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 60
SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences
Learning-based approaches have increasingly been explored for SAT solving, with particular attention to improving branching decisions in conflict-driven clause learning (CDCL) solvers.In-Model Context Compression with Agentic Soft Tokens for Long-Horizon LLM Agents
Long-horizon LLM agents play an important role in solving complex and sustained tasks, with ever-growing interaction contexts.rl_rob: A transparent, from-scratch Python library for teaching reinforcement learning from tabular methods to deep policy gradients
rl_rob is an open-source Python library for teaching reinforcement learning.Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching
Generating small molecules to target protein-protein interactions (PPIs) remains one of the most challenging yet high-reward frontiers in drug discovery.StrictPRMBench: A Replayable Evaluation Benchmark for Auditing Fixed-Score PRM Aggregation
Process reward models (PRMs) score reasoning steps, but best-of-N selection also requires a rule that aggregates those scores.Operon-S1: a fast decision controller for long-horizon biomedical agents
Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reasoning that does the work…Quantile Propagation Planning for Budgeted Tail-Risk Evaluation
Risk-aware planning must identify rare, costly outcomes using only a limited number of model evaluations.Generated storm lifecycles fill the rare-event tail of short rainfall records
Historically rare ''one-in-a-generation'' storms are occurring with unprecedented frequency, causing catastrophic damage and mounting casualties, and exposing the vulnerability of infrastructure…What We Keep of What We Forget: Replacement Operators and Routing Semantics in Training-Free MoE Expert Pruning
Training-free expert pruning makes two decisions: which experts to remove, and what the layer computes when its router still selects a removed expert.From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings
Choosing among the hundreds of thousands of available large language models (LLMs) requires a thorough understanding of each candidate model's properties.Riemannian Optimization on Unknown Manifolds via Stochastic Proximal Refinement
We study Riemannian optimization on an unknown manifold accessed only through feasible samples.Anomalies as Residuals: Cauchy Displacement Networks
Neighbourhood-based detectors such as KNN, LOF and LUNAR remain among the most accurate methods for tabular anomaly detection, but they compare every query with the stored training set, so their…DUGO: Dual-Scale Gaussian Memory for Online Temporal Action Localization in Egocentric Procedural Videos
Online Temporal Action Localization (OnTAL) aims to detect and localize action instances from untrimmed streaming videos in real time.Conditional Neural SDEs for Financial Time-Series Generation
Conditional generation of time-series paths is a central problem in probabilistic modeling, where the goal is to simulate future trajectories that are both realistic and responsive to external…SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models
Vision-Language-Action (VLA) models enable capable robot behavior, but their large memory footprint limits deployment on resource-constrained robotic platforms.Certifying Retraining Regret through Residual Structure
We certify a fixed ridge predictor's regret against full-feature retraining over every continuous completion of an interval-valued table.SparseGDN: Chunk Sparse in Linear Attention
Gated Delta Networks (GDNs) offer linear-time sequence modeling, yet long-context prefill remains costly due to dense intra-chunk computation, recurrent-state updates, and intermediate state storage.A Unified XAI-NSAI Analytical Framework for Trustworthy IoT Anomaly Detection
The widespread deployment of Internet of Things (IoT) devices in critical environments makes anomaly detection essential for identifying abnormal behaviors and supporting timely investigation and…A prospective randomized study of patient-centered AI for clinical visit preparation
Patients often arrive at brief, time-constrained clinical visits unsure of what to expect or ask, and millions of adults now turn to general-purpose AI chatbots to prepare beforehand.From Representation to Readout: Mechanistic Analysis of Membership Signals in Language Models
Membership inference aims to determine whether a particular example was included in a model's training data.