#Machine Learning
Latest news articles tagged with "Machine Learning". Follow the timeline of events, related topics, and entities.
Articles (30)
-
🇺🇸 A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
[USA]
arXiv:2602.23163v1 Announce Type: new Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms....
Related: #AI Safety, #Steganography, #Information Theory -
🇺🇸 Survey on Neural Routing Solvers
[USA]
arXiv:2602.21761v1 Announce Type: cross Abstract: Neural routing solvers (NRSs) that leverage deep learning to tackle vehicle routing problems have demonstrated notable potential for practical applic...
Related: #Artificial Intelligence, #Optimization -
🇺🇸 SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
[USA]
arXiv:2602.22225v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has strong potential for producing accurate and factual outputs by combining language models (LMs) with evidence...
Related: #Information Retrieval, #Artificial Intelligence -
🇺🇸 Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials
[USA]
arXiv:2602.22251v1 Announce Type: cross Abstract: General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities. However, most existi...
Related: #Artificial Intelligence, #Chemical Modeling -
🇺🇸 Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging
[USA]
arXiv:2602.22279v1 Announce Type: cross Abstract: Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack...
Related: #Signal Processing, #Self-Supervised Learning -
🇺🇸 Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion
[USA]
arXiv:2602.22280v1 Announce Type: cross Abstract: Cardiovascular disease is the primary cause of death globally, necessitating early identification, precise risk classification, and dependable decisi...
Related: #Medical AI, #Healthcare Technology -
🇺🇸 Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
[USA]
arXiv:2602.22751v1 Announce Type: new Abstract: Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly tra...
Related: #Artificial Intelligence, #Reasoning Models -
🇺🇸 UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs
[USA]
arXiv:2602.22296v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and program...
Related: #Artificial Intelligence, #Language Models -
🇺🇸 Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory
[USA]
arXiv:2602.22345v1 Announce Type: cross Abstract: This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework ...
Related: #AI Efficiency, #Model Reliability -
🇺🇸 Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models
[USA]
arXiv:2602.22469v1 Announce Type: cross Abstract: Vision-language models (VLMs) frequently hallucinate objects absent from the input image. We trace this failure to spatial credit collapse: activatio...
Related: #Artificial Intelligence, #Computer Vision -
🇺🇸 GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
[USA]
arXiv:2602.22434v1 Announce Type: cross Abstract: Machine learning training pipelines consume data in batches. A single training step may require thousands of samples drawn from shards distributed ac...
Related: #Distributed Computing, #Data Optimization, #Storage Efficiency -
🇺🇸 Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints
[USA]
arXiv:2602.22488v1 Announce Type: cross Abstract: Distributed denial-of-service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-const...
Related: #Cybersecurity, #IoT Systems, #Explainable AI -
🇺🇸 Revisiting Chebyshev Polynomial and Anisotropic RBF Models for Tabular Regression
[USA]
arXiv:2602.22422v1 Announce Type: cross Abstract: Smooth-basis models such as Chebyshev polynomial regressors and radial basis function (RBF) networks are well established in numerical analysis. Thei...
Related: #Model Comparison, #Tabular Regression, #Smooth-basis Models -
🇺🇸 PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
[USA]
arXiv:2602.23161v1 Announce Type: new Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations...
Related: #Artificial Intelligence, #Time Series Analysis -
🇺🇸 Predicting Tennis Serve directions with Machine Learning
[USA]
arXiv:2602.22527v1 Announce Type: cross Abstract: Serves, especially first serves, are very important in professional tennis. Servers choose their serve directions strategically to maximize their win...
Related: #Sports Analytics, #Strategic Decision Making -
🇺🇸 Autoregressive Visual Decoding from EEG Signals
[USA]
arXiv:2602.22555v1 Announce Type: cross Abstract: Electroencephalogram (EEG) signals have become a popular medium for decoding visual information due to their cost-effectiveness and high temporal res...
