AI-generated summaries

Today's ML research,
without the noise.

Daily summaries of the latest machine learning papers from arXiv, processed every 8 hours.

64 Papers today
8h Update frequency
7 Days of history
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
Borui Kang, Jinrui Gu, Junhan Lv, Wenbin Li, Lei Wang, Yang Gao
NLP Multimodal Theory
  • Introduction of Harness Continual Learning (HCL) paradigm focusing on harness adaptation rather than model parameter changes.
  • Identification of harness-level forgetting as a challenge in continual learning.
  • Development of a framework with components for managing harness state and learning.
  • Demonstration of capability accumulation and failure recovery in various experimental settings.
Read more
Complementary, Not Cumulative: Interaction Effects in Physics-Informed Neural Networks for Navier-Stokes Vortex Shedding
Devesh Shah
Theory Optimization Efficient ML
  • Systematic evaluation of various PINN techniques reveals that many do not improve performance when used alone.
  • The combination of periodic activations and causal weighting is identified as effective for learning vortex shedding.
  • Adding more techniques beyond the effective combination can lead to performance degradation.
  • The study highlights the nonlinear interactions between different PINN enhancements.
Read more
Multi-Source Wasserstein Distributionally Robust Graph Learning
Chuansen Peng, Yifan Xia, Jinshan Zhong, Xiaojing Shen
Graph Learning Optimization Theory
  • Introduces MS-WDRO framework for robust graph learning from multi-source data.
  • Utilizes Wasserstein barycenter for effective fusion of heterogeneous data sources.
  • Establishes non-asymptotic performance guarantees for the proposed method.
  • Achieves superior performance in graph recovery and sample efficiency compared to existing methods.
Read more
Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention
Sotirios P. Chatzis, Loukas Papadoulas
Time Series
  • Lévy Attention integrates uncertainty estimation directly into the attention mechanism, eliminating the need for separate models or additional passes.
  • The mechanism uses a stochastic formulation that allows for closed-form computation of both predictions and their uncertainty.
  • Experiments indicate that Lévy Attention maintains high accuracy while significantly improving uncertainty estimation, especially in sparse datasets.
  • The method is computationally efficient, providing error bars and uncertainty metrics with minimal additional cost.
Read more
Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution
Kaizhen Tan, Xin Xu, Siru Tao, Yixiao Li, Hanzhe Hong, Yang Feng, Heqing Du
Multimodal Robotics Theory
  • Introduces the Disjoint-Bridge Operator-Substitution Certificate (DBOSC) for certifying multimodal representations.
  • Demonstrates that audio and acceleration modalities can interchangeably represent the same physical responses.
  • Establishes a hierarchy of capabilities in multimodal learning, including response substitution and ordered execution.
  • Shows that the executor's capability is critical for successful execution of programs in multimodal systems.
Read more
DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule
Euijin Hong, Guannan Qu
Optimization
  • DELTAMOMENTUM introduces a direction-aware momentum update that adapts forgetting rates based on the frequency of gradient directions.
  • The method is built on a key-value structure derived from the gradients of linear layers, enhancing the efficiency of momentum updates.
  • It provides theoretical guarantees of validity and performance, outperforming traditional EMA momentum in clearing stale directions.
  • DELTAMOMENTUM is a drop-in replacement for existing momentum buffers, maintaining compatibility with other optimization techniques.
Read more
Improved Confidence Estimates for Black-Box Large Language Models
Sokhna Diarra Mbacke, Mouloud Belbahri, Gabriel Loaiza-Ganem
NLP Large Language Models Interpretability
  • Proposes a novel framework for uncertainty quantification in LLMs using labeled datasets.
  • Utilizes simple classifiers to predict response correctness based on uncertainty scores and similar query correctness.
  • Demonstrates minimal computational overhead and flexibility in aggregating uncertainty scores.
  • Empirical results show consistent improvement over existing UQ methods across various datasets.
Read more
Multi-Agent Off-Policy Deep Reinforcement Learning for Smart Campus Coverage
Omar Rady, Mohamed Ayman, Ali Arafa, Mohamed Shalma
Reinforcement Learning Optimization
  • The optimization of BS placement in non-convex campus environments is NP-hard.
