificing team performance. We also show that recent observations about the world and teammates' behavior collected by an agent over the course of an episode combined with ToM inferences are crucial to generate team-aware plans for dynamic adaptation to teammates, especially when no prior information is provided about them.
Authors: Kehan Long, Ki Myung Brian Lee, Nikola Raicevic, Niyas Attasseri, Melvin Leok, Nikolay Atanasov
Abstract: Planning and control for high-dimensional robot manipulators in cluttered, dynamic environments require both computational efficiency and robust safety guarantees. Inspired by recent advances in learning configuration-space distance functions (CDFs) as robot body representations, we propose a unified framework for motion planning and control that formulates safety constraints as CDF barriers. A CDF barrier approximates the local free configuration space, substantially reducing the number of collision-checking operations during motion planning. However, learning a CDF barrier with a neural network and relying on online sensor observations introduce uncertainties that must be considered during control synthesis. To address this, we develop a distributionally robust CDF barrier formulation for control that explicitly accounts for modeling errors and sensor noise without assuming a known underlying distribution. Simulations and hardware experiments on a 6-DoF xArm manipulator show that our neural CDF barrier formulation enables efficient planning and robust real-time safe control in cluttered and dynamic environments, relying only on onboard point-cloud observations.
Authors: Nawaf Alampara, Mara Schilling-Wilhelmi, Kevin Maik Jablonka
Abstract: Measurements are fundamental to knowledge creation in science, enabling consistent sharing of findings and serving as the foundation for scientific discovery. As machine learning systems increasingly transform scientific fields, the question of how to effectively evaluate these systems becomes crucial for ensuring reliable progress. In this review, we examine the current state and future directions of evaluation frameworks for machine learning in science. We organize the review around a broadly applicable framework for evaluating machine learning systems through the lens of statistical measurement theory, using materials science as our primary context for examples and case studies. We identify key challenges common across machine learning evaluation such as construct validity, data quality issues, metric design limitations, and benchmark maintenance problems that can lead to phantom progress when evaluation frameworks fail to capture real-world performance needs. By examining both traditional benchmarks and emerging evaluation approaches, we demonstrate how evaluation choices fundamentally shape not only our measurements but also research priorities and scientific progress. These findings reveal the critical need for transparency in evaluation design and reporting, leading us to propose evaluation cards as a structured approach to documenting measurement choices and limitations. Our work highlights the importance of developing a more diverse toolbox of evaluation techniques for machine learning in materials science, while offering insights that can inform evaluation practices in other scientific domains where similar challenges exist.
Authors: Etienne Gauthier, Francis Bach, Michael I. Jordan
Abstract: Conformal prediction is a powerful framework for distribution-free uncertainty quantification. The standard approach to conformal prediction relies on comparing the ranks of prediction scores: under exchangeability, the rank of a future test point cannot be too extreme relative to a calibration set. This rank-based method can be reformulated in terms of p-values. In this paper, we explore an alternative approach based on e-values, known as conformal e-prediction. E-values offer key advantages that cannot be achieved with p-values, enabling new theoretical and practical capabilities. In particular, we present three applications that leverage the unique strengths of e-values: batch anytime-valid conformal prediction, fixed-size conformal sets with data-dependent coverage, and conformal prediction under ambiguous ground truth. Overall, these examples demonstrate that e-value-based constructions provide a flexible expansion of the toolbox of conformal prediction.
Authors: Dian Chen, Han Jun Yoon, Zelin Wan, Nithin Alluru, Sang Won Lee, Richard He, Terrence J. Moore, Frederica F. Nelson, Sunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Jin-Hee Cho
Abstract: Human-Machine Teaming (HMT) is revolutionizing collaboration across domains such as defense, healthcare, and autonomous systems by integrating AI-driven decision-making, trust calibration, and adaptive teaming. This survey presents a comprehensive taxonomy of HMT, analyzing theoretical models, including reinforcement learning, instance-based learning, and interdependence theory, alongside interdisciplinary methodologies. Unlike prior reviews, we examine team cognition, ethical AI, multi-modal interactions, and real-world evaluation frameworks. Key challenges include explainability, role allocation, and scalable benchmarking. We propose future research in cross-domain adaptation, trust-aware AI, and standardized testbeds. By bridging computational and social sciences, this work lays a foundation for resilient, ethical, and scalable HMT systems.
