Authors: Ziyi Cao, Qingyi Si, Jingbin Zhang, Bingquan Liu
Abstract: Large language models face significant cost challenges in long-sequence inference. To address this, reusing historical Key-Value (KV) Cache for improved inference efficiency has become a mainstream approach. Recent advances further enhance throughput by sparse attention mechanisms to select the most relevant KV Cache, thereby reducing sequence length. However, such techniques are limited to single-context scenarios, where historical KV Cache is computed sequentially with causal-attention dependencies. In retrieval-augmented generation (RAG) scenarios, where retrieved documents as context are unknown beforehand, each document's KV Cache is computed and stored independently (termed multiple-context KV Cache), lacking cross-attention between contexts. This renders existing methods ineffective. Although prior work partially recomputes multiple-context KV Cache to mitigate accuracy loss from missing cross-attention, it requires retaining all KV Cache throughout, failing to reduce memory overhead. This paper presents SamKV, the first exploration of attention sparsification for multiple-context KV Cache. Specifically, SamKV takes into account the complementary information of other contexts when sparsifying one context, and then locally recomputes the sparsified information. Experiments demonstrate that our method compresses sequence length to 15% without accuracy degradation compared with full-recompuation baselines, significantly boosting throughput in multi-context RAG scenarios.
Authors: Bryan E. Tuck, Rakesh M. Verma
Abstract: Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining. We introduce Representation Stability (RS), a model-agnostic detection framework that identifies adversarial examples by measuring how embedding representations change when important words are masked. RS first ranks words using importance heuristics, then measures embedding sensitivity to masking top-k critical words, and processes the resulting patterns with a BiLSTM detector. Experiments show that adversarially perturbed words exhibit disproportionately high masking sensitivity compared to naturally important words. Across three datasets, three attack types, and two victim models, RS achieves over 88% detection accuracy and demonstrates competitive performance compared to existing state-of-the-art methods, often at lower computational cost. Using Normalized Discounted Cumulative Gain (NDCG) to measure perturbation identification quality, we reveal that gradient-based ranking outperforms attention and random selection approaches, with identification quality correlating with detection performance for word-level attacks. RS also generalizes well to unseen datasets, attacks, and models without retraining, providing a practical solution for adversarial text detection.
Authors: Wentao Li, Yonghu He, Kun Gao, Qing Liu, Yali Zheng
Abstract: Noninvasive arterial blood pressure (ABP) monitoring is essential for patient management in critical care and perioperative settings, providing continuous assessment of cardiovascular hemodynamics with minimal risks. Numerous deep learning models have developed to reconstruct ABP waveform from noninvasively acquired physiological signals such as electrocardiogram and photoplethysmogram. However, limited research has addressed the issue of model performance and computational load for deployment on embedded systems. The study introduces a lightweight sInvResUNet, along with a collaborative learning scheme named KDCL_sInvResUNet. With only 0.89 million parameters and a computational load of 0.02 GFLOPS, real-time ABP estimation was successfully achieved on embedded devices with an inference time of just 8.49 milliseconds for a 10-second output. We performed subject-independent validation in a large-scale and heterogeneous perioperative dataset containing 1,257,141 data segments from 2,154 patients, with a wide BP range (41-257 mmHg for SBP, and 31-234 mmHg for DBP). The proposed KDCL_sInvResUNet achieved lightly better performance compared to large models, with a mean absolute error of 10.06 mmHg and mean Pearson correlation of 0.88 in tracking ABP changes. Despite these promising results, all deep learning models showed significant performance variations across different demographic and cardiovascular conditions, highlighting their limited ability to generalize across such a broad and diverse population. This study lays a foundation work for real-time, unobtrusive ABP monitoring in real-world perioperative settings, providing baseline for future advancements in this area.
Authors: Haojie Zhang, Yixiong Liang, Hulin Kuang, Lihui Cen, Zhe Qu, Yigang Cen, Min Zeng, Shichao Kan
Abstract: Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs. Existing incremental learning methods focus on task expansion within a single modality, whereas MBIIL seeks to train a unified model incrementally across modalities. The MBIIL faces two challenges: I) How to preserve previously learned knowledge during incremental updates? II) How to effectively leverage knowledge acquired from existing modalities to support new modalities? To address these challenges, we propose MSLoRA-CR, a method that fine-tunes Modality-Specific LoRA modules while incorporating Contrastive Regularization to enhance intra-modality knowledge sharing and promote inter-modality knowledge differentiation. Our approach builds upon a large vision-language model (LVLM), keeping the pretrained model frozen while incrementally adapting new LoRA modules for each modality or task. Experiments on the incremental learning of biomedical images demonstrate that MSLoRA-CR outperforms both the state-of-the-art (SOTA) approach of training separate models for each modality and the general incremental learning method (incrementally fine-tuning LoRA). Specifically, MSLoRA-CR achieves a 1.88% improvement in overall performance compared to unconstrained incremental learning methods while maintaining computational efficiency. Our code is publicly available at https://github.com/VentusAislant/MSLoRA_CR.
Authors: Shaodi Feng, Zhuoyi Lin, Jianan Zhou, Cong Zhang, Jingwen Li, Kuan-Wen Chen, Senthilnath Jayavelu, Yew-Soon Ong
Abstract: Deep learning has been extensively explored to solve vehicle routing problems (VRPs), which yields a range of data-driven neural solvers with promising outcomes. However, most neural solvers are trained to tackle VRP instances in a relatively monotonous context, e.g., simplifying VRPs by using Euclidean distance between nodes and adhering to a single problem size, which harms their off-the-shelf application in different scenarios. To enhance their versatility, this paper presents a novel lifelong learning framework that incrementally trains a neural solver to manage VRPs in distinct contexts. Specifically, we propose a lifelong learner (LL), exploiting a Transformer network as the backbone, to solve a series of VRPs. The inter-context self-attention mechanism is proposed within LL to transfer the knowledge obtained from solving preceding VRPs into the succeeding ones. On top of that, we develop a dynamic context scheduler (DCS), employing the cross-context experience replay to further facilitate LL looking back on the attained policies of solving preceding VRPs. Extensive results on synthetic and benchmark instances (problem sizes up to 18k) show that our LL is capable of discovering effective policies for tackling generic VRPs in varying contexts, which outperforms other neural solvers and achieves the best performance for most VRPs.
Authors: Aditya Akella, Jonathan Farah
Abstract: Demographic shifts, influenced by globalization, economic conditions, geopolitical events, and environmental factors, pose significant challenges for policymakers and researchers. Accurate demographic forecasting is essential for informed decision-making in areas such as urban planning, healthcare, and economic policy. This study explores the application of time series foundation models to predict demographic changes in the United States using datasets from the U.S. Census Bureau and Federal Reserve Economic Data (FRED). We evaluate the performance of the Time Series Foundation Model (TimesFM) against traditional baselines including Long Short-Term Memory (LSTM) networks, Autoregressive Integrated Moving Average (ARIMA), and Linear Regression. Our experiments across six demographically diverse states demonstrate that TimesFM achieves the lowest Mean Squared Error (MSE) in 86.67% of test cases, with particularly strong performance on minority populations with sparse historical data. These findings highlight the potential of pre-trained foundation models to enhance demographic analysis and inform proactive policy interventions without requiring extensive task-specific fine-tuning.
Authors: Qian Cao, Jielin Chen, Junchao Zhao, Rudi Stouffs
Abstract: The spatial layout of urban sites shapes land-use efficiency and spatial organization. Traditional site planning often relies on experiential judgment and single-source data, limiting systematic quantification of multifunctional layouts. We propose a Site Planning Layout Indicator (SPLI) system, a data-driven framework integrating empirical knowledge with heterogeneous multi-source data to produce structured urban spatial information. The SPLI supports multimodal spatial data systems for analytics, inference, and retrieval by combining OpenStreetMap (OSM), Points of Interest (POI), building morphology, land use, and satellite imagery. It extends conventional metrics through five dimensions: (1) Hierarchical Building Function Classification, refining empirical systems into clear hierarchies; (2) Spatial Organization, quantifying seven layout patterns (e.g., symmetrical, concentric, axial-oriented); (3) Functional Diversity, transforming qualitative assessments into measurable indicators using Functional Ratio (FR) and Simpson Index (SI); (4) Accessibility to Essential Services, integrating facility distribution and transport networks for comprehensive accessibility metrics; and (5) Land Use Intensity, using Floor Area Ratio (FAR) and Building Coverage Ratio (BCR) to assess utilization efficiency. Data gaps are addressed through deep learning, including Relational Graph Neural Networks (RGNN) and Graph Neural Networks (GNN). Experiments show the SPLI improves functional classification accuracy and provides a standardized basis for automated, data-driven urban spatial analytics.
Authors: Songyao Jin, Biwei Huang
Abstract: Multivariate Hawkes process provides a powerful framework for modeling temporal dependencies and event-driven interactions in complex systems. While existing methods primarily focus on uncovering causal structures among observed subprocesses, real-world systems are often only partially observed, with latent subprocesses posing significant challenges. In this paper, we show that continuous-time event sequences can be represented by a discrete-time model as the time interval shrinks, and we leverage this insight to establish necessary and sufficient conditions for identifying latent subprocesses and the causal influences. Accordingly, we propose a two-phase iterative algorithm that alternates between inferring causal relationships among discovered subprocesses and uncovering new latent subprocesses, guided by path-based conditions that guarantee identifiability. Experiments on both synthetic and real-world datasets show that our method effectively recovers causal structures despite the presence of latent subprocesses.
Authors: Xiangxiang Cui, Min Zhao, Dongmei Zhi, Shile Qi, Vince D Calhoun, Jing Sui
Abstract: Existing deep learning models for functional MRI-based classification have limitations in network architecture determination (relying on experience) and feature space fusion (mostly simple concatenation, lacking mutual learning). Inspired by the human brain's mechanism of updating neural connections through learning and decision-making, we proposed a novel BRain-Inspired feature Fusion (BRIEF) framework, which is able to optimize network architecture automatically by incorporating an improved neural network connection search (NCS) strategy and a Transformer-based multi-feature fusion module. Specifically, we first extracted 4 types of fMRI temporal representations, i.e., time series (TCs), static/dynamic functional connection (FNC/dFNC), and multi-scale dispersion entropy (MsDE), to construct four encoders. Within each encoder, we employed a modified Q-learning to dynamically optimize the NCS to extract high-level feature vectors, where the NCS is formulated as a Markov Decision Process. Then, all feature vectors were fused via a Transformer, leveraging both stable/time-varying connections and multi-scale dependencies across different brain regions to achieve the final classification. Additionally, an attention module was embedded to improve interpretability. The classification performance of our proposed BRIEF was compared with 21 state-of-the-art models by discriminating two mental disorders from healthy controls: schizophrenia (SZ, n=1100) and autism spectrum disorder (ASD, n=1550). BRIEF demonstrated significant improvements of 2.2% to 12.1% compared to 21 algorithms, reaching an AUC of 91.5% - 0.6% for SZ and 78.4% - 0.5% for ASD, respectively. This is the first attempt to incorporate a brain-inspired, reinforcement learning strategy to optimize fMRI-based mental disorder classification, showing significant potential for identifying precise neuroimaging biomarkers.
Authors: Luc Houriez (X the Moonshot Factory - Bellwether, Stanford University), Sebastian Pilarski (X the Moonshot Factory - Bellwether), Behzad Vahedi (X the Moonshot Factory - Bellwether), Ali Ahmadalipour (X the Moonshot Factory - Bellwether), Teo Honda Scully (X the Moonshot Factory - Bellwether), Nicholas Aflitto (X the Moonshot Factory - Bellwether), David Andre (X the Moonshot Factory - Bellwether), Caroline Jaffe (X the Moonshot Factory - Bellwether), Martha Wedner (X the Moonshot Factory - Bellwether), Rich Mazzola (X the Moonshot Factory - Bellwether), Josh Jeffery (X the Moonshot Factory - Bellwether), Ben Messinger (X the Moonshot Factory - Bellwether), Sage McGinley-Smith (X the Moonshot Factory - Bellwether), Sarah Russell (X the Moonshot Factory - Bellwether)
Abstract: High-quality labeled geospatial datasets are essential for extracting insights and understanding our planet. Unfortunately, these datasets often do not span the entire globe and are limited to certain geographic regions where data was collected. Google DeepMind's recently released AlphaEarth Foundations (AEF) provides an information-dense global geospatial representation designed to serve as a useful input across a wide gamut of tasks. In this article we propose and evaluate a methodology which leverages AEF to extend geospatial labeled datasets beyond their initial geographic regions. We show that even basic models like random forests or logistic regression can be used to accomplish this task. We investigate a case study of extending LANDFIRE's Existing Vegetation Type (EVT) dataset beyond the USA into Canada at two levels of granularity: EvtPhys (13 classes) and EvtGp (80 classes). Qualitatively, for EvtPhys, model predictions align with ground truth. Trained models achieve 81% and 73% classification accuracy on EvtPhys validation sets in the USA and Canada, despite discussed limitations.
Authors: Hemanth Macharla, Mayukha Pal
Abstract: Real-time fault classification in resource-constrained Internet of Things (IoT) devices is critical for industrial safety, yet training robust models in such heterogeneous environments remains a significant challenge. Standard Federated Learning (FL) often fails in the presence of non-IID data, leading to model divergence. This paper introduces Fed-Meta-Align, a novel four-phase framework designed to overcome these limitations through a sophisticated initialization and training pipeline. Our process begins by training a foundational model on a general public dataset to establish a competent starting point. This model then undergoes a serial meta-initialization phase, where it sequentially trains on a subset of IOT Device data to learn a heterogeneity-aware initialization that is already situated in a favorable region of the loss landscape. This informed model is subsequently refined in a parallel FL phase, which utilizes a dual-criterion aggregation mechanism that weights for IOT devices updates based on both local performance and cosine similarity alignment. Finally, an on-device personalization phase adapts the converged global model into a specialized expert for each IOT Device. Comprehensive experiments demonstrate that Fed-Meta-Align achieves an average test accuracy of 91.27% across heterogeneous IOT devices, outperforming personalized FedAvg and FedProx by up to 3.87% and 3.37% on electrical and mechanical fault datasets, respectively. This multi-stage approach of sequenced initialization and adaptive aggregation provides a robust pathway for deploying high-performance intelligence on diverse TinyML networks.
Authors: Michael Bereket, Jure Leskovec
Abstract: Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing language models in verifiable domains with stochastic outcomes, like scientific experiments. Through applications to synthetic data and real-world biological experiments, we demonstrate that Group Relative Policy Optimization (GRPO) induces overconfident probability predictions for binary stochastic outcomes, while Proximal Policy Optimization (PPO) and REINFORCE Leave-One-Out (RLOO) yield well-calibrated models. We show that removing group standard normalization in GRPO fixes its miscalibration and provide a theoretical explanation for why normalization causes overconfidence. Our results provide new evidence against the use of standard normalization in GRPO and help pave the way for applications of RL for reasoning language models beyond deterministic domains.
Authors: Nitish Nagesh, Salar Shakibhamedan, Mahdi Bagheri, Ziyu Wang, Nima TaheriNejad, Axel Jantsch, Amir M. Rahmani
Abstract: Generating synthetic data is crucial in privacy-sensitive, data-scarce settings, especially for tabular datasets widely used in real-world applications. A key challenge is improving counterfactual and causal fairness, while preserving high utility. We present FairTabGen, a fairness-aware large language model-based framework for tabular synthetic data generation. We integrate multiple fairness definitions including counterfactual and causal fairness into both its generation and evaluation pipelines. We use in-context learning, prompt refinement, and fairness-aware data curation to balance fairness and utility. Across diverse datasets, our method outperforms state-of-the-art GAN-based and LLM-based methods, achieving up to 10% improvements on fairness metrics such as demographic parity and path-specific causal effects while retaining statistical utility. Remarkably, it achieves these gains using less than 20% of the original data, highlighting its efficiency in low-data regimes. These results demonstrate a principled and practical approach for generating fair and useful synthetic tabular data.
Authors: Hoang-Thang Ta, Duy-Quy Thai, Phuong-Linh Tran-Thi
Abstract: For years, many neural networks have been developed based on the Kolmogorov-Arnold Representation Theorem (KART), which was created to address Hilbert's 13th problem. Recently, relying on KART, Kolmogorov-Arnold Networks (KANs) have attracted attention from the research community, stimulating the use of polynomial functions such as B-splines and RBFs. However, these functions are not fully supported by GPU devices and are still considered less popular. In this paper, we propose the use of fast computational functions, such as ReLU and trigonometric functions (e.g., ReLU, sin, cos, arctan), as basis components in Kolmogorov-Arnold Networks (KANs). By integrating these function combinations into the network structure, we aim to enhance computational efficiency. Experimental results show that these combinations maintain competitive performance while offering potential improvements in training time and generalization.
Authors: Yuto Omae
Abstract: Convolutional Neural Networks (CNNs) are an effective approach for classification tasks, particularly when the training dataset is large. Although CNNs have long been considered a black-box classification method, they can be used as a white-box method through visualization techniques such as Grad-CAM. When training samples are limited, incorporating a Principal Component Analysis (PCA) layer and/or a Support Vector Machine (SVM) classifier into a CNN can effectively improve classification performance. However, traditional Grad-CAM cannot be directly applied to PCA and/or SVM layers. It is important to generate attention regions for PCA and/or SVM layers in CNNs to facilitate the development of white-box methods. Therefore, we propose ``PCA-Grad-CAM'', a method for visualizing attention regions in PCA feature vectors, and ``SVM-Grad-CAM'', a method for visualizing attention regions in an SVM classifier layer. To complete our methods analytically, it is necessary to solve the closed-form Jacobian consisting of partial derivatives from the last convolutional layer to the PCA and/or SVM layers. In this paper, we present the exact closed-form Jacobian and the visualization results of our methods applied to several major datasets.
Authors: Yibo Zhong
Abstract: Efficient modeling of long sequences of high-order data requires a more efficient architecture than Transformer. In this paper, we investigate two key aspects of extending linear recurrent models, especially those originally designed for language modeling, to high-order data (1D to ND): scanning strategies and attention-hybrid architectures. Empirical results suggest that scanning provides limited benefits, while attention-hybrid models yield promising results. Focusing on the latter, we further evaluate types of attention and find that tiled high-order sliding window attention (SWA) is efficient in both theory and practice. We term the resulting hybrid architecture of linear recurrence and high-order SWA as Efficient N-dimensional Attention (ENA). We then conduct several experiments to demonstrate its effectiveness. The intuition behind ENA is that linear recurrence compresses global information into a state, while SWA complements it by enforcing strict local modeling. Together, they form a simple framework that offers a promising and practical solution for ultra-long high-order data modeling.
Authors: Yan Wu, Lihong Pei, Yukai Han, Yang Cao, Yu Kang, Yanlong Zhao
Abstract: Long-term traffic emission forecasting is crucial for the comprehensive management of urban air pollution. Traditional forecasting methods typically construct spatiotemporal graph models by mining spatiotemporal dependencies to predict emissions. However, due to the multi-scale entanglement of traffic emissions across time and space, these spatiotemporal graph modeling method tend to suffer from cascading error amplification during long-term inference. To address this issue, we propose a Scale-Disentangled Spatio-Temporal Modeling (SDSTM) framework for long-term traffic emission forecasting. It leverages the predictability differences across multiple scales to decompose and fuse features at different scales, while constraining them to remain independent yet complementary. Specifically, the model first introduces a dual-stream feature decomposition strategy based on the Koopman lifting operator. It lifts the scale-coupled spatiotemporal dynamical system into an infinite-dimensional linear space via Koopman operator, and delineates the predictability boundary using gated wavelet decomposition. Then a novel fusion mechanism is constructed, incorporating a dual-stream independence constraint based on cross-term loss to dynamically refine the dual-stream prediction results, suppress mutual interference, and enhance the accuracy of long-term traffic emission prediction. Extensive experiments conducted on a road-level traffic emission dataset within Xi'an's Second Ring Road demonstrate that the proposed model achieves state-of-the-art performance.
Authors: Tim van Erven, Jack Mayo, Julia Olkhovskaya, Chen-Yu Wei
Abstract: We present an efficient algorithm for linear contextual bandits with adversarial losses and stochastic action sets. Our approach reduces this setting to misspecification-robust adversarial linear bandits with fixed action sets. Without knowledge of the context distribution or access to a context simulator, the algorithm achieves $\tilde{O}(\min\{d^2\sqrt{T}, \sqrt{d^3T\log K}\})$ regret and runs in $\text{poly}(d,C,T)$ time, where $d$ is the feature dimension, $C$ is an upper bound on the number of linear constraints defining the action set in each round, $K$ is an upper bound on the number of actions in each round, and $T$ is number of rounds. This resolves the open question by Liu et al. (2023) on whether one can obtain $\text{poly}(d)\sqrt{T}$ regret in polynomial time independent of the number of actions. For the important class of combinatorial bandits with adversarial losses and stochastic action sets where the action sets can be described by a polynomial number of linear constraints, our algorithm is the first to achieve $\text{poly}(d)\sqrt{T}$ regret in polynomial time, while no prior algorithm achieves even $o(T)$ regret in polynomial time to our knowledge. When a simulator is available, the regret bound can be improved to $\tilde{O}(d\sqrt{L^\star})$, where $L^\star$ is the cumulative loss of the best policy.
Authors: Yuehan Qin, Li Li, Defu Cao, Tiankai Yang, Yue Zhao
Abstract: Out-of-distribution (OOD) robustness is a critical challenge for modern machine learning systems, particularly as they increasingly operate in multimodal settings involving inputs like video, audio, and sensor data. Currently, many OOD detection methods have been proposed, each with different designs targeting various distribution shifts. A single OOD detector may not prevail across all the scenarios; therefore, how can we automatically select an ideal OOD detection model for different distribution shifts? Due to the inherent unsupervised nature of the OOD detection task, it is difficult to predict model performance and find a universally Best model. Also, systematically comparing models on the new unseen data is costly or even impractical. To address this challenge, we introduce M3OOD, a meta-learning-based framework for OOD detector selection in multimodal settings. Meta learning offers a solution by learning from historical model behaviors, enabling rapid adaptation to new data distribution shifts with minimal supervision. Our approach combines multimodal embeddings with handcrafted meta-features that capture distributional and cross-modal characteristics to represent datasets. By leveraging historical performance across diverse multimodal benchmarks, M3OOD can recommend suitable detectors for a new data distribution shift. Experimental evaluation demonstrates that M3OOD consistently outperforms 10 competitive baselines across 12 test scenarios with minimal computational overhead.
Authors: Yuannuo Feng, Wenyong Zhou, Yuexi Lyu, Yixiang Zhang, Zhengwu Liu, Ngai Wong, Wang Kang
Abstract: Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training methods have been proposed to address this issue, they typically rely on idealized and differentiable noise models that fail to capture the full complexity of analog CIM hardware variations. Motivated by the Straight-Through Estimator (STE) framework in quantization, we decouple forward noise simulation from backward gradient computation, enabling noise-aware training with more accurate but computationally intractable noise modeling in analog CIM systems. We provide theoretical analysis demonstrating that our approach preserves essential gradient directional information while maintaining computational tractability and optimization stability. Extensive experiments show that our extended STE framework achieves up to 5.3% accuracy improvement on image classification, 0.72 perplexity reduction on text generation, 2.2$\times$ speedup in training time, and 37.9% lower peak memory usage compared to standard noise-aware training methods.
Authors: Sishun Liu, Ke Deng, Xiuzhen Zhang, Yan Wang
Abstract: Neural network-based Marked Temporal Point Process (MTPP) models have been widely adopted to model event sequences in high-stakes applications, raising concerns about the trustworthiness of outputs from these models. This study focuses on Explanation for MTPP, aiming to identify the minimal and rational explanation, that is, the minimum subset of events in history, based on which the prediction accuracy of MTPP matches that based on full history to a great extent and better than that based on the complement of the subset. This study finds that directly defining Explanation for MTPP as counterfactual explanation or factual explanation can result in irrational explanations. To address this issue, we define Explanation for MTPP as a combination of counterfactual explanation and factual explanation. This study proposes Counterfactual and Factual Explainer for MTPP (CFF) to solve Explanation for MTPP with a series of deliberately designed techniques. Experiments demonstrate the correctness and superiority of CFF over baselines regarding explanation quality and processing efficiency.
Authors: Yunning Cao, Lihong Pei, Jian Guo, Yang Cao, Yu Kang, Yanlong Zhao
Abstract: Identifying high-emission vehicles is a crucial step in regulating urban pollution levels and formulating traffic emission reduction strategies. However, in practical monitoring data, the proportion of high-emission state data is significantly lower compared to normal emission states. This characteristic long-tailed distribution severely impedes the extraction of discriminative features for emission state identification during data mining. Furthermore, the highly nonlinear nature of vehicle emission states and the lack of relevant prior knowledge also pose significant challenges to the construction of identification models.To address the aforementioned issues, we propose a Set-Valued Transformer Network (SVTN) to achieve comprehensive learning of discriminative features from high-emission samples, thereby enhancing detection accuracy. Specifically, this model first employs the transformer to measure the temporal similarity of micro-trip condition variations, thus constructing a mapping rule that projects the original high-dimensional emission data into a low-dimensional feature space. Next, a set-valued identification algorithm is used to probabilistically model the relationship between the generated feature vectors and their labels, providing an accurate metric criterion for the classification algorithm. To validate the effectiveness of our proposed approach, we conducted extensive experiments on the diesel vehicle monitoring data of Hefei city in 2020. The results demonstrate that our method achieves a 9.5\% reduction in the missed detection rate for high-emission vehicles compared to the transformer-based baseline, highlighting its superior capability in accurately identifying high-emission mobile pollution sources.
Authors: Zhanhao Cao, Clement Truong, Andrew Lizarraga
Abstract: Recent advances in large language models are driven by scale, while parameter-efficient fine-tuning (PEFT) enables updating only a small fraction of parameters. Low-Rank Adaptation (LoRA) stores parameter deltas as the product of two small matrices, which makes them natural building blocks that can be composed. Motivated by the superposition principle, we hypothesize that independently trained LoRA modules on disjoint domains are approximately orthogonal and can be combined by simple addition. Using GPT-2 Small (117M) with LoRA rank 4 and alpha=64, we train adapters for three QA domains (math, medicine, finance). In pairwise tests, adding Math+Medicine adapters improves perplexity by -9.10% relative to merged-data fine-tuning, while Math+Finance and Finance+Medicine change by +4.54% and +27.56%, respectively. Across combinations, the RMS cosine similarity between LoRA deltas correlates positively and approximately linearly with the change in perplexity. Naive summation requires no additional training, can be applied in seconds, and achieves performance comparable to models trained on merged data, while clarifying when interference appears in higher-order compositions.
Authors: Evan Dogariu, Anand Brahmbhatt, Elad Hazan
Abstract: We study the fundamental problem of learning a marginally stable unknown nonlinear dynamical system. We describe an algorithm for this problem, based on the technique of spectral filtering, which learns a mapping from past observations to the next based on a spectral representation of the system. Using techniques from online convex optimization, we prove vanishing prediction error for any nonlinear dynamical system that has finitely many marginally stable modes, with rates governed by a novel quantitative control-theoretic notion of learnability. The main technical component of our method is a new spectral filtering algorithm for linear dynamical systems, which incorporates past observations and applies to general noisy and marginally stable systems. This significantly generalizes the original spectral filtering algorithm to both asymmetric dynamics as well as incorporating noise correction, and is of independent interest.
Authors: You Hak Lee, Xiaofan Yu, Quanling Zhao, Flavio Ponzina, Tajana Rosing
Abstract: Unsupervised federated learning (UFL) has gained attention as a privacy-preserving, decentralized machine learning approach that eliminates the need for labor-intensive data labeling. However, UFL faces several challenges in practical applications: (1) non-independent and identically distributed (non-iid) data distribution across devices, (2) expensive computational and communication costs at the edge, and (3) vulnerability to communication noise. Previous UFL approaches have relied on deep neural networks (NN), which introduce substantial overhead in both computation and communication. In this paper, we propose FedUHD, the first UFL framework based on Hyperdimensional Computing (HDC). HDC is a brain-inspired computing scheme with lightweight training and inference operations, much smaller model size, and robustness to communication noise. FedUHD introduces two novel HDC-based designs to improve UFL performance. On the client side, a kNN-based cluster hypervector removal method addresses non-iid data samples by eliminating detrimental outliers. On the server side, a weighted HDC aggregation technique balances the non-iid data distribution across clients. Our experiments demonstrate that FedUHD achieves up to 173.6x and 612.7x better speedup and energy efficiency, respectively, in training, up to 271x lower communication cost, and 15.50% higher accuracy on average across diverse settings, along with superior robustness to various types of noise compared to state-of-the-art NN-based UFL approaches.
Authors: Zahra Kharaghani, Ali Dadras, Tommy L\"ofstedt
Abstract: Federated Learning (FL) has emerged as a vital paradigm in modern machine learning that enables collaborative training across decentralized data sources without exchanging raw data. This approach not only addresses privacy concerns but also allows access to overall substantially larger and potentially more diverse datasets, without the need for centralized storage or hardware resources. However, heterogeneity in client data may cause certain clients to have disproportionate impacts on the global model, leading to disparities in the clients' performances. Fairness, therefore, becomes a crucial concern in FL and can be addressed in various ways. However, the effectiveness of existing fairness-aware methods, particularly in heterogeneous data settings, remains unclear, and the relationships between different approaches are not well understood. In this work, we focus on performance equitable fairness, which aims to minimize differences in performance across clients. We restrict our study to fairness-aware methods that explicitly regularize client losses, evaluating both existing and newly proposed approaches. We identify and theoretically explain connections between the investigated fairness methods, and empirically show that FairGrad (approximate) and FairGrad* (exact) (two variants of a gradient variance regularization method introduced here for performance equitable fairness) improve both fairness and overall model performance in heterogeneous data settings.
Authors: Daria Diatlova, Nikita Balagansky, Alexander Varlamov, Egor Spirin
Abstract: Conventional methods for aggregating layers in fine-tuned self-supervised speech models, such as using the final layer or weighted sum, suffer from information bottlenecks and static feature weighting for all dataset examples. We propose VARAN, a framework that dynamically tailors layer aggregation to individual inputs. By employing layer-specialized probing heads and data-dependent weighting, VARAN adaptively prioritizes layer's features based on input. Evaluations on automatic speech recognition and speech emotion recognition tasks demonstrate VARAN's superior performance, particularly when using the LoRA fine-tuning technique. The framework resolves the trade-off between preserving layer-specific information and enabling flexible feature utilization, advancing efficient adaptation of self-supervised speech representations.
Authors: Ningzhe Shi, Yiqing Zhou, Ling Liu, Jinglin Shi, Yihao Wu, Haiwei Shi, Hanxiao Yu
Abstract: Integrated sensing and communication (ISAC) can enhance artificial intelligence-generated content (AIGC) networks by providing efficient sensing and transmission. Existing AIGC services usually assume that the accuracy of the generated content can be ensured, given accurate input data and prompt, thus only the content generation quality (CGQ) is concerned. However, it is not applicable in ISAC-based AIGC networks, where content generation is based on inaccurate sensed data. Moreover, the AIGC model itself introduces generation errors, which depend on the number of generating steps (i.e., computing resources). To assess the quality of experience of ISAC-based AIGC services, we propose a content accuracy and quality aware service assessment metric (CAQA). Since allocating more resources to sensing and generating improves content accuracy but may reduce communication quality, and vice versa, this sensing-generating (computing)-communication three-dimensional resource tradeoff must be optimized to maximize the average CAQA (AvgCAQA) across all users with AIGC (CAQA-AIGC). This problem is NP-hard, with a large solution space that grows exponentially with users. To solve the CAQA-AIGC problem with low complexity, a linear programming (LP) guided deep reinforcement learning (DRL) algorithm with an action filter (LPDRL-F) is proposed. Through the LP-guided approach and the action filter, LPDRL-F can transform the original three-dimensional solution space to two dimensions, reducing complexity while improving the learning performance of DRL. Simulations show that compared to existing DRL and generative diffusion model algorithms without LP, LPDRL-F converges faster by over 60% and finds better resource allocation solutions, improving AvgCAQA by more than 14%. With LPDRL-F, CAQA-AIGC can achieve an improvement in AvgCAQA of more than 50% compared to existing schemes focusing solely on CGQ.
Authors: Shane Waxler, Paul Blazek, Davis White, Daniel Sneider, Kevin Chung, Mani Nagarathnam, Patrick Williams, Hank Voeller, Karen Wong, Matthew Swanhorst, Sheng Zhang, Naoto Usuyama, Cliff Wong, Tristan Naumann, Hoifung Poon, Andrew Loza, Daniella Meeker, Seth Hain, Rahul Shah
Abstract: Realizing personalized medicine at scale calls for methods that distill insights from longitudinal patient journeys, which can be viewed as a sequence of medical events. Foundation models pretrained on large-scale medical event data represent a promising direction for scaling real-world evidence generation and generalizing to diverse downstream tasks. Using Epic Cosmos, a dataset with medical events from de-identified longitudinal health records for 16.3 billion encounters over 300 million unique patient records from 310 health systems, we introduce the Cosmos Medical Event Transformer ( CoMET) models, a family of decoder-only transformer models pretrained on 118 million patients representing 115 billion discrete medical events (151 billion tokens). We present the largest scaling-law study for medical event data, establishing a methodology for pretraining and revealing power-law scaling relationships for compute, tokens, and model size. Based on this, we pretrained a series of compute-optimal models with up to 1 billion parameters. Conditioned on a patient's real-world history, CoMET autoregressively generates the next medical event, simulating patient health timelines. We studied 78 real-world tasks, including diagnosis prediction, disease prognosis, and healthcare operations. Remarkably for a foundation model with generic pretraining and simulation-based inference, CoMET generally outperformed or matched task-specific supervised models on these tasks, without requiring task-specific fine-tuning or few-shot examples. CoMET's predictive power consistently improves as the model and pretraining scale. Our results show that CoMET, a generative medical event foundation model, can effectively capture complex clinical dynamics, providing an extensible and generalizable framework to support clinical decision-making, streamline healthcare operations, and improve patient outcomes.
Authors: Haebin Shin, Lei Ji, Xiao Liu, Zhiwei Yu, Qi Chen, Yeyun Gong
Abstract: As numerous instruction-tuning datasets continue to emerge during the post-training stage, dynamically balancing and optimizing their mixtures has become a critical challenge. To address this, we propose DynamixSFT, a dynamic and automated method for instruction-tuning dataset mixture optimization. We formulate the problem as a multi-armed bandit setup and introduce a Prior-scaled Boltzmann Exploration that softly anchors the updated sampling distribution to the original dataset proportions, thereby preserving the inherent diversity and coverage of the collection. Sampling probabilities are updated using a lightweight 1-Step Look-ahead Reward, reflecting how much the dataset contributes to improving the model's performance at its current state. When applied to the Tulu-v2-mixture collection comprising 16 instruction-tuning datasets, DynamixSFT achieves up to a 2.2% performance improvement across 10 benchmarks. Furthermore, we provide a comprehensive analysis and visualizations to offer deeper insights into the adaptive dynamics of our method.
Authors: Lorenzo Livi
Abstract: We study how gating mechanisms in recurrent neural networks (RNNs) implicitly induce adaptive learning-rate behavior, even when training is carried out with a fixed, global learning rate. This effect arises from the coupling between state-space time scales--parametrized by the gates--and parameter-space dynamics during gradient descent. By deriving exact Jacobians for leaky-integrator and gated RNNs, we obtain a first-order expansion that makes explicit how constant, scalar, and multi-dimensional gates reshape gradient propagation, modulate effective step sizes, and introduce anisotropy in parameter updates. These findings reveal that gates not only control memory retention in the hidden states, but also act as data-driven preconditioners that adapt optimization trajectories in parameter space. We further draw formal analogies with learning-rate schedules, momentum, and adaptive methods such as Adam, showing that these optimization behaviors emerge naturally from gating. Numerical experiments confirm the validity of our perturbative analysis, supporting the view that gate-induced corrections remain small while exerting systematic effects on training dynamics. Overall, this work provides a unified dynamical-systems perspective on how gating couples state evolution with parameter updates, explaining why gated architectures achieve robust trainability and stability in practice.
Authors: Frederik L. Dennig, Daniel A. Keim
Abstract: Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection, while invertible projections allow the synthesis of new data instances. However, existing methods perform poorly when dealing with out-of-distribution samples in either the data or embedding space. Thus, we propose DE-VAE, an uncertainty-aware variational AE using differential entropy (DE) to improve the learned parametric and invertible projections. Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space. We conduct quantitative and qualitative evaluations on four well-known datasets, using UMAP and t-SNE as baseline projection methods. Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches while enabling the analysis of embedding uncertainty.
Authors: J. M. I. H. Jayakody, A. M. H. H. Alahakoon, C. R. M. Perera, R. M. L. C. Srimal, Roshan Ragel, Vajira Thambawita, Isuru Nawinne
Abstract: The paradigm of electrocardiogram (ECG) analysis has evolved into real-time digital analysis, facilitated by artificial intelligence (AI) and machine learning (ML), which has improved the diagnostic precision and predictive capacity of cardiac diseases. This work proposes a novel deep learning (DL) architecture called the attention-integrated convolutional residual network (AICRN) to regress key ECG parameters such as the PR interval, the QT interval, the QRS duration, the heart rate, the peak amplitude of the R wave, and the amplitude of the T wave for interpretable ECG analysis. Our architecture is specially designed with spatial and channel attention-related mechanisms to address the type and spatial location of the ECG features for regression. The models employ a convolutional residual network to address vanishing and exploding gradient problems. The designed system addresses traditional analysis challenges, such as loss of focus due to human errors, and facilitates the fast and easy detection of cardiac events, thereby reducing the manual efforts required to solve analysis tasks. AICRN models outperform existing models in parameter regression with higher precision. This work demonstrates that DL can play a crucial role in the interpretability and precision of ECG analysis, opening up new clinical applications for cardiac monitoring and management.
Authors: Chuanliu Fan, Zicheng Ma, Jun Gao, Nan Yu, Jun Zhang, Ziqiang Cao, Yi Qin Gao, Guohong Fu
Abstract: Recent advances in protein large language models, such as ProtTeX, represent both side-chain amino acids and backbone structure as discrete token sequences of residue length. While this design enables unified modeling of multimodal protein information, it suffers from two major limitations: (1) The concatenation of sequence and structure tokens approximately doubles the protein length and breaks the intrinsic residue-level alignment between modalities. (2) Constrained by the training corpus and limited context window, ProtTeX is typically trained on single-protein inputs, rendering it incompatible with in-context learning (ICL) and thus limiting its generalization capability. To address these issues, we propose ProtTeX-CC, a lightweight two-stage compression framework designed to enhance ProtTeX under few-shot settings. We first design a joint embedding compression mechanism that fuses sequence and structure representations at the residue level, effectively reducing the protein input length by half without sacrificing performance. Then we propose a self-compression module that aggregates each full demonstration into the latent space of the last few linguistic tokens, reducing the average demonstration length from 751 tokens to less than 16 tokens. Compared to the original ProtTeX, our self-compression approach achieves a compression ratio of approximately 93.68% in the total prompt length under the 16-shot setting. Without modifying the backbone model, ProtTeX-CC introduces only a small number of additional parameters through PEFT-based tuning in the joint embedding compression stage and a single trainable projection layer in the self-compression stage. Extensive experiments on protein function prediction show that ProtTeX-CC improves performance on the in-domain benchmark by 2%, and generalizes well to the out-of-domain dataset with a performance gain of 11%.
Authors: Abdullah X
Abstract: We study the right to be forgotten (GDPR Art. 17) for large language models and frame unlearning as a reproducible systems problem. Our approach treats training as a deterministic program and logs a minimal per-microbatch record (ordered ID hash, RNG seed, learning-rate value, optimizer-step counter, and accumulation boundary). Under a pinned stack and deterministic kernels, replaying the training tail while filtering only the forget closure yields the same parameters as training on the retain set (bit-identical in the training dtype) when preconditions hold. To meet latency and availability constraints, we add complementary paths: (i) exact reverts of recent steps via micro-checkpoints or dense per-step deltas, (ii) cohort-scoped adapter deletion when the base is frozen, and (iii) a curvature-guided anti-update followed by a short retain-tune, audit-gated with escalation to exact replay. We report storage/latency budgets and a toy artifact validating mechanics; in a controlled run that satisfies the preconditions we demonstrate byte-identical equality of model and optimizer states.
Authors: Sagar Shrestha, Rajesh Shrestha, Tri Nguyen, Subash Timilsina
Abstract: Recent advancement in generative models have demonstrated remarkable performance across various data modalities. Beyond their typical use in data synthesis, these models play a crucial role in distribution matching tasks such as latent variable modeling, domain translation, and domain adaptation. Generative Adversarial Networks (GANs) have emerged as the preferred method of distribution matching due to their efficacy in handling high-dimensional data and their flexibility in accommodating various constraints. However, GANs often encounter challenge in training due to their bi-level min-max optimization objective and susceptibility to mode collapse. In this work, we propose a novel approach for distribution matching inspired by the consistency models employed in Continuous Normalizing Flow (CNF). Our model inherits the advantages of CNF models, such as having a straight forward norm minimization objective, while remaining adaptable to different constraints similar to GANs. We provide theoretical validation of our proposed objective and demonstrate its performance through experiments on synthetic and real-world datasets.
Authors: Sagar Shrestha
Abstract: In distributed optimization and federated learning, asynchronous alternating direction method of multipliers (ADMM) serves as an attractive option for large-scale optimization, data privacy, straggler nodes and variety of objective functions. However, communication costs can become a major bottleneck when the nodes have limited communication budgets or when the data to be communicated is prohibitively large. In this work, we propose introducing coarse quantization to the data to be exchanged in aynchronous ADMM so as to reduce communication overhead for large-scale federated learning and distributed optimization applications. We experimentally verify the convergence of the proposed method for several distributed learning tasks, including neural networks.
Authors: Peng Chen, Yihang Wang, Yang Shu, Yunyao Cheng, Kai Zhao, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
Abstract: With the success of pre-trained language models (PLMs) in various application fields beyond natural language processing, language models have raised emerging attention in the field of time series forecasting (TSF) and have shown great prospects. However, current PLM-based TSF methods still fail to achieve satisfactory prediction accuracy matching the strong sequential modeling power of language models. To address this issue, we propose Cross-Model and Cross-Modality Learning with PLMs for time series forecasting (CC-Time). We explore the potential of PLMs for time series forecasting from two aspects: 1) what time series features could be modeled by PLMs, and 2) whether relying solely on PLMs is sufficient for building time series models. In the first aspect, CC-Time incorporates cross-modality learning to model temporal dependency and channel correlations in the language model from both time series sequences and their corresponding text descriptions. In the second aspect, CC-Time further proposes the cross-model fusion block to adaptively integrate knowledge from the PLMs and time series model to form a more comprehensive modeling of time series patterns. Extensive experiments on nine real-world datasets demonstrate that CC-Time achieves state-of-the-art prediction accuracy in both full-data training and few-shot learning situations.
Authors: Fan Li, Xiaoyang Wang, Wenjie Zhang, Ying Zhang, Xuemin Lin
Abstract: Although conventional deep graph models have achieved great success in relational learning, their focus on pairwise relationships limits their capacity to learn pervasive higher-order interactions in real-world complex systems, which can be naturally modeled as hypergraphs. To tackle this, hypergraph neural networks (HNNs), the dominant approach in deep hypergraph learning (DHGL), has garnered substantial attention in recent years. Despite the proposal of numerous HNN methods, there is no comprehensive benchmark for HNNs, which creates a great obstacle to understanding the progress of DHGL in several aspects: (i) insufficient coverage of datasets, algorithms, and tasks; (ii) a narrow evaluation of algorithm performance; and (iii) inconsistent dataset usage, preprocessing, and experimental setups that hinder comparability. To fill the gap, we introduce DHG-Bench, the first comprehensive benchmark for DHGL. Specifically, DHG-Bench integrates 20 diverse datasets spanning node-, edge-, and graph-level tasks, along with 16 state-of-the-art HNN algorithms, under consistent data processing and experimental protocols. Our benchmark systematically investigates the characteristics of HNNs in terms of four dimensions: effectiveness, efficiency, robustness, and fairness. Further, to facilitate reproducible research, we have developed an easy-to-use library for training and evaluating different HNN methods. Extensive experiments conducted with DHG-Bench reveal both the strengths and inherent limitations of existing algorithms, offering valuable insights and directions for future research. The code is publicly available at: https://github.com/Coco-Hut/DHG-Bench.
Authors: Haolong Chen, Liang Zhang, Zhengyuan Xin, Guangxu Zhu
Abstract: Recently, spatio-temporal time-series prediction has developed rapidly, yet existing deep learning methods struggle with learning complex long-term spatio-temporal dependencies efficiently. The long-term spatio-temporal dependency learning brings two new challenges: 1) The long-term temporal sequence includes multiscale information naturally which is hard to extract efficiently; 2) The multiscale temporal information from different nodes is highly correlated and hard to model. To address these challenges, we propose an efficient \textit{\textbf{S}patio-\textbf{T}emporal \textbf{M}ultiscale \textbf{M}amba} (STM2) that includes a multiscale Mamba architecture to capture the multiscale information efficiently and simultaneously, and an adaptive graph causal convolution network to learn the complex multiscale spatio-temporal dependency. STM2 includes hierarchical information aggregation for different-scale information that guarantees their distinguishability. To capture diverse temporal dynamics across all spatial nodes more efficiently, we further propose an enhanced version termed \textit{\textbf{S}patio-\textbf{T}emporal \textbf{M}ixture of \textbf{M}ultiscale \textbf{M}amba} (STM3) that employs a special Mixture-of-Experts architecture, including a more stable routing strategy and a causal contrastive learning strategy to enhance the scale distinguishability. We prove that STM3 has much better routing smoothness and guarantees the pattern disentanglement for each expert successfully. Extensive experiments on real-world benchmarks demonstrate STM2/STM3's superior performance, achieving state-of-the-art results in long-term spatio-temporal time-series prediction.
Authors: Manish Shukla
Abstract: Time-series forecasting underpins critical decisions across aviation, energy, retail and health. Classical autoregressive integrated moving average (ARIMA) models offer interpretability via coefficients but struggle with nonlinearities, whereas tree-based machine-learning models such as XGBoost deliver high accuracy but are often opaque. This paper presents a unified framework for interpreting time-series forecasts using local interpretable model-agnostic explanations (LIME) and SHapley additive exPlanations (SHAP). We convert a univariate series into a leakage-free supervised learning problem, train a gradient-boosted tree alongside an ARIMA baseline and apply post-hoc explainability. Using the Air Passengers dataset as a case study, we show that a small set of lagged features -- particularly the twelve-month lag -- and seasonal encodings explain most forecast variance. We contribute: (i) a methodology for applying LIME and SHAP to time series without violating chronology; (ii) theoretical exposition of the underlying algorithms; (iii) empirical evaluation with extensive analysis; and (iv) guidelines for practitioners.
Authors: Gal Lifshitz, Shahar Zuler, Ori Fouks, Dan Raviv
Abstract: End-to-end deep learning has achieved impressive results but remains limited by its reliance on large labeled datasets, poor generalization to unseen scenarios, and growing computational demands. In contrast, classical optimization methods are data-efficient and lightweight but often suffer from slow convergence. While learned optimizers offer a promising fusion of both worlds, most focus on first-order methods, leaving learned second-order approaches largely unexplored. We propose a novel learned second-order optimizer that introduces a trainable preconditioning unit to enhance the classical Symmetric-Rank-One (SR1) algorithm. This unit generates data-driven vectors used to construct positive semi-definite rank-one matrices, aligned with the secant constraint via a learned projection. Our method is evaluated through analytic experiments and on the real-world task of Monocular Human Mesh Recovery (HMR), where it outperforms existing learned optimization-based approaches. Featuring a lightweight model and requiring no annotated data or fine-tuning, our approach offers strong generalization and is well-suited for integration into broader optimization-based frameworks.
Authors: Siyue Xie, Da Sun Handason Tam, Wing Cheong Lau
Abstract: Graph Neural Networks (GNNs) are widely used as the engine for various graph-related tasks, with their effectiveness in analyzing graph-structured data. However, training robust GNNs often demands abundant labeled data, which is a critical bottleneck in real-world applications. This limitation severely impedes progress in Graph Anomaly Detection (GAD), where anomalies are inherently rare, costly to label, and may actively camouflage their patterns to evade detection. To address these problems, we propose Context Refactoring Contrast (CRoC), a simple yet effective framework that trains GNNs for GAD by jointly leveraging limited labeled and abundant unlabeled data. Different from previous works, CRoC exploits the class imbalance inherent in GAD to refactor the context of each node, which builds augmented graphs by recomposing the attributes of nodes while preserving their interaction patterns. Furthermore, CRoC encodes heterogeneous relations separately and integrates them into the message-passing process, enhancing the model's capacity to capture complex interaction semantics. These operations preserve node semantics while encouraging robustness to adversarial camouflage, enabling GNNs to uncover intricate anomalous cases. In the training stage, CRoC is further integrated with the contrastive learning paradigm. This allows GNNs to effectively harness unlabeled data during joint training, producing richer, more discriminative node embeddings. CRoC is evaluated on seven real-world GAD datasets with varying scales. Extensive experiments demonstrate that CRoC achieves up to 14% AUC improvement over baseline GNNs and outperforms state-of-the-art GAD methods under limited-label settings.
Authors: Wei Jiang, Lijun Zhang
Abstract: In this paper, we analyze the convergence properties of the Lion optimizer. First, we establish that the Lion optimizer attains a convergence rate of $\mathcal{O}(d^{1/2}T^{-1/4})$ under standard assumptions, where $d$ denotes the problem dimension and $T$ is the iteration number. To further improve this rate, we introduce the Lion optimizer with variance reduction, resulting in an enhanced convergence rate of $\mathcal{O}(d^{1/2}T^{-1/3})$. We then analyze in distributed settings, where the standard and variance reduced version of the distributed Lion can obtain the convergence rates of $\mathcal{O}(d^{1/2}(nT)^{-1/4})$ and $\mathcal{O}(d^{1/2}(nT)^{-1/3})$, with $n$ denoting the number of nodes. Furthermore, we investigate a communication-efficient variant of the distributed Lion that ensures sign compression in both communication directions. By employing the unbiased sign operations, the proposed Lion variant and its variance reduction counterpart, achieve convergence rates of $\mathcal{O}\left( \max \left\{\frac{d^{1/4}}{T^{1/4}}, \frac{d^{1/10}}{n^{1/5}T^{1/5}} \right\} \right)$ and $\mathcal{O}\left( \frac{d^{1/4}}{T^{1/4}} \right)$, respectively.
Authors: Xun Su, Jianming Huang, Yang Yusen, Zhongxi Fang, Hiroyuki Kasai
Abstract: Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods largely stems from globally fitting the The reward-tilted distribution, which inherently preserves diversity during multi-modal search. However, current applications of SMC to diffusion models face a fundamental dilemma: early-stage noise samples offer high potential for improvement but are difficult to evaluate accurately, whereas late-stage samples can be reliably assessed but are largely irreversible. To address this exploration-exploitation trade-off, we approach the problem from the perspective of the search algorithm and propose two strategies: Funnel Schedule and Adaptive Temperature. These simple yet effective methods are tailored to the unique generation dynamics and phase-transition behavior of diffusion models. By progressively reducing the number of maintained particles and down-weighting the influence of early-stage rewards, our methods significantly enhance sample quality without increasing the total number of Noise Function Evaluations. Experimental results on multiple benchmarks and state-of-the-art text-to-image diffusion models demonstrate that our approach outperforms previous baselines.
