Authors: Tao Yin, Chen Zhao, Xiaoyan Liu, Minglai Shao
Abstract: Graph neural networks (GNNs) are proven effective in extracting complex node and structural information from graph data. While current GNNs perform well in node classification tasks within in-distribution (ID) settings, real-world scenarios often present distribution shifts, leading to the presence of out-of-distribution (OOD) nodes. OOD detection in graphs is a crucial and challenging task. Most existing research focuses on homogeneous graphs, but real-world graphs are often heterogeneous, consisting of diverse node and edge types. This heterogeneity adds complexity and enriches the informational content. To the best of our knowledge, OOD detection in heterogeneous graphs remains an underexplored area. In this context, we propose a novel methodology for OOD detection in heterogeneous graphs (OODHG) that aims to achieve two main objectives: 1) detecting OOD nodes and 2) classifying all ID nodes based on the first task's results. Specifically, we learn representations for each node in the heterogeneous graph, calculate energy values to determine whether nodes are OOD, and then classify ID nodes. To leverage the structural information of heterogeneous graphs, we introduce a meta-path-based energy propagation mechanism and an energy constraint to enhance the distinction between ID and OOD nodes. Extensive experimental findings substantiate the simplicity and effectiveness of OODHG, demonstrating its superiority over baseline models in OOD detection tasks and its accuracy in ID node classification.
Authors: Linqing Chen, Weilei Wang, Wentao Wu, Hanmeng Zhong
Abstract: Hierarchical Extreme Multi-Label Classification poses greater difficulties compared to traditional multi-label classification because of the intricate hierarchical connections of labels within a domain-specific taxonomy and the substantial number of labels. Some of the prior research endeavors centered on classifying text through several ancillary stages such as the cluster algorithm and multiphase classification. Others made attempts to leverage the assistance of generative methods yet were unable to properly control the output of the generative model. We redefine the task from hierarchical multi-Label classification to Hierarchical Multi-Label Generation (HMG) and employ a generative framework with Probabilistic Level Constraints (PLC) to generate hierarchical labels within a specific taxonomy that have complex hierarchical relationships. The approach we proposed in this paper enables the framework to generate all relevant labels across levels for each document without relying on preliminary operations like clustering. Meanwhile, it can control the model output precisely in terms of count, length, and level aspects. Experiments demonstrate that our approach not only achieves a new SOTA performance in the HMG task, but also has a much better performance in constrained the output of model than previous research work.
Authors: Hansi Denis, Siegfried Mercelis, Ngoc-Quang Luong
Abstract: Optimization of the last-mile delivery and first-mile pickup of parcels is an integral part of the broader logistics optimization pipeline as it entails both cost and resource efficiency as well as a heightened service quality. Such optimization requires accurate route and time prediction systems to adapt to different scenarios in advance. This work tackles the first building block, namely route prediction. This is done by introducing a novel Proximity Attention mechanism in an encoder-decoder architecture utilizing a Pointer Network in the decoding process (Proximity Attention Encoder and Pointer Network decoder: PAPN) to leverage the underlying connections between the different visitable pickup positions at each timestep. To this local attention process is coupled global context computing via a multi-head attention transformer encoder. The obtained global context is then mixed to an aggregated version of the local embedding thus achieving a mix of global and local attention for complete modeling of the problems. Proximity attention is also used in the decoding process to skew predictions towards the locations with the highest attention scores and thus using inter-connectivity of locations as a base for next-location prediction. This method is trained, validated and tested on a large industry-level dataset of real-world, large-scale last-mile delivery and first-mile pickup named LaDE[1]. This approach shows noticeable promise, outperforming all state-of-the-art supervised systems in terms of most metrics used for benchmarking methods on this dataset while still being competitive with the best-performing reinforcement learning method named DRL4Route[2].
Authors: LG AI Research, Sehyun Chun, Jiye Kim, Ahra Jo, Yeonsik Jo, Seungyul Oh, Seungjun Lee, Kwangrok Ryoo, Jongmin Lee, Seunghwan Kim, Byung Jun Kang, Soonyoung Lee, Jun Ha Park, Chanwoo Moon, Jiwon Ham, Haein Lee, Heejae Han, Jaeseung Byun, Soojong Do, Minju Ha, Dongyun Kim, Kyunghoon Bae, Woohyung Lim, Edward Hwayoung Lee, Yongmin Park, Jeongsang Yu, Gerrard Jeongwon Jo, Yeonjung Hong, Kyungjae Yoo, Sehui Han, Jaewan Lee, Changyoung Park, Kijeong Jeon, Sihyuk Yi
Abstract: The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. To address this, we introduce MolMole, a vision-based deep learning framework that unifies molecule detection, reaction diagram parsing, and optical chemical structure recognition (OCSR) into a single pipeline for automating the extraction of chemical data directly from page-level documents. Recognizing the lack of a standard page-level benchmark and evaluation metric, we also present a testset of 550 pages annotated with molecule bounding boxes, reaction labels, and MOLfiles, along with a novel evaluation metric. Experimental results demonstrate that MolMole outperforms existing toolkits on both our benchmark and public datasets. The benchmark testset will be publicly available, and the MolMole toolkit will be accessible soon through an interactive demo on the LG AI Research website. For commercial inquiries, please contact us at \href{mailto:contact_ddu@lgresearch.ai}{contact\_ddu@lgresearch.ai}.
Authors: Jonathan Viquerat, Paul Garnier, Amirhossein Bateni, Elie Hachem
Abstract: Dragonfly is a deep reinforcement learning library focused on modularity, in order to ease experimentation and developments. It relies on a json serialization that allows to swap building blocks and perform parameter sweep, while minimizing code maintenance. Some of its features are specifically designed for CPU-intensive environments, such as numerical simulations. Its performance on standard agents using common benchmarks compares favorably with the literature.
Authors: Tao Liu, Tianyu Zhang, Yongxue Chen, Weiming Wang, Yu Jiang, Yuming Huang, Charlie C. L. Wang
Abstract: We propose a neural network-based computational framework for the simultaneous optimization of structural topology, curved layers, and path orientations to achieve strong anisotropic strength in fiber-reinforced thermoplastic composites while ensuring manufacturability. Our framework employs three implicit neural fields to represent geometric shape, layer sequence, and fiber orientation. This enables the direct formulation of both design and manufacturability objectives - such as anisotropic strength, structural volume, machine motion control, layer curvature, and layer thickness - into an integrated and differentiable optimization process. By incorporating these objectives as loss functions, the framework ensures that the resultant composites exhibit optimized mechanical strength while remaining its manufacturability for filament-based multi-axis 3D printing across diverse hardware platforms. Physical experiments demonstrate that the composites generated by our co-optimization method can achieve an improvement of up to 33.1% in failure loads compared to composites with sequentially optimized structures and manufacturing sequences.
Authors: Jin Yu, JaeHo Park, TaeJun Park, Gyurin Kim, JiHyun Lee, Min Sung Lee, Joon-myoung Kwon, Jeong Min Son, Yong-Yeon Jo
Abstract: Leveraging Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) for analyzing medical data, particularly Electrocardiogram (ECG), offers high accuracy and convenience. However, generating reliable, evidence-based results in specialized fields like healthcare remains a challenge, as RAG alone may not suffice. We propose a Zero-shot ECG diagnosis framework based on RAG for ECG analysis that incorporates expert-curated knowledge to enhance diagnostic accuracy and explainability. Evaluation on the PTB-XL dataset demonstrates the framework's effectiveness, highlighting the value of structured domain expertise in automated ECG interpretation. Our framework is designed to support comprehensive ECG analysis, addressing diverse diagnostic needs with potential applications beyond the tested dataset.
Authors: Tian Chen, Shengping Liu, Li Liu, Heng Yong
Abstract: Accurate modeling of closure terms is a critical challenge in engineering and scientific research, particularly when data is sparse (scarse or incomplete), making widely applicable models difficult to develop. This study proposes a novel approach for constructing closure models in such challenging scenarios. We introduce a Series-Parallel Multi-Network Architecture that integrates Physics-Informed Neural Networks (PINNs) to incorporate physical constraints and heterogeneous data from multiple initial and boundary conditions, while employing dedicated subnetworks to independently model unknown closure terms, enhancing generalizability across diverse problems. These closure models are integrated into an accurate Partial Differential Equation (PDE) solver, enabling robust solutions to complex predictive simulations in engineering applications.
Authors: Ahmed A. Metwally, A. Ali Heydari, Daniel McDuff, Alexandru Solot, Zeinab Esmaeilpour, Anthony Z Faranesh, Menglian Zhou, David B. Savage, Conor Heneghan, Shwetak Patel, Cathy Speed, Javier L. Prieto
Abstract: Insulin resistance, a precursor to type 2 diabetes, is characterized by impaired insulin action in tissues. Current methods for measuring insulin resistance, while effective, are expensive, inaccessible, not widely available and hinder opportunities for early intervention. In this study, we remotely recruited the largest dataset to date across the US to study insulin resistance (N=1,165 participants, with median BMI=28 kg/m2, age=45 years, HbA1c=5.4%), incorporating wearable device time series data and blood biomarkers, including the ground-truth measure of insulin resistance, homeostatic model assessment for insulin resistance (HOMA-IR). We developed deep neural network models to predict insulin resistance based on readily available digital and blood biomarkers. Our results show that our models can predict insulin resistance by combining both wearable data and readily available blood biomarkers better than either of the two data sources separately (R2=0.5, auROC=0.80, Sensitivity=76%, and specificity 84%). The model showed 93% sensitivity and 95% adjusted specificity in obese and sedentary participants, a subpopulation most vulnerable to developing type 2 diabetes and who could benefit most from early intervention. Rigorous evaluation of model performance, including interpretability, and robustness, facilitates generalizability across larger cohorts, which is demonstrated by reproducing the prediction performance on an independent validation cohort (N=72 participants). Additionally, we demonstrated how the predicted insulin resistance can be integrated into a large language model agent to help understand and contextualize HOMA-IR values, facilitating interpretation and safe personalized recommendations. This work offers the potential for early detection of people at risk of type 2 diabetes and thereby facilitate earlier implementation of preventative strategies.
Authors: Eleftherios Tzanis, Michail E. Klontzas
Abstract: Agentic systems built on large language models (LLMs) offer promising capabilities for automating complex workflows in healthcare AI. We introduce mAIstro, an open-source, autonomous multi-agentic framework for end-to-end development and deployment of medical AI models. The system orchestrates exploratory data analysis, radiomic feature extraction, image segmentation, classification, and regression through a natural language interface, requiring no coding from the user. Built on a modular architecture, mAIstro supports both open- and closed-source LLMs, and was evaluated using a large and diverse set of prompts across 16 open-source datasets, covering a wide range of imaging modalities, anatomical regions, and data types. The agents successfully executed all tasks, producing interpretable outputs and validated models. This work presents the first agentic framework capable of unifying data analysis, AI model development, and inference across varied healthcare applications, offering a reproducible and extensible foundation for clinical and research AI integration. The code is available at: https://github.com/eltzanis/mAIstro
Authors: Md Fahim Anjum
Abstract: Large Language Models (LLM) with reasoning capabilities offer a promising path for improving candidate evaluation in planning frameworks, but their relative performance against traditional non-reasoning models remains largely underexplored. In this study, we benchmark a distilled 1.5B parameter reasoning model (DeepSeek-R1) against several state-of-the-art non-reasoning LLMs within a generator-discriminator LLM planning framework for the text-to-SQL task. For this, we introduce a novel method for extracting soft scores from the chain-of-thought (CoT) outputs from reasoning that enables fine-grained ranking of candidates. Our central hypothesis is that reasoning models are more effective discriminators than non-reasoning LLMs. Our results show that distilled DeepSeek-R1-1.5B achieves up to $87\%$ higher F1 and $3.7\%$ better discrimination accuracy than CodeLlama-7B, as well as $3.7\%$ higher execution accuracy than CodeLlama-13B, despite having significantly fewer parameters. Furthermore, we find that there is a limit to the logical capabilities of reasoning models, and only providing more context or allowing more compute budget for reasoning is not enough to improve their discrimination performance. Finally, we demonstrate that, unlike non-reasoning LLMs, reasoning models find generation more challenging than discrimination and may underperform as generators compared to smaller non-reasoning LLMs. Our work highlights the potential of reasoning models as discriminators in agentic frameworks, far outweighing their capabilities as generators, offering insights into their optimal role within LLM planning infrastructures.
Authors: Zuraiz Baig, Sidra Nasir, Rizwan Ahmed Khan, Muhammad Zeeshan Ul Haque
Abstract: Cardiac arrhythmias are a leading cause of life-threatening cardiac events, highlighting the urgent need for accurate and timely detection. Electrocardiography (ECG) remains the clinical gold standard for arrhythmia diagnosis; however, manual interpretation is time-consuming, dependent on clinical expertise, and prone to human error. Although deep learning has advanced automated ECG analysis, many existing models abstract away the signal's intrinsic temporal and morphological features, lack interpretability, and are computationally intensive-hindering their deployment on resource-constrained platforms. In this work, we propose two novel lightweight 1D convolutional neural networks, ArrhythmiNet V1 and V2, optimized for efficient, real-time arrhythmia classification on edge devices. Inspired by MobileNet's depthwise separable convolutional design, these models maintain memory footprints of just 302.18 KB and 157.76 KB, respectively, while achieving classification accuracies of 0.99 (V1) and 0.98 (V2) on the MIT-BIH Arrhythmia Dataset across five classes: Normal Sinus Rhythm, Left Bundle Branch Block, Right Bundle Branch Block, Atrial Premature Contraction, and Premature Ventricular Contraction. In order to ensure clinical transparency and relevance, we integrate Shapley Additive Explanations and Gradient-weighted Class Activation Mapping, enabling both local and global interpretability. These techniques highlight physiologically meaningful patterns such as the QRS complex and T-wave that contribute to the model's predictions. We also discuss performance-efficiency trade-offs and address current limitations related to dataset diversity and generalizability. Overall, our findings demonstrate the feasibility of combining interpretability, predictive accuracy, and computational efficiency in practical, wearable, and embedded ECG monitoring systems.
Authors: Syoiti Ninomiya, Yuming Ma
Abstract: A new deep-learning neural network architecture based on high-order weak approximation algorithms for stochastic differential equations (SDEs) is proposed. The architecture enables the efficient learning of martingales by deep learning models. The behaviour of deep neural networks based on this architecture, when applied to the problem of pricing financial derivatives, is also examined. The core of this new architecture lies in the high-order weak approximation algorithms of the explicit Runge--Kutta type, wherein the approximation is realised solely through iterative compositions and linear combinations of vector fields of the target SDEs.
Authors: Yuren Zhang, Zhongnan Pu, Lei Jing
Abstract: With the development of Artificial Intelligence, numerous real-world tasks have been accomplished using technology integrated with deep learning. To achieve optimal performance, deep neural networks typically require large volumes of data for training. Although advances in data augmentation have facilitated the acquisition of vast datasets, most of this data is concentrated in domains like images and speech. However, there has been relatively less focus on augmenting time-series data. To address this gap and generate a substantial amount of time-series data, we propose a simple and effective method that combines the Diffusion and Transformer models. By utilizing an adjusted diffusion denoising model to generate a large volume of initial time-step action data, followed by employing a Transformer model to predict subsequent actions, and incorporating a weighted loss function to achieve convergence, the method demonstrates its effectiveness. Using the performance improvement of the model after applying augmented data as a benchmark, and comparing the results with those obtained without data augmentation or using traditional data augmentation methods, this approach shows its capability to produce high-quality augmented data.
Authors: Simon Golbert
Abstract: Boolean neural networks offer hardware-efficient alternatives to real-valued models. While quantization is common, purely Boolean training remains underexplored. We present a practical method for purely Boolean backpropagation for networks based on a single specific gate we chose, operating directly in Boolean algebra involving no numerics. Initial experiments confirm its feasibility.
Authors: Lang Feng, Weihao Tan, Zhiyi Lyu, Longtao Zheng, Haiyang Xu, Ming Yan, Fei Huang, Bo An
Abstract: Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform uncertainty to all tokens, CoSo leverages counterfactual reasoning to dynamically assess the causal influence of individual tokens on post-processed actions. By prioritizing the exploration of action-critical tokens while reducing the impact of semantically redundant or low-impact tokens, CoSo enables a more targeted and efficient online rollout process. We provide theoretical analysis proving CoSo's convergence and policy improvement guarantees, and extensive empirical evaluations supporting CoSo's effectiveness. Our results across a diverse set of agent tasks, including Android device control, card gaming, and embodied AI, highlight its remarkable ability to enhance exploration efficiency and deliver consistent performance gains. The code is available at https://github.com/langfengQ/CoSo.
Authors: Xinyue Zeng, Haohui Wang, Junhong Lin, Jun Wu, Tyler Cody, Dawei Zhou
Abstract: The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all candidates due to computational constraints. Despite the recent advances in LLM selection, a fundamental research question largely remains nascent: how can we model the dynamic behaviors of LLMs during fine-tuning, thereby enhancing our understanding of their generalization performance across diverse downstream tasks? In this work, we propose a novel theoretical framework that provides a proper lens to assess the generalization capabilities of LLMs, thereby enabling accurate and efficient LLM selection for downstream applications. In particular, we first derive a Hessian-based PAC-Bayes generalization bound that unveils fine-tuning dynamics of LLMs and then introduce LENSLLM, a Neural Tangent Kernel(NTK)-based Rectified Scaling Model that enables accurate performance predictions across diverse tasks while maintaining computational efficiency. Extensive empirical results on 3 large-scale benchmarks demonstrate that our model achieves up to 91.1% accuracy and reduces up to 88.5% computational cost in LLM selection, outperforming 5 state-of-the-art methods. We open-source our proposed LENSLLM model and corresponding results at the Github link: https://github.com/Susan571/LENSLLM.git.
Authors: \.Irfan I\c{s}ik, Ibrahim Karahan, Okan Erkaymaz
Abstract: This paper presents an improved forward-backward splitting algorithm with two inertial parameters. It aims to find a point in the real Hilbert space at which the sum of a co-coercive operator and a maximal monotone operator vanishes. Under standard assumptions, our proposed algorithm demonstrates weak convergence. We present numerous experimental results to demonstrate the behavior of the developed algorithm by comparing it with existing algorithms in the literature for regression and data classification problems. Furthermore, these implementations suggest our proposed algorithm yields superior outcomes when benchmarked against other relevant algorithms in existing literature.
Authors: Andrew Millard, Joshua Murphy, Simon Maskell, Zheng Zhao
Abstract: Partial Bayesian neural networks (pBNNs) have been shown to perform competitively with fully Bayesian neural networks while only having a subset of the parameters be stochastic. Using sequential Monte Carlo (SMC) samplers as the inference method for pBNNs gives a non-parametric probabilistic estimation of the stochastic parameters, and has shown improved performance over parametric methods. In this paper we introduce a new SMC-based training method for pBNNs by utilising a guided proposal and incorporating gradient-based Markov kernels, which gives us better scalability on high dimensional problems. We show that our new method outperforms the state-of-the-art in terms of predictive performance and optimal loss. We also show that pBNNs scale well with larger batch sizes, resulting in significantly reduced training times and often better performance.
Authors: Yiqing Shen, Hao Ding, Lalithkumar Seenivasan, Tianmin Shu, Mathias Unberath
Abstract: Current foundation models (FMs) rely on token representations that directly fragment continuous real-world multimodal data into discrete tokens. They limit FMs to learning real-world knowledge and relationships purely through statistical correlation rather than leveraging explicit domain knowledge. Consequently, current FMs struggle with maintaining semantic coherence across modalities, capturing fine-grained spatial-temporal dynamics, and performing causal reasoning. These limitations cannot be overcome by simply scaling up model size or expanding datasets. This position paper argues that the machine learning community should consider digital twin (DT) representations, which are outcome-driven digital representations that serve as building blocks for creating virtual replicas of physical processes, as an alternative to the token representation for building FMs. Finally, we discuss how DT representations can address these challenges by providing physically grounded representations that explicitly encode domain knowledge and preserve the continuous nature of real-world processes.
Authors: Hyun Lee, Chris Yi, Maminur Islam, B. D. S. Aritra
Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in various natural language processing tasks; however, their application to graph-related problems remains limited, primarily due to scalability constraints and the absence of dedicated mechanisms for processing graph structures. Existing approaches predominantly integrate LLMs with Graph Neural Networks (GNNs), using GNNs as feature encoders or auxiliary components. However, directly encoding graph structures within LLMs has been underexplored, particularly in the context of large-scale graphs where token limitations hinder effective representation. To address these challenges, we propose SDM-InstructGLM, a novel instruction-tuned Graph Language Model (InstructGLM) framework that enhances scalability and efficiency without relying on GNNs. Our method introduces a similarity-degree-based biased random walk mechanism, which selectively samples and encodes graph information based on node-feature similarity and degree centrality, ensuring an adaptive and structured representation within the LLM. This approach significantly improves token efficiency, mitigates information loss due to random sampling, and enhances performance on graph-based tasks such as node classification and link prediction. Furthermore, our results demonstrate the feasibility of LLM-only graph processing, enabling scalable and interpretable Graph Language Models (GLMs) optimized through instruction-based fine-tuning. This work paves the way for GNN-free approaches to graph learning, leveraging LLMs as standalone graph reasoning models. Our source code is available on GitHub.
Authors: Changhai Zhou, Qian Qiao, Weizhong Zhang, Cheng Jin
Abstract: Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge relates to the interaction and cooperation between low-rank and sparse matrices, while the second involves determining weight allocation across different layers, as redundancy varies considerably among them. To address these challenges, we propose a novel two-stage LLM compression method with the capability of global rank and sparsity optimization. It is noteworthy that the overall optimization space is vast, making comprehensive optimization computationally prohibitive. Therefore, to reduce the optimization space, our first stage utilizes robust principal component analysis to decompose the weight matrices of LLMs into low-rank and sparse components, which span the low dimensional and sparse spaces containing the resultant low-rank and sparse matrices, respectively. In the second stage, we propose a probabilistic global optimization technique to jointly identify the low-rank and sparse structures within the above two spaces. The appealing feature of our approach is its ability to automatically detect the redundancy across different layers and to manage the interaction between the sparse and low-rank components. Extensive experimental results indicate that our method significantly surpasses state-of-the-art techniques for sparsification and composite approximation.
Authors: Changhai Zhou, Yuhua Zhou, Qian Qiao, Weizhong Zhang, Cheng Jin
Abstract: QLoRA effectively combines low-bit quantization and LoRA to achieve memory-friendly fine-tuning for large language models (LLM). Recently, methods based on SVD for continuous update iterations to initialize LoRA matrices to accommodate quantization errors have generally failed to consistently improve performance. Dynamic mixed precision is a natural idea for continuously improving the fine-tuning performance of quantized models, but previous methods often optimize low-rank subspaces or quantization components separately, without considering their synergy. To address this, we propose \textbf{QR-Adaptor}, a unified, gradient-free strategy that uses partial calibration data to jointly search the quantization components and the rank of low-rank spaces for each layer, thereby continuously improving model performance. QR-Adaptor does not minimize quantization error but treats precision and rank allocation as a discrete optimization problem guided by actual downstream performance and memory usage. Compared to state-of-the-art (SOTA) quantized LoRA fine-tuning methods, our approach achieves a 4.89\% accuracy improvement on GSM8K, and in some cases even outperforms the 16-bit fine-tuned model while maintaining the memory footprint of the 4-bit setting.
Authors: Chen Xu, Yuxuan Yue, Zukang Xu, Xing Hu, Jiangyong Yu, Zhixuan Chen, Sifan Zhou, Zhihang Yuan, Dawei Yang
Abstract: RWKV is a modern RNN architecture with comparable performance to Transformer, but still faces challenges when deployed to resource-constrained devices. Post Training Quantization (PTQ), which is a an essential technique to reduce model size and inference latency, has been widely used in Transformer models. However, it suffers significant degradation of performance when applied to RWKV. This paper investigates and identifies two key constraints inherent in the properties of RWKV: (1) Non-linear operators hinder the parameter-fusion of both smooth- and rotation-based quantization, introducing extra computation overhead. (2) The larger amount of uniformly distributed weights poses challenges for cluster-based quantization, leading to reduced accuracy. To this end, we propose RWKVQuant, a PTQ framework tailored for RWKV models, consisting of two novel techniques: (1) a coarse-to-fine proxy capable of adaptively selecting different quantization approaches by assessing the uniformity and identifying outliers in the weights, and (2) a codebook optimization algorithm that enhances the performance of cluster-based quantization methods for element-wise multiplication in RWKV. Experiments show that RWKVQuant can quantize RWKV-6-14B into about 3-bit with less than 1% accuracy loss and 2.14x speed up.
Authors: Xing Hu, Zhixuan Chen, Dawei Yang, Zukang Xu, Chen Xu, Zhihang Yuan, Sifan Zhou, Jiangyong Yu
Abstract: Mixture-of-Experts (MoE) large language models (LLMs), which leverage dynamic routing and sparse activation to enhance efficiency and scalability, have achieved higher performance while reducing computational costs. However, these models face significant memory overheads, limiting their practical deployment and broader adoption. Post-training quantization (PTQ), a widely used method for compressing LLMs, encounters severe accuracy degradation and diminished generalization performance when applied to MoE models. This paper investigates the impact of MoE's sparse and dynamic characteristics on quantization and identifies two primary challenges: (1) Inter-expert imbalance, referring to the uneven distribution of samples across experts, which leads to insufficient and biased calibration for less frequently utilized experts; (2) Intra-expert imbalance, arising from MoE's unique aggregation mechanism, which leads to varying degrees of correlation between different samples and their assigned experts. To address these challenges, we propose MoEQuant, a novel quantization framework tailored for MoE LLMs. MoE-Quant includes two novel techniques: 1) Expert-Balanced Self-Sampling (EBSS) is an efficient sampling method that efficiently constructs a calibration set with balanced expert distributions by leveraging the cumulative probabilities of tokens and expert balance metrics as guiding factors. 2) Affinity-Guided Quantization (AGQ), which incorporates affinities between experts and samples into the quantization process, thereby accurately assessing the impact of individual samples on different experts within the MoE layer. Experiments demonstrate that MoEQuant achieves substantial performance gains (more than 10 points accuracy gain in the HumanEval for DeepSeekMoE-16B under 4-bit quantization) and boosts efficiency.
Authors: Nguyen Van Thanh
Abstract: Randomized Uphill Climbing is a lightweight, stochastic search heuristic that has delivered state of the art equity alpha factors for quantitative hedge funds. I propose to generalize RUC into a model agnostic feature optimization framework for multivariate time series forecasting. The core idea is to synthesize candidate feature programs by randomly composing operators from a domain specific grammar, score candidates rapidly with inexpensive surrogate models on rolling windows, and filter instability via nested cross validation and information theoretic shrinkage. By decoupling feature discovery from GPU heavy deep learning, the method promises faster iteration cycles, lower energy consumption, and greater interpretability. Societal relevance: accurate, transparent forecasting tools empower resource constrained institutions, energy regulators, climate risk NGOs to make data driven decisions without proprietary black box models.
Authors: Mehran Mazandarani, Marzieh Najariyan
Abstract: This article introduces Perception-Informed Neural Networks (PrINNs), a framework designed to incorporate perception-based information into neural networks, addressing both systems with known and unknown physics laws or differential equations. Moreover, PrINNs extend the concept of Physics-Informed Neural Networks (PINNs) and their variants, offering a platform for the integration of diverse forms of perception precisiation, including singular, probability distribution, possibility distribution, interval, and fuzzy graph. In fact, PrINNs allow neural networks to model dynamical systems by integrating expert knowledge and perception-based information through loss functions, enabling the creation of modern data-driven models. Some of the key contributions include Mixture of Experts Informed Neural Networks (MOEINNs), which combine heterogeneous expert knowledge into the network, and Transformed-Knowledge Informed Neural Networks (TKINNs), which facilitate the incorporation of meta-information for enhanced model performance. Additionally, Fuzzy-Informed Neural Networks (FINNs) as a modern class of fuzzy deep neural networks leverage fuzzy logic constraints within a deep learning architecture, allowing online training without pre-training and eliminating the need for defuzzification. PrINNs represent a significant step forward in bridging the gap between traditional physics-based modeling and modern data-driven approaches, enabling neural networks to learn from both structured physics laws and flexible perception-based rules. This approach empowers neural networks to operate in uncertain environments, model complex systems, and discover new forms of differential equations, making PrINNs a powerful tool for advancing computational science and engineering.