  • Multi-Agent DDPG outperforms single-agent approaches in terms of coverage and fairness.
  • The proposed framework achieves a Jain’s fairness index of 0.94 and guarantees full coverage.
  • The study introduces a boundary projection mechanism to enhance optimization.
Read more
Answer-Level Trust Selection for Physical Vision-Language Reasoning
Rongyu Yu, Ke Niu, Fengxiang He
Multimodal Computer Vision Interpretability
  • Introduces Answer-Level Trust Selection (ATS) for evaluating individual predictions of VLMs.
  • ATS is model-agnostic and requires no fine-tuning or access to internal model logits.
  • Utilizes eight behavioral diagnostic scores to generate a unified trust score for predictions.
  • Demonstrates that ATS can identify hidden failure modes in VLM predictions.
Read more
MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents
Bo Qian, Yuting Wu, Shuang Zeng, Huaiyu Wan, Dalin Zhang, Jiqiang Liu
Reinforcement Learning Large Language Models Optimization
  • MileGPO reveals the limitations of final-goal-distance credit in distinguishing same-state branches.
  • The proposed method learns from rollout graphs and on-policy rewards without needing external annotations or auxiliary inference.
  • MileGPO achieves state-of-the-art performance on ALFWorld and WebShop benchmarks.
  • The method effectively calibrates intermediate credit, leading to improved decision-making in long-horizon tasks.
Read more
Auditing Recorded Predictive Lead Service-Line Classifications Against Physical Verification: A Statewide Study of New York
Muhammad Sarmad Sohail
Theory
  • 49% of localities showed zero output variance in predictive classifications, raising concerns about model reliability.
  • New York City reported a uniform classification for over 43,000 addresses, indicating potential issues with the predictive model.
  • Physical verification revealed lead presence across all construction eras, contradicting the predictive model's findings.
  • The study identifies significant gaps in the predictive modeling approach, necessitating more rigorous validation methods.
Read more
SAGE-XGBoost: Spatially Augmented Graph Embeddings–Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity
Mohammad H. Vahidnia, Ali Pourkarimi
Graph Learning
  • SAGE-XGBoost improves natural hazard susceptibility mapping under data scarcity.
  • The framework combines data augmentation with graph embeddings for feature enhancement.
  • Significant performance improvements were observed over traditional machine learning models.
  • The model achieved high AUC values for both landslide and wildfire susceptibility.
Read more
FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design
Guofeng Zhang, Rong Han, Xiaoyu Wang, Zhiyun Li, Zongbo Han, Xiaohong Liu, Guangyu Wang
Generative Models Optimization
  • FAR-DPO addresses the challenges of cyclic peptide design by focusing on feasibility and robustness.
  • The framework integrates a novel preference construction strategy that accounts for structural and biophysical constraints.
  • FAR-DPO shows significant improvements in the success rate of feasible cyclic peptide designs across multiple generative models.
  • The methodology includes difficulty-aware optimization to ensure consistent performance across heterogeneous targets.
Read more
Green BOA: Determining the environmental break-even point for ML-based data compression
Caterina Doglioni, Akshat Gupta, Thomas Elliott, Hanzila Hussain, Sanjiban Sengupta
Efficient ML
  • The environmental break-even point for ML-based data compression is sensitive to the carbon intensity of the energy source.
  • ML-based compression algorithms can offer better compression ratios but may have higher carbon costs compared to traditional methods.
  • The study provides a framework for assessing the carbon footprint of ML training and inference against storage savings.
  • Future work will explore a broader range of scenarios and improve throughput for ML-based compression.
Read more
Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records
Jun Ni Du, Lukas Adamek, Maxim Kryukov, Flavio Dormont, Ziv Bar-Joseph, Sven Jager, Brandon Rufino
NLP Interpretability
  • Introduction of BERT-LER, a transformer model that combines laboratory data representation with interpretability.
  • Utilization of percentile-based binning for encoding laboratory results, preserving graded information.
  • Demonstrated competitive performance on EHRShot and real-world asthma progression tasks.
  • Token-level attributions using Integrated Gradients align with clinically known risk factors.
Read more
SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval
Zhenyao Cui, Siyuan Kan, Siyang Li, Ziwei Wang, Dongrui Wu
Multimodal
  • SCORE identifies that different subjects express similar concept relationships in distinct coordinate directions.