Authors: Rachael DeVries, Casper Christensen, Marie Lisandra Zepeda Mendoza, Ole Winther
Abstract: Electronic Health Records (EHRs), the digital representation of a patient's medical history, are a valuable resource for epidemiological and clinical research. They are also becoming increasingly complex, with recent trends indicating larger datasets, longer time series, and multi-modal integrations. Transformers, which have rapidly gained popularity due to their success in natural language processing and other domains, are well-suited to address these challenges due to their ability to model long-range dependencies and process data in parallel. But their application to EHR classification remains limited by data representations, which can reduce performance or fail to capture informative missingness. In this paper, we present the Bi-Axial Transformer (BAT), which attends to both the clinical variable and time point axes of EHR data to learn richer data relationships and address the difficulties of data sparsity. BAT achieves state-of-the-art performance on sepsis prediction and is competitive to top methods for mortality classification. In comparison to other transformers, BAT demonstrates increased robustness to data missingness, and learns unique sensor embeddings which can be used in transfer learning. Baseline models, which were previously located across multiple repositories or utilized deprecated libraries, were re-implemented with PyTorch and made available for reproduction and future benchmarking.
Authors: Ahmet Bilal Ar{\i}kan, \c{S}ener \"Oz\"onder, Mustafa Taha Ko\c{c}yi\u{g}it, H\"useyin Oktay Altun, H. K\"ubra K\"u\c{c}\"ukkartal, Murat Arslano\u{g}lu, Fatih \c{C}a\u{g}{\i}rankaya, Berk Ayvaz
Abstract: We present an integrated machine learning framework that transforms how manufacturing cost is estimated from 2D engineering drawings. Unlike traditional quotation workflows that require labor-intensive process planning, our approach about 200 geometric and statistical descriptors directly from 13,684 DWG drawings of automotive suspension and steering parts spanning 24 product groups. Gradient-boosted decision tree models (XGBoost, CatBoost, LightGBM) trained on these features achieve nearly 10% mean absolute percentage error across groups, demonstrating robust scalability beyond part-specific heuristics. By coupling cost prediction with explainability tools such as SHAP, the framework identifies geometric design drivers including rotated dimension maxima, arc statistics and divergence metrics, offering actionable insights for cost-aware design. This end-to-end CAD-to-cost pipeline shortens quotation lead times, ensures consistent and transparent cost assessments across part families and provides a deployable pathway toward real-time, ERP-integrated decision support in Industry 4.0 manufacturing environments.
Authors: \'Etienne Pepin
Abstract: This article presents an adaptive mean shift algorithm designed for datasets with varying local scale and cluster cardinality. Local distance distributions, from a point to all others, are used to estimate the cardinality of the local cluster by identifying a local minimum in the density of the distance distribution. Based on these cardinality estimates, local cluster parameters are then computed for the entire cluster in contrast to KDE-based methods, which provide insight only into localized regions of the cluster. During the mean shift execution, the cluster cardinality estimate is used to adaptively adjust the bandwidth and the mean shift kernel radius threshold. Our algorithm outperformed a recently proposed adaptive mean shift method on its original dataset and demonstrated competitive performance on a broader clustering benchmark.
Authors: Aayush Gupta, Arpit Bhayani
Abstract: Web proxies such as NGINX commonly rely on least-recently-used (LRU) eviction, which is size agnostic and can thrash under periodic bursts and mixed object sizes. We introduce Cold-RL, a learned eviction policy for NGINX that replaces LRU's forced-expire path with a dueling Deep Q-Network served by an ONNX sidecar within a strict microsecond budget. On each eviction, Cold-RL samples the K least-recently-used objects, extracts six lightweight features (age, size, hit count, inter-arrival time, remaining TTL, and last origin RTT), and requests a bitmask of victims; a hard timeout of 500 microseconds triggers immediate fallback to native LRU. Policies are trained offline by replaying NGINX access logs through a cache simulator with a simple reward: a retained object earns one point if it is hit again before TTL expiry. We compare against LRU, LFU, size-based, adaptive LRU, and a hybrid baseline on two adversarial workloads. With a 25 MB cache, Cold-RL raises hit ratio from 0.1436 to 0.3538, a 146 percent improvement over the best classical baseline; at 100 MB, from 0.7530 to 0.8675, a 15 percent gain; and at 400 MB it matches classical methods (about 0.918). Inference adds less than 2 percent CPU overhead and keeps 95th percentile eviction latency within budget. To our knowledge, this is the first reinforcement learning eviction policy integrated into NGINX with strict SLOs.
Authors: Reza Shirkavand, Shangqian Gao, Peiran Yu, Heng Huang
Abstract: We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive model profiling, assume a fixed set of experts, or use inefficient trial-and-error strategies. We introduce Cost-Spectrum Contrastive Routing (CSCR), a lightweight framework that maps both prompts and models into a shared embedding space to enable fast, cost-sensitive selection. CSCR uses compact, fast-to-compute logit footprints for open-source models and perplexity fingerprints for black-box APIs. A contrastive encoder is trained to favor the cheapest accurate expert within adaptive cost bands. At inference time, routing reduces to a single k-NN lookup via a FAISS index, requiring no retraining when the expert pool changes and enabling microsecond latency. Across multiple benchmarks, CSCR consistently outperforms baselines, improving the accuracy-cost tradeoff by up to 25%, while generalizing robustly to unseen LLMs and out-of-distribution prompts.
Authors: Denis Blessing, Julius Berner, Lorenz Richter, Carles Domingo-Enrich, Yuanqi Du, Arash Vahdat, Gerhard Neumann
Abstract: Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practice, however, this optimization is challenging in particular if the target measure differs substantially from the prior. In this work, we therefore approach the problem by iteratively solving constrained problems incorporating trust regions that aim for approaching the target measure gradually in a systematic way. It turns out that this trust region based strategy can be understood as a geometric annealing from the prior to the target measure, where, however, the incorporated trust regions lead to a principled and educated way of choosing the time steps in the annealing path. We demonstrate in multiple optimal control applications that our novel method can improve performance significantly, including tasks in diffusion-based sampling, transition path sampling, and fine-tuning of diffusion models.
Authors: Joseph Su\'arez, Kyoung Whan Choe, David Bloomin, Jianming Gao, Yunkun Li, Yao Feng, Saidinesh Pola, Kun Zhang, Yonghui Zhu, Nikhil Pinnaparaju, Hao Xiang Li, Nishaanth Kanna, Daniel Scott, Ryan Sullivan, Rose S. Shuman, Lucas de Alc\^antara, Herbie Bradley, Kirsty You, Bo Wu, Yuhao Jiang, Qimai Li, Jiaxin Chen, Louis Castricato, Xiaolong Zhu, Phillip Isola
Abstract: We present the results of the NeurIPS 2023 Neural MMO Competition, which attracted over 200 participants and submissions. Participants trained goal-conditional policies that generalize to tasks, maps, and opponents never seen during training. The top solution achieved a score 4x higher than our baseline within 8 hours of training on a single 4090 GPU. We open-source everything relating to Neural MMO and the competition under the MIT license, including the policy weights and training code for our baseline and for the top submissions.
Authors: Hyunsoo Song, Seungwhan Kim, Seungkyu Lee
Abstract: Variational autoencoders (VAEs), one of the most widely used generative models, are known to suffer from posterior collapse, a phenomenon that reduces the diversity of generated samples. To avoid posterior collapse, many prior works have tried to control the influence of regularization loss. However, the trade-off between reconstruction and regularization is not satisfactory. For this reason, several methods have been proposed to guarantee latent identifiability, which is the key to avoiding posterior collapse. However, they require structural constraints on the network architecture. For further clarification, we define local posterior collapse to reflect the importance of individual sample points in the data space and to relax the network constraint. Then, we propose Latent Reconstruction(LR) loss, which is inspired by mathematical properties of injective and composite functions, to control posterior collapse without restriction to a specific architecture. We experimentally evaluate our approach, which controls posterior collapse on varied datasets such as MNIST, fashionMNIST, Omniglot, CelebA, and FFHQ.
Authors: Minseon Kim, Jin Myung Kwak, Lama Alssum, Bernard Ghanem, Philip Torr, David Krueger, Fazl Barez, Adel Bibi
Abstract: Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief through systematic testing, showing that poor optimization choices, rather than inherent trade-offs, often cause safety problems, measured as harmful responses to adversarial prompts. By properly selecting key training hyper-parameters, e.g., learning rate, batch size, and gradient steps, we reduce unsafe model responses from 16\% to approximately 5\%, as measured by keyword matching, while maintaining utility performance. Based on this observation, we propose a simple exponential moving average (EMA) momentum technique in parameter space that preserves safety performance by creating a stable optimization path and retains the original pre-trained model's safety properties. Our experiments on the Llama families across multiple datasets (Dolly, Alpaca, ORCA) demonstrate that safety problems during fine-tuning can largely be avoided without specialized interventions, outperforming existing approaches that require additional safety data while offering practical guidelines for maintaining both model performance and safety during adaptation.
Authors: Qinwen Ge, Roza G. Bayrak, Anwar Said, Catie Chang, Xenofon Koutsoukos, Tyler Derr
Abstract: The construction of brain graphs from functional Magnetic Resonance Imaging (fMRI) data plays a crucial role in enabling graph machine learning for neuroimaging. However, current practices often rely on rigid pipelines that overlook critical data-centric choices in how brain graphs are constructed. In this work, we adopt a Data-Centric AI perspective and systematically define and benchmark a data-centric design space for brain graph construction, constrasting with primarily model-centric prior work. We organize this design space into three stages: temporal signal processing, topology extraction, and graph featurization. Our contributions lie less in novel components and more in evaluating how combinations of existing and modified techniques influence downstream performance. Specifically, we study high-amplitude BOLD signal filtering, sparsification and unification strategies for connectivity, alternative correlation metrics, and multi-view node and edge features, such as incorporating lagged dynamics. Experiments on the HCP1200 and ABIDE datasets show that thoughtful data-centric configurations consistently improve classification accuracy over standard pipelines. These findings highlight the critical role of upstream data decisions and underscore the importance of systematically exploring the data-centric design space for graph-based neuroimaging. Our code is available at https://github.com/GeQinwen/DataCentricBrainGraphs.
Authors: Hongyu Lin, Yuchen Li, Haoran Luo, Kaichun Yao, Libo Zhang, Mingjie Xing, Yanjun Wu
Abstract: Linux kernel tuning is essential for optimizing operating system (OS) performance. However, existing methods often face challenges in terms of efficiency, scalability, and generalization. This paper introduces OS-R1, an agentic Linux kernel tuning framework powered by rule-based reinforcement learning (RL). By abstracting the kernel configuration space as an RL environment, OS-R1 facilitates efficient exploration by large language models (LLMs) and ensures accurate configuration modifications. Additionally, custom reward functions are designed to enhance reasoning standardization, configuration modification accuracy, and system performance awareness of the LLMs. Furthermore, we propose a two-phase training process that accelerates convergence and minimizes retraining across diverse tuning scenarios. Experimental results show that OS-R1 significantly outperforms existing baseline methods, achieving up to 5.6% performance improvement over heuristic tuning and maintaining high data efficiency. Notably, OS-R1 is adaptable across various real-world applications, demonstrating its potential for practical deployment in diverse environments. Our dataset and code are publicly available at https://github.com/LHY-24/OS-R1.
Authors: Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Mahashweta Das
Abstract: Coding agents powered by large language models (LLMs) have gained traction for automating code generation through iterative problem-solving with minimal human involvement. Despite the emergence of various frameworks, e.g., LangChain, AutoML, and AIDE, ML scientists still struggle to effectively review and adjust the agents' coding process. The current approach of manually inspecting individual outputs is inefficient, making it difficult to track code evolution, compare coding iterations, and identify improvement opportunities. To address this challenge, we introduce a visual analytics system designed to enhance the examination of coding agent behaviors. Focusing on the AIDE framework, our system supports comparative analysis across three levels: (1) Code-Level Analysis, which reveals how the agent debugs and refines its code over iterations; (2) Process-Level Analysis, which contrasts different solution-seeking processes explored by the agent; and (3) LLM-Level Analysis, which highlights variations in coding behavior across different LLMs. By integrating these perspectives, our system enables ML scientists to gain a structured understanding of agent behaviors, facilitating more effective debugging and prompt engineering. Through case studies using coding agents to tackle popular Kaggle competitions, we demonstrate how our system provides valuable insights into the iterative coding process.
Authors: Luke Li
Abstract: To address the complexity of financial time series, this paper proposes a forecasting model combining sliding window and variational mode decomposition (VMD) methods. Historical stock prices and relevant market indicators are used to construct datasets. VMD decomposes non-stationary financial time series into smoother subcomponents, improving model adaptability. The decomposed data is then input into a deep learning model for prediction. The study compares the forecasting effects of an LSTM model trained on VMD-processed sequences with those using raw time series, demonstrating better performance and stability.
Authors: Quercus Hernandez, Max Win, Thomas C. O'Connor, Paulo E. Arratia, Nathaniel Trask
Abstract: Multiscale systems are ubiquitous in science and technology, but are notoriously challenging to simulate as short spatiotemporal scales must be appropriately linked to emergent bulk physics. When expensive high-dimensional dynamical systems are coarse-grained into low-dimensional models, the entropic loss of information leads to emergent physics which are dissipative, history-dependent, and stochastic. To machine learn coarse-grained dynamics from time-series observations of particle trajectories, we propose a framework using the metriplectic bracket formalism that preserves these properties by construction; most notably, the framework guarantees discrete notions of the first and second laws of thermodynamics, conservation of momentum, and a discrete fluctuation-dissipation balance crucial for capturing non-equilibrium statistics. We introduce the mathematical framework abstractly before specializing to a particle discretization. As labels are generally unavailable for entropic state variables, we introduce a novel self-supervised learning strategy to identify emergent structural variables. We validate the method on benchmark systems and demonstrate its utility on two challenging examples: (1) coarse-graining star polymers at challenging levels of coarse-graining while preserving non-equilibrium statistics, and (2) learning models from high-speed video of colloidal suspensions that capture coupling between local rearrangement events and emergent stochastic dynamics. We provide open-source implementations in both PyTorch and LAMMPS, enabling large-scale inference and extensibility to diverse particle-based systems.
Authors: Zohra Yagoub, Hafida Bouziane
Abstract: The prediction of amyloidogenicity in peptides and proteins remains a focal point of ongoing bioinformatics. The crucial step in this field is to apply advanced computational methodologies. Many recent approaches to predicting amyloidogenicity within proteins are highly based on evolutionary motifs and the individual properties of amino acids. It is becoming increasingly evident that the sequence information-based features show high predictive performance. Consequently, our study evaluated the contextual features of protein sequences obtained from a pretrained protein large language model leveraging bidirectional LSTM and GRU to predict amyloidogenic regions in peptide and protein sequences. Our method achieved an accuracy of 84.5% on 10-fold cross-validation and an accuracy of 83% in the test dataset. Our results demonstrate competitive performance, highlighting the potential of LLMs in enhancing the accuracy of amyloid prediction.
Authors: Like Jian, Dong Liu
Abstract: Federated learning (FL) enables decentralized clients to train a model collaboratively without sharing local data. A key distinction between FL and centralized learning is that clients' data are non-independent and identically distributed, which poses significant challenges in training a global model that generalizes well across heterogeneous local data distributions. In this paper, we analyze the convergence of overparameterized FedAvg with gradient descent (GD). We prove that the impact of data heterogeneity diminishes as the width of neural networks increases, ultimately vanishing when the width approaches infinity. In the infinite-width regime, we further prove that both the global and local models in FedAvg behave as linear models, and that FedAvg achieves the same generalization performance as centralized learning with the same number of GD iterations. Extensive experiments validate our theoretical findings across various network architectures, loss functions, and optimization methods.
Authors: Jihoon Park, Seungeun Oh, Seong-Lyun Kim
Abstract: To address the growing demand for on-device LLM inference in resource-constrained environments, hybrid language models (HLM) have emerged, combining lightweight local models with powerful cloud-based LLMs. Recent studies on HLM have primarily focused on improving accuracy and latency, while often overlooking communication and energy efficiency. We propose a token-level filtering mechanism for an energy-efficient importance- and uncertainty-aware HLM inference that leverages both epistemic uncertainty and attention-based importance. Our method opportunistically uploads only informative tokens, reducing LLM usage and communication costs. Experiments with TinyLlama-1.1B and LLaMA-2-7B demonstrate that our method achieves up to 87.5% BERT Score and token throughput of 0.37 tokens/sec while saving the energy consumption by 40.7% compared to standard HLM. Furthermore, compared to our previous U-HLM baseline, our method improves BERTScore from 85.8% to 87.0%, energy savings from 31.6% to 43.6%, and throughput from 0.36 to 0.40. This approach enables an energy-efficient and accurate deployment of LLMs in bandwidth-constrained edge environments.
Authors: Zhihao Li, Ting Wang, Guojian Zou, Ruofei Wang, Ye Li
Abstract: Traffic state estimation (TSE) fundamentally involves solving high-dimensional spatiotemporal partial differential equations (PDEs) governing traffic flow dynamics from limited, noisy measurements. While Physics-Informed Neural Networks (PINNs) enforce PDE constraints point-wise, this paper adopts a physics-informed deep operator network (PI-DeepONet) framework that reformulates TSE as an operator learning problem. Our approach trains a parameterized neural operator that maps sparse input data to the full spatiotemporal traffic state field, governed by the traffic flow conservation law. Crucially, unlike PINNs that enforce PDE constraints point-wise, PI-DeepONet integrates traffic flow conservation model and the fundamental diagram directly into the operator learning process, ensuring physical consistency while capturing congestion propagation, spatial correlations, and temporal evolution. Experiments on the NGSIM dataset demonstrate superior performance over state-of-the-art baselines. Further analysis reveals insights into optimal function generation strategies and branch network complexity. Additionally, the impact of input function generation methods and the number of functions on model performance is explored, highlighting the robustness and efficacy of proposed framework.
Authors: Vedant Puri, Aditya Joglekar, Kevin Ferguson, Yu-hsuan Chen, Yongjie Jessica Zhang, Levent Burak Kara
Abstract: The quadratic complexity of self-attention limits its applicability and scalability on large unstructured meshes. We introduce Fast Low-rank Attention Routing Engine (FLARE), a linear complexity self-attention mechanism that routes attention through fixed-length latent sequences. Each attention head performs global communication among $N$ tokens by projecting the input sequence onto a fixed length latent sequence of $M \ll N$ tokens using learnable query tokens. By routing attention through a bottleneck sequence, FLARE learns a low-rank form of attention that can be applied at $O(NM)$ cost. FLARE not only scales to unprecedented problem sizes, but also delivers superior accuracy compared to state-of-the-art neural PDE surrogates across diverse benchmarks. We also release a new additive manufacturing dataset to spur further research. Our code is available at https://github.com/vpuri3/FLARE.py.
Authors: Meng Zhang, Chao Wang, Hao Zhang, Shaojun Dong, Lixin He
Abstract: Design of neural networks that incorporate symmetry is crucial for geometric deep learning. Central to this effort is the development of invariant and equivariant operations. This works presents a systematic method for constructing valid invariant and equivariant operations. It can handle inputs and outputs in the form of Cartesian tensors with different rank, as well as spherical tensors with different types. In addition, our method features a graphical representation utilizing the symmetric tensor network, which simplifies both the proofs and constructions related to invariant and equivariant functions. We also apply this approach to design the equivariant interaction message for the geometry graph neural network, and equivariant machine learning model to learn the constitutive law of materials.
Authors: Hansol Lim, Jongseong Brad Choi, Jee Won Lee, Haeseong Jeoung, Minkyu Han
Abstract: We present a hybrid surrogate model for electric vehicle parameter estimation and power consumption. We combine our novel architecture Spectral Parameter Operator built on a Fourier Neural Operator backbone for global context and a differentiable physics module in the forward pass. From speed and acceleration alone, it outputs time-varying motor and regenerative braking efficiencies, as well as aerodynamic drag, rolling resistance, effective mass, and auxiliary power. These parameters drive a physics-embedded estimate of battery power, eliminating any separate physics-residual loss. The modular design lets representations converge to physically meaningful parameters that reflect the current state and condition of the vehicle. We evaluate on real-world logs from a Tesla Model 3, Tesla Model S, and the Kia EV9. The surrogate achieves a mean absolute error of 0.2kW (about 1% of average traction power at highway speeds) for Tesla vehicles and about 0.8kW on the Kia EV9. The framework is interpretable, and it generalizes well to unseen conditions, and sampling rates, making it practical for path optimization, eco-routing, on-board diagnostics, and prognostics health management.
Authors: Yuyang Xu, Yi Cheng, Haochao Ying, Zhuoyun Du, Renjun Hu, Xing Shi, Wei Lin, Jian Wu
Abstract: Test-time scaling has proven effective in further enhancing the performance of pretrained Large Language Models (LLMs). However, mainstream post-training methods (i.e., reinforcement learning (RL) with chain-of-thought (CoT) reasoning) often incur substantial computational overhead due to auxiliary models and overthinking. In this paper, we empirically reveal that the incorrect answers partially stem from verbose reasoning processes lacking correct self-fix, where errors accumulate across multiple reasoning steps. To this end, we propose Self-traced Step-wise Preference Optimization (SSPO), a pluggable RL process supervision framework that enables fine-grained optimization of each reasoning step. Specifically, SSPO requires neither auxiliary models nor stepwise manual annotations. Instead, it leverages step-wise preference signals generated by the model itself to guide the optimization process for reasoning compression. Experiments demonstrate that the generated reasoning sequences from SSPO are both accurate and succinct, effectively mitigating overthinking behaviors without compromising model performance across diverse domains and languages.
Authors: Florian J. Boge, Annika Schuster
Abstract: Deep learning (DL) algorithms are becoming ubiquitous in everyday life and in scientific research. However, the price we pay for their impressively accurate predictions is significant: their inner workings are notoriously opaque - it is unknown to laypeople and researchers alike what features of the data a DL system focuses on and how it ultimately succeeds in predicting correct outputs. A necessary criterion for trustworthy explanations is that they should reflect the relevant processes the algorithms' predictions are based on. The field of eXplainable Artificial Intelligence (XAI) presents promising methods to create such explanations. But recent reviews about their performance offer reasons for skepticism. As we will argue, a good criterion for trustworthiness is explanatory robustness: different XAI methods produce the same explanations in comparable contexts. However, in some instances, all methods may give the same, but still wrong, explanation. We therefore argue that in addition to explanatory robustness (ER), a prior requirement of explanation method robustness (EMR) has to be fulfilled by every XAI method. Conversely, the robustness of an individual method is in itself insufficient for trustworthiness. In what follows, we develop and formalize criteria for ER as well as EMR, providing a framework for explaining and establishing trust in DL algorithms. We also highlight interesting application cases and outline directions for future work.
Authors: Ian Dunn, David R. Koes
Abstract: A generative model capable of sampling realistic molecules with desired properties could accelerate chemical discovery across a wide range of applications. Toward this goal, significant effort has focused on developing models that jointly sample molecular topology and 3D structure. We present FlowMol3, an open-source, multi-modal flow matching model that advances the state of the art for all-atom, small-molecule generation. Its substantial performance gains over previous FlowMol versions are achieved without changes to the graph neural network architecture or the underlying flow matching formulation. Instead, FlowMol3's improvements arise from three architecture-agnostic techniques that incur negligible computational cost: self-conditioning, fake atoms, and train-time geometry distortion. FlowMol3 achieves nearly 100% molecular validity for drug-like molecules with explicit hydrogens, more accurately reproduces the functional group composition and geometry of its training data, and does so with an order of magnitude fewer learnable parameters than comparable methods. We hypothesize that these techniques mitigate a general pathology affecting transport-based generative models, enabling detection and correction of distribution drift during inference. Our results highlight simple, transferable strategies for improving the stability and quality of diffusion- and flow-based molecular generative models.
Authors: Jiyeon Kang, Songseong Kim, Chanhui Lee, Doyeong Hwang, Joanie Hayoun Chung, Yunkyung Ko, Sumin Lee, Sungwoong Kim, Sungbin Lim
Abstract: Ordering-based approaches to causal discovery identify topological orders of causal graphs, providing scalable alternatives to combinatorial search methods. Under the Additive Noise Model (ANM) assumption, recent causal ordering methods based on score matching require an accurate estimation of the Hessian diagonal of the log-densities. However, previous approaches mainly use Stein gradient estimators, which are computationally expensive and memory-intensive. Although DiffAN addresses these limitations by substituting kernel-based estimates with diffusion models, it remains numerically unstable due to the second-order derivatives of score models. To alleviate these problems, we propose Score-informed Neural Operator (SciNO), a probabilistic generative model in smooth function spaces designed to stably approximate the Hessian diagonal and to preserve structural information during the score modeling. Empirical results show that SciNO reduces order divergence by 42.7% on synthetic graphs and by 31.5% on real-world datasets on average compared to DiffAN, while maintaining memory efficiency and scalability. Furthermore, we propose a probabilistic control algorithm for causal reasoning with autoregressive models that integrates SciNO's probability estimates with autoregressive model priors, enabling reliable data-driven causal ordering informed by semantic information. Consequently, the proposed method enhances causal reasoning abilities of LLMs without additional fine-tuning or prompt engineering.
Authors: Emmanouil Kritharakis, Dusan Jakovetic, Antonios Makris, Konstantinos Tserpes
Abstract: Federated Learning (FL) enables collaborative model training across multiple clients without sharing private data. We consider FL scenarios wherein FL clients are subject to adversarial (Byzantine) attacks, while the FL server is trusted (honest) and has a trustworthy side dataset. This may correspond to, e.g., cases where the server possesses trusted data prior to federation, or to the presence of a trusted client that temporarily assumes the server role. Our approach requires only two honest participants, i.e., the server and one client, to function effectively, without prior knowledge of the number of malicious clients. Theoretical analysis demonstrates bounded optimality gaps even under strong Byzantine attacks. Experimental results show that our algorithm significantly outperforms standard and robust FL baselines such as Mean, Trimmed Mean, Median, Krum, and Multi-Krum under various attack strategies including label flipping, sign flipping, and Gaussian noise addition across MNIST, FMNIST, and CIFAR-10 benchmarks using the Flower framework.
Authors: Yuhao Zhou, Jindi Lv, Yuxin Tian, Dan Si, Qing Ye, Jiancheng Lv
Abstract: Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative learning, yet data heterogeneity remains a critical challenge. While existing methods achieve progress in addressing data heterogeneity for participating clients, they fail to generalize to non-participating clients with in-domain distribution shifts and resource constraints. To mitigate this issue, we present HyperFedZero, a novel method that dynamically generates specialized models via a hypernetwork conditioned on distribution-aware embeddings. Our approach explicitly incorporates distribution-aware inductive biases into the model's forward pass, extracting robust distribution embeddings using a NoisyEmbed-enhanced extractor with a Balancing Penalty, effectively preventing feature collapse. The hypernetwork then leverages these embeddings to generate specialized models chunk-by-chunk for non-participating clients, ensuring adaptability to their unique data distributions. Extensive experiments on multiple datasets and models demonstrate HyperFedZero's remarkable performance, surpassing competing methods consistently with minimal computational, storage, and communication overhead. Moreover, ablation studies and visualizations further validate the necessity of each component, confirming meaningful adaptations and validating the effectiveness of HyperFedZero.
Authors: Thomas Krug, Fabian Raisch, Dominik Aimer, Markus Wirnsberger, Ferdinand Sigg, Benjamin Sch\"afer, Benjamin Tischler
Abstract: Transfer learning (TL) can improve data-driven modeling of building thermal dynamics. Therefore, many new TL research areas emerge in the field, such as selecting the right source model for TL. However, these research directions require massive amounts of thermal building data which is lacking presently. Neither public datasets nor existing data generators meet the needs of TL research in terms of data quality and quantity. Moreover, existing data generation approaches typically require expert knowledge in building simulation. We present BuilDa, a thermal building data generation framework for producing synthetic data of adequate quality and quantity for TL research. The framework does not require profound building simulation knowledge to generate large volumes of data. BuilDa uses a single-zone Modelica model that is exported as a Functional Mock-up Unit (FMU) and simulated in Python. We demonstrate BuilDa by generating data and utilizing it for pretraining and fine-tuning TL models.
Authors: Seyed Mahdi Haji Seyed Hossein (ECE Department, University of Tehran, Tehran, Iran), Alireza Hosseini (ECE Department, University of Tehran, Tehran, Iran), Soheil Hajian Manesh (ECE Department, University of Tehran, Tehran, Iran), Amirali Shahriary (ECE Department, University of Tehran, Tehran, Iran)
Abstract: Connected and automated vehicles generate vast amounts of sensor data daily, raising significant privacy and communication challenges for centralized machine learning approaches in perception tasks. This study presents a decentralized, federated learning framework tailored for traffic sign detection in vehicular networks to enable collaborative model training without sharing raw data. The framework partitioned traffic sign classes across vehicles for specialized local training using lightweight object detectors, aggregated model parameters via algorithms like FedProx, FedAdam and FedAVG in a simulated environment with the Flower framework, and evaluated multiple configurations including varying server rounds, local epochs, client participation fractions, and data distributions. Experiments demonstrated that increasing server rounds from 2 to 20 boosted accuracy from below 0.1 to over 0.8, moderate local epochs (8-10) provided optimal efficiency with accuracies around 0.67, higher client participation fractions enhanced generalization up to 0.83, FedProx outperformed other aggregators in handling heterogeneity, non-IID data distributions reduced performance compared to IID, and training duration primarily scaled with the number of rounds rather than aggregation strategy. We conclude that this federated approach may offer a scalable, privacy-preserving solution for real-world vehicular deployments, potentially guiding future integrations of robust aggregation and communication optimizations to advance intelligent transportation systems.
Authors: Manning Zhu, Songtao Guo, Pengzhan Zhou, Yansong Ning, Chang Han, Dewen Qiao
Abstract: Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on the high computational and memory demands of full-model fine-tuning, which limits the potential advancement. This paper presents FedSODA, a resource-efficient FFT framework that enables clients to adapt LLMs without accessing or storing the full model. Specifically, we first propose a similarity group pruning (SGP) module, which prunes redundant layers from the full LLM while retaining the most critical layers to preserve the model performance. Moreover, we introduce an orchestrated distillation alignment (ODA) module to reduce gradient divergence between the sub-LLM and the full LLM during FFT. Through the use of the QLoRA, clients only need to deploy quantized sub-LLMs and fine-tune lightweight adapters, significantly reducing local resource requirements. We conduct extensive experiments on three open-source LLMs across a variety of downstream tasks. The experimental results demonstrate that FedSODA reduces communication overhead by an average of 70.6%, decreases storage usage by 75.6%, and improves task accuracy by 3.1%, making it highly suitable for practical FFT applications under resource constraints.
Authors: Beomseok Seo, Kichang Lee, JaeYeon Park
Abstract: Federated learning (FL) enables decentralized model training without sharing local data. However, most existing methods assume identical model architectures across clients, limiting their applicability in heterogeneous real-world environments. To address this, we propose FedUNet, a lightweight and architecture-agnostic FL framework that attaches a U-Net-inspired additive module to each client's backbone. By sharing only the compact bottleneck of the U-Net, FedUNet enables efficient knowledge transfer without structural alignment. The encoder-decoder design and skip connections in the U-Net help capture both low-level and high-level features, facilitating the extraction of clientinvariant representations. This enables cooperative learning between the backbone and the additive module with minimal communication cost. Experiment with VGG variants shows that FedUNet achieves 93.11% accuracy and 92.68% in compact form (i.e., a lightweight version of FedUNet) with only 0.89 MB low communication overhead.
Authors: Manuela Imbriani, Gina Belmonte, Mieke Massink, Alessandro Tofani, Vincenzo Ciancia
Abstract: This paper presents preliminary results in the definition of a comprehensive benchmark framework designed to systematically evaluate spatial reasoning capabilities in neural networks, with a particular focus on morphological properties such as connectivity and distance relationships. The framework is currently being used to study the capabilities of nnU-Net, exploiting the spatial model checker VoxLogicA to generate two distinct categories of synthetic datasets: maze connectivity problems for topological analysis and spatial distance computation tasks for geometric understanding. Each category is evaluated across multiple resolutions to assess scalability and generalization properties. The automated pipeline encompasses a complete machine learning workflow including: synthetic dataset generation, standardized training with cross-validation, inference execution, and comprehensive evaluation using Dice coefficient and IoU (Intersection over Union) metrics. Preliminary experimental results demonstrate significant challenges in neural network spatial reasoning capabilities, revealing systematic failures in basic geometric and topological understanding tasks. The framework provides a reproducible experimental protocol, enabling researchers to identify specific limitations. Such limitations could be addressed through hybrid approaches combining neural networks with symbolic reasoning methods for improved spatial understanding in clinical applications, establishing a foundation for ongoing research into neural network spatial reasoning limitations and potential solutions.
Authors: Sowmini Devi Veeramachaneni, Ramamurthy Garimella
Abstract: This paper presents Constrained Centroid Clustering (CCC), a method that extends classical centroid-based clustering by enforcing a constraint on the maximum distance between the cluster center and the farthest point in the cluster. Using a Lagrangian formulation, we derive a closed-form solution that maintains interpretability while controlling cluster spread. To evaluate CCC, we conduct experiments on synthetic circular data with radial symmetry and uniform angular distribution. Using ring-wise, sector-wise, and joint entropy as evaluation metrics, we show that CCC achieves more compact clusters by reducing radial spread while preserving angular structure, outperforming standard methods such as K-means and GMM. The proposed approach is suitable for applications requiring structured clustering with spread control, including sensor networks, collaborative robotics, and interpretable pattern analysis.
Authors: Cyril Voyant, Milan Despotovic, Luis Garcia-Gutierrez, Mohammed Asloune, Yves-Marie Saint-Drenan, Jean-Laurent Duchaud, hjuvan Antone Faggianelli, Elena Magliaro
Abstract: A novel methodology for short-term energy forecasting using an Extreme Learning Machine ($\mathtt{ELM}$) is proposed. Using six years of hourly data collected in Corsica (France) from multiple energy sources (solar, wind, hydro, thermal, bioenergy, and imported electricity), our approach predicts both individual energy outputs and total production (\cyr{including imports, which closely follow energy demand, modulo losses)} through a Multi-Input Multi-Output ($\mathtt{MIMO}$) architecture. To address non-stationarity and seasonal variability, sliding window techniques and cyclic time encoding are incorporated, enabling dynamic adaptation to fluctuations. The $\mathtt{ELM}$ model significantly outperforms persistence-based forecasting, particularly for solar and thermal energy, achieving an $\mathtt{nRMSE}$ of $17.9\%$ and $5.1\%$, respectively, with $\mathtt{R^2} > 0.98$ (1-hour horizon). The model maintains high accuracy up to five hours ahead, beyond which renewable energy sources become increasingly volatile. While $\mathtt{MIMO}$ provides marginal gains over Single-Input Single-Output ($\mathtt{SISO}$) architectures and offers key advantages over deep learning methods such as $\mathtt{LSTM}$, it provides a closed-form solution with lower computational demands, making it well-suited for real-time applications, including online learning. Beyond predictive accuracy, the proposed methodology is adaptable to various contexts and datasets, as it can be tuned to local constraints such as resource availability, grid characteristics, and market structures.
Authors: Jiadong Chen, Xiao He, Hengyu Ye, Fuxin Jiang, Tieying Zhang, Jianjun Chen, Xiaofeng Gao
Abstract: In the swiftly evolving domain of cloud computing, the advent of serverless systems underscores the crucial need for predictive auto-scaling systems. This necessity arises to ensure optimal resource allocation and maintain operational efficiency in inherently volatile environments. At the core of a predictive auto-scaling system is the workload forecasting model. Existing forecasting models struggle to quickly adapt to the dynamics in online workload streams and have difficulty capturing the complex periodicity brought by fine-grained, high-frequency forecasting tasks. Addressing this, we propose a novel online ensemble model, E3Former, for online workload forecasting in large-scale predictive auto-scaling. Our model synergizes the predictive capabilities of multiple subnetworks to surmount the limitations of single-model approaches, thus ensuring superior accuracy and robustness. Remarkably, it accomplishes this with a minimal increase in computational overhead, adhering to the lean operational ethos of serverless systems. Through extensive experimentation on real-world workload datasets, we establish the efficacy of our ensemble model. In online forecasting tasks, the proposed method reduces forecast error by an average of 10%, and its effectiveness is further demonstrated through a predictive auto-scaling test in the real-life online system. Currently, our method has been deployed within ByteDance's Intelligent Horizontal Pod Auto-scaling (IHPA) platform, which supports the stable operation of over 30 applications, such as Douyin E-Comerce, TouTiao, and Volcano Engine. The predictive auto-scaling capacity reaching over 600,000 CPU cores. On the basis of essentially ensuring service quality, the predictive auto-scaling system can reduce resource utilization by over 40%.
Authors: Muhammad Rajabinasab, Farhad Pakdaman, Moncef Gabbouj, Peter Schneider-Kamp, Arthur Zimek
Abstract: We propose a novel unsupervised outlier detection method based on Randomized Principal Component Analysis (PCA). Inspired by the performance of Randomized PCA (RPCA) Forest in approximate K-Nearest Neighbor (KNN) search, we develop a novel unsupervised outlier detection method that utilizes RPCA Forest for outlier detection. Experimental results showcase the superiority of the proposed approach compared to the classical and state-of-the-art methods in performing the outlier detection task on several datasets while performing competitively on the rest. The extensive analysis of the proposed method reflects it high generalization power and its computational efficiency, highlighting it as a good choice for unsupervised outlier detection.
Authors: Satoshi Noguchi, Yoshinobu Kawahara
Abstract: Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar values as they pass through successive transformer blocks. In this paper, we establish an equivalence between the hidden-state dynamics induced by stacked attention layers and graph neural diffusion on a complete graph. From this perspective, over-smoothing can be interpreted as a consequence of the dissipative nature of the underlying diffusion dynamics. Motivated by this physical interpretation, we propose Wavy Transformer, which consists of a novel attention layer based on second-order wavy dynamics. We also introduce a feed-forward network and a normalization layer designed to preserve the physical state-velocity relationship under the chain rule, thereby extending the transformer architecture. We further validate our proposed techniques on various transformer models for NLP and CV tasks. The results consistently demonstrate that Wavy Transformer improves performance with minimal additional parameters and no extra hyperparameter tuning.
Authors: Felipe Maia Polo, Xinhe Wang, Mikhail Yurochkin, Gongjun Xu, Moulinath Banerjee, Yuekai Sun
Abstract: Large language models are increasingly used as judges (LLM-as-a-judge) to evaluate model outputs at scale, but their assessments often diverge systematically from human judgments. We present Bridge, a unified statistical framework that explicitly bridges human and LLM evaluations under both absolute scoring and pairwise comparison paradigms. Bridge posits a latent human preference score for each prompt-response pair and models LLM deviations as linear transformations of covariates that capture sources of discrepancies. This offers a simple and principled framework for refining LLM ratings and characterizing systematic discrepancies between humans and LLMs. We provide an efficient fitting algorithm with asymptotic guarantees for statistical inference. Using six LLM judges and two benchmarks (BigGen Bench and Chatbot Arena), Bridge achieves higher agreement with human ratings (accuracy, calibration, and KL divergence) and exposes systematic human-LLM gaps.
Authors: Damian Machlanski, Stephanie Riley, Edward Moroshko, Kurt Butler, Panagiotis Dimitrakopoulos, Thomas Melistas, Akchunya Chanchal, Steven McDonagh, Ricardo Silva, Sotirios A. Tsaftaris
Abstract: The promise that causal modelling can lead to robust AI generalization has been challenged in recent work on domain generalization (DG) benchmarks. We revisit the claims of the causality and DG literature, reconciling apparent contradictions and advocating for a more nuanced theory of the role of causality in generalization. We also provide an interactive demo at https://chai-uk.github.io/ukairs25-causal-predictors/.
URLs: https://chai-uk.github.io/ukairs25-causal-predictors/.
Authors: Bowen Dong, Yilong Fan, Yutao Sun, Zhenyu Li, Tengyu Pan, Xun Zhou, Jianyong Wang
Abstract: Routing networks in sparsely activated mixture-of-experts (MoE) dynamically allocate input tokens to top-k experts through differentiable sparse transformations, enabling scalable model capacity while preserving computational efficiency. Traditional MoE networks impose an expert capacity constraint to ensure GPU-friendly computation. However, this leads to token dropping when capacity is saturated and results in low hardware efficiency due to padding in underutilized experts. Removing the capacity constraint, in turn, compromises load balancing and computational efficiency. To address these issues, we propose Maximum Score Routing ($\mathbf{MaxScore}$), a novel MoE routing paradigm that models routing as a minimum-cost maximum-flow problem and integrates a SoftTopk operator. MaxScore resolves the fundamental limitations of iterative rerouting and optimal transport formulations, achieving lower training losses and higher evaluation scores at equivalent FLOPs compared to both constrained and unconstrained baselines. Implementation details and experimental configurations can be obtained from $\href{https://github.com/dongbw18/MaxScore.git}{MaxScore}$.
Authors: Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Arnaud Dapogny, Alasdair Newson, Matthieu Cord
Abstract: Steering has emerged as a practical approach to enable post-hoc guidance of LLMs towards enforcing a specific behavior. However, it remains largely underexplored for multimodal LLMs (MLLMs); furthermore, existing steering techniques, such as mean steering, rely on a single steering vector, applied independently of the input query. This paradigm faces limitations when the desired behavior is dependent on the example at hand. For example, a safe answer may consist in abstaining from answering when asked for an illegal activity, or may point to external resources or consultation with an expert when asked about medical advice. In this paper, we investigate a fine-grained steering that uses an input-specific linear shift. This shift is computed using contrastive input-specific prompting. However, the input-specific prompts required for this approach are not known at test time. Therefore, we propose to train a small auxiliary module to predict the input-specific steering vector. Our approach, dubbed as L2S (Learn-to-Steer), demonstrates that it reduces hallucinations and enforces safety in MLLMs, outperforming other static baselines.
Authors: Kichang Lee, Songkuk Kim, JaeYeon Park, JeongGil Ko
Abstract: On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware learning, focusing on the trade-off between data quantity and quality via compression. We demonstrate that naive strategies, such as uniform data dropping or one-size-fits-all compression, are suboptimal. Our findings further reveal that data samples exhibit varying sensitivities to compression, supporting the feasibility of a sample-wise adaptive compression strategy. These insights provide a foundation for developing a new class of storage-aware learning systems. The primary contribution of this work is the systematic characterization of this under-explored challenge, offering valuable insights that advance the understanding of storage-aware learning.
Authors: Aditya Varre, Gizem Y\"uce, Nicolas Flammarion
Abstract: Motivated by empirical observations of prolonged plateaus and stage-wise progression during training, we investigate the loss landscape of transformer models trained on in-context next-token prediction tasks. In particular, we focus on learning in-context $n$-gram language models under cross-entropy loss, and establish a sufficient condition for parameter configurations to be stationary points. We then construct a set of parameter configurations for a simplified transformer model that represent $k$-gram estimators (for $k \leq n$), and show that the gradient of the population loss at these solutions vanishes in the limit of infinite sequence length and parameter norm. This reveals a key property of the loss landscape: {sub-$n$-grams are near-stationary points of the population cross-entropy loss}, offering theoretical insight into widely observed phenomena such as stage-wise learning dynamics and emergent phase transitions. These insights are further supported by numerical experiments that illustrate the learning dynamics of $n$-grams, characterized by discrete transitions between near-stationary solutions.
Authors: Tiancheng Zhang, Cheng Zhang, Shuren Liu, Xiaofei Wang, Shaoyuan Huang, Wenyu Wang
Abstract: With the rapid proliferation of streaming services, network load exhibits highly time-varying and bursty behavior, posing serious challenges for maintaining Quality of Service (QoS) in Crowdsourced Cloud-Edge Platforms (CCPs). While CCPs leverage Predict-then-Schedule architecture to improve QoS and profitability, accurate load forecasting remains challenging under traffic surges. Existing methods either minimize mean absolute error, resulting in underprovisioning and potential Service Level Agreement (SLA) violations during peak periods, or adopt conservative overprovisioning strategies, which mitigate SLA risks at the expense of increased resource expenditure. To address this dilemma, we propose HRS, a hybrid representation framework with scheduling awareness that integrates numerical and image-based representations to better capture extreme load dynamics. We further introduce a Scheduling-Aware Loss (SAL) that captures the asymmetric impact of prediction errors, guiding predictions that better support scheduling decisions. Extensive experiments on four real-world datasets demonstrate that HRS consistently outperforms ten baselines and achieves state-of-the-art performance, reducing SLA violation rates by 63.1% and total profit loss by 32.3%.
Authors: Aleksei Liuliakov, Alexander Schulz, Luca Hermes, Barbara Hammer
Abstract: With the growing digitalization all over the globe, the relevance of network security becomes increasingly important. Machine learning-based intrusion detection constitutes a promising approach for improving security, but it bears several challenges. These include the requirement to detect novel and unseen network events, as well as specific data properties, such as events over time together with the inherent graph structure of network communication. In this work, we propose a novel intrusion detection method, TGN-SVDD, which builds upon modern dynamic graph modelling and deep anomaly detection. We demonstrate its superiority over several baselines for realistic intrusion detection data and suggest a more challenging variant of the latter.
Authors: Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh
Abstract: We introduce TCUQ, a single pass, label free uncertainty monitor for streaming TinyML that converts short horizon temporal consistency captured via lightweight signals on posteriors and features into a calibrated risk score with an O(W ) ring buffer and O(1) per step updates. A streaming conformal layer turns this score into a budgeted accept/abstain rule, yielding calibrated behavior without online labels or extra forward passes. On microcontrollers, TCUQ fits comfortably on kilobyte scale devices and reduces footprint and latency versus early exit and deep ensembles (typically about 50 to 60% smaller and about 30 to 45% faster), while methods of similar accuracy often run out of memory. Under corrupted in distribution streams, TCUQ improves accuracy drop detection by 3 to 7 AUPRC points and reaches up to 0.86 AUPRC at high severities; for failure detection it attains up to 0.92 AUROC. These results show that temporal consistency, coupled with streaming conformal calibration, provides a practical and resource efficient foundation for on device monitoring in TinyML.
Authors: Boran Zhao, Haiming Zhai, Zihang Yuan, Hetian Liu, Tian Xia, Wenzhe Zhao, Pengju Ren
Abstract: The growing demand for sparse tensor algebra (SpTA) in machine learning and big data has driven the development of various sparse tensor accelerators. However, most existing manually designed accelerators are limited to specific scenarios, and it's time-consuming and challenging to adjust a large number of design factors when scenarios change. Therefore, automating the design of SpTA accelerators is crucial. Nevertheless, previous works focus solely on either mapping (i.e., tiling communication and computation in space and time) or sparse strategy (i.e., bypassing zero elements for efficiency), leading to suboptimal designs due to the lack of comprehensive consideration of both. A unified framework that jointly optimizes both is urgently needed. However, integrating mapping and sparse strategies leads to a combinatorial explosion in the design space(e.g., as large as $O(10^{41})$ for the workload $P_{32 \times 64} \times Q_{64 \times 48} = Z_{32 \times 48}$). This vast search space renders most conventional optimization methods (e.g., particle swarm optimization, reinforcement learning and Monte Carlo tree search) inefficient. To address this challenge, we propose an evolution strategy-based sparse tensor accelerator optimization framework, called SparseMap. SparseMap constructing a more comprehensive design space with the consideration of both mapping and sparse strategy. We introduce a series of enhancements to genetic encoding and evolutionary operators, enabling SparseMap to efficiently explore the vast and diverse design space. We quantitatively compare SparseMap with prior works and classical optimization methods, demonstrating that SparseMap consistently finds superior solutions.
Authors: Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh
Abstract: We introduce \textbf{SNAP-UQ}, a single-pass, label-free uncertainty method for TinyML that estimates risk from \emph{depth-wise next-activation prediction}: tiny int8 heads forecast the statistics of the next layer from a compressed view of the previous one, and a lightweight monotone mapper turns the resulting surprisal into an actionable score. The design requires no temporal buffers, auxiliary exits, or repeated forward passes, and adds only a few tens of kilobytes to MCU deployments. Across vision and audio backbones, SNAP-UQ consistently reduces flash and latency relative to early-exit and deep ensembles (typically $\sim$40--60\% smaller and $\sim$25--35\% faster), with competing methods of similar accuracy often exceeding memory limits. In corrupted streams it improves accuracy-drop detection by several AUPRC points and maintains strong failure detection (AUROC $\approx$0.9) in a single pass. Grounding uncertainty in layer-to-layer dynamics yields a practical, resource-efficient basis for on-device monitoring in TinyML.
Authors: Yue Xia, Tayyebeh Jahani-Nezhad, Rawad Bitar
Abstract: We propose Fed-DPRoC, a novel federated learning framework that simultaneously ensures differential privacy (DP), Byzantine robustness, and communication efficiency. We introduce the concept of robust-compatible compression, which enables users to compress DP-protected updates while maintaining the robustness of the aggregation rule. We instantiate our framework as RobAJoL, combining the Johnson-Lindenstrauss (JL) transform for compression with robust averaging for robust aggregation. We theoretically prove the compatibility of JL transform with robust averaging and show that RobAJoL preserves robustness guarantees, ensures DP, and reduces communication cost. Experiments on CIFAR-10 and Fashion MNIST validate our theoretical claims and demonstrate that RobAJoL outperforms existing methods in terms of robustness and utility under different Byzantine attacks.
Authors: Zehang Lin, Zheng Lin, Miao Yang, Jianhao Huang, Yuxin Zhang, Zihan Fang, Xia Du, Zhe Chen, Shunzhi Zhu, Wei Ni
Abstract: The increasing complexity of neural networks poses a significant barrier to the deployment of distributed machine learning (ML) on resource-constrained devices, such as federated learning (FL). Split learning (SL) offers a promising solution by offloading the primary computing load from edge devices to a server via model partitioning. However, as the number of participating devices increases, the transmission of excessive smashed data (i.e., activations and gradients) becomes a major bottleneck for SL, slowing down the model training. To tackle this challenge, we propose a communication-efficient SL framework, named SL-ACC, which comprises two key components: adaptive channel importance identification (ACII) and channel grouping compression (CGC). ACII first identifies the contribution of each channel in the smashed data to model training using Shannon entropy. Following this, CGC groups the channels based on their entropy and performs group-wise adaptive compression to shrink the transmission volume without compromising training accuracy. Extensive experiments across various datasets validate that our proposed SL-ACC framework takes considerably less time to achieve a target accuracy than state-of-the-art benchmarks.
Authors: Shalima Binta Manir, Tim Oates
Abstract: A common observation in the Graph Convolutional Network (GCN) literature is that stacking GCN layers may or may not result in better performance on tasks like node classification and edge prediction. We have found empirically that a graph's algebraic connectivity, which is known as the Fiedler value, is a good predictor of GCN performance. Intuitively, graphs with similar Fiedler values have analogous structural properties, suggesting that the same filters and hyperparameters may yield similar results when used with GCNs, and that transfer learning may be more effective between graphs with similar algebraic connectivity. We explore this theoretically and empirically with experiments on synthetic and real graph data, including the Cora, CiteSeer and Polblogs datasets. We explore multiple ways of aggregating the Fiedler value for connected components in the graphs to arrive at a value for the entire graph, and show that it can be used to predict GCN performance. We also present theoretical arguments as to why the Fiedler value is a good predictor.
