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 238
Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena
Chatbot Arena ranks language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom.Contextual Credit Policy Optimization
Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks.Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments
Learning an individualized treatment rule (ITR) with many treatments requires estimating treatment-specific effects from limited observations per arm.From Copying to Composition: How Language Models Develop In-Context Learning
In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual information controls…Genesis Steering: Better Activation Steering Through Training Data
Activation steering controls large language models at inference time, but its effectiveness depends on the choice of reference data.Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming
Structured pruning reduces LLM inference costs by removing model components to produce smaller dense models.PairIT: Autoregressive Transformers for Low-Data Molecule Optimization
Generating novel molecules with desired properties is a central challenge in drug discovery.Imagining Goals with Geometric Horizon Models for Policy Generalization
Training from offline data has allowed for substantial progress in domains such as robotics, leading to general-purpose policies that can be easily applied zero-shot or efficiently finetuned for…TRACER: Trace-Regularized Training Against Indirect Prompt Injection
Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior.Student Copula Markov Networks
This paper extends the applicability of probabilistic graphical models to non Gaussian data.MA-Bench: Measuring Operational Planning in Language Models
How well can a language model turn a large, incomplete and partly contradictory body of documents into a plan when no single correct answer exists?Online Tokenization with Optimal Delay in Linear Time
Tokenization is an essential preprocessing step in almost all large language models (LLMs).Towards Training and Inference of Graph Neural Networks in Graph Databases
Graph Neural Networks on large graphs commonly rely on in-memory graph storage with ad hoc data processing pipelines for both training and inference.Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?
On-policy distillation (OPD) is increasingly studied as a cheaper alternative to reinforcement learning, yet it remains a form of knowledge distillation (KD) that relies on teacher supervision.Into the Unknown: Benchmarking AI agents on open scientific research problems
Can AI agents carry out research on open scientific problems?Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection
Before deploying clinical prediction models, their reliability must be assessed to ensure safe use.Learning in Strategic Queuing with Geometric Recharge: From Bandits to Systems
We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with unknown service rates.Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent
Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface model reconstruction, but it remains highly nonlinear and ill-posed, especially when the initial model is inaccurate…Adaptive Computation with Conformal Certification
Scientific imaging data involving medical (e.g., 3D radiographic, microscopic images) and astronomical sensors pose different challenges from natural images.FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks
Wildfire decisions are made in hours, yet most learned spread models predict daily on targets including burned area.