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 68
Compositional Self-Improvement: Promises and Pitfalls
Although self-improvement is becoming increasingly important as tasks become more complex, models struggle to generate reliable supervision for harder, out-of-distribution instances.Stochastic learning flow: moment equations for stochastic gradient descent at finite step size
Analytical theories of learning in deep networks often assume gradient flow, discarding the finite step size and batch noise of stochastic gradient descent (SGD).PhysicsNeMo-Mesh: GPU-Native Meshes and Simulation Cases for Physics AI
PhysicsNeMo-Mesh is the mesh module of the open-source PhysicsNeMo library.Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection
Collecting naturalistic human manipulation demonstrations with accurate contact force and hand pose is essential for robot dexterous manipulation policy and foundational world model learning - yet…PALATE: Pretrained Autoregressive LATent Embeddings
Local-commerce and food-delivery marketplaces run large ads businesses: across hundreds of thousands of stores, merchants pay to be surfaced on browse and search surfaces, and a ranker decides which…Generating Critic-Guided Synthetic Experience in Latent World Models
Learning from offline datasets is limited in scalability, as collecting new experience is often costly or unsafe in the real world.From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links.Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection
Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs.Clean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones.DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
Customizing Pretrained Models (PMs) for downstream tasks demands task-specific data, which burgeoning Web3 applications provide abundantly.Learning Erasing Equal-Length Relational Pattern Languages in the Limit from Positive Data over Binary Alphabets
Relational pattern languages generalize Angluin's pattern languages by requiring the strings substituted for repeated occurrences of a variable to stand in a given relation, rather than to be…A Novel Approach to Evaluating Evaluation Metrics for Multi-Output Structured Prediction
In multi-output structured prediction tasks, while only one ground truth label may be provided in the training data, multiple equally valid outputs may be possible, making reliable evaluation a…ACAM-J-MARS: Multi-Atlas Riemannian Spectral Representations for Decoding Advanced Meditation States from fMRI
Inferring jhana-type advanced concentration absorption meditation (ACAM-J) states from fMRI data is challenging due to the spatially distributed nature of meditation-related effects, substantial…EmbodiExp: Compositional Experience Transfer for Embodied Agents
Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the…Zero-Complement Extrapolation: Parameter Recovery and Classification in Severely Imbalanced Logistic Regression under Rank-Deficient Regimes
Parameter estimation and classification in binary logistic regression deteriorate severely when the number of minority class observations ($n_1$) is smaller than the feature dimension ($p$).Analyzing Condensation on Patterned Surfaces via Deep Learning
Dropwise condensation is key to power and water systems.Pair-Dependent Judge Errors Change the Minimax Rate of Semantic Entropy
Semantic entropy, the entropy of the meanings among a language model's sampled answers, is estimated from the verdicts of a judge that declares pairs of answers equivalent or not, and automatic…Sparse Autoencoders as Implicit Diversification Regularisers for Cross-Sectional Cryptocurrency Returns
Factor models are central to asset pricing and portfolio construction, but neural factors are often difficult to interpret, and their effect on portfolio risk is unclear.Event2Reward: Learning Robotic Rewards from Progress Relations
Learning task progress from robot demonstrations provides a practical way to construct dense shaping rewards for robotic reinforcement learning.Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers
Rotary Position Embedding (RoPE) typically uses uniform coverage across Transformer layers despite heterogeneous positional requirements.