Authors: Stavros C. Kassinos
Abstract: Transformer neural networks are increasingly used for physics-based problems. In data-driven PDE surrogates, training samples from varying boundary and initial conditions can cause erratic losses and spiky gradients; in physics-informed neural networks (PINNs), stiff composite losses amplify this effect. We introduce Kourkoutas-Beta, an Adam-style optimizer where the fixed second-moment discount beta2 is replaced by a layer-wise dynamic value driven by a bounded ``sunspike'' ratio: the current pooled gradient norm divided by an exponential moving average (EMA) of past norms, squashed to the interval [0,1). Spikes lower beta2 toward beta2_min; calm phases keep it near beta2_max. Options include leaky-AMSGrad (decay), trust-region clipping (max_ratio), adaptive tiny terms, and several bias-correction modes ``none'', ``beta2max'', ``exact'). With all features off and bias_correction=``none'', the method is exactly Adam. We test on four settings: (i) a Transformer PDE surrogate (Heat2D), (ii) a 3D PINN for heat conduction (Heat3D), (iii) a lightweight MLX synthetic task with jitter and rare-trigger bursts, and (iv) a character-level Transformer on 30 MB of enwik8 (small-enwik8). Kourkoutas-Beta improves stability and final loss versus fixed-beta2 Adam. On small-enwik8 it lowers bits-per-character by about 38% vs Adam-0.95 and about 58% vs Adam-0.999 over 10 seeds, with smaller variance. The method remains drop-in, with runtime overhead comparable to Adam in testbeds A-C and within single-digit percent in testbed D. It preserves Adam-style convergence guarantees while improving robustness under spiky gradients.
Authors: Haishun Chen, Cai Xu, Jinlong Yu, Yilin Zhang, Ziyu Guan, Wei Zhao
Abstract: Multi-view evidential learning aims to integrate information from multiple views to improve prediction performance and provide trustworthy uncertainty esitimation. Most previous methods assume that view-specific evidence learning is naturally reliable. However, in practice, the evidence learning process tends to be biased. Through empirical analysis on real-world data, we reveal that samples tend to be assigned more evidence to support data-rich classes, thereby leading to unreliable uncertainty estimation in predictions. This motivates us to delve into a new Biased Evidential Multi-view Learning (BEML) problem. To this end, we propose Fairness-Aware Multi-view Evidential Learning (FAML). FAML first introduces an adaptive prior based on training trajectory, which acts as a regularization strategy to flexibly calibrate the biased evidence learning process. Furthermore, we explicitly incorporate a fairness constraint based on class-wise evidence variance to promote balanced evidence allocation. In the multi-view fusion stage, we propose an opinion alignment mechanism to mitigate view-specific bias across views, thereby encouraging the integration of consistent and mutually supportive evidence. Extensive experiments on five real-world multi-view datasets demonstrate that FAML achieves more balanced evidence allocation and improves both prediction performance and the reliability of uncertainty estimation compared to state-of-the-art methods.
Authors: Pengcheng Hao, Menghao Waiyan William Zhu, Ercan Engin Kuruoglu
Abstract: Continual learning (CL) is crucial for the adaptation of neural network models to new environments. Although outperforming weight-space regularisation approaches, the functional regularisation-based CL methods suffer from high computational costs and large linear approximation errors. In this work, we present a new functional regularisation CL framework, called MCFRCL, which approximates model prediction distributions by Monte Carlo (MC) sampling. Moreover, three continuous distributions are leveraged to capture the statistical characteristics of the MC samples via moment-based methods. Additionally, both the Wasserstein distance and the Kullback-Leibler (KL) distance are employed to construct the regularisation function. The proposed MCFRCL is evaluated against multiple benchmark methods on the MNIST and CIFAR datasets, with simulation results highlighting its effectiveness in both prediction accuracy and training efficiency.
Authors: Iam Kim de S. Hermont, Andre R. Flores, Rodrigo C. de Lamare
Abstract: In this work, we propose a robust adaptive filtering approach for active noise control applications in the presence of impulsive noise. In particular, we develop the filtered-x hyperbolic tangent exponential generalized Kernel M-estimate function (FXHEKM) robust adaptive algorithm. A statistical analysis of the proposed FXHEKM algorithm is carried out along with a study of its computational cost. {In order to evaluate the proposed FXHEKM algorithm, the mean-square error (MSE) and the average noise reduction (ANR) performance metrics have been adopted.} Numerical results show the efficiency of the proposed FXHEKM algorithm to cancel the presence of the additive spurious signals, such as \textbf{$\alpha$}-stable noises against competing algorithms.
Authors: Bipin Chhetri, Akbar Siami Namin
Abstract: Cyberattacks are increasing, and securing against such threats is costing industries billions of dollars annually. Threat Modeling, that is, comprehending the consequences of these attacks, can provide critical support to cybersecurity professionals, enabling them to take timely action and allocate resources that could be used elsewhere. Cybersecurity is heavily dependent on threat modeling, as it assists security experts in assessing and mitigating risks related to identifying vulnerabilities and threats. Recently, there has been a pressing need for automated methods to assess attack descriptions and forecast the future consequences of the increasing complexity of cyberattacks. This study examines how Natural Language Processing (NLP) and deep learning can be applied to analyze the potential impact of cyberattacks by leveraging textual descriptions from the MITRE Common Weakness Enumeration (CWE) database. We emphasize classifying attack consequences into five principal categories: Availability, Access Control, Confidentiality, Integrity, and Other. This paper investigates the use of Bidirectional Encoder Representations from Transformers (BERT) in combination with Hierarchical Attention Networks (HANs) for Multi-label classification, evaluating their performance in comparison with conventional CNN and LSTM-based models. Experimental findings show that BERT achieves an overall accuracy of $0.972$, far higher than conventional deep learning models in multi-label classification. HAN outperforms baseline forms of CNN and LSTM-based models on specific cybersecurity labels. However, BERT consistently achieves better precision and recall, making it more suitable for predicting the consequences of a cyberattack.
Authors: Varsha Ramineni, Hossein A. Rahmani, Emine Yilmaz, David Barber
Abstract: Ensuring fairness in AI systems is critical, especially in high-stakes domains such as lending, hiring, and healthcare. This urgency is reflected in emerging global regulations that mandate fairness assessments and independent bias audits. However, procuring the necessary complete data for fairness testing remains a significant challenge. In industry settings, legal and privacy concerns restrict the collection of demographic data required to assess group disparities, and auditors face practical and cultural challenges in gaining access to data. In practice, data relevant for fairness testing is often split across separate sources: internal datasets held by institutions with predictive attributes, and external public datasets such as census data containing protected attributes, each providing only partial, marginal information. Our work seeks to leverage such available separate data to estimate model fairness when complete data is inaccessible. We propose utilising the available separate data to estimate a set of feasible joint distributions and then compute the set plausible fairness metrics. Through simulation and real experiments, we demonstrate that we can derive meaningful bounds on fairness metrics and obtain reliable estimates of the true metric. Our results demonstrate that this approach can serve as a practical and effective solution for fairness testing in real-world settings where access to complete data is restricted.
Authors: Adolfo Gonz\'alez, V\'ictor Parada
Abstract: Demand forecasting is essential for strategic planning in competitive environments, enabling resource optimization and improved responsiveness to market dynamics. However, multivariate time series modeling faces challenges due to data complexity, uncertainty, and frequent regime shifts. Traditional evaluation metrics can introduce biases and limit generalization. This work compares two custom evaluation functions: FMAE (Focused Mean Absolute Error), focused on minimizing absolute errors, and HEF (Hierarchical Evaluation Function), designed to weight global metrics and penalize large deviations. Experiments were conducted under different data splits (91:9, 80:20, 70:30) using three optimizers (Grid Search, PSO, Optuna), assessing fit, relative accuracy, robustness, and computational efficiency. Results show that HEF consistently outperforms FMAE in global metrics (R2, Relative Accuracy, RMSE, RMSSE), enhancing model robustness and explanatory power. These findings were confirmed via visualizations and statistical tests. Conversely, FMAE offers advantages in local metrics (MAE, MASE) and execution time, making it suitable for short-term scenarios. The study highlights a methodological trade-off: HEF is ideal for strategic planning, while FMAE is better suited for operational efficiency. A replicable framework is proposed for optimizing predictive models in dynamic environments.
Authors: Xiaohan Wang, Zhimin Li, Joshua A. Levine, Matthew Berger
Abstract: Recently, neural surrogate models have emerged as a compelling alternative to traditional simulation workflows. This is accomplished by modeling the underlying function of scientific simulations, removing the need to run expensive simulations. Beyond just mapping from input parameter to output, surrogates have also been shown useful for inverse problems: output to input parameters. Inverse problems can be understood as search, where we aim to find parameters whose surrogate outputs contain a specified feature. Yet finding these parameters can be costly, especially for high-dimensional parameter spaces. Thus, existing surrogate-based solutions primarily focus on finding a small set of matching parameters, in the process overlooking the broader picture of plausible parameters. Our work aims to model and visualize the distribution of possible input parameters that produce a given output feature. To achieve this goal, we aim to address two challenges: (1) the approximation error inherent in the surrogate model and (2) forming the parameter distribution in an interactive manner. We model error via density estimation, reporting high density only if a given parameter configuration is close to training parameters, measured both over the input and output space. Our density estimate is used to form a prior belief on parameters, and when combined with a likelihood on features, gives us an efficient way to sample plausible parameter configurations that generate a target output feature. We demonstrate the usability of our solution through a visualization interface by performing feature-driven parameter analysis over the input parameter space of three simulation datasets. Source code is available at https://github.com/matthewberger/seeing-the-many
Authors: Mingyu Kim, Daniel Stilwell, Jorge Jimenez
Abstract: This paper presents a framework for classifying and detecting spatial commission outliers in maritime environments using seabed acoustic sensor networks and log Gaussian Cox processes (LGCPs). By modeling target arrivals as a mixture of normal and outlier processes, we estimate the probability that a newly observed event is an outlier. We propose a second-order approximation of this probability that incorporates both the mean and variance of the normal intensity function, providing improved classification accuracy compared to mean-only approaches. We analytically show that our method yields a tighter bound to the true probability using Jensen's inequality. To enhance detection, we integrate a real-time, near-optimal sensor placement strategy that dynamically adjusts sensor locations based on the evolving outlier intensity. The proposed framework is validated using real ship traffic data near Norfolk, Virginia, where numerical results demonstrate the effectiveness of our approach in improving both classification performance and outlier detection through sensor deployment.
Authors: Jason Hartline, Lunjia Hu, Yifan Wu
Abstract: Calibration requires that predictions are conditionally unbiased and, therefore, reliably interpretable as probabilities. Calibration measures quantify how far a predictor is from perfect calibration. As introduced by Haghtalab et al. (2024), a calibration measure is truthful if it is minimized in expectation when a predictor outputs the ground-truth probabilities. Although predicting the true probabilities guarantees perfect calibration, in reality, when calibration is evaluated on a finite sample, predicting the truth is not guaranteed to minimize any known calibration measure. All known calibration measures incentivize predictors to lie in order to appear more calibrated on a finite sample. Such lack of truthfulness motivated Haghtalab et al. (2024) and Qiao and Zhao (2025) to construct approximately truthful calibration measures in the sequential prediction setting, but no perfectly truthful calibration measure was known to exist even in the more basic batch setting. We design a perfectly truthful calibration measure in the batch setting: averaged two-bin calibration error (ATB). In addition to being truthful, ATB is sound, complete, continuous, and quadratically related to two existing calibration measures: the smooth calibration error (smCal) and the (lower) distance to calibration (distCal). The simplicity in our definition of ATB makes it efficient and straightforward to compute. ATB allows faster estimation algorithms with significantly easier implementations than smCal and distCal, achieving improved running time and simplicity for the calibration testing problem studied by Hu et al. (2024). We also introduce a general recipe for constructing truthful measures, which proves the truthfulness of ATB as a special case and allows us to construct other truthful calibration measures such as quantile-binned l_2-ECE.
Authors: Michael Mayr, Georgios C. Chasparis
Abstract: Foundational modelling of multi-dimensional time-series data in industrial systems presents a central trade-off: channel-dependent (CD) models capture specific cross-variable dynamics but lack robustness and adaptability as model layers are commonly bound to the data dimensionality of the tackled use-case, while channel-independent (CI) models offer generality at the cost of modelling the explicit interactions crucial for system-level predictive regression tasks. To resolve this, we propose the Causally-Guided Pairwise Transformer (CGPT), a novel architecture that integrates a known causal graph as an inductive bias. The core of CGPT is built around a pairwise modeling paradigm, tackling the CD/CI conflict by decomposing the multidimensional data into pairs. The model uses channel-agnostic learnable layers where all parameter dimensions are independent of the number of variables. CGPT enforces a CD information flow at the pair-level and CI-like generalization across pairs. This approach disentangles complex system dynamics and results in a highly flexible architecture that ensures scalability and any-variate adaptability. We validate CGPT on a suite of synthetic and real-world industrial datasets on long-term and one-step forecasting tasks designed to simulate common industrial complexities. Results demonstrate that CGPT significantly outperforms both CI and CD baselines in predictive accuracy and shows competitive performance with end-to-end trained CD models while remaining agnostic to the problem dimensionality.
Authors: Alicja Ziarko, Michal Bortkiewicz, Michal Zawalski, Benjamin Eysenbach, Piotr Milos
Abstract: In classical AI, perception relies on learning state-based representations, while planning, which can be thought of as temporal reasoning over action sequences, is typically achieved through search. We study whether such reasoning can instead emerge from representations that capture both perceptual and temporal structure. We show that standard temporal contrastive learning, despite its popularity, often fails to capture temporal structure due to its reliance on spurious features. To address this, we introduce Combinatorial Representations for Temporal Reasoning (CRTR), a method that uses a negative sampling scheme to provably remove these spurious features and facilitate temporal reasoning. CRTR achieves strong results on domains with complex temporal structure, such as Sokoban and Rubik's Cube. In particular, for the Rubik's Cube, CRTR learns representations that generalize across all initial states and allow it to solve the puzzle using fewer search steps than BestFS, though with longer solutions. To our knowledge, this is the first method that efficiently solves arbitrary Cube states using only learned representations, without relying on an external search algorithm.
Authors: Yueyang Liu, Lance Kennedy, Ruochen Kong, Joon-Seok Kim, Andreas Z\"ufle
Abstract: Individual-level human mobility prediction has emerged as a significant topic of research with applications in infectious disease monitoring, child, and elderly care. Existing studies predominantly focus on the microscopic aspects of human trajectories: such as predicting short-term trajectories or the next location visited, while offering limited attention to macro-level mobility patterns and the corresponding life routines. In this paper, we focus on an underexplored problem in human mobility prediction: determining the best practices to train a machine learning model using historical data to forecast an individuals complete trajectory over the next days and weeks. In this experiment paper, we undertake a comprehensive experimental analysis of diverse models, parameter configurations, and training strategies, accompanied by an in-depth examination of the statistical distribution inherent in human mobility patterns. Our empirical evaluations encompass both Long Short-Term Memory and Transformer-based architectures, and further investigate how incorporating individual life patterns can enhance the effectiveness of the prediction. We show that explicitly including semantic information such as day-of-the-week and user-specific historical information can help the model better understand individual patterns of life and improve predictions. Moreover, since the absence of explicit user information is often missing due to user privacy, we show that the sampling of users may exacerbate data skewness and result in a substantial loss in predictive accuracy. To mitigate data imbalance and preserve diversity, we apply user semantic clustering with stratified sampling to ensure that the sampled dataset remains representative. Our results further show that small-batch stochastic gradient optimization improves model performance, especially when human mobility training data is limited.
Authors: Haoyu He, Katrin Renz, Yong Cao, Andreas Geiger
Abstract: Diffusion language models, as a promising alternative to traditional autoregressive (AR) models, enable faster generation and richer conditioning on bidirectional context. However, they suffer from a key discrepancy between training and inference: during inference, MDLMs progressively reveal the structure of the generated sequence by producing fewer and fewer masked tokens, whereas this structure is ignored in training as tokens are masked at random. Although this discrepancy between training and inference can lead to suboptimal performance, it has been largely overlooked by previous works, leaving closing this gap between the two stages an open problem. To address this, we frame the problem of learning effective denoising trajectories as a sequential decision-making problem and use the resulting framework to apply reinforcement learning. We propose a novel Masked Diffusion Policy Optimization (MDPO) to exploit the Markov property diffusion possesses and explicitly train the model under the same progressive refining schedule used at inference. MDPO matches the performance of the previous state-of-the-art (SOTA) method with 60x fewer gradient updates, while achieving average improvements of 9.6% on MATH500 and 54.2% on Countdown over SOTA when trained within the same number of weight updates. Additionally, we improve the remasking strategy of MDLMs as a plug-in inference replacement to overcome the limitation that the model cannot refine tokens flexibly. This simple yet effective training-free strategy, what we refer to as RCR, consistently improves performance and yields additional gains when combined with MDPO. Our findings establish great potential for investigating the discrepancy between pre-training and inference of MDLMs. Code: https://github.com/autonomousvision/mdpo. Project Page: https://cli212.github.io/MDPO/.
URLs: https://github.com/autonomousvision/mdpo., https://cli212.github.io/MDPO/.
Authors: Quentin Ploussard, Xiang Li, Matija Pavi\v{c}evi\'c
Abstract: This paper addresses the problem of tightening the mixed-integer linear programming (MILP) formulation for continuous piecewise linear (CPWL) approximations of data sets in arbitrary dimensions. The MILP formulation leverages the difference-of-convex (DC) representation of CPWL functions. We introduce the concept of well-behaved CPWL interpolations and demonstrate that any CPWL interpolation of a data set has a well-behaved version. This result is critical to tighten the MILP problem. We present six different strategies to tighten the problem, which include fixing the values of some variables, introducing additional constraints, identifying small big-M parameter values and applying tighter variable bounds. These methods leverage key aspects of the DC representation and the inherent structure of well-behaved CPWL interpolations. Experimental results demonstrate that specific combinations of these tightening strategies lead to significant improvement in solution times, especially for tightening strategies that consider well-behaved CPWL solutions.
Authors: Danny Scott, William LaForest, Hritom Das, Ioannis Polykretis, Catherine D. Schuman, Charles Rizzo, James Plank, Sai Swaminathan
Abstract: The deployment of dense, low-cost sensors is critical for realizing ubiquitous smart environments. However, existing sensing solutions struggle with the energy, scalability, and reliability trade-offs imposed by battery maintenance, wireless transmission overhead, and data processing complexity. In this work, we present Vibe2Spike, a novel battery-free, wireless sensing framework that enables vibration-based activity recognition using visible light communication (VLC) and spiking neural networks (SNNs). Our system uses ultra-low-cost tags composed only of a piezoelectric disc, a Zener diode, and an LED, which harvest vibration energy and emit sparse visible light spikes without requiring batteries or RF radios. These optical spikes are captured by event cameras and classified using optimized SNN models evolved via the EONS framework. We evaluate Vibe2Spike across five device classes, achieving 94.9\% average classification fitness while analyzing the latency-accuracy trade-offs of different temporal binning strategies. Vibe2Spike demonstrates a scalable, and energy-efficient approach for enabling intelligent environments in a batteryless manner.
Authors: Zhichao Deng, Zhikun Liu, Junxue Wang, Shengqian Chen, Xiang Wei, Qiang Yu
Abstract: Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient framework for temporal information processing. However, existing studies overlook a fundamental property widely observed in biological neurons-synaptic heterogeneity, which plays a crucial role in temporal processing and cognitive capabilities. To bridge this gap, we introduce HetSyn, a generalized framework that models synaptic heterogeneity with synapse-specific time constants. This design shifts temporal integration from the membrane potential to the synaptic current, enabling versatile timescale integration and allowing the model to capture diverse synaptic dynamics. We implement HetSyn as HetSynLIF, an extended form of the leaky integrate-and-fire (LIF) model equipped with synapse-specific decay dynamics. By adjusting the parameter configuration, HetSynLIF can be specialized into vanilla LIF neurons, neurons with threshold adaptation, and neuron-level heterogeneous models. We demonstrate that HetSynLIF not only improves the performance of SNNs across a variety of tasks-including pattern generation, delayed match-to-sample, speech recognition, and visual recognition-but also exhibits strong robustness to noise, enhanced working memory performance, efficiency under limited neuron resources, and generalization across timescales. In addition, analysis of the learned synaptic time constants reveals trends consistent with empirical observations in biological synapses. These findings underscore the significance of synaptic heterogeneity in enabling efficient neural computation, offering new insights into brain-inspired temporal modeling.
Authors: Ridma Jayasundara, Ishan Fernando, Adeepa Fernando, Roshan Ragel, Vajira Thambawita, Isuru Nawinne
Abstract: Cardiovascular diseases (CVDs) are the leading cause of mortality worldwide, accounting for over 30% of global deaths according to the World Health Organization (WHO). Importantly, one-third of these deaths are preventable with timely and accurate diagnosis. The electrocardiogram (ECG), a non-invasive method for recording the electrical activity of the heart, is crucial for diagnosing CVDs. However, privacy concerns surrounding the use of patient ECG data in research have spurred interest in synthetic data, which preserves the statistical properties of real data without compromising patient confidentiality. This study explores the potential of synthetic ECG data for training deep learning models from regression to classification tasks and evaluates the feasibility of transfer learning to enhance classification performance on real ECG data. We experimented with popular deep learning models to predict four key cardiac parameters, namely, Heart Rate (HR), PR interval, QT interval, and QRS complex-using separate regression models. Subsequently, we leveraged these regression models for transfer learning to perform 5-class ECG signal classification. Our experiments systematically investigate whether transfer learning from regression to classification is viable, enabling better utilization of diverse open-access and synthetic ECG datasets. Our findings demonstrate that transfer learning from regression to classification improves classification performance, highlighting its potential to maximize the utility of available data and advance deep learning applications in this domain.
Authors: Yuanhao Li, Badong Chen, Wenjun Bai, Yasuharu Koike, Okito Yamashita
Abstract: Objective: Sparse Bayesian learning provides an effective scheme to solve the high-dimensional problem in brain signal decoding. However, traditional assumptions regarding data distributions such as Gaussian and binomial are potentially inadequate to characterize the noisy signals of brain activity. Hence, this study aims to propose a robust sparse Bayesian learning framework to address noisy highdimensional brain activity decoding. Methods: Motivated by the commendable robustness of the minimum error entropy (MEE) criterion for handling complex data distributions, we proposed an MEE-based likelihood function to facilitate the accurate inference of sparse Bayesian learning in analyzing noisy brain datasets. Results: Our proposed approach was evaluated using two high-dimensional brain decoding tasks in regression and classification contexts, respectively. The experimental results showed that, our approach can realize superior decoding metrics and physiological patterns than the conventional and state-of-the-art methods. Conclusion: Utilizing the proposed MEE-based likelihood model, sparse Bayesian learning is empowered to simultaneously address the challenges of noise and high dimensionality in the brain decoding task. Significance: This work provides a powerful tool to realize robust brain decoding, advancing biomedical engineering applications such as brain-computer interface.
Authors: Zhuo Liu, Tao Chen
Abstract: Brain-like intelligent systems need brain-like learning methods. Equilibrium Propagation (EP) is a biologically plausible learning framework with strong potential for brain-inspired computing hardware. However, existing im-plementations of EP suffer from instability and prohibi-tively high computational costs. Inspired by the structure and dynamics of the brain, we propose a biologically plau-sible Feedback-regulated REsidual recurrent neural network (FRE-RNN) and study its learning performance in EP framework. Feedback regulation enables rapid convergence by reducing the spectral radius. The improvement in con-vergence property reduces the computational cost and train-ing time of EP by orders of magnitude, delivering perfor-mance on par with backpropagation (BP) in benchmark tasks. Meanwhile, residual connections with brain-inspired topologies help alleviate the vanishing gradient problem that arises when feedback pathways are weak in deep RNNs. Our approach substantially enhances the applicabil-ity and practicality of EP in large-scale networks that un-derpin artificial intelligence. The techniques developed here also offer guidance to implementing in-situ learning in physical neural networks.
Authors: Guangli Li, Canbiao Wu, Zhen Liang
Abstract: Affective computing is a rapidly developing interdisciplinary research direction in the field of brain-computer interface. In recent years, the introduction of deep learning technology has greatly promoted the development of the field of emotion recognition. However, due to physiological differences between subjects, as well as the variations in experimental environments and equipment, cross-corpus emotion recognition faces serious challenges, especially for samples near the decision boundary. To solve the above problems, we propose an optimization method based on domain adversarial transfer learning to fine-grained alignment of affective features, named Maximum classifier discrepancy with Pairwise Learning (McdPL) framework. In McdPL, we design a dual adversarial classifier (Ada classifier and RMS classifier), and apply a three-stage adversarial training to maximize classification discrepancy and minimize feature distribution to align controversy samples near the decision boundary. In the process of domain adversarial training, the two classifiers also maintain an adversarial relationship, ultimately enabling precise cross-corpus feature alignment. In addition, the introduction of pairwise learning transforms the classification problem of samples into a similarity problem between samples, alleviating the influence of label noise. We conducted systematic experimental evaluation of the model using publicly available SEED, SEED-IV and SEED-V databases. The results show that the McdPL model is superior to other baseline models in the cross-corpus emotion recognition task, and the average accuracy improvements of 4.76\% and 3.97\%, respectively. Our work provides a promising solution for emotion recognition cross-corpus. The source code is available at https://github.com/WuCB-BCI/Mcd_PL.
Authors: Zahra Mohammadi, Parnian Fazel, Siamak Mohammadi
Abstract: Sleep stage classification is crucial for diagnosing and managing disorders such as sleep apnea and insomnia. Conventional clinical methods like polysomnography are costly and impractical for long-term home use. We present an energy-efficient pipeline that detects four sleep stages (wake, REM, light, and deep) from a single-lead ECG. Two windowing strategies are introduced: (1) a 5-minute window with 30-second steps for machine-learning models that use handcrafted features, and (2) a 30-second window with 10-second steps for deep-learning models, enabling near-real-time 10-second resolution. Lightweight networks such as MobileNet-v1 reach 92 percent accuracy and 91 percent F1-score but still draw significant energy. We therefore design SleepLiteCNN, a custom model that achieves 89 percent accuracy and 89 percent F1-score while lowering energy use to 5.48 microjoules per inference at 45 nm. Applying eight-bit quantization preserves accuracy and further reduces power, and FPGA deployment confirms low resource usage. The proposed system offers a practical solution for continuous, wearable ECG-based sleep monitoring.
Authors: Timothy Oladunni, Ehimen Aneni
Abstract: The limitations of unimodal deep learning models, particularly their tendency to overfit and limited generalizability, have renewed interest in multimodal fusion strategies. Multimodal deep neural networks (MDNN) have the capability of integrating diverse data domains and offer a promising solution for robust and accurate predictions. However, the optimal fusion strategy, intermediate fusion (feature-level) versus late fusion (decision-level) remains insufficiently examined, especially in high-stakes clinical contexts such as ECG-based cardiovascular disease (CVD) classification. This study investigates the comparative effectiveness of intermediate and late fusion strategies using ECG signals across three domains: time, frequency, and time-frequency. A series of experiments were conducted to identify the highest-performing fusion architecture. Results demonstrate that intermediate fusion consistently outperformed late fusion, achieving a peak accuracy of 97 percent, with Cohen's d > 0.8 relative to standalone models and d = 0.40 compared to late fusion. Interpretability analyses using saliency maps reveal that both models align with the discretized ECG signals. Statistical dependency between the discretized ECG signals and corresponding saliency maps for each class was confirmed using Mutual Information (MI). The proposed ECG domain-based multimodal model offers superior predictive capability and enhanced explainability, crucial attributes in medical AI applications, surpassing state-of-the-art models.
Authors: Ronald Carvalho Boadana, Ademir Guimar\~aes da Costa Junior, Ricardo Rios, F\'abio Santos da Silva
Abstract: The growing availability of music on streaming platforms has led to information overload for users. To address this issue and enhance the user experience, increasingly sophisticated recommendation systems have been proposed. This work investigates the use of Large Language Models (LLMs) from the Gemini and LLaMA families, combined with intelligent agents, in a multi-agent personalized music recommendation system. The results are compared with a traditional content-based recommendation model, considering user satisfaction, novelty, and computational efficiency. LLMs achieved satisfaction rates of up to \textit{89{,}32\%}, indicating their promising potential in music recommendation systems.
Authors: Zixia Zhou, Junyan Liu, Wei Emma Wu, Ruogu Fang, Sheng Liu, Qingyue Wei, Rui Yan, Yi Guo, Qian Tao, Yuanyuan Wang, Md Tauhidul Islam, Lei Xing
Abstract: Dynamic brain data, teeming with biological and functional insights, are becoming increasingly accessible through advanced measurements, providing a gateway to understanding the inner workings of the brain in living subjects. However, the vast size and intricate complexity of the data also pose a daunting challenge in reliably extracting meaningful information across various data sources. This paper introduces a generalizable unsupervised deep manifold learning for exploration of neurocognitive and behavioral patterns. Unlike existing methods that extract patterns directly from the input data as in the existing methods, the proposed Brain-dynamic Convolutional-Network-based Embedding (BCNE) seeks to capture the brain-state trajectories by deciphering the temporospatial correlations within the data and subsequently applying manifold learning to this correlative representation. The performance of BCNE is showcased through the analysis of several important dynamic brain datasets. The results, both visual and quantitative, reveal a diverse array of intriguing and interpretable patterns. BCNE effectively delineates scene transitions, underscores the involvement of different brain regions in memory and narrative processing, distinguishes various stages of dynamic learning processes, and identifies differences between active and passive behaviors. BCNE provides an effective tool for exploring general neuroscience inquiries or individual-specific patterns.
Authors: Maksym Shamrai, Vladyslav Hamolia
Abstract: We introduce a novel framework that utilizes the internal weight activations of modern Large Language Models (LLMs) to construct a metric space of languages. Unlike traditional approaches based on hand-crafted linguistic features, our method automatically derives high-dimensional vector representations by computing weight importance scores via an adapted pruning algorithm. Our approach captures intrinsic language characteristics that reflect linguistic phenomena. We validate our approach across diverse datasets and multilingual LLMs, covering 106 languages. The results align well with established linguistic families while also revealing unexpected inter-language connections that may indicate historical contact or language evolution. The source code, computed language latent vectors, and visualization tool are made publicly available at https://github.com/mshamrai/deep-language-geometry.
Authors: Md Basit Azam, Sarangthem Ibotombi Singh
Abstract: Non-invasive glucose monitoring remains a critical challenge in the management of diabetes. HRV during sleep shows promise for glucose prediction however, age-related autonomic changes significantly confound traditional HRV analyses. We analyzed 43 subjects with multi-modal data including sleep-stage specific ECG, HRV features, and clinical measurements. A novel age-normalization technique was applied to the HRV features by, dividing the raw values by age-scaled factors. BayesianRidge regression with 5-fold cross-validation was employed for log-glucose prediction. Age-normalized HRV features achieved R2 = 0.161 (MAE = 0.182) for log-glucose prediction, representing a 25.6% improvement over non-normalized features (R2 = 0.132). The top predictive features were hrv rem mean rr age normalized (r = 0.443, p = 0.004), hrv ds mean rr age normalized (r = 0.438, p = 0.005), and diastolic blood pressure (r = 0.437, p = 0.005). Systematic ablation studies confirmed age-normalization as the critical component, with sleep-stage specific features providing additional predictive value. Age-normalized HRV features significantly enhance glucose prediction accuracy compared with traditional approaches. This sleep-aware methodology addresses fundamental limitations in autonomic function assessment and suggests a preliminary feasibility for non-invasive glucose monitoring applications. However, these results require validation in larger cohorts before clinical consideration.
Authors: BG Tong
Abstract: Objective: This study proposes and preliminarily validates a novel "Functional-Energetic Topology Model" to uncover neurodynamic mechanisms of Non-Suicidal Self-Injury (NSSI), using Graph Neural Networks (GNNs) to decode brain network patterns from single-channel EEG in real-world settings.Methods: EEG data were collected over ~1 month from three adolescents with NSSI using a smartphone app and a portable Fp1 EEG headband during impulsive and non-impulsive states. A theory-driven GNN with seven functional nodes was built. Performance was evaluated via intra-subject (80/20 split) and leave-one-subject-out cross-validation (LOSOCV). GNNExplainer was used for interpretability.Results: The model achieved high intra-subject accuracy (>85%) and significantly above-chance cross-subject performance (approximately73.7%). Explainability analysis revealed a key finding: during NSSI states, a critical feedback loop regulating somatic sensation exhibits dysfunction and directional reversal. Specifically, the brain loses its ability to self-correct via negative bodily feedback, and the regulatory mechanism enters an "ineffective idling" state.Conclusion: This work demonstrates the feasibility of applying theory-guided GNNs to sparse, single-channel EEG for decoding complex mental states. The identified "feedback loop reversal" offers a novel, dynamic, and computable model of NSSI mechanisms, paving the way for objective biomarkers and next-generation Digital Therapeutics (DTx).
Authors: Farnaz Kaboudvand, Maham Khalid, Nydia Assaf, Vardaan Sahgal, Jon P. Ruffley, Brian J. McDermott
Abstract: Corrosion poses a significant challenge to the performance of aluminum alloys, particularly in marine environments. This study investigates the application of machine learning (ML) algorithms to predict and optimize corrosion resistance, utilizing a comprehensive open-source dataset compiled from various sources. The dataset encompasses corrosion rate data and environmental conditions, preprocessed to standardize units and formats. We explored two different approaches, a direct approach, where the material's composition and environmental conditions were used as inputs to predict corrosion rates; and an inverse approach, where corrosion rate served as the input to identify suitable material compositions as output. We employed and compared three distinct ML methodologies for forward predictions: Random Forest regression, optimized via grid search; a feed-forward neural network, utilizing ReLU activation and Adam optimization; and Gaussian Process Regression (GPR), implemented with GPyTorch and employing various kernel functions. The Random Forest and neural network models provided predictive capabilities based on elemental compositions and environmental conditions. Notably, Gaussian Process Regression demonstrated superior performance, particularly with hybrid kernel functions. Log-transformed GPR further refined predictions. This study highlights the efficacy of ML, particularly GPR, in predicting corrosion rates and material properties.
Authors: Mathis Rezzouk, Fabrice Gagnon, Alyson Champagne, Mathieu Roy, Philippe Albouy, Michel-Pierre Coll, Cem Subakan
Abstract: EEG-based analysis of pain perception, enhanced by machine learning, reveals how the brain encodes pain by identifying neural patterns evoked by noxious stimulation. However, a major challenge that remains is the generalization of machine learning models across individuals, given the high cross-participant variability inherent to EEG signals and the limited focus on direct pain perception identification in current research. In this study, we systematically evaluate the performance of cross-participant generalization of a wide range of models, including traditional classifiers and deep neural classifiers for identifying the sensory modality of thermal pain and aversive auditory stimulation from EEG recordings. Using a novel dataset of EEG recordings from 108 participants, we benchmark model performance under both within- and cross-participant evaluation settings. Our findings show that traditional models suffered the largest drop from within- to cross-participant performance, while deep learning models proved more resilient, underscoring their potential for subject-invariant EEG decoding. Even though performance variability remained high, the strong results of the graph-based model highlight its potential to capture subject-invariant structure in EEG signals. On the other hand, we also share the preprocessed dataset used in this study, providing a standardized benchmark for evaluating future algorithms under the same generalization constraints.
Authors: Francisco L\'opez, Eduardo Di Santi, Cl\'ement Lefebvre, Nenad Mijatovic, Michele Pugnaloni, Victor Mart\'in, Kenza Saiah
Abstract: Track Circuits (TC) are the main signalling devices used to detect the presence of a train on a rail track. It has been used since the 19th century and nowadays there are many types depending on the technology. As a general classification, Track Circuits can be divided into 2 main groups, DC (Direct Current) and AC (Alternating Current) circuits. This work is focused on a particular AC track circuit, called "Smart Train Detection System" (STDS), designed with both high and low-frequency bands. This approach uses STDS current data applied to an SVM (support vector machine) classifier as a type of failure identifier. The main purpose of this work consists on determine automatically which is the component of the track that is failing to improve the maintenance action. Model was trained to classify 15 different failures that belong to 3 more general categories. The method was tested with field data from 10 different track circuits and validated by the STDS track circuit expert and maintainers. All use cases were correctly classified by the method.
Authors: Vasileios Saketos, Sebastian Kaltenbach, Sergey Litvinov, Petros Koumoutsakos
Abstract: Algorithmic discovery has traditionally relied on human ingenuity and extensive experimentation. Here we investigate whether a prominent scientific computing algorithm, the Kalman Filter, can be discovered through an automated, data-driven, evolutionary process that relies on Cartesian Genetic Programming (CGP) and Large Language Models (LLM). We evaluate the contributions of both modalities (CGP and LLM) in discovering the Kalman filter under varying conditions. Our results demonstrate that our framework of CGP and LLM-assisted evolution converges to near-optimal solutions when Kalman optimality assumptions hold. When these assumptions are violated, our framework evolves interpretable alternatives that outperform the Kalman filter. These results demonstrate that combining evolutionary algorithms and generative models for interpretable, data-driven synthesis of simple computational modules is a potent approach for algorithmic discovery in scientific computing.
Authors: Zhuofan Xu, Benedikt Bollig, Matthias F\"ugger, Thomas Nowak, Vincent Le Dr\'eau
Abstract: The Centralized Training with Decentralized Execution (CTDE) paradigm has gained significant attention in multi-agent reinforcement learning (MARL) and is the foundation of many recent algorithms. However, decentralized policies operate under partial observability and often yield suboptimal performance compared to centralized policies, while fully centralized approaches typically face scalability challenges as the number of agents increases. We propose Centralized Permutation Equivariant (CPE) learning, a centralized training and execution framework that employs a fully centralized policy to overcome these limitations. Our approach leverages a novel permutation equivariant architecture, Global-Local Permutation Equivariant (GLPE) networks, that is lightweight, scalable, and easy to implement. Experiments show that CPE integrates seamlessly with both value decomposition and actor-critic methods, substantially improving the performance of standard CTDE algorithms across cooperative benchmarks including MPE, SMAC, and RWARE, and matching the performance of state-of-the-art RWARE implementations.
Authors: Irash Perera (Department of Computer Science and Engineering, University of Moratuwa, Colombo, Sri Lanka), Hiranya Abeyrathne (WSO2, Colombo, Sri Lanka), Sanjeewa Malalgoda (WSO2, Colombo, Sri Lanka), Arshardh Ifthikar (WSO2, Colombo, Sri Lanka)
Abstract: GraphQL's flexibility, while beneficial for efficient data fetching, introduces unique security vulnerabilities that traditional API security mechanisms often fail to address. Malicious GraphQL queries can exploit the language's dynamic nature, leading to denial-of-service attacks, data exfiltration through injection, and other exploits. Existing solutions, such as static analysis, rate limiting, and general-purpose Web Application Firewalls, offer limited protection against sophisticated, context-aware attacks. This paper presents a novel, AI-driven approach for real-time detection of malicious GraphQL queries. Our method combines static analysis with machine learning techniques, including Large Language Models (LLMs) for dynamic schema-based configuration, Sentence Transformers (SBERT and Doc2Vec) for contextual embedding of query payloads, and Convolutional Neural Networks (CNNs), Random Forests, and Multilayer Perceptrons for classification. We detail the system architecture, implementation strategies optimized for production environments (including ONNX Runtime optimization and parallel processing), and evaluate the performance of our detection models and the overall system under load. Results demonstrate high accuracy in detecting various threats, including SQL injection, OS command injection, and XSS exploits, alongside effective mitigation of DoS and SSRF attempts. This research contributes a robust and adaptable solution for enhancing GraphQL API security.
Authors: Shiyin Lu, Yang Li, Yu Xia, Yuwei Hu, Shanshan Zhao, Yanqing Ma, Zhichao Wei, Yinglun Li, Lunhao Duan, Jianshan Zhao, Yuxuan Han, Haijun Li, Wanying Chen, Junke Tang, Chengkun Hou, Zhixing Du, Tianli Zhou, Wenjie Zhang, Huping Ding, Jiahe Li, Wen Li, Gui Hu, Yiliang Gu, Siran Yang, Jiamang Wang, Hailong Sun, Yibo Wang, Hui Sun, Jinlong Huang, Yuping He, Shengze Shi, Weihong Zhang, Guodong Zheng, Junpeng Jiang, Sensen Gao, Yi-Feng Wu, Sijia Chen, Yuhui Chen, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang
Abstract: We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an optional "thinking mode" at inference time, allowing users to trade latency for enhanced accuracy on difficult inputs. The model is trained via a comprehensive five-phase curriculum that progressively builds its skills. The process begins with foundational visual and multimodal pretraining, advances through large-scale instruction tuning, and culminates in alignment and reasoning enhancement using DPO and GRPO. To scale these upgrades efficiently, we employ multimodal data packing and hybrid parallelism, yielding a significant end-to-end speedup. We release two open-source models: Ovis2.5-9B and Ovis2.5-2B. The latter continues the "small model, big performance" philosophy of Ovis2, making it ideal for resource-constrained, on-device scenarios. On the OpenCompass multimodal leaderboard, Ovis2.5-9B averages 78.3, marking a substantial improvement over its predecessor, Ovis2-8B, and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9, establishing SOTA for its size. Beyond aggregate scores, Ovis2.5 achieves leading results on STEM benchmarks, exhibits strong capabilities on grounding and video tasks, and achieves open-source SOTA at its scale for complex chart analysis.
Authors: Habibolla Latifizadeh, Anika C. Pirkey, Alanna Gould, David J. Klinke II
Abstract: Improved computational power has enabled different disciplines to predict causal relationships among modeled variables using Bayesian network inference. While many alternative algorithms have been proposed to improve the efficiency and reliability of network prediction, the predicted causal networks reflect the generative process but also bear an opaque imprint of the specific computational algorithm used. Following a ``wisdom of the crowds" strategy, we developed an ensemble learning approach to marginalize the impact of a single algorithm on Bayesian causal network inference. To introduce the approach, we first present the theoretical foundation of this framework. Next, we present a comprehensive implementation of the framework in terms of a new software tool called BaMANI (Bayesian Multi-Algorithm causal Network Inference). Finally, we describe a BaMANI use-case from biology, particularly within human breast cancer studies.
Authors: Noah Kasmanoff, Rahul Zalkikar
Abstract: Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a user given a prompt (input state), and a discriminator capable of classifying between expert and synthetic conversation. While our policy is effective, we recover results from our discriminator that indicate the limitations of dialog models. We argue that this technique can be used to identify adverse behavior of arbitrary data models common for dialog oriented tasks.
Authors: Zabir Al Nazi, Vagelis Hristidis, Aaron Lawson McLean, Jannat Ara Meem, Md Taukir Azam Chowdhury
Abstract: Effective Question Answering (QA) on large biomedical document collections requires effective document retrieval techniques. The latter remains a challenging task due to the domain-specific vocabulary and semantic ambiguity in user queries. We propose BMQExpander, a novel ontology-aware query expansion pipeline that combines medical knowledge - definitions and relationships - from the UMLS Metathesaurus with the generative capabilities of large language models (LLMs) to enhance retrieval effectiveness. We implemented several state-of-the-art baselines, including sparse and dense retrievers, query expansion methods, and biomedical-specific solutions. We show that BMQExpander has superior retrieval performance on three popular biomedical Information Retrieval (IR) benchmarks: NFCorpus, TREC-COVID, and SciFact - with improvements of up to 22.1% in NDCG@10 over sparse baselines and up to 6.5% over the strongest baseline. Further, BMQExpander generalizes robustly under query perturbation settings, in contrast to supervised baselines, achieving up to 15.7% improvement over the strongest baseline. As a side contribution, we publish our paraphrased benchmarks. Finally, our qualitative analysis shows that BMQExpander has fewer hallucinations compared to other LLM-based query expansion baselines.
Authors: Azam Nouri
Abstract: This study investigates whether second-order geometric cues - planar curvature magnitude, curvature sign, and gradient orientation - are sufficient on their own to drive a multilayer perceptron (MLP) classifier for handwritten character recognition (HCR), offering an alternative to convolutional neural networks (CNNs). Using these three handcrafted feature maps as inputs, our curvature-orientation MLP achieves 97 percent accuracy on MNIST digits and 89 percent on EMNIST letters. These results underscore the discriminative power of curvature-based representations for handwritten character images and demonstrate that the advantages of deep learning can be realized even with interpretable, hand-engineered features.
Authors: Zhifeng Kong, Arushi Goel, Joao Felipe Santos, Sreyan Ghosh, Rafael Valle, Wei Ping, Bryan Catanzaro
Abstract: Chain-of-thought reasoning has demonstrated significant improvements in large language models and vision language models, yet its potential for audio language models remains largely unexplored. In this technical report, we take a preliminary step towards closing this gap. For better assessment of sound reasoning, we propose AF-Reasoning-Eval, a benchmark targeting common-sense reasoning and the ability to discriminate among closely related choices. To prepare training corpus for sound reasoning abilities, we propose automatic pipelines that transform existing audio question answering and classification data into explicit reasoning chains, yielding AF-CoT-Train with 1.24M samples. We study the effect of finetuning Audio Flamingo series on AF-CoT-Train and observe considerable improvements on several reasoning benchmarks, validating the effectiveness of chain-of-thought finetuning on advanced sound understanding.
Authors: Dehn Xu, Tim Katzke, Emmanuel M\"uller
Abstract: Graph Neural Networks (GNNs) have emerged as a powerful approach for graph-based machine learning tasks. Previous work applied GNNs to image-derived graph representations for various downstream tasks such as classification or anomaly detection. These transformations include segmenting images, extracting features from segments, mapping them to nodes, and connecting them. However, to the best of our knowledge, no study has rigorously compared the effectiveness of the numerous potential image-to-graph transformation approaches for GNN-based graph-level anomaly detection (GLAD). In this study, we systematically evaluate the efficacy of multiple segmentation schemes, edge construction strategies, and node feature sets based on color, texture, and shape descriptors to produce suitable image-derived graph representations to perform graph-level anomaly detection. We conduct extensive experiments on dermoscopic images using state-of-the-art GLAD models, examining performance and efficiency in purely unsupervised, weakly supervised, and fully supervised regimes. Our findings reveal, for example, that color descriptors contribute the best standalone performance, while incorporating shape and texture features consistently enhances detection efficacy. In particular, our best unsupervised configuration using OCGTL achieves a competitive AUC-ROC score of up to 0.805 without relying on pretrained backbones like comparable image-based approaches. With the inclusion of sparse labels, the performance increases substantially to 0.872 and with full supervision to 0.914 AUC-ROC.
Authors: Marius Miron, David Robinson, Milad Alizadeh, Ellen Gilsenan-McMahon, Gagan Narula, Emmanuel Chemla, Maddie Cusimano, Felix Effenberger, Masato Hagiwara, Benjamin Hoffman, Sara Keen, Diane Kim, Jane Lawton, Jen-Yu Liu, Aza Raskin, Olivier Pietquin, Matthieu Geist
Abstract: Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral studies. Many tasks in this field, such as species, individual, and behavior classification and detection, are well-suited to machine learning. However, they often suffer from limited annotated data, highlighting the need for a general-purpose bioacoustic encoder capable of extracting useful representations for diverse downstream tasks. Such encoders have been proposed before, but are often limited in scope due to a focus on a narrow range of species (typically birds), and a reliance on a single model architecture or training paradigm. Moreover, they are usually evaluated on a small set of tasks and datasets. In this work, we present a large-scale empirical study that covers aspects of bioacoustics that are relevant to research but have previously been scarcely considered: training data diversity and scale, model architectures and training recipes, and the breadth of evaluation tasks and datasets. We obtain encoders that are state-of-the-art on the existing and proposed benchmarks. We also identify what matters for training these encoders, such that this work can be extended when more data are available or better architectures are proposed. Specifically, across 26 datasets with tasks including species classification, detection, individual ID, and vocal repertoire discovery, we find self-supervised pre-training followed by supervised post-training on a mixed bioacoustics + general-audio corpus yields the strongest in- and out-of-distribution performance. We show the importance of data diversity in both stages. To support ongoing research and application, we will release the model checkpoints.
Authors: Jenny Y. Huang, Yunyi Shen, Dennis Wei, Tamara Broderick
Abstract: We propose a method for evaluating the robustness of a widely used LLM ranking system -- the Bradley--Terry ranking system -- to dropping a worst-case very small fraction of evaluation data. Our approach is computationally fast and easy to adopt. When we apply our method to matchups from two popular human-preference platforms, Chatbot Arena and MT-Bench, we find that the Bradley--Terry rankings of top-performing models are remarkably sensitive to the removal of a small fraction of evaluations. Our framework also identifies the specific evaluations most responsible for such ranking flips, allowing for inspections of these influential preferences. We observe that the rankings derived from MT-Bench preferences are notably more robust than those from Chatbot Arena, likely due to MT-bench's use of expert annotators and carefully constructed prompts. Finally, we find that rankings based on crowdsourced human-evaluated systems are just as sensitive as those based on LLM-as-a-judge evaluations, where in both, dropping as little as 0.02% of the total evaluations in the dataset can change the top-ranked model.
Authors: Pouya Kananian, Hans-Arno Jacobsen
Abstract: Studying adversarial robustness of quantum machine learning (QML) models is essential in order to understand their potential advantages over classical models and build trustworthy systems. Distributing QML models allows leveraging multiple quantum processors to overcome the limitations of individual devices and build scalable systems. However, this distribution can affect their adversarial robustness, potentially making them more vulnerable to new attacks. Key paradigms in distributed QML include federated learning, which, similar to classical models, involves training a shared model on local data and sending only the model updates, as well as circuit distribution methods inherent to quantum computing, such as circuit cutting and teleportation-based techniques. These quantum-specific methods enable the distributed execution of quantum circuits across multiple devices. This work reviews the differences between these distribution methods, summarizes existing approaches on the adversarial robustness of QML models when distributed using each paradigm, and discusses open questions in this area.
Authors: Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haorang Wang, Matthew Lau, Wenke Lee, Wilian Lunardi, Martin Andreoni, Polo Chau
Abstract: As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the first attack that exploits standard 3DGS shading methods to create viewpoint-specific camouflage - colors and textures that change with viewing angle - to embed adversarial content in scene objects that are visible only from specific viewpoints and without requiring access to model architecture or weights. Our extensive experiments show that ComplicitSplat generalizes to successfully attack a variety of popular detector - both single-stage, multi-stage, and transformer-based models on both real-world capture of physical objects and synthetic scenes. To our knowledge, this is the first black-box attack on downstream object detectors using 3DGS, exposing a novel safety risk for applications like autonomous navigation and other mission-critical robotic systems.