Authors: Ioannis Nasios
Abstract: Harmful algal blooms are a growing threat to inland water quality and public health worldwide, creating an urgent need for efficient, accurate, and cost-effective detection methods. This research introduces a high-performing methodology that integrates multiple open-source remote sensing data with advanced artificial intelligence models. Key data sources include Copernicus Sentinel-2 optical imagery, the Copernicus Digital Elevation Model (DEM), and NOAA's High-Resolution Rapid Refresh (HRRR) climate data, all efficiently retrieved using platforms like Google Earth Engine (GEE) and Microsoft Planetary Computer (MPC). The NIR and two SWIR bands from Sentinel-2, the altitude from the elevation model, the temperature and wind from NOAA as well as the longitude and latitude were the most important features. The approach combines two types of machine learning models, tree-based models and a neural network, into an ensemble for classifying algal bloom severity. While the tree models performed strongly on their own, incorporating a neural network added robustness and demonstrated how deep learning models can effectively use diverse remote sensing inputs. The method leverages high-resolution satellite imagery and AI-driven analysis to monitor algal blooms dynamically, and although initially developed for a NASA competition in the U.S., it shows potential for global application. The complete code is available for further adaptation and practical implementation, illustrating the convergence of remote sensing data and AI to address critical environmental challenges (https://github.com/IoannisNasios/HarmfulAlgalBloomDetection).
URLs: https://github.com/IoannisNasios/HarmfulAlgalBloomDetection).
Authors: Suorong Yang, Peng Ye, Furao Shen, Dongzhan Zhou
Abstract: Dynamic data selection aims to accelerate training with lossless performance. However, reducing training data inherently limits data diversity, potentially hindering generalization. While data augmentation is widely used to enhance diversity, it is typically not optimized in conjunction with selection. As a result, directly combining these techniques fails to fully exploit their synergies. To tackle the challenge, we propose a novel online data training framework that, for the first time, unifies dynamic data selection and augmentation, achieving both training efficiency and enhanced performance. Our method estimates each sample's joint distribution of local density and multimodal semantic consistency, allowing for the targeted selection of augmentation-suitable samples while suppressing the inclusion of noisy or ambiguous data. This enables a more significant reduction in dataset size without sacrificing model generalization. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches on various benchmark datasets and architectures, e.g., reducing 50\% training costs on ImageNet-1k with lossless performance. Furthermore, our approach enhances noise resistance and improves model robustness, reinforcing its practical utility in real-world scenarios.
Authors: Euntae Choi, Sumin Song, Woosang Lim, Sungjoo Yoo
Abstract: Large Language Models (LLMs) face deployment challenges due to high computational costs, and while Post-Training Quantization (PTQ) offers a solution, existing rotation-based methods struggle at very low bit-widths like 2-bit. We introduce a novel, training-free approach to construct an improved rotation matrix, addressing the limitations of current methods. The key contributions include leveraging the Walsh-Hadamard transform with sequency ordering, which clusters similar frequency components to reduce quantization error compared to standard Hadamard matrices, significantly improving performance. Furthermore, we propose a Grouped Sequency-arranged Rotation (GSR) using block-diagonal matrices with smaller Walsh blocks, effectively isolating outlier impacts and achieving performance comparable to optimization-based methods without requiring any training. Our method demonstrates robust performance on reasoning tasks and Perplexity (PPL) score on WikiText-2. Our method also enhances results even when applied over existing learned rotation techniques.
Authors: Surajit Chakrabarty, Rukma Talwadker, Tridib Mukherjee
Abstract: This paper introduces ScarceGAN which focuses on identification of extremely rare or scarce samples from multi-dimensional longitudinal telemetry data with small and weak label prior. We specifically address: (i) severe scarcity in positive class, stemming from both underlying organic skew in the data, as well as extremely limited labels; (ii) multi-class nature of the negative samples, with uneven density distributions and partially overlapping feature distributions; and (iii) massively unlabelled data leading to tiny and weak prior on both positive and negative classes, and possibility of unseen or unknown behavior in the unlabelled set, especially in the negative class. Although related to PU learning problems, we contend that knowledge (or lack of it) on the negative class can be leveraged to learn the compliment of it (i.e., the positive class) better in a semi-supervised manner. To this effect, ScarceGAN re-formulates semi-supervised GAN by accommodating weakly labelled multi-class negative samples and the available positive samples. It relaxes the supervised discriminator's constraint on exact differentiation between negative samples by introducing a 'leeway' term for samples with noisy prior. We propose modifications to the cost objectives of discriminator, in supervised and unsupervised path as well as that of the generator. For identifying risky players in skill gaming, this formulation in whole gives us a recall of over 85% (~60% jump over vanilla semi-supervised GAN) on our scarce class with very minimal verbosity in the unknown space. Further ScarceGAN outperforms the recall benchmarks established by recent GAN based specialized models for the positive imbalanced class identification and establishes a new benchmark in identifying one of rare attack classes (0.09%) in the intrusion dataset from the KDDCUP99 challenge.
Authors: Tomaso Aste
Abstract: Information Filtering Networks (IFNs) provide a powerful framework for modeling complex systems through globally sparse yet locally dense and interpretable structures that capture multivariate dependencies. This review offers a comprehensive account of IFNs, covering their theoretical foundations, construction methodologies, and diverse applications. Tracing their origins from early network-based models to advanced formulations such as the Triangulated Maximally Filtered Graph (TMFG) and the Maximally Filtered Clique Forest (MFCF), the paper highlights how IFNs address key challenges in high-dimensional data-driven modeling. IFNs and their construction methodologies are intrinsically higher-order networks that generate simplicial complexes-structures that are only now becoming popular in the broader literature. Applications span fields including finance, biology, psychology, and artificial intelligence, where IFNs improve interpretability, computational efficiency, and predictive performance. Special attention is given to their role in graphical modeling, where IFNs enable the estimation of sparse inverse covariance matrices with greater accuracy and scalability than traditional approaches like Graphical LASSO. Finally, the review discusses recent developments that integrate IFNs with machine learning and deep learning, underscoring their potential not only to bridge classical network theory with contemporary data-driven paradigms, but also to shape the architectures of deep learning models themselves.
Authors: Antonio Valerio Miceli-Barone, Vaishak Belle, Ali Payani
Abstract: Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics. Finding training examples to teach LLMs to solve these tasks can be challenging. In this work, we explore a method to synthetically generate code reasoning training data based on a semantic inequivalence game SInQ: a generator agent creates program variants that are semantically distinct, derived from a dataset of real-world programming tasks, while an evaluator agent has to identify input examples that cause the original programs and the generated variants to diverge in their behaviour, with the agents training each other semi-adversarially. We prove that this setup enables theoretically unlimited improvement through self-play in the limit of infinite computational resources. We evaluated our approach on multiple code generation and understanding benchmarks, including cross-language vulnerability detection (Lu et al., 2021), where our method improves vulnerability detection in C/C++ code despite being trained exclusively on Python code, and the challenging Python builtin identifier swap benchmark (Miceli-Barone et al., 2023), showing that whereas modern LLMs still struggle with this benchmark, our approach yields substantial improvements. We release the code needed to replicate the experiments, as well as the generated synthetic data, which can be used to fine-tune LLMs.
Authors: Johannes Schneider
Abstract: We propose two novel test-time fine-tuning methods to improve uncertain model predictions. Our methods require no auxiliary data and use the given test instance only. Instead of performing a greedy selection of the most likely class to make a prediction, we introduce an additional focus on the likely classes step during inference. By applying a single-step gradient descent, we refine predictions when an initial forward pass indicates high uncertainty. This aligns predictions more closely with the ideal of assigning zero probability to less plausible outcomes. Our theoretical discussion provides a deeper understanding highlighting the impact on shared and non-shared features among (focus) classes. The experimental evaluation highlights accuracy gains on samples exhibiting high decision uncertainty for a diverse set of models from both the text and image domain using the same hyperparameters.
Authors: Hao Wu, Jialiang Wang
Abstract: Quality-of-Service (QoS) data plays a crucial role in cloud service selection. Since users cannot access all services, QoS can be represented by a high-dimensional and incomplete (HDI) matrix. Latent factor analysis (LFA) models have been proven effective as low-rank representation techniques for addressing this issue. However, most LFA models rely on first-order optimizers and use L2-norm regularization, which can lead to lower QoS prediction accuracy. To address this issue, this paper proposes a double regularized second-order latent factor (DRSLF) model with two key ideas: a) integrating L1-norm and L2-norm regularization terms to enhance the low-rank representation performance; b) incorporating second-order information by calculating the Hessian-vector product in each conjugate gradient step. Experimental results on two real-world response-time QoS datasets demonstrate that DRSLF has a higher low-rank representation capability than two baselines.
Authors: Anushiya Arunan, Yan Qin, Xiaoli Li, Yuen Chau
Abstract: Classification of multi-dimensional time series from real-world systems require fine-grained learning of complex features such as cross-dimensional dependencies and intra-class variations-all under the practical challenge of low training data availability. However, standard deep learning (DL) struggles to learn generalizable features in low-data environments due to model overfitting. We propose a versatile yet data-efficient framework, Intelligently Augmented Contrastive Tensor Factorization (ITA-CTF), to learn effective representations from multi-dimensional time series. The CTF module learns core explanatory components of the time series (e.g., sensor factors, temporal factors), and importantly, their joint dependencies. Notably, unlike standard tensor factorization (TF), the CTF module incorporates a new contrastive loss optimization to induce similarity learning and class-awareness into the learnt representations for better classification performance. To strengthen this contrastive learning, the preceding ITA module generates targeted but informative augmentations that highlight realistic intra-class patterns in the original data, while preserving class-wise properties. This is achieved by dynamically sampling a "soft" class prototype to guide the warping of each query data sample, which results in an augmentation that is intelligently pattern-mixed between the "soft" class prototype and the query sample. These augmentations enable the CTF module to recognize complex intra-class variations despite the limited original training data, and seek out invariant class-wise properties for accurate classification performance. The proposed method is comprehensively evaluated on five different classification tasks. Compared to standard TF and several DL benchmarks, notable performance improvements up to 18.7% were achieved.
Authors: Xin Wang, Ling Feng, Huijun Zhang, Lei Cao, Kaisheng Zeng, Qi Li, Yang Ding, Yi Dai, David Clifton
Abstract: Stress haunts people in modern society, which may cause severe health issues if left unattended. With social media becoming an integral part of daily life, leveraging social media to detect stress has gained increasing attention. While the majority of the work focuses on classifying stress states and stress categories, this study introduce a new task aimed at estimating more specific stressors (like exam, writing paper, etc.) through users' posts on social media. Unfortunately, the diversity of stressors with many different classes but a few examples per class, combined with the consistent arising of new stressors over time, hinders the machine understanding of stressors. To this end, we cast the stressor estimation problem within a practical scenario few-shot learning setting, and propose a novel meta-learning based stressor estimation framework that is enhanced by a meta-knowledge inheritance mechanism. This model can not only learn generic stressor context through meta-learning, but also has a good generalization ability to estimate new stressors with little labeled data. A fundamental breakthrough in our approach lies in the inclusion of the meta-knowledge inheritance mechanism, which equips our model with the ability to prevent catastrophic forgetting when adapting to new stressors. The experimental results show that our model achieves state-of-the-art performance compared with the baselines. Additionally, we construct a social media-based stressor estimation dataset that can help train artificial intelligence models to facilitate human well-being. The dataset is now public at \href{https://www.kaggle.com/datasets/xinwangcs/stressor-cause-of-mental-health-problem-dataset}{\underline{Kaggle}} and \href{https://huggingface.co/datasets/XinWangcs/Stressor}{\underline{Hugging Face}}.
URLs: https://www.kaggle.com/datasets/xinwangcs/stressor-cause-of-mental-health-problem-dataset, https://huggingface.co/datasets/XinWangcs/Stressor
Authors: Jonathan Gorard, Ammar Hakim, Hong Qin, Kyle Parfrey, Shantenu Jha
Abstract: Many inverse problems in nuclear fusion and high-energy astrophysics research, such as the optimization of tokamak reactor geometries or the inference of black hole parameters from interferometric images, necessitate high-dimensional parameter scans and large ensembles of simulations to be performed. Such inverse problems typically involve large uncertainties, both in the measurement parameters being inverted and in the underlying physics models themselves. Monte Carlo sampling, when combined with modern non-linear dimensionality reduction techniques such as autoencoders and manifold learning, can be used to reduce the size of the parameter spaces considerably. However, there is no guarantee that the resulting combinations of parameters will be physically valid, or even mathematically consistent. In this position paper, we advocate adopting a hybrid approach that leverages our recent advances in the development of formal verification methods for numerical algorithms, with the goal of constructing parameter space restrictions with provable mathematical and physical correctness properties, whilst nevertheless respecting both experimental uncertainties and uncertainties in the underlying physical processes.
Authors: Kyunghyun Cho
Abstract: This lecture note is intended to prepare early-year master's and PhD students in data science or a related discipline with foundational ideas in machine learning. It starts with basic ideas in modern machine learning with classification as a main target task. These basic ideas include loss formulation, backpropagation, stochastic gradient descent, generalization, model selection as well as fundamental blocks of artificial neural networks. Based on these basic ideas, the lecture note explores in depth the probablistic approach to unsupervised learning, covering directed latent variable models, product of experts, generative adversarial networks and autoregressive models. Finally, the note ends by covering a diverse set of further topics, such as reinforcement learning, ensemble methods and meta-learning. After reading this lecture note, a student should be ready to embark on studying and researching more advanced topics in machine learning and more broadly artificial intelligence.
Authors: Hans Hohenfeld, Marius Beuerle, Elie Mounzer
Abstract: Tensor networks, a class of variational quantum many-body wave functions have attracted considerable research interest across many disciplines, including classical machine learning. Recently, Aizpurua et al. demonstrated explainable anomaly detection with matrix product states on a discrete-valued cyber-security task, using quantum-inspired methods to gain insight into the learned model and detected anomalies. Here, we extend this framework to real-valued data domains. We furthermore introduce tree tensor networks for the task of explainable anomaly detection. We demonstrate these methods with three benchmark problems, show adequate predictive performance compared to several baseline models and both tensor network architectures' ability to explain anomalous samples. We thereby extend the application of tensor networks to a broader class of potential problems and open a pathway for future extensions to more complex tensor network architectures.
Authors: Pedram Pad, Hadi Hammoud, Mohamad Dia, Nadim Maamari, L. Andrea Dunbar
Abstract: Feature selection is a critical step in data-driven applications, reducing input dimensionality to enhance learning accuracy, computational efficiency, and interpretability. Existing state-of-the-art methods often require post-selection retraining and extensive hyperparameter tuning, complicating their adoption. We introduce a novel, non-intrusive feature selection layer that, given a target feature count $k$, automatically identifies and selects the $k$ most informative features during neural network training. Our method is uniquely simple, requiring no alterations to the loss function, network architecture, or post-selection retraining. The layer is mathematically elegant and can be fully described by: \begin{align} \nonumber \tilde{x}_i = a_i x_i + (1-a_i)z_i \end{align} where $x_i$ is the input feature, $\tilde{x}_i$ the output, $z_i$ a Gaussian noise, and $a_i$ trainable gain such that $\sum_i{a_i^2}=k$. This formulation induces an automatic clustering effect, driving $k$ of the $a_i$ gains to $1$ (selecting informative features) and the rest to $0$ (discarding redundant ones) via weighted noise distortion and gain normalization. Despite its extreme simplicity, our method delivers state-of-the-art performance on standard benchmark datasets and a novel real-world dataset, outperforming or matching existing approaches without requiring hyperparameter search for $k$ or retraining. Theoretical analysis in the context of linear regression further validates its efficacy. Our work demonstrates that simplicity and performance are not mutually exclusive, offering a powerful yet straightforward tool for feature selection in machine learning.
Authors: John Christopher Tidwell, John Storm Tidwell
Abstract: This project addresses the challenge of automated stock trading, where traditional methods and direct reinforcement learning (RL) struggle with market noise, complexity, and generalization. Our proposed solution is an integrated deep learning framework combining a Convolutional Neural Network (CNN) to identify patterns in technical indicators formatted as images, a Long Short-Term Memory (LSTM) network to capture temporal dependencies across both price history and technical indicators, and a Deep Q-Network (DQN) agent which learns the optimal trading policy (buy, sell, hold) based on the features extracted by the CNN and LSTM.
Authors: Noah Schutte, Grigorii Veviurko, Krzysztof Postek, Neil Yorke-Smith
Abstract: When solving optimization problems under uncertainty with contextual data, utilizing machine learning to predict the uncertain parameters is a popular and effective approach. Decision-focused learning (DFL) aims at learning a predictive model such that decision quality, instead of prediction accuracy, is maximized. Common practice here is to predict a single value for each uncertain parameter, implicitly assuming that there exists a (single-scenario) deterministic problem approximation (proxy) that is sufficient to obtain an optimal decision. Other work assumes the opposite, where the underlying distribution needs to be estimated. However, little is known about when either choice is valid. This paper investigates for the first time problem properties that justify using either assumption. Using this, we present effective decision proxies for DFL, with very limited compromise on the complexity of the learning task. We show the effectiveness of presented approaches in experiments on problems with continuous and discrete variables, as well as uncertainty in the objective function and in the constraints.
Authors: Charupriya Sharma, I\~naki Estella Aguerri, Daniel Guimarans
Abstract: Hierarchical forecasting with reconciliation requires forecasting values of a hierarchy (e.g.~customer demand in a state and district), such that forecast values are linked (e.g.~ district forecasts should add up to the state forecast). Basic forecasting provides no guarantee for these desired structural relationships. Reconciliation addresses this problem, which is crucial for organizations requiring coherent predictions across multiple aggregation levels. Current methods like minimum trace (MinT) are mostly limited to tree structures and are computationally expensive. We introduce FlowRec, which reformulates hierarchical forecast reconciliation as a network flow optimization, enabling forecasting on generalized network structures. While reconciliation under the $\ell_0$ norm is NP-hard, we prove polynomial-time solvability for all $\ell_{p > 0}$ norms and , for any strictly convex and continuously differentiable loss function. For sparse networks, FlowRec achieves $O(n^2\log n)$ complexity, significantly improving upon MinT's $O(n^3)$. Furthermore, we prove that FlowRec extends MinT to handle general networks, replacing MinT's error-covariance estimation step with direct network structural information. A key novelty of our approach is its handling of dynamic scenarios: while traditional methods recompute both base forecasts and reconciliation, FlowRec provides efficient localised updates with optimality guarantees. Monotonicity ensures that when forecasts improve incrementally, the initial reconciliation remains optimal. We also establish efficient, error-bounded approximate reconciliation, enabling fast updates in time-critical applications. Experiments on both simulated and real benchmarks demonstrate that FlowRec improves accuracy, runtime by 3-40x and memory usage by 5-7x. These results establish FlowRec as a powerful tool for large-scale hierarchical forecasting applications.
Authors: Guilherme S. Imai Aldeia, Hengzhe Zhang, Geoffrey Bomarito, Miles Cranmer, Alcides Fonseca, Bogdan Burlacu, William G. La Cava, Fabr\'icio Olivetti de Fran\c{c}a
Abstract: Symbolic Regression (SR) is a powerful technique for discovering interpretable mathematical expressions. However, benchmarking SR methods remains challenging due to the diversity of algorithms, datasets, and evaluation criteria. In this work, we present an updated version of SRBench. Our benchmark expands the previous one by nearly doubling the number of evaluated methods, refining evaluation metrics, and using improved visualizations of the results to understand the performances. Additionally, we analyze trade-offs between model complexity, accuracy, and energy consumption. Our results show that no single algorithm dominates across all datasets. We propose a call for action from SR community in maintaining and evolving SRBench as a living benchmark that reflects the state-of-the-art in symbolic regression, by standardizing hyperparameter tuning, execution constraints, and computational resource allocation. We also propose deprecation criteria to maintain the benchmark's relevance and discuss best practices for improving SR algorithms, such as adaptive hyperparameter tuning and energy-efficient implementations.
Authors: Aroon Sankoh, Victor Wickerhauser
Abstract: Stochastic differential equations such as the Ornstein-Uhlenbeck process have long been used to model realworld probablistic events such as stock prices and temperature fluctuations. While statistical methods such as Maximum Likelihood Estimation (MLE), Kalman Filtering, Inverse Variable Method, and more have historically been used to estimate the parameters of stochastic differential equations, the recent explosion of deep learning technology suggests that models such as a Recurrent Neural Network (RNN) could produce more precise estimators. We present a series of experiments that compare the estimation accuracy and computational expensiveness of a statistical method (MLE) with a deep learning model (RNN) for the parameters of the Ornstein-Uhlenbeck process.
Authors: Hengyuan Hu, Aniket Das, Dorsa Sadigh, Nima Anari
Abstract: Denoising Diffusion Probabilistic Models (DDPMs) have emerged as powerful tools for generative modeling. However, their sequential computation requirements lead to significant inference-time bottlenecks. In this work, we utilize the connection between DDPMs and Stochastic Localization to prove that, under an appropriate reparametrization, the increments of DDPM satisfy an exchangeability property. This general insight enables near-black-box adaptation of various performance optimization techniques from autoregressive models to the diffusion setting. To demonstrate this, we introduce \emph{Autospeculative Decoding} (ASD), an extension of the widely used speculative decoding algorithm to DDPMs that does not require any auxiliary draft models. Our theoretical analysis shows that ASD achieves a $\tilde{O} (K^{\frac{1}{3}})$ parallel runtime speedup over the $K$ step sequential DDPM. We also demonstrate that a practical implementation of autospeculative decoding accelerates DDPM inference significantly in various domains.
Authors: Jarren Briscoe, Garrett Kepler, Daryl Deford, Assefaw Gebremedhin
Abstract: Evaluating machine learning models is crucial not only for determining their technical accuracy but also for assessing their potential societal implications. While the potential for low-sample-size bias in algorithms is well known, we demonstrate the significance of sample-size bias induced by combinatorics in classification metrics. This revelation challenges the efficacy of these metrics in assessing bias with high resolution, especially when comparing groups of disparate sizes, which frequently arise in social applications. We provide analyses of the bias that appears in several commonly applied metrics and propose a model-agnostic assessment and correction technique. Additionally, we analyze counts of undefined cases in metric calculations, which can lead to misleading evaluations if improperly handled. This work illuminates the previously unrecognized challenge of combinatorics and probability in standard evaluation practices and thereby advances approaches for performing fair and trustworthy classification methods.
Authors: Prudhviraj Naidu, Zixian Wang, Leon Bergen, Ramamohan Paturi
Abstract: We train Transformer-based language models on ten foundational algorithmic tasks and observe pronounced phase transitions in their loss curves that deviate from established power-law scaling trends. Over large ranges of compute, the validation loss barely improves, then abruptly decreases. Probing the models' internal representations reveals the learning of quiet features during the stagnant phase, followed by sudden acquisition of loud features that coincide with the sharp drop in loss. Our ablation experiments show that disrupting a single learned feature can dramatically degrade performance, providing evidence of their causal role in task performance. These findings challenge the prevailing assumption that next-token predictive loss reliably tracks incremental progress; instead, key internal features may be developing below the surface until they coalesce, triggering a rapid performance gain.
Authors: Devan Selvaraj
Abstract: The muon optimizer has picked up much attention as of late as a possible replacement to the seemingly omnipresent Adam optimizer. Recently, care has been taken to document the scaling laws of hyper-parameters under muon such as weight decay and learning rate. However, at much larger scales the iterative orthogonalization procedure present in muon may suffer a possible issue as the singular values of random matrices shrink with scale. This paper shows this scaling behavior theoretically and empirically on random matrices but does not suggest what to do about it.
Authors: Xuyang Wang, Siyuan Duan, Qizhi Li, Guiduo Duan, Yuan Sun, Dezhong Peng
Abstract: Recently, trustworthy multi-view learning has attracted extensive attention because evidence learning can provide reliable uncertainty estimation to enhance the credibility of multi-view predictions. Existing trusted multi-view learning methods implicitly assume that multi-view data is secure. In practice, however, in safety-sensitive applications such as autonomous driving and security monitoring, multi-view data often faces threats from adversarial perturbations, thereby deceiving or disrupting multi-view learning models. This inevitably leads to the adversarial unreliability problem (AUP) in trusted multi-view learning. To overcome this tricky problem, we propose a novel multi-view learning framework, namely Reliable Disentanglement Multi-view Learning (RDML). Specifically, we first propose evidential disentanglement learning to decompose each view into clean and adversarial parts under the guidance of corresponding evidences, which is extracted by a pretrained evidence extractor. Then, we employ the feature recalibration module to mitigate the negative impact of adversarial perturbations and extract potential informative features from them. Finally, to further ignore the irreparable adversarial interferences, a view-level evidential attention mechanism is designed. Extensive experiments on multi-view classification tasks with adversarial attacks show that our RDML outperforms the state-of-the-art multi-view learning methods by a relatively large margin.
Authors: Tuochao Chen, Nicholas Batchelder, Alisa Liu, Noah Smith, Shyamnath Gollakota
Abstract: We introduce LlamaPIE, the first real-time proactive assistant designed to enhance human conversations through discreet, concise guidance delivered via hearable devices. Unlike traditional language models that require explicit user invocation, this assistant operates in the background, anticipating user needs without interrupting conversations. We address several challenges, including determining when to respond, crafting concise responses that enhance conversations, leveraging knowledge of the user for context-aware assistance, and real-time, on-device processing. To achieve this, we construct a semi-synthetic dialogue dataset and propose a two-model pipeline: a small model that decides when to respond and a larger model that generates the response. We evaluate our approach on real-world datasets, demonstrating its effectiveness in providing helpful, unobtrusive assistance. User studies with our assistant, implemented on Apple Silicon M2 hardware, show a strong preference for the proactive assistant over both a baseline with no assistance and a reactive model, highlighting the potential of LlamaPie to enhance live conversations.
Authors: Teddy Foley, Spencer Guo, Henry Josephson, Anqi Qu, Jack Sanderson
Abstract: This paper examines whether large language model (LLM) capabilities can continue to advance without additional compute by analyzing the development and role of algorithms used in state-of-the-art LLMs. Motivated by regulatory efforts that have largely focused on restricting access to high-performance hardware, we ask: Can LLMs progress in a compute-constrained environment, and how do algorithmic innovations perform under such conditions? To address these questions, we introduce a novel classification framework that distinguishes between compute-dependent innovations -- which yield disproportionate benefits at high compute levels (e.g., the Transformer architecture and mixture-of-experts models) and compute-independent innovations, which improve efficiency across all compute scales (e.g., rotary positional encoding, FlashAttention, or layer normalization). We quantify these contributions using a metric called compute-equivalent gain (CEG), which estimates the additional compute that would be required to achieve similar improvements without these algorithmic advancements. To validate this framework, we conduct small-scale training experiments with a scaled-down GPT-2 model. Our results confirm that compute-independent advancements yield meaningful performance gains even in resource-constrained settings, with a CEG of up to $3.5\times$ over a baseline model. By contrast, compute-dependent advancements provided little benefit or even degraded performance at the small scale, reinforcing the importance of compute availability for certain algorithmic gains.
Authors: Aditya K. Ranjan, Siddharth Singh, Cunyang Wei, Abhinav Bhatele
Abstract: Graph neural networks have emerged as a potent class of neural networks capable of leveraging the connectivity and structure of real-world graphs to learn intricate properties and relationships between nodes. Many real-world graphs exceed the memory capacity of a GPU due to their sheer size, and using GNNs on them requires techniques such as mini-batch sampling to scale. However, this can lead to reduced accuracy in some cases, and sampling and data transfer from the CPU to the GPU can also slow down training. On the other hand, distributed full-graph training suffers from high communication overhead and load imbalance due to the irregular structure of graphs. We propose Plexus, a three-dimensional (3D) parallel approach for full-graph training that tackles these issues and scales to billion-edge graphs. Additionally, we introduce optimizations such as a permutation scheme for load balancing, and a performance model to predict the optimal 3D configuration. We evaluate Plexus on several graph datasets and show scaling results for up to 2048 GPUs on Perlmutter, which is 33% of the machine, and 2048 GCDs on Frontier. Plexus achieves unprecedented speedups of 2.3x-12.5x over existing methods and a reduction in the time to solution by 5.2-8.7x on Perlmutter and 7-54.2x on Frontier.