  • The framework allows for EEG-to-image retrieval without the need for target labels or encoder updates.
  • SCORE achieves superior accuracy in cross-subject retrieval compared to existing methods.
  • The method generalizes well across different EEG encoders and remains effective under various conditions.
Read more
Safe Domain Adaptation for Physics: Overcoming Nuisances, Label Shifts, and Simulation Priors
Ivan Kharuk
Theory
  • Traditional domain adaptation methods assume that differences between training and target domains are nuisances, which is often not true in physics.
  • The study reveals that standard adversarial domain adaptation can lead to biased predictions when energy spectra differ between domains.
  • An adaptive domain adaptation method is proposed to focus on genuine physical mismatches by reweighting simulated events.
  • A label-free model selection rule is introduced to help identify optimal training configurations without target labels.
Read more
NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification
S M Asif Hossain, Shruti Kshirsagar
Efficient ML Time Series
  • NanoSleep is a compact hybrid architecture for sleep stage classification with only 0.35 million parameters.
  • The model effectively combines multi-scale temporal and spectral feature extraction.
  • A weighted calibrated focal loss is used to address class imbalance in sleep stage datasets.
  • NanoSleep outperforms several state-of-the-art methods while being efficient for deployment on resource-constrained devices.
Read more
In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
Benjamin Smith, Levin Kuhlmann, Kaushik Roy, Gideon Kowadlo
Theory Generative Models Efficient ML
  • Introduction of 4MAS, a dual-hemisphere architecture for continual learning.
  • Utilization of a wake-sleep training cycle to enhance memory consolidation.
  • Competitive accuracy on Split-MNIST (98.3%), Split-Fashion-MNIST (84.9%), and Split-CIFAR-100 (29.29%).
  • Demonstration of low representational drift across tasks.
Read more
A FEM-Based Surrogate Modelling and Optimization Framework for Physics-Constrained Electromagnetic Coil Design
Yucheng Liu
Optimization
  • Introduces a FEM-based surrogate modeling framework for electromagnetic coil design.
  • Demonstrates the impact of FEM evaluation budget on optimizer performance.
  • Compares multiple optimization methods, revealing strengths and weaknesses based on budget constraints.
  • Provides an automated Python-MPh-COMSOL workflow for efficient design exploration.
Read more
CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
Alexander Marusov, Dmitry Anikin, Petr Sokerin, Vitaliy Pozdnyakov, Ilya Kuleshov, Alexey Zaytsev
Generative Models Time Series Optimization
  • CLaST introduces a VAE framework that preserves contextual similarity for improved time series forecasting.
  • The concept of Lag-Invariant Non-stationary Time Series (LINTS) is introduced to model temporal dependencies effectively.
  • The contrastive loss function enhances training stability and representation quality compared to traditional mutual information estimators.
  • CLaST achieves up to 16.4% improvement in CRPS and 14.4% in NMAE for short-term forecasting, and up to 48.6% and 25.1% improvements for long-term forecasting.
Read more
Vector Symbolic Policy Gradient
Ryozo Masukawa, Sanggeon Yun, SungHeon Jeong, Hyunwoo Oh, Raheeb Hassan, Pietro Mercati, Nathaniel D. Bastian, Mahdi Imani, Mohsen Imani
Reinforcement Learning Theory Efficient ML
  • Introduction of VSPG, a discrete-action policy-gradient actor using unit-norm hypervectors.
  • Exact vector-symbolic interpretation of the policy-gradient update as advantage-weighted bundling.
  • Creation of fixed-size compressed kernel memories for efficient learning and inference.
  • Demonstration of competitive performance and sample efficiency across multiple benchmarks.
Read more
Multi-stage neural operator learning with application for convolutions
Zhiping Mao, Zhenye Wen, Yong Zhang, Xiaofei Zhao
Theory Efficient ML
  • Introduction of two multi-stage neural operator learning frameworks: DCNO (supervised) and DGNO (unsupervised).
  • Both frameworks improve approximation accuracy by progressively constructing neural operator bases.
  • Theoretical analysis supports the convergence and approximation capabilities of the proposed methods.
  • Numerical experiments show that the methods achieve high accuracy and efficiency in convolution problems.