Authors: Ruoxi Cheng, Haoxuan Ma, Weixin Wang
Abstract: The alignment of large language models (LLMs) with human values remains critical yet hindered by four key challenges: (1) scarcity of balanced safety datasets, (2) alignment tax, (3) vulnerability to jailbreak attacks due to shallow alignment, and (4) inability to dynamically adapt rewards according to task difficulty. To address these limitations, we introduce HAIR (Hardness-Aware Inverse Reinforcement Learning with Introspective Reasoning), a novel alignment approach inspired by shadow models in membership inference attacks. Our approach consists of two main components: (1) construction of a balanced safety Chain-of-Draft (CoD) dataset for seven harmful categories using structured prompts that leverage the introspective reasoning capabilities of LLMs; and (2) training of category-specific reward models with Group Relative Policy Optimization (GRPO), dynamically tuning optimization to task difficulty at both the data and model levels. Comprehensive experiments across four harmlessness and four usefulness benchmarks demonstrate that HAIR achieves state-of-the-art performance, outperforming all baseline methods in safety while maintaining high levels of usefulness.
Authors: Zijun Jia
Abstract: Road rage, often triggered by emotional suppression and sudden outbursts, significantly threatens road safety by causing collisions and aggressive behavior. Speech emotion recognition technologies can mitigate this risk by identifying negative emotions early and issuing timely alerts. However, current SER methods, such as those based on hidden markov models and Long short-term memory networks, primarily handle one-dimensional signals, frequently experience overfitting, and lack calibration, limiting their safety-critical effectiveness. We propose a novel risk-controlled prediction framework providing statistically rigorous guarantees on prediction accuracy. This approach employs a calibration set to define a binary loss function indicating whether the true label is included in the prediction set. Using a data-driven threshold $\beta$, we optimize a joint loss function to maintain an expected test loss bounded by a user-specified risk level $\alpha$. Evaluations across six baseline models and two benchmark datasets demonstrate our framework consistently achieves a minimum coverage of $1 - \alpha$, effectively controlling marginal error rates despite varying calibration-test split ratios (e.g., 0.1). The robustness and generalizability of the framework are further validated through an extension to small-batch online calibration under a local exchangeability assumption. We construct a non-negative test martingale to maintain prediction validity even in dynamic and non-exchangeable environments. Cross-dataset tests confirm our method's ability to uphold reliable statistical guarantees in realistic, evolving data scenarios.
Authors: Kyuhan Lee, Geon Lee, Kijung Shin
Abstract: Hypergraphs offer a powerful framework for modeling higher-order interactions that traditional pairwise graphs cannot fully capture. However, practical constraints often lead to their simplification into projected graphs, resulting in substantial information loss and ambiguity in representing higher-order relationships. In this work, we propose MARIOH, a supervised approach for reconstructing the original hypergraph from its projected graph by leveraging edge multiplicity. To overcome the difficulties posed by the large search space, MARIOH integrates several key ideas: (a) identifying provable size-2 hyperedges, which reduces the candidate search space, (b) predicting the likelihood of candidates being hyperedges by utilizing both structural and multiplicity-related features, and (c) not only targeting promising hyperedge candidates but also examining less confident ones to explore alternative possibilities. Together, these ideas enable MARIOH to efficiently and effectively explore the search space. In our experiments using 10 real-world datasets, MARIOH achieves up to 74.51% higher reconstruction accuracy compared to state-of-the-art methods.
Authors: Mahjabin Nahar, Eun-Ju Lee, Jin Won Park, Dongwon Lee
Abstract: While we increasingly rely on large language models (LLMs) for various tasks, these models are known to produce inaccurate content or `hallucinations' with potentially disastrous consequences. The recent integration of web search results into LLMs prompts the question of whether people utilize them to verify the generated content, thereby accurately detecting hallucinations. An online experiment (N = 560) investigated how the provision of search results, either static (i.e., fixed search results provided by LLM) or dynamic (i.e., participant-led searches), affects participants' perceived accuracy of LLM-generated content (i.e., genuine, minor hallucination, major hallucination), self-confidence in accuracy ratings, as well as their overall evaluation of the LLM, as compared to the control condition (i.e., no search results). Results showed that participants in both static and dynamic conditions (vs. control) rated hallucinated content to be less accurate and perceived the LLM more negatively. However, those in the dynamic condition rated genuine content as more accurate and demonstrated greater overall self-confidence in their assessments than those in the static search or control conditions. We highlighted practical implications of incorporating web search functionality into LLMs in real-world contexts.
