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 243
QBFF: Deep Quantum Bottleneck for Automatic Speaker Verification Anti-Spoofing
A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining executable on real hardware.RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning
Multi-step retrosynthesis planning is often considered solved once a route to purchasable starting materials is found, but such a route should also be practical in real-world chemistry.Sampling from Neural Operator Priors to Solve Partial Differential Equations
Guided sampling with sparse observations and PDE residuals has recently been combined with neural operator priors to solve partial differential equations in function space, their natural setting.Learning $ω$-Powered Conditional Distributions with Importance-Weighted Flow Matching
Classifier-Free Guidance (CFG) with guidance scale $γ$ is commonly motivated by the $ω$-powered conditional distribution obtained by setting $ω=γ$, but CFG does not, in general, sample from this…Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning
Recursive reasoning models such as the Tiny Recursive Model (TRM) iteratively refine two latent states: an answer state y, decoded into the output, and a reasoning state z, which is never decoded.Taming Nonconvexity with Epigraph Lifting
We consider inverse problems regularized by a trained neural network with \emph{convex activations} and \emph{unrestricted weights}.ECHO: Correcting Time Series Foundation Model Forecasts with Historical Analogues and Errors
Time Series Foundation Models (TSFMs) provide general-purpose forecasting capabilities, yet their forecasts can remain misaligned with the temporal characteristics of a target domain.ARMED: Adaptive Retrieval-Augmented Medication Recommendation
Medication recommendation requires jointly considering diagnoses, comorbidities, longitudinal patient history, and treatment interactions.Explaining Heterogeneous Treatment Effects with Causal Forests and the Hoeffding Functional Decomposition
The estimation of heterogeneous treatment effects is a central objective of causal inference.CryptoFlowBench: Benchmarking Multi-Hop Reasoning on Blockchains for Cryptocurrency Fund Tracing
Pseudonymous accounts and complex smart-contract ecosystems substantially hinder the tracing of illicit cryptocurrency fund flows.StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning
Fine-tuning large language models at scale is increasingly limited by the memory cost of backpropagation.A temporal graph dissimilarity measure capturing epidemic spreading behavior
Comparing temporal networks is a challenging problem in network analysis.Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about political beliefs…Online Individualized Treatment Selection under Partial Feedback: False Discovery Control and Minimax Optimality
We study online individualized treatment selection when only the outcome under the assigned treatment is observed.SLEM: Spectrum-Aware Latent Expert Merging
Mixture-of-Experts (MoE) models scale model capacity efficiently by activating only a small subset of experts for each input, while still requiring all parameters to be stored in memory, resulting…Growing and Transferring Pathways for LLM Reinforcement Learning
Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources.Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems
Improving an agent through successive revisions requires balancing exploration and evaluation under a limited budget.KARAMEL: Knowledge-Aware Ranking for Multimodal Entity Linking in the Arts via Heterogeneous Graphs
Discovering and disambiguating entities from multimodal and heterogeneous data is a key challenge in discovery science, where relevant knowledge is often implicit and distributed across modalities.pi-Net: Empirical Latent Representations for Differentiable Physics Heads in Data-Scarce Systems
Developing reliable predictive models for multi-physics systems often forces a compromise between computationally demanding physical simulators and data-hungry, opaque machine learning (ML)…Trust-Calibrated VLA Policy Post-Training with Evolving Imagination
Vision-Language-Action (VLA) models are often pretrained via imitation learning, making reinforcement learning (RL) post-training important when deployment moves beyond demonstration coverage.