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 51
Hinted Scaling Laws
Scaling laws predict the outcome of large, expensive training runs by extrapolating trends from smaller, cheaper runs.Invertible Graph Aggregation Can Increase ReLU Readout Width
An invertible graph aggregation preserves the complete feature table, but can increase the size of a classifier that reads one node at a time.Atom-Wise Allocation of Message-Passing Scale for Molecular Property Prediction
Molecular properties depend on chemical structure at different ranges, from local polar groups governing solvation to extended substructures shaping bioactivity, yet graph neural networks usually…Concise-9B: Removing the Slack from a Reasoning Model's Thinking
Reasoning models answer better when they think longer, but a thinking trace keeps going well after its answer has formed.FactorSpec: Serving Exact Relational Constraints as Speculative Drafts
Speculative decoding speeds up LLM serving by drafting tokens that the target model verifies in one pass, and its gain grows with the drafts the target accepts.Lie Routing Vision Language Models for View-Robust 3D Understanding
Multimodal Large Language Models (MLLMs) have made substantial progress in 3D scene understanding from multi-view RGB observations.EMBERS: Empirically Motivated Robustness Testing of Deep Research Systems via Defect-Guided Fuzzing
Deep Research (DR) systems extend large language models into autonomous agents that decompose complex information needs, iteratively search the web, and synthesize evidence to answer challenging…Does the Trust Boundary Hold over Time? A Long-Horizon Benchmark for Receiver-Directed Federated Learning
In receiver-directed federated learning, each site draws a trust boundary.DualClusterNet: Personalized Pattern-Space Composition for Next-POI Recommendation
Next point-of-interest (POI) recommendation supports personalized place discovery on location-based Web platforms.Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench
Benchmarks built from model hubs combine interaction data, knowledge graphs (KGs) and resource documentation, but valid files do not ensure that these artifacts describe the same objects.Complete Donor-Set Guidance for Frozen Diffusion Docking Models
Metalloprotein docking requires a ligand pose to satisfy both global pocket fit and the identity and geometry of metal-coordinating atoms.Minimal Superior Penalties: Characterising and Calibrating Decision-Aware Proper Scoring Rules
Training a classifier means letting a validation metric decide which model is kept and when training stops.HyVox: Rethinking Low-Power Voice Intelligence towards Neuromorphic-von Neumann Edge Computing
We present HyVox, a hybrid neuromorphic--von Neumann system for low-energy open-set speaker identification under tight energy budgets.SSPE: Robust Sequential Staypoint Extraction in Degraded Trajectory Data
Extracting semantically meaningful staypoints from raw trajectory streams is a foundational prerequisite for mobility analytics.RATSIFT: Resolution-Adaptive Transformer for Solar Irradiance Forecasting and Temporal Downscaling
Accurate forecasting and temporal downscaling of solar irradiance is critical for reliable renewable energy integration and grid management.BIOTRAM: Biochemistry-informed Transformer for Relative Abundance via Metabarcoding
Arthropod monitoring at scale begins with metabarcoding of bulk samples: trap collections of hundreds to thousands of specimens processed as one unit, extraction of DNA from the bulked specimens…Ensemble Classification and Cancer-Specific Gene Signatures from Quality-Aware Hybrid Gene Selection in TCGA RNA-Seq data
Gene-expression classifiers of cancer type are usually developed and validated within one cohort using random splits.Where Causal Discovery Breaks on Real Data: Measuring the Assumptions One Property at a Time
Causal discovery is usually evaluated on simulators or on systems whose ground truth follows from physics or design.Integer-Exact Microscaling: Running MXFP4 Language Models on INT8 Matrix Units
On hardware whose fastest matrix datapath is INT8$\times$INT8, such as the Neural Accelerators of Apple's M5 GPUs, 4-bit weights must become INT8 operands.VoirDire: Counterfactual Calibration for Reliable LLM-as-a-Judge Aggregation
LLM-as-a-judge systems often aggregate multiple judges to improve evaluation reliability.