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 136
Towards Adversarially Robust Multigraph Neural Networks for Financial Crime Analysis
Financial transaction networks are naturally represented as multigraphs, where repeated transactions between the same pair of accounts are modeled as distinct edges.End-to-End Differentiable Diffusion Conditioning for Physics-Informed Optimization
Optimizing high-dimensional physical systems under expensive evaluations and complex constraints is a central challenge in science and engineering.Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems
Microservice systems have become a dominant architecture for large-scale cloud applications, enabling rapid deployment and elastic scaling.Operationalising Weaker Faithfulness: Recovery, Ambiguity and Computational Limits
Variables can predict an outcome jointly while each is individually independent of it, causing structure learners to discard informative links.Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control
Effective human-machine teaming requires agents that coordinate with unpredictable human partners.When and How Does Muon Precondition? The Role of Structured Gradient Noise
Muon has become a popular optimizer for large language model training, yet its theoretical foundations remain poorly understood.ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis
Multimodal sentiment analysis (MSA) aims to predict human sentiments by integrating signals from different modalities such as text, video, and audio.Learning to Be Monitored: Causal Bounds and Intervention-Aware Post-Training Recipes for Chain-of-Thought Monitorability
Chain-of-thought (CoT) monitoring aims to detect potentially harmful behaviors in large language models (LLMs) from their CoTs.Efficient Omni-modal Large Language Model Inference via Per-Query Modality Selection
Omni-modal large language models (Omni-LLMs) can jointly process a broad range of modalities, such as text, audio, and video, enabling stronger multimodal understanding and reasoning capabilities…Benchmarks Are Surprisingly Compaction-Friendly
Long horizon agentic tasks are now pushing LLM agents past their context window.Early learning in large residual networks
We study the early training dynamics of nonlinear residual networks with blocks of zero hidden layers as a model of more general residual networks.Not All Retained Clients Are Equal: Client Selection for Federated Unlearning
Federated unlearning (FU) aims to remove a designated target client's influence from a trained model without the prohibitive cost of retraining from scratch.PaperScorer: How Predictable Is Paper Acceptance?
Automated research is largely evaluated by benchmark performance, but the value of research rarely reduces to a single score.CuraLoc: Repository-Level Fault Localization via Planned Code Inspection
A bug report describes what went wrong, but rarely where the code should change.Nested Sparsity for Scalable Pretraining and Continual Learning
Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional computation: only a sparse subset of model weights is used in each forward pass.Speculative Diffusion is a Tale of Two Tradeoffs
Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model.SEVI: Safe Evidential Real-World Reinforcement Learning
Real-world reinforcement learning has enabled contact-rich manipulation tasks to be trained directly on physical robots, but unsafe interactions during online learning remain a key barrier to…Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons
Intelligent agents should learn from their mistakes so that experience leads to continuous improvement.Rethinking Multi-View Fusion for Urban Representation Learning
Urban region representation learning encodes heterogeneous urban signals, such as mobility flows, points of interest, and land-use patterns, into unified embeddings for downstream tasks, including…Cautious Conflict-Free Inverse Gradient Methods
Partial differential equations (PDEs) are indispensable tools for modeling complex phenomena in physics and engineering.