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 5
EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets
Energy forecasting models are usually compared on backtests and fixed public datasets.Decodability Is Not Validity: Evaluating Nuisance Sensitivity in Language Model Concept Probes
Two concept probes can be equally accurate at predicting a concept from a language model's hidden states while their scores contain different mixtures of the target concept and a correlated nuisance…Estimating Spectrum-Free Information Bounds for Generative Surrogates Beyond Conditional Collapse
Conditional generative surrogates in high-energy physics, such as models that predict reconstructed jets from partons, are often evaluated on $1\text{D}$ marginal divergences among other metrics.Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis
Recent innovations in medical imaging have markedly improved brain tumor identification, surpassing conventional diagnostic approaches that suffer from low resolution, radiation exposure, and…Masked diffusion as random sequential adsorption: an exactly solvable model for parallel decoding
Masked diffusion models generate text by reversing a stochastic masking process.Computation, not weight access: large language models as auditors of clinical prediction networks
Frontier large language models (LLMs) have been reported to read, edit and write the weights of small neural networks, raising the prospect of auditing clinical prediction models from their files…PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State
Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities.Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness
Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and verifying them by executing tests or by extended reasoning is costly.When, Where, How: Active In-Context Learning for Tabular Foundation Models
Tabular Foundation Models (TFMs) adapt to a new task only through the labeled rows in their context.DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning
Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch.Structure from Collision via Hypothesis-Space Reasoning
Knowledge of the hidden interior structure of an object, including the presence and location of cavities, is essential for predictive simulation, robotic manipulation, and nondestructive inspection.EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure
Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under-constrained…Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models
Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions.Flux as a Codec: Zero-Shot Lossy Compression with Flux
We propose FluxC, a zero-shot codec that uses Flux as a compression prior.AttnSR: Attention Step Reward for Long-Horizon Agentic RL
Long-horizon LLM agents make multi-step decisions, yet outcome-reward-only reinforcement learning provides little direct supervision for individual steps.The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning
Reinforcement learning (RL) provides a framework for continuous improvement through interaction with an environment.Joint Modeling of Conditional Mean and Variability in Multilevel Functional Data: Application to Postprandial Glucose Trajectories in the AEGIS Study
Functional data analysis provides a framework for studying time-varying associations between covariates and high-frequency biological signals.Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification
Benchmarks of class-imbalance strategies for multimodal chest X-ray (CXR) and electronic health record (EHR) prediction are often evaluated on record-level splits of cohorts in which one patient…Invariance before structure: two modes of emergent compression in representation learning
Learned representations show striking invariance across biological and artificial neural networks, with different substrates and variations driven by drift, heterogeneity and initialisation.A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems
Frontier artificial intelligence (AI) systems are increasingly operating over longer horizons with diminishing human oversight, raising the risk of loss of control: systems acting beyond effective…