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 82
Revisiting Temporal Link Prediction through Structural Proximity
Existing temporal link prediction methods typically rely on learned temporal representations to capture evolving interaction patterns.Does Chain-of-Thought Reliance Follow a Scaling Law?Larger Models Follow Their Steps More, Independent of Post-Training
Monitoring a model's chain of thought (CoT) is useful for safety only if the final answer depends on the written steps.Continual Adaptation Across Modalities: Learning and Forgetting in Unified Multimodal Models
Unified multimodal models (UMMs), which can process and generate diverse modalities within a single framework, have recently emerged as a powerful paradigm.Capacity of the Hopfield-Hebbian dynamics with correlated patterns
Allowing for small fraction of errors in retrieved stored binary patterns, Hopfield-Hebbian neural network (NN) associative memory dynamics [14] achieves linearly scaled capacity.Recurrent Bipartite Graph Neural Networks for QC-MDPC Error Decoding in McEliece Cryptosystems
As the advent of large-scale quantum computing threatens classical encryption, Quasi-Cyclic Moderate Density Parity-Check (QC-MDPC) codes have emerged as a foundational element of Post-Quantum…Beyond Reachability: When Edit Order Preserves Couplings in Graph Flow Matching
Shortest-path optimality does not guarantee that a memoryless graph generator preserves a prescribed source-target correspondence.Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following
Behavior Cloning (BC) of expert controllers for multiscale dynamical systems is challenging: state variables evolving at widely separated timescales induce highly nonlinear couplings that a shared…AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models
Diffusion and flow matching models offer scalable approaches to generating crystalline materials, molecular conformers, and protein-ligand complexes.Value Probes: Learned Value Functions for Beam-Search Red Teaming
Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors.REVBRAIN: Real-time Probabilistic EEG Forecasting Using Residual Vector Quantization
Real-time forecasting of resting-state EEG signals is required by applications like brain-state-dependent stimulation, where computer generated actions are coupled with ongoing neural oscillations.A goodness of fit approach to select the optimal visit sequence for nonparametric data synthesis
Synthetic data are a promising way to maintain privacy while disseminating research data, thereby enabling compliance with the open science principles.Persona Learning from Feedback for Personalized AI Assistants
Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts.Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting
There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics.Dual DeltaNet: Value-Side Memory Reorganization for Linear Attention
Linear attention and state space models (SSMs) offer efficient alternatives to softmax attention by maintaining a fixed-size recurrent state, but this design requires careful management to preserve…Structural Pattern Mining in Inka Khipus: A KFG Re-Analysis
This paper reports a methodological pivot from the Open Khipu Repository to the Khipu Field Guide (KFG) database, prompted by stalled progress on the OKR, and a full re-analysis of the resulting…Robust Active Learning for More Efficient and Reliable Paths to Optimal Design
Simulation-driven design optimization requires active learning strategies that efficiently combine models with different computational costs and levels of fidelity.Rethinking LLM Jailbreak Evaluation: Continuous Risk Landscapes Beyond Binary Outcomes
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where each input is mapped to a single prediction.Two-Stage Clipping: Linear-Time Approximate and Exact Mixed-Norm Projections for Transformers
Large Language Models (LLMs) based on Transformer architectures have achieved remarkable performance across artificial intelligence tasks, but their computational cost remains a major bottleneck.On-Policy Self-Distillation with Teacher Evolution
On-Policy Self-Distillation (OPSD), which aligns a student model's token-level distribution with that of its self-teacher prompted by privileged context, has emerged as a promising direction to…CFKS: Continuum-Feature Kernel PDE Solvers
Neural-network-based PDE solvers require architectural choices, particularly the number of layers and neurons per layer.