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 226
Dynamic K-Head: Difficulty-Supervised Budget Selection for Continuous Latent Reasoning
Chain-of-thought (CoT) improves reasoning but incurs substantial autoregressive rationale cost.Deficit-Driven Stratified Acquisition for Building STRATA-S12: An Open SAR-Optical Corpus for Self-Supervised Learning
Building a co-registered SAR-optical corpus for self-supervised Earth Observation is above all an acquisition problem, yet the main multi-modal datasets are collected opportunistically, with no…LatentRiskBench: Measuring State-Dependent Risks in Enterprise Agents
Enterprise agents face safety risks that cannot be determined from individual actions alone.Encoding Context into LLM Weights: What Makes It Context?
Longer contexts allow large language models (LLMs) to condition their predictions on more information, but inference costs grow prohibitively with context length.MedEvo: Medical Reasoning Evolution through Knowledge Navigation
Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while general-domain correction…zPocket: Better Pocket Finding with Frozen Co-Folding Features
Identifying protein-ligand binding sites (pockets) is important for understanding protein function and developing drugs.LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck.Understanding Gene Expression-to-Image Learning: Spatial Structure and Information Fidelity
Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene expression profiles…A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry
3D scene graph prediction is commonly supervised with local object and predicate classification losses.Focus on What You Need: Global-to-Local Dynamic Attention for Multimodal Sarcasm Detection
Multimodal sarcasm detection has attracted increasing attention due to the widespread use of images and text on social media platforms.Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning
Imitation learning typically treats every demonstration state as equally important, optimizing a behavior-cloning objective uniformly across the dataset.Confine to the Task, Anchor the Rest: Concept-Guided Retention Regularizer for Parameter-Efficient Fine-Tuning
Parameter-efficient fine-tuning (PEFT) has been widely used, yet the adapted model suffers catastrophic forgetting of pre-trained knowledge.MissPath-FM: Flow Matching with Structured Priors for Partially Observed Time Series
Flow matching has emerged as a powerful alternative to diffusion models for generative modeling, but standard conditional flow matching is fundamentally misaligned with partially observed time…ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence.Representation Geometry and Inductive Biases in Quantum Classifiers across Classical Visual Benchmarks
Quantum Machine Learning (QML) has a theoretical advantage over classical algorithms for specific synthetic data that is computationally hard.Evidence-First Agentic Verification
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace.TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training
Large language model (LLM) agents excel at complex, multi-step tasks but suffer from catastrophic forgetting during continual learning--acquiring new skills often degrades previously mastered…DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation
Low-rank adaptation (LoRA) often underperforms full fine-tuning.CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning
Rubric-based reinforcement learning (RL) evaluates responses against explicit criteria to construct rewards, offering a viable way to train large language models on open-ended tasks.Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning
Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR).