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 53
Roz: A Taste Test for World Model Latents
State of the art latent dynamics world models achieve impressive performance for robot planning.ECG2Gene: Deep Learning-Based Germline Tumor Susceptibility Gene Risk Assessment Using Electrocardiograms
Electrocardiograms (ECGs) may contain physiological information related to hereditary cancer susceptibility, but its relationship with future cancer risk remains unclear.Log-Driven Semantic Tuning for Mixed Integer Programming Solvers
Automated configuration of mixed-integer programming (MIP) solvers largely relies on black-box optimization.XLA from the Trenches: Correctness on TPU Workloads at Scale
Accelerating modern foundational models has pushed domain-specific compilers toward increasingly complex, multi-tiered optimization pipelines.From Confounding to Counterfactuals: A Cross-Layer Causal Model for RAN Scheduling
Data-driven control in radio access networks (RANs) selects resource allocations using associations between control actions and key performance indicators (KPIs) learned from network telemetry.Structural Dual Adaptation for Safe Reinforcement Learning
Primal-dual methods enforce safety constraints in reinforcement learning through Lagrangian relaxation.ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics
Electrochemistry is central to solving many modern-day challenges, including energy storage systems for a sustainable future, and its advancement relies heavily on the data from past findings.Bridging Singular Learning Theory and Mechanistic Interpretability at the Billion-Parameter Scale
Mechanistic interpretability (MI) explains a computation in a trained network by identifying the components and variables that implement it and testing them with interventions.Representative Learning for Distributed Support Vector Machines
Distributed support vector machine (SVM) learning is challenging under heterogeneous local data and limited communication.Selecting LLM-Generated Hypotheses Raises Truth Beyond What an LLM Panel Expects: A Pre-registered Study on NAS-Bench-201 and HPOBench
LLM research-ideation systems aim for hypotheses that are both true and non-obvious, yet neither property can normally be checked.Heirloom: Carrying a Phone's Personalization Across Base-Model Generations
On-device language models can learn a user's preferences through adapters trained on private data.Inference First, Training Underneath: Layer-Granular LoRA Co-Serving with LayerLoom
Serving and fine-tuning a large language model on the same GPUs can turn the idle capacity between inference bursts into training progress, and low-rank adaptation (LoRA) makes this co-location…Regularized Wasserstein Distance for Discrete Generative Modeling and Clustering Analysis
In this paper, we formulate clustering analysis as discrete generative modeling.GateTrim: Adaptive-Rank Quantization for Large Language Models
We introduce GateTrim, an adaptive-rank post-training quantization method for large language models that learns matrix-specific ranks through gate optimization and threshold-based rank selection.Audit at the Precision You Deploy: Quantization Reshapes a Subliminally Learned Preference
Subliminal learning allows AI models to inherit hidden preferences from seemingly unrelated training data, such as number sequences.Versatile Graph Foundation Models from Frozen Time-Series Foundation Models via Parallel Flows
Graph foundation models aim to serve unseen graphs across tasks, feature spaces, and label sets.Generative Forecasting from Coarse-Grained Observations: When Does Cascading Help?
We study probabilistic forecasting of dynamical systems such as fluids and waves from coarse observations.Shaped by What's Missing: Topological Invariance Simplification Discovers Behavioral Transitions
Understanding how animals move between behaviors is a central question in neuroethology, yet most segmentation methods first partition time into discrete states, leaving transitions as the unmodeled…ALDER: A Single-Loop Augmented-Lagrangian Damped Extragradient Method for Nonconvex--Concave Minimax Problems with Nonlinear Coupled Constraints
ALDER, a single-loop augmented-Lagrangian damped extragradient method, is proposed for smooth nonconvex--concave minimax problems with nonlinear coupled inequality constraints.Boosted Physics-Informed Neural Networks for Solving Homogeneous and Non-Homogeneous Lane-Emden Type Equations
The Lane-Emden Equation is a class of nonlinear differential equations commonly used to model phenomena in astrophysics and mathematical physics, such as stellar structure and thermal behavior in…