Authors: Andrei-Valentin T\u{a}nase, Elena Pelican
Abstract: Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that reimagines subword segmentation through three innovations: cross-boundary pattern learning that discovers multi-word semantic units, entropy-driven data curation that optimizes training corpus quality, and multi-phase curriculum learning for stable convergence. Our approach extends Byte-Pair Encoding by learning "superword" tokens, coherent multi-word expressions that preserve semantic unity while maximizing compression efficiency. SupraTok achieves 31% improvement in English tokenization efficiency (5.91 versus 4.51 characters per token) compared to OpenAI's o200k tokenizer and 30% improvement over Google's Gemma 3 tokenizer (256k vocabulary), while maintaining competitive performance across 38 languages. When integrated with a GPT-2 scale model (124M parameters) trained on 10 billion tokens from the FineWeb-Edu dataset, SupraTok yields 8.4% improvement on HellaSWAG and 9.5% on MMLU benchmarks without architectural modifications. While these results are promising at this scale, further validation at larger model scales is needed. These findings suggest that efficient tokenization can complement architectural innovations as a path to improved language model performance.
Authors: Mansi Sood, Eray Can Elumar, Osman Yagan
Abstract: In several applications in distributed systems, an important design criterion is ensuring that the network is sparse, i.e., does not contain too many edges, while achieving reliable connectivity. Sparsity ensures communication overhead remains low, while reliable connectivity is tied to reliable communication and inference on decentralized data reservoirs and computational resources. A class of network models called random K-out graphs appear widely as a heuristic to balance connectivity and sparsity, especially in settings with limited trust, e.g., privacy-preserving aggregation of networked data in which networks are deployed. However, several questions remain regarding how to choose network parameters in response to different operational requirements, including the need to go beyond asymptotic results and the ability to model the stochastic and adversarial environments. To address this gap, we present theorems to inform the choice of network parameters that guarantee reliable connectivity in regimes where nodes can be finite or unreliable. We first derive upper and lower bounds for probability of connectivity in random K-out graphs when the number of nodes is finite. Next, we analyze the property of r-robustness, a stronger notion than connectivity that enables resilient consensus in the presence of malicious nodes. Finally, motivated by aggregation mechanisms based on pairwise masking, we model and analyze the impact of a subset of adversarial nodes, modeled as deletions, on connectivity and giant component size - metrics that are closely tied to privacy guarantees. Together, our results pave the way for end-to-end performance guarantees for a suite of algorithms for reliable inference on networks.
Authors: Xinxing Wu
Abstract: In practical teaching, we observe that few students thoroughly read or fully comprehend the information provided in traditional, text-based course syllabi. As a result, essential details, such as course policies and learning outcomes, are frequently overlooked. To address this challenge, in this paper, we propose a novel approach leveraging AI-generated singing and virtual avatars to present syllabi in a format that is more visually appealing, engaging, and memorable. Especially, we leveraged the open-source tool, HeyGem, to transform textual syllabi into audiovisual presentations, in which digital avatars perform the syllabus content as songs. The proposed approach aims to stimulate students' curiosity, foster emotional connection, and enhance retention of critical course information. Student feedback indicated that AI-sung syllabi significantly improved awareness and recall of key course information.
Authors: Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Shao Tang, Sayan Ghosh, Xuanzhao Dong, Rajat Koner, Yalin Wang
Abstract: Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference cost remains a major bottleneck, particularly in video. We empirically analyze visual token sampling in MLLMs and observe a strong correlation between subset token coverage and segmentation performance. This motivates our design of a simple and effective token pruning method that selects a compact yet spatially representative subset of tokens to accelerate inference. In this paper, we introduce a novel visual token pruning method for IVS, called EVTP-IV, which builds upon the k-center by integrating spatial information to ensure better coverage. We further provide an information-theoretic analysis to support our design. Experiments on standard IVS benchmarks show that our method achieves up to 5X speed-up on video tasks and 3.5X on image tasks, while maintaining comparable accuracy using only 20% of the tokens. Our method also consistently outperforms state-of-the-art pruning baselines under varying pruning ratios.
Authors: Azam Nouri
Abstract: We revisit the classical Sobel operator to ask a simple question: Are first-order edge maps sufficient to drive an all-dense multilayer perceptron (MLP) for handwritten character recognition (HCR), as an alternative to convolutional neural networks (CNNs)? Using only horizontal and vertical Sobel derivatives as input, we train an MLP on MNIST and EMNIST Letters. Despite its extreme simplicity, the resulting network reaches 98% accuracy on MNIST digits and 92% on EMNIST letters -- approaching CNNs while offering a smaller memory footprint and transparent features. Our findings highlight that much of the class-discriminative information in handwritten character images is already captured by first-order gradients, making edge-aware MLPs a compelling option for HCR.
Authors: Yongsheng Chen, Wei Guo, Qi Tang, Xinghui Zhong
Abstract: We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems that unifies latent-space discovery and dynamics learning within a single, end-to-end neural architecture. The encoder-decoder is built from Henon neural networks (HenonNets) and may be augmented with linear SGS-reflector layers. This yields an exact symplectic map between full and latent phase spaces. Latent dynamics are advanced by a symplectic flow map implemented as a HenonNet. This unified neural architecture ensures exact preservation of the underlying symplectic structure at the reduced-order level, significantly enhancing the fidelity and long-term stability of the resulting ROM. We validate our method through comprehensive numerical experiments on canonical Hamiltonian systems. The results demonstrate the method's capability for accurate trajectory reconstruction, robust predictive performance beyond the training horizon, and accurate Hamiltonian preservation. These promising outcomes underscore the effectiveness and potential applicability of our symplectic ROM framework for complex dynamical systems across a broad range of scientific and engineering disciplines.
Authors: Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin
Abstract: Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified. In this paper, we present the Conversational Robustness Evaluation Score: CORE, a metric to quantify the effectiveness of language use within multi-agent systems across different game-theoretic interactions. CORE integrates measures of cluster entropy, lexical repetition, and semantic similarity, providing a direct lens of dialog quality. We apply CORE to pairwise LLM dialogs across competitive, cooperative, and neutral settings, further grounding our analysis in Zipf's and Heaps' Laws to characterize word frequency distributions and vocabulary growth. Our findings show that cooperative settings exhibit both steeper Zipf distributions and higher Heap exponents, indicating more repetition alongside greater vocabulary expansion. In contrast, competitive interactions display lower Zipf and Heaps exponents, reflecting less repetition and more constrained vocabularies. These results provide new insights into how social incentives influence language adaptation, and highlight CORE as a robust diagnostic for measuring linguistic robustness in multi-agent LLM systems. Our code is available at https://github.com/psyonp/core.
Authors: Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng
Abstract: The need for detecting LLM-generated code necessitates watermarking systems capable of operating within its highly structured and syntactically constrained environment. To address this, we introduce CodeTracer, an innovative adaptive code watermarking framework underpinned by a novel reinforcement learning training paradigm. At its core, CodeTracer features a policy-driven approach that utilizes a parameterized model to intelligently bias token choices during next-token prediction. This strategy ensures that embedded watermarks maintain code functionality while exhibiting subtle yet statistically detectable deviations from typical token distributions. To facilitate policy learning, we devise a comprehensive reward system that seamlessly integrates execution feedback with watermark embedding signals, balancing process-level and outcome-level rewards. Additionally, we employ Gumbel Top-k reparameterization to enable gradient-based optimization of discrete watermarking decisions. Extensive comparative evaluations demonstrate CodeTracer's significant superiority over state-of-the-art baselines in both watermark detectability and the preservation of generated code's functionality.
Authors: Yuannuo Feng, Wenyong Zhou, Yuexi Lyu, Hanjie Liu, Zhengwu Liu, Ngai Wong, Wang Kang
Abstract: State Space Models (SSMs) are efficient alternatives to traditional sequence models, excelling at processing long sequences with lower computational complexity. Their reliance on matrix multiplications makes them ideal for compute-in-memory (CIM) architectures, which improve energy efficiency by computing within memory arrays. However, device non-idealities in CIM introduce weight perturbations that can degrade inference accuracy. In this paper, we systematically analyze the robustness of SSMs under noisy conditions, identifying that the final block and output projection layers are more susceptible to perturbations compared to other components. Building on these insights, we propose HPD, a Hybrid Projection Decomposition strategy for the last output projection layer. We replace the original weight matrix with the multiplication of U and {\Sigma} in its SVD to ensure compatibility with existing hardware architectures, while offloading V> to digital hardware for precise and robust correction. Comprehensive tests on Mamba models show that our method reduces perplexity by up to 99.57% under various noise conditions compared to baseline models, with accuracy gains of up to 96.67% on the PIQA benchmark for commonsense reasoning.
Authors: Xiaodong Qu, Andrews Damoah, Joshua Sherwood, Peiyan Liu, Christian Shun Jin, Lulu Chen, Minjie Shen, Nawwaf Aleisa, Zeyuan Hou, Chenyu Zhang, Lifu Gao, Yanshu Li, Qikai Yang, Qun Wang, Cristabelle De Souza
Abstract: Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data, advances in deep learning, reinforcement learning, and multi-agent coordination have accelerated this transformation. Yet, designing and deploying unified AI agents that seamlessly integrate cognition, planning, and interaction remains a grand challenge. In this review, we systematically examine the architectural principles, foundational components, and emergent paradigms that define the landscape of contemporary AI agents. We synthesize insights from cognitive science-inspired models, hierarchical reinforcement learning frameworks, and large language model-based reasoning. Moreover, we discuss the pressing ethical, safety, and interpretability concerns associated with deploying these agents in real-world scenarios. By highlighting major breakthroughs, persistent challenges, and promising research directions, this review aims to guide the next generation of AI agent systems toward more robust, adaptable, and trustworthy autonomous intelligence.
Authors: Viacheslav Yusupov, Maxim Rakhuba, Evgeny Frolov
Abstract: Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a novel hyperbolic recommendation model that uses geometrical insights to improve representation learning and increase computational stability at the same time. We reformulate the notion of hyperbolic distances to unlock additional representation capacity over conventional Euclidean space and learn more expressive user and item representations. To better capture user-items interactions, we construct a triplet loss that models ternary relations between users and their corresponding preferred and nonpreferred choices through a mix of pairwise interaction terms driven by the geometry of data. Our hyperbolic approach not only outperforms existing Euclidean and hyperbolic models but also reduces popularity bias, leading to more diverse and personalized recommendations.
Authors: Zhiyuan Zeng, Jiashuo Liu, Siyuan Chen, Tianci He, Yali Liao, Jinpeng Wang, Zaiyuan Wang, Yang Yang, Lingyue Yin, Mingren Yin, Zhenwei Zhu, Tianle Cai, Zehui Chen, Jiecao Chen, Yantao Du, Xiang Gao, Jiacheng Guo, Liang Hu, Jianpeng Jiao, Xiangsheng Li, Jingkai Liu, Shuang Ni, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, Xin Zhou, Jose Blanchet, Xipeng Qiu, Mengdi Wang, Wenhao Huang
Abstract: Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time updates and retrieving timely, accurate answers. To address this, we introduce $\textbf{FutureX}$, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is the largest and most diverse live benchmark for future prediction, supporting real-time daily updates and eliminating data contamination through an automated pipeline for question gathering and answer collection. We evaluate 25 LLM/agent models, including those with reasoning, search capabilities, and integration of external tools such as the open-source Deep Research Agent and closed-source Deep Research models. This comprehensive evaluation assesses agents' adaptive reasoning and performance in dynamic environments. Additionally, we provide in-depth analyses of agents' failure modes and performance pitfalls in future-oriented tasks, including the vulnerability to fake web pages and the temporal validity. Our goal is to establish a dynamic, contamination-free evaluation standard that drives the development of LLM agents capable of performing at the level of professional human analysts in complex reasoning and predictive thinking.
Authors: Daoze Zhang, Zhanheng Nie, Jianyu Liu, Chenghan Fu, Wanxian Guan, Yuan Gao, Jun Song, Pengjie Wang, Jian Xu, Bo Zheng
Abstract: With the rapid advancement of e-commerce, exploring general representations rather than task-specific ones has attracted increasing research attention. For product understanding, although existing discriminative dual-flow architectures drive progress in this field, they inherently struggle to model the many-to-one alignment between multiple images and texts of products. Therefore, we argue that generative Multimodal Large Language Models (MLLMs) hold significant potential for improving product representation learning. Nevertheless, achieving this goal still remains non-trivial due to several key challenges: the lack of multimodal and aspect-aware modeling modules in typical LLMs; the common presence of background noise in product images; and the absence of a standard benchmark for evaluation. To address these issues, we propose the first generative MLLM-based model named MOON for product representation learning. Our method (1) employs a guided Mixture-of-Experts (MoE) module for targeted modeling of multimodal and aspect-specific product content; (2) effectively detects core semantic regions in product images to mitigate the distraction and interference caused by background noise; and (3) introduces the specialized negative sampling strategy to increase the difficulty and diversity of negative samples. In addition, we release a large-scale multimodal benchmark MBE for various product understanding tasks. Experimentally, our model demonstrates competitive zero-shot performance on both our benchmark and the public dataset, showcasing strong generalization across various downstream tasks, including cross-modal retrieval, product classification, and attribute prediction. Furthermore, the case study and visualization illustrate the effectiveness of MOON for product understanding.
Authors: Arnav Ramamoorthy
Abstract: This paper addresses the challenges of Hindi speech separation and enhancement using advanced neural network architectures, with a focus on edge devices. We propose a refined approach leveraging the DEMUCS model to overcome limitations of traditional methods, achieving substantial improvements in speech clarity and intelligibility. The model is fine-tuned with U-Net and LSTM layers, trained on a dataset of 400,000 Hindi speech clips augmented with ESC-50 and MS-SNSD for diverse acoustic environments. Evaluation using PESQ and STOI metrics shows superior performance, particularly under extreme noise conditions. To ensure deployment on resource-constrained devices like TWS earbuds, we explore quantization techniques to reduce computational requirements. This research highlights the effectiveness of customized AI algorithms for speech processing in Indian contexts and suggests future directions for optimizing edge-based architectures.
Authors: Szymon Pawlonka, Miko{\l}aj Ma{\l}ki\'nski, Jacek Ma\'ndziuk
Abstract: Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings, which might not fully capture the complexity of real-world scenes. Subsequent BP datasets employed real-world images, albeit the represented concepts are identifiable from high-level image features, reducing the task complexity. Differently, the recently released Bongard-RWR dataset aimed at representing abstract concepts formulated in the original BPs using fine-grained real-world images. Its manual construction, however, limited the dataset size to just $60$ instances, constraining evaluation robustness. In this work, we introduce Bongard-RWR+, a BP dataset composed of $5\,400$ instances that represent original BP abstract concepts using real-world-like images generated via a vision language model (VLM) pipeline. Building on Bongard-RWR, we employ Pixtral-12B to describe manually curated images and generate new descriptions aligned with the underlying concepts, use Flux.1-dev to synthesize images from these descriptions, and manually verify that the generated images faithfully reflect the intended concepts. We evaluate state-of-the-art VLMs across diverse BP formulations, including binary and multiclass classification, as well as textual answer generation. Our findings reveal that while VLMs can recognize coarse-grained visual concepts, they consistently struggle with discerning fine-grained concepts, highlighting limitations in their reasoning capabilities.
Authors: Filippo Torresan, Keisuke Suzuki, Ryota Kanai, Manuel Baltieri
Abstract: Active inference is a formal approach to study cognition based on the notion that adaptive agents can be seen as engaging in a process of approximate Bayesian inference, via the minimisation of variational and expected free energies. Minimising the former provides an account of perceptual processes and learning as evidence accumulation, while minimising the latter describes how agents select their actions over time. In this way, adaptive agents are able to maximise the likelihood of preferred observations or states, given a generative model of the environment. In the literature, however, different strategies have been proposed to describe how agents can plan their future actions. While they all share the notion that some kind of expected free energy offers an appropriate way to score policies, sequences of actions, in terms of their desirability, there are different ways to consider the contribution of past motor experience to the agent's future behaviour. In some approaches, agents are assumed to know their own actions, and use such knowledge to better plan for the future. In other approaches, agents are unaware of their actions, and must infer their motor behaviour from recent observations in order to plan for the future. This difference reflects a standard point of departure in two leading frameworks in motor control based on the presence, or not, of an efference copy signal representing knowledge about an agent's own actions. In this work we compare the performances of action-aware and action-unaware agents in two navigations tasks, showing how action-unaware agents can achieve performances comparable to action-aware ones while at a severe disadvantage.
Authors: Zhangyu You, Jiahao Ma, Hongzong Li, Ye-Fan Hu, Jian-Dong Huang
Abstract: Accurate prediction of antibody-binding sites (epitopes) on antigens is crucial for vaccine design, immunodiagnostics, therapeutic antibody development, antibody engineering, research into autoimmune and allergic diseases, and for advancing our understanding of immune responses. Despite in silico methods that have been proposed to predict both linear (continuous) and conformational (discontinuous) epitopes, they consistently underperform in predicting conformational epitopes. In this work, we propose a conformer-based model trained on antigen sequences derived from 1,080 antigen-antibody complexes, leveraging convolutional neural networks (CNNs) to extract local features and Transformers to capture long-range dependencies within antigen sequences. Ablation studies demonstrate that CNN enhances the prediction of linear epitopes, and the Transformer module improves the prediction of conformational epitopes. Experimental results show that our model outperforms existing baselines in terms of PCC, ROC-AUC, PR-AUC, and F1 scores on conformational epitopes.
Authors: Jing Wang, HaiYing Wang, Kun Chen
Abstract: Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the target and external data, as well as various practical concerns that prevent a na\"ive data integration. We consider a realistic scenario where the target data is limited in size while the external data is large but contaminated with outliers; such data contamination, along with other computational and operational constraints, necessitates proper selection or subsampling of the external data for transfer learning. To our knowledge,transfer learning and subsampling under data contamination have not been thoroughly investigated. We address this gap by studying various transfer learning methods with subsamples of the external data, accounting for outliers deviating from the underlying true model due to arbitrary mean shifts. Two subsampling strategies are investigated: one aimed at reducing biases and the other at minimizing variances. Approaches to combine these strategies are also introduced to enhance the performance of the estimators. We provide non-asymptotic error bounds for the transfer learning estimators, clarifying the roles of sample sizes, signal strength, sampling rates, magnitude of outliers, and tail behaviors of model error distributions, among other factors. Extensive simulations show the superior performance of the proposed methods. Additionally, we apply our methods to analyze the risk of hard landings in A380 airplanes by utilizing data from other airplane types,demonstrating that robust transfer learning can improve estimation efficiency for relatively rare airplane types with the help of data from other types of airplanes.
Authors: Seungju Yoo, Hyuk Kwon, Joong-Won Hwang, Kibok Lee
Abstract: Recent advances in computer vision have made training object detectors more efficient and effective; however, assessing their performance in real-world applications still relies on costly manual annotation. To address this limitation, we develop an automated model evaluation (AutoEval) framework for object detection. We propose Prediction Consistency and Reliability (PCR), which leverages the multiple candidate bounding boxes that conventional detectors generate before non-maximum suppression (NMS). PCR estimates detection performance without ground-truth labels by jointly measuring 1) the spatial consistency between boxes before and after NMS, and 2) the reliability of the retained boxes via the confidence scores of overlapping boxes. For a more realistic and scalable evaluation, we construct a meta-dataset by applying image corruptions of varying severity. Experimental results demonstrate that PCR yields more accurate performance estimates than existing AutoEval methods, and the proposed meta-dataset covers a wider range of detection performance. The code is available at https://github.com/YonseiML/autoeval-det.
Authors: Yao Wu
Abstract: In large language model (LLM) adaptation, balancing multiple optimization objectives such as improving factuality (heat) and increasing confidence (via low entropy) poses a fundamental challenge, especially when prompt parameters (e.g., hidden-layer insertions h and embedding modifications w) interact in non-trivial ways. Existing multi-objective optimization strategies often rely on scalar gradient aggregation, ignoring the deeper geometric structure between objectives and parameters. We propose J6, a structured Jacobian-based method that decomposes the gradient interaction matrix into six interpretable components. This decomposition enables both hard decision-making (e.g., choosing the dominant update direction via argmax) and soft strategies (e.g., attention-style weighting via softmax over J6), forming a dynamic update framework that adapts to local conflict and synergy. Moreover, the interpretable structure of J6 provides insight into parameter attribution, task interference, and geometry-aligned adaptation. Our work introduces a principled and extensible mechanism for conflict-aware prompt optimization, and opens a new avenue for incorporating structured Jacobian reasoning into multi-objective neural tuning.
Authors: Haiquan Hu, Jiazhi Jiang, Shiyou Xu, Ruhan Zeng, Tian Wang
Abstract: Evaluating large language models (LLMs) has become increasingly challenging as model capabilities advance rapidly. While recent models often achieve higher scores on standard benchmarks, these improvements do not consistently reflect enhanced real-world reasoning capabilities. Moreover, widespread overfitting to public benchmarks and the high computational cost of full evaluations have made it both expensive and less effective to distinguish meaningful differences between models. To address these challenges, we propose the \textbf{S}tructured \textbf{T}ransition \textbf{E}valuation \textbf{M}ethod (STEM), a lightweight and interpretable evaluation framework for efficiently estimating the relative capabilities of LLMs. STEM identifies \textit{significant transition samples} (STS) by analyzing consistent performance transitions among LLMs of the same architecture but varying parameter scales. These samples enable STEM to effectively estimate the capability position of an unknown model. Qwen3 model family is applied to construct the STS pool on six diverse and representative benchmarks. To assess generalizability. Experimental results indicate that STEM reliably captures performance trends, aligns with ground-truth rankings of model capability. These findings highlight STEM as a practical and scalable method for fine-grained, architecture-agnostic evaluation of LLMs.
Authors: Wenqing Wang, Yun Fu
Abstract: Emotion is a critical component of artificial social intelligence. However, while current methods excel in lip synchronization and image quality, they often fail to generate accurate and controllable emotional expressions while preserving the subject's identity. To address this challenge, we introduce RealTalk, a novel framework for synthesizing emotional talking heads with high emotion accuracy, enhanced emotion controllability, and robust identity preservation. RealTalk employs a variational autoencoder (VAE) to generate 3D facial landmarks from driving audio, which are concatenated with emotion-label embeddings using a ResNet-based landmark deformation model (LDM) to produce emotional landmarks. These landmarks and facial blendshape coefficients jointly condition a novel tri-plane attention Neural Radiance Field (NeRF) to synthesize highly realistic emotional talking heads. Extensive experiments demonstrate that RealTalk outperforms existing methods in emotion accuracy, controllability, and identity preservation, advancing the development of socially intelligent AI systems.
Authors: Gokul Puthumanaillam, Aditya Penumarti, Manav Vora, Paulo Padrao, Jose Fuentes, Leonardo Bobadilla, Jane Shin, Melkior Ornik
Abstract: Robots equipped with rich sensor suites can localize reliably in partially-observable environments, but powering every sensor continuously is wasteful and often infeasible. Belief-space planners address this by propagating pose-belief covariance through analytic models and switching sensors heuristically--a brittle, runtime-expensive approach. Data-driven approaches--including diffusion models--learn multi-modal trajectories from demonstrations, but presuppose an accurate, always-on state estimate. We address the largely open problem: for a given task in a mapped environment, which \textit{minimal sensor subset} must be active at each location to maintain state uncertainty \textit{just low enough} to complete the task? Our key insight is that when a diffusion planner is explicitly conditioned on a pose-belief raster and a sensor mask, the spread of its denoising trajectories yields a calibrated, differentiable proxy for the expected localisation error. Building on this insight, we present Belief-Conditioned One-Step Diffusion (B-COD), the first planner that, in a 10 ms forward pass, returns a short-horizon trajectory, per-waypoint aleatoric variances, and a proxy for localisation error--eliminating external covariance rollouts. We show that this single proxy suffices for a soft-actor-critic to choose sensors online, optimising energy while bounding pose-covariance growth. We deploy B-COD in real-time marine trials on an unmanned surface vehicle and show that it reduces sensing energy consumption while matching the goal-reach performance of an always-on baseline.
Authors: ChangJae Lee, Heecheol Yang, Jonghak Choi
Abstract: Forecasting from atmospheric soundings is a fundamental task in operational meteorology, often requiring structured visual reasoning over Skew-T log-P diagrams by human forecasters. While recent advances in Vision-Language Models (VLMs) have shown promise in other scientific domains, their application to meteorological diagram interpretation remains largely unexplored. In this study, we present a lightweight AI assistant that interprets Skew-T diagrams using a small language model (LM) and a small VLM fine-tuned to emulate human forecasters. Using a curriculum learning framework, we first train the models to identify key atmospheric features from diagrams through visual question answering, followed by chain-of-thought reasoning tasks that estimate precipitation probability based on the derived visual groundings. Model inputs include either textual summaries or generated Skew-T diagrams derived from operational Numerical Weather Prediction (NWP) forecasts, paired with three-hour precipitation observations from South Korea's Auto Weather Stations network. Evaluation results demonstrate that the fine-tuned VLM achieves skill comparable to an operational NWP model, despite relying solely on static atmospheric profiles. Ablation studies reveal that visual grounding and reasoning supervision are critical for performance, while attention map analysis confirms that the model learns to focus on relevant meteorological features. These findings highlight the potential of compact, interpretable multimodal models to support weather forecasting tasks. The approach offers a computationally efficient alternative to large-scale systems, and future work could extend it to more complex applications.
Authors: Mauro Belgiovine, Suyash Pradhan, Johannes Lange, Michael L\"ohning, Kaushik Chowdhury
Abstract: Industry adoption of Artificial Intelligence (AI)-native wireless receivers, or even modular, Machine Learning (ML)-aided wireless signal processing blocks, has been slow. The main concern is the lack of explainability of these trained ML models and the significant risks posed to network functionalities in case of failures, especially since (i) testing on every exhaustive case is infeasible and (ii) the data used for model training may not be available. This paper proposes ATLAS, an AI-guided approach that generates a battery of tests for pre-trained AI-native receiver models and benchmarks the performance against a classical receiver architecture. Using gradient-based optimization, it avoids spanning the exhaustive set of all environment and channel conditions; instead, it generates the next test in an online manner to further probe specific configurations that offer the highest risk of failure. We implement and validate our approach by adopting the well-known DeepRx AI-native receiver model as well as a classical receiver using differentiable tensors in NVIDIA's Sionna environment. ATLAS uncovers specific combinations of mobility, channel delay spread, and noise, where fully and partially trained variants of AI-native DeepRx perform suboptimally compared to the classical receivers. Our proposed method reduces the number of tests required per failure found by 19% compared to grid search for a 3-parameters input optimization problem, demonstrating greater efficiency. In contrast, the computational cost of the grid-based approach scales exponentially with the number of variables, making it increasingly impractical for high-dimensional problems.
Authors: Yize Cai, Baoshen Guo, Flora Salim, Zhiqing Hong
Abstract: As a critical component of Wearable AI, IMU-based Human Activity Recognition (HAR) has attracted increasing attention from both academia and industry in recent years. Although HAR performance has improved considerably in specific scenarios, its generalization capability remains a key barrier to widespread real-world adoption. For example, domain shifts caused by variations in users, sensor positions, or environments can significantly decrease the performance in practice. As a result, in this survey, we explore the rapidly evolving field of IMU-based generalizable HAR, reviewing 229 research papers alongside 25 publicly available datasets to provide a broad and insightful overview. We first present the background and overall framework of IMU-based HAR tasks, as well as the generalization-oriented training settings. Then, we categorize representative methodologies from two perspectives: (i) model-centric approaches, including pre-training method, end-to-end method, and large language model (LLM)-based learning method; and (ii) data-centric approaches, including multi-modal learning and data augmentation techniques. In addition, we summarize widely used datasets in this field, as well as relevant tools and benchmarks. Building on these methodological advances, the broad applicability of IMU-based HAR is also reviewed and discussed. Finally, we discuss persistent challenges (e.g., data scarcity, efficient training, and reliable evaluation) and also outline future directions for HAR, including the adoption of foundation and large language models, physics-informed and context-aware reasoning, generative modeling, and resource-efficient training and inference. The complete list of this survey is available at https://github.com/rh20624/Awesome-IMU-Sensing, which will be updated continuously.
Authors: Jun Liu, Zhenglun Kong, Pu Zhao, Weihao Zeng, Hao Tang, Xuan Shen, Changdi Yang, Wenbin Zhang, Geng Yuan, Wei Niu, Xue Lin, Yanzhi Wang
Abstract: Autonomous driving platforms encounter diverse driving scenarios, each with varying hardware resources and precision requirements. Given the computational limitations of embedded devices, it is crucial to consider computing costs when deploying on target platforms like the NVIDIA\textsuperscript{\textregistered} DRIVE PX 2. Our objective is to customize the semantic segmentation network according to the computing power and specific scenarios of autonomous driving hardware. We implement dynamic adaptability through a three-tier control mechanism -- width multiplier, classifier depth, and classifier kernel -- allowing fine-grained control over model components based on hardware constraints and task requirements. This adaptability facilitates broad model scaling, targeted refinement of the final layers, and scenario-specific optimization of kernel sizes, leading to improved resource allocation and performance. Additionally, we leverage Bayesian Optimization with surrogate modeling to efficiently explore hyperparameter spaces under tight computational budgets. Our approach addresses scenario-specific and task-specific requirements through automatic parameter search, accommodating the unique computational complexity and accuracy needs of autonomous driving. It scales its Multiply-Accumulate Operations (MACs) for Task-Specific Learning Adaptation (TSLA), resulting in alternative configurations tailored to diverse self-driving tasks. These TSLA customizations maximize computational capacity and model accuracy, optimizing hardware utilization.
Authors: Tomer Krichli, Bhiksha Raj, Joseph Keshet
Abstract: Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcription. However, these models are not designed for streaming (online or real-time) transcription, due to limitations in their architecture and training methodology. We propose a method to turn the transformer encoder-decoder model into a low-latency streaming model that is careless about future context. We present an analysis explaining why it is not straightforward to convert an encoder-decoder transformer to a low-latency streaming model. Our proposed method modifies the existing (non-causal) encoder to a causal encoder by fine-tuning both the encoder and decoder using Low-Rank Adaptation (LoRA) and a weakly aligned dataset. We then propose an updated inference mechanism that utilizes the fine-tune causal encoder and decoder to yield greedy and beam-search decoding, and is shown to be locally optimal. Experiments on low-latency chunk sizes (less than 300 msec) show that our fine-tuned model outperforms existing non-fine-tuned streaming approaches in most cases, while using a lower complexity. Additionally, we observe that our training process yields better alignment, enabling a simple method for extracting word-level timestamps. We release our training and inference code, along with the fine-tuned models, to support further research and development in streaming ASR.
Authors: Ahmet H. G\"uzel, Ilija Bogunovic, Jack Parker-Holder
Abstract: Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise due to limited exposure to diverse states. The complexity of visual data introduces additional challenges such as noise, distractions, and spurious correlations, which can misguide the policy and increase the risk of overfitting if the training data is not sufficiently diverse. Indeed, this makes it challenging to leverage vision-based offline data in training robust agents that can generalize to unseen environments. To solve this problem, we propose a simple approach generating additional synthetic training data. We propose a two-step process, first augmenting the originally collected offline data to improve zero-shot generalization by introducing diversity, then using a diffusion model to generate additional data in latent space. We test our method across both continuous action spaces (Visual D4RL) and discrete action spaces (Procgen), demonstrating that it significantly improves generalization without requiring any algorithmic changes to existing model-free offline RL methods. We show that our method not only increases the diversity of the training data but also significantly reduces the generalization gap at test time while maintaining computational efficiency. We believe this approach could fuel additional progress in generating synthetic data to train more general agents in the future.
Authors: Zidong Cui, Pan Zhang, Ying Tang
Abstract: Flow matching has rapidly become a dominant paradigm in classical generative modeling, offering an efficient way to interpolate between two complex distributions. We extend this idea to the quantum realm and introduce Quantum Flow Matching (QFM)-a fully quantum-circuit realization that offers efficient interpolation between two density matrices. QFM offers systematic preparation of density matrices and generation of samples for accurately estimating observables, and can be realized on a quantum computer without the need for costly circuit redesigns. We validate its versatility on a set of applications: (i) generating target states with prescribed magnetization and entanglement entropy, (ii) estimating nonequilibrium free-energy differences to test the quantum Jarzynski equality, and (iii) expediting the study on superdiffusion breakdown. These results position QFM as a unifying and promising framework for generative modeling across quantum systems.
Authors: Yeongwoo Song, Jaeyong Bae, Dong-Kyum Kim, Hawoong Jeong
Abstract: Large language models (LLMs) exhibit impressive in-context learning (ICL) abilities, enabling them to solve wide range of tasks via textual prompts alone. As these capabilities advance, the range of applicable domains continues to expand significantly. However, identifying the precise mechanisms or internal structures within LLMs that allow successful ICL across diverse, distinct classes of tasks remains elusive. Physics-based tasks offer a promising testbed for probing this challenge. Unlike synthetic sequences such as basic arithmetic or symbolic equations, physical systems provide experimentally controllable, real-world data based on structured dynamics grounded in fundamental principles. This makes them particularly suitable for studying the emergent reasoning behaviors of LLMs in a realistic yet tractable setting. Here, we mechanistically investigate the ICL ability of LLMs, especially focusing on their ability to reason about physics. Using a dynamics forecasting task in physical systems as a proxy, we evaluate whether LLMs can learn physics in context. We first show that the performance of dynamics forecasting in context improves with longer input contexts. To uncover how such capability emerges in LLMs, we analyze the model's residual stream activations using sparse autoencoders (SAEs). Our experiments reveal that the features captured by SAEs correlate with key physical variables, such as energy. These findings demonstrate that meaningful physical concepts are encoded within LLMs during in-context learning. In sum, our work provides a novel case study that broadens our understanding of how LLMs learn in context.
Authors: Xuhui Zhan, Tyler Derr
Abstract: Traditional multimodal learning approaches require expensive alignment pre-training to bridge vision and language modalities, typically projecting visual features into discrete text token spaces. We challenge both fundamental assumptions underlying this paradigm by proposing Inverse-LLaVA, a novel approach that eliminates alignment pre-training entirely while inverting the conventional mapping direction. Rather than projecting visual features to text space, our method maps text embeddings into continuous visual representation space and performs fusion within transformer intermediate layers. Through selective additive components in attention mechanisms, we enable dynamic integration of visual and textual representations without requiring massive image-text alignment datasets. Comprehensive experiments across nine multimodal benchmarks demonstrate nuanced performance trade-offs: Inverse-LLaVA achieves notable improvements on reasoning-intensive and cognitive tasks (MM-VET: +0.2%, VizWiz: +1.8%, ScienceQA: +0.2%, cognitive reasoning: +27.2%), while showing expected decreases in perception tasks requiring memorized visual-text associations (celebrity recognition: -49.5%, OCR: -21.3%). These results provide the first empirical evidence that alignment pre-training is not necessary for effective multimodal learning, particularly for complex reasoning tasks. Our work establishes the feasibility of a new paradigm that reduces computational requirements by 45%, challenges conventional wisdom about modality fusion, and opens new research directions for efficient multimodal architectures that preserve modality-specific characteristics. Our project website with code and additional resources is available at https://inverse-llava.github.io.
Authors: Ratun Rahman, Atit Pokharel, Md Raihan Uddin, Dinh C. Nguyen
Abstract: Quantum federated learning (QFL) is an emerging field that has the potential to revolutionize computation by taking advantage of quantum physics concepts in a distributed machine learning (ML) environment. However, the majority of available quantum simulators are primarily built for general quantum circuit simulation and do not include integrated support for machine learning tasks such as training, evaluation, and iterative optimization. Furthermore, designing and assessing quantum learning algorithms is still a difficult and resource-intensive task. Real-time updates are essential for observing model convergence, debugging quantum circuits, and making conscious choices during training with the use of limited resources. Furthermore, most current simulators fail to support the integration of user-specific data for training purposes, undermining the main purpose of using a simulator. In this study, we introduce SimQFL, a customized simulator that simplifies and accelerates QFL experiments in quantum network applications. SimQFL supports real-time, epoch-wise output development and visualization, allowing researchers to monitor the process of learning across each training round. Furthermore, SimQFL offers an intuitive and visually appealing interface that facilitates ease of use and seamless execution. Users can customize key variables such as the number of epochs, learning rates, number of clients, and quantum hyperparameters such as qubits and quantum layers, making the simulator suitable for various QFL applications. The system gives immediate feedback following each epoch by showing intermediate outcomes and dynamically illustrating learning curves. SimQFL is a practical and interactive platform enabling academics and developers to prototype, analyze, and tune quantum neural networks with greater transparency and control in distributed quantum networks.
Authors: Constantin Ruhdorfer, Matteo Bortoletto, Andreas Bulling
Abstract: Developing collaborative AI hinges on Theory of Mind (ToM) - the ability to reason about the beliefs of others to build and maintain common ground. Existing ToM benchmarks, however, are restricted to passive observer settings or lack an assessment of how agents establish and maintain common ground over time. To address these gaps, we introduce the Yokai Learning Environment (YLE) - a multi-agent reinforcement learning (RL) environment based on the cooperative card game Yokai. In the YLE, agents take turns peeking at hidden cards and moving them to form clusters based on colour. Success requires tracking evolving beliefs, remembering past observations, using hints as grounded communication, and maintaining common ground with teammates. Our evaluation yields two key findings: First, current RL agents struggle to solve the YLE, even when given access to perfect memory. Second, while belief modelling improves performance, agents are still unable to effectively generalise to unseen partners or form accurate beliefs over longer games, exposing a reliance on brittle conventions rather than robust belief tracking. We use the YLE to investigate research questions in belief modelling, memory, partner generalisation, and scaling to higher-order ToM.
Authors: Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao, Ziyi Wang, Chenxiao Yu, Shawn Li, Jie Wang, Xiyang Hu, Yue Zhao
Abstract: Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such hallucinations. However, existing reasoning approaches in LLMs, such as Chain-of-Thought (CoT) and its graph-based variants, operate at the linguistic token level rather than modeling the underlying causal relationships between variables, lacking the ability to represent conditional independencies or satisfy causal identification assumptions. To bridge this gap, we introduce causal-DAG construction and reasoning (CDCR-SFT), a supervised fine-tuning framework that trains LLMs to explicitly construct variable-level directed acyclic graph (DAG) and then perform reasoning over it. Moreover, we present a dataset comprising 25,368 samples (CausalDR), where each sample includes an input question, explicit causal DAG, graph-based reasoning trace, and validated answer. Experiments on four LLMs across eight tasks show that CDCR-SFT improves the causal reasoning capability with the state-of-the-art 95.33% accuracy on CLADDER (surpassing human performance of 94.8% for the first time) and reduces the hallucination on HaluEval with 10% improvements. It demonstrates that explicit causal structure modeling in LLMs can effectively mitigate logical inconsistencies in LLM outputs. Code is available at https://github.com/MrLYG/CDCR-SFT.
Authors: Rahmat K. Adesunkanmi, Ashfaq Khokhar, Goce Trajcevski, Sohail Murad
Abstract: Molecular dynamics simulations (MDS) face challenges, including resource-heavy computations and the need to manually scan outputs to detect "interesting events," such as the formation and persistence of hydrogen bonds between atoms of different molecules. A critical research gap lies in identifying the underlying causes of hydrogen bond formation and separation -understanding which interactions or prior events contribute to their emergence over time. With this challenge in mind, we propose leveraging spatio-temporal data analytics and machine learning models to enhance the detection of these phenomena. In this paper, our approach is inspired by causal modeling and aims to identify the root cause variables of hydrogen bond formation and separation events. Specifically, we treat the separation of hydrogen bonds as an "intervention" occurring and represent the causal structure of the bonding and separation events in the MDS as graphical causal models. These causal models are built using a variational autoencoder-inspired architecture that enables us to infer causal relationships across samples with diverse underlying causal graphs while leveraging shared dynamic information. We further include a step to infer the root causes of changes in the joint distribution of the causal models. By constructing causal models that capture shifts in the conditional distributions of molecular interactions during bond formation or separation, this framework provides a novel perspective on root cause analysis in molecular dynamic systems. We validate the efficacy of our model empirically on the atomic trajectories that used MDS for chiral separation, demonstrating that we can predict many steps in the future and also find the variables driving the observed changes in the system.
Authors: Khai Nguyen
Abstract: Sliced Optimal Transport (SOT) is a rapidly developing branch of optimal transport (OT) that exploits the tractability of one-dimensional OT problems. By combining tools from OT, integral geometry, and computational statistics, SOT enables fast and scalable computation of distances, barycenters, and kernels for probability measures, while retaining rich geometric structure. This paper provides a comprehensive review of SOT, covering its mathematical foundations, methodological advances, computational methods, and applications. We discuss key concepts of OT and one-dimensional OT, the role of tools from integral geometry such as Radon transform in projecting measures, and statistical techniques for estimating sliced distances. The paper further explores recent methodological advances, including non-linear projections, improved Monte Carlo approximations, statistical estimation techniques for one-dimensional optimal transport, weighted slicing techniques, and transportation plan estimation methods. Variational problems, such as minimum sliced Wasserstein estimation, barycenters, gradient flows, kernel constructions, and embeddings are examined alongside extensions to unbalanced, partial, multi-marginal, and Gromov-Wasserstein settings. Applications span machine learning, statistics, computer graphics and computer visions, highlighting SOT's versatility as a practical computational tool. This work will be of interest to researchers and practitioners in machine learning, data sciences, and computational disciplines seeking efficient alternatives to classical OT.
Authors: Seonglae Cho, Zekun Wu, Adriano Koshiyama
Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large activation storage. To address these limitations, we propose CorrSteer, which selects features by correlating sample correctness with SAE activations from generated tokens at inference time. This approach uses only inference-time activations to extract more relevant features, thereby avoiding spurious correlations. It also obtains steering coefficients from average activations, automating the entire pipeline. Our method shows improved task performance on QA, bias mitigation, jailbreaking prevention, and reasoning benchmarks on Gemma 2 2B and LLaMA 3.1 8B, notably achieving a +4.1% improvement in MMLU performance and a +22.9% improvement in HarmBench with only 4000 samples. Selected features demonstrate semantically meaningful patterns aligned with each task's requirements, revealing the underlying capabilities that drive performance. Our work establishes correlationbased selection as an effective and scalable approach for automated SAE steering across language model applications.
Authors: Prabath Abeysekara, Hai Dong
Abstract: We propose a data-driven and context-aware approach to bootstrap trustworthiness of homogeneous Internet of Things (IoT) services in Mobile Edge Computing (MEC) based industrial IoT (IIoT) systems. The proposed approach addresses key limitations in adapting existing trust bootstrapping approaches into MEC-based IIoT systems. These key limitations include, the lack of opportunity for a service consumer to interact with a lesser-known service over a prolonged period of time to get a robust measure of its trustworthiness, inability of service consumers to consistently interact with their peers to receive reliable recommendations of the trustworthiness of a lesser-known service as well as the impact of uneven context parameters in different MEC environments causing uneven trust environments for trust evaluation. In addition, the proposed approach also tackles the problem of data sparsity via enabling knowledge sharing among different MEC environments within a given MEC topology. To verify the effectiveness of the proposed approach, we carried out a comprehensive evaluation on two real-world datasets suitably adjusted to exhibit the context-dependent trust information accumulated in MEC environments within a given MEC topology. The experimental results affirmed the effectiveness of our approach and its suitability to bootstrap trustworthiness of services in MEC-based IIoT systems.
Authors: Qingyan Meng, Mingqing Xiao, Zhengyu Ma, Huihui Zhou, Yonghong Tian, Zhouchen Lin
Abstract: Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging because of the non-differentiable spike generation function. To address this issue, the commonly used approach is to adopt the backpropagation through time framework, while assigning the gradient of the non-differentiable function with some surrogates. Similarly, Binary Neural Networks (BNNs) also face the non-differentiability problem and rely on approximating gradients. However, the deep relationship between these two fields and how their training techniques can benefit each other has not been systematically researched. Furthermore, training binary-weight SNNs is even more difficult. In this work, we present a novel perspective on the dynamics of SNNs and their close connection to BNNs through an analysis of the backpropagation process. We demonstrate that training a feedforward SNN can be viewed as training a self-ensemble of a binary-activation neural network with noise injection. Drawing from this new understanding of SNN dynamics, we introduce the Self-Ensemble Inspired training method for (Binary-Weight) SNNs (SEI-BWSNN), which achieves high-performance results with low latency even for the case of the 1-bit weights. Specifically, we leverage a structure of multiple shortcuts and a knowledge distillation-based training technique to improve the training of (binary-weight) SNNs. Notably, by binarizing FFN layers in a Transformer architecture, our approach achieves 82.52% accuracy on ImageNet with only 2 time steps, indicating the effectiveness of our methodology and the potential of binary-weight SNNs.
Authors: Zhongqin Wang, J. Andrew Zhang, Kai Wu, Min Xu, Y. Jay Guo
Abstract: Integrated Sensing and Communication (ISAC) is a key enabler for next-generation wireless systems. However, real-world deployment is often limited to low-cost, single-antenna transceivers. In such bistatic Single-Input Single-Output (SISO) setup, clock asynchrony introduces random phase offsets in Channel State Information (CSI), which cannot be mitigated using conventional multi-antenna methods. This work proposes WiDFS 3.0, a lightweight bistatic SISO sensing framework that enables accurate delay and Doppler estimation from distorted CSI by effectively suppressing Doppler mirroring ambiguity. It operates with only a single antenna at both the transmitter and receiver, making it suitable for low-complexity deployments. We propose a self-referencing cross-correlation (SRCC) method for SISO random phase removal and employ delay-domain beamforming to resolve Doppler ambiguity. The resulting unambiguous delay-Doppler-time features enable robust sensing with compact neural networks. Extensive experiments show that WiDFS 3.0 achieves accurate parameter estimation, with performance comparable to or even surpassing that of prior multi-antenna methods, especially in delay estimation. Validated under single- and multi-target scenarios, the extracted ambiguity-resolved features show strong sensing accuracy and generalization. For example, when deployed on the embedded-friendly MobileViT-XXS with only 1.3M parameters, WiDFS 3.0 consistently outperforms conventional features such as CSI amplitude, mirrored Doppler, and multi-receiver aggregated Doppler.
Authors: Ming Li, Zihuai He, Min Zhang, Xiaowei Zhan, Changshuai Wei, Robert C Elston, Qing Lu
Abstract: With the advance of high-throughput sequencing technologies, it has become feasible to investigate the influence of the entire spectrum of sequencing variations on complex human diseases. Although association studies utilizing the new sequencing technologies hold great promise to unravel novel genetic variants, especially rare genetic variants that contribute to human diseases, the statistical analysis of high-dimensional sequencing data remains a challenge. Advanced analytical methods are in great need to facilitate high-dimensional sequencing data analyses. In this article, we propose a generalized genetic random field (GGRF) method for association analyses of sequencing data. Like other similarity-based methods (e.g., SIMreg and SKAT), the new method has the advantages of avoiding the need to specify thresholds for rare variants and allowing for testing multiple variants acting in different directions and magnitude of effects. The method is built on the generalized estimating equation framework and thus accommodates a variety of disease phenotypes (e.g., quantitative and binary phenotypes). Moreover, it has a nice asymptotic property, and can be applied to small-scale sequencing data without need for small-sample adjustment. Through simulations, we demonstrate that the proposed GGRF attains an improved or comparable power over a commonly used method, SKAT, under various disease scenarios, especially when rare variants play a significant role in disease etiology. We further illustrate GGRF with an application to a real dataset from the Dallas Heart Study. By using GGRF, we were able to detect the association of two candidate genes, ANGPTL3 and ANGPTL4, with serum triglyceride.
Authors: Bastian Brandst\"otter, Erich Kobler
Abstract: Contrast-enhanced (CE) T1-weighted MRI is central to neuro-oncologic diagnosis but requires gadolinium-based agents, which add cost and scan time, raise environmental concerns, and may pose risks to patients. In this work, we propose a two-stage Posterior-Mean Rectified Flow (PMRF) pipeline for synthesizing volumetric CE brain MRI from non-contrast inputs. First, a patch-based 3D U-Net predicts the voxel-wise posterior mean (minimizing MSE). Then, this initial estimate is refined by a time-conditioned 3D rectified flow to incorporate realistic textures without compromising structural fidelity. We train this model on a multi-institutional collection of paired pre- and post-contrast T1w volumes (BraTS 2023-2025). On a held-out test set of 360 diverse volumes, our best refined outputs achieve an axial FID of $12.46$ and KID of $0.007$ ($\sim 68.7\%$ lower FID than the posterior mean) while maintaining low volumetric MSE of $0.057$ ($\sim 27\%$ higher than the posterior mean). Qualitative comparisons confirm that our method restores lesion margins and vascular details realistically, effectively navigating the perception-distortion trade-off for clinical deployment.
Authors: Hengnian Gu, Zhifu Chen, Yuxin Chen, Jin Peng Zhou, Dongdai Zhou
Abstract: Cognitive structure is a student's subjective organization of an objective knowledge system, reflected in the psychological construction of concepts and their relations. However, cognitive structure assessment remains a long-standing challenge in student modeling and psychometrics, persisting as a foundational yet largely unassessable concept in educational practice. This paper introduces a novel framework, Cognitive Structure Generation (CSG), in which we first pretrain a Cognitive Structure Diffusion Probabilistic Model (CSDPM) to generate students' cognitive structures from educational priors, and then further optimize its generative process as a policy with hierarchical reward signals via reinforcement learning to align with genuine cognitive development levels during students' learning processes. Experimental results on four popular real-world education datasets show that cognitive structures generated by CSG offer more comprehensive and effective representations for student modeling, substantially improving performance on KT and CD tasks while enhancing interpretability.
Authors: Dmitry Belousov, Yury Yanovich
Abstract: Non-fungible tokens (NFTs) have become a significant digital asset class, each uniquely representing virtual entities such as artworks. These tokens are stored in collections within smart contracts and are actively traded across platforms on Ethereum, Bitcoin, and Solana blockchains. The value of NFTs is closely tied to their distinctive characteristics that define rarity, leading to a growing interest in quantifying rarity within both industry and academia. While there are existing rarity meters for assessing NFT rarity, comparing them can be challenging without direct access to the underlying collection data. The Rating over all Rarities (ROAR) benchmark addresses this challenge by providing a standardized framework for evaluating NFT rarity. This paper explores a dimension reduction approach to rarity design, introducing new performance measures and meters, and evaluates them using the ROAR benchmark. Our contributions to the rarity meter design issue include developing an optimal rarity meter design using non-metric weighted multidimensional scaling, introducing Dissimilarity in Trades (DIT) as a performance measure inspired by dimension reduction techniques, and unveiling the non-interpretable rarity meter DIT, which demonstrates superior performance compared to existing methods.
Authors: Haruka Ezoe, Hiroki Matsumoto, Ryohei Hisano
Abstract: Dynamic relational structures play a central role in many AI tasks, but their evolving nature presents challenges for consistent and interpretable representation. A common approach is to learn time-varying node embeddings, whose effectiveness depends on satisfying key stability properties. In this paper, we propose Unfolded Laplacian Spectral Embedding, a new method that extends the Unfolded Adjacency Spectral Embedding framework to normalized Laplacians while preserving both cross-sectional and longitudinal stability. We provide formal proof that our method satisfies these stability conditions. In addition, as a bonus of using the Laplacian matrix, we establish a new Cheeger-style inequality that connects the embeddings to the conductance of the underlying dynamic graphs. Empirical evaluations on synthetic and real-world datasets support our theoretical findings and demonstrate the strong performance of our method. These results establish a principled and stable framework for dynamic network representation grounded in spectral graph theory.