Related: #Brain-Computer Interface, #Neuroscience, #Computer Vision -
🇺🇸 How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
[USA]
arXiv:2602.22441v1 Announce Type: new Abstract: Latent reasoning has been recently proposed as a reasoning paradigm and performs multi-step reasoning through generating steps in the latent space inst...
Related: #Artificial Intelligence, #Reasoning Paradigms -
🇺🇸 CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines
[USA]
arXiv:2602.22452v1 Announce Type: new Abstract: A reliable action feasibility scorer is a critical bottleneck in embodied agent pipelines: before any planning or reasoning occurs, the agent must iden...
Related: #Artificial Intelligence, #Robotics -
🇺🇸 DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
[USA]
arXiv:2602.22839v1 Announce Type: new Abstract: Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presen...
Related: #Artificial Intelligence, #Presentation Generation, #Agent Frameworks -
🇺🇸 OmniGAIA: Towards Native Omni-Modal AI Agents
[USA]
arXiv:2602.22897v1 Announce Type: new Abstract: Human intelligence naturally intertwines omni-modal perception -- spanning vision, audio, and language -- with complex reasoning and tool usage to inte...
Related: #Artificial Intelligence, #Multi-modal Systems -
🇺🇸 To Deceive is to Teach? Forging Perceptual Robustness via Adversarial Reinforcement Learning
[USA]
arXiv:2602.22227v1 Announce Type: cross Abstract: Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex sc...
Related: #Artificial Intelligence, #Computer Vision, #Model Robustness -
🇺🇸 Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction
[USA]
arXiv:2602.22274v1 Announce Type: cross Abstract: Traffic flow forecasting has emerged as an indispensable mission for daily life, which is required to utilize the spatiotemporal relationship between...
Related: #Traffic Prediction, #Smart Cities -
🇺🇸 Causal Direction from Convergence Time: Faster Training in the True Causal Direction
[USA]
arXiv:2602.22254v1 Announce Type: cross Abstract: We introduce Causal Computational Asymmetry (CCA), a principle for causal direction identification based on optimization dynamics in which one neural...
Related: #Causal Inference, #Optimization Dynamics -
🇺🇸 Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning
[USA]
arXiv:2602.22285v1 Announce Type: cross Abstract: Objective: The objective of this study is to develop a machine learning (ML)-based framework for early risk stratification of clinical trials (CTs) a...
Related: #Clinical Trials, #Risk Stratification, #Medical Safety -
🇺🇸 Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function
[USA]
arXiv:2602.22255v1 Announce Type: cross Abstract: We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space...
Related: #Quantum Computing, #Natural Language Processing, #Theoretical Computer Science -
🇺🇸 Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault Detection
[USA]
arXiv:2602.22297v1 Announce Type: cross Abstract: Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not ful...
Related: #Industrial Diagnostics, #Reinforcement Learning -
🇺🇸 AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
[USA]
arXiv:2602.22298v1 Announce Type: cross Abstract: Current AI weather forecasting models predict conventional atmospheric variables but cannot distinguish between cloud microphysical species critical ...
Related: #Aviation Safety, #Weather Forecasting -
🇺🇸 A 1/R Law for Kurtosis Contrast in Balanced Mixtures
[USA]
arXiv:2602.22334v1 Announce Type: cross Abstract: Kurtosis-based Independent Component Analysis (ICA) weakens in wide, balanced mixtures. We prove a sharp redundancy law: for a standardized projectio...
Related: #Statistical Analysis, #Signal Processing -
🇺🇸 Learning geometry-dependent lead-field operators for forward ECG modeling
[USA]
arXiv:2602.22367v1 Announce Type: cross Abstract: Modern forward electrocardiogram (ECG) computational models rely on an accurate representation of the torso domain. The lead-field method enables fas...
Related: #Medical Technology, #Computational Modeling, #Healthcare Innovation -
🇺🇸 Reinforcement-aware Knowledge Distillation for LLM Reasoning
[USA]
arXiv:2602.22495v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the hi...
Related: #Knowledge Distillation, #Reinforcement Learning