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 141
Reader--Writer Coupling in Transformer MLPs
A transformer MLP gives each hidden channel two roles: a reader that decides when the channel responds, and a writer that decides what it adds back to the residual stream.Decodability Is Not Controllability: Local and Anisotropic Speaker Control in Continuous-Latent TTS
High linear decodability does not entail causal controllability in continuous-latent text-to-speech (TTS).Benchmarking and Error Analysis of Deep Search and Deep Research LLM Agents
As Large Language Models (LLMs) evolve into autonomous Deep Search and Deep Research Agents capable of executing long-horizon, multi-step tasks, evaluating their reliability becomes increasingly…Data Schedules and Learning Rate Schedules Should Be Designed Together
Mid-training (MT) is a training phase in LLM training pipelines that continues pretraining (PT) on smaller datasets of higher value.Closed-Loop Dual-Reference Guidance for Accent Control in Cross-Lingual Voice Cloning
Zero-shot cross-lingual voice cloning often carries the reference speaker's accent into the target language.GaP-MoE : Explicit Expert Specialization in Mixture-of-Experts via Orthogonal Gradient Accumulation and Projection
Sparse Mixture-of-Experts (SMoE) models improve scalability by routing input tokens to only a subset of expert networks, but they often suffer from representation collapse, in which multiple experts…Compositional neural networks for multimodal X-ray and neutron scattering inversion
X-ray and neutron scattering are indispensable for structural characterization across condensed-matter physics and materials science.Right On Q: Recovering Reasoning under Quantization via Self-Generated Trajectories
Quantization-aware training (QAT) aims to recover reasoning capabilities in low-bit large language models (LLMs).Cascading Bandits with Noisy Observations: Algorithms and Regret Bounds
We propose a novel stochastic cascading bandit setup where probing an ordered shortlist of $K$ out of $L$ arms incurs position-dependent costs, and the learner observes only noisy feedback regarding…Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories
Language models relying on verbalized Chain-of-Thought (CoT) are constrained to token-by-token generation in the language space, where many tokens serve textual coherence rather than core reasoning.Nominate-then-Adjudicate: LLM-Assisted One-Pass and Per-Instance MIP Solver Tuning
Mixed-integer programming solvers expose hundreds or even thousands of parameters whose best setting varies per instance, yet per-instance search is prohibitively expensive.Progressive Permutation Alignment with Temperature-Controlled Spectral Sharpening
In implicit neural representations (INRs), 3D signals are encoded directly in network weights, making stable weight-space operations essential.Region-Aware Multi-View Inspection Using Deep Learning and Domain-Informed Decision Fusion
Automated optical inspection of precision components with tiny surface defects remains challenging when different regions of the same component exhibit different defect characteristics and…The Predictive--Optimization Gap in GuanDan Self-Play
Outcome-predictive signals are often treated as promising optimization targets in reinforcement learning, but predictive validity and optimization utility are different claims.Alternative Strategies for Active Learning with Bayesian Bradley Terry Model
Comparative judgement uses pairwise comparisons to rank items, but recovering accurate rankings from a limited number of judgements depends on both the inference method and the pairs selected.When Thoughts Become Memory: Unifying In-Context Learning and Fine-Tuning
We are the first to give a certified rule for whether unseen data belong in a pretrained model's context or its weights, built on an exact law for their information value.Generalization Bounds via Vector-Valued $L_p$ Correlation $V_α$
Understanding generalization of randomized learning algorithms remains a central challenge.BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
While agentic reinforcement learning (RL) has emerged as a promising paradigm for training small language models (SLMs), existing frameworks are predominantly tool-centric and struggle with…One Act, Many Masks: Effect-Marginal Policy Optimization for Long-Horizon Agents
Recent advances in multi-turn reinforcement learning (RL) have substantially improved the performance of LLM agents on complex, long-horizon interactive tasks.How Far Can Foundation Models Be Distilled for Efficient Jet Tagging?
Jet tagging is one of the most important applications of machine learning at the Large Hadron Collider.