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 228
MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
Time-series analysis is increasingly studied in multimodal settings, yet most benchmarks pair temporal signals with text or with visualizations derived from the same signal.TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
Long-term time series forecasting requires temporal dependency modeling that remains stable and generalizable under temporal distribution shifts.RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions
Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains.Searching for What Matters: Open-Ended Discovery of Multiple Hypotheses with Agentic Data Exploration
Discovering what drives an outcome from data is central to science and often requires deciding what is worth investigating before a specific hypothesis is known.Deep Mesoscopic Dynamics
Microscopic simulations resolve spatial patterns but are feasible only over small domains and short timescales, whereas bulk descriptions erase those patterns through spatial averaging.Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions…Interaction-as-a-Judge
Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games.Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features
Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational.PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning.FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention
Long-context training of large language and multimodal models couples structured attention masks (document, prefix-LM, share-question, sliding-window, block-sparse) with multi-node context…Stable-Plastic Subspace Construction for Differentially Private Continual LoRA
Continual learning (CL) adapts pretrained models to a sequence of tasks while retaining knowledge acquired from earlier tasks.NBCLT: Parameter-Agnostic Norm-Ball Clipped Local Training
Distributed learning with multiple local steps reduces communication but aggravates drift, and its practical performance often depends on carefully tuned hyperparameters under heterogeneous data and…Stein Variational Distributional Reinforcement Learning: Score-Guided Particles for Multivariate Return Distributions
Decisions that weigh several reward signals against each other require the joint distribution of the return vector.Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification
Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction.HaloBlock: Faster and Better Decoding for Diffusion Large Language Models
Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding.Learning Distributions from Samples and Qualities
We study parameter estimation when each sample from a continuous parametric distribution is accompanied by a binary quality label governed by the same unknown parameter.CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms
Predictive service assurance converts forecasts of key performance indicators into alarms, and that conversion decides whether the assurance function is deployable.Better Capturing Interactions Between Products in~Retail: Revisited Negative Sampling for~Basket Choice Modeling
Brick-and-mortar retailers face many different challenges that involve understanding thoroughly its products catalog and customer preferences.BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation
Long-context inference makes the key-value (KV) cache a major memory bottleneck for large language models.Neural Dimensional Analysis: Foundations of Dimensionless and Scale-Consistent Computation
Modern Transformers rely on many scale-control mechanisms, including normalization, residual scaling, attention temperatures, loss weighting, and adaptive updates.