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 78
Fair Recommender Systems for Intersecting Groups
Recommendation systems that optimize for the average user can fail to capture the preferences of diverse demographic groups.Benchmarking Forecasting Agents on Yesterday's Tomorrows
Digital agents can now gather and organize information, reason over it, and use tools to complete complex tasks.Kernel-based Interpolatory Methods for Context Compression of Attention Mechanisms
The bottleneck of attention mechanisms, which are the fundamental building block of modern language models, is their quadratic complexity in terms of context size.On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning
On-policy reinforcement learning for large language models assumes that training responses are sampled from the current policy.Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
Chain-of-thought (CoT) reasoning allows large language models (LLMs) to generate intermediate reasoning traces in natural language while solving complex tasks.CAMEL: Cross-Architecture Masked Embedding Learning for Ultra-Lightweight Retinal Foundation Models
Recent progress in deep learning has substantially advanced automated grading of ophthalmologic pathologies, supported by large annotated datasets and improved representation learning.Monte Carlo Random Walk Kernel
We introduce the Monte Carlo Random Walk Kernel (MCRWK), an estimator whose per-pair cost is independent of graph size and derived directly from the random walk kernel (RWK) expansion.Fewer Heads, Fewer Memories: Pruning Redundant Attention Heads Suppresses Verbatim Memorisation
Large language models have been shown to memorise and reproduce verbatim sequences from their training data, raising concerns about privacy leakage, intellectual property exposure, and the limits of…RC Prediction: A Python Package for Parameter-Aware Reservoir Computing
A nonlinear dynamical system can be characterized by the autonomous evolution of its state in time and its dependence on system parameters.Can Personal Requirements Become Supervision for Planning?
Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving established eating habits.Steering Vectors as a Training Signal in LLM Post-Training
Steering vectors (SVs) are residual-stream directions that shift the behavior of LLMs when added to hidden states at inference time.When Can Unlabeled Data Pools Replace Membership Queries?
Membership queries let a learner label arbitrary points and give near-optimal $\tilde O(n\log(1/\eps))$ label complexity for halfspaces under every marginal.MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing
In multi-task settings, combining multiple modalities allows task representations to draw on signals that a single modality alone would not capture.Towards Understanding Score-Seeking in LLMs
Production large language models sometimes reward-hack, exploiting flaws in how tasks are scored rather than performing the tasks as intended, sometimes in highly sophisticated and adversarial ways.Do Language Models Know What Compelling Scientific Evidence Looks Like?
Expert scientists excel at weighing empirical findings from multiple sources that vary in both statistical reliability and epistemic relevance.Density-Guided Bootstrap Boundaries for Latent World-Model Reinforcement Learning
Latent world models allow reinforcement learning agents to learn policies from imagined trajectories, yet determining the optimal depth of model reliance remains a fundamental challenge.Omniprediction for All Mixable Proper Losses and Beyond
Omniprediction concerns the task of making predictions that are simultaneously accurate with respect to different losses.When can Optimally Trained Transformers Achieve Near-Lossless Token Prediction for non-Markovian Data?
There exists little mathematical theory explaining why Transformer architectures are empirically successful even for non-Markovian data.Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs
As Mixture-of-Experts (MoE) large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored…Before We Adapt: The Zero-Shot Generalization Bottleneck in Continual World Models
Continual reinforcement learning (CRL) requires agents to operate under environmental changes while reusing prior knowledge whenever possible.