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 3
Using Transformers to Generate 3-Manifold Triangulations
Using dehydration signatures as an encoding, we train GPT-2-style transformers to generate triangulations of 3-dimensional manifolds.Understanding Data Influence in Transportation Networks: A Physics-Constrained Influence-Function Framework
Understanding how individual training observations influence model predictions is important for developing reliable and interpretable data-driven transportation systems.The Memory Trap: Language Agents Overgeneralize from Benign Interactions
Language agents increasingly use persistent memory to record user preferences and procedures across sessions.Provable Zeroth-Order Safe Exploration for Reinforcement Learning from Human Feedback
Safe reinforcement learning from human feedback (Safe-RLHF) seeks to improve helpfulness while satisfying harmlessness constraints.MambaTG: Candidate-Aware State Space Modeling for Future Link Prediction on Temporal Graphs
Future link prediction on temporal graphs involves both repeated interactions between previously connected node pairs and first-time interactions between pairs with no prior interaction.ACSeL: Adaptive Configuration Search for Hardware-Constrained LLM Inference
Serving large language models (LLMs) under tight memory and latency service-level objectives (SLOs), including on edge devices, requires jointly selecting the model size, batch size, quantization…Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
As LLM agents advance rapidly in autonomy, the risk of hidden objectives that bypass safety constraints becomes increasingly plausible.Learning and Steering in Incomplete-Information Games
In many modern multi-agent systems, a mediator seeks to influence strategic decision dynamics using only outcome-level feedback and without knowing agents' utilities.TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs
Vision-language models (VLMs) applied to 3D medical scans face a structural memory wall.Binding Paraphrased Instructions to Encountered Objects in sLLM Agents under Partial Observability
Reliable deployment of LLM agents requires grounding diverse user expressions in their environments.Embedding-Space Fingerprinting of LoRA Fine-Tunes: Recovering the Training-Data Domain from the Model Artifact Alone
When a base language model is fine-tuned with Low-Rank Adaptation (LoRA), how much of the training data domain leaks into the resulting artifact?Monotone Viability Learning for Offline Safe Reinforcement Learning
Offline safe reinforcement learning requires reliable long-horizon safety estimates from fixed data.Online Learning with Ordered Experts (via Two-point Feedback)
We study adversarial online learning with expert recommendations in a totally ordered action space, where the experts' recommendations may change and be reordered arbitrarily.Measuring the Marginal Value of Verifier-Based RL Beyond Supervised Fine-Tuning
Reinforcement learning from verifiable rewards (RLVR) is usually evaluated as an alternative to supervised fine-tuning (SFT), or as a stage that follows it, with the implicit assumption that the RL…WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning
Neural operators offer fast surrogates for solving PDEs, but training them typically requires expensive input-solution pairs.English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models
Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant.Simple Meta-Learning for HPO and CASH Using Performance Representations
Bayesian optimization for Hyperparameter Optimization (HPO) and Combined Algorithm Selection and Hyperparameter Optimization (CASH) often relies on explicit hyperparameter encodings as surrogate…Extracting Single-Mode Rayleigh--Taylor Instability dynamics from data via SINDy
Rayleigh-Taylor instability (RTI) is of fundamental importance in fields such as inertial confinement fusion and supernova explosions, and its evolution is commonly described by potential--flow…An Information Bottleneck for Post-hoc Memorization Mitigation in LLMs
Recent studies have shown that large language models (LLMs) can memorize and reproduce copyrighted training data, raising serious privacy and intellectual property concerns.Calibrated Target Noise Recovers Curvature from the Gradients
Estimating curvature information from gradients alone is a fundamental problem in machine learning.