arXiv cs.LG Machine Learning

Eric Qu, Brandon M. Wood, Aditi S. Krishnapriyan, Zachary W. Ulissi: A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention https://arxiv.org/abs/2603.06567 https://arxiv.org/pdf/2603.06567 https://arxiv.org/html/2603.06567

Joshua Brendan Melander, Zaki Alaoui, Shenghua Liu, Surya Ganguli, Stephen A. Baccus: Causal Interpretation of Neural Network Computations with Contribution Decomposition https://arxiv.org/abs/2603.06557 https://arxiv.org/pdf/2603.06557 https://arxiv.org/html/2603.06557

Kamarthi, Xu, Tong, Zhou, Peters, Czyzyk, Prakash: Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations https://arxiv.org/abs/2603.06555 https://arxiv.org/pdf/2603.06555 https://arxiv.org/html/2603.06555

Qitong Wang, Haoran Dai, Haotian Zhang, Christopher Rasmussen, Binghui Wang: When One Modality Rules Them All: Backdoor Modality Collapse in Multimodal Diffusion Models https://arxiv.org/abs/2603.06508 https://arxiv.org/pdf/2603.06508 https://arxiv.org/html/2603.06508

Kartik Sharma, Rakshit S. Trivedi: COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics https://arxiv.org/abs/2603.06495 https://arxiv.org/pdf/2603.06495 https://arxiv.org/html/2603.06495

Ethan Smith (Canva Research): NOBLE: Accelerating Transformers with Nonlinear Low-Rank Branches https://arxiv.org/abs/2603.06492 https://arxiv.org/pdf/2603.06492 https://arxiv.org/html/2603.06492

Chen-Yu Liu, Leonardo Placidi, Eric Brunner, Enrico Rinaldi: Toward Generative Quantum Utility via Correlation-Complexity Map https://arxiv.org/abs/2603.06440 https://arxiv.org/pdf/2603.06440 https://arxiv.org/html/2603.06440

Xianzhi Zhang, Yue Xu, Yinlin Zhu, Di Wu, Yipeng Zhou, Miao Hu, Guocong Quan: Adapter-Augmented Bandits for Online Multi-Constrained Multi-Modal Inference Scheduling https://arxiv.org/abs/2603.06403 https://arxiv.org/pdf/2603.06403 https://arxiv.org/html/2603.06403

Ganzhao Yuan: Adaptive Lipschitz-Free Conditional Gradient Methods for Stochastic Composite Nonconvex Optimization https://arxiv.org/abs/2603.06369 https://arxiv.org/pdf/2603.06369 https://arxiv.org/html/2603.06369

Mohammadhossein Ghahramani, Mengchu Zhou: CLAIRE: Compressed Latent Autoencoder for Industrial Representation and Evaluation -- A Deep Learning Framework for Smart Manufacturing https://arxiv.org/abs/2603.06361 https://arxiv.org/pdf/2603.06361 https://arxiv.org/html/2603.06361

Charles Meyers, Aaron MacSween, Erik Elmroth, Tommy L\"ofstedt: Tiny, Hardware-Independent, Compression-based Classification https://arxiv.org/abs/2603.06359 https://arxiv.org/pdf/2603.06359 https://arxiv.org/html/2603.06359

Yaojun Li, Yulong Yang, Christine Allen-Blanchette: Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics https://arxiv.org/abs/2603.06354 https://arxiv.org/pdf/2603.06354 https://arxiv.org/html/2603.06354

Azza Jenane, Nassim Walha, Lukas Kuhn, Florian Buettner: From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty https://arxiv.org/abs/2603.06317 https://arxiv.org/pdf/2603.06317 https://arxiv.org/html/2603.06317

Zongyu Shi, Laibin Zhang, Maoyin Chen: Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis https://arxiv.org/abs/2603.06303 https://arxiv.org/pdf/2603.06303 https://arxiv.org/html/2603.06303

Lin Niu, Xin Luo, Linchuan Xie, Yifu Sun, Guanghua Yu, Jianchen Zhu, S Kevin Zhou: Stem: Rethinking Causal Information Flow in Sparse Attention https://arxiv.org/abs/2603.06274 https://arxiv.org/pdf/2603.06274 https://arxiv.org/html/2603.06274