Read more
A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs
Tianhang Tan, Han Wu, Tousif Rahman, Shengyu Duan, Alex Yakovlev, Rishad Shafik
Efficient ML Time Series
  • Introduction of a Tsetlin Machine-based framework for NILM on MCUs.
  • Achieves high precision and recall rates for appliance classification.
  • Designed for real-time processing with minimal memory footprint.
  • Open-source implementation available for further research and development.
Read more
Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
Jialun Zheng, Hanchen Yang, Jiannong Cao, Yankai Chen, Yuanjing Feng, Philip S. Yu
Graph Learning
  • Introduces OTTA-DGAD for online test-time adaptation in dynamic graph anomaly detection.
  • Utilizes dynamic prototypes to capture evolving normal and anomalous patterns.
  • Implements a memory buffer that retains both general and domain-specific patterns.
  • Demonstrates superior performance on diverse datasets compared to existing methods.
Read more
Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
Astrid Horn Brorholt, Maris F. L. Galesloot, Nils Jansen, Kim Guldstrand Larsen, Christian Schilling
Reinforcement Learning
  • Introduces adaptive probabilistic shielding for safe reinforcement learning.
  • Combines online model learning with MDPs to estimate transition probabilities.
  • Addresses the exploration-exploitation dilemma in the context of safety.
  • Empirical evaluations show improved performance in various environments.
Read more
When to Retrain: An Empirical Study of Retraining Policies for Streaming ML Under Concept Drift, Budget, and Latency Constraints
Sawan Dasari
Theory Efficient ML Time Series
  • Incremental learning significantly impacts the effectiveness of retraining policies.
  • Periodic retraining outperforms reactive policies under abrupt and gradual drift.
  • Reactive policies exhibit systematic failures, including budget exhaustion and drift blindness.
  • A latency-budget interaction can reduce effective retraining budgets by half.
Read more
Quantifying Event Impacts on Time Series via Multiscale Contrastive Learning
Yiming Sun, Shengyu Chen, Zhengzhang Chen, Haoyu Wang, Xiaowei Jia, Haifeng Chen
Time Series
  • Introduces EventTime, a novel framework for estimating financial impacts of cybersecurity events.
  • Incorporates multi-resolution market context and event metadata for enhanced prediction.
  • Utilizes a dynamic contrastive learning approach to address sparse supervision challenges.
  • Demonstrates superior performance over state-of-the-art models in estimating abnormal losses.
Read more
When Does Dynamic Ensembling Pay Off? Diagnosing Regionwise Gains in Regression under Distribution Shift
Tianxin Zhou, Ruixi Lin
Theory Optimization Efficient ML
  • Introduction of bDCF5, a diagnostic tool for assessing dynamic ensembling gains in regression under distribution shifts.
  • High predictive accuracy of bDCF5 with a Spearman correlation of +0.98 across diverse dataset-shift pairs.
  • Development of the Probe-Validated Ensemble Selector to choose between static and dynamic models based on validated gains.
  • Demonstrated significant risk reduction in test scenarios using dynamic ensembling compared to static methods.
Read more
Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
Haiyue Zhang
Reinforcement Learning Large Language Models Theory
  • Existing step-level credit signals do not effectively identify causally important steps in LLM agents.
  • Causal contributions are sparse and vary significantly between different model architectures.
  • Implicit credit scores correlate more with policy fluency than with actual causal contributions.
  • A confidence-only routing rule can reduce costs while maintaining performance at chance levels.
Read more
Transportable Causal Effect Estimation across Networks under Interference
Xiaojing Du, Jiuyong Li, Lin Liu, Debo Cheng, Jixue Liu, Thuc Duy Le
Graph Learning Theory
  • Introduces TranCE, a novel algorithm for causal effect estimation across different networks under interference.
  • Establishes graphical conditions for causal effect transportability using a selection diagram.
  • Derives transport formulas for direct, spillover, and total effects in the deployment population.
  • Demonstrates the effectiveness of the proposed method through extensive experiments on real-world data.
