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 213
HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation
Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduces where a particular learner succeeds and…MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in completing complex tasks through multi-step reasoning and tool interactions.Enhancing Latent World Models with Associative Memory
World models trained via latent dynamics offer a scalable path for embodied planning, yet existing methods suffer from representational collapse, computational overhead, and limited long-horizon…Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes.Function-Space Temporal Self-Distillation for Policy Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in language models, but scalar outcomes provide coarse supervision over response trajectories.Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics
Gaussian diffusion models offer a practical framework for generative modeling.ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning
Low-rank adaptation (LoRA) enables parameter-efficient fine-tuning by learning low-rank weight updates.New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Multi-session agents can switch between LLMs to balance performance and inference cost.Learning Individual Scientific Taste with Privileged Hindsight Distillation
Scientific taste shapes which research directions researchers pursue, and it varies across individuals.Articulation Upper Bounds for Language Models
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers.TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models
Time-series foundation models provide strong zero-shot forecast, but deployment for real-world applications still requires task-specific designs for model inputs and outputs.What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
Goal misgeneralization is a common failure mode in which an agent behaves competently out of distribution but does not pursue the intended goal.ProtModernBERT: Compute-Efficient Protein Language Modeling
Large protein language models provide a powerful framework for learning sequence-function relationships and guiding experimental design.Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
Discriminative models are trained with task-specific objectives such as classification, detection, or representation learning, yet their practical utility depends on generalizing beyond the training…CAST: History-Adaptive Spectral Clipping for LLM Pretraining
Soft spectral clipping (SSC) reduces gradient singular values, but its effect depends on the gradient scale and clipping threshold.Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection
Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on large-scale training data introduces a critical…Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers
Looped transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with.When Does the Dependency Graph Help Code-to-Architecture Mapping?
Architectural technical debt arises when a system's implementation drifts from its inten ded modular decomposition, while the mapping between source files and architectural modu les is missing…From Global to Tail Convergence: Dynamics of $α$-Stable Score-Based Generative Models
Score-based generative models driven by $α$-stable L{é}vy processes have been proposed as an alternative to Brownian diffusion models, with empirical evidence suggesting improved sampling and better…SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discrete node and edge features.