Authors: Johann Licher, Max Bartholdt, Henrik Krauss, Tim-Lukas Habich, Thomas Seel, Moritz Schappler
Abstract: Dynamic control of soft continuum robots (SCRs) holds great potential for expanding their applications, but remains a challenging problem due to the high computational demands of accurate dynamic models. While data-driven approaches like Koopman-operator-based methods have been proposed, they typically lack adaptability and cannot capture the full robot shape, limiting their applicability. This work introduces a real-time-capable nonlinear model-predictive control (MPC) framework for SCRs based on a domain-decoupled physics-informed neural network (DD-PINN) with adaptable bending stiffness. The DD-PINN serves as a surrogate for the dynamic Cosserat rod model with a speed-up factor of 44000. It is also used within an unscented Kalman filter for estimating the model states and bending compliance from end-effector position measurements. We implement a nonlinear evolutionary MPC running at 70 Hz on the GPU. In simulation, it demonstrates accurate tracking of dynamic trajectories and setpoint control with end-effector position errors below 3 mm (2.3% of the actuator's length). In real-world experiments, the controller achieves similar accuracy and accelerations up to 3.55 m/s2.
Authors: Xingshan Zeng, Weiwen Liu, Lingzhi Wang, Liangyou Li, Fei Mi, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu
Abstract: Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions, often involving complex function calls and dynamic user-agent exchanges. Existing simulation-based data generation methods for such scenarios rely heavily on costly autoregressive interactions between multiple LLM agents, thereby limiting real-world performance of agentic tasks. In this paper, we propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues. ToolACE-MT generates full conversational trajectories through three stages: coarse-grained initialization, iterative refinement, and offline verification. The initialization phase builds a structurally complete yet semantically coarse dialogue skeleton; the iterative refinement phase introduces realistic complexities and continued refinement via mask-and-fill operations; and the offline verification phase ensures correctness and coherence via rule- and model-based checks. Experiments demonstrate that ToolACE-MT enables efficient, effective and generalizable agentic data generation, offering a new paradigm for high-quality data construction in tool-augmented LLM scenarios.
Authors: Dongjae Jeon, Taeheon Kim, Seongwon Cho, Minhyuk Seo, Jonghyun Choi
Abstract: Test-time Adaptation (TTA) poses a challenge, requiring models to dynamically adapt and perform optimally on shifting target domains. This task is particularly emphasized in real-world driving scenes, where weather domain shifts occur frequently. To address such dynamic changes, our proposed method, TTA-DAME, leverages source domain data augmentation into target domains. Additionally, we introduce a domain discriminator and a specialized domain detector to mitigate drastic domain shifts, especially from daytime to nighttime conditions. To further improve adaptability, we train multiple detectors and consolidate their predictions through Non-Maximum Suppression (NMS). Our empirical validation demonstrates the effectiveness of our method, showing significant performance enhancements on the SHIFT Benchmark.
Authors: Yuanxin Wei, Lansong Diao, Bujiao Chen, Shenggan Cheng, Zhengping Qian, Wenyuan Yu, Nong Xiao, Wei Lin, Jiangsu Du
Abstract: Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality video generation. However, their multi-step iterative denoising process incurs high computational cost and inference latency. Caching, a widely adopted optimization method in DiT models, leverages the redundancy in the diffusion process to skip computations in different granularities (e.g., step, cfg, block). Nevertheless, existing caching methods are limited to single-granularity strategies, struggling to balance generation quality and inference speed in a flexible manner. In this work, we propose MixCache, a training-free caching-based framework for efficient video DiT inference. It first distinguishes the interference and boundary between different caching strategies, and then introduces a context-aware cache triggering strategy to determine when caching should be enabled, along with an adaptive hybrid cache decision strategy for dynamically selecting the optimal caching granularity. Extensive experiments on diverse models demonstrate that, MixCache can significantly accelerate video generation (e.g., 1.94$\times$ speedup on Wan 14B, 1.97$\times$ speedup on HunyuanVideo) while delivering both superior generation quality and inference efficiency compared to baseline methods.
Authors: Taeheon Kim, San Kim, Minhyuk Seo, Dongjae Jeon, Wonje Jeong, Jonghyun Choi
Abstract: Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen classes. CIR assumes that we can easily access abundant unlabeled data from external sources, such as the Internet. Therefore, we propose two components that efficiently use the unlabeled data to ensure the high stability and the plasticity of models trained in CIR setup. First, we introduce multi-level knowledge distillation (MLKD) that distills knowledge from multiple previous models across multiple perspectives, including features and logits, so the model can maintain much various previous knowledge. Moreover, we implement dynamic self-supervised loss (SSL) to utilize the unlabeled data that accelerates the learning of new classes, while dynamic weighting of SSL keeps the focus of training to the primary task. Both of our proposed components significantly improve the performance in CIR setup, achieving 2nd place in the CVPR 5th CLVISION Challenge.
Authors: Jaeung Lee, Suhyeon Yu, Yurim Jang, Simon S. Woo, Jaemin Jo
Abstract: Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe that researchers in this rapidly emerging field face challenges in analyzing and understanding the behavior of different MU methods, especially in terms of three fundamental principles in MU: accuracy, efficiency, and privacy. Consequently, they often rely on aggregate metrics and ad-hoc evaluations, making it difficult to accurately assess the trade-offs between methods. To fill this gap, we introduce a visual analytics system, Unlearning Comparator, designed to facilitate the systematic evaluation of MU methods. Our system supports two important tasks in the evaluation process: model comparison and attack simulation. First, it allows the user to compare the behaviors of two models, such as a model generated by a certain method and a retrained baseline, at class-, instance-, and layer-levels to better understand the changes made after unlearning. Second, our system simulates membership inference attacks (MIAs) to evaluate the privacy of a method, where an attacker attempts to determine whether specific data samples were part of the original training set. We evaluate our system through a case study visually analyzing prominent MU methods and demonstrate that it helps the user not only understand model behaviors but also gain insights that can inform the improvement of MU methods.
Authors: Sebastian Hirt, Lukas Theiner, Maik Pfefferkorn, Rolf Findeisen
Abstract: Many control problems require repeated tuning and adaptation of controllers across distinct closed-loop tasks, where data efficiency and adaptability are critical. We propose a hierarchical Bayesian optimization (BO) framework that is tailored to efficient controller parameter learning in sequential decision-making and control scenarios for distinct tasks. Instead of treating the closed-loop cost as a black-box, our method exploits structural knowledge of the underlying problem, consisting of a dynamical system, a control law, and an associated closed-loop cost function. We construct a hierarchical surrogate model using Gaussian processes that capture the closed-loop state evolution under different parameterizations, while the task-specific weighting and accumulation into the closed-loop cost are computed exactly via known closed-form expressions. This allows knowledge transfer and enhanced data efficiency between different closed-loop tasks. The proposed framework retains sublinear regret guarantees on par with standard black-box BO, while enabling multi-task or transfer learning. Simulation experiments with model predictive control demonstrate substantial benefits in both sample efficiency and adaptability when compared to purely black-box BO approaches.
Authors: Theodoros Bermperidis, Joe Vero, Elizabeth B Torres
Abstract: There is a tradeoff between attaining statistical power with large, difficult to gather data sets, and producing highly scalable assays that register brief data samples. Often, as grand-averaging techniques a priori assume normally-distributed parameters and linear, stationary processes in biorhythmic, time series data, important information is lost, averaged out as gross data. We developed an affective computing platform that enables taking brief data samples while maintaining personalized statistical power. This is achieved by combining a new data type derived from the micropeaks present in time series data registered from brief (5-second-long) face videos with recent advances in AI-driven face-grid estimation methods. By adopting geometric and nonlinear dynamical systems approaches to analyze the kinematics, especially the speed data, the new methods capture all facial micropeaks. These include as well the nuances of different affective micro expressions. We offer new ways to differentiate dynamical and geometric patterns present in autistic individuals from those found more commonly in neurotypical development.
Authors: Chenyang Wang, Roger Olsson, Stefan Forsstr\"om, Qing He
Abstract: Empowered by deep learning, semantic communication marks a paradigm shift from transmitting raw data to conveying task-relevant meaning, enabling more efficient and intelligent wireless systems. In this study, we explore a deep learning-based task-oriented communication framework that jointly considers classification performance, computational latency, and communication cost. We adopt ResNets-based models and evaluate them on the CIFAR-10 and CIFAR-100 datasets to simulate real-world classification tasks in wireless environments. We partition the model at various points to simulate split inference across a wireless channel. By varying the split location and the size of the transmitted semantic feature vector, we systematically analyze the trade-offs between task accuracy and resource efficiency. Experimental results show that, with appropriate model partitioning and semantic feature compression, the system can retain over 85\% of baseline accuracy while significantly reducing both computational load and communication overhead.
Authors: Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, Xijun Gu, Peiyi Tu, Jiaxin Liu, Wenyu Chen, Yuzhuo Fu, Zhiting Fan, Yanmei Gu, Yuanyuan Wang, Zhengkai Yang, Jianguo Li, Junbo Zhao
Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such as passing unit tests in code generation or matching correct answers in mathematical reasoning. While effective, this requirement largely confines RLVR to domains with automatically checkable outcomes. To overcome this, we extend the RLVR paradigm to open-ended tasks by integrating rubric-based rewards, where carefully designed rubrics serve as structured, model-interpretable criteria for automatic scoring of subjective outputs. We construct, to our knowledge, the largest rubric reward system to date, with over 10,000 rubrics from humans, LLMs, or a hybrid human-LLM collaboration. Implementing rubric-based RL is challenging; we tackle these issues with a clear framework and present an open-sourced Qwen-30B-A3B model with notable gains: 1) With only 5K+ samples, our system improves by +5.2% on open-ended benchmarks (especially humanities), outperforming a 671B DeepSeek-V3 model by +2.4%, while preserving general and reasoning abilities. 2) Our method provides fine-grained stylistic control, using rubrics as anchors to mitigate the "AI-like" tone and produce more human-like, expressive responses. We share key lessons in rubric construction, data selection, and training, and discuss limitations and future releases.
Authors: Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy
Abstract: We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 -> 3.03, 2.57 ->2.44, 2.09 -> 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models will be released.
Authors: Friedhelm Hamann, Emil Mededovic, Fabian G\"ulhan, Yuli Wu, Johannes Stegmaier, Jing He, Yiqing Wang, Kexin Zhang, Lingling Li, Licheng Jiao, Mengru Ma, Hongxiang Huang, Yuhao Yan, Hongwei Ren, Xiaopeng Lin, Yulong Huang, Bojun Cheng, Se Hyun Lee, Gyu Sung Ham, Kanghan Oh, Gi Hyun Lim, Boxuan Yang, Bowen Du, Guillermo Gallego
Abstract: We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. We provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md
URLs: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md
Authors: Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong, Guoqiang Yang
Abstract: The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the data sent from the client to the untrusted cloud server often contains sensitive information. Existing CNN privacy-preserving schemes, while effective in ensuring data confidentiality through homomorphic encryption and secret sharing, face efficiency bottlenecks, particularly in convolution operations. In this paper, we propose a novel verifiable privacy-preserving scheme tailored for CNN convolutional layers. Our scheme enables efficient encryption and decryption, allowing resource-constrained clients to securely offload computations to the untrusted cloud server. Additionally, we present a verification mechanism capable of detecting the correctness of the results with a success probability of at least $1-\frac{1}{\left|Z\right|}$. Extensive experiments conducted on 10 datasets and various CNN models demonstrate that our scheme achieves speedups ranging $26 \times$ ~ $\ 87\times$ compared to the original plaintext model while maintaining accuracy.
Authors: Hiroshi Horii (SU), Sothea Has (KHM)
Abstract: Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (ML), can be recast through a continuous-time approximation as a Fokker-Planck equation for Langevin dynamics, a viewpoint that has motivated many theoretical studies. Within this framework, we study the relationship between the quasi-stationary distribution derived from this equation and the initial distribution through the Kullback-Leibler (KL) divergence. As the quasi-steady-state distribution depends on the expected cost function, the KL divergence eventually reveals the connection between the expected cost function and the initialization distribution. By applying this to deep neural network models (DNNs), we can express the bounds of the expected loss function explicitly in terms of the initialization parameters. Then, by minimizing this bound, we obtain an optimal condition of the initialization variance in the Gaussian case. This result provides a concrete mathematical criterion, rather than a heuristic approach, to select the scale of weight initialization in DNNs. In addition, we experimentally confirm our theoretical results by using the classical SGD to train fully connected neural networks on the MNIST and Fashion-MNIST datasets. The result shows that if the variance of the initialization distribution satisfies our theoretical optimal condition, then the corresponding DNN model always achieves lower final training loss and higher test accuracy than the conventional He-normal initialization. Our work thus supplies a mathematically grounded indicator that guides the choice of initialization variance and clarifies its physical meaning of the dynamics of parameters in DNNs.
Authors: Artem Pshenitsyn, Aleksandr Panov, Alexey Skrynnik
Abstract: Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with challenging coordination and planning tasks. We introduce CAMAR, a new MARL benchmark designed explicitly for multi-agent pathfinding in environments with continuous actions. CAMAR supports cooperative and competitive interactions between agents and runs efficiently at up to 100,000 environment steps per second. We also propose a three-tier evaluation protocol to better track algorithmic progress and enable deeper analysis of performance. In addition, CAMAR allows the integration of classical planning methods such as RRT and RRT* into MARL pipelines. We use them as standalone baselines and combine RRT* with popular MARL algorithms to create hybrid approaches. We provide a suite of test scenarios and benchmarking tools to ensure reproducibility and fair comparison. Experiments show that CAMAR presents a challenging and realistic testbed for the MARL community.
Authors: David Hirnschall, Robert Bajons
Abstract: We present a novel framework for predicting next actions in soccer possessions by leveraging path signatures to encode their complex spatio-temporal structure. Unlike existing approaches, we do not rely on fixed historical windows and handcrafted features, but rather encode the entire recent possession, thereby avoiding the inclusion of potentially irrelevant or misleading historical information. Path signatures naturally capture the order and interaction of events, providing a mathematically grounded feature encoding for variable-length time series of irregular sampling frequencies without the necessity for manual feature engineering. Our proposed approach outperforms a transformer-based benchmark across various loss metrics and considerably reduces computational cost. Building on these results, we introduce a new possession evaluation metric based on well-established frameworks in soccer analytics, incorporating both predicted action type probabilities and action location. Our metric shows greater reliability than existing metrics in domain-specific comparisons. Finally, we validate our approach through a detailed analysis of the 2017/18 Premier League season and discuss further applications and future extensions.
Authors: Michael Deistler, Jan Boelts, Peter Steinbach, Guy Moss, Thomas Moreau, Manuel Gloeckler, Pedro L. C. Rodrigues, Julia Linhart, Janne K. Lappalainen, Benjamin Kurt Miller, Pedro J. Gon\c{c}alves, Jan-Matthis Lueckmann, Cornelius Schr\"oder, Jakob H. Macke
Abstract: A central challenge in many areas of science and engineering is to identify model parameters that are consistent with prior knowledge and empirical data. Bayesian inference offers a principled framework for this task, but can be computationally prohibitive when models are defined by stochastic simulators. Simulation-based Inference (SBI) is a suite of methods developed to overcome this limitation, which has enabled scientific discoveries in fields such as particle physics, astrophysics, and neuroscience. The core idea of SBI is to train neural networks on data generated by a simulator, without requiring access to likelihood evaluations. Once trained, inference is amortized: The neural network can rapidly perform Bayesian inference on empirical observations without requiring additional training or simulations. In this tutorial, we provide a practical guide for practitioners aiming to apply SBI methods. We outline a structured SBI workflow and offer practical guidelines and diagnostic tools for every stage of the process -- from setting up the simulator and prior, choosing and training inference networks, to performing inference and validating the results. We illustrate these steps through examples from astrophysics, psychophysics, and neuroscience. This tutorial empowers researchers to apply state-of-the-art SBI methods, facilitating efficient parameter inference for scientific discovery.
Authors: Kyriaki-Margarita Bintsi, Ya\"el Balbastre, Jingjing Wu, Julia F. Lehman, Suzanne N. Haber, Anastasia Yendiki
Abstract: Anatomic tracer studies are critical for validating and improving diffusion MRI (dMRI) tractography. However, large-scale analysis of data from such studies is hampered by the labor-intensive process of annotating fiber bundles manually on histological slides. Existing automated methods often miss sparse bundles or require complex post-processing across consecutive sections, limiting their flexibility and generalizability. We present a streamlined, fully automated framework for fiber bundle segmentation in macaque tracer data, based on a U-Net architecture with large patch sizes, foreground aware sampling, and semisupervised pre-training. Our approach eliminates common errors such as mislabeling terminals as bundles, improves detection of sparse bundles by over 20% and reduces the False Discovery Rate (FDR) by 40% compared to the state-of-the-art, all while enabling analysis of standalone slices. This new framework will facilitate the automated analysis of anatomic tracing data at a large scale, generating more ground-truth data that can be used to validate and optimize dMRI tractography methods.
Authors: Mary Tonwe
Abstract: Public service systems in many African regions suffer from delayed emergency response and spatial inequity, causing avoidable suffering. This paper introduces OPTIC-ER, a reinforcement learning (RL) framework for real-time, adaptive, and equitable emergency response. OPTIC-ER uses an attention-guided actor-critic architecture to manage the complexity of dispatch environments. Its key innovations are a Context-Rich State Vector, encoding action sub-optimality, and a Precision Reward Function, which penalizes inefficiency. Training occurs in a high-fidelity simulation using real data from Rivers State, Nigeria, accelerated by a precomputed Travel Time Atlas. The system is built on the TALS framework (Thin computing, Adaptability, Low-cost, Scalability) for deployment in low-resource settings. In evaluations on 500 unseen incidents, OPTIC-ER achieved a 100.00% optimality rate with negligible inefficiency, confirming its robustness and generalization. Beyond dispatch, the system generates Infrastructure Deficiency Maps and Equity Monitoring Dashboards to guide proactive governance and data-informed development. This work presents a validated blueprint for AI-augmented public services, showing how context-aware RL can bridge the gap between algorithmic decision-making and measurable human impact.
Authors: Michael Mayer, Mario V. W\"uthrich
Abstract: Originally introduced in cooperative game theory, Shapley values have become a very popular tool to explain machine learning predictions. Based on Shapley's fairness axioms, every input (feature component) gets a credit how it contributes to an output (prediction). These credits are then used to explain the prediction. The only limitation in computing the Shapley values (credits) for many different predictions is of computational nature. There are two popular sampling approximations, sampling KernelSHAP and sampling PermutationSHAP. Our first novel contributions are asymptotic normality results for these sampling approximations. Next, we show that the paired-sampling approaches provide exact results in case of interactions being of maximal order two. Furthermore, the paired-sampling PermutationSHAP possesses the additive recovery property, whereas its kernel counterpart does not.
Authors: Branislav Gerazov, Marcello Politi, S\'ebastien Brati\`eres
Abstract: We explore the performance of several state-of-the-art automatic speech recognition (ASR) models on a large-scale Arabic speech dataset, the SADA (Saudi Audio Dataset for Arabic), which contains 668 hours of high-quality audio from Saudi television shows. The dataset includes multiple dialects and environments, specifically a noisy subset that makes it particularly challenging for ASR. We evaluate the performance of the models on the SADA test set, and we explore the impact of fine-tuning, language models, as well as noise and denoising on their performance. We find that the best performing model is the MMS 1B model finetuned on SADA with a 4-gram language model that achieves a WER of 40.9\% and a CER of 17.6\% on the SADA test clean set.
Authors: Jose L. Bonilla, Krzysztof M. Graczyk, Artur M. Ankowski, Rwik Dharmapal Banerjee, Beata E. Kowal, Hemant Prasad, Jan T. Sobczyk
Abstract: We utilize transfer learning to extrapolate the physics knowledge encoded in a Generative Adversarial Network (GAN) model trained on synthetic charged-current (CC) neutrino-carbon inclusive scattering data. This base model is adapted to generate CC inclusive scattering events (lepton kinematics only) for neutrino-argon and antineutrino-carbon interactions. Furthermore, we assess the effectiveness of transfer learning in re-optimizing a custom model when new data comes from a different neutrino-nucleus interaction model. Our results demonstrate that transfer learning significantly outperforms training generative models from scratch. To study this, we consider two training data sets: one with 10,000 and another with 100,000 events. The models obtained via transfer learning perform well even with smaller training data. The proposed method provides a promising approach for constructing neutrino scattering event generators in scenarios where experimental data is sparse.
Authors: Jiawen Xu, Odej Kao
Abstract: Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent approaches have addressed these problems, particularly OSR, by heuristically promoting feature diversity, few studies have directly examined the role that feature diversity plays in tackling them. In this work, we provide empirical evidence that enhancing feature diversity improves the recognition of open set samples. Moreover, increased feature diversity also facilitates both the retention of previously learned data and the integration of new data in continual learning. We hope our findings can inspire further research into both practical methods and theoretical understanding in these domains.
Authors: Seongeun Ryu, Yunyong Ko, Sang-Wook Kim
Abstract: Personalized news recommendation aims to deliver news articles aligned with users' interests, serving as a key solution to alleviate the problem of information overload on online news platforms. While prior work has improved interest matching through refined representations of news and users, the following time-related challenges remain underexplored: (C1) leveraging the age of clicked news to infer users' interest persistence, and (C2) modeling the varying lifetime of news across topics and users. To jointly address these challenges, we propose a novel Lifetime-aware Interest Matching framework for nEws recommendation, named LIME, which incorporates three key strategies: (1) User-Topic lifetime-aware age representation to capture the relative age of news with respect to a user-topic pair, (2) Candidate-aware lifetime attention for generating temporally aligned user representation, and (3) Freshness-guided interest refinement for prioritizing valid candidate news at prediction time. Extensive experiments on two real-world datasets demonstrate that LIME consistently outperforms a wide range of state-of-the-art news recommendation methods, and its model agnostic strategies significantly improve recommendation accuracy.
Authors: Tanjim Islam Riju, Shuchismita Anwar, Saman Sarker Joy, Farig Sadeque, Swakkhar Shatabda
Abstract: We propose a two-stage multimodal framework that enhances disease classification and region-aware radiology report generation from chest X-rays, leveraging the MIMIC-Eye dataset. In the first stage, we introduce a gaze-guided contrastive learning architecture for disease classification. It integrates visual features, clinical labels, bounding boxes, and radiologist eye-tracking signals and is equipped with a novel multi-term gaze-attention loss combining MSE, KL divergence, correlation, and center-of-mass alignment. Incorporating fixations improves F1 score from 0.597 to 0.631 (+5.70%) and AUC from 0.821 to 0.849 (+3.41%), while also improving precision and recall, highlighting the effectiveness of gaze-informed attention supervision. In the second stage, we present a modular report generation pipeline that extracts confidence-weighted diagnostic keywords, maps them to anatomical regions using a curated dictionary constructed from domain-specific priors, and generates region-aligned sentences via structured prompts. This pipeline improves report quality as measured by clinical keyword recall and ROUGE overlap. Our results demonstrate that integrating gaze data improves both classification performance and the interpretability of generated medical reports.
Authors: Sara Karimi, Nikolaos N. Vlassis
Abstract: Programmable structures are systems whose undeformed geometries and material property distributions are deliberately designed to achieve prescribed deformed configurations under specific loading conditions. Inflatable structures are a prominent example, using internal pressurization to realize large, nonlinear deformations in applications ranging from soft robotics and deployable aerospace systems to biomedical devices and adaptive architecture. We present a generative design framework based on denoising diffusion probabilistic models (DDPMs) for the inverse design of elastic structures undergoing large, nonlinear deformations under pressure-driven actuation. The method formulates the inverse design as a conditional generation task, using geometric descriptors of target deformed states as inputs and outputting image-based representations of the undeformed configuration. Representing these configurations as simple images is achieved by establishing a pre- and postprocessing pipeline that involves a fixed image processing, simulation setup, and descriptor extraction methods. Numerical experiments with scalar and higher-dimensional descriptors show that the framework can quickly produce diverse undeformed configurations that achieve the desired deformations when inflated, enabling parallel exploration of viable design candidates while accommodating complex constraints.
Authors: Dara Bahri, John Wieting
Abstract: Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded by the language model and the set of input prompts. However, entropy can be quite limited in practice, especially for models that are post-trained, for example via instruction tuning or reinforcement learning from human feedback (RLHF), which makes detection based on watermarking alone challenging. In this work, we investigate whether detection can be improved by combining watermark detectors with non-watermark ones. We explore a number of hybrid schemes that combine the two, observing performance gains over either class of detector under a wide range of experimental conditions.
Authors: Pranjal Aggarwal, Seungone Kim, Jack Lanchantin, Sean Welleck, Jason Weston, Ilia Kulikov, Swarnadeep Saha
Abstract: Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. This has led to the development of separate thinking and non-thinking LLM variants, leaving the onus of selecting the optimal model for each query on the end user. In this work, we introduce OptimalThinkingBench, a unified benchmark that jointly evaluates overthinking and underthinking in LLMs and also encourages the development of optimally-thinking models that balance performance and efficiency. Our benchmark comprises two sub-benchmarks: OverthinkingBench, featuring simple queries in 72 domains, and UnderthinkingBench, containing 11 challenging reasoning tasks. Using novel thinking-adjusted accuracy metrics, we perform extensive evaluation of 33 different thinking and non-thinking models and show that no model is able to optimally think on our benchmark. Thinking models often overthink for hundreds of tokens on the simplest user queries without improving performance. In contrast, large non-thinking models underthink, often falling short of much smaller thinking models. We further explore several methods to encourage optimal thinking, but find that these approaches often improve on one sub-benchmark at the expense of the other, highlighting the need for better unified and optimal models in the future.
Authors: Zhongang Cai, Yubo Wang, Qingping Sun, Ruisi Wang, Chenyang Gu, Wanqi Yin, Zhiqian Lin, Zhitao Yang, Chen Wei, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Jiaqi Li, Xiangyu Fan, Hanming Deng, Lewei Lu, Bo Li, Ziwei Liu, Quan Wang, Dahua Lin, Lei Yang
Abstract: Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilities to achieving artificial general intelligence. With the recent release of GPT-5, allegedly the most powerful AI model to date, it is timely to examine where the leading models stand on the path toward spatial intelligence. First, we propose a comprehensive taxonomy of spatial tasks that unifies existing benchmarks and discuss the challenges in ensuring fair evaluation. We then evaluate state-of-the-art proprietary and open-source models on eight key benchmarks, at a cost exceeding one billion total tokens. Our empirical study reveals that (1) GPT-5 demonstrates unprecedented strength in spatial intelligence, yet (2) still falls short of human performance across a broad spectrum of tasks. Moreover, we (3) identify the more challenging spatial intelligence problems for multi-modal models, and (4) proprietary models do not exhibit a decisive advantage when facing the most difficult problems. In addition, we conduct a qualitative evaluation across a diverse set of scenarios that are intuitive for humans yet fail even the most advanced multi-modal models.
Authors: David Heineman, Valentin Hofmann, Ian Magnusson, Yuling Gu, Noah A. Smith, Hannaneh Hajishirzi, Kyle Lo, Jesse Dodge
Abstract: Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more reliable for such decisions, and interventions to design higher-quality evaluation benchmarks. We introduce two key metrics that show differences in current benchmarks: signal, a benchmark's ability to separate better models from worse models, and noise, a benchmark's sensitivity to random variability between training steps. We demonstrate that benchmarks with a better signal-to-noise ratio are more reliable when making decisions at small scale, and those with less noise have lower scaling law prediction error. These results suggest that improving signal or noise will lead to more useful benchmarks, so we introduce three interventions designed to directly affect signal or noise. For example, we propose that switching to a metric that has better signal and noise (e.g., perplexity rather than accuracy) leads to better reliability and improved scaling law error. We also find that filtering noisy subtasks, to improve an aggregate signal-to-noise ratio, leads to more reliable multi-task evaluations. We also find that averaging the output of a model's intermediate checkpoints to reduce noise leads to consistent improvements. We conclude by recommending that those creating new benchmarks, or selecting which existing benchmarks to use, aim for high signal and low noise. We use 30 benchmarks for these experiments, and 375 open-weight language models from 60M to 32B parameters, resulting in a new, publicly available dataset of 900K evaluation benchmark results, totaling 200M instances.
Authors: Yizhou Wang, Dongliang Guo, Sheng Li, Octavia Camps, Yun Fu
Abstract: Anomaly detection and localization in visual data, including images and videos, are crucial in machine learning and real-world applications. Despite rapid advancements in visual anomaly detection (VAD), interpreting these often black-box models and explaining why specific instances are flagged as anomalous remains challenging. This paper provides the first comprehensive survey focused specifically on explainable 2D visual anomaly detection (X-VAD), covering methods for both images (IAD) and videos (VAD). We first introduce the background of IAD and VAD. Then, as the core contribution, we present a thorough literature review of explainable methods, categorized by their underlying techniques (e.g., attention-based, generative model-based, reasoning-based, foundation model-based). We analyze the commonalities and differences in applying these methods across image and video modalities, highlighting modality-specific challenges and opportunities for explainability. Additionally, we summarize relevant datasets and evaluation metrics, discussing both standard performance metrics and emerging approaches for assessing explanation quality (e.g., faithfulness, stability). Finally, we discuss promising future directions and open problems, including quantifying explanation quality, explaining diverse AD paradigms (SSL, zero-shot), enhancing context-awareness, leveraging foundation models responsibly, and addressing real-world constraints like efficiency and robustness. A curated collection of related resources is available at https://github.com/wyzjack/Awesome-XAD.
Authors: Xin Li
Abstract: We introduce the \emph{delta-homology analogy}, which formalizes memory as a set of sparse, topologically irreducible attractors. A \emph{Dirac delta-like memory trace} \( \delta_\gamma \) is identified with a nontrivial homology generator \( [\gamma] \in H_1(\mathcal{Z}) \) on a latent manifold of cognitive states. Such traces are sharply localized along reproducible topological cycles and are only activated when inference trajectories complete a full cycle. They encode minimal, path-dependent memory units that cannot be synthesized from local features alone. Based on the analogy, we propose a topological framework for memory and inference grounded in the structure of spike-timing dynamics and persistent homology. Starting from the observation that polychronous neural groups (PNGs) encode reproducible, time-locked spike sequences shaped by axonal delays and synaptic plasticity, we construct \emph{spatiotemporal complexes} whose temporally consistent transitions define chain complexes over which robust activation cycles emerge. These activation loops are abstracted into \emph{cell posets}, enabling a compact and causally ordered representation of neural activity with overlapping and compositional memory traces.
Authors: Yifan Qin, Zheyu Yan, Dailin Gan, Jun Xia, Zixuan Pan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi
Abstract: Compute-in-memory accelerators built upon non-volatile memory devices excel in energy efficiency and latency when performing deep neural network (DNN) inference, thanks to their in-situ data processing capability. However, the stochastic nature and intrinsic variations of non-volatile memory devices often result in performance degradation during DNN inference. Introducing these non-ideal device behaviors in DNN training enhances robustness, but drawbacks include limited accuracy improvement, reduced prediction confidence, and convergence issues. This arises from a mismatch between the deterministic training and non-deterministic device variations, as such training, though considering variations, relies solely on the model's final output. In this work, inspired by control theory, we propose Negative Feedback Training (NeFT), a novel concept supported by theoretical analysis, to more effectively capture the multi-scale noisy information throughout the network. We instantiate this concept with two specific instances, oriented variational forward (OVF) and intermediate representation snapshot (IRS). Based on device variation models extracted from measured data, extensive experiments show that our NeFT outperforms existing state-of-the-art methods with up to a 45.08% improvement in inference accuracy while reducing epistemic uncertainty, boosting output confidence, and improving convergence probability. These results underline the generality and practicality of our NeFT framework for increasing the robustness of DNNs against device variations. The source code for these two instances is available at https://github.com/YifanQin-ND/NeFT_CIM
Authors: Anshul Ahluwalia, Payman Behnam, Rohit Das, Alind Khare, Biswadeep Chakraborty, Pan Li, Alexey Tumanov
Abstract: Recent advancements in Graph Neural Networks (GNNs) have led to increased model sizes to enhance their capacity and accuracy. Such large models incur high memory usage, latency, and computational costs, thereby restricting their inference deployment. GNN compression techniques compress large GNNs into smaller ones with negligible accuracy loss. One of the most promising compression techniques is knowledge distillation (KD). However, most KD approaches for GNNs only consider the outputs of the last layers and do not consider the outputs of the intermediate layers of the GNNs. The intermediate layers may contain important inductive biases indicated by the graph structure and embeddings. Ignoring these layers may lead to a high accuracy drop, especially when the compression ratio is high. To address these shortcomings, we propose a novel KD approach for GNN compression that we call Structure and Embedding Distillation with Attention (STRIDE). STRIDE utilizes attention to identify important intermediate teacher-student layer pairs and focuses on using those pairs to align graph structure and node embeddings. We evaluate STRIDE on several datasets, such as OGBN-Mag and OGBN-Arxiv, using different model architectures, including GCNIIs, RGCNs, and GraphSAGE. On average, STRIDE achieves a 2.13% increase in accuracy with a 32.3X compression ratio on OGBN-Mag, a large graph dataset, compared to state-of-the-art approaches. On smaller datasets (e.g., Pubmed), STRIDE achieves up to a 141X compression ratio with the same accuracy as state-of-the-art approaches. These results highlight the effectiveness of focusing on intermediate-layer knowledge to obtain compact, accurate, and practical GNN models.
Authors: Javier Gonz\'alez, Risa Ueno, Cliff Wong, Zelalem Gero, Jass Bagga, Isabel Chien, Eduard Oravkin, Emre Kiciman, Aditya Nori, Roshanthi Weerasinghe, Rom S. Leidner, Brian Piening, Tristan Naumann, Carlo Bifulco, Hoifung Poon
Abstract: The rapid digitization of real-world data presents an unprecedented opportunity to optimize healthcare delivery and accelerate biomedical discovery. However, these data are often found in unstructured forms such as clinical notes in electronic medical records (EMRs), and is typically plagued by confounders, making it challenging to generate robust real-world evidence (RWE). Therefore, we present TRIALSCOPE, a framework designed to distil RWE from population level observational data at scale. TRIALSCOPE leverages biomedical language models to structure clinical text at scale, employs advanced probabilistic modeling for denoising and imputation, and incorporates state-of-the-art causal inference techniques to address common confounders in treatment effect estimation. Extensive experiments were conducted on a large-scale dataset of over one million cancer patients from a single large healthcare network in the United States. TRIALSCOPE was shown to automatically curate high-quality structured patient data, expanding the dataset and incorporating key patient attributes only available in unstructured form. The framework reduces confounding in treatment effect estimation, generating comparable results to randomized controlled lung cancer trials. Additionally, we demonstrate simulations of unconducted clinical trials - including a pancreatic cancer trial with varying eligibility criteria - using a suite of validation tests to ensure robustness. Thorough ablation studies were conducted to better understand key components of TRIALSCOPE and establish best practices for RWE generation from EMRs. TRIALSCOPE was able to extract data cancer treatment data from EMRs, overcoming limitations of manual curation. We were also able to show that TRIALSCOPE could reproduce results of lung and pancreatic cancer clinical trials from the extracted real world data.
Authors: Deqian Kong, Dehong Xu, Minglu Zhao, Bo Pang, Jianwen Xie, Andrew Lizarraga, Yuhao Huang, Sirui Xie, Ying Nian Wu
Abstract: In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of step-wise rewards as one key technical challenge. We introduce the Latent Plan Transformer (LPT), a novel model that leverages a latent variable to connect a Transformer-based trajectory generator and the final return. LPT can be learned with maximum likelihood estimation on trajectory-return pairs. In learning, posterior sampling of the latent variable naturally integrates sub-trajectories to form a consistent abstraction despite the finite context. At test time, the latent variable is inferred from an expected return before policy execution, realizing the idea of planning as inference. Our experiments demonstrate that LPT can discover improved decisions from sub-optimal trajectories, achieving competitive performance across several benchmarks, including Gym-Mujoco, Franka Kitchen, Maze2D, and Connect Four. It exhibits capabilities in nuanced credit assignments, trajectory stitching, and adaptation to environmental contingencies. These results validate that latent variable inference can be a strong alternative to step-wise reward prompting.
Authors: Xiangfei Qiu, Jilin Hu, Lekui Zhou, Xingjian Wu, Junyang Du, Buang Zhang, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Zhenli Sheng, Bin Yang
Abstract: Time series are generated in diverse domains such as economic, traffic, health, and energy, where forecasting of future values has numerous important applications. Not surprisingly, many forecasting methods are being proposed. To ensure progress, it is essential to be able to study and compare such methods empirically in a comprehensive and reliable manner. To achieve this, we propose TFB, an automated benchmark for Time Series Forecasting (TSF) methods. TFB advances the state-of-the-art by addressing shortcomings related to datasets, comparison methods, and evaluation pipelines: 1) insufficient coverage of data domains, 2) stereotype bias against traditional methods, and 3) inconsistent and inflexible pipelines. To achieve better domain coverage, we include datasets from 10 different domains: traffic, electricity, energy, the environment, nature, economic, stock markets, banking, health, and the web. We also provide a time series characterization to ensure that the selected datasets are comprehensive. To remove biases against some methods, we include a diverse range of methods, including statistical learning, machine learning, and deep learning methods, and we also support a variety of evaluation strategies and metrics to ensure a more comprehensive evaluations of different methods. To support the integration of different methods into the benchmark and enable fair comparisons, TFB features a flexible and scalable pipeline that eliminates biases. Next, we employ TFB to perform a thorough evaluation of 21 Univariate Time Series Forecasting (UTSF) methods on 8,068 univariate time series and 14 Multivariate Time Series Forecasting (MTSF) methods on 25 datasets. The benchmark code and data are available at https://github.com/decisionintelligence/TFB. We have also launched an online time series leaderboard: https://decisionintelligence.github.io/OpenTS/OpenTS-Bench/.
URLs: https://github.com/decisionintelligence/TFB., https://decisionintelligence.github.io/OpenTS/OpenTS-Bench/.
Authors: Yangchen Pan, Junfeng Wen, Chenjun Xiao, Philip Torr
Abstract: In traditional statistical learning, data points are usually assumed to be independently and identically distributed (i.i.d.) following an unknown probability distribution. This paper presents a contrasting viewpoint, perceiving data points as interconnected and employing a Markov reward process (MRP) for data modeling. We reformulate the typical supervised learning as an on-policy policy evaluation problem within reinforcement learning (RL), introducing a generalized temporal difference (TD) learning algorithm as a resolution. Theoretically, our analysis establishes connections between the solutions of linear TD learning and ordinary least squares (OLS). Under specific conditions -- particularly when the noise is correlated -- the TD solution serves as a more effective estimator than OLS. Furthermore, we show that when our algorithm is applied with many commonly used loss functions -- such as those found in generalized linear models -- it corresponds to the application of a novel and generalized Bellman operator. We prove that this operator admits a unique fixed point, and based on this, we establish convergence guarantees for our generalized TD algorithm under linear function approximation. Empirical studies verify our theoretical results, examine the vital design of our TD algorithm and show practical utility across various datasets, encompassing tasks such as regression and image classification with deep learning.
Authors: Lea Richtmann, Viktoria-S. Schmiesing, Dennis Wilken, Jan Heine, Aaron Tranter, Avishek Anand, Tobias J. Osborne, Mich\`ele Heurs
Abstract: Setting up and controlling optical systems is often a challenging and tedious task. The high number of degrees of freedom to control mirrors, lenses, or phases of light makes automatic control challenging, especially when the complexity of the system cannot be adequately modeled due to noise or non-linearities. Here, we show that reinforcement learning (RL) can overcome these challenges when coupling laser light into an optical fiber, using a model-free RL approach that trains directly on the experiment without pre-training on simulations. By utilizing the sample-efficient algorithms Soft Actor-Critic (SAC), Truncated Quantile Critics (TQC), or CrossQ, our agents learn to couple with 90% efficiency. A human expert reaches this efficiency, but the RL agents are quicker. In particular, the CrossQ agent outperforms the other agents in coupling speed while requiring only half the training time. We demonstrate that direct training on an experiment can replace extensive system modeling. Our result exemplifies RL's potential to tackle problems in optics, paving the way for more complex applications where full noise modeling is not feasible.
Authors: Andrea Napoli, Paul White
Abstract: This paper considers the problem of model selection under domain shift. Motivated by principles from distributionally robust optimisation and domain adaptation theory, it is proposed that the training-validation split should maximise the distribution mismatch between the two sets. By adopting the maximum mean discrepancy (MMD) as the measure of mismatch, it is shown that the partitioning problem reduces to kernel k-means clustering. A constrained clustering algorithm, which leverages linear programming to control the size, label, and (optionally) group distributions of the splits, is presented. The algorithm does not require additional metadata, and comes with convergence guarantees. In experiments, the technique consistently outperforms alternative splitting strategies across a range of datasets and training algorithms, for both domain generalisation and unsupervised domain adaptation tasks. Analysis also shows the MMD between the training and validation sets to be well-correlated with test domain accuracy, further substantiating the validity of this approach.
Authors: Yihan Wang, Yiwei Lu, Guojun Zhang, Franziska Boenisch, Adam Dziedzic, Yaoliang Yu, Xiao-Shan Gao
Abstract: Machine unlearning offers effective solutions for revoking the influence of specific training data on pre-trained model parameters. While existing approaches address unlearning for classification and generative models, they overlook an important category of machine learning models: contrastive learning (CL) methods. This paper addresses this gap by introducing the Machine Unlearning for Contrastive Learning (MUC) framework and adapting existing methods. We identify limitations in current approaches, noting that several methods perform inadequately as unlearners and that existing evaluation tools insufficiently validate unlearning effects in contrastive learning. To address these issues, we propose Alignment Calibration (AC), a novel method that explicitly considers contrastive learning properties and optimizes towards new auditing metrics for easy verification of unlearning. Through empirical comparisons with baseline methods on SimCLR, MoCo, and CLIP, we demonstrate that AC: (1) achieves state-of-the-art performance, approximating exact unlearning (retraining); (2) enables data owners to clearly visualize unlearning effects through black-box evaluation. The code is available at https://github.com/EhanW/Alignment-Calibration.
Authors: Floor Eijkelboom, Grigory Bartosh, Christian Andersson Naesseth, Max Welling, Jan-Willem van de Meent
Abstract: We present a formulation of flow matching as variational inference, which we refer to as variational flow matching (VFM). Based on this formulation we develop CatFlow, a flow matching method for categorical data. CatFlow is easy to implement, computationally efficient, and achieves strong results on graph generation tasks. In VFM, the objective is to approximate the posterior probability path, which is a distribution over possible end points of a trajectory. We show that VFM admits both the CatFlow objective and the original flow matching objective as special cases. We also relate VFM to score-based models, in which the dynamics are stochastic rather than deterministic, and derive a bound on the model likelihood based on a reweighted VFM objective. We evaluate CatFlow on one abstract graph generation task and two molecular generation tasks. In all cases, CatFlow exceeds or matches performance of the current state-of-the-art models.
Authors: Utsav Singh, Pramit Bhattacharyya, Vinay P. Namboodiri
Abstract: Large language models (LLMs) have shown remarkable abilities in logical reasoning, in-context learning, and code generation. However, translating natural language instructions into effective robotic control policies remains a significant challenge, especially for tasks requiring long-horizon planning and operating under sparse reward conditions. Hierarchical Reinforcement Learning (HRL) provides a natural framework to address this challenge in robotics; however, it typically suffers from non-stationarity caused by the changing behavior of the lower-level policy during training, destabilizing higher-level policy learning. We introduce LGR2, a novel HRL framework that leverages LLMs to generate language-guided reward functions for the higher-level policy. By decoupling high-level reward generation from low-level policy changes, LGR2 fundamentally mitigates the non-stationarity problem in off-policy HRL, enabling stable and efficient learning. To further enhance sample efficiency in sparse environments, we integrate goal-conditioned hindsight experience relabeling. Extensive experiments across simulated and real-world robotic navigation and manipulation tasks demonstrate LGR2 outperforms both hierarchical and non-hierarchical baselines, achieving over 55% success rates on challenging tasks and robust transfer to real robots, without additional fine-tuning.
Authors: Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson
Abstract: When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others introduce sampling methods that can be prohibitively expensive. In this work, we first argue that prompting on its own is insufficient to achieve good calibration and then show that fine-tuning on a small dataset of correct and incorrect answers can create an uncertainty estimate with good generalization and small computational overhead. We show that a thousand graded examples are sufficient to outperform baseline methods and that training through the features of a model is necessary for good performance and tractable for large open-source models when using LoRA. We also investigate the mechanisms that enable reliable LLM uncertainty estimation, finding that many models can be used as general-purpose uncertainty estimators, applicable not just to their own uncertainties but also the uncertainty of other models. Lastly, we show that uncertainty estimates inform human use of LLMs in human-AI collaborative settings through a user study.
Authors: Matteo Tiezzi, Michele Casoni, Alessandro Betti, Marco Gori, Stefano Melacci
Abstract: Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have pursued algorithms and architectures capable of processing sequences of patterns, retaining information about past inputs while still leveraging future data, without losing precious long-term dependencies and correlations. While such an ultimate goal is inspired by the human hallmark of continuous real-time processing of sensory information, several solutions have simplified the learning paradigm by artificially limiting the processed context or dealing with sequences of limited length, given in advance. These solutions were further emphasized by the ubiquity of Transformers, which initially overshadowed the role of Recurrent Neural Nets. However, recurrent networks are currently experiencing a strong recent revival due to the growing popularity of (deep) State-Space models and novel instances of large-context Transformers, which are both based on recurrent computations that aim to go beyond several limits of currently ubiquitous technologies. The fast development of Large Language Models has renewed the interest in efficient solutions to process data over time. This survey provides an in-depth summary of the latest approaches that are based on recurrent models for sequential data processing. A complete taxonomy of recent trends in architectural and algorithmic solutions is reported and discussed, guiding researchers in this appealing research field. The emerging picture suggests that there is room for exploring novel routes, constituted by learning algorithms that depart from the standard Backpropagation Through Time, towards a more realistic scenario where patterns are effectively processed online, leveraging local-forward computations, and opening new directions for research on this topic.
Authors: Lior Friedman, Ron Meir
Abstract: In continual learning, knowledge must be preserved and re-used between tasks, maintaining good transfer to future tasks and minimizing forgetting of previously learned ones. While several practical algorithms have been devised for this setting, there have been few theoretical works aiming to quantify and bound the degree of Forgetting in general settings. For \emph{exemplar-free} methods, we provide both data-dependent upper bounds that apply \emph{regardless of model and algorithm choice}, and oracle bounds for Gibbs posteriors. We derive an algorithm based on our bounds and demonstrate empirically that our approach yields tight and practical bounds on forgetting for several continual learning problems and algorithms.
Authors: Ningyi Liao, Haoyu Liu, Zulun Zhu, Siqiang Luo, Laks V. S. Lakshmanan
Abstract: With recent advancements in graph neural networks (GNNs), spectral GNNs have received increasing popularity by virtue of their ability to retrieve graph signals in the spectral domain. These models feature uniqueness in efficient computation as well as rich expressiveness, which stems from advanced management and profound understanding of graph data. However, few systematic studies have been conducted to assess spectral GNNs, particularly in benchmarking their efficiency, memory consumption, and effectiveness in a unified and fair manner. There is also a pressing need to select spectral models suitable for learning specific graph data and deploying them to massive web-scale graphs, which is currently constrained by the varied model designs and training settings. In this work, we extensively benchmark spectral GNNs with a focus on the spectral perspective, demystifying them as spectral graph filters. We analyze and categorize 35 GNNs with 27 corresponding filters, spanning diverse formulations and utilizations of the graph data. Then, we implement the filters within a unified spectral-oriented framework with dedicated graph computations and efficient training schemes. In particular, our implementation enables the deployment of spectral GNNs over million-scale graphs and various tasks with comparable performance and less overhead. Thorough experiments are conducted on the graph filters with comprehensive metrics on effectiveness and efficiency, offering novel observations and practical guidelines that are only available from our evaluations across graph scales. Different from the prevailing belief, our benchmark reveals an intricate landscape regarding the effectiveness and efficiency of spectral graph filters, demonstrating the potential to achieve desirable performance through tailored spectral manipulation of graph data.
Authors: Krzysztof Kotowski, Christoph Haskamp, Jacek Andrzejewski, Bogdan Ruszczak, Jakub Nalepa, Daniel Lakey, Peter Collins, Aybike Kolmas, Mauro Bartesaghi, Jose Martinez-Heras, Gabriele De Canio
Abstract: Machine learning has vast potential to improve anomaly detection in satellite telemetry which is a crucial task for spacecraft operations. This potential is currently hampered by a lack of comprehensible benchmarks for multivariate time series anomaly detection, especially for the challenging case of satellite telemetry. The European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry (ESA-ADB) aims to address this challenge and establish a new standard in the domain. It is a result of close cooperation between spacecraft operations engineers from the European Space Agency (ESA) and machine learning experts. The newly introduced ESA Anomalies Dataset contains annotated real-life telemetry from three different ESA missions, out of which two are included in ESA-ADB. Results of typical anomaly detection algorithms assessed in our novel hierarchical evaluation pipeline show that new approaches are necessary to address operators' needs. All elements of ESA-ADB are publicly available to ensure its full reproducibility.
Authors: Bingliang Zhang, Wenda Chu, Julius Berner, Chenlin Meng, Anima Anandkumar, Yang Song
Abstract: Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifically, we decouple consecutive steps in a diffusion sampling trajectory, allowing them to vary considerably from one another while ensuring their time-marginals anneal to the true posterior as we reduce noise levels. This approach enables the exploration of a larger solution space, improving the success rate for accurate reconstructions. We demonstrate that DAPS significantly improves sample quality and stability across multiple image restoration tasks, particularly in complicated nonlinear inverse problems.
Authors: Gabriel Turinici
Abstract: We introduce a novel method to handle the time dimension when Physics-Informed Neural Networks (PINNs) are used to solve time-dependent differential equations; our proposal focuses on how time sampling and weighting strategies affect solution quality. While previous methods proposed heuristic time-weighting schemes, our approach is grounded in theoretical insights derived from the Lyapunov exponents, which quantify the sensitivity of solutions to perturbations over time. This principled methodology automatically adjusts weights based on the stability regime of the system -- whether chaotic, periodic, or stable. Numerical experiments on challenging benchmarks, including the chaotic Lorenz system and the Burgers' equation, demonstrate the effectiveness and robustness of the proposed method. Compared to existing techniques, our approach offers improved convergence and accuracy without requiring additional hyperparameter tuning. The findings underline the importance of incorporating causality and dynamical system behavior into PINN training strategies, providing a robust framework for solving time-dependent problems with enhanced reliability.
Authors: Hangfeng He, Weijie J. Su
Abstract: Large language models (LLMs) have been widely employed across various application domains, yet their black-box nature poses significant challenges to understanding how these models process input data internally to make predictions. In this paper, we introduce a precise and quantitative law that governs the learning of contextualized token embeddings through intermediate layers in pre-trained LLMs for next-token prediction. Our findings reveal that each layer contributes equally to enhancing prediction accuracy, from the lowest to the highest layer -- a universal phenomenon observed across a diverse array of open-source LLMs, irrespective of their architectures or pre-training data. We demonstrate that this law offers new perspectives and actionable insights to inform and guide practices in LLM development and applications, including model scaling, pre-training tasks, and interpretation.
