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 62
A Constructive Orbit-Based Theory of Learnability
We develop a finite-dimensional orbit framework for constructing data-adapted dictionaries, sparse realizations, and predictive extensions.On the Generation Order in GFlowNets
Sampling from discrete distributions specified by unnormalised probability functions is a classical statistical problem.Enhancing Medical Lesion Segmentation via Several Simple Modules
This work introduces three lightweight enhancement modules for medical lesion segmentation to improve clinical applicability, particularly under data-scarce and computationally constrained…$\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation
Robot policy learning is dominated by zeroth-order methods such as PPO, which treat the simulator as a black box and pay for it with enormous sample counts.When the Past Shapes Action: Understanding Embodied Memory
Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution.Does Reasoning Make Language Models Agree?
Language models face two opposing concerns: monoculture, in which models err in correlated ways, and multiplicity, in which equally accurate models make conflicting decisions.From WSIs to Bulk, Spatial and Single-Cell Transcriptomics via Multi-Scale Graph Neural Networks
Understanding the spatial distribution of gene expression is key to studying complex diseases like cancer.From fleet trajectories to single-cell promises: hierarchically weighted conformal prediction for battery SOH monitoring
Interval predictions from conformal prediction are usually read as "90% coverage", but on nested battery data that number promises the fleet average, not the individual cell.TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents
Terminal feedback in multi-turn agent training leaves both rollout allocation and local credit underdetermined.Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width
Residual connections underpin Transformers, but they implicitly tie the residual width carried through depth to the compute width used inside each layer.UpLoop: Training Looped Transformers via Upcycling at No Extra Pretraining Compute
Looped language models can strengthen reasoning through repeated computation with shared weights, increasing execution depth without adding independent parameters.Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models
In quantum computing, the readout always carries finite-shot sampling noise.From Training Exposure to Membership Evidence: A Controlled Study of OLMo 2
Yet most membership-inference (MI) evaluations on language models collect members and non-members after the fact, so success may reflect distribution shift and failure is inconclusive.Leakage-Controlled Structure-Preserving Augmentation and Template-Aware Evaluation for Bangla Symptom-Based Disease Prediction
Bangla symptom-based disease prediction is commonly evaluated on a small, imbalanced structured benchmark containing many profiles that differ by only one or two symptoms.Locality-Controlled Out-of-Distribution Guidance for Robust Regulatory DNA Sequence Design
Designing regulatory DNA sequences for targeted gene-expression control is an important challenge.Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components
Task Vectors (TVs) provide a compact way to steer large language models, but they are typically treated as atomized directions merely extracted from hidden states, leaving their internal functional…Do LLMs Know When They Are Wrong About Molecules? In-Context Property Prediction with Self-Reported Uncertainty
Large language models (LLMs) are used in many domains, but molecular property prediction with them is still little explored.Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
Bridging independent vision-language models (VLMs) and small language models (SLMs) in a modular multi-agent system typically forces them to exchange information as discrete text, which creates a…Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings
Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based…Implicit Assumptions About Tasks in Continual Learning
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once.