Read more
Atrial Fibrillation Detection with Arbitrary Leads via a Codebook-Based Reconstruction-Classification Framework
Hongtao Li, Jia Wei, Guoyao Li, Yuchen Lei, Guangnian Ma, Jia Xiao, Yuanjun Lai, Shuzhen Lv, Xueqiang Ouyang
Time Series Generative Models Graph Learning
  • DCGCNet introduces a novel codebook-based framework for joint classification and reconstruction of ECG signals.
  • The model incorporates a Local-Global Contrastive Module to enhance noise resilience.
  • DCGCNet demonstrates exceptional performance with AUC > 0.98 across multiple datasets and conditions.
  • The approach effectively addresses the limitations of existing AF detection methods by integrating reconstruction and classification tasks.
Read more
DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers
MD Saifur Rahman Mazumder, Feng Yu
Efficient ML Interpretability Theory
  • DICS leverages clustering to create a compact set of candidate splits, enhancing computational efficiency.
  • Theoretical analysis shows that DICS maintains predictive performance compared to exhaustive split search.
  • DICS can be applied to various tree-based models, including random forests and gradient-boosting machines.
  • Extensive experiments validate that DICS achieves similar accuracy while significantly reducing training time.
Read more
Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation
Jia-Qi Lin, Yuangang Pan, Chang-Dong Wang, Haizhang Zhang, Ivor W. Tsang, Joey Tianyi Zhou
Computer Vision Theory Efficient ML
  • Introduction of neural collapse concept to Open-World Test-Time Adaptation (OWTTA).
  • Development of the Reliable Neural Collapse approximation (ReNC) method for effective adaptation.
  • Utilization of classifier weights as source domain prototypes to filter OOD samples.
  • Demonstration of ReNC's superiority through extensive experiments on open-world benchmarks.
Read more
FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration
Huang Cheng, Scott Zhang, Aubert Li
Large Language Models Optimization Efficient ML
  • FleetSieve focuses on decision-critical profiling to optimize LLM fleet configurations.
  • It models capacity and tail latency jointly to avoid infeasible configurations.
  • The method reduces profiling GPU-seconds significantly compared to traditional methods.
  • FleetSieve provides a three-state decision certificate indicating feasibility.
Read more
Towards On-Board Implementation of ML-Based Helicopter Weight Estimator
Nicolas Valot, Ammar Mechouche, Benjamin Lesage, Claire Pagetti, Louis Fabre
Time Series Optimization Robotics
  • Development of a supervised ML model for helicopter weight estimation.
  • Alignment with EASA and Eurocae ED-324 standards for safety assurance.
  • Implementation of an LSTM architecture for the weight estimator.
  • Verification of the model on legacy avionics systems for practical deployment.
Read more
A Locally Tokenized Generative Model for Robust Time-Series Watermarking
Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park, Jaewook Lee
Generative Models Time Series
  • Introduces L-VQVAE, a generative model that relies on local tokenization for time-series data.
  • Proposes LVQMark, a watermarking method that enhances robustness against post-editing attacks.
  • Demonstrates that traditional watermarking methods suffer from false positives due to global re-encoding instability.
  • Achieves stable detection power and reduced false-positive rates in attacked non-watermarked samples.
Read more
H$^2$EDL: Hyper Evidential Deep Learning for Hierarchical Classification
Yuanye Liu, Xiahai Zhuang
Computer Vision Theory Interpretability
  • H2EDL provides a unified framework for uncertainty representation in hierarchical classification.
  • The model uses a taxonomy to create a linear-size focal family for hyper-evidential beliefs.
  • H2EDL reduces calibration error by approximately half compared to traditional methods.
  • The model maintains hierarchical coherence and exposes uncertainty at each decision level.
Read more
Infrared Universality of Collective Dynamics across Transformer and State-Space Architectures
Byung Gyu Chae
Theory Large Language Models NLP
  • Investigates collective dynamics in Transformers and Mamba, a state-space model.
  • Finds that both architectures exhibit similar infrared organization despite different microscopic mechanisms.
  • Demonstrates that Mamba's long-sequence exponent stabilizes near βM ≃−0.17, indicating long-memory dynamics.
  • Extends the understanding of collective dynamics in neural networks beyond Transformers.
Read more
Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models
Grégoire Sergeant-Perthuis, Elias Tsigaridas, Jules Tsukahara
Theory
  • Introduces a deterministic algorithm for exact computation of local RLCTs in two-dimensional models.