Authors: Gleb Bazhenov, Oleg Platonov, Liudmila Prokhorenkova
Abstract: Although data that can be naturally represented as graphs is widespread in real-world applications across diverse industries, popular graph ML benchmarks for node property prediction only cover a surprisingly narrow set of data domains, and graph neural networks (GNNs) are often evaluated on just a few academic citation networks. This issue is particularly pressing in light of the recent growing interest in designing graph foundation models. These models are supposed to be able to transfer to diverse graph datasets from different domains, and yet the proposed graph foundation models are often evaluated on a very limited set of datasets from narrow applications. To alleviate this issue, we introduce GraphLand: a benchmark of 14 diverse graph datasets for node property prediction from a range of different industrial applications. GraphLand allows evaluating graph ML models on a wide range of graphs with diverse sizes, structural characteristics, and feature sets, all in a unified setting. Further, GraphLand allows investigating such previously underexplored research questions as how realistic temporal distributional shifts under transductive and inductive settings influence graph ML model performance. To mimic realistic industrial settings, we use GraphLand to compare GNNs with gradient-boosted decision trees (GBDT) models that are popular in industrial applications and show that GBDTs provided with additional graph-based input features can sometimes be very strong baselines. Further, we evaluate currently available general-purpose graph foundation models and find that they fail to produce competitive results on our proposed datasets.
Authors: Md Abrar Jahin, Md. Akmol Masud, M. F. Mridha, Zeyar Aung, Nilanjan Dey
Abstract: Heart failure is a leading cause of global mortality, necessitating improved diagnostic strategies. Classical machine learning models struggle with challenges such as high-dimensional data, class imbalances, poor feature representations, and a lack of interpretability. While quantum machine learning holds promise, current hybrid models have not fully exploited quantum advantages. In this paper, we propose the Kolmogorov-Arnold Classical-Quantum Dual-Channel Neural Network (KACQ-DCNN), a novel hybrid architecture that replaces traditional multilayer perceptrons with Kolmogorov-Arnold Networks (KANs), enabling learnable univariate activation functions. Our KACQ-DCNN 4-qubit, 1-layer model outperforms 37 benchmark models, including 16 classical and 12 quantum neural networks, achieving an accuracy of 92.03%, with macro-average precision, recall, and F1 scores of 92.00%. It also achieved a ROC-AUC of 94.77%, surpassing other models by significant margins, as validated by paired t-tests with a significance threshold of 0.0056 (after Bonferroni correction). Ablation studies highlight the synergistic effect of classical-quantum integration, improving performance by about 2% over MLP variants. Additionally, LIME and SHAP explainability techniques enhance feature interpretability, while conformal prediction provides robust uncertainty quantification. Our results demonstrate that KACQ-DCNN improves cardiovascular diagnostics by combining high accuracy with interpretability and uncertainty quantification.
Authors: Raphael C. Kim, Falco J. Bargagli-Stoffi, Kevin L. Chen, Rachel C. Nethery
Abstract: The substantial effect of air pollution on cardiovascular disease and mortality burdens is well-established. Emissions-reducing interventions on coal-fired power plants -- a major source of hazardous air pollution -- have proven to be an effective, but costly, strategy for reducing pollution-related health burdens. Targeting the power plants that achieve maximum health benefits while satisfying realistic cost constraints is challenging. The primary difficulty lies in quantifying the health benefits of intervening at particular plants. This is further complicated because interventions are applied on power plants, while health impacts occur in potentially distant communities, a setting known as bipartite network interference (BNI). In this paper, we introduce novel policy learning methods based on Q- and A-Learning to determine the optimal policy under arbitrary BNI. We derive asymptotic properties and demonstrate finite sample efficacy in simulations. We apply our novel methods to a comprehensive dataset of Medicare claims, power plant data, and pollution transport networks. Our goal is to determine the optimal strategy for installing power plant scrubbers to minimize ischemic heart disease (IHD) hospitalizations under various cost constraints. We find that annual IHD hospitalization rates could be reduced in a range from 23.37-55.30 per 10,000 person-years through optimal policies under different cost constraints.
Authors: Bryan L. M. de Oliveira, Luana G. B. Martins, Bruno Brand\~ao, Murilo L. da Luz, Telma W. de L. Soares, Luckeciano C. Melo
Abstract: Effective visual representation learning is crucial for reinforcement learning (RL) agents to extract task-relevant information from raw sensory inputs and generalize across diverse environments. However, existing RL benchmarks lack the ability to systematically evaluate representation learning capabilities in isolation from other learning challenges. To address this gap, we introduce the Sliding Puzzles Gym (SPGym), a novel benchmark that transforms the classic 8-tile puzzle into a visual RL task with images drawn from arbitrarily large datasets. SPGym's key innovation lies in its ability to precisely control representation learning complexity through adjustable grid sizes and image pools, while maintaining fixed environment dynamics, observation, and action spaces. This design enables researchers to isolate and scale the visual representation challenge independently of other learning components. Through extensive experiments with model-free and model-based RL algorithms, we uncover fundamental limitations in current methods' ability to handle visual diversity. As we increase the pool of possible images, all algorithms exhibit in- and out-of-distribution performance degradation, with sophisticated representation learning techniques often underperforming simpler approaches like data augmentation. These findings highlight critical gaps in visual representation learning for RL and establish SPGym as a valuable tool for driving progress in robust, generalizable decision-making systems.
Authors: Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler, Anit Kumar Sahu, Mubarak Shah, Vinay P. Namboodiri, Amrit Singh Bedi
Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However, HRL methods often suffer from two fundamental challenges: (i) non-stationarity, caused by the changing behavior of the lower-level policy during training, which destabilizes higher-level policy learning, and (ii) the generation of infeasible subgoals that lower-level policies cannot achieve. In this work, we introduce DIPPER, a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem and leverages direct preference optimization (DPO) to train the higher-level policy using preference feedback. By optimizing the higher-level policy with DPO, we decouple higher-level learning from the non-stationary lower-level reward signal, thus mitigating non-stationarity. To further address the infeasible subgoal problem, DIPPER incorporates a regularization that tries to ensure the feasibility of subgoal tasks within the capabilities of the lower-level policy. Extensive experiments on challenging robotic navigation and manipulation benchmarks demonstrate that DIPPER achieves up to 40\% improvement over state-of-the-art baselines in sparse reward scenarios, highlighting its effectiveness in overcoming longstanding limitations of HRL.
Authors: Kathryn T. Farrell, Kirsten Ziman, Michael S. A. Graziano
Abstract: Growing evidence suggests that the brain uses an attention schema, or a simplified model of attention, to help control what it attends to. One proposed benefit of this model is to allow agents to model the attention states of other agents, and thus predict and interact with other agents. The effects of an attention schema may be examined in artificial agents. Although attention mechanisms in artificial agents are different from in biological brains, there may be some principles in common. In both cases, select features or representations are emphasized for better performance. Here, using neural networks with transformer attention mechanisms, we asked whether the addition of an attention schema affected the ability of agents to make judgements about and cooperate with each other. First, we found that an agent with an attention schema is better at categorizing the attention states of other agents (higher accuracy). Second, an agent with an attention schema develops a pattern of attention that is easier for other agents to categorize. Third, in a joint task where two agents must predict each other to paint a scene together, adding an attention schema improves performance. Finally, the performance improvements are not caused by a general increase in network complexity. Instead, improvement is specific to tasks involving judging, categorizing, or predicting the attention of other agents. These results support the hypothesis that an attention schema has computational properties beneficial to mutual interpretability and interactive behavior. We speculate that the same principles might pertain to biological attention and attention schemas in people.
Authors: Luciano S. Martinez-Rau, Yuxuan Zhang, Bengt Oelmann, Sebastian Bader
Abstract: Conveyor belts are crucial in mining operations by enabling the continuous and efficient movement of bulk materials over long distances, which directly impacts productivity. While detecting anomalies in specific conveyor belt components has been widely studied, identifying the root causes of these failures, such as changing production conditions and operator errors, remains critical. Continuous monitoring of mining conveyor belt work cycles is still at an early stage and requires robust solutions. Recently, an anomaly detection method for duty cycle operations of a mining conveyor belt has been proposed. Based on its limited performance and unevaluated long-term proper operation, this study proposes two novel methods for classifying normal and abnormal duty cycles. The proposed approaches are pattern recognition systems that make use of threshold-based duty-cycle detection mechanisms, manually extracted features, pattern-matching, and supervised tiny machine learning models. The explored low-computational models include decision tree, random forest, extra trees, extreme gradient boosting, Gaussian naive Bayes, and multi-layer perceptron. A comprehensive evaluation of the former and proposed approaches is carried out on two datasets. Both proposed methods outperform the former method in anomaly detection, with the best-performing approach being dataset-dependent. The heuristic rule-based approach achieves the highest F1-score in the same dataset used for algorithm training, with 97.3% for normal cycles and 80.2% for abnormal cycles. The ML-based approach performs better on a dataset including the effects of machine aging, with an F1-score scoring 91.3% for normal cycles and 67.9% for abnormal cycles. Implemented on two low-power microcontrollers, the methods demonstrate efficient, real-time operation with energy consumption of 13.3 and 20.6 \textmu J during inference. These results ...
Authors: Mahammad Humayoo
Abstract: In numerous episodic reinforcement learning (RL) environments, SARSA-based methodologies are employed to enhance policies aimed at maximizing returns over long horizons. Traditional SARSA algorithms face challenges in achieving an optimal balance between bias and variation, primarily due to their dependence on a single, constant discount factor ($\eta$). This investigation enhances the temporal difference decomposition method, TD($\Delta$), by applying it to the SARSA algorithm, now designated as SARSA($\Delta$). SARSA is a widely used on-policy RL method that enhances action-value functions via temporal difference updates. By splitting the action-value function down into components that are linked to specific discount factors, SARSA($\Delta$) makes learning easier across a range of time scales. This analysis makes learning more effective and ensures consistency, particularly in situations where long-horizon improvement is needed. The results of this research show that the suggested strategy works to lower bias in SARSA's updates and speed up convergence in both deterministic and stochastic settings, even in dense reward Atari environments. Experimental results from a variety of benchmark settings show that the proposed SARSA($\Delta$) outperforms existing TD learning techniques in both tabular and deep RL environments.
Authors: Zixian Su, Jingwei Guo, Xi Yang, Qiufeng Wang, Kaizhu Huang
Abstract: Deploying deep models in real-world scenarios remains challenging due to significant performance drops under distribution shifts between training and deployment environments. Test-Time Adaptation (TTA) has recently emerged as a promising solution, enabling on-the-fly model adaptation without access to source data. However, its effectiveness degrades significantly in the presence of complex, mixed distribution shifts - common in practical settings - where multiple latent domains coexist. Adapting under such intrinsic heterogeneity, especially in unlabeled and online conditions, remains an open and underexplored challenge. In this paper, we study TTA under mixed distribution shifts and move beyond conventional homogeneous adaptation paradigms. By revisiting TTA from a frequency-domain perspective, we observe that distribution heterogeneity often manifests in Fourier space - for instance, high-frequency components tend to carry domain-specific variations. This motivates us to perform domain-aware separation using high-frequency texture cues, making diverse shift patterns more tractable. To this end, we propose FreDA, a novel Frequency-based Decentralized Adaptation framework that decomposes globally heterogeneous data into locally homogeneous components in the frequency domain. It further employs decentralized learning and augmentation strategies to robustly adapt under complex, evolving shifts. Extensive experiments across various environments (corrupted, natural, and medical) demonstrate the superiority of our proposed framework over the state-of-the-arts.
Authors: Zian Zhai, Sima Qing, Xiaoyang Wang, Wenjie Zhang
Abstract: Signed Graph Neural Networks (SGNNs) are effective in learning expressive representations for signed graphs but typically require substantial task-specific labels, limiting their applicability in label-scarce industrial scenarios. In contrast, unsigned graph structures are abundant and can be readily leveraged to pre-train Graph Neural Networks (GNNs), offering a promising solution to reduce supervision requirements in downstream signed graph tasks. However, transferring knowledge from unsigned to signed graphs is non-trivial due to the fundamental discrepancies in graph types and task objectives between pre-training and downstream phases. To address this challenge, we propose Signed Graph Prompt Tuning (SGPT), a novel graph prompting framework that adapts pre-trained unsigned GNNs to few-shot signed graph tasks. We first design a graph template based on balance theory to disentangle mixed node relationships introduced by negative links, mitigating the structural mismatches between unsigned and signed graphs. We further introduce a task template that reformulates downstream signed tasks into a unified link prediction objective, aligning their optimization goals with the pre-training task. Furthermore, we develop feature prompts that align downstream semantic spaces with the feature spaces learned during pre-training, and semantic prompts to integrate link sign semantics in a task-aware manner. We conduct extensive experiments on seven benchmark signed graph datasets, demonstrating that SGPT significantly outperforms existing state-of-the-art methods, establishing a powerful and generalizable solution for few-shot signed graph learning.
Authors: Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster, Tom Rainforth
Abstract: The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this stems from the aleatoric-epistemic view being insufficiently expressive to capture all the distinct quantities that researchers are interested in. To address this we present a decision-theoretic perspective that relates rigorous notions of uncertainty, predictive performance and statistical dispersion in data. This serves to support clearer thinking as the field moves forward. Additionally we provide insights into popular information-theoretic quantities, showing they can be poor estimators of what they are often purported to measure, while also explaining how they can still be useful in guiding data acquisition.
Authors: Satchel Grant, Noah D. Goodman, James L. McClelland
Abstract: What types of numeric representations emerge in neural systems, and what would a satisfying answer to this question look like? In this work, we interpret Neural Network (NN) solutions to sequence based number tasks using a variety of methods to understand how well we can interpret them through the lens of interpretable Symbolic Algorithms (SAs) -- precise programs describable by rules and typed, mutable variables. We use autoregressive GRUs, LSTMs, and Transformers trained on tasks where the correct tokens depend on numeric information only latent in the task structure. We show through multiple causal and theoretical methods that we can interpret raw NN activity through the lens of simplified SAs when we frame the activity in terms of neural subspaces rather than individual neurons. Using Distributed Alignment Search (DAS), we find that, depending on network architecture, dimensionality, and task specifications, alignments with SA's can be very high, or they can be only approximate, or fail altogether. We extend our analytic toolkit to address the failure cases by expanding the DAS framework to a broader class of alignment functions that more flexibly capture NN activity in terms of interpretable variables from SAs, and we provide theoretic and empirical explorations of Linear Alignment Functions (LAFs) in contrast to the preexisting Orthogonal Alignment Functions (OAFs). Through analyses of specific cases we confirm the usefulness of causal interventions on neural subspaces for NN interpretability, and we show that recurrent models can develop graded, symbol-like number variables in their neural activity. We further show that shallow Transformers learn very different solutions than recurrent networks, and we prove that such models must use anti-Markovian solutions -- solutions that do not rely on cumulative, Markovian hidden states -- in the absence of sufficient attention layers.
Authors: Chenhui Xu, Dancheng Liu, Yuting Hu, Jiajie Li, Ruiyang Qin, Qingxiao Zheng, Jinjun Xiong
Abstract: Physics-Informed Neural Networks (PINNs) are a kind of deep-learning-based numerical solvers for partial differential equations (PDEs). Existing PINNs often suffer from failure modes of being unable to propagate patterns of initial conditions. We discover that these failure modes are caused by the simplicity bias of neural networks and the mismatch between PDE's continuity and PINN's discrete sampling. We reveal that the State Space Model (SSM) can be a continuous-discrete articulation allowing initial condition propagation, and that simplicity bias can be eliminated by aligning a sequence of moderate granularity. Accordingly, we propose PINNMamba, a novel framework that introduces sub-sequence modeling with SSM. Experimental results show that PINNMamba can reduce errors by up to 86.3\% compared with state-of-the-art architecture. Our code is available at https://github.com/miniHuiHui/PINNMamba.
Authors: Yuan Gao, Hao Wu, Ruiqi Shu, Huanshuo Dong, Fan Xu, Rui Ray Chen, Yibo Yan, Qingsong Wen, Xuming Hu, Kun Wang, Jiahao Wu, Qing Li, Hui Xiong, Xiaomeng Huang
Abstract: Accurate weather forecasts are important for disaster prevention, agricultural planning, etc. Traditional numerical weather prediction (NWP) methods offer physically interpretable high-accuracy predictions but are computationally expensive and fail to fully leverage rapidly growing historical data. In recent years, deep learning models have made significant progress in weather forecasting, but challenges remain, such as balancing global and regional high-resolution forecasts, excessive smoothing in extreme event predictions, and insufficient dynamic system modeling. To address these issues, this paper proposes a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks. By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region to capture local high-frequency features. We introduce an adaptive messaging mechanism, using dynamic gating units to deeply integrate node and edge features for more accurate extreme event forecasting. For high-resolution regional forecasts, we propose a neural nested grid method to mitigate boundary information loss. Experimental results show that OneForecast performs excellently across global to regional scales and short-term to long-term forecasts, especially in extreme event predictions. Codes link https://github.com/YuanGao-YG/OneForecast.
Authors: Nikita Gushchin, David Li, Daniil Selikhanovych, Evgeny Burnaev, Dmitry Baranchuk, Alexander Korotin
Abstract: Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow inference. To address it, we propose a novel distillation technique based on the inverse bridge matching formulation and derive the tractable objective to solve it in practice. Unlike previously developed DBM distillation techniques, the proposed method can distill both conditional and unconditional types of DBMs, distill models in a one-step generator, and use only the corrupted images for training. We evaluate our approach for both conditional and unconditional types of bridge matching on a wide set of setups, including super-resolution, JPEG restoration, sketch-to-image, and other tasks, and show that our distillation technique allows us to accelerate the inference of DBMs from 4x to 100x and even provide better generation quality than used teacher model depending on particular setup. We provide the code at https://github.com/ngushchin/IBMD
Authors: Grigoriy Ksenofontov, Alexander Korotin
Abstract: The Schr\"odinger Bridge (SB) is a powerful framework for solving generative modeling tasks such as unpaired domain translation. Most SB-related research focuses on continuous data space $\mathbb{R}^{D}$ and leaves open theoretical and algorithmic questions about applying SB methods to discrete data, e.g, on finite spaces $\mathbb{S}^{D}$. Notable examples of such sets $\mathbb{S}$ are codebooks of vector-quantized (VQ) representations of modern autoencoders, tokens in texts, categories of atoms in molecules, etc. In this paper, we provide a theoretical and algorithmic foundation for solving SB in discrete spaces using the recently introduced Iterative Markovian Fitting (IMF) procedure. Specifically, we theoretically justify the convergence of discrete-time IMF (D-IMF) to SB in discrete spaces. This enables us to develop a practical computational algorithm for SB, which we call Categorical Schr\"odinger Bridge Matching (CSBM). We show the performance of CSBM via a series of experiments with synthetic data and VQ representations of images. The code of CSBM is available at https://github.com/gregkseno/csbm.
Authors: Alessio Russo, Aldo Pacchiano
Abstract: We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\epsilon,\delta)$-PAC perspective to achieve $\epsilon$-accurate estimates with high confidence across finite or convex sets of rewards, a setting that has not been investigated in the literature. Building on prior work on Multi-Reward Best Policy Identification, we adapt the MR-NaS exploration scheme to jointly minimize sample complexity for evaluating different policies across different reward sets. Our approach leverages an instance-specific lower bound revealing how the sample complexity scales with a measure of value deviation, guiding the design of an efficient exploration policy. Although computing this bound entails a hard non-convex optimization, we propose an efficient convex approximation that holds for both finite and convex reward sets. Experiments in tabular domains demonstrate the effectiveness of this adaptive exploration scheme.
Authors: Xinwei Shen, Nicolai Meinshausen, Tong Zhang
Abstract: Learning complex distributions is a fundamental challenge in contemporary applications. Shen and Meinshausen (2024) introduced engression, a generative approach based on scoring rules that maps noise (and covariates, if available) directly to data. While effective, engression can struggle with highly complex distributions, such as those encountered in image data. In this work, we propose reverse Markov learning (RML), a framework that defines a general forward process transitioning from the target distribution to a known distribution (e.g., Gaussian) and then learns a reverse Markov process using multiple engression models. This reverse process reconstructs the target distribution step by step. This framework accommodates general forward processes, allows for dimension reduction, and naturally discretizes the generative process. In the special case of diffusion-based forward processes, RML provides an efficient discretization strategy for both training and inference in diffusion models. We further introduce an alternating sampling scheme to enhance post-training performance. Our statistical analysis establishes error bounds for RML and elucidates its advantages in estimation efficiency and flexibility in forward process design. Empirical results on simulated and climate data corroborate the theoretical findings, demonstrating the effectiveness of RML in capturing complex distributions.
Authors: Xuyang Li, Romit Maulik
Abstract: Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems--especially those requiring precise and reliable performance--often demand interpretability in the sense of a-priori assessments of agent behavior to identify safe or failure-prone interactions with environments. To address this limitation, we propose SALSA-RL (Stability Analysis in the Latent Space of Actions), a novel RL framework that models control actions as dynamic, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system, our approach enables interpretability through local stability analysis, where instantaneous growth in action-norms can be predicted before their execution. We demonstrate that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation, SALSA-RL provides a powerful tool for advancing the design, analysis, and theoretical understanding of RL systems.
Authors: Peter Halmos, Julian Gold, Xinhao Liu, Benjamin J. Raphael
Abstract: Optimal transport (OT) has enjoyed great success in machine learning as a principled way to align datasets via a least-cost correspondence, driven in large part by the runtime efficiency of the Sinkhorn algorithm (Cuturi, 2013). However, Sinkhorn has quadratic space and time complexity in the number of points, limiting scalability to larger datasets. Low-rank OT achieves linear complexity, but by definition, cannot compute a one-to-one correspondence between points. When the optimal transport problem is an assignment problem between datasets then an optimal mapping, known as the Monge map, is guaranteed to be a bijection. In this setting, we show that the factors of an optimal low-rank coupling co-cluster each point with its image under the Monge map. We leverage this invariant to derive an algorithm, Hierarchical Refinement (HiRef), that dynamically constructs a multiscale partition of each dataset using low-rank OT subproblems, culminating in the bijective Monge map. Hierarchical Refinement runs in log-linear time and linear space, retaining the advantages of low-rank OT while overcoming its limited resolution. We demonstrate the advantages of Hierarchical Refinement on several datasets, including ones containing over a million points, scaling full-rank OT to problems previously beyond Sinkhorn's reach.
Authors: Alexander Kolpakov, Igor Rivin
Abstract: We propose a new dimensionality reduction toolkit designed to address some of the challenges faced by traditional methods like UMAP and tSNE such as loss of global structure and computational efficiency. Built on the JAX framework, DiRe leverages modern hardware acceleration to provide an efficient, scalable, and interpretable solution for visualizing complex data structures, and for quantitative analysis of lower-dimensional embeddings. The toolkit shows considerable promise in preserving both local and global structures within the data as compared to state-of-the-art UMAP and tSNE implementations. This makes it suitable for a wide range of applications in machine learning, bio-informatics, and data science.
Authors: Edoardo Zorzi, Alberto Castellini, Leonidas Bakopoulos, Georgios Chalkiadakis, Alessandro Farinelli
Abstract: Most offline RL algorithms return optimal policies but do not provide statistical guarantees on desirable behaviors. This could generate reliability issues in safety-critical applications, such as in some multiagent domains where agents, and possibly humans, need to interact to reach their goals without harming each other. In this work, we propose a novel offline RL approach, inspired by Seldonian optimization, which returns policies with good performance and statistically guaranteed properties with respect to predefined desirable behaviors. In particular, our focus is on Ad Hoc Teamwork settings, where agents must collaborate with new teammates without prior coordination. Our method requires only a pre-collected dataset, a set of candidate policies for our agent, and a specification about the possible policies followed by the other players -- it does not require further interactions, training, or assumptions on the type and architecture of the policies. We test our algorithm in Ad Hoc Teamwork problems and show that it consistently finds reliable policies while improving sample efficiency with respect to standard ML baselines.
Authors: Jihyun Lim, Junhyuk Jo, Tuo Zhang, Sunwoo Lee
Abstract: Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to perform KD on the server side. However, they often assume that unlabeled data collected at the edge is centralized on the server. Moreover, the logit ensemble method personalizes local models, which can degrade the quality of soft targets, especially when data is highly non-IID. To address these critical limitations,we propose a novel on-device KD-based heterogeneous FL method. Our approach leverages a small auxiliary model to learn from labeled local data. Subsequently, a subset of clients with strong system resources transfers knowledge to a large model through on-device KD using their unlabeled data. Our extensive experiments demonstrate that our on-device KD-based heterogeneous FL method effectively utilizes the system resources of all edge devices as well as the unlabeled data, resulting in higher accuracy compared to SOTA KD-based FL methods.
Authors: Jiexia Ye, Weiqi Zhang, Ziyue Li, Jia Li, Fugee Tsung
Abstract: Accurate medical time series (MedTS) classification is essential for effective clinical diagnosis, yet remains challenging due to complex multi-channel temporal dependencies, information redundancy, and label scarcity. While transformer-based models have shown promise in time series analysis, most are designed for forecasting tasks and fail to fully exploit the unique characteristics of MedTS. In this paper, we introduce MedSpaformer, a transformer-based framework tailored for MedTS classification. It incorporates a sparse token-based dual-attention mechanism that enables global context modeling and token sparsification, allowing dynamic feature refinement by focusing on informative tokens while reducing redundancy. This mechanism is integrated into a multi-granularity cross-channel encoding scheme to capture intra- and inter-granularity temporal dependencies and inter-channel correlations, enabling progressive refinement of task-relevant patterns in medical signals. The sparsification design allows our model to flexibly accommodate inputs with variable lengths and channel dimensions. We also introduce an adaptive label encoder to extract label semantics and address cross-dataset label space misalignment. Together, these components enhance the model's transferability across heterogeneous medical datasets, which helps alleviate the challenge of label scarcity. Our model outperforms 13 baselines across 7 medical datasets under supervised learning. It also excels in few-shot learning and demonstrates zero-shot capability in both in-domain and cross-domain diagnostics. These results highlight MedSpaformer's robustness and its potential as a unified solution for MedTS classification across diverse settings.
Authors: Yunhao Tang, Kunhao Zheng, Gabriel Synnaeve, R\'emi Munos
Abstract: In this work, we investigate the merits of explicitly optimizing for inference time algorithmic performance during model training. We show how optimizing for inference time performance can improve overall model efficacy. We consider generic inference time objectives with $k$ samples, with a focus on pass@$k$ and majority voting as two main applications. With language model training on reasoning datasets, we showcase the performance trade-off enabled by training with such objectives. When training on code generation tasks, we show that the approach significantly improves pass@$k$ objectives compared to the baseline method.
Authors: Qinyu Li, Yee Whye Teh, Razvan Pascanu
Abstract: The canonical deep learning approach for learning requires computing a gradient term at each block by back-propagating the error signal from the output towards each learnable parameter. Given the stacked structure of neural networks, where each block builds on the representation of the block below, this approach leads to hierarchical representations. More abstract features live on the top blocks of the model, while features on lower blocks are expected to be less abstract. In contrast to this, we introduce a new learning method named NoProp, which does not rely on either forward or backwards propagation across the entire network. Instead, NoProp takes inspiration from diffusion and flow matching methods, where each block independently learns to denoise a noisy target using only local targets and back-propagation within the block. We believe this work takes a first step towards introducing a new family of learning methods that does not learn hierarchical representations -- at least not in the usual sense. NoProp needs to fix the representation at each block beforehand to a noised version of the target, learning a local denoising process that can then be exploited at inference. We demonstrate the effectiveness of our method on MNIST, CIFAR-10, and CIFAR-100 image classification benchmarks. Our results show that NoProp is a viable learning algorithm, is easy to use and computationally efficient. By departing from the traditional learning paradigm which requires back-propagating a global error signal, NoProp alters how credit assignment is done within the network, enabling more efficient distributed learning as well as potentially impacting other characteristics of the learning process.
Authors: Ramin Zarei Sabzevar, Hamed Mohammadzadeh, Tahmineh Tavakoli, Ahad Harati
Abstract: Despite the advantages of discriminative prototype-based methods, their role in adversarial robustness remains underexplored. Meanwhile, current adversarial training methods predominantly focus on robustness against adversarial attacks without explicitly leveraging geometric structures in the latent space, usually resulting in reduced accuracy on the original clean data. We propose a novel framework named Adversarially trained Deep Positive-Negative Prototypes (Adv-DPNP), which integrates discriminative prototype-based learning with adversarial training. Adv-DPNP uses unified class prototypes that serve as both classifier weights and robust anchors in the latent space. Moreover, a novel dual-branch training mechanism maintains stable prototypes by updating them exclusively with clean data, while the feature extractor is trained on both clean and adversarial inputs to increase invariance to adversarial perturbations. In addition, we use a composite loss that combines positive-prototype alignment, negative-prototype repulsion, and consistency regularization to further enhance discrimination, adversarial robustness, and clean accuracy. Extensive experiments on standard benchmarks (CIFAR-10/100 and SVHN) confirm that Adv-DPNP improves clean accuracy over state-of-the-art defenses and baseline methods, while maintaining competitive or superior robustness under a suite of widely used attacks, including FGSM, PGD, C\&W, and AutoAttack. We also evaluate robustness to common corruptions on CIFAR-10-C, where Adv-DPNP achieves the highest average accuracy across severities and corruption types. Additionally, we provide an in-depth analysis of the discriminative quality of the learned feature representations, highlighting the effectiveness of Adv-DPNP in maintaining compactness and clear separation in the latent space.
Authors: Beilong Tang, Bang Zeng, Ming Li
Abstract: We propose LauraTSE, an Auto-Regressive Decoder-Only Language Model for Target Speaker Extraction built upon the LauraGPT backbone. LauraTSE employs a small-scale auto-regressive decoder-only language model that generates the initial layers of the target speech's discrete codec representations from the continuous embeddings of both the mixture and reference speech. These outputs serve as coarse-grained predictions. To refine them, a one-step encoder-only language model reconstructs the full codec representation by integrating information from both the mixture and the reference speech, adding fine-grained details. Experimental results show that our approach can achieve promising performance. Additionally, we conduct ablation studies to investigate the data scalability and the contribution of the encoder-only model.
Authors: Raghavv Goel, Junyoung Park, Mukul Gagrani, Dalton Jones, Matthew Morse, Harper Langston, Mingu Lee, Chris Lott
Abstract: While long context support of large language models has extended their abilities, it also incurs challenges in memory and compute which becomes crucial bottlenecks in resource-restricted devices. Token eviction, a widely adopted post-training methodology designed to alleviate the bottlenecks by evicting less important tokens from the cache, typically uses attention scores as proxy metrics for token importance. However, one major limitation of attention score as a token-wise importance metrics is that it lacks the information about contribution of tokens to the attention output. In this paper, we propose a simple eviction criterion based on the contribution of cached tokens to attention outputs. Our method, CAOTE, optimizes for eviction error due to token eviction, by seamlessly integrating attention scores and value vectors. This is the first method which uses value tokens on top of attention-based eviction scores in closed-form. Additionally, CAOTE can act as a meta-heuristic method with flexible usage with any token eviction method. We show that CAOTE, when combined with the state-of-the-art attention score-based methods, always improves accuracies on the downstream task, indicating the importance of leveraging information from values during token eviction process.
Authors: Bernhard Jaeger, Daniel Dauner, Jens Bei{\ss}wenger, Simon Gerstenecker, Kashyap Chitta, Andreas Geiger
Abstract: We investigate reinforcement learning (RL) for privileged planning in autonomous driving. State-of-the-art approaches for this task are rule-based, but these methods do not scale to the long tail. RL, on the other hand, is scalable and does not suffer from compounding errors like imitation learning. Contemporary RL approaches for driving use complex shaped rewards that sum multiple individual rewards, \eg~progress, position, or orientation rewards. We show that PPO fails to optimize a popular version of these rewards when the mini-batch size is increased, which limits the scalability of these approaches. Instead, we propose a new reward design based primarily on optimizing a single intuitive reward term: route completion. Infractions are penalized by terminating the episode or multiplicatively reducing route completion. We find that PPO scales well with higher mini-batch sizes when trained with our simple reward, even improving performance. Training with large mini-batch sizes enables efficient scaling via distributed data parallelism. We scale PPO to 300M samples in CARLA and 500M samples in nuPlan with a single 8-GPU node. The resulting model achieves 64 DS on the CARLA longest6 v2 benchmark, outperforming other RL methods with more complex rewards by a large margin. Requiring only minimal adaptations from its use in CARLA, the same method is the best learning-based approach on nuPlan. It scores 91.3 in non-reactive and 90.6 in reactive traffic on the Val14 benchmark while being an order of magnitude faster than prior work.
Authors: Vincent-Daniel Yun
Abstract: Deep neural networks achieve high performance across many domains but can still face challenges in generalization when optimization is influenced by small or noisy gradient components. Sharpness-Aware Minimization improves generalization by perturbing parameters toward directions of high curvature, but it uses the entire gradient vector, which means that small or noisy components may affect the ascent step and cause the optimizer to miss optimal solutions. We propose Z-Score Filtered Sharpness-Aware Minimization, which applies Z-score based filtering to gradients in each layer. Instead of using all gradient components, a mask is constructed to retain only the top percentile with the largest absolute Z-scores. The percentile threshold $Q_p$ determines how many components are kept, so that the ascent step focuses on directions that stand out most compared to the average of the layer. This selective perturbation refines the search toward flatter minima while reducing the influence of less significant gradients. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet with architectures including ResNet, VGG, and Vision Transformers show that the proposed method consistently improves test accuracy compared to Sharpness-Aware Minimization and its variants.
Authors: Francisco Andrade, Gabriel Peyr\'e, Clarice Poon
Abstract: Estimating parameters from samples of an optimal probability distribution is essential in applications ranging from socio-economic modeling to biological system analysis. In these settings, the probability distribution arises as the solution to an optimization problem that captures either static interactions among agents or the dynamic evolution of a system over time. We introduce a general methodology based on a new class of loss functions, called sharpened Fenchel-Young losses, which measure the sub-optimality gap of the optimization problem over the space of probability measures. We provide explicit stability guarantees for two relevant settings in the context of optimal transport: The first is inverse unbalanced optimal transport (iUOT) with entropic regularization, where the parameters to estimate are cost functions that govern transport computations; this method has applications such as link prediction in machine learning. The second is inverse gradient flow (iJKO), where the objective is to recover a potential function that drives the evolution of a probability distribution via the Jordan-Kinderlehrer-Otto (JKO) time-discretization scheme; this is particularly relevant for understanding cell population dynamics in single-cell genomics. We also establish source conditions to ensure stability of our method under mirror stratifiable regularizers (such as l1 or nuclear norm) that promote structure. Finally, we present optimization algorithms specifically tailored to efficiently solve iUOT and iJKO problems. We validate our approach through numerical experiments on Gaussian distributions, where closed-form solutions are available, to demonstrate the practical performance of our methods.
Authors: Yotam Norman, Ron Meir
Abstract: We propose a novel unsupervised framework for \emph{Invariant Risk Minimization} (IRM), extending the concept of invariance to settings where labels are unavailable. Traditional IRM methods rely on labeled data to learn representations that are robust to distributional shifts across environments. In contrast, our approach redefines invariance through feature distribution alignment, enabling robust representation learning from unlabeled data. We introduce two methods within this framework: Principal Invariant Component Analysis (PICA), a linear method that extracts invariant directions under Gaussian assumptions, and Variational Invariant Autoencoder (VIAE), a deep generative model that disentangles environment-invariant and environment-dependent latent factors. Our approach is based on a novel ``unsupervised'' structural causal model and supports environment-conditioned sample-generation and intervention. Empirical evaluations on synthetic dataset and modified versions of MNIST demonstrate the effectiveness of our methods in capturing invariant structure, preserving relevant information, and generalizing across environments without access to labels.
Authors: Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
Abstract: To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank decomposition methods. Specifically, we focus on three key issues related to decomposition in FL: what to decompose, how to decompose, and how to aggregate. Subsequently, we introduce three novel techniques: Model Update Decomposition (MUD), Block-wise Kronecker Decomposition (BKD), and Aggregation-Aware Decomposition (AAD), each targeting a specific issue. These techniques are complementary and can be applied simultaneously to achieve optimal performance. Additionally, we provide a rigorous theoretical analysis to ensure the convergence of the proposed MUD. Extensive experimental results show that our approach achieves faster convergence and superior accuracy compared to relevant baseline methods. The code is available at https://github.com/Leopold1423/fedmud-icml25.
Authors: Shiwei Li, Xiandi Luo, Xing Tang, Haozhao Wang, Hao Chen, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li
Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method. In standard LoRA layers, one of the matrices, $A$ or $B$, is initialized to zero, ensuring that fine-tuning starts from the pretrained model. However, there is no theoretical support for this practice. In this paper, we investigate the impact of non-zero initialization on LoRA's fine-tuning dynamics from an infinite-width perspective. Our analysis reveals that, compared to zero initialization, simultaneously initializing $A$ and $B$ to non-zero values improves LoRA's robustness to suboptimal learning rates, particularly smaller ones. Further analysis indicates that although the non-zero initialization of $AB$ introduces random noise into the pretrained weight, it generally does not affect fine-tuning performance. In other words, fine-tuning does not need to strictly start from the pretrained model. The validity of our findings is confirmed through extensive experiments across various models and datasets. The code is available at https://github.com/Leopold1423/non_zero_lora-icml25.
Authors: Sakhinana Sagar Srinivas, Shivam Gupta, Venkataramana Runkana
Abstract: Recent advances in generative AI have accelerated the discovery of novel chemicals and materials. However, scaling these discoveries to industrial production remains a major bottleneck due to the synthesis gap -- the need to develop entirely new manufacturing processes. This challenge requires detailed engineering blueprints: PFDs for equipment layouts and material/energy flows, and PIDs for process plant operations. Current AI systems cannot yet reliably generate these critical engineering schematics, creating a fundamental obstacle to manufacturing scale-up of novel discoveries. We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs. The framework integrates three key components: (1) domain-specialized small language models (SLMs) trained for auto-generation of PFDs and PIDs, (2) a hierarchical knowledge graph containing process flow and instrumentation descriptions for 1,020+ chemicals for Graph Retrieval-Augmented Generation (GRAG), and (3) an open-source chemical process simulator for modeling, simulation, optimization, and analysis of novel chemical processes. The SLMs are trained through a multi-stage pipeline on synthetic datasets, with process simulator-in-the-loop validation ensuring feasibility. To enhance computational efficiency, the framework implements structural pruning (width and depth) guided by importance heuristics to reduce language model size while preserving accuracy, followed by advanced inference optimizations including FlashAttention, Lookahead Decoding, PagedAttention with KV-cache quantization, and Test-Time Inference Scaling. Experimental results demonstrate that our framework generates simulator-validated process descriptions with high fidelity.
Authors: Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xinyun Liu, Yulia Tsvetkov
Abstract: Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for shortest path: we need generalization from synthetic graph data to real-world tasks with implicit graph structures. In this work, we propose to unlock generalizable learning of graph with post-training alignment with synthetic data. We first design solution-based and process-based rewards for synthetic graph problems: instead of rigid memorizing response patterns in direct fine-tuning, we posit that post-training alignment would help LLMs grasp the essentials underlying graph reasoning and alleviate overfitting on synthetic data. We employ post-training alignment algorithms such as GRPO and DPO, aligning both off-the-shelf LLMs and LLMs fine-tuned on synthetic graph data. We then compare them against existing settings on both in-domain synthetic tasks and out-of-domain real-world tasks with implicit graph structures such as multi-hop QA, structured planning, and more. Extensive experiments demonstrate that our post-training alignment recipe leads to statistically significant improvement on 5 datasets, with an average gain of 12.9% over baseline settings. Further analysis reveals that process-based rewards consistently outperform solution-based rewards on synthetic data but not on real-world tasks, and compositionality and explainable intermediate steps remains a critical challenge even after post-training alignment.
Authors: Ryotaro Kawata, Kohsei Matsutani, Yuri Kinoshita, Naoki Nishikawa, Taiji Suzuki
Abstract: Mixture of Experts (MoE), an ensemble of specialized models equipped with a router that dynamically distributes each input to appropriate experts, has achieved successful results in the field of machine learning. However, theoretical understanding of this architecture is falling behind due to its inherent complexity. In this paper, we theoretically study the sample and runtime complexity of MoE following the stochastic gradient descent (SGD) when learning a regression task with an underlying cluster structure of single index models. On the one hand, we prove that a vanilla neural network fails in detecting such a latent organization as it can only process the problem as a whole. This is intrinsically related to the concept of information exponent which is low for each cluster, but increases when we consider the entire task. On the other hand, we show that a MoE succeeds in dividing this problem into easier subproblems by leveraging the ability of each expert to weakly recover the simpler function corresponding to an individual cluster. To the best of our knowledge, this work is among the first to explore the benefits of the MoE framework by examining its SGD dynamics in the context of nonlinear regression.
Authors: Minh Luu, Surya Jasper, Khoi Le, Evan Pan, Michael Quinn, Aakash Tyagi, Jiang Hu
Abstract: Failure triage in design functional verification is critical but time-intensive, relying on manual specification reviews, log inspections, and waveform analyses. While machine learning (ML) has improved areas like stimulus generation and coverage closure, its application to RTL-level simulation failure triage, particularly for large designs, remains limited. VCDiag offers an efficient, adaptable approach using VCD data to classify failing waveforms and pinpoint likely failure locations. In the largest experiment, VCDiag achieves over 94% accuracy in identifying the top three most likely modules. The framework introduces a novel signal selection and statistical compression approach, achieving over 120x reduction in raw data size while preserving features essential for classification. It can also be integrated into diverse Verilog/SystemVerilog designs and testbenches.
Authors: Chase Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn, David J. Schwab
Abstract: In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate empirically the conditions necessary on the pretraining distribution for ICL to emerge and generalize \emph{out-of-distribution}. Previous work has focused on the number of distinct tasks necessary in the pretraining dataset. Here, we use a different notion of task diversity to study the emergence of ICL in transformers trained on linear functions. We find that as task diversity increases, transformers undergo a transition from a specialized solution, which exhibits ICL only within the pretraining task distribution, to a solution which generalizes out of distribution to the entire task space. We also investigate the nature of the solutions learned by the transformer on both sides of the transition, and observe similar transitions in nonlinear regression problems. We construct a phase diagram to characterize how our concept of task diversity interacts with the number of pretraining tasks. In addition, we explore how factors such as the depth of the model and the dimensionality of the regression problem influence the transition.
Authors: Saptarshi Nath, Christos Peridis, Eseoghene Benjamin, Xinran Liu, Soheil Kolouri, Peter Kinnell, Zexin Li, Cong Liu, Shirin Dora, Andrea Soltoggio
Abstract: Agentic AI aims to create systems that set their own goals, adapt proactively to change, and refine behavior through continuous experience. Recent advances suggest that, when facing multiple and unforeseen tasks, agents could benefit from sharing machine-learned knowledge and reuse policies that have already been fully or partially learned by other agents. However, how to query, select, and retrieve policies from a pool of agents, and how to integrate such policies remains a largely unexplored area. This study explores how an agent decides what knowledge to select, from whom, and when and how to integrate it in its own policy in order to accelerate its own learning. The proposed algorithm, \emph{Modular Sharing and Composition in Collective Learning} (MOSAIC), improves learning in agentic collectives by combining (1) knowledge selection using performance signals and cosine similarity on Wasserstein task embeddings, (2) modular and transferable neural representations via masks, and (3) policy integration, composition and fine-tuning. MOSAIC outperforms isolated learners and global sharing approaches in both learning speed and overall performance, and in some cases solves tasks that isolated agents cannot. The results also demonstrate that selective, goal-driven reuse leads to less susceptibility to task interference. We also observe the emergence of self-organization, where agents solving simpler tasks accelerate the learning of harder ones through shared knowledge.
Authors: Andr\'es Guzm\'an-Cordero, Floor Eijkelboom, Jan-Willem van de Meent
Abstract: While denoising diffusion and flow matching have driven major advances in generative modeling, their application to tabular data remains limited, despite its ubiquity in real-world applications. To this end, we develop TabbyFlow, a variational Flow Matching (VFM) method for tabular data generation. To apply VFM to data with mixed continuous and discrete features, we introduce Exponential Family Variational Flow Matching (EF-VFM), which represents heterogeneous data types using a general exponential family distribution. We hereby obtain an efficient, data-driven objective based on moment matching, enabling principled learning of probability paths over mixed continuous and discrete variables. We also establish a connection between variational flow matching and generalized flow matching objectives based on Bregman divergences. Evaluation on tabular data benchmarks demonstrates state-of-the-art performance compared to baselines.
Authors: Mohammad Jalali, Bahar Dibaei Nia, Farzan Farnia
Abstract: While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable comparison of different embeddings requires identifying and analyzing mismatches between sample groups clustered within the embedding spaces. In this work, we propose the \emph{Spectral Pairwise Embedding Comparison (SPEC)} framework to compare embeddings and identify their differences in clustering a reference dataset. Our approach examines the kernel matrices derived from two embeddings and leverages the eigendecomposition of the difference kernel matrix to detect sample clusters that are captured differently by the two embeddings. We present a scalable implementation of this kernel-based approach, with computational complexity that grows linearly with the sample size. Furthermore, we introduce an optimization problem using this framework to align two embeddings, ensuring that clusters identified in one embedding are also captured in the other model. We provide numerical results demonstrating the SPEC's application to compare and align embeddings on large-scale datasets such as ImageNet and MS-COCO. The project page is available at https://mjalali.github.io/SPEC/.
Authors: Yuanzhe Hu, Kinshuk Goel, Vlad Killiakov, Yaoqing Yang
Abstract: Diagnosing deep neural networks (DNNs) by analyzing the eigenspectrum of their weights has been an active area of research in recent years. One of the main approaches involves measuring the heavytailness of the empirical spectral densities (ESDs) of weight matrices. This analysis has been shown to provide insights to help diagnose whether a model is well-trained or undertrained, and has been used to guide training methods involving layer-wise hyperparameter assignment. In this paper, we address an often-overlooked challenge in estimating the heavytailness of these ESDs: the impact of the aspect ratio of weight matrices. We demonstrate that matrices of varying sizes (and aspect ratios) introduce a non-negligible bias in estimating the heavytailness of ESDs, leading to inaccurate model diagnosis and layer-wise hyperparameter assignment. To overcome this challenge, we propose FARMS (Fixed-Aspect-Ratio Matrix Subsampling), a method that normalizes the weight matrices by subsampling submatrices with a fixed aspect ratio. Instead of measuring the heavytailness of the original ESD, we measure the average ESD of these subsampled submatrices. We show that this method effectively mitigates the aspect ratio bias. We validate our approach across various optimization techniques and application domains that involve eigenspectrum analysis of weights, including image classification in computer vision (CV) models, scientific machine learning (SciML) model training, and large language model (LLM) pruning. Our results show that despite its simplicity, FARMS uniformly improves the accuracy of eigenspectrum analysis while enabling more effective layer-wise hyperparameter assignment. In one of the LLM pruning experiments, FARMS reduces the perplexity of the LLaMA-7B model by 17.3% when compared with state-of-the-art methods.
Authors: Ruitao Chen, Mozhang Guo, Jinge Li
Abstract: Automated driving (AD) has substantially improved vehicle safety and driving comfort, but their impact on passenger well-being, particularly infant sleep, is not sufficiently studied. Sudden acceleration, abrupt braking, and sharp maneuvers can disrupt infant sleep, compromising both passenger comfort and parental convenience. To solve this problem, this paper explores the integration of reinforcement learning (RL) within AD to personalize driving behavior and optimally balance occupant comfort and travel efficiency. In particular, we propose an intelligent cruise control framework that adapts to varying driving conditions to enhance infant sleep quality by effectively synergizing wearable sensing and vehicle data. Long short-term memory (LSTM) and transformer-based neural networks are integrated with RL to model the relationship between driving behavior and infant sleep quality under diverse traffic and road conditions. Based on the sleep quality indicators from the wearable sensors, driving action data from vehicle controllers, and map data from map applications, the model dynamically computes the optimal driving aggressiveness level, which is subsequently translated into specific AD control strategies, e.g., the magnitude and frequency of acceleration, lane change, and overtaking. Simulation experiments conducted in the CARLA environment indicate that the proposed solution significantly improves infant sleep quality compared to baseline methods, while preserving desirable travel efficiency.
Authors: Yuan Yuan, Yukun Liu, Chonghua Han, Jie Feng, Yong Li
Abstract: Human mobility prediction is vital for urban planning, transportation optimization, and personalized services. However, the inherent randomness, non-uniform time intervals, and complex patterns of human mobility, compounded by the heterogeneity introduced by varying city structures, infrastructure, and population densities, present significant challenges in modeling. Existing solutions often require training separate models for each city due to distinct spatial representations and geographic coverage. In this paper, we propose UniMove, a unified model for multi-city human mobility prediction, addressing two challenges: (1) constructing universal spatial representations for effective token sharing across cities, and (2) modeling heterogeneous mobility patterns from varying city characteristics. We propose a trajectory-location dual-tower architecture, with a location tower for universal spatial encoding and a trajectory tower for sequential mobility modeling. We also design MoE Transformer blocks to adaptively select experts to handle diverse movement patterns. Extensive experiments across multiple datasets from diverse cities demonstrate that UniMove truly embodies the essence of a unified model. By enabling joint training on multi-city data with mutual data enhancement, it significantly improves mobility prediction accuracy by over 10.2\%. UniMove represents a key advancement toward realizing a true foundational model with a unified architecture for human mobility. We release the implementation at https://github.com/tsinghua-fib-lab/UniMove/.
Authors: Jihao Andreas Lin, Sebastian Ament, Maximilian Balandat, David Eriksson, Jos\'e Miguel Hern\'andez-Lobato, Eytan Bakshy
Abstract: Applying Gaussian processes (GPs) to very large datasets remains a challenge due to limited computational scalability. Matrix structures, such as the Kronecker product, can accelerate operations significantly, but their application commonly entails approximations or unrealistic assumptions. In particular, the most common path to creating a Kronecker-structured kernel matrix is by evaluating a product kernel on gridded inputs that can be expressed as a Cartesian product. However, this structure is lost if any observation is missing, breaking the Cartesian product structure, which frequently occurs in real-world data such as time series. To address this limitation, we propose leveraging latent Kronecker structure, by expressing the kernel matrix of observed values as the projection of a latent Kronecker product. In combination with iterative linear system solvers and pathwise conditioning, our method facilitates inference of exact GPs while requiring substantially fewer computational resources than standard iterative methods. We demonstrate that our method outperforms state-of-the-art sparse and variational GPs on real-world datasets with up to five million examples, including robotics, automated machine learning, and climate applications.
Authors: Simardeep Singh
Abstract: Large language models (LLMs) are known to memorize parts of their training data, raising important concerns around privacy and security. While previous research has focused on studying memorization in pre-trained models, much less is known about how knowledge distillation (KD) affects memorization.In this study, we explore how different KD methods influence the memorization of fine-tuned task data when a large teacher model is distilled into smaller student variants.This study demonstrates that distilling a larger teacher model, fine-tuned on a dataset, into a smaller variant not only lowers computational costs and model size but also significantly reduces the memorization risks compared to standard fine-tuning approaches.
Authors: Swagatam Das
Abstract: We present a formal operator-theoretic framework for analyzing Transformer-based language models using free probability theory. By modeling token embeddings and attention mechanisms as self-adjoint operators in a tracial \( W^* \)-probability space, we reinterpret attention as non-commutative convolution and describe representation propagation via free additive convolution. This leads to a spectral dynamic system interpretation of deep Transformers. We derive entropy-based generalization bounds under freeness assumptions and provide insight into positional encoding, spectral evolution, and representational complexity. This work offers a principled, though theoretical, perspective on structural dynamics in large language models.
