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 34
Hindsight Credit Assignment over Trees for Agentic RL
Reinforcement learning for long-horizon LLM agents faces a fundamental dilemma: successful experiences are essential for policy improvement, yet limited policy capabilities make such experiences…MURFormer: Attention-Based Lightweight Multi-Scale Uncertainty-Guided Refinement Framework for PPG Denoising
Photoplethysmography (PPG) is a widely used physiological signal for its convenience but is highly susceptible to motion artifacts that degrade waveform quality and limit downstream analysis.The Staged Pandora's Box: Reservation Indices for Multi-Fidelity Bayesian Optimization
A staged search must decide which candidate to advance next and when to stop.Feature extraction for LSTM-based finger-joint angle estimation from sEMG
Continuous estimation of finger-joint angles from surface electromyography (sEMG) is a promising approach for controlling dexterous myoelectric prostheses.MoviEdit: Long-form Multi-Shot Video Editing Made Easy
Long-form multi-shot video editing requires an intended edit to remain coherent across abrupt changes in scene, viewpoint, and subject appearance, while processing substantially longer visual…Beyond Monotonicity: Stochastic Online Optimization under Semi-Bandit Feedback
We study stochastic online optimization (SOO) under semi-bandit feedback: in each of $T$ rounds, a policy adaptively observes $n$ independent random variables with unknown distributions, learning…Subspace Representations for Synthetic-to-Real Transfer in 3-D Surface Inspection
This paper studies what subspace representations contribute to synthetic-to-real transfer in 3-D surface inspection, where models learn from synthetic defects and the only real data before…Replay for LLM Continual Learning with Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) distills several domain experts into one student and is used in the post-training of recent large language models.What Drives the Zero-to-One Jump? Diagnosing and Steering Hard-Prompt Learning in RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved mathematical reasoning, yet progress on hard prompts often stalls: a prompt can remain unsolved for many training…Investigating the effects of the patch size in Time Series Foundation Models
Patch size is a central design choice in patch-based time-series foundation models, controlling temporal resolution, sequence length, and computational cost.DIKT: A Diagnostic and Interpretable Knowledge Tracing Framework for Prediction and Model-based Learning Analysis
Knowledge tracing is a key component of intelligent educational systems.LipLingo: CNN Model for Lip Reading
Lip reading plays a crucial role in applications such as speech recognition, assistive technologies for the hearing-impaired, and biometric authentication.Spectral Degeneration of Self-Attention under Isotropic Score Geometry
We study the spectral structure of the self-attention matrix in Transformer models through an idealized spectral model for the pre-softmax score matrix.Stop Handcrafting Your Engine! GenDB-V: Towards AI-Generated and Formally Verified Database Systems
For over 50 years, the database community has developed a wide range of successful engines to answer two fundamental questions: how can database systems run faster, and how can we ensure their…HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness
LLM agents are rapidly shifting software development toward intent-driven \emph{vibe coding}, yet their effectiveness drops sharply in high-level synthesis (HLS), where code optimization must…POD-CNF: reduced order modeling of parametrized stochastic PDEs via normalizing flows and proper orthogonal decomposition
Reduced-order models (ROMs) learned from trusted numerical simulations enable the real-time simulation of complex physical systems, making computationally prohibitive tasks-such as uncertainty…SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping
Robust multimodal perception for soft robotic grasping is challenged by modality-dependent noise, semantic ambiguity, and limited coordinated multisensory data.SelfImprove-Bench: Evaluating Generalization in Self-Improving Agents
Recursively self-improving (RSI) systems are increasingly viewed as a promising means of accelerating progress toward artificial general intelligence.SynForecast: Controlled Synthetic Time Series for Forecasting Research
Synthetic time series constitute a substantial share of the training corpora of several recent forecasting foundation models.CARE: Contrastive Representation Learning with Environment-Invariance Regularization for Behavioural Intention Prediction
Trajectory-based behavioural intention prediction faces environmental variation, and representations learned with a pooled contrastive objective may retain environment-specific regularities.