Authors: Sarah Hartman, Cheng Soon Ong, Julia Powles, Petra Kuhnert
Abstract: This position paper argues that achieving meaningful scientific and societal advances with artificial intelligence (AI) requires a responsible, application-driven approach (RAD) to AI research. As AI is increasingly integrated into society, AI researchers must engage with the specific contexts where AI is being applied. This includes being responsive to ethical and legal considerations, technical and societal constraints, and public discourse. We present the case for RAD-AI to drive research through a three-staged approach: (1) building transdisciplinary teams and people-centred studies; (2) addressing context-specific methods, ethical commitments, assumptions, and metrics; and (3) testing and sustaining efficacy through staged testbeds and a community of practice. We present a vision for the future of application-driven AI research to unlock new value through technically feasible methods that are adaptive to the contextual needs and values of the communities they ultimately serve.
Authors: David Noever, Forrest McKee
Abstract: This study presents a novel benchmark for evaluating Large Language Models (LLMs) using challenges derived from the Financial Modeling World Cup (FMWC) Excel competitions. We introduce a methodology for converting 113 existing FMWC challenges into programmatically evaluable JSON formats and use this dataset to compare the performance of several leading LLMs. Our findings demonstrate significant variations in performance across different challenge categories, with models showing specific strengths in pattern recognition tasks but struggling with complex numerical reasoning. The benchmark provides a standardized framework for assessing LLM capabilities in realistic business-oriented tasks rather than abstract academic problems. This research contributes to the growing field of AI benchmarking by establishing proficiency among the 1.5 billion people who daily use Microsoft Excel as a meaningful evaluation metric that bridges the gap between academic AI benchmarks and practical business applications.
Authors: Hongyi Li, Jun Xu, William Ward Armstrong
Abstract: We introduce the Learning Hyperplane Tree (LHT), a novel oblique decision tree model designed for expressive and interpretable classification. LHT fundamentally distinguishes itself through a non-iterative, statistically-driven approach to constructing splitting hyperplanes. Unlike methods that rely on iterative optimization or heuristics, LHT directly computes the hyperplane parameters, which are derived from feature weights based on the differences in feature expectations between classes within each node. This deterministic mechanism enables a direct and well-defined hyperplane construction process. Predictions leverage a unique piecewise linear membership function within leaf nodes, obtained via local least-squares fitting. We formally analyze the convergence of the LHT splitting process, ensuring that each split yields meaningful, non-empty partitions. Furthermore, we establish that the time complexity for building an LHT up to depth $d$ is $O(mnd)$, demonstrating the practical feasibility of constructing trees with powerful oblique splits using this methodology. The explicit feature weighting at each split provides inherent interpretability. Experimental results on benchmark datasets demonstrate LHT's competitive accuracy, positioning it as a practical, theoretically grounded, and interpretable alternative in the landscape of tree-based models. The implementation of the proposed method is available at https://github.com/Hongyi-Li-sz/LHT_model.
Authors: Yulong Wang, Yushuo Liu, Xiaoyi Duan, Kai Wang
Abstract: Multivariate time series forecasting is crucial across various industries, where accurate extraction of complex periodic and trend components can significantly enhance prediction performance. However, existing models often struggle to capture these intricate patterns. To address these challenges, we propose FilterTS, a novel forecasting model that utilizes specialized filtering techniques based on the frequency domain. FilterTS introduces a Dynamic Cross-Variable Filtering Module, a key innovation that dynamically leverages other variables as filters to extract and reinforce shared variable frequency components across variables in multivariate time series. Additionally, a Static Global Filtering Module captures stable frequency components, identified throughout the entire training set. Moreover, the model is built in the frequency domain, converting time-domain convolutions into frequency-domain multiplicative operations to enhance computational efficiency. Extensive experimental results on eight real-world datasets have demonstrated that FilterTS significantly outperforms existing methods in terms of prediction accuracy and computational efficiency.
Authors: Baida Zhang, Yakai Chen, Huichun Li, Zhenghu Zu
Abstract: Globally, the outbreaks of infectious diseases have exerted an extremely profound and severe influence on health security and the economy. During the critical phases of epidemics, devising effective intervention measures poses a significant challenge to both the academic and practical arenas. There is numerous research based on reinforcement learning to optimize intervention measures of infectious diseases. Nevertheless, most of these efforts have been confined within the differential equation based on infectious disease models. Although a limited number of studies have incorporated reinforcement learning methodologies into individual-based infectious disease models, the models employed therein have entailed simplifications and limitations, rendering it incapable of modeling the complexity and dynamics inherent in infectious disease transmission. We establish a decision-making framework based on an individual agent-based transmission model, utilizing reinforcement learning to continuously explore and develop a strategy function. The framework's validity is verified through both experimental and theoretical approaches. Covasim, a detailed and widely used agent-based disease transmission model, was modified to support reinforcement learning research. We conduct an exhaustive exploration of the application efficacy of multiple algorithms across diverse action spaces. Furthermore, we conduct an innovative preliminary theoretical analysis concerning the issue of "time coverage". The results of the experiment robustly validate the effectiveness and feasibility of the methodological framework of this study. The coping strategies gleaned therefrom prove highly efficacious in suppressing the expansion of the epidemic scale and safeguarding the stability of the economic system, thereby providing crucial reference perspectives for the formulation of global public health security strategies.
Authors: Sungwon Han, Seungeon Lee, Meeyoung Cha, Sercan O Arik, Jinsung Yoon
Abstract: Time series forecasting uses historical data to predict future trends, leveraging the relationships between past observations and available features. In this paper, we propose RAFT, a retrieval-augmented time series forecasting method to provide sufficient inductive biases and complement the model's learning capacity. When forecasting the subsequent time frames, we directly retrieve historical data candidates from the training dataset with patterns most similar to the input, and utilize the future values of these candidates alongside the inputs to obtain predictions. This simple approach augments the model's capacity by externally providing information about past patterns via retrieval modules. Our empirical evaluations on ten benchmark datasets show that RAFT consistently outperforms contemporary baselines with an average win ratio of 86%.
Authors: Yulong Wang, Xiaofeng Hu, Xiaojian Cui, Kai Wang
Abstract: Irregular multivariate time series (IMTS) are prevalent in real-world applications across many fields, where varying sensor frequencies and asynchronous measurements pose significant modeling challenges. Existing solutions often rely on a pre-alignment strategy to normalize data, which can distort intrinsic patterns and escalate computational and memory demands. Addressing these limitations, we introduce STRGCN, a Spatio-Temporal Relational Graph Convolutional Network that avoids pre-alignment and directly captures the complex interdependencies in IMTS by representing them as a fully connected graph. Each observation is represented as a node, allowing the model to effectively handle misaligned timestamps by mapping all inter-node relationships, thus faithfully preserving the asynchronous nature of the data. Moreover, we enhance this model with a hierarchical ``Sandwich'' structure that strategically aggregates nodes to optimize graph embeddings, reducing computational overhead while maintaining detailed local and global context. Extensive experiments on four public datasets demonstrate that STRGCN achieves state-of-the-art accuracy, competitive memory usage and training speed.
Authors: Zixiao Wang, Wenqian Zhao, Yunheng Shen, Yang Bai, Guojin Chen, Farzan Farnia, Bei Yu
Abstract: Recent advancements in layout pattern generation have been dominated by deep generative models. However, relying solely on neural networks for legality guarantees raises concerns in many practical applications. In this paper, we present \tool{DiffPattern}-Flex, a novel approach designed to generate reliable layout patterns efficiently. \tool{DiffPattern}-Flex incorporates a new method for generating diverse topologies using a discrete diffusion model while maintaining a lossless and compute-efficient layout representation. To ensure legal pattern generation, we employ {an} optimization-based, white-box pattern assessment process based on specific design rules. Furthermore, fast sampling and efficient legalization technologies are employed to accelerate the generation process. Experimental results across various benchmarks demonstrate that \tool{DiffPattern}-Flex significantly outperforms existing methods and excels at producing reliable layout patterns.
Authors: Ju-Hyung Lee, Yanqing Lu
Abstract: Wireless roaming is a critical yet challenging task for maintaining seamless connectivity in dynamic mobile environments. Conventional threshold-based or heuristic schemes often fail, leading to either sticky or excessive handovers. We introduce the first cross-layer use of an on-device large language model (LLM): high-level reasoning in the application layer that issues real-time actions executed in the PHY/MAC stack. The LLM addresses two tasks: (i) context-aware AP selection, where structured prompts fuse environmental cues (e.g., location, time) to choose the best BSSID; and (ii) dynamic threshold adjustment, where the model adaptively decides when to roam. To satisfy the tight latency and resource budgets of edge hardware, we apply a suite of optimizations-chain-of-thought prompting, parameter-efficient fine-tuning, and quantization. Experiments on indoor and outdoor datasets show that our approach surpasses legacy heuristics and DRL baselines, achieving a strong balance between roaming stability and signal quality. These findings underscore the promise of application-layer LLM reasoning for lower-layer wireless control in future edge systems.
Authors: Bang You, Chenxu Wang, Huaping Liu
Abstract: Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing intricate and spurious correlations between observations and actions, leading to failure under slight perturbations to the environment. To tackle this problem, in this work we introduce a novel inductive bias towards simple policies in reinforcement learning. The simplicity inductive bias is introduced by minimizing the entropy of entire action trajectories, corresponding to the number of bits required to describe information in action trajectories after the agent observes state trajectories. Our reinforcement learning agent, Trajectory Entropy Reinforcement Learning, is optimized to minimize the trajectory entropy while maximizing rewards. We show that the trajectory entropy can be effectively estimated by learning a variational parameterized action prediction model, and use the prediction model to construct an information-regularized reward function. Furthermore, we construct a practical algorithm that enables the joint optimization of models, including the policy and the prediction model. Experimental evaluations on several high-dimensional locomotion tasks show that our learned policies produce more cyclical and consistent action trajectories, and achieve superior performance, and robustness to noise and dynamic changes than the state-of-the-art.
Authors: Sung Yoo Lim, Hyunsoo Yun, Prateek Bansal, Dong-Kyu Kim, Eui-Jin Kim
Abstract: Generating a synthetic population that is both feasible and diverse is crucial for ensuring the validity of downstream activity schedule simulation in activity-based models (ABMs). While deep generative models (DGMs), such as variational autoencoders and generative adversarial networks, have been applied to this task, they often struggle to balance the inclusion of rare but plausible combinations (i.e., sampling zeros) with the exclusion of implausible ones (i.e., structural zeros). To improve feasibility while maintaining diversity, we propose a fine-tuning method for large language models (LLMs) that explicitly controls the autoregressive generation process through topological orderings derived from a Bayesian Network (BN). Experimental results show that our hybrid LLM-BN approach outperforms both traditional DGMs and proprietary LLMs (e.g., ChatGPT-4o) with few-shot learning. Specifically, our approach achieves approximately 95% feasibility, significantly higher than the ~80% observed in DGMs, while maintaining comparable diversity, making it well-suited for practical applications. Importantly, the method is based on a lightweight open-source LLM, enabling fine-tuning and inference on standard personal computing environments. This makes the approach cost-effective and scalable for large-scale applications, such as synthesizing populations in megacities, without relying on expensive infrastructure. By initiating the ABM pipeline with high-quality synthetic populations, our method improves overall simulation reliability and reduces downstream error propagation. The source code for these methods is available for research and practical application.
Authors: Ahmed Sayeed Faruk, Jason Sulskis, Elena Zheleva
Abstract: The gold standard for estimating causal effects is randomized controlled trial (RCT) or A/B testing where a random group of individuals from a population of interest are given treatment and the outcome is compared to a random group of individuals from the same population. However, A/B testing is challenging in the presence of interference, commonly occurring in social networks, where individuals can impact each others outcome. Moreover, A/B testing can incur a high performance loss when one of the treatment arms has a poor performance and the test continues to treat individuals with it. Therefore, it is important to design a strategy that can adapt over time and efficiently learn the total treatment effect in the network. We introduce two cluster-based multi-armed bandit (MAB) algorithms to gradually estimate the total treatment effect in a network while maximizing the expected reward by making a tradeoff between exploration and exploitation. We compare the performance of our MAB algorithms with a vanilla MAB algorithm that ignores clusters and the corresponding RCT methods on semi-synthetic data with simulated interference. The vanilla MAB algorithm shows higher reward-action ratio at the cost of higher treatment effect error due to undesired spillover. The cluster-based MAB algorithms show higher reward-action ratio compared to their corresponding RCT methods without sacrificing much accuracy in treatment effect estimation.
Authors: Mateo Lopez-Ledezma, Gissel Velarde
Abstract: Cybersecurity has become essential worldwide and at all levels, concerning individuals, institutions, and governments. A basic principle in cybersecurity is to be always alert. Therefore, automation is imperative in processes where the volume of daily operations is large. Several cybersecurity applications can be addressed as binary classification problems, including anomaly detection, fraud detection, intrusion detection, spam detection, or malware detection. We present three experiments. In the first experiment, we evaluate single classifiers including Random Forests, Light Gradient Boosting Machine, eXtreme Gradient Boosting, Logistic Regression, Decision Tree, and Gradient Boosting Decision Tree. In the second experiment, we test different sampling techniques including over-sampling, under-sampling, Synthetic Minority Over-sampling Technique, and Self-Paced Ensembling. In the last experiment, we evaluate Self-Paced Ensembling and its number of base classifiers. We found that imbalance learning techniques had positive and negative effects, as reported in related studies. Thus, these techniques should be applied with caution. Besides, we found different best performers for each dataset. Therefore, we recommend testing single classifiers and imbalance learning techniques for each new dataset and application involving imbalanced datasets as is the case in several cyber security applications.
Authors: Sanghyeon Park, Soo-Mook Moon
Abstract: Federated learning (FL) enables collaborative model training across distributed clients while preserving data locality. Although FedAvg pioneered synchronous rounds for global model averaging, slower devices can delay collective progress. Asynchronous FL (e.g., FedAsync) addresses stragglers by continuously integrating client updates, yet naive implementations risk client drift due to non-IID data and stale contributions. Some Blockchain-based FL approaches (e.g., BRAIN) employ robust weighting or scoring of updates to resist malicious or misaligned proposals. However, performance drops can still persist under severe data heterogeneity or high staleness, and synchronization overhead has emerged as a new concern due to its aggregator-free architectures. We introduce Fast-and-Reliable AI Network, FRAIN, a new asynchronous FL method that mitigates these limitations by incorporating two key ideas. First, our FastSync strategy eliminates the need to replay past model versions, enabling newcomers and infrequent participants to efficiently approximate the global model. Second, we adopt spherical linear interpolation (SLERP) when merging parameters, preserving models' directions and alleviating destructive interference from divergent local training. Experiments with a CNN image-classification model and a Transformer-based language model demonstrate that FRAIN achieves more stable and robust convergence than FedAvg, FedAsync, and BRAIN, especially under harsh environments: non-IID data distributions, networks that experience delays and require frequent re-synchronization, and the presence of malicious nodes.
Authors: Grzegorz Miebs, Rafa{\l} A. Bachorz
Abstract: Accurate estimation of production times is critical for effective manufacturing scheduling, yet traditional methods relying on expert analysis or historical data often fall short in dynamic or customized production environments. This paper introduces a data-driven approach that predicts manufacturing steps and their durations directly from a product's 3D model. By rendering the model into multiple 2D images and leveraging a neural network inspired by the Generative Query Network, the method learns to map geometric features into time estimates for predefined production steps enabling scalable, adaptive, and precise process planning across varied product types.
Authors: Jan Blechschmidt, Tom-Christian Riemer, Max Winkler, Martin Stoll, Jan-F. Pietschmann
Abstract: We develop a novel physics informed deep learning approach for solving nonlinear drift-diffusion equations on metric graphs. These models represent an important model class with a large number of applications in areas ranging from transport in biological cells to the motion of human crowds. While traditional numerical schemes require a large amount of tailoring, especially in the case of model design or parameter identification problems, physics informed deep operator networks (DeepONet) have emerged as a versatile tool for the solution of partial differential equations with the particular advantage that they easily incorporate parameter identification questions. We here present an approach where we first learn three DeepONet models for representative inflow, inner and outflow edges, resp., and then subsequently couple these models for the solution of the drift-diffusion metric graph problem by relying on an edge-based domain decomposition approach. We illustrate that our framework is applicable for the accurate evaluation of graph-coupled physics models and is well suited for solving optimization or inverse problems on these coupled networks.
Authors: Weiwei Ye, Zhuopeng Xu, Ning Gui
Abstract: Due to the dynamics of underlying physics and external influences, the uncertainty of time series often varies over time. However, existing Denoising Diffusion Probabilistic Models (DDPMs) often fail to capture this non-stationary nature, constrained by their constant variance assumption from the additive noise model (ANM). In this paper, we innovatively utilize the Location-Scale Noise Model (LSNM) to relax the fixed uncertainty assumption of ANM. A diffusion-based probabilistic forecasting framework, termed Non-stationary Diffusion (NsDiff), is designed based on LSNM that is capable of modeling the changing pattern of uncertainty. Specifically, NsDiff combines a denoising diffusion-based conditional generative model with a pre-trained conditional mean and variance estimator, enabling adaptive endpoint distribution modeling. Furthermore, we propose an uncertainty-aware noise schedule, which dynamically adjusts the noise levels to accurately reflect the data uncertainty at each step and integrates the time-varying variances into the diffusion process. Extensive experiments conducted on nine real-world and synthetic datasets demonstrate the superior performance of NsDiff compared to existing approaches. Code is available at https://github.com/wwy155/NsDiff.
Authors: Jacob Glenn Ayers, Buvaneswari A. Ramanan, Manzoor A. Khan
Abstract: As the adoption of deep learning models has grown beyond human capacity for verification, meta-algorithms are needed to ensure reliable model inference. Concept drift detection is a field dedicated to identifying statistical shifts that is underutilized in monitoring neural networks that may encounter inference data with distributional characteristics diverging from their training data. Given the wide variety of model architectures, applications, and datasets, it is important that concept drift detection algorithms are adaptable to different inference scenarios. In this paper, we introduce an application of the $\chi^2$ Goodness of Fit Hypothesis Test as a drift detection meta-algorithm applied to a multilayer perceptron, a convolutional neural network, and a transformer trained for machine vision as they are exposed to simulated drift during inference. To that end, we demonstrate how unexpected drops in accuracy due to concept drift can be detected without directly examining the inference outputs. Our approach enhances safety by ensuring models are continually evaluated for reliability across varying conditions.
Authors: Swagato Das, Arghya Pratihar, Swagatam Das
Abstract: Clustering algorithms play a pivotal role in unsupervised learning by identifying and grouping similar objects based on shared characteristics. While traditional clustering techniques, such as hard and fuzzy center-based clustering, have been widely used, they struggle with complex, high-dimensional, and non-Euclidean datasets. In particular, the Fuzzy $C$-Means (FCM) algorithm, despite its efficiency and popularity, exhibits notable limitations in non-Euclidean spaces. Euclidean spaces assume linear separability and uniform distance scaling, limiting their effectiveness in capturing complex, hierarchical, or non-Euclidean structures in fuzzy clustering. To overcome these challenges, we introduce Filtration-based Hyperbolic Fuzzy $C$-Means (HypeFCM), a novel clustering algorithm tailored for better representation of data relationships in non-Euclidean spaces. HypeFCM integrates the principles of fuzzy clustering with hyperbolic geometry and employs a weight-based filtering mechanism to improve performance. The algorithm initializes weights using a Dirichlet distribution and iteratively refines cluster centroids and membership assignments based on a hyperbolic metric in the Poincar\'e Disc model. Extensive experimental evaluations demonstrate that HypeFCM significantly outperforms conventional fuzzy clustering methods in non-Euclidean settings, underscoring its robustness and effectiveness.
Authors: Zichen Liu, Wei Zhang, Christof Sch\"utte, Tiejun Li
Abstract: We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets of functions, including most of the manifolds relevant to applications. Existing methods for generative modeling on manifolds rely on substantial geometric information such as geodesic curves or eigenfunctions of the Laplace-Beltrami operator and, as a result, they are limited to manifolds where such information is available. In contrast, our method, built on a projection scheme, can be applied to more general manifolds, as it only requires being able to evaluate the value and the first order derivatives of the function that defines the submanifold. We provide a theoretical analysis of our method in the continuous-time limit, which elucidates the connection between our RDDPMs and score-based generative models on manifolds. The capability of our method is demonstrated on datasets from previous studies and on new datasets sampled from two high-dimensional manifolds, i.e. $\mathrm{SO}(10)$ and the configuration space of molecular system alanine dipeptide with fixed dihedral angle.
Authors: Hao Peng, Xiang Huang, Shuo Sun, Ruitong Zhang, Philip S. Yu
Abstract: DBSCAN, a well-known density-based clustering algorithm, has gained widespread popularity and usage due to its effectiveness in identifying clusters of arbitrary shapes and handling noisy data. However, it encounters challenges in producing satisfactory cluster results when confronted with datasets of varying density scales, a common scenario in real-world applications. In this paper, we propose a novel Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning cluster framework, namely AR-DBSCAN. First, we model the initial dataset as a two-level encoding tree and categorize the data vertices into distinct density partitions according to the information uncertainty determined in the encoding tree. Each partition is then assigned to an agent to find the best clustering parameters without manual assistance. The allocation is density-adaptive, enabling AR-DBSCAN to effectively handle diverse density distributions within the dataset by utilizing distinct agents for different partitions. Second, a multi-agent deep reinforcement learning guided automatic parameter searching process is designed. The process of adjusting the parameter search direction by perceiving the clustering environment is modeled as a Markov decision process. Using a weakly-supervised reward training policy network, each agent adaptively learns the optimal clustering parameters by interacting with the clusters. Third, a recursive search mechanism adaptable to the data's scale is presented, enabling efficient and controlled exploration of large parameter spaces. Extensive experiments are conducted on nine artificial datasets and a real-world dataset. The results of offline and online tasks show that AR-DBSCAN not only improves clustering accuracy by up to 144.1% and 175.3% in the NMI and ARI metrics, respectively, but also is capable of robustly finding dominant parameters.
Authors: Hong Jin, Kaicheng Zhou, Jie Yin, Lan You, Zhifeng Zhou
Abstract: Heterogeneous graph neural networks (HeteGNNs) have demonstrated strong abilities to learn node representations by effectively extracting complex structural and semantic information in heterogeneous graphs. Most of the prevailing HeteGNNs follow the neighborhood aggregation paradigm, leveraging meta-path based message passing to learn latent node representations. However, due to the pairwise nature of meta-paths, these models fail to capture high-order relations among nodes, resulting in suboptimal performance. Additionally, the challenge of ``over-squashing'', where long-range message passing in HeteGNNs leads to severe information distortion, further limits the efficacy of these models. To address these limitations, this paper proposes MGA-HHN, a Multi-Granular Attention based Heterogeneous Hypergraph Neural Network for heterogeneous graph representation learning. MGA-HHN introduces two key innovations: (1) a novel approach for constructing meta-path based heterogeneous hypergraphs that explicitly models higher-order semantic information in heterogeneous graphs through multiple views, and (2) a multi-granular attention mechanism that operates at both the node and hyperedge levels. This mechanism enables the model to capture fine-grained interactions among nodes sharing the same semantic context within a hyperedge type, while preserving the diversity of semantics across different hyperedge types. As such, MGA-HHN effectively mitigates long-range message distortion and generates more expressive node representations. Extensive experiments on real-world benchmark datasets demonstrate that MGA-HHN outperforms state-of-the-art models, showcasing its effectiveness in node classification, node clustering and visualization tasks.
Authors: Arghya Pratihar, Kushal Bose, Swagatam Das
Abstract: Clustering aims to form groups of similar data points in an unsupervised regime. Yet, clustering complex datasets containing critically intertwined shapes poses significant challenges. The prevailing clustering algorithms widely depend on evaluating similarity measures based on Euclidean metrics. Exploring topological characteristics to perform clustering of complex datasets inevitably presents a better scope. The topological clustering algorithms predominantly perceive the point set through the lens of Simplicial complexes and Persistent homology. Despite these approaches, the existing topological clustering algorithms cannot somehow fully exploit topological structures and show inconsistent performances on some highly complicated datasets. This work aims to mitigate the limitations by identifying topologically similar neighbors through the Vietoris-Rips complex and Betti number filtration. In addition, we introduce the concept of the Betti sequences to capture flexibly essential features from the topological structures. Our proposed algorithm is adept at clustering complex, intertwined shapes contained in the datasets. We carried out experiments on several synthetic and real-world datasets. Our algorithm demonstrated commendable performances across the datasets compared to some of the well-known topology-based clustering algorithms.
Authors: Stavros Sykiotis
Abstract: The global energy landscape is undergoing a profound transformation, often referred to as the energy transition, driven by the urgent need to mitigate climate change, reduce greenhouse gas emissions, and ensure sustainable energy supplies. However, the undoubted complexity of new investments in renewables, as well as the phase out of high CO2-emission energy sources, hampers the pace of the energy transition and raises doubts as to whether new renewable energy sources are capable of solely meeting the climate target goals. This highlights the need to investigate alternative pathways to accelerate the energy transition, by identifying human activity domains with higher/excessive energy demands. Two notable examples where there is room for improvement, in the sense of reducing energy consumption and consequently CO2 emissions, are residential energy consumption and road transport. This dissertation investigates the development of novel Deep Learning techniques to create tools which solve limitations in these two key energy domains. Reduction of residential energy consumption can be achieved by empowering end-users with the user of Non-Intrusive Load Monitoring, whereas optimization of EV charging with Deep Reinforcement Learning can tackle road transport decarbonization.
Authors: Filipe Santos (CISUC, DEI, University of Coimbra), Jo\~ao Paulo Fernandes (LIACC, New York University Abu Dhabi), Lu\'is Macedo (CISUC, DEI, University of Coimbra)
Abstract: Action selection based on flags is a Reinforcement Learning (RL) exploration policy that improves the exploration of the state space through the use of flags, which can identify the most promising actions to take in each state. The quantum counterpart of this exploration policy further improves upon this by taking advantage of a quadratic speedup for sampling flagged actions. This approach has already been successfully employed for the game of Checkers. In this work, we describe the application of this method to the context of Connect Four, in order to study its performance in a different setting, which can lead to a better generalization of the technique. We also kept track of a metric that wasn't taken into account in previous work: the average number of iterations to obtain a flagged action. Since going second is a significant disadvantage in Connect Four, we also had the intent of exploring how this more complex scenario would impact the performance of our approach. The experiments involved training and testing classical and quantum RL agents that played either going first or going second against a Randomized Negamax opponent. The results showed that both flagged exploration policies were clearly superior to a simple epsilon-greedy policy. Furthermore, the quantum agents did in fact sample flagged actions in less iterations. Despite obtaining tagged actions more consistently, the win rates between the classical and quantum versions of the approach were identical, which could be due to the simplicity of the training scenario chosen.
Authors: Jenni Lampainen, Kaisa Joki, Napsu Karmitsa, Marko M. M\"akel\"a
Abstract: Clustering is a fundamental task in data mining and machine learning, particularly for analyzing large-scale data. In this paper, we introduce Clust-Splitter, an efficient algorithm based on nonsmooth optimization, designed to solve the minimum sum-of-squares clustering problem in very large datasets. The clustering task is approached through a sequence of three nonsmooth optimization problems: two auxiliary problems used to generate suitable starting points, followed by a main clustering formulation. To solve these problems effectively, the limited memory bundle method is combined with an incremental approach to develop the Clust-Splitter algorithm. We evaluate Clust-Splitter on real-world datasets characterized by both a large number of attributes and a large number of data points and compare its performance with several state-of-the-art large-scale clustering algorithms. Experimental results demonstrate the efficiency of the proposed method for clustering very large datasets, as well as the high quality of its solutions, which are on par with those of the best existing methods.