Authors: Floor Eijkelboom, Heiko Zimmermann, Sharvaree Vadgama, Erik J Bekkers, Max Welling, Christian A. Naesseth, Jan-Willem van de Meent
Abstract: We derive a controlled generation objective within the framework of Variational Flow Matching (VFM), which casts flow matching as a variational inference problem. We demonstrate that controlled generation can be implemented two ways: (1) by way of end-to-end training of conditional generative models, or (2) as a Bayesian inference problem, enabling post hoc control of unconditional models without retraining. Furthermore, we establish the conditions required for equivariant generation and provide an equivariant formulation of VFM tailored for molecular generation, ensuring invariance to rotations, translations, and permutations. We evaluate our approach on both uncontrolled and controlled molecular generation, achieving state-of-the-art performance on uncontrolled generation and outperforming state-of-the-art models in controlled generation, both with end-to-end training and in the Bayesian inference setting. This work strengthens the connection between flow-based generative modeling and Bayesian inference, offering a scalable and principled framework for constraint-driven and symmetry-aware generation.
Authors: Zhihao Zhan, Jianan Zhao, Zhaocheng Zhu, Jian Tang
Abstract: Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominant Transformer architecture scales quadratically with the sequence length. While state-space models (SSMs) offer alternative sub-quadratic solutions, they struggle to capture long-range dependencies effectively. In this work, we focus on analyzing and improving the long-context modeling capabilities of SSMs. We show that the widely used synthetic task, associative recall, which requires a model to recall a value associated with a single key without context, insufficiently represents the complexities of real-world long-context modeling. To address this limitation, we extend the associative recall to a novel synthetic task, \emph{joint recall}, which requires a model to recall the value associated with a key given in a specified context. Theoretically, we prove that SSMs do not have the expressiveness to solve multi-query joint recall in sub-quadratic time complexity. To resolve this issue, we propose a solution based on integrating SSMs with Context-Dependent Sparse Attention (CDSA), which has the expressiveness to solve multi-query joint recall with sub-quadratic computation. To bridge the gap between theoretical analysis and real-world applications, we propose locality-sensitive Hashing Attention with sparse Key Selection (HAX), which instantiates the theoretical solution and is further tailored to natural language domains. Extensive experiments on both synthetic and real-world long-context benchmarks show that HAX consistently outperforms SSM baselines and SSMs integrated with context-independent sparse attention (CISA).
Authors: Zihan Tan, Suyuan Huang, Guancheng Wan, Wenke Huang, He Li, Mang Ye
Abstract: Federated Graph Learning (FGL) combines the privacy-preserving capabilities of federated learning (FL) with the strong graph modeling capability of Graph Neural Networks (GNNs). Current research addresses subgraph-FL from the structural perspective, neglecting the propagation of graph signals on spatial and spectral domains of the structure. From a spatial perspective, subgraph-FL introduces edge disconnections between clients, leading to disruptions in label signals and a degradation in the semantic knowledge of the global GNN. From a spectral perspective, spectral heterogeneity causes inconsistencies in signal frequencies across subgraphs, which makes local GNNs overfit the local signal propagation schemes. As a result, spectral client drift occurs, undermining global generalizability. To tackle the challenges, we propose a global knowledge repository to mitigate the challenge of poor semantic knowledge caused by label signal disruption. Furthermore, we design a frequency alignment to address spectral client drift. The combination of Spatial and Spectral strategies forms our framework S2FGL. Extensive experiments on multiple datasets demonstrate the superiority of S2FGL. The code is available at https://github.com/Wonder7racer/S2FGL.git.
Authors: Chongjie Si, Debing Zhang, Wei Shen
Abstract: We propose AdaMuon, a novel optimizer that combines element-wise adaptivity with orthogonal updates for large-scale neural network training. AdaMuon incorporates two tightly coupled mechanisms: (1) an element-wise second momentum estimator applied to orthogonalized update directions, and (2) a sign-stabilized orthogonal update, where the momentum is first sign-transformed before orthogonalization. These two components jointly enable variance-adaptive scaling while maintaining stable update geometry. In addition, AdaMuon employs an RMS-aligned rescaling strategy to match the root-mean-square update magnitude to Adam, allowing direct reuse of existing learning rate schedules without extra tuning. Experiments demonstrate that AdaMuon not only maintains stability but can surpass Adam by more than 40% training efficiency in large-scale scenarios.
Authors: Antoine Saillenfest, Pirmin Lemberger
Abstract: Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address this issue through concept erasure, a process that removes information related to a specific concept from distributed representations while preserving as much of the remaining semantic information as possible. Our approach involves learning an orthogonal projection in the embedding space, designed to make the class-conditional feature distributions of the discrete concept to erase indistinguishable after projection. By adjusting the rank of the projector, we control the extent of information removal, while its orthogonality ensures strict preservation of the local structure of the embeddings. Our method, termed $\overline{\mathrm{L}}$EOPARD, achieves state-of-the-art performance in nonlinear erasure of a discrete attribute on classic natural language processing benchmarks. Furthermore, we demonstrate that $\overline{\mathrm{L}}$EOPARD effectively mitigates bias in deep nonlinear classifiers, thereby promoting fairness.
Authors: H. M. Sabbir Ahmad, Ehsan Sabouni, Alexander Wasilkoff, Param Budhraja, Zijian Guo, Songyuan Zhang, Chuchu Fan, Christos Cassandras, Wenchao Li
Abstract: We address the problem of safe policy learning in multi-agent safety-critical autonomous systems. In such systems, it is necessary for each agent to meet the safety requirements at all times while also cooperating with other agents to accomplish the task. Toward this end, we propose a safe Hierarchical Multi-Agent Reinforcement Learning (HMARL) approach based on Control Barrier Functions (CBFs). Our proposed hierarchical approach decomposes the overall reinforcement learning problem into two levels learning joint cooperative behavior at the higher level and learning safe individual behavior at the lower or agent level conditioned on the high-level policy. Specifically, we propose a skill-based HMARL-CBF algorithm in which the higher level problem involves learning a joint policy over the skills for all the agents and the lower-level problem involves learning policies to execute the skills safely with CBFs. We validate our approach on challenging environment scenarios whereby a large number of agents have to safely navigate through conflicting road networks. Compared with existing state of the art methods, our approach significantly improves the safety achieving near perfect (within 5%) success/safety rate while also improving performance across all the environments.
Authors: Aditya Sharma, Ananya Gupta, Chengyu Wang, Chiamaka Adebayo, Jakub Kowalski
Abstract: Large Language Models (LLMs), despite their advanced linguistic capabilities, fundamentally lack an intuitive understanding of physical dynamics, which limits their effectiveness in real-world scenarios that require causal reasoning. In this paper, we introduce Causal World Model Induction (CWMI), a novel framework designed to embed an explicit model of causal physics within an LLM. Our approach incorporates a dedicated Causal Physics Module (CPM) and a new training objective called Causal Intervention Loss, encouraging the model to learn cause-and-effect relationships from multimodal data. By training the model to predict the outcomes of hypothetical interventions instead of merely capturing statistical correlations, CWMI develops a robust internal representation of physical laws. Experimental results show that CWMI significantly outperforms state-of-the-art LLMs on zero-shot physical reasoning tasks, including the PIQA benchmark and our newly proposed PhysiCa-Bench dataset. These findings demonstrate that inducing a causal world model is a critical step toward more reliable and generalizable AI systems.
Authors: Tianyi Xu, Yiting Chen, Henger Li, Zheyong Bian, Emiliano Dall'Anese, Zizhan Zheng
Abstract: We formalize sequential decision-making with information acquisition as the probing-augmented user-centric selection (PUCS) framework, where a learner first probes a subset of arms to obtain side information on resources and rewards, and then assigns $K$ plays to $M$ arms. PUCS covers applications such as ridesharing, wireless scheduling, and content recommendation, in which both resources and payoffs are initially unknown and probing is costly. For the offline setting with known distributions, we present a greedy probing algorithm with a constant-factor approximation guarantee $\zeta = (e-1)/(2e-1)$. For the online setting with unknown distributions, we introduce OLPA, a stochastic combinatorial bandit algorithm that achieves a regret bound $\mathcal{O}(\sqrt{T} + \ln^{2} T)$. We also prove a lower bound $\Omega(\sqrt{T})$, showing that the upper bound is tight up to logarithmic factors. Experiments on real-world data demonstrate the effectiveness of our solutions.
Authors: Zhilong Zhao, Yindi Liu
Abstract: LLMs enable qualitative coding at large scale, but assessing reliability remains challenging where human experts seldom agree. We investigate confidence-diversity calibration as a quality assessment framework for accessible coding tasks where LLMs already demonstrate strong performance but exhibit overconfidence. Analysing 5,680 coding decisions from eight state-of-the-art LLMs across ten categories, we find that mean self-confidence tracks inter-model agreement closely (Pearson r=0.82). Adding model diversity quantified as normalised Shannon entropy produces a dual signal explaining agreement almost completely (R-squared=0.979), though this high predictive power likely reflects task simplicity for current LLMs. The framework enables a three-tier workflow auto-accepting 35 percent of segments with less than 5 percent error, cutting manual effort by 65 percent. Cross-domain validation confirms transferability (kappa improvements of 0.20 to 0.78). While establishing a methodological foundation for AI judgement calibration, the true potential likely lies in more challenging scenarios where LLMs may demonstrate comparative advantages over human cognitive limitations.
Authors: Bang Hu, Changze Lv, Mingjie Li, Yunpeng Liu, Xiaoqing Zheng, Fengzhe Zhang, Wei cao, Fan Zhang
Abstract: Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, offer a distinctive approach for capturing the complexities of temporal data. However, their potential for spatial modeling in multivariate time-series forecasting remains largely unexplored. To bridge this gap, we introduce a brand new SNN architecture, which is among the first to seamlessly integrate graph structural learning with spike-based temporal processing for multivariate time-series forecasting. Specifically, we first embed time features and an adaptive matrix, eliminating the need for predefined graph structures. We then further learn sequence features through the Observation (OBS) Block. Building upon this, our Multi-Scale Spike Aggregation (MSSA) hierarchically aggregates neighborhood information through spiking SAGE layers, enabling multi-hop feature extraction while eliminating the need for floating-point operations. Finally, we propose a Dual-Path Spike Fusion (DSF) Block to integrate spatial graph features and temporal dynamics via a spike-gated mechanism, combining LSTM-processed sequences with spiking self-attention outputs, effectively improve the model accuracy of long sequence datasets. Experiments show that our model surpasses the state-of-the-art SNN-based iSpikformer on all datasets and outperforms traditional temporal models at long horizons, thereby establishing a new paradigm for efficient spatial-temporal modeling.
Authors: Hanqi Feng, Peng Qiu, Mengchun Zhang, Yiran Tao, You Fan, Jingtao Xu, Barnabas Poczos
Abstract: Recent advances in diffusion models have shown remarkable potential for antibody design, yet existing approaches apply uniform generation strategies that cannot adapt to each antigen's unique requirements. Inspired by B cell affinity maturation, where antibodies evolve through multi-objective optimization balancing affinity, stability, and self-avoidance, we propose the first biologically-motivated framework that leverages physics-based domain knowledge within an online meta-learning system. Our method employs multiple specialized experts (van der Waals, molecular recognition, energy balance, and interface geometry) whose parameters evolve during generation based on iterative feedback, mimicking natural antibody refinement cycles. Instead of fixed protocols, this adaptive guidance discovers personalized optimization strategies for each target. Our experiments demonstrate that this approach: (1) discovers optimal SE(3)-equivariant guidance strategies for different antigen classes without pre-training, preserving molecular symmetries throughout optimization; (2) significantly enhances hotspot coverage and interface quality through target-specific adaptation, achieving balanced multi-objective optimization characteristic of therapeutic antibodies; (3) establishes a paradigm for iterative refinement where each antibody-antigen system learns its unique optimization profile through online evaluation; (4) generalizes effectively across diverse design challenges, from small epitopes to large protein interfaces, enabling precision-focused campaigns for individual targets.
Authors: Jaehyung Lim, Wonbin Kweon, Woojoo Kim, Junyoung Kim, Seongjin Choi, Dongha Kim, Hwanjo Yu
Abstract: The increasing emphasis on privacy in recommendation systems has led to the adoption of Federated Learning (FL) as a privacy-preserving solution, enabling collaborative training without sharing user data. While Federated Recommendation (FedRec) effectively protects privacy, existing methods struggle with non-stationary data streams, failing to maintain consistent recommendation quality over time. On the other hand, Continual Learning Recommendation (CLRec) methods address evolving user preferences but typically assume centralized data access, making them incompatible with FL constraints. To bridge this gap, we introduce Federated Continual Recommendation (FCRec), a novel task that integrates FedRec and CLRec, requiring models to learn from streaming data while preserving privacy. As a solution, we propose F3CRec, a framework designed to balance knowledge retention and adaptation under the strict constraints of FCRec. F3CRec introduces two key components: Adaptive Replay Memory on the client side, which selectively retains past preferences based on user-specific shifts, and Item-wise Temporal Mean on the server side, which integrates new knowledge while preserving prior information. Extensive experiments demonstrate that F3CRec outperforms existing approaches in maintaining recommendation quality over time in a federated environment.
Authors: Feiyu Wang, Guoan Wang, Yihao Zhang, Shengfan Wang, Weitao Li, Bokai Huang, Shimao Chen, Zihan Jiang, Rui Xu, Tong Yang
Abstract: Quantization-Aware Training (QAT) integrates quantization into the training loop, enabling LLMs to learn robust low-bit representations, and is widely recognized as one of the most promising research directions. All current QAT research focuses on minimizing quantization error on full-precision models, where the full-precision accuracy acts as an upper bound (accuracy ceiling). No existing method has even attempted to surpass this ceiling. To break this ceiling, we propose a new paradigm: raising the ceiling (full-precision model), and then still quantizing it efficiently into 2 bits. We propose Fairy$\pm i$, the first 2-bit quantization framework for complex-valued LLMs. Specifically, our method leverages the representational advantages of the complex domain to boost full-precision accuracy. We map weights to the fourth roots of unity $\{\pm1, \pm i\}$, forming a perfectly symmetric and information-theoretically optimal 2-bit representation. Importantly, each quantized weight has either a zero real or imaginary part, enabling multiplication-free inference using only additions and element swaps. Experimental results show that Fairy$\pm i$ outperforms the ceiling of existing 2-bit quantization approaches in terms of both PPL and downstream tasks, while maintaining strict storage and compute efficiency. This work opens a new direction for building highly accurate and practical LLMs under extremely low-bit constraints.
Authors: Ruiyu Zhang, Ce Zhao, Xin Zhao, Lin Nie, Wai-Fung Lam
Abstract: Learning interpretable latent representations from tabular data remains a challenge in deep generative modeling. We introduce SE-VAE (Structural Equation-Variational Autoencoder), a novel architecture that embeds measurement structure directly into the design of a variational autoencoder. Inspired by structural equation modeling, SE-VAE aligns latent subspaces with known indicator groupings and introduces a global nuisance latent to isolate construct-specific confounding variation. This modular architecture enables disentanglement through design rather than through statistical regularizers alone. We evaluate SE-VAE on a suite of simulated tabular datasets and benchmark its performance against a series of leading baselines using standard disentanglement metrics. SE-VAE consistently outperforms alternatives in factor recovery, interpretability, and robustness to nuisance variation. Ablation results reveal that architectural structure, rather than regularization strength, is the key driver of performance. SE-VAE offers a principled framework for white-box generative modeling in scientific and social domains where latent constructs are theory-driven and measurement validity is essential.
Authors: Keyuan Zhang, Yin Sun, Bo Ji
Abstract: We consider a remote inference system with multiple modalities, where a multimodal machine learning (ML) model performs real-time inference using features collected from remote sensors. When sensor observations evolve dynamically over time, fresh features are critical for inference tasks. However, timely delivery of features from all modalities is often infeasible because of limited network resources. Towards this end, in this paper, we study a two-modality scheduling problem that seeks to minimize the ML model's inference error, expressed as a penalty function of the Age of Information (AoI) vector of the two modalities. We develop an index-based threshold policy and prove its optimality. Specifically, the scheduler switches to the other modality once the current modality's index function exceeds a predetermined threshold. We show that both modalities share the same threshold and that the index functions and the threshold can be computed efficiently. Our optimality results hold for general AoI functions (which could be non-monotonic and non-separable) and heterogeneous transmission times across modalities. To demonstrate the importance of considering a task-oriented AoI function, we conduct numerical experiments based on robot state prediction and compare our policy with round-robin and uniform random policies (both are oblivious to the AoI and the inference error).n The results show that our policy reduces inference error by up to 55% compared with these baselines.
Authors: Junyu Wu, Weiming Chang, Xiaotao Liu, Guanyou He, Tingfeng Xian, Haoqiang Hong, Boqi Chen, Hongtao Tian, Tao Yang, Yunsheng Shi, Feng Lin, Ting Yao, Jiatao Xu
Abstract: Reinforcement Learning from Human Feedback (RLHF) has emerged as a prominent paradigm for training large language models and multimodal systems. Despite the notable advances enabled by existing RLHF training frameworks, significant challenges remain to scale to complex multimodal workflows and adapt to dynamic workloads. In particular, current systems often encounter limitations related to controller scalability when managing large models, as well as inefficiencies in orchestrating intricate RLHF pipelines, especially in scenarios that require dynamic sampling and resource allocation. In this paper, we introduce WeChat-YATT Yet Another Transformer Trainer in WeChat, a simple, scalable, and balanced RLHF training framework specifically designed to address these challenges. WeChat-YATT features a parallel controller programming model that enables flexible and efficient orchestration of complex RLHF workflows, effectively mitigating bottlenecks associated with centralized controller architectures and facilitating scalability in large-scale data scenarios. In addition, we propose a dynamic placement schema that adaptively partitions computational resources and schedules workloads, thereby significantly reducing hardware idle time and improving GPU utilization under variable training conditions. We evaluate WeChat-YATT across diverse experimental scenarios, demonstrating its substantial throughput improvements over state-of-the-art RLHF training frameworks. Furthermore, WeChat-YATT has been successfully deployed to train models that support WeChat product features for a large-scale user base, underscoring its effectiveness and robustness in real-world applications. We have made WeChat-YATT publicly available at https://www.github.com/tencent/WeChat-YATT.
Authors: Ke Niu, Haiyang Yu, Zhuofan Chen, Mengyang Zhao, Teng Fu, Bin Li, Xiangyang Xue
Abstract: Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.
Authors: Will Fein, Ryan J. Horwitz, John E. Brown III, Amit Misra, Felipe Oviedo, Kevin White, Juan M. Lavista Ferres, Samuel K. Wasser
Abstract: The transnational ivory trade continues to drive the decline of elephant populations across Africa, and trafficking networks remain difficult to disrupt. Tusks seized by law enforcement officials carry forensic information on the traffickers responsible for their export, including DNA evidence and handwritten markings made by traffickers. For 20 years, analyses of tusk DNA have identified where elephants were poached and established connections among shipments of ivory. While the links established using genetic evidence are extremely conclusive, genetic data is expensive and sometimes impossible to obtain. But though handwritten markings are easy to photograph, they are rarely documented or analyzed. Here, we present an AI-driven pipeline for extracting and analyzing handwritten markings on seized elephant tusks, offering a novel, scalable, and low-cost source of forensic evidence. Having collected 6,085 photographs from eight large seizures of ivory over a 6-year period (2014-2019), we used an object detection model to extract over 17,000 individual markings, which were then labeled and described using state-of-the-art AI tools. We identified 184 recurring "signature markings" that connect the tusks on which they appear. 20 signature markings were observed in multiple seizures, establishing forensic links between these seizures through traffickers involved in both shipments. This work complements other investigative techniques by filling in gaps where other data sources are unavailable. The study demonstrates the transformative potential of AI in wildlife forensics and highlights practical steps for integrating handwriting analysis into efforts to disrupt organized wildlife crime.
Authors: Parsa Omidi, Xingshuai Huang, Axel Laborieux, Bahareh Nikpour, Tianyu Shi, Armaghan Eshaghi
Abstract: Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context retention, continual learning, and knowledge integration. This review presents a unified framework bridging neuroscience principles, including dynamic multi-timescale memory, selective attention, and consolidation, with engineering advances in Memory-Augmented Transformers. We organize recent progress through three taxonomic dimensions: functional objectives (context extension, reasoning, knowledge integration, adaptation), memory representations (parameter-encoded, state-based, explicit, hybrid), and integration mechanisms (attention fusion, gated control, associative retrieval). Our analysis of core memory operations (reading, writing, forgetting, and capacity management) reveals a shift from static caches toward adaptive, test-time learning systems. We identify persistent challenges in scalability and interference, alongside emerging solutions including hierarchical buffering and surprise-gated updates. This synthesis provides a roadmap toward cognitively-inspired, lifelong-learning Transformer architectures.
Authors: Ari Karchmer, Martin Pawelczyk, Seth Neel
Abstract: Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical influence or "datamodeling" remains very computationally expensive. This causes a critical trust issue: if only a few computationally rich parties can obtain data attributions, how can resource-constrained parties trust that the provided attributions are indeed "good," especially when they are used for important downstream applications (e.g., data pricing)? In this paper, we address this trust issue by proposing an interactive verification paradigm for data attribution. An untrusted and computationally powerful Prover learns data attributions, and then engages in an interactive proof with a resource-constrained Verifier. Our main result is a protocol that provides formal completeness, soundness, and efficiency guarantees in the sense of Probably-Approximately-Correct (PAC) verification. Specifically, if both Prover and Verifier follow the protocol, the Verifier accepts data attributions that are {\epsilon}-close to the optimal data attributions (in terms of the Mean Squared Error) with probability 1-{\delta}. Conversely, if the Prover arbitrarily deviates from the protocol, even with infinite compute, then this is detected (or it still yields data attributions to the Verifier) except with probability {\delta}. Importantly, our protocol ensures the Verifier's workload, measured by the number of independent model retrainings it must perform, scales only as O(1/{\epsilon}); i.e., independently of the dataset size. At a technical level, our results apply to efficiently verifying any linear function over the boolean hypercube computed by the Prover, making them broadly applicable to various attribution tasks.
Authors: Haitong Luo, Suhang Wang, Weiyao Zhang, Ruiqi Meng, Xuying Meng, Yujun Zhang
Abstract: Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, existing methods rely on homophily-based low-frequency knowledge, failing to handle diverse spectral distributions in real-world graphs with varying homophily. Our theoretical analysis reveals a spectral specificity principle: optimal knowledge transfer requires alignment between pre-trained spectral filters and the intrinsic spectrum of downstream graphs. Under limited supervision, large spectral gaps between pre-training and downstream tasks impede effective adaptation. To bridge this gap, we propose the HS-GPPT model, a novel framework that ensures spectral alignment throughout both pre-training and prompt-tuning. We utilize a hybrid spectral filter backbone and local-global contrastive learning to acquire abundant spectral knowledge. Then we design prompt graphs to align the spectral distribution with pretexts, facilitating spectral knowledge transfer across homophily and heterophily. Extensive experiments validate the effectiveness under both transductive and inductive learning settings. Our code is available at https://anonymous.4open.science/r/HS-GPPT-62D2/.
Authors: Shigang Li, Torsten Hoefler
Abstract: Communication overhead is one of the major obstacles to train large deep learning models at scale. Gradient sparsification is a promising technique to reduce the communication volume. However, it is very challenging to obtain real performance improvement because of (1) the difficulty of achieving an scalable and efficient sparse allreduce algorithm and (2) the sparsification overhead. This paper proposes O$k$-Top$k$, a scheme for distributed training with sparse gradients. O$k$-Top$k$ integrates a novel sparse allreduce algorithm (less than 6$k$ communication volume which is asymptotically optimal) with the decentralized parallel Stochastic Gradient Descent (SGD) optimizer, and its convergence is proved. To reduce the sparsification overhead, O$k$-Top$k$ efficiently selects the top-$k$ gradient values according to an estimated threshold. Evaluations are conducted on the Piz Daint supercomputer with neural network models from different deep learning domains. Empirical results show that O$k$-Top$k$ achieves similar model accuracy to dense allreduce. Compared with the optimized dense and the state-of-the-art sparse allreduces, O$k$-Top$k$ is more scalable and significantly improves training throughput (e.g., 3.29x-12.95x improvement for BERT on 256 GPUs).
Authors: Tzu-Quan Lin, Tsung-Huan Yang, Chun-Yao Chang, Kuang-Ming Chen, Tzu-hsun Feng, Hung-yi Lee, Hao Tang
Abstract: Transformer-based self-supervised models have achieved remarkable success in speech processing, but their large size and high inference cost present significant challenges for real-world deployment. While numerous compression techniques have been proposed, inconsistent evaluation metrics make it difficult to compare their practical effectiveness. In this work, we conduct a comprehensive study of four common compression methods, including weight pruning, head pruning, low-rank approximation, and knowledge distillation on self-supervised speech Transformers. We evaluate each method under three key metrics: parameter count, multiply-accumulate operations, and real-time factor. Results show that each method offers distinct advantages. In addition, we contextualize recent compression techniques, comparing DistilHuBERT, FitHuBERT, LightHuBERT, ARMHuBERT, and STaRHuBERT under the same framework, offering practical guidance on compression for deployment.
Authors: Rahul Singh, Suhas Vijaykumar
Abstract: We provide uniform confidence bands for kernel ridge regression (KRR), a widely used nonparametric regression estimator for nonstandard data such as preferences, sequences, and graphs. Despite the prevalence of these data--e.g., student preferences in school matching mechanisms--the inferential theory of KRR is not fully known. We construct valid and sharp confidence sets that shrink at nearly the minimax rate, allowing nonstandard regressors. Our bootstrap procedure uses anti-symmetric multipliers for computational efficiency and for validity under mis-specification. We use the procedure to develop a test for match effects, i.e. whether students benefit more from the schools they rank highly.
Authors: Iman Sharifi, Mustafa Yildirim, Saber Fallah
Abstract: The dynamic nature of driving environments and the presence of diverse road users pose significant challenges for decision-making in autonomous driving. Deep reinforcement learning (DRL) has emerged as a popular approach to tackle this problem. However, the application of existing DRL solutions is mainly confined to simulated environments due to safety concerns, impeding their deployment in real-world. To overcome this limitation, this paper introduces a novel neuro-symbolic model-free DRL approach, called DRL with Symbolic Logic (DRLSL) that combines the strengths of DRL (learning from experience) and symbolic first-order logic (knowledge-driven reasoning) to enable safe learning in real-time interactions of autonomous driving within real environments. This innovative approach provides a means to learn autonomous driving policies by actively engaging with the physical environment while ensuring safety. We have implemented the DRLSL framework in a highway driving scenario using the HighD dataset and demonstrated that our method successfully avoids unsafe actions during both the training and testing phases. Furthermore, our results indicate that DRLSL achieves faster convergence during training and exhibits better generalizability to new highway driving scenarios compared to traditional DRL methods.
Authors: Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He
Abstract: Zero-sum Linear Quadratic (LQ) games are fundamental in optimal control and can be used (i)~as a dynamic game formulation for risk-sensitive or robust control and (ii)~as a benchmark setting for multi-agent reinforcement learning with two competing agents in continuous state-control spaces. In contrast to the well-studied single-agent linear quadratic regulator problem, zero-sum LQ games entail solving a challenging nonconvex-nonconcave min-max problem with an objective function that lacks coercivity. Recently, Zhang et al. showed that an~$\epsilon$-Nash equilibrium (NE) of finite horizon zero-sum LQ games can be learned via nested model-free Natural Policy Gradient (NPG) algorithms with poly$(1/\epsilon)$ sample complexity. In this work, we propose a simpler nested Zeroth-Order (ZO) algorithm improving sample complexity by several orders of magnitude and guaranteeing convergence of the last iterate. Our main results are two-fold: (i) in the deterministic setting, we establish the first global last-iterate linear convergence result for the nested algorithm that seeks NE of zero-sum LQ games; (ii) in the model-free setting, we establish a~$\widetilde{\mathcal{O}}(\epsilon^{-2})$ sample complexity using a single-point ZO estimator. For our last-iterate convergence results, our analysis leverages the Implicit Regularization (IR) property and a new gradient domination condition for the primal function. Our key improvements in the sample complexity rely on a more sample-efficient nested algorithm design and a finer control of the ZO natural gradient estimation error utilizing the structure endowed by the finite-horizon setting.
Authors: Borui Tang, Jin Zhu, Junxian Zhu, Xueqin Wang, Heping Zhang
Abstract: Analysis of high-dimensional data has led to increased interest in both single index models (SIMs) and the best-subset selection. SIMs provide an interpretable and flexible modeling framework for high-dimensional data, while the best-subset selection aims to find a sparse model from a large set of predictors. However, the best-subset selection in high-dimensional models is known to be computationally intractable. Existing proxy algorithms are appealing but do not yield the bestsubset solution. In this paper, we directly tackle the intractability by proposing a provably scalable algorithm for the best-subset selection in high-dimensional SIMs. We directly proved the subset selection consistency and oracle property for our algorithmic solution, distinguishing it from other state-of-the-art support recovery methods in SIMs. The algorithm comprises a generalized information criterion to determine the support size of the regression coefficients, eliminating the model selection tuning. Moreover, our method does not assume an error distribution or a specific link function and hence is flexible to apply. Extensive simulation results demonstrate that our method is not only computationally efficient but also able to exactly recover the best subset in various settings (e.g., linear regression, Poisson regression, heteroscedastic models).
Authors: Mou Deb, Madhab Deb, Mrinal Kanti Dhar
Abstract: Accurate teeth segmentation and orientation are fundamental in modern oral healthcare, enabling precise diagnosis, treatment planning, and dental implant design. In this study, we present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep-learning techniques. We built an end-to-end instance segmentation network that uses an encoder-decoder architecture reinforced with grid-aware attention gates along the skip connections. We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation. Evaluating our approach on the publicly available DNS dataset, comprising 543 panoramic X-ray images, we achieve the highest Intersection-over-Union (IoU) score of 82.43% and a Dice Similarity Coefficient (DSC) score of 90.37% among compared models in teeth instance segmentation. In OBB analysis, we obtain a Rotated IoU (RIoU) score of 82.82%. We also conduct detailed analyses of individual tooth labels and categorical performance, shedding light on strengths and weaknesses. The proposed model's accuracy and versatility offer promising prospects for improving dental diagnoses, treatment planning, and personalized healthcare in the oral domain. Our generated OBB coordinates and code are available at https://github.com/mrinal054/Instance/teeth/segmentation.
URLs: https://github.com/mrinal054/Instance/teeth/segmentation.
Authors: Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Nathaniel Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter
Abstract: Prompt engineering is an effective but labor-intensive way to control text-to-image (T2I) generative models. Its time-intensive nature and complexity have spurred the development of algorithms for automated prompt generation. However, these methods often struggle with transferability across T2I models, require white-box access to the underlying model, or produce non-intuitive prompts. In this work, we introduce PRISM, an algorithm that automatically produces human-interpretable and transferable prompts that can effectively generate desired concepts given only black-box access to T2I models. Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompt distribution built upon the reference images. Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles, and images across multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney.
Authors: Lingxia Zhang, Xiaodie Lin, Peidong Wang, Kaiyan Yang, Xiao Zeng, Zhaohui Wei, Zizhu Wang
Abstract: Optimization drives advances in quantum science and machine learning, yet most generative models aim to mimic data rather than to discover optimal answers to challenging problems. Here we present a variational generative optimization network that learns to map simple random inputs into high quality solutions across a variety of quantum tasks. We demonstrate that the network rapidly identifies entangled states exhibiting an optimal advantage in entanglement detection when allowing classical communication, attains the ground state energy of an eighteen spin model without encountering the barren plateau phenomenon that hampers standard hybrid algorithms, and-after a single training run-outputs multiple orthogonal ground states of degenerate quantum models. Because the method is model agnostic, parallelizable and runs on current classical hardware, it can accelerate future variational optimization problems in quantum information, quantum computing and beyond.
Authors: Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang
Abstract: Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial Networks (CcGANs) were designed for this task, their instability during adversarial learning often leads to suboptimal results. Conditional Diffusion Models (CDMs) offer a promising alternative, generating more realistic images, but their diffusion processes, label conditioning, and model fitting procedures are either not optimized for or incompatible with CCGM, making it difficult to integrate CcGANs' vicinal approach. To address these issues, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM specifically tailored for CCGM. CCDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, a customized label embedding method, and efficient conditional sampling procedures. Through comprehensive experiments on four datasets with resolutions ranging from 64x64 to 192x192, we demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark. Ablation studies further validate the model design and implementation, highlighting that some widely used CDM implementations are ineffective for the CCGM task. Our code is publicly available at https://github.com/UBCDingXin/CCDM.
Authors: Yanling Wang, Haoyang Li, Hao Zou, Jing Zhang, Xinlei He, Qi Li, Ke Xu
Abstract: Despite advancements in large language models (LLMs), non-factual responses still persist in fact-seeking question answering. Unlike extensive studies on post-hoc detection of these responses, this work studies non-factuality prediction (NFP), predicting whether an LLM will generate a non-factual response prior to the response generation. Previous NFP methods have shown LLMs' awareness of their knowledge, but they face challenges in terms of efficiency and transferability. In this work, we propose a lightweight model named Factuality Lens (FacLens), which effectively probes hidden representations of fact-seeking questions for the NFP task. Moreover, we discover that hidden question representations sourced from different LLMs exhibit similar NFP patterns, enabling the transferability of FacLens across different LLMs to reduce development costs. Extensive experiments highlight FacLens's superiority in both effectiveness and efficiency.
Authors: Sophie Ostmeier, Brian Axelrod, Maya Varma, Michael E. Moseley, Akshay Chaudhari, Curtis Langlotz
Abstract: Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that encodes relative positions through fixed, block-diagonal, rotation matrices applied to key-query interactions. We hypothesize that this inductive bias limits their RoPE's effectiveness for modalities with high dimensional structure. Lie Relative Encodings (LieRE) introduce a principled generalization of RoPE, aimed at increasing the representational capacity of positional encodings in transformers. Instead of fixed 2D rotations, LieRE learns dense skew-symmetric matrices (Lie algebra elements), which are then differentiable mapped to form high-dimensional rotation matrices (Lie group elements). This results in richer, learnable, and continuous, encodings of both relative and absolute positional information. We demonstrate the effectiveness of LieRE on 2D and 3D vision tasks, showing that it generalizes well to higher input resolutions while maintaining computational efficiency. The code and checkpoints are publicly available at https://github.com/StanfordMIMI/LieRE.
Authors: David P. Hofmeyr, Francois Kamper, Michail C. Melonas
Abstract: In the Naive Bayes classification model the class conditional densities are estimated as the products of their marginal densities along the cardinal basis directions. We study the problem of obtaining an alternative basis for this factorisation with the objective of enhancing the discriminatory power of the associated classification model. We formulate the problem as a projection pursuit to find the optimal linear projection on which to perform classification. Optimality is determined based on the multinomial likelihood within which probabilities are estimated using the Naive Bayes factorisation of the projected data. Projection pursuit offers the added benefits of dimension reduction and visualisation. We discuss an intuitive connection with class conditional independent components analysis, and show how this is realised visually in practical applications. The performance of the resulting classification models is investigated using a large collection of (162) publicly available benchmark data sets and in comparison with relevant alternatives. We find that the proposed approach substantially outperforms other popular probabilistic discriminant analysis models and is highly competitive with Support Vector Machines. Code to implement the proposed approach, in the form of an R package, is available from https://github.com/DavidHofmeyr/OPNB
Authors: Hyunjong Ok, Jaeho Lee
Abstract: Singing voices contain much richer information than common voices, including varied vocal and acoustic properties. However, current open-source audio-text datasets for singing voices capture only a narrow range of attributes and lack acoustic features, leading to limited utility towards downstream tasks, such as style captioning. To fill this gap, we formally define the singing style captioning task and present S2Cap, a dataset of singing voices with detailed descriptions covering diverse vocal, acoustic, and demographic characteristics. Using this dataset, we develop an efficient and straightforward baseline algorithm for singing style captioning. The dataset is available at https://zenodo.org/records/15673764.
Authors: Giovanni Monea, Antoine Bosselut, Kiant\'e Brantley, Yoav Artzi
Abstract: Large Language Models (LLMs) excel at in-context learning (ICL), a supervised learning technique that relies on adding annotated examples to the model context. We investigate a contextual bandit version of in-context reinforcement learning (ICRL), where models learn in-context, online, from external reward, instead of supervised data. We show that LLMs effectively demonstrate such learning, and provide a detailed study of the phenomena, experimenting with challenging classification tasks and models of sizes from 500M to 70B parameters. This includes identifying and addressing the instability of the process, demonstrating learning with both semantic and abstract labels, and showing scaling trends. Our findings highlight ICRL capabilities in LLMs, while also underscoring fundamental limitations in their implicit reasoning about errors.
Authors: Amit Kumar Singh, Vrijendra Singh
Abstract: Deep learning and contactless sensing technologies have significantly advanced the automated assessment of human behaviors in healthcare. In the context of autism spectrum disorder (ASD), repetitive motor behaviors such as spinning, head banging, and arm flapping are key indicators for diagnosis. This study focuses on distinguishing between children with ASD and typically developed (TD) peers by analyzing videos captured in natural, uncontrolled environments. Using the publicly available Self-Stimulatory Behavior Dataset (SSBD), we address the classification task as a binary problem, ASD vs. TD, based on stereotypical repetitive gestures. We adopt a pipeline integrating YOLOv7-based detection, extensive video augmentations, and the VideoMAE framework, which efficiently captures both spatial and temporal features through a high-ratio masking and reconstruction strategy. Our proposed approach achieves 95% accuracy, 0.93 precision, 0.94 recall, and 0.94 F1 score, surpassing the previous state-of-the-art by a significant margin. These results demonstrate the effectiveness of combining advanced object detection, robust data augmentation, and masked autoencoder-based video modeling for reliable ASD vs. TD classification in naturalistic settings.
Authors: Yuki Ohnishi, Jordan Awan
Abstract: Differential privacy is the leading mathematical framework for privacy protection, providing a probabilistic guarantee that safeguards individuals' private information when publishing statistics from a dataset. This guarantee is achieved by applying a randomized algorithm to the original data, which introduces unique challenges in data analysis by distorting inherent patterns. In particular, causal inference using observational data in privacy-sensitive contexts is challenging because it requires covariate balance between treatment groups, yet checking the true covariates is prohibited to prevent leakage of sensitive information. In this article, we present a differentially private two-stage covariate balancing weighting estimator to infer causal effects from observational data. Our algorithm produces both point and interval estimators with statistical guarantees, such as consistency and rate optimality, under a given privacy budget.
Authors: Zhipeng Wei, Yuqi Liu, N. Benjamin Erichson
Abstract: Jailbreaking techniques trick Large Language Models (LLMs) into producing restricted output, posing a potential threat. One line of defense is to use another LLM as a Judge to evaluate the harmfulness of generated text. However, we reveal that these Judge LLMs are vulnerable to token segmentation bias, an issue that arises when delimiters alter the tokenization process, splitting words into smaller sub-tokens. This alters the embeddings of the entire sequence, reducing detection accuracy and allowing harmful content to be misclassified as safe. In this paper, we introduce Emoji Attack, a novel strategy that amplifies existing jailbreak prompts by exploiting token segmentation bias. Our method leverages in-context learning to systematically insert emojis into text before it is evaluated by a Judge LLM, inducing embedding distortions that significantly lower the likelihood of detecting unsafe content. Unlike traditional delimiters, emojis also introduce semantic ambiguity, making them particularly effective in this attack. Through experiments on state-of-the-art Judge LLMs, we demonstrate that Emoji Attack substantially reduces the unsafe prediction rate, bypassing existing safeguards.
Authors: Jonas Zausinger, Lars Pennig, Anamarija Kozina, Sean Sdahl, Julian Sikora, Adrian Dendorfer, Timofey Kuznetsov, Mohamad Hagog, Nina Wiedemann, Kacper Chlodny, Vincent Limbach, Anna Ketteler, Thorben Prein, Vishwa Mohan Singh, Michael Morris Danziger, Jannis Born
Abstract: While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving quantitative reasoning, especially arithmetic. One fundamental limitation is the nature of the cross-entropy (CE) loss, which assumes a nominal scale and thus cannot convey proximity between generated number tokens. In response, we here present a regression-like loss that operates purely on token level. Our proposed Number Token Loss (NTL) comes in two flavors and minimizes either the $L_p$ norm or the Wasserstein distance between the numerical values of the real and predicted number tokens. NTL can easily be added to any language model and extend the CE objective during training without runtime overhead. We evaluate the proposed scheme on various mathematical datasets and find that it consistently improves performance in math-related tasks. In a direct comparison on a regression task, we find that NTL can match the performance of a regression head, despite operating on token level. Finally, we scale NTL up to 3B parameter models and observe improved performance, demonstrating its potential for seamless integration into LLMs. We hope to inspire LLM developers to improve their pretraining objectives and distribute NTL as a minimalistic and lightweight PyPI package $ntloss$: https://github.com/ai4sd/number-token-loss. Development code for full paper reproduction is available separately.
Authors: Somayeh Farahani, Marjaneh Hejazi, Mehnaz Tabassum, Antonio Di Ieva, Neda Mahdavifar, Sidong Liu
Abstract: Objectives We aimed to evaluate the diagnostic performance of deep learning (DL)-based radiomics models for the noninvasive prediction of isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deletion status in glioma patients using MRI sequences, and to identify methodological factors influencing accuracy and generalizability. Materials and methods Following PRISMA guidelines, we systematically searched major databases (PubMed, Scopus, Embase, Web of Science, and Google Scholar) up to March 2025, screening studies that utilized DL to predict IDH and 1p/19q co-deletion status from MRI data. We assessed study quality and risk of bias using the Radiomics Quality Score and the QUADAS-2 tool. Our meta-analysis employed a bivariate model to compute pooled sensitivity and specificity, and meta-regression to assess interstudy heterogeneity. Results Among the 1517 unique publications, 104 were included in the qualitative synthesis, and 72 underwent meta-analysis. Pooled estimates for IDH prediction in test cohorts yielded a sensitivity of 0.80 and specificity of 0.85. For 1p/19q co-deletion, sensitivity was 0.75 and specificity was 0.82. Meta-regression identified the tumor segmentation method and the extent of DL integration into the radiomics pipeline as significant contributors to interstudy variability. Conclusion Although DL models demonstrate strong potential for noninvasive molecular classification of gliomas, clinical translation requires several critical steps: harmonization of multi-center MRI data using techniques such as histogram matching and DL-based style transfer; adoption of standardized and automated segmentation protocols; extensive multi-center external validation; and prospective clinical validation.
Authors: Aycan Deniz Vit, Ujal Rzayev, Bahrem Serhat Danis, Ali Najjar Amiri, Kazim Gorgulu, Emir Salih Magden
Abstract: We propose a novel design paradigm for arbitrarily capable deep photonic networks of cascaded Mach-Zehnder Interferometers (MZIs) for on-chip universal polarization handling. Using a device architecture made of cascaded Mach-Zehnder interferometers, we modify and train the phase difference between interferometer arms for both polarizations through wide operation bandwidths. Three proof-of-concept polarization handling devices are illustrated using a software-defined, physics-informed neural framework, to achieve user-specified target device responses as functions of polarization and wavelength. These devices include a polarization splitter, a polarization-independent power splitter, and an arbitrary polarization-dependent splitter to illustrate the capabilities of the design framework. The performance for all three devices is optimized using transfer matrix calculations; and their final responses are verified through 3D-FDTD simulations. All devices demonstrate state-of-the-art performance metrics with over 20 dB extinction, and flat-top transmission bands through bandwidths of 120 nm. In addition to the functional diversity enabled, the optimization for each device is completed in under a minute, highlighting the computational efficiency of the design paradigm presented. These results demonstrate the versatility of the deep photonic network design ecosystem in polarization management, unveiling promising prospects for advanced on-chip applications in optical communications, sensing, and computing.
Authors: Jakob Heiss, Florian Krach, Thorsten Schmidt, F\'elix B. Tambe-Ndonfack
Abstract: Neural Jump ODEs model the conditional expectation between observations by neural ODEs and jump at arrival of new observations. They have demonstrated effectiveness for fully data-driven online forecasting in settings with irregular and partial observations, operating under weak regularity assumptions. This work extends the framework to input-output systems, enabling direct applications in online filtering and classification. We establish theoretical convergence guarantees for this approach, providing a robust solution to $L^2$-optimal filtering. Empirical experiments highlight the model's superior performance over classical parametric methods, particularly in scenarios with complex underlying distributions. These results emphasise the approach's potential in time-sensitive domains such as finance and health monitoring, where real-time accuracy is crucial.
Authors: SeungBum Ha, Taehwan Lee, Jiyoun Lim, Sung Whan Yoon
Abstract: Federated learning (FL) enables decentralized training while preserving data privacy, yet existing FL benchmarks address relatively simple classification tasks, where each sample is annotated with a one-hot label. However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse semantic information, such as relations between objects. Because the existing benchmarks are designed to distribute data in a narrow view of a single semantic, managing the complicated semantic heterogeneity across clients when formalizing FL benchmarks is non-trivial. In this paper, we propose a benchmark process to establish an FL benchmark with controllable semantic heterogeneity across clients: two key steps are (i) data clustering with semantics and (ii) data distributing via controllable semantic heterogeneity across clients. As a proof of concept, we construct a federated PSG benchmark, demonstrating the efficacy of the existing PSG methods in an FL setting with controllable semantic heterogeneity of scene graphs. We also present the effectiveness of our benchmark by applying robust federated learning algorithms to data heterogeneity to show increased performance. To our knowledge, this is the first benchmark framework that enables federated learning and its evaluation for multi-semantic vision tasks under the controlled semantic heterogeneity. Our code is available at https://github.com/Seung-B/FL-PSG.
Authors: Marius Memmel, Jacob Berg, Bingqing Chen, Abhishek Gupta, Jonathan Francis
Abstract: Robot learning is witnessing a significant increase in the size, diversity, and complexity of pre-collected datasets, mirroring trends in domains such as natural language processing and computer vision. Many robot learning methods treat such datasets as multi-task expert data and learn a multi-task, generalist policy by training broadly across them. Notably, while these generalist policies can improve the average performance across many tasks, the performance of generalist policies on any one task is often suboptimal due to negative transfer between partitions of the data, compared to task-specific specialist policies. In this work, we argue for the paradigm of training policies during deployment given the scenarios they encounter: rather than deploying pre-trained policies to unseen problems in a zero-shot manner, we non-parametrically retrieve and train models directly on relevant data at test time. Furthermore, we show that many robotics tasks share considerable amounts of low-level behaviors and that retrieval at the "sub"-trajectory granularity enables significantly improved data utilization, generalization, and robustness in adapting policies to novel problems. In contrast, existing full-trajectory retrieval methods tend to underutilize the data and miss out on shared cross-task content. This work proposes STRAP, a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion. STRAP outperforms both prior retrieval algorithms and multi-task learning methods in simulated and real experiments, showing the ability to scale to much larger offline datasets in the real world as well as the ability to learn robust control policies with just a handful of real-world demonstrations.
Authors: Shekhar Madhav Khairnar, Huu Phong Nguyen, Alexis Desir, Carla Holcomb, Daniel J. Scott, Ganesh Sankaranarayanan
Abstract: Automated assessment of surgical skills using artificial intelligence (AI) provides trainees with instantaneous feedback. After bimanual tool motions are captured, derived kinematic metrics are reliable predictors of performance in laparoscopic tasks. Implementing automated tool tracking requires time-intensive human annotation. We developed AI-based tool tracking using the Segment Anything Model (SAM) to eliminate the need for human annotators. Here, we describe a study evaluating the usefulness of our tool tracking model in automated assessment during a laparoscopic suturing task in the fundoplication procedure. An automated tool tracking model was applied to recorded videos of Nissen fundoplication on porcine bowel. Surgeons were grouped as novices (PGY1-2) and experts (PGY3-5, attendings). The beginning and end of each suturing step were segmented, and motions of the left and right tools were extracted. A low-pass filter with a 24 Hz cut-off frequency removed noise. Performance was assessed using supervised and unsupervised models, and an ablation study compared results. Kinematic features--RMS velocity, RMS acceleration, RMS jerk, total path length, and Bimanual Dexterity--were extracted and analyzed using Logistic Regression, Random Forest, Support Vector Classifier, and XGBoost. PCA was performed for feature reduction. For unsupervised learning, a Denoising Autoencoder (DAE) model with classifiers, such as a 1-D CNN and traditional models, was trained. Data were extracted for 28 participants (9 novices, 19 experts). Supervised learning with PCA and Random Forest achieved an accuracy of 0.795 and an F1 score of 0.778. The unsupervised 1-D CNN achieved superior results with an accuracy of 0.817 and an F1 score of 0.806, eliminating the need for kinematic feature computation. We demonstrated an AI model capable of automated performance classification, independent of human annotation.
Authors: Alexandre Caboussat, Anna Peruso
Abstract: Optimal transportation of raw material from suppliers to customers is an issue arising in logistics that is addressed here with a continuous model relying on optimal transport theory. A physics informed neuralnetwork method is advocated here for the solution of the corresponding generalized Monge-Amp`ere equation. Convex neural networks are advocated to enforce the convexity of the solution to the Monge-Amp\`ere equation and obtain a suitable approximation of the optimal transport map. A particular focus is set on the enforcement of transport boundary conditions in the loss function. Numerical experiments illustrate the solution to the optimal transport problem in several configurations, and sensitivity analyses are performed.
Authors: Fabrizio Sandri, Elia Cunegatti, Giovanni Iacca
Abstract: We propose a novel Two-Stage framework for Structured Pruning (\textsc{2SSP}) for pruning Large Language Models (LLMs), which combines two different strategies of pruning, namely Width and Depth Pruning. The first stage (Width Pruning) removes entire neurons, hence their corresponding rows and columns, aiming to preserve the connectivity among the pruned structures in the intermediate state of the Feed-Forward Networks in each Transformer block. This is done based on an importance score measuring the impact of each neuron on the output magnitude. The second stage (Depth Pruning), instead, removes entire Attention submodules. This is done by applying an iterative process that removes the Attention with the minimum impact on a given metric of interest (in our case, perplexity). We also propose a novel mechanism to balance the sparsity rate of the two stages w.r.t. to the desired global sparsity. We test \textsc{2SSP} on four LLM families and three sparsity rates (25\%, 37.5\%, and 50\%), measuring the resulting perplexity over three language modeling datasets as well as the performance over six downstream tasks. Our method consistently outperforms five state-of-the-art competitors over three language modeling and six downstream tasks, with an up to two-order-of-magnitude gain in terms of pruning time. The code is available at https://github.com/FabrizioSandri/2SSP.
Authors: Atsushi Nitanda, Anzelle Lee, Damian Tan Xing Kai, Mizuki Sakaguchi, Taiji Suzuki
Abstract: Mean-field Langevin dynamics (MFLD) is an optimization method derived by taking the mean-field limit of noisy gradient descent for two-layer neural networks in the mean-field regime. Recently, the propagation of chaos (PoC) for MFLD has gained attention as it provides a quantitative characterization of the optimization complexity in terms of the number of particles and iterations. A remarkable progress by Chen et al. (2022) showed that the approximation error due to finite particles remains uniform in time and diminishes as the number of particles increases. In this paper, by refining the defective log-Sobolev inequality -- a key result from that earlier work -- under the neural network training setting, we establish an improved PoC result for MFLD, which removes the exponential dependence on the regularization coefficient from the particle approximation term of the optimization complexity. As an application, we propose a PoC-based model ensemble strategy with theoretical guarantees.
