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 129
Federated Graph Retrieval-Augmented Generation
Graph Retrieval-Augmented Generation (GraphRAG) leverages centralized knowledge graphs to enhance large language models with structured knowledge retrieval.Width and Depth Limits Commute During Training in Linear Residual Networks
Recent work established that the infinite-width and infinite-depth limits of residual networks commute at initialization when residual branches are scaled by $1/\sqrt{depth}$.Random Remasking Scales Masked Diffusion Inference
Masked diffusion models (MDMs) generate sequences by progressively unmasking tokens, but errors introduced during decoding are typically irreversible.Wavenumber-Aware Deep Learning for Robust Analysis of Raman Spectra
Machine-learning models for spectroscopy usually treat a spectrum as a fixed-grid intensity vector, leaving the physical coordinate implicit in the array index.Visualizing and Interpreting Temporal Care Team Dynamics for Cancer Survival Risk Analysis
Cancer care is a longitudinal, time-sensitive process requiring coordination among diverse healthcare professionals (HCPs), whose collaboration evolves throughout treatment.Primal-Dual Representation Learning for Low-Rank Constrained MDPs
Representation learning has substantially improved the efficiency of unconstrained continuous-state Markov Decision Processes (MDPs), but its extension to Constrained MDPs (CMDPs) is difficult…Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks
Content caching via unmanned aerial vehicles (UAVs) becomes one of the solutions to maintain content delivery when terrestrial infrastructure is unavailable or disrupted.One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection
Graph anomaly detection (GAD) aims to identify irregular entities in graph-structured data, yet heterogeneous anomaly patterns and distributional differences across graphs challenge generalizable…Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving
KV caching reduces the serving cost of large language models (LLMs), but the growing KV cache footprint is increasingly exceeds GPU and host-memory capacity.Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training
Scaling GUI reinforcement learning requires environments that preserve real-app behavior.GIFT: Gradient Informed Filtering for Distillation Augmented Reasoning RL
Training large language models for complex reasoning tasks relies on two complementary signals: sparse, outcome-grounded reinforcement learning (RL) for correctness, and dense, token-level…Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JIT) compilation frameworks such as Triton.A Computationally Efficient and Rate-Optimal Algorithm for Adversarial Linear MDPs with (Aggregate) Bandit Feedback
We study episodic linear Markov decision processes with unknown transitions, adversarial losses, and bandit feedback.Is spectral predictability enough? Testing Ω-matching for synthetic pretraining under distribution shift
Synthetic pretraining under distribution shift requires deciding what synthetic data to use.What Lies Beyond Perception: A Partition Theory of the Limits of AI Evaluation and Oversight
Replacing the judge can move a benchmark score, and models can be trained to hide capabilities.xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs
Graphs play a crucial role in many applications, ranging from drug discovery to social network modeling and astronomy.Neural Spectral Capacity with Residual Context for Heterogeneous Resource Allocation within Transformers
Predicting relative trained performance from architectural specifications can guide design when training costs limit experimentation.Semi-Linear Gaussian Bayesian Networks: Enhancing Flexibility in Node Dependencies via penalized B-Splines
Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-parametric approaches provide…Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries
We introduce Lean Finder V2, a semantic search framework for Mathlib that disambiguates user queries through complementary model-level adversarial training and input-level query rewriting.Reverse-KL Policy Distillation: Statistical Guarantees and Limits
Reverse Kullback-Leibler (KL) distillation has shown empirical promise for training language models, but its statistical guarantees and limits remain poorly understood.