Authors: Jingnan Wang, Jie Chao, Shangshang Yang, Congyi Nai, Kaijun Ren, Kefeng Deng, Xi Chen, Yaxin Liu, Hanqiuzi Wen, Ziniu Xiao, Lifeng Zhang, Xiaodong Wang, Jiping Guan, Baoxiang Pan
Abstract: The planning and operation of renewable energy, especially wind power, depend crucially on accurate, timely, and high-resolution weather information. Coarse-grid global numerical weather forecasts are typically downscaled to meet these requirements, introducing challenges of scale inconsistency, process representation error, computation cost, and entanglement of distinct uncertainty sources from chaoticity, model bias, and large-scale forcing. We address these challenges by learning the climatological distribution of a target wind farm using its high-resolution numerical weather simulations. An optimal combination of this learned high-resolution climatological prior with coarse-grid large scale forecasts yields highly accurate, fine-grained, full-variable, large ensemble of weather pattern forecasts. Using observed meteorological records and wind turbine power outputs as references, the proposed methodology verifies advantageously compared to existing numerical/statistical forecasting-downscaling pipelines, regarding either deterministic/probabilistic skills or economic gains. Moreover, a 100-member, 10-day forecast with spatial resolution of 1 km and output frequency of 15 min takes < 1 hour on a moderate-end GPU, as contrast to $\mathcal{O}(10^3)$ CPU hours for conventional numerical simulation. By drastically reducing computational costs while maintaining accuracy, our method paves the way for more efficient and reliable renewable energy planning and operation.
Authors: Ren Wang, Pengcheng Zhou
Abstract: Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local details with global topological integrity from noisy data or construct a balanced dimensionality reduction, resulting in distorted or fractured embeddings. We present an AutoEncoder-based method that integrates a manifold reconstruction layer, which uncovers latent manifold structures from noisy point clouds, and further provides regularizations on topological and geometric properties during dimensionality reduction, whereas the two components promote each other during training. Experiments on point cloud datasets demonstrate that our method outperforms baselines like t-SNE, UMAP, and Topological AutoEncoders in discovering manifold structures from noisy data and preserving them through dimensionality reduction, as validated by visualization and quantitative metrics. This work demonstrates the significance of combining manifold reconstruction with manifold learning to achieve reliable representation of the latent manifold, particularly when dealing with noisy real-world data. Code repository: https://github.com/Thanatorika/mrtg.
Authors: Georg A. Gottwald, Shuigen Liu, Youssef Marzouk, Sebastian Reich, Xin T. Tong
Abstract: Diffusion models are the state-of-the-art tools for various generative tasks. However, estimating high-dimensional score functions makes them potentially suffer from the curse of dimensionality (CoD). This underscores the importance of better understanding and exploiting low-dimensional structure in the target distribution. In this work, we consider locality structure, which describes sparse dependencies between model components. Under locality structure, the score function is effectively low-dimensional, so that it can be estimated by a localized neural network with significantly reduced sample complexity. This motivates the localized diffusion model, where a localized score matching loss is used to train the score function within a localized hypothesis space. We prove that such localization enables diffusion models to circumvent CoD, at the price of additional localization error. Under realistic sample size scaling, we show both theoretically and numerically that a moderate localization radius can balance the statistical and localization error, leading to a better overall performance. The localized structure also facilitates parallel training of diffusion models, making it potentially more efficient for large-scale applications.
Authors: Vahideh Hayyolalam, \"Oznur \"Ozkasap
Abstract: Federated Learning (FL) is a distributed Machine Learning (ML) setup, where a shared model is collaboratively trained by various clients using their local datasets while keeping the data private. Considering resource-constrained devices, FL clients often suffer from restricted transmission capacity. Aiming to enhance the system performance, the communication between clients and server needs to be diminished. Current FL strategies transmit a tremendous amount of data (model weights) within the FL process, which needs a high communication bandwidth. Considering resource constraints, increasing the number of clients and, consequently, the amount of data (model weights) can lead to a bottleneck. In this paper, we introduce the Federated Black Widow Optimization (FedBWO) technique to decrease the amount of transmitted data by transmitting only a performance score rather than the local model weights from clients. FedBWO employs the BWO algorithm to improve local model updates. The conducted experiments prove that FedBWO remarkably improves the performance of the global model and the communication efficiency of the overall system. According to the experimental outcomes, FedBWO enhances the global model accuracy by an average of 21% over FedAvg, and 12% over FedGWO. Furthermore, FedBWO dramatically decreases the communication cost compared to other methods.
Authors: Xiaozheng Qu, Zhaochuan Li, Zhuang Qi, Xiang Li, Haibei Huang, Lei Meng, Xiangxu Meng
Abstract: The clustering performance of Fuzzy Adaptive Resonance Theory (Fuzzy ART) is highly dependent on the preset vigilance parameter, where deviations in its value can lead to significant fluctuations in clustering results, severely limiting its practicality for non-expert users. Existing approaches generally enhance vigilance parameter robustness through adaptive mechanisms such as particle swarm optimization and fuzzy logic rules. However, they often introduce additional hyperparameters or complex frameworks that contradict the original simplicity of the algorithm. To address this, we propose Iterative Refinement Adaptive Resonance Theory (IR-ART), which integrates three key phases into a unified iterative framework: (1) Cluster Stability Detection: A dynamic stability detection module that identifies unstable clusters by analyzing the change of sample size (number of samples in the cluster) in iteration. (2) Unstable Cluster Deletion: An evolutionary pruning module that eliminates low-quality clusters. (3) Vigilance Region Expansion: A vigilance region expansion mechanism that adaptively adjusts similarity thresholds. Independent of the specific execution of clustering, these three phases sequentially focus on analyzing the implicit knowledge within the iterative process, adjusting weights and vigilance parameters, thereby laying a foundation for the next iteration. Experimental evaluation on 15 datasets demonstrates that IR-ART improves tolerance to suboptimal vigilance parameter values while preserving the parameter simplicity of Fuzzy ART. Case studies visually confirm the algorithm's self-optimization capability through iterative refinement, making it particularly suitable for non-expert users in resource-constrained scenarios.
Authors: Mirazul Haque, Petr Babkin, Farima Farmahinifarahani, Manuela Veloso
Abstract: Large Language Models (LLMs) show promising performance on various programming tasks, including Automatic Program Repair (APR). However, most approaches to LLM-based APR are limited to the static analysis of the programs, while disregarding their runtime behavior. Inspired by knowledge-augmented NLP, in this work, we aim to remedy this potential blind spot by augmenting standard APR prompts with program execution traces. We evaluate our approach using the GPT family of models on three popular APR datasets. Our findings suggest that simply incorporating execution traces into the prompt provides a limited performance improvement over trace-free baselines, in only 2 out of 6 tested dataset / model configurations. We further find that the effectiveness of execution traces for APR diminishes as their complexity increases. We explore several strategies for leveraging traces in prompts and demonstrate that LLM-optimized prompts help outperform trace-free prompts more consistently. Additionally, we show trace-based prompting to be superior to finetuning a smaller LLM on a small-scale dataset; and conduct probing studies reinforcing the notion that execution traces can complement the reasoning abilities of the LLMs.
Authors: Pengfei Jiao, Hongjiang Chen, Xuan Guo, Zhidong Zhao, Dongxiao He, Di Jin
Abstract: Temporal interaction graphs (TIGs), defined by sequences of timestamped interaction events, have become ubiquitous in real-world applications due to their capability to model complex dynamic system behaviors. As a result, temporal interaction graph representation learning (TIGRL) has garnered significant attention in recent years. TIGRL aims to embed nodes in TIGs into low-dimensional representations that effectively preserve both structural and temporal information, thereby enhancing the performance of downstream tasks such as classification, prediction, and clustering within constantly evolving data environments. In this paper, we begin by introducing the foundational concepts of TIGs and emphasize the critical role of temporal dependencies. We then propose a comprehensive taxonomy of state-of-the-art TIGRL methods, systematically categorizing them based on the types of information utilized during the learning process to address the unique challenges inherent to TIGs. To facilitate further research and practical applications, we curate the source of datasets and benchmarks, providing valuable resources for empirical investigations. Finally, we examine key open challenges and explore promising research directions in TIGRL, laying the groundwork for future advancements that have the potential to shape the evolution of this field.
Authors: Louis Ohl, Fredrik Lindsten
Abstract: Evaluating the performance of clustering models is a challenging task where the outcome depends on the definition of what constitutes a cluster. Due to this design, current existing metrics rarely handle multiple clustering models with diverse cluster definitions, nor do they comply with the integration of constraints when available. In this work, we take inspiration from consensus clustering and assume that a set of clustering models is able to uncover hidden structures in the data. We propose to construct a discriminative ordering through ensemble clustering based on the distance between the connectivity of a clustering model and the consensus matrix. We first validate the proposed method with synthetic scenarios, highlighting that the proposed score ranks the models that best match the consensus first. We then show that this simple ranking score significantly outperforms other scoring methods when comparing sets of different clustering algorithms that are not restricted to a fixed number of clusters and is compatible with clustering constraints.
Authors: Hyeju Shin, Kyudan Jung, Seongwon Yun, Juyoung Yun
Abstract: This paper introduces the FFT-Enhanced Kalman Filter (FFTKF), a differentially private optimization method that addresses the challenge of preserving performance in DP-SGD, where added noise typically degrades model utility. FFTKF integrates frequency-domain noise shaping with Kalman filtering to enhance gradient quality while preserving $(\varepsilon, \delta)$-DP guarantees. It employs a high-frequency shaping mask in the Fourier domain to concentrate differential privacy noise in less informative spectral components, preserving low-frequency gradient signals. A scalar-gain Kalman filter with finite-difference Hessian approximation further refines the denoised gradients. With a per-iteration complexity of $\mathcal{O}(d \log d)$, FFTKF demonstrates improved test accuracy over DP-SGD and DiSK across MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets using CNNs, Wide ResNets, and Vision Transformers. Theoretical analysis confirms that FFTKF maintains equivalent privacy guarantees while achieving a tighter privacy-utility trade-off through reduced noise and controlled bias.
Authors: Vincent Souveton, S\'ebastien Terrana
Abstract: Many conservative physical systems can be described using the Hamiltonian formalism. A notable example is the Vlasov-Poisson equations, a set of partial differential equations that govern the time evolution of a phase-space density function representing collisionless particles under a self-consistent potential. These equations play a central role in both plasma physics and cosmology. Due to the complexity of the potential involved, analytical solutions are rarely available, necessitating the use of numerical methods such as Particle-In-Cell. In this work, we introduce a novel approach based on Hamiltonian-informed Normalizing Flows, specifically a variant of Fixed-Kinetic Neural Hamiltonian Flows. Our method transforms an initial Gaussian distribution in phase space into the final distribution using a sequence of invertible, volume-preserving transformations derived from Hamiltonian dynamics. The model is trained on a dataset comprising initial and final states at a fixed time T, generated via numerical simulations. After training, the model enables fast sampling of the final distribution from any given initial state. Moreover, by automatically learning an interpretable physical potential, it can generalize to intermediate states not seen during training, offering insights into the system's evolution across time.
Authors: Michail Theologitis, Vasilis Samoladas, Antonios Deligiannakis
Abstract: Federated learning (FL) makes it possible to train models on data that would otherwise remain untapped and inaccessible. Simultaneously, pre-trained language models (LMs) have emerged as indispensable tools in modern workflows. These models exhibit extraordinary capabilities and are easily adapted to downstream tasks. This opens one of the most exciting frontiers in FL: fine-tuning LMs. However, a persistent challenge in FL is the frequent, rigid communication of parameters, a problem which is magnified by the sheer size of these modern models. Currently, the FedOpt family of algorithms is the prevailing approach in FL, though it relies on fixed, heuristic intervals for model synchronization. Recently, the FDA algorithm introduced a dynamic alternative by monitoring training progress, but it came with its own drawbacks; namely, a hard-to-tune threshold parameter and a rigid synchronization scheme. In this work, we introduce the FDA-Opt family of algorithms -- a unified generalization that extends the principles behind both FDA and FedOpt, while resolving their core limitations. We evaluate our approach on fine-tuning LMs across a range of downstream NLP tasks, and demonstrate that it consistently outperforms FedOpt -- even when FDA-Opt operates under hyper-parameter settings originally optimized for its competitors. In other words, we show that FDA-Opt is a practical, drop-in replacement for FedOpt in modern FL libraries and systems: it requires no additional configuration and delivers superior performance out of the box.
Authors: Wenzhao Liu, Haoran Li, Congying Han, Zicheng Zhang, Anqi Li, Tiande Guo
Abstract: Achieving generalization in neural approaches across different scales and distributions remains a significant challenge for the Traveling Salesman Problem~(TSP). A key obstacle is that neural networks often fail to learn robust principles for identifying universal patterns and deriving optimal solutions from diverse instances. In this paper, we first uncover Purity Law (PuLa), a fundamental structural principle for optimal TSP solutions, defining that edge prevalence grows exponentially with the sparsity of surrounding vertices. Statistically validated across diverse instances, PuLa reveals a consistent bias toward local sparsity in global optima. Building on this insight, we propose Purity Policy Optimization~(PUPO), a novel training paradigm that explicitly aligns characteristics of neural solutions with PuLa during the solution construction process to enhance generalization. Extensive experiments demonstrate that PUPO can be seamlessly integrated with popular neural solvers, significantly enhancing their generalization performance without incurring additional computational overhead during inference.
Authors: Guanghui Wang, Zhiyong Yang, Zitai Wang, Shi Wang, Qianqian Xu, Qingming Huang
Abstract: Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD (RKLD). It has become an effective training paradigm due to the broader supervision information provided by the teacher distribution compared to one-hot labels. We identify that the core challenge in KD lies in balancing two mode-concentration effects: the \textbf{\textit{Hardness-Concentration}} effect, which refers to focusing on modes with large errors, and the \textbf{\textit{Confidence-Concentration}} effect, which refers to focusing on modes with high student confidence. Through an analysis of how probabilities are reassigned during gradient updates, we observe that these two effects are entangled in FKLD and RKLD, but in extreme forms. Specifically, both are too weak in FKLD, causing the student to fail to concentrate on the target class. In contrast, both are too strong in RKLD, causing the student to overly emphasize the target class while ignoring the broader distributional information from the teacher. To address this imbalance, we propose ABKD, a generic framework with $\alpha$-$\beta$-divergence. Our theoretical results show that ABKD offers a smooth interpolation between FKLD and RKLD, achieving an effective trade-off between these effects. Extensive experiments on 17 language/vision datasets with 12 teacher-student settings confirm its efficacy. The code is available at https://github.com/ghwang-s/abkd.
Authors: Lucas R. C. Farias, Talita P. Silva, Pedro H. M. Araujo
Abstract: This paper presents a multitask learning approach based on long-short-term memory (LSTM) networks for the joint prediction of arboviral outbreaks and case counts of dengue, chikungunya, and Zika in Recife, Brazil. Leveraging historical public health data from DataSUS (2017-2023), the proposed model concurrently performs binary classification (outbreak detection) and regression (case forecasting) tasks. A sliding window strategy was adopted to construct temporal features using varying input lengths (60, 90, and 120 days), with hyperparameter optimization carried out using Keras Tuner. Model evaluation used time series cross-validation for robustness and a held-out test from 2023 for generalization assessment. The results show that longer windows improve dengue regression accuracy, while classification performance peaked at intermediate windows, suggesting an optimal trade-off between sequence length and generalization. The multitask architecture delivers competitive performance across diseases and tasks, demonstrating the feasibility and advantages of unified modeling strategies for scalable epidemic forecasting in data-limited public health scenarios.
Authors: Wenjun Cao
Abstract: Reinforcement learning (RL) fine-tuning transforms large language models while creating a vulnerability we experimentally verify: Our experiment shows that malicious RL fine-tuning dismantles safety guardrails with remarkable efficiency, requiring only 50 steps and minimal adversarial prompts, with harmful escalating from 0-2 to 7-9. This attack vector particularly threatens open-source models with parameter-level access. Existing defenses targeting supervised fine-tuning prove ineffective against RL's dynamic feedback mechanisms. We introduce Reward Neutralization, the first defense framework specifically designed against RL fine-tuning attacks, establishing concise rejection patterns that render malicious reward signals ineffective. Our approach trains models to produce minimal-information rejections that attackers cannot exploit, systematically neutralizing attempts to optimize toward harmful outputs. Experiments validate that our approach maintains low harmful scores (no greater than 2) after 200 attack steps, while standard models rapidly deteriorate. This work provides the first constructive proof that robust defense against increasingly accessible RL attacks is achievable, addressing a critical security gap for open-weight models.
Authors: Michael Crawshaw, Mingrui Liu
Abstract: Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms of problem parameters like the smoothness constants. The complexity guaranteed by such algorithms to find an $\epsilon$-stationary point may be significantly larger than the optimal complexity of $\Theta \left( \Delta L \sigma^2 \epsilon^{-4} \right)$ achieved by SGD in the $L$-smooth setting, where $\Delta$ is the initial optimality gap, $\sigma^2$ is the variance of stochastic gradient. However, it is currently not known whether these higher-order dependencies can be tightened. To answer this question, we investigate complexity lower bounds for several adaptive optimization algorithms in the $(L_0, L_1)$-smooth setting, with a focus on the dependence in terms of problem parameters $\Delta, L_0, L_1$. We provide complexity bounds for three variations of AdaGrad, which show at least a quadratic dependence on problem parameters $\Delta, L_0, L_1$. Notably, we show that the decorrelated variant of AdaGrad-Norm requires at least $\Omega \left( \Delta^2 L_1^2 \sigma^2 \epsilon^{-4} \right)$ stochastic gradient queries to find an $\epsilon$-stationary point. We also provide a lower bound for SGD with a broad class of adaptive stepsizes. Our results show that, for certain adaptive algorithms, the $(L_0, L_1)$-smooth setting is fundamentally more difficult than the standard smooth setting, in terms of the initial optimality gap and the smoothness constants.
Authors: Lorenzo Beretta, Nathaniel Harms, Caleb Koch
Abstract: We prove tight upper and lower bounds of $\Theta\left(\tfrac{1}{\epsilon}\left( \sqrt{2^k \log\binom{n}{k} } + \log\binom{n}{k} \right)\right)$ on the number of samples required for distribution-free $k$-junta testing. This is the first tight bound for testing a natural class of Boolean functions in the distribution-free sample-based model. Our bounds also hold for the feature selection problem, showing that a junta tester must learn the set of relevant variables. For tolerant junta testing, we prove a sample lower bound of $\Omega(2^{(1-o(1)) k} + \log\binom{n}{k})$ showing that, unlike standard testing, there is no large gap between tolerant testing and learning.
Authors: Drew Prinster, Xing Han, Anqi Liu, Suchi Saria
Abstract: Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but moreover continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Statistical methods for nonparametric change-point detection -- especially the tools of conformal test martingales (CTMs) and anytime-valid inference -- offer promising approaches to this monitoring task. However, existing methods are restricted to monitoring limited hypothesis classes or ``alarm criteria,'' such as data shifts that violate certain exchangeability assumptions, or do not allow for online adaptation in response to shifts. In this paper, we expand the scope of these monitoring methods by proposing a weighted generalization of conformal test martingales (WCTMs), which lay a theoretical foundation for online monitoring for any unexpected changepoints in the data distribution while controlling false-alarms. For practical applications, we propose specific WCTM algorithms that accommodate online adaptation to mild covariate shifts (in the marginal input distribution) while raising alarms in response to more severe shifts, such as concept shifts (in the conditional label distribution) or extreme (out-of-support) covariate shifts that cannot be easily adapted to. On real-world datasets, we demonstrate improved performance relative to state-of-the-art baselines.
Authors: Abdulaziz Almuzairee, Rohan Patil, Dwait Bhatt, Henrik I. Christensen
Abstract: Vision is well-known for its use in manipulation, especially using visual servoing. To make it robust, multiple cameras are needed to expand the field of view. That is computationally challenging. Merging multiple views and using Q-learning allows the design of more effective representations and optimization of sample efficiency. Such a solution might be expensive to deploy. To mitigate this, we introduce a Merge And Disentanglement (MAD) algorithm that efficiently merges views to increase sample efficiency while augmenting with single-view features to allow lightweight deployment and ensure robust policies. We demonstrate the efficiency and robustness of our approach using Meta-World and ManiSkill3. For project website and code, see https://aalmuzairee.github.io/mad
Authors: Yanbiao Liang, Huihong Shi, Haikuo Shao, Zhongfeng Wang
Abstract: Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on resource-constrained edge devices poses significant challenges, including (1) intensive computations and huge model sizes, (2) great memory and bandwidth demands introduced by the autoregressive generation process, and (3) limited scalability for handling long sequences. To address these challenges, we propose AccLLM, a comprehensive acceleration framework that enables efficient and fast long-context LLM inference through algorithm and hardware co-design. At the algorithmic level, we integrate (1) pruning, (2) {\Lambda}-shaped attention, and (3) an innovative W2A8KV4 (2-bit weights, 8-bit activations, and 4-bit KV cache) quantization scheme, thus effectively reducing memory and bandwidth requirements while facilitating LLMs' long-sequence generation. At the hardware level, we design a dedicated FPGA-based accelerator with a reconfigurable computing engine to effectively and flexibly accommodate diverse operations arising from our compression algorithm, thereby fully translating the algorithmic innovations into tangible hardware efficiency. We validate AccLLM on the Xilinx Alveo U280 FPGA, demonstrating a 4.07x energy efficiency and a 2.98x throughput compared to the state-of-the-art work FlightLLM.
Authors: Hang Zhang, Jiuchen Shi, Yixiao Wang, Quan Chen, Yizhou Shan, Minyi Guo
Abstract: Multiple Low-Rank Adapters (Multi-LoRAs) are gaining popularity for task-specific Large Language Model (LLM) applications. For multi-LoRA serving, caching hot KV caches and LoRA adapters in high bandwidth memory of accelerations can improve inference performance. However, existing Multi-LoRA inference systems fail to optimize serving performance like Time-To-First-Toke (TTFT), neglecting usage dependencies when caching LoRAs and KVs. We therefore propose FASTLIBRA, a Multi-LoRA caching system to optimize the serving performance. FASTLIBRA comprises a dependency-aware cache manager and a performance-driven cache swapper. The cache manager maintains the usage dependencies between LoRAs and KV caches during the inference with a unified caching pool. The cache swapper determines the swap-in or out of LoRAs and KV caches based on a unified cost model, when the HBM is idle or busy, respectively. Experimental results show that ELORA reduces the TTFT by 63.4% on average, compared to state-of-the-art works.
Authors: Vinicius Francisco Rofatto, Luiz Felipe Rodrigues de Almeida, Marcelo Tomio Matsuoka, Ivandro Klein, Mauricio Roberto Veronez, Luiz Gonzaga Da Silveira Junior
Abstract: Coordinate transformation models often fail to account for nonlinear and spatially dependent distortions, leading to significant residual errors in geospatial applications. Here we propose a residual-based neural correction strategy, in which a neural network learns to model only the systematic distortions left by an initial geometric transformation. By focusing solely on residual patterns, the proposed method reduces model complexity and improves performance, particularly in scenarios with sparse or structured control point configurations. We evaluate the method using both simulated datasets with varying distortion intensities and sampling strategies, as well as under the real-world image georeferencing tasks. Compared with direct neural network coordinate converter and classical transformation models, the residual-based neural correction delivers more accurate and stable results under challenging conditions, while maintaining comparable performance in ideal cases. These findings demonstrate the effectiveness of residual modelling as a lightweight and robust alternative for improving coordinate transformation accuracy.
Authors: Asad Aali, Adney Cardoza, Melissa Capo
Abstract: Efficient inference of LLMs remains a crucial challenge, with two main phases: a compute-intensive prompt computation and a memory-intensive token generation. Despite existing batching and scheduling techniques, token generation phases fail to fully utilize compute resources, especially when compared to prompt computation phases. To address these challenges, we propose Splitwiser, a methodology that splits the two phases of an LLM inference request onto the same GPU, thereby reducing overhead and improving memory access and cache utilization. By eliminating the need to transfer data across devices, Splitwiser aims to minimize network-related overheads. In this report, we describe the basic structure of our proposed pipeline while sharing preliminary results and analysis. We implement our proposed multiprocessing design on two widely-used and independent LLM architectures: Huggingface and vLLM. We open-source our code for the respective implementations: 1) Huggingface (https://github.com/asad-aali/splitwiser), and 2) vLLM (https://github.com/adney11/vllm-sysml).
URLs: https://github.com/asad-aali/splitwiser),, https://github.com/adney11/vllm-sysml).
Authors: Ganghua Wang, Zhaorun Chen, Bo Li, Haifeng Xu
Abstract: As foundation models continue to scale, the size of trained models grows exponentially, presenting significant challenges for their evaluation. Current evaluation practices involve curating increasingly large datasets to assess the performance of large language models (LLMs). However, there is a lack of systematic analysis and guidance on determining the sufficiency of test data or selecting informative samples for evaluation. This paper introduces a certifiable and cost-efficient evaluation framework for LLMs. Our framework adapts to different evaluation objectives and outputs confidence intervals that contain true values with high probability. We use ``test sample complexity'' to quantify the number of test points needed for a certifiable evaluation and derive tight bounds on test sample complexity. Based on the developed theory, we develop a partition-based algorithm, named Cer-Eval, that adaptively selects test points to minimize the cost of LLM evaluation. Real-world experiments demonstrate that Cer-Eval can save 20% to 40% test points across various benchmarks, while maintaining an estimation error level comparable to the current evaluation process and providing a 95% confidence guarantee.
Authors: Aditya Shinde, Prashant Doshi
Abstract: This paper presents a holistic approach to attacker preference modeling from system-level audit logs using inverse reinforcement learning (IRL). Adversary modeling is an important capability in cybersecurity that lets defenders characterize behaviors of potential attackers, which enables attribution to known cyber adversary groups. Existing approaches rely on documenting an ever-evolving set of attacker tools and techniques to track known threat actors. Although attacks evolve constantly, attacker behavioral preferences are intrinsic and less volatile. Our approach learns the behavioral preferences of cyber adversaries from forensics data on their tools and techniques. We model the attacker as an expert decision-making agent with unknown behavioral preferences situated in a computer host. We leverage attack provenance graphs of audit logs to derive a state-action trajectory of the attack. We test our approach on open datasets of audit logs containing real attack data. Our results demonstrate for the first time that low-level forensics data can automatically reveal an adversary's subjective preferences, which serves as an additional dimension to modeling and documenting cyber adversaries. Attackers' preferences tend to be invariant despite their different tools and indicate predispositions that are inherent to the attacker. As such, these inferred preferences can potentially serve as unique behavioral signatures of attackers and improve threat attribution.
Authors: Yogesh Gajula
Abstract: E-commerce platforms generate vast volumes of user feedback, such as star ratings, written reviews, and comments. However, most recommendation engines rely primarily on numerical scores, often overlooking the nuanced opinions embedded in free text. This paper comprehensively reviews sentiment-aware recommendation systems from a natural language processing perspective, covering advancements from 2023 to early 2025. It highlights the benefits of integrating sentiment analysis into e-commerce recommenders to enhance prediction accuracy and explainability through detailed opinion extraction. Our survey categorizes recent work into four main approaches: deep learning classifiers that combine sentiment embeddings with user item interactions, transformer based methods for nuanced feature extraction, graph neural networks that propagate sentiment signals, and conversational recommenders that adapt in real time to user feedback. We summarize model architectures and demonstrate how sentiment flows through recommendation pipelines, impacting dialogue-based suggestions. Key challenges include handling noisy or sarcastic text, dynamic user preferences, and bias mitigation. Finally, we outline research gaps and provide a roadmap for developing smarter, fairer, and more user-centric recommendation tools.
Authors: Esra Hoto\u{g}lu, Sevil Sen, Burcu Can
Abstract: Deep learning has revolutionized email filtering, which is critical to protect users from cyber threats such as spam, malware, and phishing. However, the increasing sophistication of adversarial attacks poses a significant challenge to the effectiveness of these filters. This study investigates the impact of adversarial attacks on deep learning-based spam detection systems using real-world datasets. Six prominent deep learning models are evaluated on these datasets, analyzing attacks at the word, character sentence, and AI-generated paragraph-levels. Novel scoring functions, including spam weights and attention weights, are introduced to improve attack effectiveness. This comprehensive analysis sheds light on the vulnerabilities of spam filters and contributes to efforts to improve their security against evolving adversarial threats.