  • Demonstrates the limitations of classical information criteria in singular models and proposes WBIC as a solution.
  • Reveals that effective model complexity can decrease with depth in polynomial neural networks, challenging conventional wisdom.
  • Provides a complexity bound for the proposed algorithm, ensuring its applicability across a broad class of models.
Read more
Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems
Mark Kozdoba, Shie Mannor
Theory
  • Traditional spectral methods can lead to linear masking, omitting entire components from models of dynamical systems.
  • The proposed method focuses on scoring the σ-algebra generated by coordinates, allowing for more efficient representation.
  • A finite budget of coordinates can capture the entire spectrum of the transfer operator, avoiding the pitfalls of rank-based methods.
  • The approach is validated through benchmark systems, demonstrating superior performance in recovering masked components.
Read more
Scale-Aware Pretraining of Time Series Foundation Models via Multi-Patch Token Alignment and Hybrid Masking
Taihua Chen, Xiang Ma, Yixin Zhang, Tailin Zhan, Manyu Sun, Lizhen Cui
Time Series
  • SATS introduces a scale-aware token alignment mechanism for time series pretraining.
  • The method preserves scale-specific expressiveness while unifying token spaces across patch scales.
  • A hybrid masking strategy is designed to capture both fine-grained and long-range temporal dependencies.
  • SATS demonstrates superior performance on LSTF benchmarks compared to existing methods.
Read more
DraftFM: A Foundation Model for Day-Zero Drafting in Magic: The Gathering
Brian Ward
Theory
  • DraftFM operates effectively in a day-zero drafting context, scoring unseen cards based on public information.
  • The model achieved significant predictive accuracy, outperforming random selection and existing models trained on specific sets.
  • It provides a novel approach to card representation using frozen embeddings, avoiding reliance on set-specific data.
  • The model's predictions for the unreleased set 'The Hobbit' were validated against expert opinions.
Read more
Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation
Guiv Farmanfarmaian
NLP Large Language Models Efficient ML
  • Introduces a candidate-free control to measure the net value of candidate conditioning.
  • Finds that conditioning improves accuracy when multiple candidates are correct but reduces it when all candidates are wrong.
  • Demonstrates that failures in all-wrong scenarios often match displayed candidate answers.
  • Shows that explicit answer fields can guide outputs, while masking does not improve accuracy.
Read more
A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
Anton Lambrecht, Reda El Hail, Xianjun Jiao, Pieter Crombez, Dominique Schreurs, Peter Karsmakers, Adnan Shahid, Eli De Poorter
Time Series
  • Controlled comparison of FMCW, IR-UWB, and Wi-Fi sensing technologies under identical conditions.
  • IR-UWB outperforms in cross-subject activity recognition, while FMCW excels in generalization to new environments.
  • All technologies demonstrate high performance in sleep monitoring tasks.
  • Identifies a trade-off between recognition performance and robustness based on signal characteristics.
Read more
Towards Reversible Forgetting: Managing Obsolete Knowledge in Continual Enterprise AI Agents
Nilutpaul Sarker Yash, Tirtho Roy, Ushashi Bhattacharjee
Theory
  • Reversible forgetting allows for the suppression of obsolete knowledge without permanent erasure.
  • The framework introduces three operational memory states: active, dormant, and retired.
  • The Hysteretic Reversible Memory Controller (HRMC) manages knowledge transitions with evidence accumulation and policy gates.
  • The approach reframes continual learning as a management of knowledge lifecycle rather than mere retention.
Read more
Tensor Field Models
Alexander Strunk, Roland Assam
Generative Models Theory Efficient ML
  • Introduction of Tensor Field Models (TFMs) as a new mathematical structure for machine learning.
  • TFMs utilize a learned operator to map component-section families to time-dependent tangent sections.
  • The architecture allows for efficient reuse of condition representations across multiple queries.
  • Experiments demonstrate improved performance and faster generation through amortized sampling.
Read more
Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval
Zhenyao Cui, Siyuan Kan, Dingkun Liu, Dongrui Wu
Multimodal
  • Identification of a non-transitive alignment pattern in few-repetition brain-to-image retrieval.
  • Introduction of the NEAR framework that enhances retrieval accuracy by anchoring neural and visual representations.
