AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 110
Minimax Regret for Sobolev Kernel-Based Reinforcement Learning
We study the minimax regret rate for episodic kernel-based reinforcement learning, where the expected reward and transition density belong to a Sobolev reproducing kernel Hilbert space, with…Leveraging Dale's Principle as an Inductive Bias in Recurrent Neural Networks
One of the fundamental differences between biological neural networks and artificial neural networks (ANNs) is that biological neurons obey Dale's principle: each neuron projects either exclusively…INTRA: Interleaved Non-contiguous Token spaRse Attention
Transformers achieve strong performance across modalities but are bottlenecked by the quadratic cost of attention.T2D: Target-to-Draft Model Pruning & Adaptation for Efficient Speculative Decoding
Speculative decoding significantly accelerates autoregressive text generation in Large Language Models (LLMs), but its efficacy depends largely on two key factors: the distributional alignment…Synthetic Data Augmentation for Functional Data: Wasserstein Risk Bounds and Diffusion-Based Conditional Generation
Functional data are costly to collect; samples of tens to hundreds of curves are common.BE-CTDE: Blockchain-Enabled Multi-Agent Reinforcement Learning with Anomaly Detection and Token Economics
Multi-agent reinforcement learning supports cooperative decision-making in Internet of Things systems, but strategic deviations can disrupt coordination and undermine confidence in the training…Enhancing Type 2 Diabetes Diagnosis with Evolutionary Algorithms and Machine Learning
Type 2 diabetes is a widespread chronic disease that requires early and accurate diagnosis to prevent serious complications.HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model
Humanoid robots have recently achieved remarkable success in motion tracking.Bug Severity Classification with Fine-Tuned Open LLMs: A Paired Comparison with TF-IDF and CodeBERT Baselines on Eclipse Reports
Open large language models (LLMs) small enough to run on a laptop are an obvious candidate for automatic bug severity prediction.Self-Evolution Reasoner: Continuous Optimization via Policy-Intrinsic Exploration and Exploitation
Reinforcement learning with verifiable rewards (RLVR) enables large language models (LLMs) to continuously self-improve their reasoning capabilities.Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification
On million-node graphs, the memory wall arrives before the compute wall: a GNN that never fits in VRAM cannot deliver the all-node inference its accuracy promises.Reversion, Retention, and Semantic Intervention: Measuring Functional Content in CLIP Fine-Tuning Deltas
Fine-tuning adapts pretrained models to new tasks, but identifying which weight changes support the resulting behavior remains difficult.Execution Logs Sway VLM Judges of Robot Progress
Vision-language models now grade robot videos, and text placed beside the frames can change their verdicts.Edge-Centric Adaptive Neural Activation via Parametric Tanh Functions
Within the broader landscape of artificial intelligence architectures, this paper introduces a compact, edge-centric neural framework that resolves the computational bottlenecks of modern…Last-Iterate Stationarity of Muon with Finitely Many Newton-Schulz Iterations
Muon has achieved strong empirical performance in large-scale language-model training, motivating a better theoretical understanding of its practical implementation.Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks
Lithium-ion batteries are widely used in industrial applications, but their performance gradually degrades over time, making accurate lifetime prediction important for safety and reliability.Reinforcement Learning for Adaptive Crowd Flow Control Using Dynamic Barriers
Crowd barriers are widely used to regulate pedestrian movement during large public events such as pilgrimages.MetaARIMA: Configuration-Level Transfer Learning for ARIMA Models
Time Series Foundation Models have demonstrated that pretraining on diverse datasets enables effective transfer to new forecasting tasks.Reasoning or Just Prompting? Probing the Mechanism of Latent Chemical Reasoning
Latent reasoning performs intermediate computation in continuous space rather than through explicit tokens, which is particularly appealing in chemistry, where errors in explicit reasoning can…Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime
Instruction-based image editors built on diffusion transformers run tens of denoising steps.