Authors: Xuechao Wang, Sven Nomm, Junqing Huang, Kadri Medijainen, Aaro Toomela, Michael Ruzhansky
Abstract: Deep neural networks have shown potential in analyzing digitized hand-drawn signals for early diagnosis of Parkinson's disease. However, the lack of clear interpretability in existing diagnostic methods presents a challenge to clinical trust. In this paper, we propose PointExplainer, an explainable diagnostic strategy to identify hand-drawn regions that drive model diagnosis. Specifically, PointExplainer assigns discrete attribution values to hand-drawn segments, explicitly quantifying their relative contributions to the model's decision. Its key components include: (i) a diagnosis module, which encodes hand-drawn signals into 3D point clouds to represent hand-drawn trajectories, and (ii) an explanation module, which trains an interpretable surrogate model to approximate the local behavior of the black-box diagnostic model. We also introduce consistency measures to further address the issue of faithfulness in explanations. Extensive experiments on two benchmark datasets and a newly constructed dataset show that PointExplainer can provide intuitive explanations with no diagnostic performance degradation. The source code is available at https://github.com/chaoxuewang/PointExplainer.
Authors: Cairong Yan, Jinyi Han, Jin Ju, Yanting Zhang, Zijian Wang, Xuan Shao
Abstract: Clustering bandits have gained significant attention in recommender systems by leveraging collaborative information from neighboring users to better capture target user preferences. However, these methods often lack a clear definition of similar users and face challenges when users with unique preferences lack appropriate neighbors. In such cases, relying on divergent preferences of misidentified neighbors can degrade recommendation quality. To address these limitations, this paper proposes an adaptive Collaborative Combinatorial Bandits algorithm (CoCoB). CoCoB employs an innovative two-sided bandit architecture, applying bandit principles to both the user and item sides. The user-bandit employs an enhanced Bayesian model to explore user similarity, identifying neighbors based on a similarity probability threshold. The item-bandit treats items as arms, generating diverse recommendations informed by the user-bandit's output. CoCoB dynamically adapts, leveraging neighbor preferences when available or focusing solely on the target user otherwise. Regret analysis under a linear contextual bandit setting and experiments on three real-world datasets demonstrate CoCoB's effectiveness, achieving an average 2.4% improvement in F1 score over state-of-the-art methods.
Authors: Ioannis Kyprakis, Vasileios Skaramagkas, Iro Boura, Georgios Karamanis, Dimitrios I. Fotiadis, Zinovia Kefalopoulou, Cleanthe Spanaki, Manolis Tsiknakis
Abstract: Parkinson's disease (PD) is a neurodegenerative disorder, manifesting with motor and non-motor symptoms. Depressive symptoms are prevalent in PD, affecting up to 45% of patients. They are often underdiagnosed due to overlapping motor features, such as hypomimia. This study explores deep learning (DL) models-ViViT, Video Swin Tiny, and 3D CNN-LSTM with attention layers-to assess the presence and severity of depressive symptoms, as detected by the Geriatric Depression Scale (GDS), in PD patients through facial video analysis. The same parameters were assessed in a secondary analysis taking into account whether patients were one hour after (ON-medication state) or 12 hours without (OFF-medication state) dopaminergic medication. Using a dataset of 1,875 videos from 178 patients, the Video Swin Tiny model achieved the highest performance, with up to 94% accuracy and 93.7% F1-score in binary classification (presence of absence of depressive symptoms), and 87.1% accuracy with an 85.4% F1-score in multiclass tasks (absence or mild or severe depressive symptoms).
Authors: Janhavi Giri, Attila Lengyel, Don Kent, Edward Kibardin
Abstract: Semiconductor manufacturing generates vast amounts of image data, crucial for defect identification and yield optimization, yet often exceeds manual inspection capabilities. Traditional clustering techniques struggle with high-dimensional, unlabeled data, limiting their effectiveness in capturing nuanced patterns. This paper introduces an advanced clustering framework that integrates deep Topological Data Analysis (TDA) with self-supervised and transfer learning techniques, offering a novel approach to unsupervised image clustering. TDA captures intrinsic topological features, while self-supervised learning extracts meaningful representations from unlabeled data, reducing reliance on labeled datasets. Transfer learning enhances the framework's adaptability and scalability, allowing fine-tuning to new datasets without retraining from scratch. Validated on synthetic and open-source semiconductor image datasets, the framework successfully identifies clusters aligned with defect patterns and process variations. This study highlights the transformative potential of combining TDA, self-supervised learning, and transfer learning, providing a scalable solution for proactive process monitoring and quality control in semiconductor manufacturing and other domains with large-scale image datasets.
Authors: Alireza Khayatian, Anil Vullikanti, Aritra Konar
Abstract: Many graph datasets involve sensitive network data, motivating the need for privacy-preserving graph mining. The Densest-$k$-subgraph (D$k$S) problem is a key primitive in graph mining that aims to extract a subset of $k$ vertices with the maximum internal connectivity. Although non-private algorithms are known for D$k$S, this paper is the first to design algorithms that offer formal differential privacy (DP) guarantees for the problem. We base our general approach on using the principal component (PC) of the graph adjacency matrix to output a subset of $k$ vertices under edge DP. For this task, we first consider output perturbation, which traditionally offer good scalability, but at the expense of utility. Our tight on the local sensitivity indicate a big gap with the global sensitivity, motivating the use of instance specific sensitive methods for private PC. Next, we derive a tight bound on the smooth sensitivity and show that it can be close to the global sensitivity. This leads us to consider the Propose-Test-Release (PTR) framework for private PC. Although computationally expensive in general, we design a novel approach for implementing PTR in the same time as computation of a non-private PC, while offering good utility for \DkS{}. Additionally, we also consider the iterative private power method (PPM) for private PC, albeit it is significantly slower than PTR on large networks. We run our methods on diverse real-world networks, with the largest having 3 million vertices, and show good privacy-utility trade-offs. Although PTR requires a slightly larger privacy budget, on average, it achieves a 180-fold improvement in runtime over PPM.
Authors: H\^ong V\^an L\^e, H\`a Quang Minh, Frederic Protin, Wilderich Tuschmann
Abstract: We present and discuss applications of the category of probabilistic morphisms, initially developed in \cite{Le2023}, as well as some geometric methods to several classes of problems in statistical, machine and manifold learning which shall be, along with many other topics, considered in depth in the forthcoming book \cite{LMPT2024}.
Authors: Qiaomu Li, Ying Xie
Abstract: Artificial intelligence is rapidly evolving towards multi-agent systems where numerous AI agents collaborate and interact with external tools. Two key open standards, Google's Agent to Agent (A2A) protocol for inter-agent communication and Anthropic's Model Context Protocol (MCP) for standardized tool access, promise to overcome the limitations of fragmented, custom integration approaches. While their potential synergy is significant, this paper argues that effectively integrating A2A and MCP presents unique, emergent challenges at their intersection, particularly concerning semantic interoperability between agent tasks and tool capabilities, the compounded security risks arising from combined discovery and execution, and the practical governance required for the envisioned "Agent Economy". This work provides a critical analysis, moving beyond a survey to evaluate the practical implications and inherent difficulties of combining these horizontal and vertical integration standards. We examine the benefits (e.g., specialization, scalability) while critically assessing their dependencies and trade-offs in an integrated context. We identify key challenges increased by the integration, including novel security vulnerabilities, privacy complexities, debugging difficulties across protocols, and the need for robust semantic negotiation mechanisms. In summary, A2A+MCP offers a vital architectural foundation, but fully realizing its potential requires substantial advancements to manage the complexities of their combined operation.
Authors: Asif Rahman, Veljko Cvetkovic, Kathleen Reece, Aidan Walters, Yasir Hassan, Aneesh Tummeti, Bryan Torres, Denise Cooney, Margaret Ellis, Dimitrios S. Nikolopoulos
Abstract: Large language models (LLMs) have transformed software development through code generation capabilities, yet their effectiveness for high-performance computing (HPC) remains limited. HPC code requires specialized optimizations for parallelism, memory efficiency, and architecture-specific considerations that general-purpose LLMs often overlook. We present MARCO (Multi-Agent Reactive Code Optimizer), a novel framework that enhances LLM-generated code for HPC through a specialized multi-agent architecture. MARCO employs separate agents for code generation and performance evaluation, connected by a feedback loop that progressively refines optimizations. A key innovation is MARCO's web-search component that retrieves real-time optimization techniques from recent conference proceedings and research publications, bridging the knowledge gap in pre-trained LLMs. Our extensive evaluation on the LeetCode 75 problem set demonstrates that MARCO achieves a 14.6% average runtime reduction compared to Claude 3.5 Sonnet alone, while the integration of the web-search component yields a 30.9% performance improvement over the base MARCO system. These results highlight the potential of multi-agent systems to address the specialized requirements of high-performance code generation, offering a cost-effective alternative to domain-specific model fine-tuning.
Authors: Michael Xu, Yi Shi, KangKang Yin, Xue Bin Peng
Abstract: Humans excel in navigating diverse, complex environments with agile motor skills, exemplified by parkour practitioners performing dynamic maneuvers, such as climbing up walls and jumping across gaps. Reproducing these agile movements with simulated characters remains challenging, in part due to the scarcity of motion capture data for agile terrain traversal behaviors and the high cost of acquiring such data. In this work, we introduce PARC (Physics-based Augmentation with Reinforcement Learning for Character Controllers), a framework that leverages machine learning and physics-based simulation to iteratively augment motion datasets and expand the capabilities of terrain traversal controllers. PARC begins by training a motion generator on a small dataset consisting of core terrain traversal skills. The motion generator is then used to produce synthetic data for traversing new terrains. However, these generated motions often exhibit artifacts, such as incorrect contacts or discontinuities. To correct these artifacts, we train a physics-based tracking controller to imitate the motions in simulation. The corrected motions are then added to the dataset, which is used to continue training the motion generator in the next iteration. PARC's iterative process jointly expands the capabilities of the motion generator and tracker, creating agile and versatile models for interacting with complex environments. PARC provides an effective approach to develop controllers for agile terrain traversal, which bridges the gap between the scarcity of motion data and the need for versatile character controllers.
Authors: Yinzhuang Yi, Jorge Cort\'es, Nikolay Atanasov
Abstract: This paper provides a formulation of the particle flow particle filter from the perspective of variational inference. We show that the transient density used to derive the particle flow particle filter follows a time-scaled trajectory of the Fisher-Rao gradient flow in the space of probability densities. The Fisher-Rao gradient flow is obtained as a continuous-time algorithm for variational inference, minimizing the Kullback-Leibler divergence between a variational density and the true posterior density.
Authors: Darren Yow-Bang Wang, Zhengyuan Shen, Soumya Smruti Mishra, Zhichao Xu, Yifei Teng, Haibo Ding
Abstract: Structured outputs are essential for large language models (LLMs) in critical applications like agents and information extraction. Despite their capabilities, LLMs often generate outputs that deviate from predefined schemas, significantly hampering reliable application development. We present SLOT (Structured LLM Output Transformer), a model-agnostic approach that transforms unstructured LLM outputs into precise structured formats. While existing solutions predominantly rely on constrained decoding techniques or are tightly coupled with specific models, SLOT employs a fine-tuned lightweight language model as a post-processing layer, achieving flexibility across various LLMs and schema specifications. We introduce a systematic pipeline for data curation and synthesis alongside a formal evaluation methodology that quantifies both schema accuracy and content fidelity. Our results demonstrate that fine-tuned Mistral-7B model with constrained decoding achieves near perfect schema accuracy (99.5%) and content similarity (94.0%), outperforming Claude-3.5-Sonnet by substantial margins (+25 and +20 percentage points, respectively). Notably, even compact models like Llama-3.2-1B can match or exceed the structured output capabilities of much larger proprietary models when equipped with SLOT, enabling reliable structured generation in resource-constrained environments.
Authors: Shan Yu, Jiarong Xing, Yifan Qiao, Mingyuan Ma, Yangmin Li, Yang Wang, Shuo Yang, Zhiqiang Xie, Shiyi Cao, Ke Bao, Ion Stoica, Harry Xu, Ying Sheng
Abstract: Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new opportunities and challenges for this task. The long-tail popularity of models and their long idle periods present opportunities to improve utilization through GPU sharing. However, existing GPU sharing systems lack the ability to adjust their resource allocation and sharing policies at runtime, making them ineffective at meeting latency service-level objectives (SLOs) under rapidly fluctuating workloads. This paper presents Prism, a multi-LLM serving system that unleashes the full potential of GPU sharing to achieve both cost efficiency and SLO attainment. At its core, Prism tackles a key limitation of existing systems$\unicode{x2014}$the lack of $\textit{cross-model memory coordination}$, which is essential for flexibly sharing GPU memory across models under dynamic workloads. Prism achieves this with two key designs. First, it supports on-demand memory allocation by dynamically mapping physical to virtual memory pages, allowing flexible memory redistribution among models that space- and time-share a GPU. Second, it improves memory efficiency through a two-level scheduling policy that dynamically adjusts sharing strategies based on models' runtime demands. Evaluations on real-world traces show that Prism achieves more than $2\times$ cost savings and $3.3\times$ SLO attainment compared to state-of-the-art systems.
Authors: Ayana Moshruba, Hamed Poursiami, Maryam Parsa
Abstract: Biological neurons exhibit diverse temporal spike patterns, which are believed to support efficient, robust, and adaptive neural information processing. While models such as Izhikevich can replicate a wide range of these firing dynamics, their complexity poses challenges for directly integrating them into scalable spiking neural networks (SNN) training pipelines. In this work, we propose two probabilistically driven, input-level temporal spike transformations: Poisson-Burst and Delayed-Burst that introduce biologically inspired temporal variability directly into standard Leaky Integrate-and-Fire (LIF) neurons. This enables scalable training and systematic evaluation of how spike timing dynamics affect privacy, generalization, and learning performance. Poisson-Burst modulates burst occurrence based on input intensity, while Delayed-Burst encodes input strength through burst onset timing. Through extensive experiments across multiple benchmarks, we demonstrate that Poisson-Burst maintains competitive accuracy and lower resource overhead while exhibiting enhanced privacy robustness against membership inference attacks, whereas Delayed-Burst provides stronger privacy protection at a modest accuracy trade-off. These findings highlight the potential of biologically grounded temporal spike dynamics in improving the privacy, generalization and biological plausibility of neuromorphic learning systems.
Authors: Kang Liu, Wei Peng, Jianchen Hu
Abstract: We propose an input convex neural network (ICNN)-based self-supervised learning framework to solve continuous constrained optimization problems. By integrating the augmented Lagrangian method (ALM) with the constraint correction mechanism, our framework ensures \emph{non-strict constraint feasibility}, \emph{better optimality gap}, and \emph{best convergence rate} with respect to the state-of-the-art learning-based methods. We provide a rigorous convergence analysis, showing that the algorithm converges to a Karush-Kuhn-Tucker (KKT) point of the original problem even when the internal solver is a neural network, and the approximation error is bounded. We test our approach on a range of benchmark tasks including quadratic programming (QP), nonconvex programming, and large-scale AC optimal power flow problems. The results demonstrate that compared to existing solvers (e.g., \texttt{OSQP}, \texttt{IPOPT}) and the latest learning-based methods (e.g., DC3, PDL), our approach achieves a superior balance among accuracy, feasibility, and computational efficiency.
Authors: Thien Nhan Vo, Bac Nam Ho, Thanh Xuan Truong
Abstract: A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers.
Authors: Vihaan Miriyala, Smrithi Bukkapatnam, Lavanya Prahallad
Abstract: We explore the use of Chain-of-Thought (CoT) prompting with large language models (LLMs) to improve the accuracy of granular sentiment categorization in app store reviews. Traditional numeric and polarity-based ratings often fail to capture the nuanced sentiment embedded in user feedback. We evaluated the effectiveness of CoT prompting versus simple prompting on 2000 Amazon app reviews by comparing each method's predictions to human judgements. CoT prompting improved classification accuracy from 84% to 93% highlighting the benefit of explicit reasoning in enhancing sentiment analysis performance.
Authors: Yu Yamaoka or Weng Ian Chan, Shigeto Seno, Soichiro Fukada, Hideo Matsuda
Abstract: Evaluating the regeneration process of damaged muscle tissue is a fundamental analysis in muscle research to measure experimental effect sizes and uncover mechanisms behind muscle weakness due to aging and disease. The conventional approach to assessing muscle tissue regeneration involves whole-slide imaging and expert visual inspection of the recovery stages based on the morphological information of cells and fibers. There is a need to replace these tasks with automated methods incorporating machine learning techniques to ensure a quantitative and objective analysis. Given the limited availability of fully labeled data, a possible approach is Learning from Label Proportions (LLP), a weakly supervised learning method using class label proportions. However, current LLP methods have two limitations: (1) they cannot adapt the feature extractor for muscle tissues, and (2) they treat the classes representing recovery stages and cell morphological changes as nominal, resulting in the loss of ordinal information. To address these issues, we propose Ordinal Scale Learning from Similarity Proportion (OSLSP), which uses a similarity proportion loss derived from two bag combinations. OSLSP can update the feature extractor by using class proportion attention to the ordinal scale of the class. Our model with OSLSP outperforms large-scale pre-trained and fine-tuning models in classification tasks of skeletal muscle recovery stages.
Authors: Soumik Dey, Hansi Wu, Binbin Li
Abstract: E-commerce sellers are recommended keyphrases based on their inventory on which they advertise to increase buyer engagement (clicks/sales). The relevance of advertiser keyphrases plays an important role in preventing the inundation of search systems with numerous irrelevant items that compete for attention in auctions, in addition to maintaining a healthy seller perception. In this work, we describe the shortcomings of training Advertiser keyphrase relevance filter models on click/sales/search relevance signals and the importance of aligning with human judgment, as sellers have the power to adopt or reject said keyphrase recommendations. In this study, we frame Advertiser keyphrase relevance as a complex interaction between 3 dynamical systems -- seller judgment, which influences seller adoption of our product, Advertising, which provides the keyphrases to bid on, and Search, who holds the auctions for the same keyphrases. This study discusses the practicalities of using human judgment via a case study at eBay Advertising and demonstrate that using LLM-as-a-judge en-masse as a scalable proxy for seller judgment to train our relevance models achieves a better harmony across the three systems -- provided that they are bound by a meticulous evaluation framework grounded in business metrics.
Authors: Maria Marina, Nikolay Ivanov, Sergey Pletenev, Mikhail Salnikov, Daria Galimzianova, Nikita Krayko, Vasily Konovalov, Alexander Panchenko, Viktor Moskvoretskii
Abstract: Large Language Models~(LLMs) are prone to hallucinations, and Retrieval-Augmented Generation (RAG) helps mitigate this, but at a high computational cost while risking misinformation. Adaptive retrieval aims to retrieve only when necessary, but existing approaches rely on LLM-based uncertainty estimation, which remain inefficient and impractical. In this study, we introduce lightweight LLM-independent adaptive retrieval methods based on external information. We investigated 27 features, organized into 7 groups, and their hybrid combinations. We evaluated these methods on 6 QA datasets, assessing the QA performance and efficiency. The results show that our approach matches the performance of complex LLM-based methods while achieving significant efficiency gains, demonstrating the potential of external information for adaptive retrieval.
Authors: Isabella Caranzano, Corrado Pancotti, Cesare Rollo, Flavio Sartori, Pietro Li\`o, Piero Fariselli, Tiziana Sanavia
Abstract: Biologically-informed neural networks typically leverage pathway annotations to enhance performance in biomedical applications. We hypothesized that the benefits of pathway integration does not arise from its biological relevance, but rather from the sparsity it introduces. We conducted a comprehensive analysis of all relevant pathway-based neural network models for predictive tasks, critically evaluating each study's contributions. From this review, we curated a subset of methods for which the source code was publicly available. The comparison of the biologically informed state-of-the-art deep learning models and their randomized counterparts showed that models based on randomized information performed equally well as biologically informed ones across different metrics and datasets. Notably, in 3 out of the 15 analyzed models, the randomized versions even outperformed their biologically informed counterparts. Moreover, pathway-informed models did not show any clear advantage in interpretability, as randomized models were still able to identify relevant disease biomarkers despite lacking explicit pathway information. Our findings suggest that pathway annotations may be too noisy or inadequately explored by current methods. Therefore, we propose a methodology that can be applied to different domains and can serve as a robust benchmark for systematically comparing novel pathway-informed models against their randomized counterparts. This approach enables researchers to rigorously determine whether observed performance improvements can be attributed to biological insights.
Authors: Moseli Mots'oehli, Hope Mogale, Kyungim Baek
Abstract: Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise, remains largely unexplored. Given the utility and versatility of transformer architectures, this study investigates their practicality under low-budget constraints and noisy labels. We explore how classification accuracy and calibration are affected by symmetric label noise in active learning settings, evaluating four vision transformer configurations (Base and Large with 16x16 and 32x32 patch sizes) and three Swin Transformer configurations (Tiny, Small, and Base) on CIFAR10 and CIFAR100 datasets, under varying label noise rates. Our findings show that larger ViT models (ViTl32 in particular) consistently outperform their smaller counterparts in both accuracy and calibration, even under moderate to high label noise, while Swin Transformers exhibit weaker robustness across all noise levels. We find that smaller patch sizes do not always lead to better performance, as ViTl16 performs consistently worse than ViTl32 while incurring a higher computational cost. We also find that information-based Active Learning strategies only provide meaningful accuracy improvements at moderate label noise rates, but they result in poorer calibration compared to models trained on randomly acquired labels, especially at high label noise rates. We hope these insights provide actionable guidance for practitioners looking to deploy vision transformers in resource-constrained environments, where balancing model complexity, label noise, and compute efficiency is critical in model fine-tuning or distillation.
Authors: Anton Selitskiy, Maitreya Kocharekar
Abstract: In this work, we address the voice conversion (VC) task using a vector-based interface. To align audio embeddings between speakers, we employ discrete optimal transport mapping. Our evaluation results demonstrate the high quality and effectiveness of this method. Additionally, we show that applying discrete optimal transport as a post-processing step in audio generation can lead to the incorrect classification of synthetic audio as real.
Authors: Ziyuan Li, Uwe Jaekel, Babette Dellen
Abstract: We propose a deep product-unit residual neural network (PURe) that integrates product units into residual blocks to improve the expressiveness and parameter efficiency of deep convolutional networks. Unlike standard summation neurons, product units enable multiplicative feature interactions, potentially offering a more powerful representation of complex patterns. PURe replaces conventional convolutional layers with 2D product units in the second layer of each residual block, eliminating nonlinear activation functions to preserve structural information. We validate PURe on three benchmark datasets. On Galaxy10 DECaLS, PURe34 achieves the highest test accuracy of 84.89%, surpassing the much deeper ResNet152, while converging nearly five times faster and demonstrating strong robustness to Poisson noise. On ImageNet, PURe architectures outperform standard ResNet models at similar depths, with PURe34 achieving a top-1 accuracy of 80.27% and top-5 accuracy of 95.78%, surpassing deeper ResNet variants (ResNet50, ResNet101) while utilizing significantly fewer parameters and computational resources. On CIFAR-10, PURe consistently outperforms ResNet variants across varying depths, with PURe272 reaching 95.01% test accuracy, comparable to ResNet1001 but at less than half the model size. These results demonstrate that PURe achieves a favorable balance between accuracy, efficiency, and robustness. Compared to traditional residual networks, PURe not only achieves competitive classification performance with faster convergence and fewer parameters, but also demonstrates greater robustness to noise. Its effectiveness across diverse datasets highlights the potential of product-unit-based architectures for scalable and reliable deep learning in computer vision.
Authors: Wei Wang, Peizheng Li, Angela Doufexi, Mark A. Beach
Abstract: Optimizing discrete phase shifts in large-scale reconfigurable intelligent surfaces (RISs) is challenging due to their non-convex and non-linear nature. In this letter, we propose a heuristic-integrated deep reinforcement learning (DRL) framework that (1) leverages accumulated actions over multiple steps in the double deep Q-network (DDQN) for RIS column-wise control and (2) integrates a greedy algorithm (GA) into each DRL step to refine the state via fine-grained, element-wise optimization of RIS configurations. By learning from GA-included states, the proposed approach effectively addresses RIS optimization within a small DRL action space, demonstrating its capability to optimize phase-shift configurations of large-scale RISs.
Authors: Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu
Abstract: Large language models (LLMs) trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extracting target tokens, building retain sets, and fine-tuning with a tailored loss function comprising three components -- masking, distillation, and world fact. Using low-rank adapters (LoRA), it ensures efficiency without compromising unlearning quality. We conduct experiments on multiple datasets, including the Harry Potter series, WMDP, and TOFU, using a comprehensive suite of metrics: forget quality (new document-level memorization score), model utility, and fluency. Results demonstrate its effectiveness in resisting membership inference attacks, minimizing the impact on retained data, and maintaining robustness across diverse scenarios.
Authors: Sumit Kumar, Parampreet Singh, Vipul Arora
Abstract: Ornamentations, embellishments, or microtonal inflections are essential to melodic expression across many musical traditions, adding depth, nuance, and emotional impact to performances. Recognizing ornamentations in singing voices is key to MIR, with potential applications in music pedagogy, singer identification, genre classification, and controlled singing voice generation. However, the lack of annotated datasets and specialized modeling approaches remains a major obstacle for progress in this research area. In this work, we introduce R\=aga Ornamentation Detection (ROD), a novel dataset comprising Indian classical music recordings curated by expert musicians. The dataset is annotated using a custom Human-in-the-Loop tool for six vocal ornaments marked as event-based labels. Using this dataset, we develop an ornamentation detection model based on deep time-series analysis, preserving ornament boundaries during the chunking of long audio recordings. We conduct experiments using different train-test configurations within the ROD dataset and also evaluate our approach on a separate, manually annotated dataset of Indian classical concert recordings. Our experimental results support the superior performance of our proposed approach over the baseline CRNN.
Authors: Yohannis Telila, Tommaso Cucinotta, Davide Bacciu
Abstract: Automatic music transcription (AMT) is the problem of analyzing an audio recording of a musical piece and detecting notes that are being played. AMT is a challenging problem, particularly when it comes to polyphonic music. The goal of AMT is to produce a score representation of a music piece, by analyzing a sound signal containing multiple notes played simultaneously. In this work, we design a processing pipeline that can transform classical piano audio files in .wav format into a music score representation. The features from the audio signals are extracted using the constant-Q transform, and the resulting coefficients are used as an input to the convolutional neural network (CNN) model.
Authors: Louis Ohl, Pierre-Alexandre Mattei, Fr\'ed\'eric Precioso
Abstract: To cluster data is to separate samples into distinctive groups that should ideally have some cohesive properties. Today, numerous clustering algorithms exist, and their differences lie essentially in what can be perceived as ``cohesive properties''. Therefore, hypotheses on the nature of clusters must be set: they can be either generative or discriminative. As the last decade witnessed the impressive growth of deep clustering methods that involve neural networks to handle high-dimensional data often in a discriminative manner; we concentrate mainly on the discriminative hypotheses. In this paper, our aim is to provide an accessible historical perspective on the evolution of discriminative clustering methods and notably how the nature of assumptions of the discriminative models changed over time: from decision boundaries to invariance critics. We notably highlight how mutual information has been a historical cornerstone of the progress of (deep) discriminative clustering methods. We also show some known limitations of mutual information and how discriminative clustering methods tried to circumvent those. We then discuss the challenges that discriminative clustering faces with respect to the selection of the number of clusters. Finally, we showcase these techniques using the dedicated Python package, GemClus, that we have developed for discriminative clustering.