Authors: Youngjune Lee, Haeyu Jeong, Changgeon Lim, Jeong Choi, Hongjun Lim, Hangon Kim, Jiyoon Kwon, Saehun Kim
Abstract: Online community platforms require dynamic personalized retrieval and recommendation that can continuously adapt to evolving user interests and new documents. However, optimizing models to handle such changes in real-time remains a major challenge in large-scale industrial settings. To address this, we propose the Interest-aware Representation and Alignment (IRA) framework, an efficient and scalable approach that dynamically adapts to new interactions through a cumulative structure. IRA leverages two key mechanisms: (1) Interest Units that capture diverse user interests as contextual texts, while reinforcing or fading over time through cumulative updates, and (2) a retrieval process that measures the relevance between Interest Units and documents based solely on semantic relationships, eliminating dependence on click signals to mitigate temporal biases. By integrating cumulative Interest Unit updates with the retrieval process, IRA continuously adapts to evolving user preferences, ensuring robust and fine-grained personalization without being constrained by past training distributions. We validate the effectiveness of IRA through extensive experiments on real-world datasets, including its deployment in the Home Section of NAVER's CAFE, South Korea's leading community platform.
Authors: Raza Ul Mustafa, Sesha Dassanayake, Noman Ashraf, Romana Aziz, Ala Saleh Alluhaidan
Abstract: The Quality of Experience (QoE) is the users satisfaction while streaming a video session over an over-the-top (OTT) platform like YouTube. QoE of YouTube reflects the smooth streaming session without any buffering and quality shift events. One of the most important factors nowadays affecting QoE of YouTube is frequent shifts from higher to lower resolutions and vice versa. These shifts ensure a smooth streaming session; however, it might get a lower mean opinion score. For instance, dropping from 1080p to 480p during a video can preserve continuity but might reduce the viewers enjoyment. Over time, OTT platforms are looking for alternative ways to boost user experience instead of relying on traditional Quality of Service (QoS) metrics such as bandwidth, latency, and throughput. As a result, we look into the relationship between quality shifting in YouTube streaming sessions and the channel metrics RSRP, RSRQ, and SNR. Our findings state that these channel metrics positively correlate with shifts. Thus, in real-time, OTT can only rely on them to predict video streaming sessions into lower- and higher-resolution categories, thus providing more resources to improve user experience. Using traditional Machine Learning (ML) classifiers, we achieved an accuracy of 77-percent, while using only RSRP, RSRQ, and SNR. In the era of 5G and beyond, where ultra-reliable, low-latency networks promise enhanced streaming capabilities, the proposed methodology can be used to improve OTT services.
Authors: Vijay Prakash S
Abstract: Straight line equation $y=mx$ with slope $m$, when singularly perturbed as $ay^3+y=mx$ with a positive parameter $a$, results in S-shaped curves or S-curves on a real plane. As $a\rightarrow 0$, we get back $y=mx$ which is a cumulative distribution function of a continuous uniform distribution that describes the occurrence of every event in an interval to be equally probable. As $a\rightarrow\infty$, the derivative of $y$ has finite support only at $y=0$ resembling a degenerate distribution. Based on these arguments, in this work, we propose that these S-curves can represent maximum entropy uniform distribution to a zero entropy single value. We also argue that these S-curves are superposable as they are only parametrically nonlinear but fundamentally linear. So far, the superposed forms have been used to capture the patterns of natural systems such as nonlinear dynamics of biological growth and kinetics of enzyme reactions. Here, we attempt to use the S-curve and its superposed form as statistical models. We fit the models on a classical dataset containing flower measurements of iris plants and analyze their usefulness in pattern recognition. Based on these models, we claim that any non-uniform pattern can be represented as a singular perturbation to uniform distribution. However, our parametric estimation procedure have some limitations such as sensitivity to initial conditions depending on the data at hand.
Authors: Natnael Alemayehu
Abstract: This study presents a convolutional neural network (CNN)-based approach for the multi-class classification of brain tumors using magnetic resonance imaging (MRI) scans. We utilize a publicly available dataset containing MRI images categorized into four classes: glioma, meningioma, pituitary tumor, and no tumor. Our primary objective is to build a light weight deep learning model that can automatically classify brain tumor types with high accuracy. To achieve this goal, we incorporate image preprocessing steps, including normalization, data augmentation, and a cropping technique designed to reduce background noise and emphasize relevant regions. The CNN architecture is optimized through hyperparameter tuning using Keras Tuner, enabling systematic exploration of network parameters. To ensure reliable evaluation, we apply 5-fold cross-validation, where each hyperparameter configuration is evaluated across multiple data splits to mitigate overfitting. Experimental results demonstrate that the proposed model achieves a classification accuracy of 98.78%, indicating its potential as a diagnostic aid in clinical settings. The proposed method offers a low-complexity yet effective solution for assisting in early brain tumor diagnosis.
