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 185
Query-Dependent Reading for Quantized Inner-Product Estimation: A Minimax Separation
We study quantization for inner-product estimation when storage and reading have separate budgets.Scalable and Adaptive Distribution Regression via Random Features
Distribution regression seeks to learn mappings from probability distributions to response variables and has emerged as a unifying framework for kernel methods, multi-instance learning, and…LastWords: Boring Problems Revisited
In 2022, the second author published a Last Words piece in Computational Linguistics in which he pointed out that, despite the advances in AI up to that point, there were still some problems in…Distribution-Based Regularization for Reward Fine-Tuning Diffusion and Flow Models
Reward fine-tuning is an effective way to adapt pretrained diffusion and flow-matching models to downstream objectives, but aggressive optimization often leads to mode collapse and distributional…A Symmetry-Matching Approach to Blind-Spot Reduction in Sparse Autoencoders
Language models can treat semantically distinct inputs as interchangeable at the representation level, creating blind spots that standard sparse autoencoder (SAE) objectives do not target.ATLAS: Expert-Guided Sustainable Satellite Backhaul for Off-Grid Wildlife Monitoring
Remote wildlife monitoring increasingly depends on high-fidelity cameras and sensors deployed far from grid power and terrestrial networks.Arctic-SWE: Revisiting the Long Horizon Agent Training by Modeling-System Co-Design
Long-horizon agent training, including software engineering, is advancing rapidly, but the recipe and infrastructure needed for a strong reinforcement-learning baseline remain difficult to reproduce.CARTA: Self-Supervised Reusable Transaction Embeddings via Heterogeneous Tokenization and Cross-Attention
Acquiring fraud labels for payment transactions is expensive and inconsistent across tasks, and high-cardinality identifiers such as merchant names make one-hot feature pipelines infeasible at scale.Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objectives, and to personalize their behavior to…CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning
Treatment planning is intrinsically counterfactual: clinicians must compare how a patient's tumor and survival would evolve under competing regimens, whereas a retrospective cohort records only the…ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation
Sanskrit verse recitation is governed by $\textit{Chandas}$, a strict prosodic framework defined by rhythmic $\textit{Laghu}$ (light) and $\textit{Guru}$ (heavy) syllables.Expert-Guided Rubrics as Dense Reward Signals for Reinforcement Learning in Non-Verifiable Domains
Large language models (LLMs) are increasingly deployed as autonomous agents in non-verifiable domains such as financial services, where they must interpret user intent, rewrite queries, and retrieve…Shape-Aware Neural Time Fields for Rigid-Body Motion and Manipulation Planning
Rigid-body motion planning is fundamental to robotic transport and manipulation, where both object position and orientation determine whether a body can move through cluttered environments.Acquisition Function-Guided Generation for Bayesian Optimization over Discrete Spaces
Bayesian optimization (BO) over discrete spaces is challenging due to missing gradients and the sparsity of valid solutions.One Communicator, Three Vendors: Extending the MoA Predictive Theory to a Real NVIDIA+AMD+CPU MPI Ensemble
The companion MPI-extension paper validated the first communication-bearing machine-shape ensemble: four NVIDIA A100 ranks and four CPU ranks on one NCSA Delta node under one Open MPI job…Unit-level aggregation breaks coverage in causal foundation models
Causal foundation models (CFMs) show promising results for treatment-effect estimation, with unit-level estimates that are competitive on standard benchmarks.Reusing Calibration Gains across Model Representations
Scale calibration learns an update for one model representation.Anytime Contracts for AI Services
AI services are prone to moral hazard, as model providers can silently route requests to cheaper, lower-quality models, and the inherent stochasticity of model outputs makes this degradation hard to…Next Token or Vector? Learning How Far to Decode
Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together.Ori: Drift-Aware Streaming $k$-PCA for Very Low-Rank LLM Training
A prominent family of low-rank LLM optimizers, pioneered by GaLore, performs gradient-subspace projection: at each step, they project the gradient into a low-dimensional subspace and map the update…