Authors: Anirban Samaddar, Yixuan Sun, Viktor Nilsson, Sandeep Madireddy
Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models. Building upon the ideas of continuous normalizing flows, flow matching models generalize the transport path of the diffusion models from a simple prior distribution to the data. Most flow matching models in the literature do not explicitly model the underlying structure/manifold in the target data when learning the flow from a simple source distribution like the standard Gaussian. This leads to inefficient learning, especially for many high-dimensional real-world datasets, which often reside in a low-dimensional manifold. Existing strategies of incorporating manifolds, including data with underlying multi-modal distribution, often require expensive training and hence frequently lead to suboptimal performance. To this end, we present \texttt{Latent-CFM}, which provides simplified training/inference strategies to incorporate multi-modal data structures using pretrained deep latent variable models. Through experiments on multi-modal synthetic data and widely used image benchmark datasets, we show that \texttt{Latent-CFM} exhibits improved generation quality with significantly less training ($\sim 50\%$ less in some cases) and computation than state-of-the-art flow matching models. Using a 2d Darcy flow dataset, we demonstrate that our approach generates more physically accurate samples than competitive approaches. In addition, through latent space analysis, we demonstrate that our approach can be used for conditional image generation conditioned on latent features.
Authors: Axel Friedrich Wolter, Tobias Sutter
Abstract: We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the challenge of designing algorithms that leverage off-policy data while maintaining on-policy exploration, we propose PGDA-RL, a novel primal-dual Projected Gradient Descent-Ascent algorithm for solving regularized Markov Decision Processes (MDPs). PGDA-RL integrates experience replay-based gradient estimation with a two-timescale decomposition of the underlying nested optimization problem. The algorithm operates asynchronously, interacts with the environment through a single trajectory of correlated data, and updates its policy online in response to the dual variable associated with the occupation measure of the underlying MDP. We prove that PGDA-RL converges almost surely to the optimal value function and policy of the regularized MDP. Our convergence analysis relies on tools from stochastic approximation theory and holds under weaker assumptions than those required by existing primal-dual RL approaches, notably removing the need for a simulator or a fixed behavioral policy.
Authors: Asma Baobaid, Mahmoud Meribout
Abstract: Cost-effective machine vision systems dedicated to real-time and accurate face detection and recognition in public places are crucial for many modern applications. However, despite their high performance, which could be reached using specialized edge or cloud AI hardware accelerators, there is still room for improvement in throughput and power consumption. This paper aims to suggest a combined hardware-software approach that optimizes face detection and recognition systems on one of the latest edge GPUs, namely NVIDIA Jetson AGX Orin. First, it leverages the simultaneous usage of all its hardware engines to improve processing time. This offers an improvement over previous works where these tasks were mainly allocated automatically and exclusively to the CPU or, to a higher extent, to the GPU core. Additionally, the paper suggests integrating a face tracker module to avoid redundantly running the face recognition algorithm for every frame but only when a new face appears in the scene. The results of extended experiments suggest that simultaneous usage of all the hardware engines that are available in the Orin GPU and tracker integration into the pipeline yield an impressive throughput of 290 FPS (frames per second) on 1920 x 1080 input size frames containing in average of 6 faces/frame. Additionally, a substantial saving of power consumption of around 800 mW was achieved when compared to running the task on the CPU/GPU engines only and without integrating a tracker into the Orin GPU\'92s pipeline. This hardware-codesign approach can pave the way to design high-performance machine vision systems at the edge, critically needed in video monitoring in public places where several nearby cameras are usually deployed for a same scene.
Authors: Kunlun Xu, Xu Zou, Gang Hua, Jiahuan Zhou
Abstract: Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectively store multi-domain knowledge in prompt parameters and obtain advanced performance through cross-domain prompt fusion, we reveal an intrinsic limitation: component-wise misalignment between domain-specific prompts leads to conflicting knowledge integration and degraded predictions. This arises from the random positioning of knowledge components within prompts, where irrelevant component fusion introduces interference.To address this, we propose Componential Prompt-Knowledge Alignment (KA-Prompt), a novel prompt-based DIL method that introduces component-aware prompt-knowledge alignment during training, significantly improving both the learning and inference capacity of the model. KA-Prompt operates in two phases: (1) Initial Componential Structure Configuring, where a set of old prompts containing knowledge relevant to the new domain are mined via greedy search, which is then exploited to initialize new prompts to achieve reusable knowledge transfer and establish intrinsic alignment between new and old prompts. (2) Online Alignment Preservation, which dynamically identifies the target old prompts and applies adaptive componential consistency constraints as new prompts evolve. Extensive experiments on DIL benchmarks demonstrate the effectiveness of our KA-Prompt. Our source code is available at https://github.com/zhoujiahuan1991/ICML2025-KA-Prompt
Authors: St\'ephane Aroca-Ouellette, Miguel Aroca-Ouellette, Katharina von der Wense, Alessandro Roncone
Abstract: In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA$^2$: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA$^2$ in the Overcooked environment, demonstrating statistically significant improvement over existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.
Authors: Nathaniel Dennler, Zhonghao Shi, Uksang Yoo, Stefanos Nikolaidis, Maja Matari\'c
Abstract: Rehabilitation robots are often used in game-like interactions for rehabilitation to increase a person's motivation to complete rehabilitation exercises. By adjusting exercise difficulty for a specific user throughout the exercise interaction, robots can maximize both the user's rehabilitation outcomes and the their motivation throughout the exercise. Previous approaches have assumed exercises have generic difficulty values that apply to all users equally, however, we identified that stroke survivors have varied and unique perceptions of exercise difficulty. For example, some stroke survivors found reaching vertically more difficult than reaching farther but lower while others found reaching farther more challenging than reaching vertically. In this paper, we formulate a causal tree-based method to calculate exercise difficulty based on the user's performance. We find that this approach accurately models exercise difficulty and provides a readily interpretable model of why that exercise is difficult for both users and caretakers.
Authors: Yuning Du, Jingshuai Liu, Rohan Dharmakumar, Sotirios A. Tsaftaris
Abstract: Despite the superior diagnostic capability of Magnetic Resonance Imaging (MRI), its use as a Point-of-Care (PoC) device remains limited by high cost and complexity. To enable such a future by reducing the magnetic field strength, one key approach will be to improve sampling strategies. Previous work has shown that it is possible to make diagnostic decisions directly from k-space with fewer samples. Such work shows that single diagnostic decisions can be made, but if we aspire to see MRI as a true PoC, multiple and sequential decisions are necessary while minimizing the number of samples acquired. We present a novel multi-objective reinforcement learning framework enabling comprehensive, sequential, diagnostic evaluation from undersampled k-space data. Our approach during inference actively adapts to sequential decisions to optimally sample. To achieve this, we introduce a training methodology that identifies the samples that contribute the best to each diagnostic objective using a step-wise weighting reward function. We evaluate our approach in two sequential knee pathology assessment tasks: ACL sprain detection and cartilage thickness loss assessment. Our framework achieves diagnostic performance competitive with various policy-based benchmarks on disease detection, severity quantification, and overall sequential diagnosis, while substantially saving k-space samples. Our approach paves the way for the future of MRI as a comprehensive and affordable PoC device. Our code is publicly available at https://github.com/vios-s/MRI_Sequential_Active_Sampling
URLs: https://github.com/vios-s/MRI_Sequential_Active_Sampling
Authors: Wenhui Sophia Lu, Wing Hung Wong
Abstract: When the likelihood is analytically unavailable and computationally intractable, approximate Bayesian computation (ABC) has emerged as a widely used methodology for approximate posterior inference; however, it suffers from severe computational inefficiency in high-dimensional settings or under diffuse priors. To overcome these limitations, we propose Adaptive Bayesian Inference (ABI), a framework that bypasses traditional data-space discrepancies and instead compares distributions directly in posterior space through nonparametric distribution matching. By leveraging a novel Marginally-augmented Sliced Wasserstein (MSW) distance on posterior measures and exploiting its quantile representation, ABI transforms the challenging problem of measuring divergence between posterior distributions into a tractable sequence of one-dimensional conditional quantile regression tasks. Moreover, we introduce a new adaptive rejection sampling scheme that iteratively refines the posterior approximation by updating the proposal distribution via generative density estimation. Theoretically, we establish parametric convergence rates for the trimmed MSW distance and prove that the ABI posterior converges to the true posterior as the tolerance threshold vanishes. Through extensive empirical evaluation, we demonstrate that ABI significantly outperforms data-based Wasserstein ABC, summary-based ABC, and state-of-the-art likelihood-free simulators, especially in high-dimensional or dependent observation regimes.
Authors: Leonardo V. Santoro, Kartik G. Waghmare, Victor M. Panaretos
Abstract: We establish that testing for the equality of two probability measures on a general separable and compact metric space is equivalent to testing for the singularity between two corresponding Gaussian measures on a suitable Reproducing Kernel Hilbert Space. The corresponding Gaussians are defined via the notion of kernel mean and covariance embedding of a probability measure. Discerning two singular Gaussians is fundamentally simpler from an information-theoretic perspective than non-parametric two-sample testing, particularly in high-dimensional settings. Our proof leverages the Feldman-Hajek criterion for singularity/equivalence of Gaussians on Hilbert spaces, and shows that discrepancies between distributions are heavily magnified through their corresponding Gaussian embeddings: at a population level, distinct probability measures lead to essentially separated Gaussian embeddings. This appears to be a new instance of the blessing of dimensionality that can be harnessed for the design of efficient inference tools in great generality.
Authors: Jessie Richter-Powell, Antonio Torralba, Jonathan Lorraine
Abstract: We introduce Audio-SDS, a generalization of Score Distillation Sampling (SDS) to text-conditioned audio diffusion models. While SDS was initially designed for text-to-3D generation using image diffusion, its core idea of distilling a powerful generative prior into a separate parametric representation extends to the audio domain. Leveraging a single pretrained model, Audio-SDS enables a broad range of tasks without requiring specialized datasets. In particular, we demonstrate how Audio-SDS can guide physically informed impact sound simulations, calibrate FM-synthesis parameters, and perform prompt-specified source separation. Our findings illustrate the versatility of distillation-based methods across modalities and establish a robust foundation for future work using generative priors in audio tasks.
Authors: Jean-Michel Tucny, Mihir Durve, Sauro Succi
Abstract: It is shown that the weight matrices of a Physics-informed neural network (PINN)-based deep learning application to a rarefied gas dynamics problem described by the Boltzmann equation bear no evident link to the mathematical structure of the physical problem. Instead, the weights appear close to Gaussian distributed random matrices. Although significantly more work is needed to support a robust assessment in this direction, these results suggest that deep-learning and the numerical solution of the Boltzmann equation represent two equivalent, but largely distinct paths to the same physical knowledge. If so, Explainable AI might be an unrealistic target and possibly even an ill-posed one.
Authors: Nhan Duy Truong, Jing Yan Haw, Syed Muhamad Assad, Ping Koy Lam, Omid Kavehei
Abstract: Random number generators (RNGs) that are crucial for cryptographic applications have been the subject of adversarial attacks. These attacks exploit environmental information to predict generated random numbers that are supposed to be truly random and unpredictable. Though quantum random number generators (QRNGs) are based on the intrinsic indeterministic nature of quantum properties, the presence of classical noise in the measurement process compromises the integrity of a QRNG. In this paper, we develop a predictive machine learning (ML) analysis to investigate the impact of deterministic classical noise in different stages of an optical continuous variable QRNG. Our ML model successfully detects inherent correlations when the deterministic noise sources are prominent. After appropriate filtering and randomness extraction processes are introduced, our QRNG system, in turn, demonstrates its robustness against ML. We further demonstrate the robustness of our ML approach by applying it to uniformly distributed random numbers from the QRNG and a congruential RNG. Hence, our result shows that ML has potentials in benchmarking the quality of RNG devices.
Authors: Ming Zhu, Xiao-Yang Liu, Sem Borst, Anwar Walid
Abstract: Smart traffic lights in intelligent transportation systems (ITSs) are envisioned to greatly increase traffic efficiency and reduce congestion. Deep reinforcement learning (DRL) is a promising approach to adaptively control traffic lights based on the real-time traffic situation in a road network. However, conventional methods may suffer from poor scalability. In this paper, we investigate deep reinforcement learning to control traffic lights, and both theoretical analysis and numerical experiments show that the intelligent behavior ``greenwave" (i.e., a vehicle will see a progressive cascade of green lights, and not have to brake at any intersection) emerges naturally a grid road network, which is proved to be the optimal policy in an avenue with multiple cross streets. As a first step, we use two DRL algorithms for the traffic light control problems in two scenarios. In a single road intersection, we verify that the deep Q-network (DQN) algorithm delivers a thresholding policy; and in a grid road network, we adopt the deep deterministic policy gradient (DDPG) algorithm. Secondly, numerical experiments show that the DQN algorithm delivers the optimal control, and the DDPG algorithm with passive observations has the capability to produce on its own a high-level intelligent behavior in a grid road network, namely, the ``greenwave" policy emerges. We also verify the ``greenwave" patterns in a $5 \times 10$ grid road network. Thirdly, the ``greenwave" patterns demonstrate that DRL algorithms produce favorable solutions since the ``greenwave" policy shown in experiment results is proved to be optimal in a specified traffic model (an avenue with multiple cross streets). The delivered policies both in a single road intersection and a grid road network demonstrate the scalability of DRL algorithms.
Authors: Alessio Brini, Elisa Giovannini, Elia Smaniotto
Abstract: The beekeeping sector has experienced significant production fluctuations in recent years, largely due to increasingly frequent adverse weather events linked to climate change. These events can severely affect the environment, reducing its suitability for bee activity. We conduct a forecasting analysis of honey production across Italy using a range of machine learning models, with a particular focus on weather-related variables as key predictors. Our analysis relies on a dataset collected in 2022, which combines hive-level observations with detailed weather data. We train and compare several linear and nonlinear models, evaluating both their predictive accuracy and interpretability. By examining model explanations, we identify the main drivers of honey production. We also ensemble models from different families to assess whether combining predictions improves forecast accuracy. These insights support beekeepers in managing production risks and may inform the development of insurance products against unexpected losses due to poor harvests.
Authors: Dimitris Bertsimas, Ryan Cory-Wright, Sean Lo, Jean Pauphilet
Abstract: Low-rank matrix completion consists of computing a matrix of minimal complexity that recovers a given set of observations as accurately as possible. Unfortunately, existing methods for matrix completion are heuristics that, while highly scalable and often identifying high-quality solutions, do not possess any optimality guarantees. We reexamine matrix completion with an optimality-oriented eye. We reformulate low-rank matrix completion problems as convex problems over the non-convex set of projection matrices and implement a disjunctive branch-and-bound scheme that solves them to certifiable optimality. Further, we derive a novel and often near-exact class of convex relaxations by decomposing a low-rank matrix as a sum of rank-one matrices and incentivizing that two-by-two minors in each rank-one matrix have determinant zero. In numerical experiments, our new convex relaxations decrease the optimality gap by two orders of magnitude compared to existing attempts, and our disjunctive branch-and-bound scheme solves $n \times m$ rank-$r$ matrix completion problems to certifiable optimality or near optimality in hours for $\max \{m, n\} \leq 2500$ and $r \leq 5$. Moreover, this improvement in the training error translates into an average $2\%$--$50\%$ improvement in the test set error.
Authors: Thi Kieu Khanh Ho, Narges Armanfard
Abstract: Mainstream unsupervised anomaly detection algorithms often excel in academic datasets, yet their real-world performance is restricted due to the controlled experimental conditions involving clean training data. Addressing the challenge of training with noise, a prevalent issue in practical anomaly detection, is frequently overlooked. In a pioneering endeavor, this study delves into the realm of label-level noise within sensory time-series anomaly detection (TSAD). This paper presents a novel and practical end-to-end unsupervised TSAD when the training data is contaminated with anomalies. The introduced approach, called TSAD-C, is devoid of access to abnormality labels during the training phase. TSAD-C encompasses three core modules: a Decontaminator to rectify anomalies (aka noise) present during training, a Long-range Variable Dependency Modeling module to capture long-term intra- and inter-variable dependencies within the decontaminated data that is considered as a surrogate of the pure normal data, and an Anomaly Scoring module to detect anomalies from all types. Our extensive experiments conducted on four reliable and diverse datasets conclusively demonstrate that TSAD-C surpasses existing methodologies, thus establishing a new state-of-the-art in the TSAD field.
Authors: Priyam Gupta, Peter J. Schmid, Denis Sipp, Taraneh Sayadi, Georgios Rigas
Abstract: The Koopman operator presents an attractive approach to achieve global linearization of nonlinear systems, making it a valuable method for simplifying the understanding of complex dynamics. While data-driven methodologies have exhibited promise in approximating finite Koopman operators, they grapple with various challenges, such as the judicious selection of observables, dimensionality reduction, and the ability to predict complex system behaviours accurately. This study presents a novel approach termed Mori-Zwanzig autoencoder (MZ-AE) to robustly approximate the Koopman operator in low-dimensional spaces. The proposed method leverages a nonlinear autoencoder to extract key observables for approximating a finite invariant Koopman subspace and integrates a non-Markovian correction mechanism using the Mori-Zwanzig formalism. Consequently, this approach yields an approximate closure of the dynamics within the latent manifold of the nonlinear autoencoder, thereby enhancing the accuracy and stability of the Koopman operator approximation. Demonstrations showcase the technique's improved predictive capability for flow around a cylinder. It also provides a low dimensional approximation for Kuramoto-Sivashinsky (KS) with promising short-term predictability and robust long-term statistical performance. By bridging the gap between data-driven techniques and the mathematical foundations of Koopman theory, MZ-AE offers a promising avenue for improved understanding and prediction of complex nonlinear dynamics.
Authors: Ruijie Jiang, Thuan Nguyen, Shuchin Aeron, Prakash Ishwar
Abstract: For a widely-studied data model and general loss and sample-hardening functions we prove that the losses of Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised Contrastive Learning (UCL) are minimized by representations that exhibit Neural-Collapse (NC), i.e., the class means form an Equiangular Tight Frame (ETF) and data from the same class are mapped to the same representation. We also prove that for any representation mapping, the HSCL and Hard-UCL (HUCL) losses are lower bounded by the corresponding SCL and UCL losses. In contrast to existing literature, our theoretical results for SCL do not require class-conditional independence of augmented views and work for a general loss function class that includes the widely used InfoNCE loss function. Moreover, our proofs are simpler, compact, and transparent. Similar to existing literature, our theoretical claims also hold for the practical scenario where batching is used for optimization. We empirically demonstrate, for the first time, that Adam optimization (with batching) of HSCL and HUCL losses with random initialization and suitable hardness levels can indeed converge to the NC-geometry if we incorporate unit-ball or unit-sphere feature normalization. Without incorporating hard-negatives or feature normalization, however, the representations learned via Adam suffer from Dimensional-Collapse (DC) and fail to attain the NC-geometry. These results exemplify the role of hard-negative sampling in contrastive representation learning and we conclude with several open theoretical problems for future work. The code can be found at https://github.com/rjiang03/HCL/tree/main
Authors: Dimitrios Danopoulos, Georgios Zervakis, Dimitrios Soudris, J\"org Henkel
Abstract: Vision Transformer (ViT) models which were recently introduced by the transformer architecture have shown to be very competitive and often become a popular alternative to Convolutional Neural Networks (CNNs). However, the high computational requirements of these models limit their practical applicability especially on low-power devices. Current state-of-the-art employs approximate multipliers to address the highly increased compute demands of DNN accelerators but no prior research has explored their use on ViT models. In this work we propose TransAxx, a framework based on the popular PyTorch library that enables fast inherent support for approximate arithmetic to seamlessly evaluate the impact of approximate computing on DNNs such as ViT models. Using TransAxx we analyze the sensitivity of transformer models on the ImageNet dataset to approximate multiplications and perform approximate-aware finetuning to regain accuracy. Furthermore, we propose a methodology to generate approximate accelerators for ViT models. Our approach uses a Monte Carlo Tree Search (MCTS) algorithm to efficiently search the space of possible configurations using a hardware-driven hand-crafted policy. Our evaluation demonstrates the efficacy of our methodology in achieving significant trade-offs between accuracy and power, resulting in substantial gains without compromising on performance.
Authors: Shuhao Cao, Francesco Brarda, Ruipeng Li, Yuanzhe Xi
Abstract: Recent advancements in operator-type neural networks have shown promising results in approximating the solutions of spatiotemporal Partial Differential Equations (PDEs). However, these neural networks often entail considerable training expenses, and may not always achieve the desired accuracy required in many scientific and engineering disciplines. In this paper, we propose a new learning framework to address these issues. A new spatiotemporal adaptation is proposed to generalize any Fourier Neural Operator (FNO) variant to learn maps between Bochner spaces, which can perform an arbitrary-length temporal super-resolution for the first time. To better exploit this capacity, a new paradigm is proposed to refine the commonly adopted end-to-end neural operator training and evaluations with the help from the wisdom from traditional numerical PDE theory and techniques. Specifically, in the learning problems for the turbulent flow modeled by the Navier-Stokes Equations (NSE), the proposed paradigm trains an FNO only for a few epochs. Then, only the newly proposed spatiotemporal spectral convolution layer is fine-tuned without the frequency truncation. The spectral fine-tuning loss function uses a negative Sobolev norm for the first time in operator learning, defined through a reliable functional-type a posteriori error estimator whose evaluation is exact thanks to the Parseval identity. Moreover, unlike the difficult nonconvex optimization problems in the end-to-end training, this fine-tuning loss is convex. Numerical experiments on commonly used NSE benchmarks demonstrate significant improvements in both computational efficiency and accuracy, compared to end-to-end evaluation and traditional numerical PDE solvers under certain conditions. The source code is publicly available at https://github.com/scaomath/torch-cfd.
Authors: Philippe Chlenski, Quentin Chu, Itsik Pe'er
Abstract: We extend decision tree and random forest algorithms to product space manifolds: Cartesian products of Euclidean, hyperspherical, and hyperbolic manifolds. Such spaces have extremely expressive geometries capable of representing many arrangements of distances with low metric distortion. To date, all classifiers for product spaces fit a single linear decision boundary, and no regressor has been described. Our method enables a simple, expressive method for classification and regression in product manifolds. We demonstrate the superior accuracy of our tool compared to Euclidean methods operating in the ambient space or the tangent plane of the manifold across a range of constant-curvature and product manifolds. Code for our implementation and experiments is available at https://github.com/pchlenski/embedders.
Authors: Christian Raymond
Abstract: Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even the most basic tasks. Meta-learning aims to resolve this issue by leveraging past experiences from similar learning tasks to embed the appropriate inductive biases into the learning system. Historically methods for meta-learning components such as optimizers, parameter initializations, and more have led to significant performance increases. This thesis aims to explore the concept of meta-learning to improve performance, through the often-overlooked component of the loss function. The loss function is a vital component of a learning system, as it represents the primary learning objective, where success is determined and quantified by the system's ability to optimize for that objective successfully.
Authors: Lyudong Jin, Ming Tang, Jiayu Pan, Meng Zhang, Hao Wang
Abstract: In the realm of emerging real-time networked applications like cyber-physical systems (CPS), the Age of Information (AoI) has merged as a pivotal metric for evaluating the timeliness. To meet the high computational demands, such as those in intelligent manufacturing within CPS, mobile edge computing (MEC) presents a promising solution for optimizing computing and reducing AoI. In this work, we study the timeliness of computational-intensive updates and explores jointly optimize the task updating and offloading policies to minimize AoI. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The fractional objective introduced by AoI and the semi-Markov game nature of the problem render this challenge particularly difficult, with existing approaches not directly applicable. To this end, we present a comprehensive framework to fractional reinforcement learning (RL). We first introduce a fractional single-agent RL framework and prove its linear convergence. We then extend this to a fractional multi-agent RL framework with a convergence analysis. To tackle the challenge of asynchronous control in semi-Markov game, we further design an asynchronous model-free fractional multi-agent RL algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 52.6% compared with the best baseline algorithm in our experiments.
Authors: Hung Manh Pham, Aaqib Saeed, Dong Ma
Abstract: The accurate interpretation of Electrocardiogram (ECG) signals is pivotal for diagnosing cardiovascular diseases. Integrating ECG signals with accompanying textual reports further holds immense potential to enhance clinical diagnostics by combining physiological data and qualitative insights. However, this integration faces significant challenges due to inherent modality disparities and the scarcity of labeled data for robust cross-modal learning. To address these obstacles, we propose D-BETA, a novel framework that pre-trains ECG and text data using a contrastive masked auto-encoder architecture. D-BETA uniquely combines the strengths of generative with boosted discriminative capabilities to achieve robust cross-modal representations. This is accomplished through masked modality modeling, specialized loss functions, and an improved negative sampling strategy tailored for cross-modal alignment. Extensive experiments on five public datasets across diverse downstream tasks demonstrate that D-BETA significantly outperforms existing methods, achieving an average AUC improvement of 15% in linear probing with only one percent of training data and 2% in zero-shot performance without requiring training data over state-of-the-art models. These results highlight the effectiveness of D-BETA, underscoring its potential to advance automated clinical diagnostics through multi-modal representations. Our sample code and checkpoint are made available at https://github.com/manhph2211/D-BETA.
Authors: Jenna Fromer, Runzhong Wang, Mrunali Manjrekar, Austin Tripp, Jos\'e Miguel Hern\'andez-Lobato, Connor W. Coley
Abstract: Batched Bayesian optimization (BO) can accelerate molecular design by efficiently identifying top-performing compounds from a large chemical library. Existing acquisition strategies for batch design in BO aim to balance exploration and exploitation. This often involves optimizing non-additive batch acquisition functions, necessitating approximation via myopic construction and/or diversity heuristics. In this work, we propose an acquisition strategy for discrete optimization that is motivated by pure exploitation, qPO (multipoint Probability of Optimality). qPO maximizes the probability that the batch includes the true optimum, which is expressible as the sum over individual acquisition scores and thereby circumvents the combinatorial challenge of optimizing a batch acquisition function. We differentiate the proposed strategy from parallel Thompson sampling and discuss how it implicitly captures diversity. Finally, we apply our method to the model-guided exploration of large chemical libraries and provide empirical evidence that it is competitive with and complements other state-of-the-art methods in batched Bayesian optimization.
Authors: Matthew X. Burns, Qingyuan Hou, Michael C. Huang
Abstract: Analog dynamical accelerators (DXs) are a growing sub-field in computer architecture research, offering order-of-magnitude gains in power efficiency and latency over traditional digital methods in several machine learning, optimization, and sampling tasks. However, limited-capacity accelerators require hybrid analog/digital algorithms to solve real-world problems, commonly using large-neighborhood local search (LNLS) frameworks. Unlike fully digital algorithms, hybrid LNLS has no non-asymptotic convergence guarantees and no principled hyperparameter selection schemes, particularly limiting cross-device training and inference. In this work, we provide non-asymptotic convergence guarantees for hybrid LNLS by reducing to block Langevin Diffusion (BLD) algorithms. Adapting tools from classical sampling theory, we prove exponential KL-divergence convergence for randomized and cyclic block selection strategies using ideal DXs. With finite device variation, we provide explicit bounds on the 2-Wasserstein bias in terms of step duration, noise strength, and function parameters. Our BLD model provides a key link between established theory and novel computing platforms, and our theoretical results provide a closed-form expression linking device variation, algorithm hyperparameters, and performance.
Authors: Weizhu Qian, Dalin Zhang, Yan Zhao, Yunyao Cheng
Abstract: Time series imputation is important for numerous real-world applications. To overcome the limitations of diffusion model-based imputation methods, e.g., slow convergence in inference, we propose a novel method for time series imputation in this work, called Conditional Lagrangian Wasserstein Flow (CLWF). Following the principle of least action in Lagrangian mechanics, we learn the velocity by minimizing the corresponding kinetic energy. Moreover, to enhance the model's performance, we estimate the gradient of a task-specific potential function using a time-dependent denoising autoencoder and integrate it into the base estimator to reduce the sampling variance. Finally, the proposed method demonstrates competitive performance compared to other state-of-the-art imputation approaches.