  • Demonstrated improvements in retrieval performance across multiple datasets and modalities.
  • Reduction of reliance on repeated stimulus presentations, addressing latency and user burden.
Read more
Graphical Design of Interpretable Architectures
Pietro Barbiero
Interpretability
  • Introduces a graphical notation for interpretable AI architectures based on Penrose tensor notation.
  • Provides a global view of architectures while mapping directly to PyTorch einsum code.
  • Describes interpretable architectures by construction, enhancing understanding and reproducibility.
  • Demonstrates the notation with a case study on the Steerling-8B language model.
Read more
Systematic Evaluation of TabPFN-TS for Zero-Shot Probabilistic Heat Load Forecasting in District Heating Networks
Ben Spoek, Karim K. Ben Hicham, Kai Derzsi, Philipp Althaus, Alexander Mitsos, Dirk Müller
Time Series
  • TabPFN-TS is evaluated for its effectiveness in zero-shot probabilistic heat load forecasting.
  • The study identifies optimal configurations for forecasting, emphasizing the importance of context length and covariate selection.
  • TabPFN-TS performs competitively with established models like Chronos-2, particularly in calibration.
  • A new Multi-Resolution Residual-Correction Forecaster is proposed to improve forecasting accuracy for longer horizons.
Read more
Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW
Kang Liu, Suyan Li
Optimization Theory
  • Formulation of localized minibatch influence as a signed finite-horizon response under paired AdamW trajectories.
  • Development of a joint parameter-moment ISO operator to characterize the propagation of perturbations and their effects on loss.
  • Establishment of an exact multistep error decomposition that separates various sources of error in the response dynamics.
  • Experimental validation of the proposed response mechanism and optimizer-state effects.
Read more
Inadvertent Context Leakage in Language Models
Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar
NLP Large Language Models Theory
  • Inadvertent context leakage allows sensitive information to be reconstructed from benign model outputs.
  • Controlled experiments show high accuracy in reconstructing numeric secrets from model responses.
  • More capable models exhibit greater leakage, suggesting a correlation between model capability and privacy risks.
  • The study introduces a suppression mechanism to mitigate leakage and evaluates its effectiveness across various models.
Read more
SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
Hugo Porta, Emanuele Dalsasso, Chang Xu, Theo Gnassounou, Devis Tuia
Interpretability
  • Introduction of a geographic location-aware SAE (GeoTopK) for ExEE analysis.
  • Development of SAE-Xplainers for rule-based interpretation of complex features.
  • Demonstrated improvements in reconstruction performance and feature utilization.
  • Validated on three types of extreme Earth events: fires, tropical cyclones, and atmospheric rivers.
Read more
DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
Alexander Marusov, Dmitry Anikin, Alexey Zaytsev
Time Series Generative Models Interpretability
  • DecoVAE provides a lightweight and interpretable framework for probabilistic time series forecasting.
  • The model explicitly decomposes time series into trend and seasonal components using specialized mechanisms.
  • DecoVAE achieves significant accuracy improvements over strong baselines while maintaining high computational efficiency.
  • The framework employs a differential regularizer for trend smoothness and complex-domain modeling for seasonality.
Read more
Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
Vijay Erramilli
Interpretability
  • Introduces mechanistic tomography as a unified framework for measurement in mechanistic interpretability.
  • Establishes a common measurement language for various interpretability methods.
  • Demonstrates the importance of control-oriented validation in assessing interpretability.
  • Provides empirical results showing the effectiveness of the proposed measurement strategies.
Read more
GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models
Qi Qin, Jiajie Zhu, Dali Chen, Yuzhao Zhang, Jia-Xing Han, Yu Su, Peng Zhang, Ying Yan, Yifan Sun
Efficient ML
  • GEAR distills TFMs into efficient MLP or tree-based models for practical deployment.
  • The two-stage process includes Generative Expansion and Real Anchoring to enhance model performance.
  • Significant improvements in AUC scores over traditional supervised models were observed.
  • GEAR reduces inference time by up to 2866 times and memory usage by 3.3 times.
Read more
Orthogonal JEPA: Factorized Predictive States for Latent World Models
Taoyong Cui, Pheng Ann Heng, Wanli Ouyang
Computer Vision Time Series Robotics
  • Introduction of Orthogonal JEPA for improved latent world modeling.
