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 50
When Is Personalized Federated Learning Worth Its Deployment Cost?
Personalized federated learning (PFL) may improve client-level performance, but deeper personalization increases deployment cost.Value Forcing: Aligning Return Distributions at All Noise Levels
Learning accurate value functions is central to reinforcement learning (RL), yet remains challenging because supervision is limited and indirect: ground-truth values are unavailable, and each…Rewarded for Not Getting Caught: Why Alignment Training Selects for Conditional Compliance and Cannot Instill Norms
Current alignment training cannot be expected to deliver what it is meant to deliver: AI agents that comply with norms whatever the gains and whether or not anyone is watching.Restrained Diffusion Bridges: Targeted Denoiser Training and Refinement
Diffusion models are often inaccurate in critical, data-sparse regions of the target distribution.Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics
Diagonal state space models process long sequences at linear cost, yet the same transition is applied at every step of a rollout, so an unconstrained recurrence holds no quantity fixed and the state…ANCHOR: KL-Anchored Adaptation for Stable Offline-to-Online RL
Offline-to-online reinforcement learning (RL) follows the pretrain-finetune paradigm: an agent is first pretrained on historical data and then adapted through online interaction.Inner-Speech Decoding from EEG Across Three Corpora Under a Fixed Architecture and Protocol
Inner-speech decoding from electroencephalography could support non-invasive communication for people with severe motor impairment, but comparison across studies is hindered by dataset- and…Fuzzy-Enhanced Machine Learning Approach for Type 2 Diabetes Diagnosis
Accurate diabetes prediction is critical for early clinical intervention, yet existing machine-learning pipelines often fail due to class imbalance, noisy physiological measurements, and redundant…Built on Broken Assumptions (BOBA): Why Coding Agents Cannot Be Left Alone
Coding agents are autonomous developers.Test-Time Scaling for Open-Ended Reasoning at Small Model Scale
A vote over a model's samples can only help when the samples disagree.Discrimination, Calibration, and Ranking: A Unified Matrix Framework
Discrimination, calibration, and ranking are the three pillars of classifier evaluation, yet no single algebraic language spans all three.Beyond Ensemble Disagreement: Predictive STL Monitoring of RL Locomotion under Distribution Shift
RL locomotion policies trained under nominal simulation conditions may encounter distribution shifts that compromise safety.Who Should Score the Cache? Mid-Depth Layers Are the Best Judges of KV-Cache Eviction
Key-value (KV) cache eviction methods rank tokens by attention scores, and each layer scores its own cache.Iterative Gumbel Planning for Continuous Control
Search-based planning remains a powerful policy improvement paradigm in reinforcement learning, driving milestone successes in discrete domains.Nonreciprocal Spherical Attention and Retrieval: Sharp Coarsening Clocks and Certified Score Correction
We develop nonreciprocal spherical attention as a mathematical framework for coarsening and compressed nearest-neighbor retrieval.Metamorphic Testing for Evaluating Robustness of Sentiment Analysis Models
Machine learning systems are challenging to test using traditional software testing methods because their behavior is learned from data rather than explicitly programmed.Retrain, Alert, or Rollback? A Three-Response Decision Framework for Production ML Under Concept Drift
When a deployed model degrades under concept drift, an operator can retrain it, raise an alert and monitor, or roll back.Partial Invariance for Classification under Structural Causal Models
Making predictions in an unseen environment from data collected across multiple training environments is challenging.Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism Thresholding
We consider classification in high-dimensional feature spaces where only a vanishing fraction of features are useful and the number of classes may be large.Overcoming Demand Censoring through Randomization for Risk-Sensitive Newsvendor Learning
We study online newsvendor learning with bounded demand, censored observations, and convex nonlinear shortage costs.