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: Daiqi Gao, Hsin-Yu Lai, Predrag Klasnja, Susan A. Murphy
Abstract: We consider reinforcement learning (RL) for a class of problems with bagged decision times. A bag contains a finite sequence of consecutive decision times. The transition dynamics are non-Markovian and non-stationary within a bag. All actions within a bag jointly impact a single reward, observed at the end of the bag. For example, in mobile health, multiple activity suggestions in a day collectively affect a user's daily commitment to being active. Our goal is to develop an online RL algorithm to maximize the discounted sum of the bag-specific rewards. To handle non-Markovian transitions within a bag, we utilize an expert-provided causal directed acyclic graph (DAG). Based on the DAG, we construct states as a dynamical Bayesian sufficient statistic of the observed history, which results in Markov state transitions within and across bags. We then formulate this problem as a periodic Markov decision process (MDP) that allows non-stationarity within a period. An online RL algorithm based on Bellman equations for stationary MDPs is generalized to handle periodic MDPs. We show that our constructed state achieves the maximal optimal value function among all state constructions for a periodic MDP. Finally, we evaluate the proposed method on testbed variants built from real data in a mobile health clinical trial.
Authors: Flavio Corradini, Flavio Gerosa, Marco Gori, Carlo Lucheroni, Marco Piangerelli, Martina Zannotti
Abstract: In recent years, spatio-temporal graph neural networks (GNNs) have attracted considerable interest in the field of time series analysis, due to their ability to capture dependencies among variables and across time points. The objective of the presented systematic literature review is hence to provide a comprehensive overview of the various modeling approaches and application domains of GNNs for time series classification and forecasting. A database search was conducted, and over 150 journal papers were selected for a detailed examination of the current state-of-the-art in the field. This examination is intended to offer to the reader a comprehensive collection of proposed models, links to related source code, available datasets, benchmark models, and fitting results. All this information is hoped to assist researchers in future studies. To the best of our knowledge, this is the first systematic literature review presenting a detailed comparison of the results of current spatio-temporal GNN models in different domains. In addition, in its final part this review discusses current limitations and challenges in the application of spatio-temporal GNNs, such as comparability, reproducibility, explainability, poor information capacity, and scalability.
Authors: Wentao Zhang, Jingyuan Wang, Yifan Yang, Leong Hou U
Abstract: Electronic maps consist of diverse entities, such as points of interest (POIs), road networks, and land parcels, playing a vital role in applications like ITS and LBS. Map entity representation learning (MapRL) generates versatile and reusable data representations, providing essential tools for efficiently managing and utilizing map entity data. Despite the progress in MapRL, two key challenges constrain further development. First, existing research is fragmented, with models classified by the type of map entity, limiting the reusability of techniques across different tasks. Second, the lack of unified benchmarks makes systematic evaluation and comparison of models difficult. To address these challenges, we propose a novel taxonomy for MapRL that organizes models based on functional module-such as encoders, pre-training tasks, and downstream tasks-rather than by entity type. Building on this taxonomy, we present a taxonomy-driven library, VecCity, which offers easy-to-use interfaces for encoding, pre-training, fine-tuning, and evaluation. The library integrates datasets from nine cities and reproduces 21 mainstream MapRL models, establishing the first standardized benchmarks for the field. VecCity also allows users to modify and extend models through modular components, facilitating seamless experimentation. Our comprehensive experiments cover multiple types of map entities and evaluate 21 VecCity pre-built models across various downstream tasks. Experimental results demonstrate the effectiveness of VecCity in streamlining model development and provide insights into the impact of various components on performance. By promoting modular design and reusability, VecCity offers a unified framework to advance research and innovation in MapRL. The code is available at https://github.com/Bigscity-VecCity/VecCity.
Authors: Qingtian Zhu, Yumin Zheng, Yuling Sang, Yifan Zhan, Ziyan Zhu, Jun Ding, Yinqiang Zheng
Abstract: Spatial Transcriptomics (ST) is a method that captures gene expression profiles aligned with spatial coordinates. The discrete spatial distribution and the super-high dimensional sequencing results make ST data challenging to be modeled effectively. In this paper, we manage to model ST in a continuous and compact manner by the proposed tool, SUICA, empowered by the great approximation capability of Implicit Neural Representations (INRs) that can enhance both the spatial density and the gene expression. Concretely within the proposed SUICA, we incorporate a graph-augmented Autoencoder to effectively model the context information of the unstructured spots and provide informative embeddings that are structure-aware for spatial mapping. We also tackle the extremely skewed distribution in a regression-by-classification fashion and enforce classification-based loss functions for the optimization of SUICA. By extensive experiments of a wide range of common ST platforms under varying degradations, SUICA outperforms both conventional INR variants and SOTA methods regarding numerical fidelity, statistical correlation, and bio-conservation. The prediction by SUICA also showcases amplified gene signatures that enriches the bio-conservation of the raw data and benefits subsequent analysis. The code is available at https://github.com/Szym29/SUICA.
Authors: Guang Wu, Yun Wang, Qian Zhou, Ziyang Zhang
Abstract: Accurate photovoltaic (PV) power forecasting is critical for integrating renewable energy sources into the grid, optimizing real-time energy management, and ensuring energy reliability amidst increasing demand. However, existing models often struggle with effectively capturing the complex relationships between target variables and covariates, as well as the interactions between temporal dynamics and multivariate data, leading to suboptimal forecasting accuracy. To address these challenges, we propose a novel model architecture that leverages the iTransformer for feature extraction from target variables and employs long short-term memory (LSTM) to extract features from covariates. A cross-attention mechanism is integrated to fuse the outputs of both models, followed by a Kolmogorov-Arnold network (KAN) mapping for enhanced representation. The effectiveness of the proposed model is validated using publicly available datasets from Australia, with experiments conducted across four seasons. Results demonstrate that the proposed model effectively capture seasonal variations in PV power generation and improve forecasting accuracy.
Authors: Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
Abstract: Federated learning (FL) is a widely used and impactful distributed optimization framework that achieves consensus through averaging locally trained models. While effective, this approach may not align well with Bayesian inference, where the model space has the structure of a distribution space. Taking an information-geometric perspective, we reinterpret FL aggregation as the problem of finding the barycenter of local posteriors using a prespecified divergence metric, minimizing the average discrepancy across clients. This perspective provides a unifying framework that generalizes many existing methods and offers crisp insights into their theoretical underpinnings. We then propose BA-BFL, an algorithm that retains the convergence properties of Federated Averaging in non-convex settings. In non-independent and identically distributed scenarios, we conduct extensive comparisons with statistical aggregation techniques, showing that BA-BFL achieves performance comparable to state-of-the-art methods while offering a geometric interpretation of the aggregation phase. Additionally, we extend our analysis to Hybrid Bayesian Deep Learning, exploring the impact of Bayesian layers on uncertainty quantification and model calibration.
Authors: Yichen Li, Yuying Wang, Haozhao Wang, Yining Qi, Tianzhe Xiao, Ruixuan Li
Abstract: Continual Federated Learning (CFL) allows distributed devices to collaboratively learn novel concepts from continuously shifting training data while avoiding knowledge forgetting of previously seen tasks. To tackle this challenge, most current CFL approaches rely on extensive rehearsal of previous data. Despite effectiveness, rehearsal comes at a cost to memory, and it may also violate data privacy. Considering these, we seek to apply regularization techniques to CFL by considering their cost-efficient properties that do not require sample caching or rehearsal. Specifically, we first apply traditional regularization techniques to CFL and observe that existing regularization techniques, especially synaptic intelligence, can achieve promising results under homogeneous data distribution but fail when the data is heterogeneous. Based on this observation, we propose a simple yet effective regularization algorithm for CFL named FedSSI, which tailors the synaptic intelligence for the CFL with heterogeneous data settings. FedSSI can not only reduce computational overhead without rehearsal but also address the data heterogeneity issue. Extensive experiments show that FedSSI achieves superior performance compared to state-of-the-art methods.
Authors: Rui Wang, Mingxuan Xia, Chang Yao, Lei Feng, Junbo Zhao, Gang Chen, Haobo Wang
Abstract: Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality annotated data in a dynamic learning system can be extremely expensive. To mitigate this problem, we propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL), where the sequentially arrived data relate to a set of candidate labels rather than the ground truth. Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i.e., label ambiguity and catastrophic forgetting. To handle the former, PGDR encapsulates a momentum-based pseudo-labeling algorithm along with prototype-guided initialization, resulting in a balanced perception of classes. To alleviate forgetting, we develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity. By jointly distilling knowledge from curated memory data, our framework exhibits a great disambiguation ability for samples of new tasks and achieves less forgetting of knowledge. Extensive experiments demonstrate that PGDR achieves superior
Authors: Michael Crawshaw, Blake Woodworth, Mingrui Liu
Abstract: We analyze two variants of Local Gradient Descent applied to distributed logistic regression with heterogeneous, separable data and show convergence at the rate $O(1/KR)$ for $K$ local steps and sufficiently large $R$ communication rounds. In contrast, all existing convergence guarantees for Local GD applied to any problem are at least $\Omega(1/R)$, meaning they fail to show the benefit of local updates. The key to our improved guarantee is showing progress on the logistic regression objective when using a large stepsize $\eta \gg 1/K$, whereas prior analysis depends on $\eta \leq 1/K$.
Authors: Hao-Zhe Tan, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
Abstract: Pre-trained Vision-Language Models (VLMs) are becoming increasingly popular across various visual tasks, and several open-sourced VLM variants have been released. However, selecting the best-performing pre-trained VLM for a specific downstream task is challenging since no single VLM can achieve promising performance on all downstream tasks, and evaluating all available VLMs is impossible due to time and data limitations. To address this problem, this paper proposes a novel paradigm to select and reuse VLM for downstream tasks, called Model Label Learning (MLL). The proposal contains three key modules: \emph{model labeling}, which assigns labels to each VLM to describe their specialty and utility; \emph{model selection}, which matches the requirements of the target task with model labels; and \emph{model reuse}, which applies selected VLMs to the target task in an ensemble manner. The proposal is highly computationally efficient and growable since the model labeling process is completed target task independent and the ability could grow with the number of candidate VLMs. We also introduce a new benchmark for evaluating VLM selection methods, including 49 VLMs and 17 target task datasets. Experimental results clearly demonstrate the effectiveness of the proposed method for selecting and reusing VLMs.
Authors: Terje Mildner, Oliver Hamelijnck, Paris Giampouras, Theodoros Damoulas
Abstract: We introduce FedGVI, a probabilistic Federated Learning (FL) framework that is robust to both prior and likelihood misspecification. FedGVI addresses limitations in both frequentist and Bayesian FL by providing unbiased predictions under model misspecification, with calibrated uncertainty quantification. Our approach generalises previous FL approaches, specifically Partitioned Variational Inference (Ashman et al., 2022), by allowing robust and conjugate updates, decreasing computational complexity at the clients. We offer theoretical analysis in terms of fixed-point convergence, optimality of the cavity distribution, and provable robustness to likelihood misspecification. Further, we empirically demonstrate the effectiveness of FedGVI in terms of improved robustness and predictive performance on multiple synthetic and real world classification data sets.
Authors: Fakrul Islam Tushar, Lavsen Dahal, Cindy McCabe, Fong Chi Ho, Paul Segars, Ehsan Abadi, Kyle J. Lafata, Ehsan Samei, Joseph Y. Lo
Abstract: AI models for lung cancer screening are limited by data scarcity, impacting generalizability and clinical applicability. Generative models address this issue but are constrained by training data variability. We introduce SYN-LUNGS, a framework for generating high-quality 3D CT images with detailed annotations. SYN-LUNGS integrates XCAT3 phantoms for digital twin generation, X-Lesions for nodule simulation (varying size, location, and appearance), and DukeSim for CT image formation with vendor and parameter variability. The dataset includes 3,072 nodule images from 1,044 simulated CT scans, with 512 lesions and 174 digital twins. Models trained on clinical + simulated data outperform clinical only models, achieving 10% improvement in detection, 2-9% in segmentation and classification, and enhanced synthesis. By incorporating anatomy-informed simulations, SYN-LUNGS provides a scalable approach for AI model development, particularly in rare disease representation and improving model reliability.
Authors: Roberto Garcia, Jerry Liu, Daniel Sorvisto, Sabri Eyuboglu
Abstract: Large Language Models (LLMs) are computationally intensive, particularly during inference. Neuron-adaptive techniques, which selectively activate neurons in Multi-Layer Perceptron (MLP) layers, offer some speedups but suffer from limitations in modern Transformers. These include reliance on sparse activations, incompatibility with attention layers, and the use of costly neuron masking techniques. To address these issues, we propose the Adaptive Rank Allocation framework and introduce the Rank and Neuron Allocator (RaNA) adapter. RaNA adapters leverage rank adapters, which operate on linear layers by applying both low-rank matrix decompositions and adaptive masking to efficiently allocate compute without depending on activation sparsity. This enables RaNA to be generally applied to MLPs and linear components of attention modules, while eliminating the need for expensive maskers found in neuron-adaptive methods. Notably, when compared to neuron adapters, RaNA improves perplexity by up to 7 points and increases accuracy by up to 8 percentage-points when reducing FLOPs by $\sim$44% in state-of-the-art Transformer architectures. These results position RaNA as a robust solution for improving inference efficiency in modern Transformer architectures.
Authors: Christoforos N. Spartalis, Theodoros Semertzidis, Efstratios Gavves, Petros Daras
Abstract: We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the model up to an information-theoretic bound, mitigating its over-confidence stemming from data memorization. We evaluate LoTUS on Transformer and ResNet18 models against eight baselines across five public datasets. Beyond established MU benchmarks, we evaluate unlearning on ImageNet1k, a large-scale dataset, where retraining is impractical, simulating real-world conditions. Moreover, we introduce the novel Retrain-Free Jensen-Shannon Divergence (RF-JSD) metric to enable evaluation under real-world conditions. The experimental results show that LoTUS outperforms state-of-the-art methods in terms of both efficiency and effectiveness. Code: https://github.com/cspartalis/LoTUS.
Authors: Weihao Zeng, Yuzhen Huang, Qian Liu, Wei Liu, Keqing He, Zejun Ma, Junxian He
Abstract: DeepSeek-R1 has shown that long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning (RL) framework with rule-based rewards, where the training may directly start from the base models-a paradigm referred to as zero RL training. Most recent efforts to reproduce zero RL training have primarily focused on the Qwen2.5 model series, which may not be representative as we find the base models already exhibit strong instruction-following and self-reflection abilities. In this work, we investigate zero RL training across 10 diverse base models, spanning different families and sizes including LLama3-8B, Mistral-7B/24B, DeepSeek-Math-7B, Qwen2.5-math-7B, and all Qwen2.5 models from 0.5B to 32B. Leveraging several key design strategies-such as adjusting format reward and controlling query difficulty-we achieve substantial improvements in both reasoning accuracy and response length across most settings. However, by carefully monitoring the training dynamics, we observe that different base models exhibit distinct patterns during training. For instance, the increased response length does not always correlate with the emergence of certain cognitive behaviors such as verification (i.e., the "aha moment"). Notably, we observe the "aha moment" for the first time in small models not from the Qwen family. We share the key designs that enable successful zero RL training, along with our findings and practices. To facilitate further research, we open-source the code, models, and analysis tools.
Authors: Haoyuan Li, Mathias Funk, Jindong Wang, Aaqib Saeed
Abstract: Federated Active Learning (FAL) has emerged as a promising framework to leverage large quantities of unlabeled data across distributed clients while preserving data privacy. However, real-world deployments remain limited by high annotation costs and communication-intensive sampling processes, particularly in a cross-silo setting, when clients possess substantial local datasets. This paper addresses the crucial question: What is the best practice to reduce communication costs in human-in-the-loop learning with minimal annotator effort? Existing FAL methods typically rely on iterative annotation processes that separate active sampling from federated updates, leading to multiple rounds of expensive communication and annotation. In response, we introduce FAST, a two-pass FAL framework that harnesses foundation models for weak labeling in a preliminary pass, followed by a refinement pass focused exclusively on the most uncertain samples. By leveraging representation knowledge from foundation models and integrating refinement steps into a streamlined workflow, FAST substantially reduces the overhead incurred by iterative active sampling. Extensive experiments on diverse medical and natural image benchmarks demonstrate that FAST outperforms existing FAL methods by an average of 4.36% while reducing communication rounds eightfold under a limited 5% labeling budget.
Authors: Sanyam Paresh Shah, Abdullah Mamun, Shovito Barua Soumma, Hassan Ghasemzadeh
Abstract: Metabolic Syndrome (MetS) is a cluster of interrelated risk factors that significantly increases the risk of cardiovascular diseases and type 2 diabetes. Despite its global prevalence, accurate prediction of MetS remains challenging due to issues such as class imbalance, data scarcity, and methodological inconsistencies in existing studies. In this paper, we address these challenges by systematically evaluating and optimizing machine learning (ML) models for MetS prediction, leveraging advanced data balancing techniques and counterfactual analysis. Multiple ML models, including XGBoost, Random Forest, TabNet, etc., were trained and compared under various data balancing techniques such as random oversampling (ROS), SMOTE, ADASYN, and CTGAN. Additionally, we introduce MetaBoost, a novel hybrid framework that integrates SMOTE, ADASYN, and CTGAN, optimizing synthetic data generation through weighted averaging and iterative weight tuning to enhance the model's performance (achieving up to a 1.87% accuracy improvement over individual balancing techniques). A comprehensive counterfactual analysis is conducted to quantify the feature-level changes required to shift individuals from high-risk to low-risk categories. The results indicate that blood glucose (50.3%) and triglycerides (46.7%) were the most frequently modified features, highlighting their clinical significance in MetS risk reduction. Additionally, probabilistic analysis shows elevated blood glucose (85.5% likelihood) and triglycerides (74.9% posterior probability) as the strongest predictors. This study not only advances the methodological rigor of MetS prediction but also provides actionable insights for clinicians and researchers, highlighting the potential of ML in mitigating the public health burden of metabolic syndrome.
Authors: Christopher M. Ackerman, Nina Panickssery
Abstract: Many-shot jailbreaking (MSJ) is an adversarial technique that exploits the long context windows of modern LLMs to circumvent model safety training by including in the prompt many examples of a "fake" assistant responding inappropriately before the final request. With enough examples, the model's in-context learning abilities override its safety training, and it responds as if it were the "fake" assistant. In this work, we probe the effectiveness of different fine-tuning and input sanitization approaches on mitigating MSJ attacks, alone and in combination. We find incremental mitigation effectiveness for each, and show that the combined techniques significantly reduce the effectiveness of MSJ attacks, while retaining model performance in benign in-context learning and conversational tasks. We suggest that our approach could meaningfully ameliorate this vulnerability if incorporated into model safety post-training.
Authors: Georgios Papadopoulos, Shaltiel Eloul, Yash Satsangi, Jamie Heredge, Niraj Kumar, Chun-Fu Chen, Marco Pistoia
Abstract: The loss landscape of Variational Quantum Neural Networks (VQNNs) is characterized by local minima that grow exponentially with increasing qubits. Because of this, it is more challenging to recover information from model gradients during training compared to classical Neural Networks (NNs). In this paper we present a numerical scheme that successfully reconstructs input training, real-world, practical data from trainable VQNNs' gradients. Our scheme is based on gradient inversion that works by combining gradients estimation with the finite difference method and adaptive low-pass filtering. The scheme is further optimized with Kalman filter to obtain efficient convergence. Our experiments show that our algorithm can invert even batch-trained data, given the VQNN model is sufficiently over-parameterized.
Authors: Essential AI, :, Ishaan Shah, Anthony M. Polloreno, Karl Stratos, Philip Monk, Adarsh Chaluvaraju, Andrew Hojel, Andrew Ma, Anil Thomas, Ashish Tanwer, Darsh J Shah, Khoi Nguyen, Kurt Smith, Michael Callahan, Michael Pust, Mohit Parmar, Peter Rushton, Platon Mazarakis, Ritvik Kapila, Saurabh Srivastava, Somanshu Singla, Tim Romanski, Yash Vanjani, Ashish Vaswani
Abstract: We demonstrate that Muon, the simplest instantiation of a second-order optimizer, explicitly expands the Pareto frontier over AdamW on the compute-time tradeoff. We find that Muon is more effective than AdamW in retaining data efficiency at large batch sizes, far beyond the so-called critical batch size, while remaining computationally efficient, thus enabling more economical training. We study the combination of Muon and the maximal update parameterization (muP) for efficient hyperparameter transfer and present a simple telescoping algorithm that accounts for all sources of error in muP while introducing only a modest overhead in resources. We validate our findings through extensive experiments with model sizes up to four billion parameters and ablations on the data distribution and architecture.
Authors: Juyoung Yun
Abstract: Sharpness-Aware Minimization (SAM) improves neural network generalization by optimizing the worst-case loss within a neighborhood of parameters, yet it perturbs parameters using the entire gradient vector, including components with low statistical significance. We introduce ZSharp, a refined sharpness-aware optimization method that incorporates layer-wise Z-score normalization followed by percentile-based filtering. This process selects only the most statistically significant gradient components-those with large standardized magnitudes-for constructing the perturbation direction. ZSharp retains the standard two-phase SAM structure of ascent and descent while modifying the ascent step to focus on sharper, curvature-relevant directions. We evaluate ZSharp on CIFAR-10, CIFAR-100, and Tiny-ImageNet using a range of models including ResNet, VGG, and Vision Transformers. Across all architectures and datasets, ZSharp consistently achieves higher test accuracy compared to SAM, ASAM, and Friendly-SAM. These results indicate that Z-score-based gradient filtering can enhance the sharpness sensitivity of the update direction, leading to improved generalization in deep neural network training.
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 Prediction Market. Our results suggest future designs where the price update rule is separate from the fee structure, yet guarantees are preserved.
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: 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: 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: Jonathan Scarlett
Abstract: We consider the problem of Bayesian optimization (BO) in one dimension, under a Gaussian process prior and Gaussian sampling noise. We provide a theoretical analysis showing that, under fairly mild technical assumptions on the kernel, the best possible cumulative regret up to time $T$ behaves as $\Omega(\sqrt{T})$ and $O(\sqrt{T\log T})$. This gives a tight characterization up to a $\sqrt{\log T}$ factor, and includes the first non-trivial lower bound for noisy BO. Our assumptions are satisfied, for example, by the squared exponential and Mat\'ern-$\nu$ kernels, with the latter requiring $\nu > 2$. Our results certify the near-optimality of existing bounds (Srinivas {\em et al.}, 2009) for the SE kernel, while proving them to be strictly suboptimal for the Mat\'ern kernel with $\nu > 2$.
Authors: Victor Chernozhukov, Whitney Newey, Vira Semenova
Abstract: This paper introduces metrics for welfare analysis in dynamic models. We develop estimation and inference for these parameters even in the presence of a high-dimensional state space. Examples of welfare metrics include average welfare, average marginal welfare effects, and welfare decompositions into direct and indirect effects similar to Oaxaca (1973) and Blinder (1973). We derive dual and doubly robust representations of welfare metrics that facilitate debiased inference. For average welfare, the value function does not have to be estimated. In general, debiasing can be applied to any estimator of the value function, including neural nets, random forests, Lasso, boosting, and other high-dimensional methods. In particular, we derive Lasso and Neural Network estimators of the value function and associated dynamic dual representation and establish associated mean square convergence rates for these functions. Debiasing is automatic in the sense that it only requires knowledge of the welfare metric of interest, not the form of bias correction. The proposed methods are applied to estimate a dynamic behavioral model of teacher absenteeism in \cite{DHR} and associated average teacher welfare.
Authors: Frederik Pahde, Maximilian Dreyer, Leander Weber, Moritz Weckbecker, Christopher J. Anders, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin
Abstract: With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CAVs are computed by leveraging linear classifiers optimizing the separability of latent representations of samples with and without a given concept. However, in this paper we show that such a separability-oriented computation leads to solutions, which may diverge from the actual goal of precisely modeling the concept direction. This discrepancy can be attributed to the significant influence of distractor directions, i.e., signals unrelated to the concept, which are picked up by filters (i.e., weights) of linear models to optimize class-separability. To address this, we introduce pattern-based CAVs, solely focussing on concept signals, thereby providing more accurate concept directions. We evaluate various CAV methods in terms of their alignment with the true concept direction and their impact on CAV applications, including concept sensitivity testing and model correction for shortcut behavior caused by data artifacts. We demonstrate the benefits of pattern-based CAVs using the Pediatric Bone Age, ISIC2019, and FunnyBirds datasets with VGG, ResNet, ReXNet, EfficientNet, and Vision Transformer as model architectures.
Authors: Jiahua Xu, Yebo Feng, Daniel Perez, Benjamin Livshits
Abstract: Decentralized finance (DeFi) is an integral component of the blockchain ecosystem, enabling a range of financial activities through smart-contract-based protocols. Traditional DeFi governance typically involves manual parameter adjustments by protocol teams or token holder votes, and is thus prone to human bias and financial risks, undermining the system's integrity and security. While existing efforts aim to establish more adaptive parameter adjustment schemes, there remains a need for a governance model that is both more efficient and resilient to significant market manipulations. In this paper, we introduce "Auto$.$gov", a learning-based governance framework that employs a deep Qnetwork (DQN) reinforcement learning (RL) strategy to perform semi-automated, data-driven parameter adjustments. We create a DeFi environment with an encoded action-state space akin to the Aave lending protocol for simulation and testing purposes, where Auto$.$gov has demonstrated the capability to retain funds that would have otherwise been lost to price oracle attacks. In tests with real-world data, Auto$.$gov outperforms the benchmark approaches by at least 14% and the static baseline model by tenfold, in terms of the preset performance metric--protocol profitability. Overall, the comprehensive evaluations confirm that Auto$.$gov is more efficient and effective than traditional governance methods, thereby enhancing the security, profitability, and ultimately, the sustainability of DeFi protocols.
Authors: Chenyang Qiu, Yingsheng Geng, Junrui Lu, Kaida Chen, Shitong Zhu, Ya Su, Guoshun Nan, Can Zhang, Junsong Fu, Qimei Cui, Xiaofeng Tao
Abstract: Network-based intrusion detection system (NIDS) monitors network traffic for malicious activities, forming the frontline defense against increasing attacks over information infrastructures. Although promising, our quantitative analysis shows that existing methods perform inconsistently in declaring various unknown attacks (e.g., 9% and 35% F1 respectively for two distinct unknown threats for an SVM-based method) or detecting diverse known attacks (e.g., 31% F1 for the Backdoor and 93% F1 for DDoS by a GCN-based state-of-the-art method), and reveals that the underlying cause is entangled distributions of flow features. This motivates us to propose 3D-IDS, a novel method that aims to tackle the above issues through two-step feature disentanglements and a dynamic graph diffusion scheme. Specifically, we first disentangle traffic features by a non-parameterized optimization based on mutual information, automatically differentiating tens and hundreds of complex features of various attacks. Such differentiated features will be fed into a memory model to generate representations, which are further disentangled to highlight the attack-specific features. Finally, we use a novel graph diffusion method that dynamically fuses the network topology for spatial-temporal aggregation in evolving data streams. By doing so, we can effectively identify various attacks in encrypted traffics, including unknown threats and known ones that are not easily detected. Experiments show the superiority of our 3D-IDS. We also demonstrate that our two-step feature disentanglements benefit the explainability of NIDS.
Authors: Peike Li, Boyu Chen, Yao Yao, Yikai Wang, Allen Wang, Alex Wang
Abstract: Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical structures and high sampling rate requirements. Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization. This paper introduces JEN-1, a universal high-fidelity model for text-to-music generation. JEN-1 is a diffusion model incorporating both autoregressive and non-autoregressive training. Through in-context learning, JEN-1 performs various generation tasks including text-guided music generation, music inpainting, and continuation. Evaluations demonstrate JEN-1's superior performance over state-of-the-art methods in text-music alignment and music quality while maintaining computational efficiency. Our demos are available at https://jenmusic.ai/audio-demos
Authors: Prateek Verma
Abstract: With the advent of modern AI architectures, a shift has happened towards end-to-end architectures. This pivot has led to neural architectures being trained without domain-specific biases/knowledge, optimized according to the task. We in this paper, learn audio embeddings via diverse feature representations, in this case, domain-specific. For the case of audio classification over hundreds of categories of sound, we learn robust separate embeddings for diverse audio properties such as pitch, timbre, and neural representation, along with also learning it via an end-to-end architecture. We observe handcrafted embeddings, e.g., pitch and timbre-based, although on their own, are not able to beat a fully end-to-end representation, yet adding these together with end-to-end embedding helps us, significantly improve performance. This work would pave the way to bring some domain expertise with end-to-end models to learn robust, diverse representations, surpassing the performance of just training end-to-end models.
