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 180
Quadratic Sample Complexity for Strictly Replicable Realizable Learning with Unknown Marginals
Under the quantifier $\exists A\,\forall D$, where the realizable distribution and its marginal are unknown, we determine the finite-class sample-complexity exponent for strict replicability: two…Beyond Policy Discrepancy: Capability-Aware Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation (MOPD) integrates domain specialists into a shared student, but determining how strongly each teacher should supervise remains challenging.Dynamic System Inspired Continuous Large Language Model for AI4Science Tasks
Scientific foundation models increasingly operate on continuous phenomena, yet still use discrete residual computation.FoundPDE: A generative foundation model for data-driven symbolic discovery of partial differential equations
Discovering governing partial differential equations (PDEs) from observed data is a central inverse problem in computational science and engineering: the goal is not only to predict trajectories…When Weak Submodularity Meets Matroids: How Does Standard Greedy Behave?
Weakly submodular maximization finds numerous applications in machine learning, data mining and statistics.SZED at ArGuard Shared Tasks: Multi-Task Label-Attention and Cross-Modal Fusion for Arabic Hateful Meme Detection
We present SZED's submission to ArGuard 2026 Track A: Arabic hateful meme detection.Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes
We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initialization.Power-Law Correlations Without Apparent Temperature-Tuned Criticality in Fixed-Tree Hierarchical Languages
Sampling temperature can substantially reshape autoregressive generation, but it is unclear when temperature changes in long-range correlations reflect a genuine phase transition rather than a…Uniform convergence at optimal rate and scale
Uniform convergence asks how many random samples suffice for empirical averages to approximate expectations simultaneously over an entire class of functions.What Matters for NVFP4 Training? A Comparative Study of Low-Precision Pretraining Recipes
Training large language models directly in 4-bit floating-point (FP) formats promises substantial improvements in throughput and energy efficiency.The Certification Exponent: Instance-Optimal Sequential Certification of Policy Improvement from History Dependent Logs
Before a new policy replaces a deployed one, we often want a certificate, computed from logged episodes, that it is better.Measuring the Task Value of Precision Upgrades in Closed-Loop Agents
A low-precision agent can call its full-precision (BF16) model at selected decisions as a fallback.Exact Risk Certificates for Pairwise-Judged Reranking
Pairwise relevance judgments constrain both the loss numerator and the ideal-ranking denominator of nDCG.Blackbox Performance Analysis of LLM-based Network Control
LLMs are becoming an indispensable part of network control systems due to their impressive reasoning.Can Agents Keep Secrets They Were Never Told? Benchmarking Latent Privacy Risks Across Sessions with MemJoin
To support sustained interactions and personalized assistance, agents use long-term memory to retain and combine user information across sessions.Revisiting Smoothed Online Learning: Competitive Ratio, Dynamic Regret with Switching Cost, and Best of Both Worlds
We revisit smoothed online learning and develop algorithms with improved competitive ratios, optimal dynamic regret with switching cost, and best-of-both-worlds guarantees.Learning from the Right Regions: Class-Conditioned Explanation Guidance for Medical Imaging
Deep neural networks can achieve strong predictive performance in medical imaging while relying on regions unrelated to the predicted finding.A decomposition-integration framework coupling singular spectrum analysis with a volatility-adaptive LSTM for stock price forecasting
Financial time series exhibit multi-scale, high-noise, and non-stationary volatility dynamics.Learning volatility-adaptive forgetting via GARCH-modulated LSTM for stock price forecasting
Stock price forecasting is hindered by the heteroscedastic nature of financial time series, in which turbulent and tranquil regimes alternate.MSCR: Jointly Balancing Utilization Across Modalities and Discovering Synergistic Information
In multimodal learning, modality imbalance often lets one modality dominate optimization and keeps the model from fully exploiting cross-modal interactions.