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 16
Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation
Dexterous robotic hands are increasingly coupled to large-scale human data and foundation models, yet progress in hardware, representation learning and evaluation is often assessed separately.Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
Streaming video understanding requires models to repeatedly decide whether to respond or continue observing.Template Gap Reconstruction for Shell Output Simulation with Small Language Models
Small language models offer a compact basis for shell simulation without executing submitted commands, but full-output decoding requires them to predict recurring utility structure alongside content…ConceptARC at Scale: Studying Conceptual Understanding in Reasoning Models
Large reasoning models (LRMs) perform well on challenging benchmarks, yet it remains unclear whether they form generalizable abstractions across conceptually related reasoning tasks.Coupled Scene Graph Anticipation: When With-Constraint Recall Hides Structural Inconsistency
Scene Graph Anticipation (SGA) predicts object relationships in future video frames.Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks
We study logistic regression for continual learning with linear predictors in a high-dimensional statistical setting.FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
One-shot and few-round federated learning (FL) reduce communication burden by constructing a global model within one or a few communication rounds, but often achieve lower performance than…Ranking Agreement Does Not Reveal Paragraph-Edit Agreement in Two Released Paper Acceptance Predictors
A fast acceptance classifier could select revisions for a slower evaluator.Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3
Sample-efficient fluid intelligence requires agents that rapidly form working models of unfamiliar interactive environments.Message-passing graph persistence
Message-passing graph neural networks (GNNs) are limited in expressive power by the one-dimensional Weisfeiler-Leman test.ConDR: Conservative Reachability through Neural Hamilton-Jacobi Subsolutions
Hamilton-Jacobi (HJ) Reachability identifies the unsafe states of a dynamical system from which it can be forced into failure under worst-case disturbance.Evolutionary Design of Interpretable Spatial Descriptors for Structure-Property Relationship Discovery
Structure property prediction is a classical task in machine learning, ranging from molecular activity and materials properties to local functional responses measured in microscopy.GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes
Choosing a quantum error-correcting code for a real device means scoring candidates with circuit-level simulations so slow that only a few hundred can be run.Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs
Gated-delta linear attention layers such as Gated DeltaNet (GDN), Kimi Delta Attention (KDA), and GDN-2 are tuned for GPUs, where small tensor-core tiles and fast vector registers make per-channel…Enabling AWS Cloud FPGA Development Using High-Level Vitis HLS
We present a toolchain for development of ML models on AWS EC2 F2 cloud FPGA infrastructure from high-level language, implementing a complete Vitis HLS to HDK bridge to AFI workflow that has been…Alignment Myopia in Generative AI
Current generative AI alignment relies on a myopic paradigm that prioritizes immediate conversational satisfaction.Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Under stochastic decoding, a single context can elicit many different answers from a language model.Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models
Ask SD3.5-Medium for twelve of an object and then, from the same starting noise, for twenty-five.Thermally Conditioned Time-Series Forecasting of Grain Growth in Polycrystalline Materials
Grain growth during heat treatment strongly affects the microstructure of polycrystalline materials and, consequently, their mechanical properties.Navigating Disagreement Among Criteria for Evaluating Explanation Faithfulness
Faithfulness requires that algorithmic explanations accurately reflect the model's behavior.