Authors: Jinghuai Yao, Puyuan Du, Yucheng Zhao, Yubo Wang
Abstract: Visible (VIS) imagery is important for monitoring Tropical Cyclones (TCs) but is unavailable at night. This study presents a Conditional Generative Adversarial Networks (CGAN) model to generate nighttime VIS imagery with significantly enhanced accuracy and spatial resolution. Our method offers three key improvements compared to existing models. First, we replaced the L1 loss in the pix2pix framework with the Structural Similarity Index Measure (SSIM) loss, which significantly reduced image blurriness. Second, we selected multispectral infrared (IR) bands as input based on a thorough examination of their spectral properties, providing essential physical information for accurate simulation. Third, we incorporated the direction parameters of the sun and the satellite, which addressed the dependence of VIS images on sunlight directions and enabled a much larger training set from continuous daytime data. The model was trained and validated using data from the Advanced Himawari Imager (AHI) in the daytime, achieving statistical results of SSIM = 0.923 and Root Mean Square Error (RMSE) = 0.0299, which significantly surpasses existing models. We also performed a cross-satellite nighttime model validation using the Day/Night Band (DNB) of the Visible/Infrared Imager Radiometer Suite (VIIRS), which yields outstanding results compared to existing models. Our model is operationally applied to generate accurate VIS imagery with arbitrary virtual sunlight directions, significantly contributing to the nighttime monitoring of various meteorological phenomena.
Authors: Arjun Gupta, Michelle Zhang, Rishik Sathua, Saurabh Gupta
Abstract: What does it take to build mobile manipulation systems that can competently operate on previously unseen objects in previously unseen environments? This work answers this question using opening of articulated structures as a mobile manipulation testbed. Specifically, our focus is on the end-to-end performance on this task without any privileged information, i.e. the robot starts at a location with the novel target articulated object in view, and has to approach the object and successfully open it. We first develop a system for this task, and then conduct 100+ end-to-end system tests across 13 real world test sites. Our large-scale study reveals a number of surprising findings: a) modular systems outperform end-to-end learned systems for this task, even when the end-to-end learned systems are trained on 1000+ demonstrations, b) perception, and not precise end-effector control, is the primary bottleneck to task success, and c) state-of-the-art articulation parameter estimation models developed in isolation struggle when faced with robot-centric viewpoints. Overall, our findings highlight the limitations of developing components of the pipeline in isolation and underscore the need for system-level research, providing a pragmatic roadmap for building generalizable mobile manipulation systems. Videos, code, and models are available on the project website: https://arjung128.github.io/opening-articulated-structures/
URLs: https://arjung128.github.io/opening-articulated-structures/
Authors: Peng Liu, Nian Wang, Cong Xu, Ming Zhao, Bin Wang, Yi Ren
Abstract: Recommender Systems (RSs) provide personalized recommendation service based on user interest, which are widely used in various platforms. However, there are lots of users with sparse interest due to lacking consumption behaviors, which leads to poor recommendation results for them. This problem is widespread in large-scale RSs and is particularly difficult to address. To solve this challenging problem, we propose an innovative solution called User Interest Enhancement (UIE). UIE enhances user interest including user profile and user history behavior sequences by leveraging the enhancement vectors and personalized enhancement vectors generated based on dynamic streaming clustering of similar users and items from multiple perspectives, which are stored and updated in memory networks. UIE not only remarkably improves model performance for users with sparse interest, but also delivers notable gains for other users. As an end-to-end solution, UIE is easy to implement on top of existing ranking models. Furthermore, we extend our approach to long-tail items using similar methods, which also yields excellent improvements. We conduct extensive offline and online experiments in a large-scale industrial RS. The results demonstrate that our model substantially outperforms other existing approaches, especially for users with sparse interest. UIE has been deployed in several large-scale RSs at Tencent since 2022, which was made public on 21 May 2024. In addition, UIE-based methods have also been successfully applied in candidate generation, pre-ranking, and context-DNN stages. Multiple teams have developed solutions based on UIE, focusing primarily on updating clustering algorithms and attention mechanisms. As far as we know, UIE has been deployed by many companies. The thoughts of UIE, dynamic streaming clustering and similarity enhancement, have inspired subsequent relevant works.
Authors: Aaron T. Wang, William Convertino, Xiang Cheng, Ricardo Henao, Lawrence Carin
Abstract: In-context learning based on attention models is examined for data with categorical outcomes, with inference in such models viewed from the perspective of functional gradient descent (GD). We develop a network composed of attention blocks, with each block employing a self-attention layer followed by a cross-attention layer, with associated skip connections. This model can exactly perform multi-step functional GD inference for in-context inference with categorical observations. We perform a theoretical analysis of this setup, generalizing many prior assumptions in this line of work, including the class of attention mechanisms for which it is appropriate. We demonstrate the framework empirically on synthetic data, image classification and language generation.
Authors: Hussein Jawad, Yassine Chenik, Nicolas J. -B. Brunel
Abstract: The rapid adoption of Large Language Models (LLMs) has exposed critical security and ethical vulnerabilities, particularly their susceptibility to adversarial manipulations. This paper introduces QROA, a novel black-box jailbreak method designed to identify adversarial suffixes that can bypass LLM alignment safeguards when appended to a malicious instruction. Unlike existing suffix-based jailbreak approaches, QROA does not require access to the model's logit or any other internal information. It also eliminates reliance on human-crafted templates, operating solely through the standard query-response interface of LLMs. By framing the attack as an optimization bandit problem, QROA employs a surrogate model and token level optimization to efficiently explore suffix variations. Furthermore, we propose QROA-UNV, an extension that identifies universal adversarial suffixes for individual models, enabling one-query jailbreaks across a wide range of instructions. Testing on multiple models demonstrates Attack Success Rate (ASR) greater than 80\%. These findings highlight critical vulnerabilities, emphasize the need for advanced defenses, and contribute to the development of more robust safety evaluations for secure AI deployment. The code is made public on the following link: https://github.com/qroa/QROA
Authors: Johannes M\"uller, Semih Cayci
Abstract: We study the error introduced by entropy regularization in infinite-horizon, discrete, discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength both in a weighted KL-divergence and in value with a problem-specific exponent. This is in contrast to previously known estimates, of the order $O(\tau)$, where $\tau$ is the regularization strength. We provide a lower bound matching our upper bound up to a polynomial term, thereby characterizing the exponential convergence rate for entropy regularization. Our proof relies on the observation that the solutions of entropy-regularized Markov decision processes solve a gradient flow of the unregularized reward with respect to a Riemannian metric common in natural policy gradient methods. This correspondence allows us to identify the limit of this gradient flow as the generalized maximum entropy optimal policy, thereby characterizing the implicit bias of this gradient flow, which corresponds to a time-continuous version of the natural policy gradient method. We use our improved error estimates to show that for entropy-regularized natural policy gradient methods, the overall error decays exponentially in the square root of the number of iterations, improving over existing sublinear guarantees. Finally, we extend our analysis to settings beyond the entropy. In particular, we characterize the implicit bias regarding general convex potentials and their resulting generalized natural policy gradients.
Authors: Zeyue Tian, Zhaoyang Liu, Ruibin Yuan, Jiahao Pan, Qifeng Liu, Xu Tan, Qifeng Chen, Wei Xue, Yike Guo
Abstract: In this work, we systematically study music generation conditioned solely on the video. First, we present a large-scale dataset comprising 360K video-music pairs, including various genres such as movie trailers, advertisements, and documentaries. Furthermore, we propose VidMuse, a simple framework for generating music aligned with video inputs. VidMuse stands out by producing high-fidelity music that is both acoustically and semantically aligned with the video. By incorporating local and global visual cues, VidMuse enables the creation of musically coherent audio tracks that consistently match the video content through Long-Short-Term modeling. Through extensive experiments, VidMuse outperforms existing models in terms of audio quality, diversity, and audio-visual alignment. The code and datasets are available at https://vidmuse.github.io/.
Authors: Ismail Rasim Ulgen, Shreeram Suresh Chandra, Junchen Lu, Berrak Sisman
Abstract: Synthesizing the voices of unseen speakers remains a persisting challenge in multi-speaker text-to-speech (TTS). Existing methods model speaker characteristics through speaker conditioning during training, leading to increased model complexity and limiting reproducibility and accessibility. A lower-complexity method would enable speech synthesis research with limited computational and data resources to reach to a wider use. To this end, we propose SelectTTS, a simple and effective alternative. SelectTTS selects appropriate frames from the target speaker and decodes them using frame-level self-supervised learning (SSL) features. We demonstrate that this approach can effectively capture speaker characteristics for unseen speakers and achieves performance comparable to state-of-the-art multi-speaker TTS frameworks on both objective and subjective metrics. By directly selecting frames from the target speaker's speech, SelectTTS enables generalization to unseen speakers with significantly lower model complexity. Compared to baselines such as XTTS-v2 and VALL-E, SelectTTS achieves better speaker similarity while reducing model parameters by over 8x and training data requirements by 270x.
Authors: Abdul-Lateef Haji-Ali, Marcelo Pereyra, Luke Shaw, Konstantinos Zygalakis
Abstract: Generative diffusion models have recently emerged as a powerful strategy to perform stochastic sampling in Bayesian inverse problems, delivering remarkably accurate solutions for a wide range of challenging applications. However, diffusion models often require a large number of neural function evaluations per sample in order to deliver accurate posterior samples. As a result, using diffusion models as stochastic samplers for Monte Carlo integration in Bayesian computation can be highly computationally expensive, particularly in applications that require a substantial number of Monte Carlo samples for conducting uncertainty quantification analyses. This cost is especially high in large-scale inverse problems such as computational imaging, which rely on large neural networks that are expensive to evaluate. With quantitative imaging applications in mind, this paper presents a Multilevel Monte Carlo strategy that significantly reduces the cost of Bayesian computation with diffusion models. This is achieved by exploiting cost-accuracy trade-offs inherent to diffusion models to carefully couple models of different levels of accuracy in a manner that significantly reduces the overall cost of the calculation, without reducing the final accuracy. The proposed approach achieves a $4\times$-to-$8\times$ reduction in computational cost w.r.t. standard techniques across three benchmark imaging problems.
Authors: Grace Luo, Trevor Darrell, Amir Bar
Abstract: Autoregressive vision-language models (VLMs) can handle many tasks within a single model, yet the representations that enable this capability remain opaque. We find that VLMs align conceptually equivalent inputs into a shared task vector, which is invariant to modality (text, image) and format (examples, instruction), and may simplify VLM processing. We measure this alignment via cross-modal transfer -- the ability of a task vector derived in one modality to trigger the correct generation in another -- on a range of tasks and model architectures. Although the task vector is highly compressed, we find that this single vector outperforms prompting the model with the full task information, unique to this cross-modal case. Furthermore, we show that task vectors can be transferred from a base language model to its fine-tuned vision-language counterpart, and that they can be derived solely from instructions without the need for examples. Taken together, our findings shed light on how VLMs internally process task information, and how they map different modalities into common semantic representations. Project page: https://vlm-cross-modal-reps.github.io.
Authors: Keiya Hirashima, Kana Moriwaki, Michiko S. Fujii, Yutaka Hirai, Takayuki R. Saitoh, Junnichiro Makino, Ulrich P. Steinwandel, Shirley Ho
Abstract: We introduce new high-resolution galaxy simulations accelerated by a surrogate model that reduces the computation cost by approximately 75 percent. Massive stars with a Zero Age Main Sequence mass of more than about 10 $\mathrm{M_\odot}$ explode as core-collapse supernovae (CCSNe), which play a critical role in galaxy formation. The energy released by CCSNe is essential for regulating star formation and driving feedback processes in the interstellar medium (ISM). However, the short integration timesteps required for SNe feedback have presented significant bottlenecks in astrophysical simulations across various scales. Overcoming this challenge is crucial for enabling star-by-star galaxy simulations, which aim to capture the dynamics of individual stars and the inhomogeneous shell's expansion within the turbulent ISM. To address this, our new framework combines direct numerical simulations and surrogate modeling, including machine learning and Gibbs sampling. The star formation history and the time evolution of outflow rates in the galaxy match those obtained from resolved direct numerical simulations. Our new approach achieves high-resolution fidelity while reducing computational costs, effectively bridging the physical scale gap and enabling multi-scale simulations.
Authors: Yingying Fang, Zihao Jin, Shaojie Guo, Jinda Liu, Zhiling Yue, Yijian Gao, Junzhi Ning, Zhi Li, Simon Walsh, Guang Yang
Abstract: Despite significant advancements in automated report generation, the opaqueness of text interpretability continues to cast doubt on the reliability of the content produced. This paper introduces a novel approach to identify specific image features in X-ray images that influence the outputs of report generation models. Specifically, we propose Cyclic Vision-Language Manipulator CVLM, a module to generate a manipulated X-ray from an original X-ray and its report from a designated report generator. The essence of CVLM is that cycling manipulated X-rays to the report generator produces altered reports aligned with the alterations pre-injected into the reports for X-ray generation, achieving the term "cyclic manipulation". This process allows direct comparison between original and manipulated X-rays, clarifying the critical image features driving changes in reports and enabling model users to assess the reliability of the generated texts. Empirical evaluations demonstrate that CVLM can identify more precise and reliable features compared to existing explanation methods, significantly enhancing the transparency and applicability of AI-generated reports.
Authors: Manuel Hagel\"uken, Marco F. Huber, Marco Roth
Abstract: Understanding the properties of excited states of complex molecules is crucial for many chemical and physical processes. Calculating these properties is often significantly more resource-intensive than calculating their ground state counterparts. We present a quantum machine learning model that predicts excited-state properties from the molecular ground state for different geometric configurations. The model comprises a symmetry-invariant quantum neural network and a conventional neural network and is able to provide accurate predictions with only a few training data points. The proposed procedure is fully NISQ compatible. This is achieved by using a quantum circuit that requires a number of parameters linearly proportional to the number of molecular orbitals, along with a parameterized measurement observable, thereby reducing the number of necessary measurements. We benchmark the algorithm on three different molecules with three different system sizes: $H_2$ with four orbitals, LiH with five orbitals, and $H_4$ with six orbitals. For these molecules, we predict the excited state transition energies and transition dipole moments. We show that, in many cases, the procedure is able to outperform various classical models (support vector machines, Gaussian processes, and neural networks) that rely solely on classical features, by up to two orders of magnitude in the test mean squared error.
Authors: Kelly Ramsay, Dylan Spicker
Abstract: We develop a univariate, differentially private mean estimator, called the private modified winsorized mean, designed to be used as the aggregator in subsample-and-aggregate. We demonstrate, via real data analysis, that common differentially private multivariate mean estimators may not perform well as the aggregator, even in large datasets, motivating our developments.We show that the modified winsorized mean is minimax optimal for several, large classes of distributions, even under adversarial contamination. We also demonstrate that, empirically, the private modified winsorized mean performs well compared to other private mean estimates. We consider the modified winsorized mean as the aggregator in subsample-and-aggregate, deriving a finite sample deviations bound for a subsample-and-aggregate estimate generated with the new aggregator. This result yields two important insights: (i) the optimal choice of subsamples depends on the bias of the estimator computed on the subsamples, and (ii) the rate of convergence of the subsample-and-aggregate estimator depends on the robustness of the estimator computed on the subsamples.
Authors: Yingchao Yu, Yaochu Jin, Kuangrong Hao, Yuchen Xiao, Yuping Yan, Hengjie Yu
Abstract: The emergence of abstract rules from exemplars is a cornerstone of genuine intelligence in both biological and artificial systems. However, the internal organizational principles underlying different abstract rules remain poorly understood. We propose a hierarchically modulated recurrent spiking neural network (HM-RSNN), inspired by astrocyte signaling. The model globally configures and locally fine-tunes intrinsic neuronal properties via a two-stage neuromodulatory mechanism. This design enhances neuronal adaptability and diversity, thus enabling fine-grained analysis of internal organizational principles. We evaluate abstract rule emergence across four cognitive task sets. To probe internal organization, we examine network-level connectivity via structural modularity analysis and neuron-level functional biases via bin-wise lesion studies based on intrinsic properties. Our experiments show that HM-RSNN successfully achieves abstract rule emergence, with rule-contingent organizational principles evident at both network and neuron levels. These findings highlight the critical role of dynamic internal organization in supporting flexible cognition.
Authors: Wang Xinyi, Kang Hongyu, Wei Peishan, Shuai Li, Yu Sun, Sai Kit Lam, Yongping Zheng
Abstract: In this paper, we aim to address the unmet demand for automated prompting and enhanced human-model interactions of SAM and SAM2 for the sake of promoting their widespread clinical adoption. Specifically, we propose Proxy Prompt (PP), auto-generated by leveraging non-target data with a pre-annotated mask. We devise a novel 3-step context-selection strategy for adaptively selecting the most representative contextual information from non-target data via vision mamba and selective maps, empowering the guiding capability of non-target image-mask pairs for segmentation on target image/video data. To reinforce human-model interactions in PP, we further propose a contextual colorization module via a dual-reverse cross-attention to enhance interactions between target features and contextual-embedding with amplifying distinctive features of user-defined object(s). Via extensive evaluations, our method achieves state-of-the-art performance on four public datasets and yields comparable results with fully-trained models, even when trained with only 16 image masks.
Authors: Chenchen Shou, Guyue Liu, Hao Nie, Huaiyu Meng, Yu Zhou, Yimin Jiang, Wenqing Lv, Yelong Xu, Yuanwei Lu, Zhang Chen, Yanbo Yu, Yichen Shen, Yibo Zhu, Daxin Jiang
Abstract: Scaling Large Language Model (LLM) training relies on multi-dimensional parallelism, where High-Bandwidth Domains (HBDs) are critical for communication-intensive parallelism like Tensor Parallelism (TP) and Expert Parallelism (EP). However, existing HBD architectures face fundamental limitations in scalability, cost, and fault resiliency: switch-centric HBDs (e.g., NVL-72) incur prohibitive scaling costs, while GPU-centric HBDs (e.g., TPUv3/Dojo) suffer from severe fault propagation. Switch-GPU hybrid HBDs such as TPUv4 takes a middle-ground approach by leveraging Optical Circuit Switches, but the fault explosion radius remains large at the cube level (e.g., 64 TPUs). We propose InfiniteHBD, a novel transceiver-centric HBD architecture that unifies connectivity and dynamic switching at the transceiver level using Optical Circuit Switching (OCS). By embedding OCS within each transceiver, InfiniteHBD achieves reconfigurable point-to-multipoint connectivity, allowing the topology to adapt into variable-size rings. This design provides: i) datacenter-wide scalability without cost explosion; ii) fault resilience by isolating failures to a single node, and iii) full bandwidth utilization for fault-free GPUs. Key innovations include a Silicon Photonic (SiPh) based low-cost OCS transceiver (OCSTrx), a reconfigurable k-hop ring topology co-designed with intra-/inter-node communication, and an HBD-DCN orchestration algorithm maximizing GPU utilization while minimizing cross-ToR datacenter network traffic. The evaluation demonstrates that InfiniteHBD achieves 31% of the cost of NVL-72, near-zero GPU waste ratio (over one order of magnitude lower than NVL-72 and TPUv4), near-zero cross-ToR traffic when node fault ratios under 7%, and improves Model FLOPs Utilization by 3.37x compared to NVIDIA DGX (8 GPUs per Node).
Authors: Zhiyuan Fang, Zicong Hong, Yuegui Huang, Yufeng Lyu, Wuhui Chen, Yue Yu, Fan Yu, Zibin Zheng
Abstract: Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are well suited for edge scenarios, have received relatively little attention due to their high memory demands. Offload-based methods have been proposed to address this challenge, but they face difficulties with expert prediction. Inaccurate expert predictions can result in prolonged inference delays. To promote the application of MoE models in edge scenarios, we propose Fate, an offloading system designed for MoE models to enable efficient inference in resource-constrained environments. The key insight behind Fate is that gate inputs from adjacent layers can be effectively used for expert prefetching, achieving high prediction accuracy without additional GPU overhead. Furthermore, Fate employs a shallow-favoring expert caching strategy that increases the expert hit rate to 99\%. Additionally, Fate integrates tailored quantization strategies for cache optimization and IO efficiency. Experimental results show that, compared to Load on Demand and Expert Activation Path-based method, Fate achieves up to 4.5x and 1.9x speedups in prefill speed and up to 4.1x and 2.2x speedups in decoding speed, respectively, while maintaining inference quality. Moreover, Fate's performance improvements are scalable across different memory budgets.
Authors: Disen Lan, Weigao Sun, Jiaxi Hu, Jusen Du, Yu Cheng
Abstract: Transformers with linear recurrent modeling offer linear-time training and constant-memory inference. Despite their demonstrated efficiency and performance, pretraining such non-standard architectures from scratch remains costly and risky. The linearization of large language models (LLMs) transforms pretrained standard models into linear recurrent structures, enabling more efficient deployment. However, current linearization methods typically introduce additional feature map modules that require extensive fine-tuning and overlook the gating mechanisms used in state-of-the-art linear recurrent models. To address these issues, this paper presents Liger, short for Linearizing LLMs to gated recurrent structures. Liger is a novel approach for converting pretrained LLMs into gated linear recurrent models without adding extra parameters. It repurposes the pretrained key matrix weights to construct diverse gating mechanisms, facilitating the formation of various gated recurrent structures while avoiding the need to train additional components from scratch. Using lightweight fine-tuning with Low-Rank Adaptation (LoRA), Liger restores the performance of the linearized gated recurrent models to match that of the original LLMs. Additionally, we introduce Liger Attention, an intra-layer hybrid attention mechanism, which significantly recovers 93\% of the Transformer-based LLM at 0.02\% pre-training tokens during the linearization process, achieving competitive results across multiple benchmarks, as validated on models ranging from 1B to 8B parameters. Code is available at https://github.com/OpenSparseLLMs/Linearization.
Authors: Zijun Jia, Jinsong Yu, Hongyu Long, Diyin Tang
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: Roman Abramov, Felix Steinbauer, Gjergji Kasneci
Abstract: Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural networks can transition from memorizing to perfectly generalizing once they detect underlying logical patterns - yet these studies have primarily used small, synthetic tasks. In this paper, for the first time, we extend grokking to real-world factual data and address the challenge of dataset sparsity by augmenting existing knowledge graphs with carefully designed synthetic data to raise the ratio $\phi_r$ of inferred facts to atomic facts above the threshold required for grokking. Surprisingly, we find that even factually incorrect synthetic data can strengthen emergent reasoning circuits rather than degrade accuracy, as it forces the model to rely on relational structure rather than memorization. When evaluated on multi-hop reasoning benchmarks, our approach achieves up to 95-100% accuracy on 2WikiMultiHopQA - substantially improving over strong baselines and matching or exceeding current state-of-the-art results. We further provide an in-depth analysis of how increasing $\phi_r$ drives the formation of generalizing circuits inside Transformers. Our findings suggest that grokking-based data augmentation can unlock implicit multi-hop reasoning capabilities, opening the door to more robust and interpretable factual reasoning in large-scale language models.
Authors: Evan Li, Tushin Mallick, Evan Rose, William Robertson, Alina Oprea, Cristina Nita-Rotaru
Abstract: LLM-integrated app systems extend the utility of Large Language Models (LLMs) with third-party apps that are invoked by a system LLM using interleaved planning and execution phases to answer user queries. These systems introduce new attack vectors where malicious apps can cause integrity violation of planning or execution, availability breakdown, or privacy compromise during execution. In this work, we identify new attacks impacting the integrity of planning, as well as the integrity and availability of execution in LLM-integrated apps, and demonstrate them against IsolateGPT, a recent solution designed to mitigate attacks from malicious apps. We propose Abstract-Concrete-Execute (ACE), a new secure architecture for LLM-integrated app systems that provides security guarantees for system planning and execution. Specifically, ACE decouples planning into two phases by first creating an abstract execution plan using only trusted information, and then mapping the abstract plan to a concrete plan using installed system apps. We verify that the plans generated by our system satisfy user-specified secure information flow constraints via static analysis on the structured plan output. During execution, ACE enforces data and capability barriers between apps, and ensures that the execution is conducted according to the trusted abstract plan. We show experimentally that our system is secure against attacks from the INJECAGENT benchmark, a standard benchmark for control flow integrity in the face of indirect prompt injection attacks, and our newly introduced attacks. Our architecture represents a significant advancement towards hardening LLM-based systems containing system facilities of varying levels of trustworthiness.
Authors: Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan, Cody Wild, Diane Wan, Alex Ku, J\"org Bornschein, Razvan Pascanu, Murray Shanahan, James L. McClelland
Abstract: Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical deductions based on trained information. These failures to generalize from fine-tuning can hinder practical application of these models. On the other hand, language models' in-context learning shows different inductive biases, and can generalize better in some cases. Here, we explore these differences in generalization between in-context- and fine-tuning-based learning. To do so, we constructed several novel datasets to evaluate and improve models' abilities to generalize from finetuning data. The datasets are designed to create clean tests of generalization, by isolating the knowledge in the dataset from that in pretraining. We expose pretrained large models to controlled subsets of the information in these datasets -- either in context, or through fine-tuning -- and evaluate their performance on test sets that require various types of generalization. We find overall that in data-matched settings, in-context learning can generalize more flexibly than fine-tuning (though we also find some qualifications of prior findings, such as cases when fine-tuning can generalize to reversals embedded in a larger structure of knowledge). We build on these findings to propose a method to enable improved generalization from fine-tuning: adding in-context inferences to finetuning data. We show that this method improves generalization across various splits of our datasets and other benchmarks. Our results have implications for understanding the inductive biases of different modes of learning in language models, and practically improving their performance.
Authors: Chutiphan Charoensuk, Nathakhun Wiroonsri
Abstract: Time series clustering is an unsupervised learning method for classifying time series data into groups with similar behavior. It is used in applications such as healthcare, finance, economics, energy, and climate science. Several time series clustering methods have been introduced and used for over four decades. Most of them focus on measuring either Euclidean distances or association dissimilarities between time series. In this work, we propose a new dissimilarity measure called ranked Pearson correlation dissimilarity (RDPC), which combines a weighted average of a specified fraction of the largest element-wise differences with the well-known Pearson correlation dissimilarity. It is incorporated into hierarchical clustering. The performance is evaluated and compared with existing clustering algorithms. The results show that the RDPC algorithm outperforms others in complicated cases involving different seasonal patterns, trends, and peaks. Finally, we demonstrate our method by clustering a random sample of customers from a Thai electricity consumption time series dataset into seven groups with unique characteristics.
Authors: Tianyu Zong, Hongzhu Yi, Bingkang Shi, Yuanxiang Wang, Jungang Xu
Abstract: Unsupervised contrastive learning has become a hot research topic in natural language processing. Existing works usually aim at constraining the orientation distribution of the representations of positive and negative samples in the high-dimensional semantic space in contrastive learning, but the semantic representation tensor possesses both modulus and orientation features, and the existing works ignore the modulus feature of the representations and cause insufficient contrastive learning. % Therefore, we firstly propose a training objective that aims at modulus constraints on the semantic representation tensor, to strengthen the alignment between the positive samples in contrastive learning. Therefore, we first propose a training objective that is designed to impose modulus constraints on the semantic representation tensor, to strengthen the alignment between positive samples in contrastive learning. Then, the BERT-like model suffers from the phenomenon of sinking attention, leading to a lack of attention to CLS tokens that aggregate semantic information. In response, we propose a cross-attention structure among the twin-tower ensemble models to enhance the model's attention to CLS token and optimize the quality of CLS Pooling. Combining the above two motivations, we propose a new \textbf{J}oint \textbf{T}ensor representation modulus constraint and \textbf{C}ross-attention unsupervised contrastive learning \textbf{S}entence \textbf{E}mbedding representation framework JTCSE, which we evaluate in seven semantic text similarity computation tasks, and the experimental results show that JTCSE's twin-tower ensemble model and single-tower distillation model outperform the other baselines and become the current SOTA. In addition, we have conducted an extensive zero-shot downstream task evaluation, which shows that JTCSE outperforms other baselines overall on more than 130 tasks.
Authors: 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: Bernardo Marenco, Paola Bermolen, Marcelo Fiori, Federico Larroca, Gonzalo Mateos
Abstract: Modeling of intricate relational patterns 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: 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.