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 111
Entropic Control for Homeostatic Optimization: Pre-empting Catastrophic Forgetting via Dynamic Feedback
Supervised Fine-Tuning (SFT) of LLMs suffers from catastrophic forgetting, and prevailing mitigation strategies struggle to reconcile the plasticity-stability dilemma.AudioFM: Towards General Purpose Audio Representation Learning
Learning audio representations that effectively bridge holistic global soundscapes with fine-grained acoustic moments is a long-standing goal in self-supervised learning.SRA: Selective Residual Adaptation for LLM Reasoning Enhancement
Knowledge distillation transfers reasoning capabilities from large language models to lightweight students.CORMA: Constraint-Routed Decision Mamba for Generalizable Multi-Constraint Offline Safe Reinforcement Learning
Offline safe reinforcement learning (RL) learns safety-aware policies from static datasets while satisfying safety constraints during deployment.Interpretable and Steerable Molecular Graph Generation using Concept Bottlenecks
Deep graph generators (DGGs) largely lack interpretability, which is a significant limitation for one of their most crucial applications, drug discovery, where interpretable and transparent…$Δτ$-Bench: Pushing Agents Toward a Moving Capability
In this paper, we introduce $Δτ$-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems.Alignment via Generalization
AI systems can become better at achieving the goals we give them without becoming better at doing what we actually want.Does Notation Matter? MusicXML Tokenisation for Symbolic Music Generation and Understanding
Symbolic music representations encode musical content at varying levels of completeness, from performance-oriented formats such as MIDI to fully notated scores such as MusicXML.Recovering Business Rules as Cascade Lookups for Enterprise Field Prediction
Enterprise sales-order systems rely on manually maintained configuration rules to determine fields such as payment terms, shipping points, and sales ownership.DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training
Multi-task post-training can develop domain specialists through independent reinforcement learning (RL) and consolidate their capabilities through multi-teacher on-policy distillation (MOPD).Transformer to GPT-5: Advancements, Limitations, and Future Directions in Large Language Model Design
Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) by their extraordinary capabilities, like contextual understanding, few-shot/zero-shot learning, code generation…Birth, Death and Diff: Insertion-Based Sequence Generation with Corrections
Insertion-based masked diffusion models enable flexible-length, parallel generation by interleaving mask insertion with token unmasking.SHIFT-JEV: Certified Abstention and Gain-Gated Continual Adaptation for LLM-Based Decision Models under Distribution Shift
Large language models (LLMs) can act as decision models that return a probability distribution over a fixed set of options, but deployed decision models face domain, label-prior, emerging-class and…A Computationally Efficient Non-Interpolation Virtual Trellis Approach for Mammogram Gradient-based Patterns Analysis
Feature analysis is a crucial step in medical image analysis, particularly in breast cancer classification.SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents
Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows.Whether or Where? Tail Calibration Signals Finite-Budget Reward Hacking in Best-of-N Selection
Best-of-N (BoN) inference returns the candidate with the highest proxy reward, so a larger $N$ tests the proxy's extreme tail more than its average ranking quality.AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents
Mobile-use multimodal agents are typically evaluated by task success from a clean initial state, which does not isolate their ability to recover from intermediate errors.Outcome-Aware Agents: When Does Causal Structure Help a Forward Model Foresee the Consequences of Actions?
Agents that act on real systems should predict what their actions will cause before acting.ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?
Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor.From Human Intent to In-Orbit Action: A Self-Learning Large Language Model Agent for 6G Satellite Networks
Autonomous control of sixth-generation (6G) low Earth orbit satellite networks is hindered by the gap between high-level human intent and low-level control logic: translating a request such as…