Authors: Akhiad Bercovich, Itay Levy, Izik Golan, Mohammad Dabbah, Ran El-Yaniv, Omri Puny, Ido Galil, Zach Moshe, Tomer Ronen, Najeeb Nabwani, Ido Shahaf, Oren Tropp, Ehud Karpas, Ran Zilberstein, Jiaqi Zeng, Soumye Singhal, Alexander Bukharin, Yian Zhang, Tugrul Konuk, Gerald Shen, Ameya Sunil Mahabaleshwarkar, Bilal Kartal, Yoshi Suhara, Olivier Delalleau, Zijia Chen, Zhilin Wang, David Mosallanezhad, Adi Renduchintala, Haifeng Qian, Dima Rekesh, Fei Jia, Somshubra Majumdar, Vahid Noroozi, Wasi Uddin Ahmad, Sean Narenthiran, Aleksander Ficek, Mehrzad Samadi, Jocelyn Huang, Siddhartha Jain, Igor Gitman, Ivan Moshkov, Wei Du, Shubham Toshniwal, George Armstrong, Branislav Kisacanin, Matvei Novikov, Daria Gitman, Evelina Bakhturina, Jane Polak Scowcroft, John Kamalu, Dan Su, Kezhi Kong, Markus Kliegl, Rabeeh Karimi, Ying Lin, Sanjeev Satheesh, Jupinder Parmar, Pritam Gundecha, Brandon Norick, Joseph Jennings, Shrimai Prabhumoye, Syeda Nahida Akter, Mostofa Patwary, Abhinav Khattar, Deepak Narayanan, Roger Waleffe, Jimmy Zhang, Bor-Yiing Su, Guyue Huang, Terry Kong, Parth Chadha, Sahil Jain, Christine Harvey, Elad Segal, Jining Huang, Sergey Kashirsky, Robert McQueen, Izzy Putterman, George Lam, Arun Venkatesan, Sherry Wu, Vinh Nguyen, Manoj Kilaru, Andrew Wang, Anna Warno, Abhilash Somasamudramath, Sandip Bhaskar, Maka Dong, Nave Assaf, Shahar Mor, Omer Ullman Argov, Scot Junkin, Oleksandr Romanenko, Pedro Larroy, Monika Katariya, Marco Rovinelli, Viji Balas, Nicholas Edelman, Anahita Bhiwandiwalla, Muthu Subramaniam, Smita Ithape, Karthik Ramamoorthy, Yuting Wu, Suguna Varshini Velury, Omri Almog, Joyjit Daw, Denys Fridman, Erick Galinkin, Michael Evans, Katherine Luna, Leon Derczynski, Nikki Pope, Eileen Long, Seth Schneider, Guillermo Siman, Tomasz Grzegorzek, Pablo Ribalta, Monika Katariya, Joey Conway, Trisha Saar, Ann Guan, Krzysztof Pawelec, Shyamala Prayaga, Oleksii Kuchaiev, Boris Ginsburg, Oluwatobi Olabiyi, Kari Briski, Jonathan Cohen, Bryan Catanzaro, Jonah Alben, Yonatan Geifman, Eric Chung, Chris Alexiuk
Abstract: We introduce the Llama-Nemotron series of models, an open family of heterogeneous reasoning models that deliver exceptional reasoning capabilities, inference efficiency, and an open license for enterprise use. The family comes in three sizes -- Nano (8B), Super (49B), and Ultra (253B) -- and performs competitively with state-of-the-art reasoning models such as DeepSeek-R1 while offering superior inference throughput and memory efficiency. In this report, we discuss the training procedure for these models, which entails using neural architecture search from Llama 3 models for accelerated inference, knowledge distillation, and continued pretraining, followed by a reasoning-focused post-training stage consisting of two main parts: supervised fine-tuning and large scale reinforcement learning. Llama-Nemotron models are the first open-source models to support a dynamic reasoning toggle, allowing users to switch between standard chat and reasoning modes during inference. To further support open research and facilitate model development, we provide the following resources: 1. We release the Llama-Nemotron reasoning models -- LN-Nano, LN-Super, and LN-Ultra -- under the commercially permissive NVIDIA Open Model License Agreement. 2. We release the complete post-training dataset: Llama-Nemotron-Post-Training-Dataset. 3. We also release our training codebases: NeMo, NeMo-Aligner, and Megatron-LM.
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: 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: 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: Lingxiao Kong, Cong Yang, Susanne Neufang, Oya Deniz Beyan, Zeyd Boukhers
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.