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 210
Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering
A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those regions, so a gate-versus-random comparison does…Target-Token Asymmetry Can Masquerade As Depth Specialization
Layer-ablation studies often perturb early or late layers of a language model, compare the damage to prediction on two corpora, and read a larger early-layer effect on one corpus as early-layer…Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision
Novelty detection is crucial in various technological and scientific domains.Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents
Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards.BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments
Clinical assessments are often collected using heterogeneous assessment systems across centers and time, leading to records that mix different but related sets of measurements.Asymptotic Behavior of Transformers
In this paper we study the behavior of transformer networks generating text over long periods of time.Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering
Activation steering adds a vector to a model's hidden states to control a named behaviour.Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
Best-of-N sampling is a simple inference-time scaling strategy for large language models, yet its behavior under incomplete reward models remains poorly understood.Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context
Dynamic graph learning models how entities and their relations evolve from historical observations to predict future graph states.The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking
Pedestrian tracking in video is important for applications such as surveillance and scene analysis, but it becomes more challenging in crowded scenarios with frequent occlusions and rapid motion.Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward.One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models
Latent world models are routinely selected, checkpointed and ablated on one-step prediction loss, on the assumption that a model which predicts the next latent better is a better model.Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning
We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism for identifying and exploiting additional information, particularly under…RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
Large Language Model (LLM) unlearning is often evaluated primarily by target suppression and clean retain utility.Fully sequential Gaussian process regression for preference learning
We study continuous global optimization problems in which the objective function cannot be directly evaluated; rather, we observe only which of two selected design points appears to perform better…Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel
Next-location prediction can support proactive mobile-network decisions, but acting on unreliable predictions can waste resources.Train to Stitch: Topology-Preserving Regularization for Interoperable Representations
As large, powerful pre-trained models become more prevalent, there is growing interest in developing methods that allow different neural networks to be seamlessly combined with little or no direct…ActMOF: Mapping Reticular Synthesis through Active Learning
Reticular chemistry allows metal-organic frameworks (MOFs) to be designed from their building units, yet their synthesis remains constrained by sparse experimental data, noisy crystallization…Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off
Large Language Model (LLM) serving systems must balance latency and throughput while efficiently utilizing distributed GPU resources.W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition
A major challenge in wearable device activity recognition is the heterogeneity across datasets in sensor placement, channel count, sampling rate and subjects.