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 41
FADE: Factored Ability--Difficulty Filtering for Online RLVR Scheduling
Group-based reinforcement learning with verifiable rewards (RLVR) learns only from prompts whose sampled completions disagree: all-pass and all-fail groups produce zero relative advantage and burn…Not All Reasoning Generalizes: A Case Study on Learning Generalizable Reasoning Strategies in RLVR
Reinforcement learning with verifiable rewards (RLVR) can enable generalizable improvement for large language model (LLM) reasoning.Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap
Muon has recently emerged as a promising optimizer for pretraining large language models, offering a speedup over AdamW in minimizing pretraining loss.WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training.Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations
Sensorized human demonstrations offer scalable data for mobile manipulation, but embodiment differences complicate policy learning.Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation
General-purpose mobile manipulation requires a combination of capable robot hardware, scalable demonstration collection, expressive whole-body control, and effective policy learning.CaRe-KT: Continuity-Aware Retrieval-Augmented Reasoning for Knowledge Tracing
Knowledge tracing (KT) estimates learners' evolving knowledge states from interaction histories to support adaptive learning.Honest Small Decision Models for Finance: Scale, Specialization Collapse, and Mixed-Corpus Remediation
Financial workflows need fast, calibrated, auditable decisions, not just generated text.Language Models Can Benefit from Domain-Specific Inductive Biases
Language models are typically trained with a single choice of architecture on diverse domains and data sources.The role of injected noise in diffusion model generalization
Diffusion models trained on distinct datasets can produce highly similar samples when prompted with the same noise input, suggesting that they learn a generalized data distribution.Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction
As general-purpose Large Language Models (LLMs), such as Gemini and DeepSeek, exhibit increasingly advanced reasoning capabilities, a critical question arises: how do their property prediction…Multi-layer Indexer: Overlapping Selection and Attention in DeepSeek Sparse Attention
Sparse attention cuts the cost of long-context inference by making the attention matrix sparse: each query attends only a subset of the sequence, chosen by a fixed pattern or, in recent production…What Malware Actually Does: An Empirical Analysis of Post-Infection Behavior Across Malware Families
Most malware detection research focuses on identifying whether a file is malicious before it executes.3D dark matter map of the JWST COSMOS-Web field using diffusion-based generative priors
Mapping the three-dimensional distribution of dark matter is key to tracing the growth of cosmic structure.BEND 2.0: Benchmarking the Capabilities Needed to Design DNA
Genomic foundation models are increasingly used to propose DNA sequences and edits.AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data
AIRoA-0 (A-0) is a bimanual manipulation system learned from 16,151 hours of handheld demonstrations, with no robot data collected at any stage.PianoBench: Evaluating Musical Perception and Reasoning in Language Models
Multimodal language models continue to improve on broad music understanding benchmarks, but which musical features can they perceive and reason about?Probabilistic Steering of Generative Priors for Lab-in-the-Loop Antibody Optimization
Therapeutic antibody development is often framed as comprising two discrete stages: initial discovery of novel binders followed by iterative optimization to refine these hits into therapeutic-grade…LaplaceDiag: Fault Diagnosis through Changes in Learned Actuator Effects
Identifying faulty components from sensor anomalies is difficult because fault effects can propagate through a plant and different faults can produce similar observations.Predictive gains, causal losses: why interventional competence cannot be learned from data alone
Retaining predictive gains can require persistent errors in a model's response to interventions.