Mina Farajiamiri, et al.: Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering https://arxiv.org/abs/2603.06271 https://arxiv.org/pdf/2603.06271 https://arxiv.org/html/2603.06271

Songqun Gao, Zanxi Ruan, Patrick Floor, Marco Roveri, Luigi Palopoli, Daniele Fontanelli: Learning to Solve Orienteering Problem with Time Windows and Variable Profits https://arxiv.org/abs/2603.06260 https://arxiv.org/pdf/2603.06260 https://arxiv.org/html/2603.06260

Leonard Pleiss, Carolin Schmidt, Maximilian Schiffer: Synthetic Monitoring Environments for Reinforcement Learning https://arxiv.org/abs/2603.06252 https://arxiv.org/pdf/2603.06252 https://arxiv.org/html/2603.06252

Aditya Varre, Mark Rofin, Nicolas Flammarion: Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions https://arxiv.org/abs/2603.06248 https://arxiv.org/pdf/2603.06248 https://arxiv.org/html/2603.06248

Han-Chen Zhang, Zi-Hao Zhou, Mao-Lin Luo, Shimin Di, Min-Ling Zhang, Tong Wei: DC-Merge: Improving Model Merging with Directional Consistency https://arxiv.org/abs/2603.06242 https://arxiv.org/pdf/2603.06242 https://arxiv.org/html/2603.06242

Felix Walger, Mehdi Ejtehadi, Anke Schmeink, Diego Paez-Granados: FedSCS-XGB -- Federated Server-centric surrogate XGBoost for continual health monitoring https://arxiv.org/abs/2603.06224 https://arxiv.org/pdf/2603.06224 https://arxiv.org/html/2603.06224

Jhonathan Barrios, Wolfram Erlhagen, Miguel F. Gago, Estela Bicho, Flora Ferreira: Topological descriptors of foot clearance gait dynamics improve differential diagnosis of Parkinsonism https://arxiv.org/abs/2603.06212 https://arxiv.org/pdf/2603.06212 https://arxiv.org/html/2603.06212

Alejandro J. Gonz\'alez-Santana, Giovanny A. Cuervo-Londo\~no, Javier S\'anchez: Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input Perturbations https://arxiv.org/abs/2603.06153 https://arxiv.org/pdf/2603.06153 https://arxiv.org/html/2603.06153

Bj\"orn van Zwol: Predictive Coding Graphs are a Superset of Feedforward Neural Networks https://arxiv.org/abs/2603.06142 https://arxiv.org/pdf/2603.06142 https://arxiv.org/html/2603.06142

Puneet Mathur, Branislav Kveton, Subhojyoti Mukherjee, Viet Dac Lai: Partial Policy Gradients for RL in LLMs https://arxiv.org/abs/2603.06138 https://arxiv.org/pdf/2603.06138 https://arxiv.org/html/2603.06138

Yuewei Li, Dalin Zhang, Huan Li, Xinyi Gong, Hongjun Chu, Zhaohui Song: DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection https://arxiv.org/abs/2603.06131 https://arxiv.org/pdf/2603.06131 https://arxiv.org/html/2603.06131

Zhipeng Yao, Rui Yu, Guisong Chang, Ying Li, Yu Zhang, Dazhou Li: Dynamic Momentum Recalibration in Online Gradient Learning https://arxiv.org/abs/2603.06120 https://arxiv.org/pdf/2603.06120 https://arxiv.org/html/2603.06120

Wenjin Wu, Ale\v{s} Leonardis, Linjiang Chen, Jianbo Jiao: Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectra https://arxiv.org/abs/2603.06113 https://arxiv.org/pdf/2603.06113 https://arxiv.org/html/2603.06113

Stanley Wei, Alex Damian, Jason D. Lee: Improved high-dimensional estimation with Langevin dynamics and stochastic weight averaging https://arxiv.org/abs/2603.06028 https://arxiv.org/pdf/2603.06028 https://arxiv.org/html/2603.06028

Lucas Pesenti, Lucas Slot, Manuel Wiedmer: Agnostic learning in (almost) optimal time via Gaussian surface area https://arxiv.org/abs/2603.06027 https://arxiv.org/pdf/2603.06027 https://arxiv.org/html/2603.06027