  • Utilization of orthogonal predictive factorization to analyze target states into multiple components.
  • Implementation of dedicated prediction branches for each component to enhance predictive capacity.
  • Incorporation of regularization techniques to maintain diversity and prevent encoder collapse.
Read more
Unsupervised Anomaly Detection Using Flow Matching on Tabular Data
Philip Konz, Tejaswini Medi, Margret Keuper
Generative Models Theory Efficient ML
  • Investigates flow-matching-based anomaly detection under contaminated training data.
  • Highlights the importance of anomaly scoring functions for robustness.
  • Demonstrates that trajectory-based scoring improves detection performance.
  • Shows that Forest-Flow can outperform TCCM with appropriate scoring functions.
Read more
An Empirical Benchmark of Deep Time-Series Models for Smart Meter Energy Forecasting
Behnaz Kavoosighafi, Maria Eidenskog, Wiktoria Glad, Katerina Vrotsou
Time Series
  • Benchmarking of nine deep learning models for energy forecasting on real-world datasets.
  • Forecasting accuracy improves with historical context only to a saturation point; accuracy declines with longer prediction horizons.
  • Lightweight architectures can achieve competitive accuracy at lower computational costs.
  • Transformer models show potential advantages for under-represented population segments, though not consistently statistically robust.
Read more
Rationally Enriched Chebyshev Trunk Bases for DeepONet Surrogates of High Péclet Entrance Transport
Mingeun Choi, Satish Kumar
Theory Optimization Efficient ML
  • Introduction of Rationally Enriched Chebyshev trunks for DeepONet models.
  • Demonstrated significant improvements in predicting solution profiles for high-Péclet transport problems.
  • REC-trunk DeepONet reduces profile-error metrics by up to 60.2% compared to traditional models.
  • Effective suppression of artificial oscillations in near-wall regions.
Read more
Forgetting, plasticity, and co-observation: a third facet of continual learning
Timm Hess, Abhishek Jha, Gido M. van de Ven, Tinne Tuytelaars
Theory
  • Introduction of the co-observation effect as a critical factor in continual learning.
  • Demonstration of performance benefits from simultaneous observation of training data.
  • Empirical validation across supervised and self-supervised learning paradigms.
  • Critique of existing continual learning methods in light of co-observation.
Read more
RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations
En Zhi Tan, Jia Xiang Lim, Bryan Lijie Chew, Tze Minh Ng, Benjamin Yan Han Yap
Efficient ML Theory NLP
  • RecPFN is the first embedding-based PFN-style ICL approach for sequential recommendation.
  • The model is pretrained on synthetic data, enabling strong performance with less computational overhead.
  • RecPFN achieves state-of-the-art zero-shot performance and is robust to domain shifts.
  • The architecture allows for next-item predictions in a single forward pass without weight updates.
Read more
Evaluating Neural Cartographic Relief Shading for Urban Environments: A Downtown Calgary Study Using High-Resolution DEM and DSM Data
Emmanuel Stefanakis
Computer Vision
  • The study compares traditional analytical hillshading methods with a neural-based approach in an urban environment.
  • Eduard, a neural system trained on mountainous terrain, shows potential for effective urban shading through parameter tuning.
  • The research identifies strengths and weaknesses of both methods, emphasizing the need for tailored neural training for urban contexts.
  • High-resolution DEM and DSM data from downtown Calgary provide a relevant test case for evaluating hillshading techniques.
Read more
Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum
Yingying Zhang, Kun Zhao, Guodong Liu, Qi Huang, Pengfei Gu, Dongchul Kim, Erik Enriquez, Alex D. Leow, Paul M. Thompson, Heng Huang, Hongchang Gao, Liang Zhan, Haoteng Tang
Time Series Theory Generative Models
  • DCP provides a continuous representation of disease severity, moving beyond discrete diagnostic categories.
  • The Disease Continuum Score (DCS) captures clinically relevant variations and predicts future disease progression.
  • DCP integrates longitudinal DTI data with weak clinical supervision for improved disease assessment.
  • Extensive validation shows DCS's strong clinical relevance and ability to characterize disease evolution.
Read more