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 165
TempoMoE: Identifying and Steering Fast-Slow Thinking Experts for Efficient Multimodal Reasoning
Multimodal Mixture-of-Experts (MoE) reasoning models rely on long chain-of-thought (CoT) for complex tasks, yet often overthink easy inputs, increasing token cost and latency, and sometimes…PnP-CF: A Consensus Flow-Matching Solver for General Inverse Problems
Plug-and-Play (PnP) methods using continuous-time deep generative models as learned data distribution priors enable synthesizing high-quality solutions of model-based inverse problems.SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code
Code generated by large language models often passes every functional test while remaining insecure.Scenario Generalization and Sector Transfer in Real Surface Irrigation Surrogate Modelling with Tabular Models
Surface irrigation planning requires screening many operating conditions and spatial configurations, while high-fidelity shallow-water-equation (SWE) simulations are expensive.ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
Performing accurate protein-glycan docking is critical to understanding protein-glycan interactions which govern many biological processes.Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
We study regret minimization in finite-horizon episodic Markov Decision Processes (MDPs).Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation
Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters.FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
Financial agents are expected to answer factual investment queries through open search, but financial multi-hop retrieval differs from general multi-hop QA in a crucial way: each intermediate answer…LeakBench: Auditing Reward Hacking through Prediction-Time Leakage in Clinical Modeling Agents
Autonomous clinical-modeling agents can optimize predictive performance while violating conditions that make a model usable.Multilingual Voicemail and Answering Machine Detection via Pretrained Audio Embeddings and Gradient Boosting Machines
Answering machine detection (AMD) is a fundamental task in telephony that classifies whether an answered call is picked up by a human or a voicemail (machine).Provable Adversarial Detection: Prime Quantization meets Gromov--Wasserstein
Adversarial vulnerability persists across modern vision architectures from CNNs to vision language models (VLMs), yet existing detection methods rely on heuristics without theoretical guarantees.Learning from a Bandit Learner
Classical inverse bandit methods typically aim to recover true reward parameters.Declarative Explanations for Graph Neural Networks: A Demonstration
Graph Neural Networks (GNNs) have proven effective for graph analytical tasks, yet their "black-box" nature complicates the understanding of their layer-wise behavior and hinders their application…From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for Classification
Time series foundation models (TSFMs) have achieved notable progress in classification tasks through large-scale pretraining.Variance-Aware Non-Stationary Bandits:All-Budget Regret Bounds and Adaptation Costs
Low reward variance reduces estimation cost, but does not eliminate monitoring of arms that may improve while unobserved.Optimal Multi-Kernel Combination for Online Multi-Label Classification
Multi-label classification is particularly challenging in streaming scenarios, where data arrives sequentially.Nash-MOPD: Optimizing Task Trade-offs in Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) aggregates the capabilities of multiple domain-expert teachers into a single student model.Reinforcement Learning Controllers for Fusion Scenario Development
Scenario development, the design of the waveforms that take a tokamak discharge from breakdown to flat-top, is still an iterative, labour-intensive process.FLMNet: Self-Ensemble Distillation from Masks to Seeds for Single-Tower CTR Prediction
Click-through rate (CTR) prediction underpins recommender systems and online advertising, where high-dimensional categorical features interact in combinatorially many ways.Physics-Driven Framework for QoS-Constrained Satellite System with Non-Linear PA Distortion
This work develops a physics-driven self-supervised graph learning framework that directly optimizes the distortion-aware precoder under nonlinear correlated power amplifier (PA) distortion, without…