Authors: Wonyoung Kim, Sungwoo Park, Garud Iyengar, Assaf Zeevi, Min-hwan Oh
Abstract: We study the linear bandit problem that accounts for partially observable features. Without proper handling, unobserved features can lead to linear regret in the decision horizon $T$, as their influence on rewards is unknown. To tackle this challenge, we propose a novel theoretical framework and an algorithm with sublinear regret guarantees. The core of our algorithm consists of (i) feature augmentation, by appending basis vectors that are orthogonal to the row space of the observed features; and (ii) the introduction of a doubly robust estimator. Our approach achieves a regret bound of $\tilde{O}(\sqrt{(d + d_h)T})$, where $d$ is the dimension of the observed features and $d_h$ depends on the extent to which the unobserved feature space is contained in the observed one, thereby capturing the intrinsic difficulty of the problem. Notably, our algorithm requires no prior knowledge of the unobserved feature space, which may expand as more features become hidden. Numerical experiments confirm that our algorithm outperforms both non-contextual multi-armed bandits and linear bandit algorithms depending solely on observed features.
Authors: Somaiyeh Dehghan, Mehmet Umut Sen, Berrin Yanikoglu
Abstract: Hate speech detection is a crucial task, especially on social media, where harmful content can spread quickly. Implementing machine learning models to automatically identify and address hate speech is essential for mitigating its impact and preventing its proliferation. The first step in developing an effective hate speech detection model is to acquire a high-quality dataset for training. Labeled data is essential for most natural language processing tasks, but categorizing hate speech is difficult due to the diverse and often subjective nature of hate speech, which can lead to varying interpretations and disagreements among annotators. This paper examines strategies for addressing annotator disagreement, an issue that has been largely overlooked. In particular, we evaluate various automatic approaches for aggregating multiple annotations, in the context of hate speech classification in Turkish tweets. Our work highlights the importance of the problem and provides state-of-the-art benchmark results for the detection and understanding of hate speech in online discourse.
Authors: Hengrui Luo, Yunzhang Zhu
Abstract: We derived the closed-form asymptotic optimism of linear regression models under random designs, and generalizes it to kernel ridge regression. Using scaled asymptotic optimism as a generic predictive model complexity measure, we studied the fundamental different behaviors of linear regression model, tangent kernel (NTK) regression model and three-layer fully connected neural networks (NN). Our contribution is two-fold: we provided theoretical ground for using scaled optimism as a model predictive complexity measure; and we show empirically that NN with ReLUs behaves differently from kernel models under this measure. With resampling techniques, we can also compute the optimism for regression models with real data.
Authors: Yupeng Hou, Jianmo Ni, Zhankui He, Noveen Sachdeva, Wang-Cheng Kang, Ed H. Chi, Julian McAuley, Derek Zhiyuan Cheng
Abstract: Generative recommendation (GR) is an emerging paradigm where user actions are tokenized into discrete token patterns and autoregressively generated as predictions. However, existing GR models tokenize each action independently, assigning the same fixed tokens to identical actions across all sequences without considering contextual relationships. This lack of context-awareness can lead to suboptimal performance, as the same action may hold different meanings depending on its surrounding context. To address this issue, we propose ActionPiece to explicitly incorporate context when tokenizing action sequences. In ActionPiece, each action is represented as a set of item features. Given the action sequence corpora, we construct the vocabulary by merging feature patterns as new tokens, based on their co-occurrence frequency both within individual sets and across adjacent sets. Considering the unordered nature of feature sets, we further introduce set permutation regularization, which produces multiple segmentations of action sequences with the same semantics. Our code is available at: https://github.com/google-deepmind/action_piece.
Authors: Yigitcan Yardimci, Mustafa Cavus
Abstract: The prediction of the Remaining Useful Life of aircraft engines is a critical area in high-reliability sectors such as aerospace and defense. Early failure predictions help ensure operational continuity, reduce maintenance costs, and prevent unexpected failures. Traditional regression models struggle with censored data, which can lead to biased predictions. Survival models, on the other hand, effectively handle censored data, improving predictive accuracy in maintenance processes. This paper introduces a novel approach based on the Rashomon perspective, which considers multiple models that achieve similar performance rather than relying on a single best model. This enables uncertainty quantification in survival probability predictions and enhances decision-making in predictive maintenance. The Rashomon survival curve was introduced to represent the range of survival probability estimates, providing insights into model agreement and uncertainty over time. The results on the CMAPSS dataset demonstrate that relying solely on a single model for RUL estimation may increase risk in some scenarios. The censoring levels significantly impact prediction uncertainty, with longer censoring times leading to greater variability in survival probabilities. These findings underscore the importance of incorporating model multiplicity in predictive maintenance frameworks to achieve more reliable and robust failure predictions. This paper contributes to uncertainty quantification in RUL prediction and highlights the Rashomon perspective as a powerful tool for predictive modeling.
Authors: Shiwon Kim, Dongjun Hwang, Sungwon Woo, Rita Singh
Abstract: Class-incremental learning (CIL) aims to adapt to continuously emerging new classes while preserving knowledge of previously learned ones. Few-shot class-incremental learning (FSCIL) presents a greater challenge that requires the model to learn new classes from only a limited number of samples per class. While incremental learning typically assumes restricted access to past data, it often remains available in many real-world scenarios. This raises a practical question: should one retrain the model on the full dataset (i.e., joint training), or continue updating it solely with new data? In CIL, joint training is considered an ideal benchmark that provides a reference for evaluating the trade-offs between performance and computational cost. However, in FSCIL, joint training becomes less reliable due to severe imbalance between base and incremental classes. This results in the absence of a practical baseline, making it unclear which strategy is preferable for practitioners. To this end, we revisit joint training in the context of FSCIL by incorporating imbalance mitigation techniques, and suggest a new imbalance-aware joint training benchmark for FSCIL. We then conduct extensive comparisons between this benchmark and FSCIL methods to analyze which approach is most suitable when prior data is accessible. Our analysis offers realistic insights and guidance for selecting training strategies in real-world FSCIL scenarios. Code is available at: https://github.com/shiwonkim/Joint_FSCIL
Authors: Emma Hannula, Arttu H\"akkinen, Antti Solonen, Felipe Uribe, Jana de Wiljes, Lassi Roininen
Abstract: Improving the energy efficiency of building heating systems is crucial for reducing global energy consumption and greenhouse gas emissions. Traditional control methods rely on static heating curves that are based solely on outdoor temperature, neglecting system state measurements, such as indoor temperature, and free heat sources, such as solar gain. A more effective strategy is model predictive control (MPC), which optimizes heating control by incorporating system state predictions based on weather forecasts, among other factors. However, current industrial MPC solutions often employ simplified physics-inspired indoor temperature models, sacrificing accuracy for robustness and interpretability. To bridge this gap, we propose a partially stochastic deep learning (DL) architecture for building-specific indoor temperature modeling. Unlike most studies that evaluate model performance through simulations or limited test buildings, our experiments across a large dataset of 100 real-world buildings, covering various heating season conditions, demonstrate that the proposed model outperforms a widely used industrial physics-based model in predictive accuracy. The proposed DL architecture shows significant potential to improve thermal comfort and energy efficiency in heating MPC solutions. Although its computational cost is higher than that of the reference model, we discuss why this trade-off is manageable, even in large-scale applications. Unlike deterministic black-box approaches, the partially stochastic DL model offers a critical advantage by enabling pre-assessment of model feasibility through predictive uncertainty quantification. This work advances heating MPC, particularly for buildings with comprehensive datasets on their thermal behavior under various weather conditions.
Authors: William Fleshman, Benjamin Van Durme
Abstract: Training large, general-purpose language models poses significant challenges. The growing availability of specialized expert models, fine-tuned from pretrained models for specific tasks or domains, offers a promising alternative. Leveraging the potential of these existing expert models in real-world applications requires effective methods to select or merge the models best suited for a given task. This paper introduces SPECTR, an approach for dynamically composing expert models at each time step during inference. Notably, our method requires no additional training and enables flexible, token- and layer-wise model combinations. Our experimental results demonstrate that SPECTR improves routing accuracy over alternative training-free methods, increasing task performance across expert domains.
Authors: Benjamin Lipkin, Benjamin LeBrun, Jacob Hoover Vigly, Jo\~ao Loula, David R. MacIver, Li Du, Jason Eisner, Ryan Cotterell, Vikash Mansinghka, Timothy J. O'Donnell, Alexander K. Lew, Tim Vieira
Abstract: The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is achieved through token masking: looping over the vocabulary and excluding non-conforming tokens. There are two important problems with this approach. (i) Evaluating the constraint on every token can be prohibitively expensive -- LM vocabularies often exceed $100,000$ tokens. (ii) LCD can distort the global distribution over strings, sampling tokens based only on local information, even if they lead down dead-end paths. This work introduces a new algorithm that addresses both these problems. First, to avoid evaluating a constraint on the full vocabulary at each step of generation, we propose an adaptive rejection sampling algorithm that typically requires orders of magnitude fewer constraint evaluations. Second, we show how this algorithm can be extended to produce low-variance, unbiased estimates of importance weights at a very small additional cost -- estimates that can be soundly used within previously proposed sequential Monte Carlo algorithms to correct for the myopic behavior of local constraint enforcement. Through extensive empirical evaluation in text-to-SQL, molecular synthesis, goal inference, pattern matching, and JSON domains, we show that our approach is superior to state-of-the-art baselines, supporting a broader class of constraints and improving both runtime and performance. Additional theoretical and empirical analyses show that our method's runtime efficiency is driven by its dynamic use of computation, scaling with the divergence between the unconstrained and constrained LM, and as a consequence, runtime improvements are greater for better models.
Authors: Feijiang Han, Jiaming Zhang, Chuyi Deng, Jianheng Tang, Yunhuai Liu
Abstract: WebShell attacks, where malicious scripts are injected into web servers, pose a significant cybersecurity threat. Traditional ML and DL methods are often hampered by challenges such as the need for extensive training data, catastrophic forgetting, and poor generalization. Recently, Large Language Models have emerged as powerful alternatives for code-related tasks, but their potential in WebShell detection remains underexplored. In this paper, we make two contributions: (1) a comprehensive evaluation of seven LLMs, including GPT-4, LLaMA 3.1 70B, and Qwen 2.5 variants, benchmarked against traditional sequence- and graph-based methods using a dataset of 26.59K PHP scripts, and (2) the Behavioral Function-Aware Detection (BFAD) framework, designed to address the specific challenges of applying LLMs to this domain. Our framework integrates three components: a Critical Function Filter that isolates malicious PHP function calls, a Context-Aware Code Extraction strategy that captures the most behaviorally indicative code segments, and Weighted Behavioral Function Profiling that enhances in-context learning by prioritizing the most relevant demonstrations based on discriminative function-level profiles. Our results show that, stemming from their distinct analytical strategies, larger LLMs achieve near-perfect precision but lower recall, while smaller models exhibit the opposite trade-off. However, all baseline models lag behind previous SOTA methods. With the application of BFAD, the performance of all LLMs improves significantly, yielding an average F1 score increase of 13.82%. Notably, larger models now outperform SOTA benchmarks, while smaller models such as Qwen-2.5-Coder-3B achieve performance competitive with traditional methods. This work is the first to explore the feasibility and limitations of LLMs for WebShell detection and provides solutions to address the challenges in this task.
Authors: Zhiyuan Zheng, Jianpeng Qi, Jiantao Li, Guoqing Chao, Junyu Dong, Yanwei Yu
Abstract: Understanding the dynamic transition of motifs in temporal graphs is essential for revealing how graph structures evolve over time, identifying critical patterns, and predicting future behaviors, yet existing methods often focus on predefined motifs, limiting their ability to comprehensively capture transitions and interrelationships. We propose a parallel motif transition process discovery algorithm, PTMT, a novel parallel method for discovering motif transition processes in large-scale temporal graphs. PTMT integrates a tree-based framework with the temporal zone partitioning (TZP) strategy, which partitions temporal graphs by time and structure while preserving lossless motif transitions and enabling massive parallelism. PTMT comprises three phases: growth zone parallel expansion, overlap-aware result aggregation, and deterministic encoding of motif transitions, ensuring accurate tracking of dynamic transitions and interactions. Results on 10 real-world datasets demonstrate that PTMT achieves speedups ranging from 12.0$\times$ to 50.3$\times$ compared to the SOTA method.
Authors: Shivasankari Kannan, Yeounoh Chung, Amita Gondi, Tristan Swadell, Fatma Ozcan
Abstract: The demand for high-fidelity test data is paramount in industrial settings where access to production data is largely restricted. Traditional data generation methods often fall short, struggling with low-fidelity and the ability to model complex data structures and semantic relationships that are critical for testing complex SQL code generation services like Natural Language to SQL (NL2SQL). In this paper, we address the critical need for generating syntactically correct and semantically ``meaningful'' mock data for complex schema that includes columns with nested structures that we frequently encounter in Google SQL code generation workloads. We highlight the limitations of existing approaches used in production, particularly their inability to handle large and complex schema, as well as the lack of semantically coherent test data that lead to limited test coverage. We demonstrate that by leveraging Large Language Models (LLMs) and incorporating strategic pre- and post-processing steps, we can generate realistic high-fidelity test data that adheres to complex structural constraints and maintains semantic integrity to the test targets (SQL queries/functions). This approach supports comprehensive testing of complex SQL queries involving joins, aggregations, and even deeply nested subqueries, ensuring robust evaluation of SQL code generation services, like NL2SQL and SQL Code Assistant services. Our results demonstrate the practical utility of an out-of-the-box LLM (\textit{gemini}) based test data generation for industrial SQL code generation services where generating realistic test data is essential due to the frequent unavailability of production datasets.
Authors: Yuankang Zhao, Matthew Engelhard
Abstract: The Hawkes process (HP) is commonly used to model event sequences with self-reinforcing dynamics, including electronic health records (EHRs). Traditional HPs capture self-reinforcement via parametric impact functions that can be inspected to understand how each event modulates the intensity of others. Neural network-based HPs offer greater flexibility, resulting in improved fit and prediction performance, but at the cost of interpretability, which is often critical in healthcare. In this work, we aim to understand and improve upon this tradeoff. We propose a novel HP formulation in which impact functions are modeled by defining a flexible impact kernel, instantiated as a neural network, in event embedding space, which allows us to model large-scale event sequences with many event types. This approach is more flexible than traditional HPs yet more interpretable than other neural network approaches, and allows us to explicitly trade flexibility for interpretability by adding transformer encoder layers to further contextualize the event embeddings. Results show that our method accurately recovers impact functions in simulations, achieves competitive performance on MIMIC-IV procedure dataset, and gains clinically meaningful interpretation on Duke-EHR with children diagnosis dataset even without transformer layers. This suggests that our flexible impact kernel is often sufficient to capture self-reinforcing dynamics in EHRs and other data effectively, implying that interpretability can be maintained without loss of performance.
Authors: Keyu Chen, Wenchao Sun, Hao Cheng, Sifa Zheng
Abstract: Achieving both realism and controllability in closed-loop traffic simulation remains a key challenge in autonomous driving. Dataset-based methods reproduce realistic trajectories but suffer from covariate shift in closed-loop deployment, compounded by simplified dynamics models that further reduce reliability. Conversely, physics-based simulation methods enhance reliable and controllable closed-loop interactions but often lack expert demonstrations, compromising realism. To address these challenges, we introduce a dual-stage AV-centric simulation framework that conducts open-loop imitation learning pre-training in a data-driven simulator to capture trajectory-level realism and route-level controllability, followed by closed-loop reinforcement learning fine-tuning in a physics-based simulator to enhance style-level controllability and mitigate covariate shift. In the fine-tuning stage, we propose RIFT, a novel RL fine-tuning strategy that evaluates all candidate modalities through group-relative optimization with a dual-clip surrogate objective, enhancing style-level controllability and mitigating covariate shift, while preserving the trajectory-level realism and route-level controllability inherited from IL pre-training. Extensive experiments demonstrate that RIFT improves realism and controllability in traffic simulation while simultaneously exposing the limitations of modern AV systems in closed-loop evaluation. Project Page: https://currychen77.github.io/RIFT/
Authors: I-Chun Arthur Liu, Jason Chen, Gaurav Sukhatme, Daniel Seita
Abstract: Learning bimanual manipulation is challenging due to its high dimensionality and tight coordination required between two arms. Eye-in-hand imitation learning, which uses wrist-mounted cameras, simplifies perception by focusing on task-relevant views. However, collecting diverse demonstrations remains costly, motivating the need for scalable data augmentation. While prior work has explored visual augmentation in single-arm settings, extending these approaches to bimanual manipulation requires generating viewpoint-consistent observations across both arms and producing corresponding action labels that are both valid and feasible. In this work, we propose Diffusion for COordinated Dual-arm Data Augmentation (D-CODA), a method for offline data augmentation tailored to eye-in-hand bimanual imitation learning that trains a diffusion model to synthesize novel, viewpoint-consistent wrist-camera images for both arms while simultaneously generating joint-space action labels. It employs constrained optimization to ensure that augmented states involving gripper-to-object contacts adhere to constraints suitable for bimanual coordination. We evaluate D-CODA on 5 simulated and 3 real-world tasks. Our results across 2250 simulation trials and 300 real-world trials demonstrate that it outperforms baselines and ablations, showing its potential for scalable data augmentation in eye-in-hand bimanual manipulation. Our project website is at: https://dcodaaug.github.io/D-CODA/.
Authors: Tong Zhang, Boyuan Zheng, Ruiqian Nai, Yingdong Hu, Yen-Jen Wang, Geng Chen, Fanqi Lin, Jiongye Li, Chuye Hong, Koushil Sreenath, Yang Gao
Abstract: The human body demonstrates exceptional motor capabilities-such as standing steadily on one foot or performing a high kick with the leg raised over 1.5 meters-both requiring precise balance control. While recent research on humanoid control has leveraged reinforcement learning to track human motions for skill acquisition, applying this paradigm to balance-intensive tasks remains challenging. In this work, we identify three key obstacles: instability from reference motion errors, learning difficulties due to morphological mismatch, and the sim-to-real gap caused by sensor noise and unmodeled dynamics. To address these challenges, we propose HuB (Humanoid Balance), a unified framework that integrates reference motion refinement, balance-aware policy learning, and sim-to-real robustness training, with each component targeting a specific challenge. We validate our approach on the Unitree G1 humanoid robot across challenging quasi-static balance tasks, including extreme single-legged poses such as Swallow Balance and Bruce Lee's Kick. Our policy remains stable even under strong physical disturbances-such as a forceful soccer strike-while baseline methods consistently fail to complete these tasks. Project website: https://hub-robot.github.io
Authors: Owen Kwon, Abraham George, Alison Bartsch, Amir Barati Farimani
Abstract: Real robots are expected to repeat the same behavior in new environments with very little new data, yet modern controllers either incur heavy per-step inference or require deployment-time fine-tuning. We propose RT-Cache, a training-free retrieval-as-control pipeline that caches diverse image action trajectories in a unified vector memory and, at test time, embeds the current frame to retrieve and replay multi-step snippets, replacing per-step model calls. A hierarchical search keeps lookups sub-second at million scale, shifting cost from compute to storage and enabling real-time control on modest GPUs. Across real-robot tasks and large open logs, RT-Cache achieves higher success and lower completion time than strong retrieval baselines (approximately x2 higher success and ~30% faster in our settings), and a single-episode anchoring study shows immediate adaptation to a more complex, contact-rich task without fine-tuning. RT-Cache turns experience into an append-only memory, offering a simple, scalable path to few-shot deployment today and a foundation for multimodal keys and optional integration with high-level policies. Project page: https://rt-cache.github.io/.
Authors: Luciano Sebastian Martinez-Rau, Quynh Nguyen Phuong Vu, Yuxuan Zhang, Bengt Oelmann, Sebastian Bader
Abstract: Keyword spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction. However, standard KWS systems deployed on embedded devices often suffer performance degradation under real-world operating conditions. Resilient KWS systems address this issue by enabling dynamic adaptation, with applications such as adding or replacing keywords, adjusting to specific users, and improving noise robustness. However, deploying resilient, standalone KWS systems with low latency on resource-constrained devices remains challenging due to limited memory and computational resources. This study proposes a low computational approach for continuous noise adaptation of pretrained neural networks used for KWS classification, requiring only 1-shot learning and one epoch. The proposed method was assessed using two pretrained models and three real-world noise sources at signal-to-noise ratios (SNRs) ranging from 24 to -3 dB. The adapted models consistently outperformed the pretrained models across all scenarios, especially at SNR $\leq$ 18 dB, achieving accuracy improvements of 4.9% to 46.0%. These results highlight the efficacy of the proposed methodology while being lightweight enough for deployment on resource-constrained devices.
Authors: Mingxing Peng, Yuting Xie, Xusen Guo, Ruoyu Yao, Hai Yang, Jun Ma
Abstract: Ensuring the safety and robustness of autonomous driving systems necessitates a comprehensive evaluation in safety-critical scenarios. However, these safety-critical scenarios are rare and difficult to collect from real-world driving data, posing significant challenges to effectively assessing the performance of autonomous vehicles. Typical existing methods often suffer from limited controllability and lack user-friendliness, as extensive expert knowledge is essentially required. To address these challenges, we propose LD-Scene, a novel framework that integrates Large Language Models (LLMs) with Latent Diffusion Models (LDMs) for user-controllable adversarial scenario generation through natural language. Our approach comprises an LDM that captures realistic driving trajectory distributions and an LLM-based guidance module that translates user queries into adversarial loss functions, facilitating the generation of scenarios aligned with user queries. The guidance module integrates an LLM-based Chain-of-Thought (CoT) code generator and an LLM-based code debugger, enhancing the controllability and robustness in generating guidance functions. Extensive experiments conducted on the nuScenes dataset demonstrate that LD-Scene achieves state-of-the-art performance in generating realistic, diverse, and effective adversarial scenarios. Furthermore, our framework provides fine-grained control over adversarial behaviors, thereby facilitating more effective testing tailored to specific driving scenarios.
Authors: Yuhang Huang, Jiazhao Zhang, Shilong Zou, Xinwang Liu, Ruizhen Hu, Kai Xu
Abstract: Predictive manipulation has recently gained considerable attention in the Embodied AI community due to its potential to improve robot policy performance by leveraging predicted states. However, generating accurate future visual states of robot-object interactions from world models remains a well-known challenge, particularly in achieving high-quality pixel-level representations. To this end, we propose LaDi-WM, a world model that predicts the latent space of future states using diffusion modeling. Specifically, LaDi-WM leverages the well-established latent space aligned with pre-trained Visual Foundation Models (VFMs), which comprises both geometric features (DINO-based) and semantic features (CLIP-based). We find that predicting the evolution of the latent space is easier to learn and more generalizable than directly predicting pixel-level images. Building on LaDi-WM, we design a diffusion policy that iteratively refines output actions by incorporating forecasted states, thereby generating more consistent and accurate results. Extensive experiments on both synthetic and real-world benchmarks demonstrate that LaDi-WM significantly enhances policy performance by 27.9\% on the LIBERO-LONG benchmark and 20\% on the real-world scenario. Furthermore, our world model and policies achieve impressive generalizability in real-world experiments.
Authors: Ghasem Pasandi, Kishor Kunal, Varun Tej, Kunjal Shah, Hanfei Sun, Sumit Jain, Chunhui Li, Chenhui Deng, Teodor-Dumitru Ene, Haoxing Ren, Sreedhar Pratty
Abstract: This paper presents JARVIS, a novel multi-agent framework that leverages Large Language Models (LLMs) and domain expertise to generate high-quality scripts for specialized Electronic Design Automation (EDA) tasks. By combining a domain-specific LLM trained with synthetically generated data, a custom compiler for structural verification, rule enforcement, code fixing capabilities, and advanced retrieval mechanisms, our approach achieves significant improvements over state-of-the-art domain-specific models. Our framework addresses the challenges of data scarcity and hallucination errors in LLMs, demonstrating the potential of LLMs in specialized engineering domains. We evaluate our framework on multiple benchmarks and show that it outperforms existing models in terms of accuracy and reliability. Our work sets a new precedent for the application of LLMs in EDA and paves the way for future innovations in this field.
Authors: Yang Zhang, Yu Yu, Bo Tang, Yu Zhu, Chuxiong Sun, Wenqiang Wei, Jie Hu, Zipeng Xie, Zhiyu Li, Feiyu Xiong, Edward Chung
Abstract: With the rapid development of Large Language Models (LLMs), aligning these models with human preferences and values is critical to ensuring ethical and safe applications. However, existing alignment techniques such as RLHF or DPO often require direct fine-tuning on LLMs with billions of parameters, resulting in substantial computational costs and inefficiencies. To address this, we propose Micro token-level Accept-Reject Aligning (MARA) approach designed to operate independently of the language models. MARA simplifies the alignment process by decomposing sentence-level preference learning into token-level binary classification, where a compact three-layer fully-connected network determines whether candidate tokens are "Accepted" or "Rejected" as part of the response. Extensive experiments across seven different LLMs and three open-source datasets show that MARA achieves significant improvements in alignment performance while reducing computational costs. The source code and implementation details are publicly available at https://github.com/IAAR-Shanghai/MARA, and the trained models are released at https://huggingface.co/IAAR-Shanghai/MARA_AGENTS.
URLs: https://github.com/IAAR-Shanghai/MARA,, https://huggingface.co/IAAR-Shanghai/MARA_AGENTS.
Authors: M. Mebratu, W. L. K. Wu
Abstract: Extragalactic foregrounds in cosmic microwave background (CMB) observations are both a source of cosmological and astrophysical information and a nuisance to the CMB. Effective field-level modeling that captures their non-Gaussian statistical distributions is increasingly important for optimal information extraction, particularly given the precise and low-noise observations from current and upcoming experiments. We explore the use of Wavelet Flow (WF) models to tackle the novel task of modeling the field-level probability distributions of multi-component CMB secondaries and foreground. Specifically, we jointly train correlated CMB lensing convergence ($\kappa$) and cosmic infrared background (CIB) maps with a WF model and obtain a network that statistically recovers the input to high accuracy -- the trained network generates samples of $\kappa$ and CIB fields whose average power spectra are within a few percent of the inputs across all scales, and whose Minkowski functionals are similarly accurate compared to the inputs. Leveraging the multiscale architecture of these models, we fine-tune both the model parameters and the priors at each scale independently, optimizing performance across different resolutions. These results demonstrate that WF models can accurately simulate correlated components of CMB secondaries, supporting improved analysis of cosmological data. Our code and trained models can be found here (https://github.com/matiwosm/HybridPriorWavletFlow.git).
URLs: https://github.com/matiwosm/HybridPriorWavletFlow.git).
Authors: Zeinab Dehghani, Mohammed Naveed Akram, Koorosh Aslansefat, Adil Khan, Yiannis Papadopoulos
Abstract: Large Language Models (LLMs) such as GPT, LLaMA, and Claude achieve remarkable performance in text generation but remain opaque in their decision-making processes, limiting trust and accountability in high-stakes applications. We present gSMILE (generative SMILE), a model-agnostic, perturbation-based framework for token-level interpretability in LLMs. Extending the SMILE methodology, gSMILE uses controlled prompt perturbations, Wasserstein distance metrics, and weighted linear surrogates to identify input tokens with the most significant impact on the output. This process enables the generation of intuitive heatmaps that visually highlight influential tokens and reasoning paths. We evaluate gSMILE across leading LLMs (OpenAI's gpt-3.5-turbo-instruct, Meta's LLaMA 3.1 Instruct Turbo, and Anthropic's Claude 2.1) using attribution fidelity, attribution consistency, attribution stability, attribution faithfulness, and attribution accuracy as metrics. Results show that gSMILE delivers reliable human-aligned attributions, with Claude 2.1 excelling in attention fidelity and GPT-3.5 achieving the highest output consistency. These findings demonstrate gSMILE's ability to balance model performance and interpretability, enabling more transparent and trustworthy AI systems.
Authors: Ajsal Shereef Palattuparambil, Thommen George Karimpanal, Santu Rana
Abstract: Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning. In contrast, reinforcement learning (RL) agents typically require extensive retraining even when new tasks share structural similarities with previously learned ones. In this work, we propose MAGIK, a novel framework that enables RL agents to transfer knowledge to analogous tasks without interacting with the target environment. Our approach leverages an imagination mechanism to map entities in the target task to their analogues in the source domain, allowing the agent to reuse its original policy. Experiments on custom MiniGrid and MuJoCo tasks show that MAGIK achieves effective zero-shot transfer using only a small number of human-labelled examples. We compare our approach to related baselines and highlight how it offers a novel and effective mechanism for knowledge transfer via imagination-based analogy mapping.
Authors: Hohyun Kim, Seunggeun Lee, Min-hwan Oh
Abstract: Generative Flow Networks (GFlowNets) offer a powerful framework for sampling graphs in proportion to their rewards. However, existing approaches suffer from systematic biases due to inaccuracies in state transition probability computations. These biases, rooted in the inherent symmetries of graphs, impact both atom-based and fragment-based generation schemes. To address this challenge, we introduce Symmetry-Aware GFlowNets (SA-GFN), a method that incorporates symmetry corrections into the learning process through reward scaling. By integrating bias correction directly into the reward structure, SA-GFN eliminates the need for explicit state transition computations. Empirical results show that SA-GFN enables unbiased sampling while enhancing diversity and consistently generating high-reward graphs that closely match the target distribution.
Authors: Jiaheng Hu, Peter Stone, Roberto Mart\'in-Mart\'in
Abstract: Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators. While reinforcement learning (RL) holds promise for autonomously acquiring robot control policies, scaling it to high-DoF embodiments remains challenging. Direct RL in the real world demands both safe exploration and high sample efficiency, which are difficult to achieve in practice. Sim-to-real RL, on the other hand, is often brittle due to the reality gap. This paper introduces SLAC, a method that renders real-world RL feasible for complex embodiments by leveraging a low-fidelity simulator to pretrain a task-agnostic latent action space. SLAC trains this latent action space via a customized unsupervised skill discovery method designed to promote temporal abstraction, disentanglement, and safety, thereby facilitating efficient downstream learning. Once a latent action space is learned, SLAC uses it as the action interface for a novel off-policy RL algorithm to autonomously learn downstream tasks through real-world interactions. We evaluate SLAC against existing methods on a suite of bimanual mobile manipulation tasks, where it achieves state-of-the-art performance. Notably, SLAC learns contact-rich whole-body tasks in under an hour of real-world interactions, without relying on any demonstrations or hand-crafted behavior priors. More information and robot videos at robo-rl.github.io
Authors: Xuanjun Chen, I-Ming Lin, Lin Zhang, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang
Abstract: Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tracing models using simulated CoSG data while maintaining strong performance on real CoSG-generated audio remains an open challenge. In this paper, we show that models trained solely on codec-resynthesized data tend to overfit to non-speech regions and struggle to generalize to unseen content. To mitigate these challenges, we introduce the Semantic-Acoustic Source Tracing Network (SASTNet), which jointly leverages Whisper for semantic feature encoding and Wav2vec2 with AudioMAE for acoustic feature encoding. Our proposed SASTNet achieves state-of-the-art performance on the CoSG test set of the CodecFake+ dataset, demonstrating its effectiveness for reliable source tracing.
Authors: Alexander Kolpakov, Igor Rivin
Abstract: Computing classical centrality measures such as betweenness and closeness is computationally expensive on large-scale graphs. In this work, we introduce an efficient force layout algorithm that embeds a graph into a low-dimensional space, where the radial distance from the origin serves as a proxy for various centrality measures. We evaluate our method on multiple graph families and demonstrate strong correlations with degree, PageRank, and paths-based centralities. As an application, it turns out that the proposed embedding allows to find high-influence nodes in a network, and provides a fast and scalable alternative to the standard greedy algorithm.
Authors: Aditya Sengar, Ali Hariri, Daniel Probst, Patrick Barth, Pierre Vandergheynst
Abstract: Generating diverse, all-atom conformational ensembles of dynamic proteins such as G-protein-coupled receptors (GPCRs) is critical for understanding their function, yet most generative models simplify atomic detail or ignore conformational diversity altogether. We present latent diffusion for full protein generation (LD-FPG), a framework that constructs complete all-atom protein structures, including every side-chain heavy atom, directly from molecular dynamics (MD) trajectories. LD-FPG employs a Chebyshev graph neural network (ChebNet) to obtain low-dimensional latent embeddings of protein conformations, which are processed using three pooling strategies: blind, sequential and residue-based. A diffusion model trained on these latent representations generates new samples that a decoder, optionally regularized by dihedral-angle losses, maps back to Cartesian coordinates. Using D2R-MD, a 2-microsecond MD trajectory (12 000 frames) of the human dopamine D2 receptor in a membrane environment, the sequential and residue-based pooling strategy reproduces the reference ensemble with high structural fidelity (all-atom lDDT of approximately 0.7; C-alpha-lDDT of approximately 0.8) and recovers backbone and side-chain dihedral-angle distributions with a Jensen-Shannon divergence of less than 0.03 compared to the MD data. LD-FPG thereby offers a practical route to system-specific, all-atom ensemble generation for large proteins, providing a promising tool for structure-based therapeutic design on complex, dynamic targets. The D2R-MD dataset and our implementation are freely available to facilitate further research.
Authors: Seungjun Shin, Jaehoon Oh, Dokwan Oh
Abstract: Attention mechanisms are central to the success of large language models (LLMs), enabling them to capture intricate token dependencies and implicitly assign importance to each token. Recent studies have revealed the sink token, which receives disproportionately high attention despite their limited semantic role. In this paper, we first expand the relationship between the sink token and other tokens, moving beyond attention to explore their similarity in hidden states, considering the layer depth. We observe that as the layers get deeper, the cosine similarity between the normalized hidden states of the sink token and those of other tokens increases, and that the normalized hidden states of the sink token exhibit negligible changes. These imply that other tokens consistently are directed toward the sink token throughout the layers. Next, we propose a dynamic token selection method, called OrthoRank, using these findings to select important tokens. Specifically, in a certain layer, we define token importance by the speed at which the token moves toward the sink token. This is converted into orthogonality with the sink token, meaning that tokens that are more orthogonal to the sink token are assigned greater importance. Finally, through extensive experiments, we demonstrated that our method results in lower perplexity and higher zero-shot accuracy compared to layer pruning methods at the same sparsity ratio with comparable throughput, while also achieving superior performance on LongBench.
Authors: William Fleshman, Benjamin Van Durme
Abstract: The proliferation of fine-tuned language model experts for specific tasks and domains signals the need for efficient selection and combination methods. We propose LoRA-Augmented Generation (LAG) for leveraging large libraries of knowledge and task-specific LoRA adapters. LAG requires no additional training or access to data, and efficiently filters, retrieves, and applies experts on a per-token and layer basis. We evaluate LAG on various knowledge-intensive tasks, achieving superior performance over existing data-free methods. We explore scenarios where additional data is available, demonstrating LAG's compatibility with alternative solutions such as retrieval-augmented generation (RAG).
Authors: Xin Li
Abstract: We present the Context-Content Uncertainty Principle (CCUP), a unified framework that models cognition as the directed flow of information between high-entropy context and low-entropy content. Inference emerges as a cycle of bidirectional interactions, bottom-up contextual disambiguation paired with top-down content reconstruction, which resolves the Information Bottleneck in Optimal Transport (iBOT). Implemented via Rao-Blackwellized variational entropy minimization, CCUP steers representations toward minimal joint uncertainty while preserving inferential directionality. Local cycle completion underpins temporal bootstrapping, chaining simulations to refine memory, and spatial bootstrapping, enabling compositional hierarchical inference. We prove a Delta Convergence Theorem showing that recursive entropy minimization yields delta-like attractors in latent space, stabilizing perceptual schemas and motor plans. Temporal bootstrapping through perception-action loops and sleep-wake consolidation further transforms episodic traces into semantic knowledge. Extending CCUP, each hierarchical level performs delta-seeded inference: low-entropy content seeds diffuse outward along goal-constrained paths shaped by top-down priors and external context, confining inference to task-relevant manifolds and circumventing the curse of dimensionality. Building on this, we propose that language emerges as a symbolic transport system, externalizing latent content to synchronize inference cycles across individuals. Together, these results establish iBOT as a foundational principle of information flow in both individual cognition and collective intelligence, positioning recursive inference as the structured conduit through which minds adapt, align, and extend.
Authors: Alexander Kolpakov
Abstract: We develop a framework for dualizing the Kolmogorov structure function $h_x(\alpha)$, which then allows using computable complexity proxies. We establish a mathematical analogy between information-theoretic constructs and statistical mechanics, introducing a suitable partition function and free energy functional. We explicitly prove the Legendre-Fenchel duality between the structure function and free energy, showing detailed balance of the Metropolis kernel, and interpret acceptance probabilities as information-theoretic scattering amplitudes. A susceptibility-like variance of model complexity is shown to peak precisely at loss-complexity trade-offs interpreted as phase transitions. Practical experiments with linear and tree-based regression models verify these theoretical predictions, explicitly demonstrating the interplay between the model complexity, generalization, and overfitting threshold.
Authors: Yuntao Du, Jiacheng Li, Yuetian Chen, Kaiyuan Zhang, Zhizhen Yuan, Hanshen Xiao, Bruno Ribeiro, Ninghui Li
Abstract: A Membership Inference Attack (MIA) assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or non-adaptive, depending on whether the adversary is allowed to train shadow models on membership queries. In the adaptive setting, where the adversary can train shadow models after accessing query instances, we highlight the importance of exploiting membership dependencies between instances and propose an attack-agnostic framework called Cascading Membership Inference Attack (CMIA), which incorporates membership dependencies via conditional shadow training to boost membership inference performance. In the non-adaptive setting, where the adversary is restricted to training shadow models before obtaining membership queries, we introduce Proxy Membership Inference Attack (PMIA). PMIA employs a proxy selection strategy that identifies samples with similar behaviors to the query instance and uses their behaviors in shadow models to perform a membership posterior odds test for membership inference. We provide theoretical analyses for both attacks, and extensive experimental results demonstrate that CMIA and PMIA substantially outperform existing MIAs in both settings, particularly in the low false-positive regime, which is crucial for evaluating privacy risks.
Authors: Yue Dong, Han Li, Shen Li, Nikhil Patel, Xing Liu, Xiaodong Wang, Chuanhao Zhuge
Abstract: Large-scale recommendation systems are pivotal to process an immense volume of daily user interactions, requiring the effective modeling of high cardinality and heterogeneous features to ensure accurate predictions. In prior work, we introduced Hierarchical Sequential Transducers (HSTU), an attention-based architecture for modeling high cardinality, non-stationary streaming recommendation data, providing good scaling law in the generative recommender framework (GR). Recent studies and experiments demonstrate that attending to longer user history sequences yields significant metric improvements. However, scaling sequence length is activation-heavy, necessitating parallelism solutions to effectively shard activation memory. In transformer-based LLMs, context parallelism (CP) is a commonly used technique that distributes computation along the sequence-length dimension across multiple GPUs, effectively reducing memory usage from attention activations. In contrast, production ranking models typically utilize jagged input tensors to represent user interaction features, introducing unique CP implementation challenges. In this work, we introduce context parallelism with jagged tensor support for HSTU attention, establishing foundational capabilities for scaling up sequence dimensions. Our approach enables a 5.3x increase in supported user interaction sequence length, while achieving a 1.55x scaling factor when combined with Distributed Data Parallelism (DDP).
Authors: M. Adeel Ajaib, Fariha Nasir, Abdul Rehman
Abstract: We explore machine learning techniques for predicting Curie temperatures of magnetic materials using the NEMAD database. By augmenting the dataset with composition-based and domain-aware descriptors, we evaluate the performance of several machine learning models. We find that the Extra Trees Regressor delivers the best performance reaching an R^2 score of up to 0.85 $\pm$ 0.01 (cross-validated) for a balanced dataset. We employ the k-means clustering algorithm to gain insights into the performance of chemically distinct material groups. Furthermore, we perform the SHAP analysis to identify key physicochemical drivers of Curie behavior, such as average atomic number and magnetic moment. By employing explainable AI techniques, this analysis offers insights into the model's predictive behavior, thereby advancing scientific interpretability.
Authors: Beilong Tang, Xiaoxiao Miao, Xin Wang, Ming Li
Abstract: Voice anonymization protects speaker privacy by concealing identity while preserving linguistic and paralinguistic content. Self-supervised learning (SSL) representations encode linguistic features but preserve speaker traits. We propose a novel speaker-embedding-free framework called SEF-MK. Instead of using a single k-means model trained on the entire dataset, SEF-MK anonymizes SSL representations for each utterance by randomly selecting one of multiple k-means models, each trained on a different subset of speakers. We explore this approach from both attacker and user perspectives. Extensive experiments show that, compared to a single k-means model, SEF-MK with multiple k-means models better preserves linguistic and emotional content from the user's viewpoint. However, from the attacker's perspective, utilizing multiple k-means models boosts the effectiveness of privacy attacks. These insights can aid users in designing voice anonymization systems to mitigate attacker threats.
Authors: Nikolai Warner, Wenjin Zhang, Irfan Essa, Apaar Sadhwani
Abstract: Lifting-based methods for 3D Human Pose Estimation (HPE), which predict 3D poses from detected 2D keypoints, often generalize poorly to new datasets and real-world settings. To address this, we propose \emph{AugLift}, a simple yet effective reformulation of the standard lifting pipeline that significantly improves generalization performance without requiring additional data collection or sensors. AugLift sparsely enriches the standard input -- the 2D keypoint coordinates $(x, y)$ -- by augmenting it with a keypoint detection confidence score $c$ and a corresponding depth estimate $d$. These additional signals are computed from the image using off-the-shelf, pre-trained models (e.g., for monocular depth estimation), thereby inheriting their strong generalization capabilities. Importantly, AugLift serves as a modular add-on and can be readily integrated into existing lifting architectures. Our extensive experiments across four datasets demonstrate that AugLift boosts cross-dataset performance on unseen datasets by an average of $10.1\%$, while also improving in-distribution performance by $4.0\%$. These gains are consistent across various lifting architectures, highlighting the robustness of our method. Our analysis suggests that these sparse, keypoint-aligned cues provide robust frame-level context, offering a practical way to significantly improve the generalization of any lifting-based pose estimation model. Code will be made publicly available.
Authors: Fotis I. Giasemis
Abstract: As the particle physics community needs higher and higher precisions in order to test our current model of the subatomic world, larger and larger datasets are necessary. With upgrades scheduled for the detectors of colliding-beam experiments around the world, and specifically at the Large Hadron Collider at CERN, more collisions and more complex interactions are expected. This directly implies an increase in data produced and consequently in the computational resources needed to process them. At CERN, the amount of data produced is gargantuan. This is why the data have to be heavily filtered and selected in real time before being permanently stored. This data can then be used to perform physics analyses, in order to expand our current understanding of the universe and improve the Standard Model of physics. This real-time filtering, known as triggering, involves complex processing happening often at frequencies as high as 40 MHz. This thesis contributes to understanding how machine learning models can be efficiently deployed in such environments, in order to maximize throughput and minimize energy consumption. Inevitably, modern hardware designed for such tasks and contemporary algorithms are needed in order to meet the challenges posed by the stringent, high-frequency data rates. In this work, I present our graph neural network-based pipeline, developed for charged particle track reconstruction at the LHCb experiment at CERN. The pipeline was implemented end-to-end inside LHCb's first-level trigger, entirely on GPUs. Its performance was compared against the classical tracking algorithms currently in production at LHCb. The pipeline was also accelerated on the FPGA architecture, and its performance in terms of power consumption and processing speed was compared against the GPU implementation.
Authors: Kun Ming Goh
Abstract: Generative adversarial networks (GANs) have emerged as a powerful paradigm for producing high-fidelity data samples, yet their performance is constrained by the quality of latent representations, typically sampled from classical noise distributions. This study investigates hybrid quantum-classical GANs (HQCGANs) in which a quantum generator, implemented via parameterised quantum circuits, produces latent vectors for a classical discriminator. We evaluate a classical GAN alongside three HQCGAN variants with 3, 5, and 7 qubits, using Qiskit's AerSimulator with realistic noise models to emulate near-term quantum devices. The binary MNIST dataset (digits 0 and 1) is used to align with the low-dimensional latent spaces imposed by current quantum hardware. Models are trained for 150 epochs and assessed with Frechet Inception Distance (FID) and Kernel Inception Distance (KID). Results show that while the classical GAN achieved the best scores, the 7-qubit HQCGAN produced competitive performance, narrowing the gap in later epochs, whereas the 3-qubit model exhibited earlier convergence limitations. Efficiency analysis indicates only moderate training time increases despite quantum sampling overhead. These findings validate the feasibility of noisy quantum circuits as latent priors in GAN architectures, highlighting their potential to enhance generative modelling within the constraints of the noisy intermediate-scale quantum (NISQ) era.
Authors: Baran Atalar, Eddie Zhang, Carlee Joe-Wong
Abstract: With the increasing popularity of large language models (LLMs) for a variety of tasks, there has been a growing interest in strategies that can predict which out of a set of LLMs will yield a successful answer at low cost. This problem promises to become more and more relevant as providers like Microsoft allow users to easily create custom LLM "assistants" specialized to particular types of queries. However, some tasks (i.e., queries) may be too specialized and difficult for a single LLM to handle alone. These applications often benefit from breaking down the task into smaller subtasks, each of which can then be executed by a LLM expected to perform well on that specific subtask. For example, in extracting a diagnosis from medical records, one can first select an LLM to summarize the record, select another to validate the summary, and then select another, possibly different, LLM to extract the diagnosis from the summarized record. Unlike existing LLM selection or routing algorithms, this setting requires that we select a sequence of LLMs, with the output of each LLM feeding into the next and potentially influencing its success. Thus, unlike single LLM selection, the quality of each subtask's output directly affects the inputs, and hence the cost and success rate, of downstream LLMs, creating complex performance dependencies that must be learned and accounted for during selection. We propose a neural contextual bandit-based algorithm that trains neural networks that model LLM success on each subtask in an online manner, thus learning to guide the LLM selections for the different subtasks, even in the absence of historical LLM performance data. Experiments on telecommunications question answering and medical diagnosis prediction datasets illustrate the effectiveness of our proposed approach compared to other LLM selection algorithms.
Authors: Qi Liu, Yabei Li, Hongsong Wang, Lei He
Abstract: Traditional closed-set 3D detection frameworks fail to meet the demands of open-world applications like autonomous driving. Existing open-vocabulary 3D detection methods typically adopt a two-stage pipeline consisting of pseudo-label generation followed by semantic alignment. While vision-language models (VLMs) recently have dramatically improved the semantic accuracy of pseudo-labels, their geometric quality, particularly bounding box precision, remains commonly neglected. To address this issue, we propose a High Box Quality Open-Vocabulary 3D Detection (HQ-OV3D) framework, dedicated to generate and refine high-quality pseudo-labels for open-vocabulary classes. The framework comprises two key components: an Intra-Modality Cross-Validated (IMCV) Proposal Generator that utilizes cross-modality geometric consistency to generate high-quality initial 3D proposals, and an Annotated-Class Assisted (ACA) Denoiser that progressively refines 3D proposals by leveraging geometric priors from annotated categories through a DDIM-based denoising mechanism. Compared to the state-of-the-art method, training with pseudo-labels generated by our approach achieves a 7.37% improvement in mAP on novel classes, demonstrating the superior quality of the pseudo-labels produced by our framework. HQ-OV3D can serve not only as a strong standalone open-vocabulary 3D detector but also as a plug-in high-quality pseudo-label generator for existing open-vocabulary detection or annotation pipelines.
Authors: Tejomay Kishor Padole, Suyash P Awate, Pushpak Bhattacharyya
Abstract: Masked diffusion language models (MDMs) have recently gained traction as a viable generative framework for natural language. This can be attributed to its scalability and ease of training compared to other diffusion model paradigms for discrete data, establishing itself as the state-of-the-art non-autoregressive generator for discrete data. Diffusion models, in general, have shown excellent ability to improve the generation quality by leveraging inference-time scaling either by increasing the number of denoising steps or by using external verifiers on top of the outputs of each step to guide the generation. In this work, we propose a verifier-based inference-time scaling method that aids in finding a better candidate generation during the denoising process of the MDM. Our experiments demonstrate the application of MDMs for standard text-style transfer tasks and establish MDMs as a better alternative to autoregressive language models. Additionally, we show that a simple soft-value-based verifier setup for MDMs using off-the-shelf pre-trained embedding models leads to significant gains in generation quality even when used on top of typical classifier-free guidance setups in the existing literature.
Authors: Shengzhuang Chen, Xu Ouyang, Michael Arthur Leopold Pearce, Thomas Hartvigsen, Jonathan Richard Schwarz
Abstract: Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no learning-based approach has emerged as a reliable solution. In this work, we propose to view the selection of training data mixtures as a black-box hyperparameter optimization problem, for which Bayesian Optimization is a well-established class of appropriate algorithms. Firstly, we cast data mixture learning as a sequential decision-making problem, in which we aim to find a suitable trade-off between the computational cost of training exploratory (proxy-) models and final mixture performance. Secondly, we systematically explore the properties of transferring mixtures learned at a small scale to larger-scale experiments, providing insights and highlighting opportunities for research at a modest scale. By proposing Multi-fidelity Bayesian Optimization as a suitable method in this common scenario, we introduce a natural framework to balance experiment cost with model fit, avoiding the risks of overfitting to smaller scales while minimizing the number of experiments at high cost. We present results for pre-training and instruction finetuning across models ranging from 1 million to 7 billion parameters, varying from simple architectures to state-of-the-art models and benchmarks spanning dozens of datasets. We demonstrate consistently strong results relative to a wide range of baselines, resulting inspeed-ups of over 500% in determining the best data mixture on our largest experiments. In addition, we broaden access to research by sharing ADMIRE IFT Runs, a dataset of 460 full training & evaluation runs worth over 13,000 GPU hours, greatly reducing the cost of conducting research in this area.
Authors: Jakub {\L}ucki, Jonathan Becktor, Georgios Georgakis, Rob Royce, Shehryar Khattak
Abstract: Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant computations, large memory footprints, and complex integration challenges. In response, this work presents Visual Perception Engine (VPEngine), a modular framework designed to enable efficient GPU usage for visual multitasking while maintaining extensibility and developer accessibility. Our framework architecture leverages a shared foundation model backbone that extracts image representations, which are efficiently shared, without any unnecessary GPU-CPU memory transfers, across multiple specialized task-specific model heads running in parallel. This design eliminates the computational redundancy inherent in feature extraction component when deploying traditional sequential models while enabling dynamic task prioritization based on application demands. We demonstrate our framework's capabilities through an example implementation using DINOv2 as the foundation model with multiple task (depth, object detection and semantic segmentation) heads, achieving up to 3x speedup compared to sequential execution. Building on CUDA Multi-Process Service (MPS), VPEngine offers efficient GPU utilization and maintains a constant memory footprint while allowing per-task inference frequencies to be adjusted dynamically during runtime. The framework is written in Python and is open source with ROS2 C++ (Humble) bindings for ease of use by the robotics community across diverse robotic platforms. Our example implementation demonstrates end-to-end real-time performance at $\geq$50 Hz on NVIDIA Jetson Orin AGX for TensorRT optimized models.